@article{MTMT:34620692, title = {Prediction of thrust force in indexable drilling of aluminum alloys with machine learning algorithms}, url = {https://m2.mtmt.hu/api/publication/34620692}, author = {Akdulum, Aslan and Kayir, Yunus}, doi = {10.1016/j.measurement.2023.113655}, journal-iso = {MEASUREMENT}, journal = {MEASUREMENT}, volume = {222}, unique-id = {34620692}, issn = {0263-2241}, abstract = {The thrust force has a direct effect on important output responses such as surface roughness, power consumption, and tool wear. The measurement process for thrust forces is very time-consuming and costly. Low success rates are achieved in the estimation of thrust force. The mechanical properties and chemical composition of the workpiece material were not taken into account as input properties in the previously established models. However, these features are of high importance in the formation of the thrust force. In this study, it is aimed at estimating the thrust force with the least input feature with a high success rate by establishing single and hybrid models with different machine learning algorithms. As a result, the thrust force can be successfully predicted by machine learning algorithms by entering two properties. Successful thrust force estimation will provide more accurate process planning, material selection, and optimization.}, keywords = {PREDICTION; machine learning; hybrid modeling; thrust force; Pearson correlation sorting}, year = {2023}, eissn = {1873-412X}, orcid-numbers = {Akdulum, Aslan/0000-0003-2030-3167; Kayir, Yunus/0000-0001-6793-7103} } @article{MTMT:34620694, title = {A novel real time sensing framework for assessment of thrust force in drilling of composites using Taguchi and NSGA-II}, url = {https://m2.mtmt.hu/api/publication/34620694}, author = {David, Amos Gamaleal and Ramalingam, Vimal Samsingh and Sundarsingh, Esther Florence}, doi = {10.1177/09544062231207491}, journal-iso = {P I MECH ENG C-J MEC}, journal = {PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE}, unique-id = {34620694}, issn = {0954-4062}, abstract = {Monitoring thrust during drilling operations is critical to optimizing drilling parameters and ensuring safe and efficient drilling. In this study, we will monitor variations in thrust force during the drilling process using a sensor coated with carbon black. These sensors measure changes in electrical resistance when the sensor is subjected to a mechanical load, such as drilling force. Carbon black at 5 wt% was used, which was embedded in a fiberglass composite. For this study, an orthogonal arrangement of Taguchi's L27 sequence was used, with drill diameter D, feed rate F, and spindle speed S as machining parameters. The thrust force was measured with a force dynamometer and the resistance change was measured simultaneously with the developed new system. Analysis of variance was used to find the optimal parameters, and in this study, a mathematical model was proposed to measure the thrust force directly using the electrical resistance detected. NSGA-II algorithm was used to predict solutions for the given parameters for comparison. A comprehensive way of drilling process and data-driven decisions to improve drilling performance and safety was studied, and a correlation between actual thrust and calculated thrust of 0.91 was found. The proposed system was able to monitor and continuously record thrust force in real time during drilling, with electrical resistance as the most important factor with an error percentage of less than 8% compared to the NSGA-II predictions of less than 5%.}, keywords = {COMPOSITES; sensors; Drilling; NSGA-II; Real time monitoring; thrust force}, year = {2023}, eissn = {2041-2983}, orcid-numbers = {David, Amos Gamaleal/0000-0002-3704-5734} } @article{MTMT:34300806, title = {Improving the quality assessment of drilled holes in aircraft structures}, url = {https://m2.mtmt.hu/api/publication/34300806}, author = {Kawano, Frederico Leoni Franco and Toledo, Claudio Fabiano Motta and Barbosa, Gustavo Franco and Sagawa, Juliana Keiko and Shiki, Sidney Bruce}, doi = {10.1007/s00170-023-11697-3}, journal-iso = {INT J ADV MANUFACT TECHNOL}, journal = {INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY}, volume = {128}, unique-id = {34300806}, issn = {0268-3768}, abstract = {This paper presents a case study conducted in an assembly cell specifically designed for the automated drilling of an aeronautical structure. The study shows how techniques approached by the 4.0 industry have the potential to contribute to manufacturing, breaking the limits imposed by the previous state-of-the art systems. This paper proposes a method that utilizes a committee of neural networks to calculate an indicator for the final quality of drilled holes. The method analyzes data obtained by monitoring the electric current consumed by the drilling system drive. Considering the tests carried out on a real product, the method presents an accuracy of 95% and has the potential to increase the efficiency of the drilling process, reducing the cycle time by up to 25%, since it can avoid measurement steps and physical inspections which increase the cycle time of the drilling process. The proposal contributes to the literature by presenting an unprecedented application and to the praxis by solving a relevant problem of the aerospace industry.}, keywords = {NEURAL NETWORKS; advanced manufacturing; Aircraft Structures; Precision holes}, year = {2023}, eissn = {1433-3015}, pages = {1155-1168}, orcid-numbers = {Shiki, Sidney Bruce/0000-0001-9373-3630} } @article{MTMT:33910108, title = {Micro-cutting of holes by centrifugal force}, url = {https://m2.mtmt.hu/api/publication/33910108}, author = {Kocovic, Vladimir and Vukelic, Djordje and Kostic, Sonja and Bijelic, Ivan and Prica, Miljana and Tadic, Branko}, doi = {10.1007/s00170-022-10581-w}, journal-iso = {INT J ADV MANUFACT TECHNOL}, journal = {INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY}, volume = {124}, unique-id = {33910108}, issn = {0268-3768}, abstract = {The paper presents a novel process of micro-cutting wherein the material removal is achieved by applying a constant penetration force of the cutting tool into the workpiece. Penetration force is achieved by a specially designed moving assembly comprising a tool and toolholder. Micro-cutting with constant cutting force is performed on conventional machine tools, using conventional cutting tools. The design of the tool and toolholder assembly enables the regulation of the penetration force intensity, i.e. the regulation of cutting depth. The regulation is achieved by changing the mass, eccentricity, and angular velocity of the moving assembly. The obtained results indicate that the applied method provides small cutting depths, a reduction of circularity deviation and roughness, and a more favourable distribution of the material in the surface layer.}, keywords = {Centrifugal force; Micro-cutting; Toolholder; Constant cutting force}, year = {2023}, eissn = {1433-3015}, pages = {1437-1455}, orcid-numbers = {Vukelic, Djordje/0000-0003-2420-6778; Prica, Miljana/0000-0002-4614-550X} } @article{MTMT:34300209, title = {Review on prognostics and health management in smart factory: From conventional to deep learning perspectives}, url = {https://m2.mtmt.hu/api/publication/34300209}, author = {Kumar, Prashant and Raouf, Izaz and Kim, Heung Soo}, doi = {10.1016/j.engappai.2023.107126}, journal-iso = {ENG APPL ARTIF INTEL}, journal = {ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE}, volume = {126}, unique-id = {34300209}, issn = {0952-1976}, abstract = {At present, the fourth industrial revolution is pushing factories toward an intelligent, interconnected grid of machinery, communication systems, and computational resources. Smart factories (SF) and smart manufacturing (SM) incorporate a cyber-physical system that employs advanced technologies such as artificial intelligence (AI) for data analysis, automated process driving, and continuous data handling. Smart factories operate by combining machines, humans, and massive amounts of data into a single, digitally interconnected ecosystem. Prognostics and health management (PHM) has become a critical requirement of smart factories to meet pro-duction needs. PHM of components/machines in the smart factory is crucial for securing uninterrupted operation and ensuring safety standards. The growing availability of computational capacity has increased the use of deep learning in PHM strategies. Deep learning supports comprehensive PHM solutions, thus reducing the need for manual feature development. This review presents an extensive study of the PHM strategies employed in the smart factory ranging from the conventional perspective to the deep learning perspective. This includes consideration of the conventional methodologies used for health management along with latest trends in the PHM domain in the smart factory.}, keywords = {VIBRATION; BEARING; big data; smart factory; Prognostics and health management (PHM)}, year = {2023}, eissn = {1873-6769}, orcid-numbers = {Kim, Heung Soo/0000-0001-7057-5174} } @article{MTMT:34453349, title = {Online tool condition monitoring in micromilling using LSTM}, url = {https://m2.mtmt.hu/api/publication/34453349}, author = {Manwar, Ashish and Varghese, Alwin and Bagri, Sumant and Joshi, Suhas S.}, doi = {10.1007/s10845-023-02273-3}, journal-iso = {J INTELL MANUF}, journal = {JOURNAL OF INTELLIGENT MANUFACTURING}, unique-id = {34453349}, issn = {0956-5515}, year = {2023}, eissn = {1572-8145}, orcid-numbers = {Joshi, Suhas S./0000-0001-5194-8334} } @article{MTMT:34248857, title = {A critical review on applications of artificial intelligence in manufacturing}, url = {https://m2.mtmt.hu/api/publication/34248857}, author = {Mypati, Omkar and Mukherjee, Avishek and Mishra, Debasish and Pal, Surjya Kanta and Chakrabarti, Partha Pratim and Pal, Arpan}, doi = {10.1007/s10462-023-10535-y}, journal-iso = {ARTIF INTELL REV}, journal = {ARTIFICIAL INTELLIGENCE REVIEW}, volume = {56}, unique-id = {34248857}, issn = {0269-2821}, abstract = {The fourth industrial revolution, Industry 4.0, has brought internet, artificial intelligence (AI), and machine learning (ML) concepts into manufacturing. There is an immediate need to understand the capabilities of AI and ML and how they can be implemented in manufacturing domains. This article presents a detailed survey of AI algorithms and their use in manufacturing. The article treats casting, forming, machining, welding, additive manufacturing (AM), and supply chain management (SCM) as six manufacturing verticals. The horizontals in each vertical are the descriptions including, the evolution of each process from the mechanization era to the present-day scenario, and developments in the automation of processes by processing signal and image information and applying ML and AI algorithms. The evolution of robotics and cloud-based technologies is also discussed. The critical review gives a realistic view of manufacturing automation and benefits of AI. Further, the article discusses several manufacturing use cases where AI and ML algorithms are deployed. As a future research direction, human-like intelligence is introduced highlighting the necessity of cognitive skills in manufacturing. In a nutshell, a reader can logically explain why, when, and how far AI will define complete manufacturing.}, keywords = {Artificial intelligence; machine learning; manufacturing; Deep learning; 0; Industry 4; Cognitive manufacturing}, year = {2023}, eissn = {1573-7462}, pages = {661-768} } @article{MTMT:34300807, title = {Tool condition monitoring method by anomaly segmentation of time-frequency images using acoustic emission in small hole drilling}, url = {https://m2.mtmt.hu/api/publication/34300807}, author = {Nakano, Taro and Koresawa, Hiroshi and Narahara, Hiroyuki}, doi = {10.1299/jamdsm.2023jamdsm0034}, journal-iso = {J ADV MECH DES SYST}, journal = {JOURNAL OF ADVANCED MECHANICAL DESIGN SYSTEMS AND MANUFACTURING}, volume = {17}, unique-id = {34300807}, issn = {1881-3054}, abstract = {Tool wear leads to a reduction in dimensional accuracy and surface quality, as well as unexpected sudden tool failure. A broken tool can cause irreparable damage to an expensive workpiece, resulting in increased operating costs and production delays. Since the mechanical strength of small-diameter drills is inadequate for the load and prone to breakage, tool condition monitoring and diagnosis is important to prevent sudden tool breakage, increase productivity, and promote automation in machining process. The present work is aimed to investigate a tool condition monitoring method based on the analysis of acoustic emission (AE) signals emitted during small-hole drilling. We propose DDM (Deep feature Distribution Modeling), a method for image-level anomaly detection and anomaly segmentation in time-series signal analysis. The peck drilling experiments on SKD61 steels were performed with high-speed steel (HSS) drills. The continuous wavelet transform (CWT) was applied to generate time-frequency (TF) image of the AE signals during the drilling process. The TF images were quantified as anomaly scores using the DDM, which establishes normality by fitting a multivariate Gaussian (MVG) to pre-trained deep features. The anomaly detection capability of the DDM and the convolutional autoencoder (CAE) was compared using dummy data for validation. The digital microscope was employed to measure tool wear. Chip morphology was also observed by the laser microscopy. As the tool wear progressed, the anomaly score increased or decreased, with several sharp increases observed between holes 3805 and 3869 just prior to tool failure. An increase in the width of the shear layer spacing of the chips was also observed just prior to failure. Changes in the anomaly score associated with tool wear were more clearly identified by creating anomaly maps. The present investigation shows that waveform processing of AE signals using the CWT and anomaly detection based on the DDM are efficient methods for tool condition monitoring. Our proposed approach makes it possible to visualize the differences in anomaly states using a more subdivided layer context by generating multiple anomaly maps with deep feature vectors obtained from multiple layers.}, keywords = {Wavelets; Acoustic emission; Anomaly detection; Drilling; TOOL WEAR; deep feature; Anomaly map}, year = {2023}, eissn = {1881-3054} } @article{MTMT:33581966, title = {Cutting anomaly detection in end-milling by multimodal variational autoencoder}, url = {https://m2.mtmt.hu/api/publication/33581966}, author = {ODA, Kazuya and SUWA, Haruhiko and MURAKAMI, Koji}, doi = {10.1299/transjsme.22-00290}, journal-iso = {TRANSACT JSME}, journal = {NIHON KIKAI GAKKAI RONBUNSHU / TRANSACTIONS OF THE JSME (IN JAPANESE)}, volume = {2023}, unique-id = {33581966}, issn = {2187-9761}, year = {2023}, pages = {1-14} } @{MTMT:33547894, title = {Surface Roughness Analysis for Peck Drilling Process on AZ31}, url = {https://m2.mtmt.hu/api/publication/33547894}, author = {Singh, Aman Preet and Pervaiz, Salman}, booktitle = {Emerging Trends in Mechanical and Industrial Engineering}, doi = {10.1007/978-981-19-6945-4_63}, unique-id = {33547894}, abstract = {One-third of the metal cutting processes performed in the manufacturing industry consists of drilling operations, thus making it a key area of interest. Drilling of metals, especially deep holes can be difficult. This is because, while drilling, the chips formed interact with the tool and the workpiece which causes tool wear, temperature rise, increase in surface roughness, and reduction of hole quality. One novel approach to avoid the mentioned drawbacks is adopting the practice of peck drilling. Peck drilling involves drilling through the workpiece to a certain depth, and then retracting the drill to the workpiece surface. This is repeated until the desired hole diameter and depth is achieved. This method allows for the chips to be evacuated from the bore, thus producing lower cutting temperatures, better surface finish, and prolongation of tool life. In this paper, peck drilling is performed on AZ31 workpiece material which is a novel material used mostly in the aerospace industry. The tests are undertaken using high-speed milling machines to assess the processes’ performance with respect to surface roughness at certain drilling cycle, cutting speed, and feed rate. Since, peck drilling takes place in certain drilling cycles, it is important to note that at each step, the surface of the hole of the previous step is being redrilled. This would ideally result in the surface roughness of the first hole to be least and last hole to be maximum. This paper also aims to look at this phenomenon in depth.}, year = {2023}, pages = {843-860} } @article{MTMT:34129087, title = {Anomalous Change Detection in Drilling Process Using Variational Autoencoder with Temperature Near Drill Edge}, url = {https://m2.mtmt.hu/api/publication/34129087}, author = {Suwa, Haruhiko and Oda, Kazuya and Murakami, Koji}, doi = {10.20965/ijat.2023.p0449}, journal-iso = {INT J AUTOM TECH}, journal = {INTERNATIONAL JOURNAL OF AUTOMATION TECHNOLOGY}, volume = {17}, unique-id = {34129087}, issn = {1881-7629}, year = {2023}, eissn = {1883-8022}, pages = {449-457} } @article{MTMT:33910106, title = {Drilling force prediction and drill wear monitoring for PCB drilling process based on spindle current signal}, url = {https://m2.mtmt.hu/api/publication/33910106}, author = {Tan, Qifeng and Tong, Hao and Li, Yong}, doi = {10.1007/s00170-023-11302-7}, journal-iso = {INT J ADV MANUFACT TECHNOL}, journal = {INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY}, unique-id = {33910106}, issn = {0268-3768}, abstract = {In the drilling process of multilayer printed circuit boards (PCB), drill wear will reduce the stability of the drilling process and affect the processing efficiency and drilling quality, so the prediction of drilling force and the monitoring of drill wear status during the drilling process are particularly important. A spindle current-based drilling force prediction and drill wear monitoring technique with theoretical models of drilling force, drill wear, and current signal is investigated to realize a feasible and low-cost online monitoring system for PCB drilling process. The prediction and monitoring technique consists of a semi-empirical theoretical model of the drilling force and torque considering drilling parameters and drill wear as well as a theoretical model between drilling torque and spindle current. The coefficients in the theoretical models were determined by measuring drilling force and spindle current signals through the drilling experiments with variable parameters and drill wear. The experimental results show that the relative errors between the predicted and experimental results of spindle current increment with variable drilling parameters and wear amounts are basically less than 10% and the prediction accuracy of the drilling force model is good when the drill flank is worn in the early and middle stages, which shows that the proposed spindle current-based drilling force prediction and drill wear monitoring technique has high prediction accuracy as well as strong effectiveness.}, keywords = {Multilayer PCB drilling; Spindle current signal; Theoretical model establishment; Drilling force prediction; Drill wear monitoring}, year = {2023}, eissn = {1433-3015} } @article{MTMT:34300805, title = {Mechanical model of back-drilling high-speed printed circuit boards with eccentricity effects}, url = {https://m2.mtmt.hu/api/publication/34300805}, author = {Zhu, Tao and Shi, Hongyan and Chen, Zhuangpei and Liu, Xianwen and Wang, Zhaoguo and Zhou, Qian}, doi = {10.1016/j.ijmecsci.2023.108638}, journal-iso = {INT J MECH SCI}, journal = {INTERNATIONAL JOURNAL OF MECHANICAL SCIENCES}, volume = {259}, unique-id = {34300805}, issn = {0020-7403}, abstract = {The rapid development of fifth-generation (5 G) communication technology is placing greater demands on the performance of high-speed printed circuit boards (PCBs). Back-drilling plays a crucial role in achieving high -frequency and high-speed signal transmission and is a key technology for improving the signal integrity of high-speed PCBs. The thrust force is considered the main factor affecting hole quality when drilling PCBs. Accurately predicting the thrust force is essential for optimizing the back-drilling process. However, back-drilling thrust force is strongly coupled with eccentricity, presenting a significant challenge in predicting its accuracy. In this paper, an ideal state mechanical model (without eccentricity effects) and an actual state mechanical model (with eccentricity effects) are proposed for the first time to predict the thrust force when back-drilling high-speed printed circuit boards. First, a length model for the effective cutting edge in back-drilling is established for the first time based on back-drilling characteristics. The contact conditions and back-drilling mechanism between the materials (glass fiber-reinforced plastic, resin and copper) and the microdrill (tungsten carbide) are further analyzed in terms of the effective cutting edge and contact mechanics. Then, by considering the eccentricity effects, mechanical models under ideal and actual states are proposed for predicting the thrust forces when back -drilling high-speed PCBs. In addition, by setting different feed rates and spindle speeds and using 4 types of microdrills with different structural parameters, a back-drilling experiment is performed on high-speed PCBs to determine eccentric distances, actual thrust forces, and stub lengths. Compared with the actual thrust force, the maximum error of the ideal model is 8.03%, while the actual model has a better applicability with a maximum error of 5.51% and a minimum error of 1.33%. The experimental results indicate that the thrust force first de-creases and then increases as the eccentric distance increases when the chisel edge is involved in the cut during back-drilling. Moreover, the stub length increases with increasing eccentricity and decreasing point angle, while the back-drilling diameter has a negligible effect.}, keywords = {ECCENTRICITY; Mechanical model; thrust force; Back-drilling; High-speed printed circuit boards; Via stub}, year = {2023}, eissn = {1879-2162}, orcid-numbers = {Zhu, Tao/0000-0003-3373-1099; Shi, Hongyan/0000-0001-8318-3305; Chen, Zhuangpei/0000-0001-6346-3473; Liu, Xianwen/0000-0002-6849-4049} } @article{MTMT:33910105, title = {Wear identification of end mills based on a feature-weighted convolutional neural network under unbalanced samples}, url = {https://m2.mtmt.hu/api/publication/33910105}, author = {Zou, Yisheng and Ding, Kun and Shi, Keming and Lai, Xuwei and Zhang, Kai and Ding, Guofu and Qin, Guohao}, doi = {10.1016/j.jmapro.2023.01.054}, journal-iso = {J MANUFACT PROCES}, journal = {JOURNAL OF MANUFACTURING PROCESSES}, volume = {89}, unique-id = {33910105}, issn = {1526-6125}, abstract = {The number of samples with various wear states gathered in processing is unbalanced because the wear rate of end mills fluctuates nonlinearly. There are still some limitations to the current approaches for identifying the end mill wear condition in this situation. It is primarily manifested in the dominance of the majority class samples in forming the classification decision boundary. The minority class samples and the samples with a more significant influence on the decision boundary in the majority class samples are closer and difficult to separate, making it challenging to identify the wear state of minority classes. Herein, a deep feature-weighted convolutional neural network (DFWCNN)-based end mill wear state identification approach is proposed to overcome the above limitations. First, the balance influence factor selectively reduces the weight of the samples that significantly influence the decision boundary to lessen the majority classes' dominance on the classification decision boundary. Then, the variance influence factor reduces the intraclass distance to lessen confusion between the samples at the classification decision boundary. The experiments conducted herein have proved that the proposed approach improves the identification accuracy of samples with various wear states, particularly accelerated wear state samples, in the case of sample imbalance.}, keywords = {TOOL WEAR; Convolutional neural network; Deep learning; END MILLS; Unbalanced sample}, year = {2023}, eissn = {2212-4616}, pages = {64-76}, orcid-numbers = {Ding, Kun/0000-0002-8677-5186} } @article{MTMT:32764405, title = {Modeling for a small-hole drilling process of engineering plastic PEEK by Taguchi-based neural network method}, url = {https://m2.mtmt.hu/api/publication/32764405}, author = {Chang, Dar-Yuan and Lin, Chien-Hung and Wu, Xing-Yao}, doi = {10.1007/s00170-021-08431-2}, journal-iso = {INT J ADV MANUFACT TECHNOL}, journal = {INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY}, volume = {119}, unique-id = {32764405}, issn = {0268-3768}, abstract = {Engineering plastics have specific properties in strength, hardness, impact resistance, and aging persistence, often used for structural plates and electronic components. However, the holes made by the drilling process always shrink after the cutting heat dispersion due to their high thermal expansion coefficient. Drilling parameters must be discussed thoughtfully especially in the small-hole fabrication to acquire a stable hole quality. This study developed parameter models by the Taguchi-based neural network method to save the experimental resources on the drilling of engineering plastic, polyetheretherketone (PEEK). A three-level full-factorial orthogonal array experiment, L-27, was first conducted for minimizing the thrust force, hole shrinkage in diameter, and roundness error. In terms of the network modeling, four variables were designated to the input layer neurons included the three drilling parameters (spindle speed, depth of peck-drilling, feed rate) and the thrust force detected, and that of the output layer neurons were two hole characteristics of diameter shrinkage and roundness. The models were trained by a stepped-learning procedure to expand the network's field information stage by stage. After three stages of training, the models developed can provide precise simulations for the network's training sets. For the non-trained cases, the prediction accuracy of the hole's characteristics discussed was below 1 mu m in the drilling of a 1-mm-diameter hole.}, keywords = {SURFACE; FEATURES; PREDICTION; QUALITY; Neural network; sensors; POWER; force; ANN; Multiobjective optimization; thrust force; Automation & Control Systems; Taguchi’s method; Stepped-learning procedure}, year = {2022}, eissn = {1433-3015}, pages = {5777-5795} } @article{MTMT:32764407, title = {Using Neural Networks for Tool Wear Prediction in Computer Numerical Control End Milling}, url = {https://m2.mtmt.hu/api/publication/32764407}, author = {Chen, Cheng-Hung and Jeng, Shiou-Yun and Lin, Cheng-Jian}, doi = {10.18494/SAM3642}, journal-iso = {SENSOR MATER}, journal = {SENSORS AND MATERIALS}, volume = {34}, unique-id = {32764407}, issn = {0914-4935}, abstract = {The precision of the machining tool in computer numerical control (CNC) machining is affected by several factors. For example, cutting parameters considerably affect machining accuracy and tool wear. Tool wear results in the manufacture of substandard products. Therefore, predicting tool wear is crucial in CNC machining. In this study, we proposed a backpropagation neural network (BPNN) to predict tool wear. In machine learning, backpropagation is a widely used algorithm for training artificial neural networks. The proposed BPNN considered the variation of tool wear with different cutting parameters, such as the spindle speed, feed, cutting depth, and cutting time. The experimental results revealed that the root mean square error of the BPNN prediction model was less than that of the linear regression prediction model. Furthermore, the proposed model achieved a coefficient of determination (R-2) of 0.9964, which indicated that the BPNN model can accurately predict tool wear.}, keywords = {SURFACE-ROUGHNESS; Linear regression; Instruments & Instrumentation; Machine tool; Tool wear prediction; Backpropagation neural network}, year = {2022}, eissn = {0914-4935}, pages = {803-817} } @article{MTMT:33324330, title = {Research on wear of Ni-Cr alloy milling based on residual network}, url = {https://m2.mtmt.hu/api/publication/33324330}, author = {Cheng, Shengming and Wang, Yajun and Leng, Junyu and Zhang, Xinchen}, doi = {10.1177/16878132221119926}, journal-iso = {ADV MECH ENG}, journal = {ADVANCES IN MECHANICAL ENGINEERING}, volume = {14}, unique-id = {33324330}, issn = {1687-8132}, abstract = {With the development of the manufacturing industry and information technology, the quality requirements of products are getting higher and higher. A cutting tool is one of the important factors affecting product quality, so it is of great significance to study cutting tool wear. In this paper, the influence of Ni-Cr alloy on milling cutter wear was studied. Deep learning is widely used in the neighborhood of signal recognition. In this paper, a convolution neural network with residual structure is proposed to classify the wear state of cutting tools. The input of the model is the collected vibration signal, and the output is the classification of tool wear. A convolution neural network can automatically extract the characteristics of signals and identify different types of wear signals. The experimental results show that the convolution neural network with residual structure can converge faster and have higher accuracy than the traditional convolution neural network and the accuracy of tool wear classification is about 98.5%. The loss rate of the model is only about 0.25%.}, keywords = {residual structure; Convolution neural network; Tool wear monitoring}, year = {2022}, eissn = {1687-8140} } @article{MTMT:33910109, title = {Prediction of Machining Condition Using Time Series Imaging and Deep Learning in Slot Milling of Titanium Alloy}, url = {https://m2.mtmt.hu/api/publication/33910109}, author = {Hojati, Faramarz and Azarhoushang, Bahman and Daneshi, Amir and Khiabani, Rostam Hajyaghaee}, doi = {10.3390/jmmp6060145}, journal-iso = {J MANUF MATER PROC}, journal = {JOURNAL OF MANUFACTURING AND MATERIALS PROCESSING}, volume = {6}, unique-id = {33910109}, abstract = {Low surface quality, undesired geometrical and dimensional tolerances, and product damage due to tool wear and tool breakage lead to a dramatic increase in production cost. In this regard, monitoring tool conditions and the machining process are crucial to prevent unwanted events during the process and guarantee cost-effective and high-quality production. This study aims to predict critical machining conditions concerning surface roughness and tool breakage in slot milling of titanium alloy. Using the Siemens SINUMERIK Edge Box integrated into a CNC machine tool, signals were recorded from main spindle and different axes. Instead of extraction of features from signals, the Gramian angular field (GAF) was used to encode the whole signal into an image with no loss of information. Afterwards, the images obtained from different machining conditions were used for training a convolutional neural network (CNN) as a suitable and frequently applied deep learning method for images. The combination of GAF and trained CNN model indicates good performance in predicting critical machining conditions, particularly in the case of an imbalanced dataset. The trained classification CNN model resulted in recall, precision, and accuracy with 75%, 88%, and 94% values, respectively, for the prediction of workpiece surface quality and tool breakage.}, keywords = {Convolutional neural network; Deep learning; Slot milling; imbalanced dataset; Gramian angular field; predictive quality analytics; Edge Box}, year = {2022}, eissn = {2504-4494} } @article{MTMT:32743431, title = {Experimental study of vibration signal for a prognostic system to prevent tool breakage in micro gun drilling}, url = {https://m2.mtmt.hu/api/publication/32743431}, author = {Hsu, Li-Yu and Lu, Ming-Chyuan}, doi = {10.1007/s00170-021-08339-x}, journal-iso = {INT J ADV MANUFACT TECHNOL}, journal = {INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY}, volume = {119}, unique-id = {32743431}, issn = {0268-3768}, year = {2022}, eissn = {1433-3015}, pages = {3469-3481} } @article{MTMT:33036171, title = {Rotating machinery fault diagnosis using a quadratic neural unit}, url = {https://m2.mtmt.hu/api/publication/33036171}, author = {Jorge, Ricardo Rodríguez and Pérez, Laura Sánchez and Bila, Jiri and Ji�, N.A. and Škvor, í}, doi = {10.1504/IJGUC.2022.124403}, journal-iso = {IJGUC}, journal = {INTERNATIONAL JOURNAL OF GRID AND UTILITY COMPUTING}, volume = {13}, unique-id = {33036171}, issn = {1741-847X}, year = {2022}, eissn = {1741-8488}, pages = {309} } @inbook{MTMT:32558438, title = {Identification of Optimal Process Parameters in Electro-Discharge Machining Using ANN and PSO}, url = {https://m2.mtmt.hu/api/publication/32558438}, author = {Kumar, Kaushik and Davim, J. Paulo}, booktitle = {Research Anthology on Artificial Neural Network Applications}, doi = {10.4018/978-1-6684-2408-7.ch038}, unique-id = {32558438}, year = {2022}, pages = {824-842} } @article{MTMT:32764406, title = {Robust tool wear monitoring system development by sensors and feature fusion}, url = {https://m2.mtmt.hu/api/publication/32764406}, author = {Lin, Yu-Ru and Lee, Ching-Hung and Lu, Ming-Chyuan}, doi = {10.1002/asjc.2741}, journal-iso = {ASIAN J CONTROL}, journal = {ASIAN JOURNAL OF CONTROL}, unique-id = {32764406}, issn = {1561-8625}, abstract = {This study introduces a tool wear monitoring system that uses multiple sensors and a feature fusion technique. To improve the robustness of the system, different tightening torque and spindle speed conditions were considered in the experimental design stage. Vibration signals in three coordinates and sound signals were collected and transformed by fast Fourier transform for feature extraction. Two types of features in the frequency domain were used to establish the proposed system, including the mean value features selected by the class mean scatter feature selection criterion and statistical features by Gradient Class Activation Mapping++ (Grad-CAM++). The proposed monitoring system was established using a hierarchical neural network structure and feature fusion of the sensors. Cross-validation was introduced to demonstrate the performance and effectiveness of our approach under various tightening torque values and spindle speeds.}, keywords = {ALGORITHM; Neural network; sensors; force; NEURAL-NETWORK; Hidden Markov model; life prediction; Fast Fourier transform; vibration signals; feature fusion; VECTOR MACHINE}, year = {2022}, eissn = {1934-6093}, orcid-numbers = {Lee, Ching-Hung/0000-0003-3081-362X} } @article{MTMT:33910107, title = {Experimental Investigation of Thrust Force in the Drilling of Titanium Alloy Using Different Machining Techniques}, url = {https://m2.mtmt.hu/api/publication/33910107}, author = {Ma, Lijie and Ma, Zunyan and Yu, Hui and Li, Shenwang and Pang, Minghua and Wang, Zhankui}, doi = {10.3390/met12111905}, journal-iso = {METALS-BASEL}, journal = {METALS}, volume = {12}, unique-id = {33910107}, abstract = {Titanium alloy is a kind of hard-to-cut material widely used in aerospace, military and medical fields, and mechanical drilling is the primary technique used for hole-making in titanium alloy materials. The drilling force is an inevitable concomitant phenomenon in the drilling process and thrust force is its most important component. During the drilling of titanium alloy, it is crucial to understand the fundamental characteristics and changing rules of thrust force for optimizing process parameters, improving machining quality and predicting tool failure. In this paper, four different techniques, such as direct drilling (DD), ultrasonic vibration drilling (UVD), peck drilling (PD) and ultrasonic vibration peck drilling (UVPD), were used to drill small holes into Ti-6Al-4V titanium alloy, the thrust force was measured and its mean, maximum and peak-to-valley value were acquired from the time-domain waveform. Then the time-domain and frequency-domain characteristics of thrust force under the four techniques were compared, and the changing rules of thrust force with vibration amplitudes during UVD and UVPD were investigated. The results showed that, when compared to DD, UVD decreased the mean thrust force F-amean by about 18.6%, and the force reduction effect was more significant as the amplitude increased. The variable velocity cutting characteristics and the antifriction effect of UVD were the primary reasons for the reduction of F-amean. The pecking motion and ultrasonic vibration had a synergistic effect on reducing thrust force; UVPD could simultaneously reduce the mean thrust force F-amean and maximum thrust force F-amax. When the amplitude A was chosen within the range of 2-3 mu m, F-amax and F-amean were reduced by approximately 37% and 40% in comparison to DD.}, keywords = {thrust force; peck drilling; Titanium alloy; Direct drilling; ultrasonic vibration drilling; ultrasonic vibration peck drilling}, year = {2022}, eissn = {2075-4701} } @article{MTMT:32764403, title = {Tool-Condition Diagnosis Model with Shock-Sharpening Algorithm for Drilling Process}, url = {https://m2.mtmt.hu/api/publication/32764403}, author = {Park, Byeonghui and Lee, Yoonjae and Yeo, Myeonghwan and Lee, Haemi and Joo, Changbeom and Lee, Changwoo}, doi = {10.3390/s22051975}, journal-iso = {SENSORS-BASEL}, journal = {SENSORS}, volume = {22}, unique-id = {32764403}, abstract = {Fault diagnosis systems are used to improve the productivity and reduce the costs of the manufacturing process. However, the feature variables in existing systems are extracted based on the classification performance of the final model, thereby limiting their applications to models with different conditions. This paper proposes an algorithm to improve the characteristics of feature variables by considering the cutting conditions. Regardless of the frequency band, the noise of the measurement data was reduced through an oversampling method, setting a window length through a cutter sampling frequency, and improving its sensitivity to shock signal. An experiment was subsequently performed to confirm the performance of the model. Using normal and wear tools on AI7075 and SM45C, the diagnosis accuracies were 97.1% and 95.6%, respectively, with a reduction of 85% and 83%, respectively, in the time required to develop a diagnosis model. Therefore, the proposed algorithm reduced the model computation time and developed a model with high accuracy by enhancing the characteristics of the feature variable. The results of this study can contribute significantly to the establishment of a high-precision monitoring system for various processing processes.}, keywords = {manufacturing; WEAR; VIBRATION; Chemistry, Analytical; support vector machine; TOOL CONDITION; Engineering, Electrical & Electronic; fault diagnosis system; sharpening algorithm; feature variable; overestimation method}, year = {2022}, eissn = {1424-8220} } @article{MTMT:33092323, title = {Experimental and predictive modelling in dry micro-drilling of titanium alloy using Ti–Al–N coated carbide tools}, url = {https://m2.mtmt.hu/api/publication/33092323}, author = {Prashanth, P. and Hiremath, Somashekhar S.}, doi = {10.1007/s12008-022-01032-7}, journal-iso = {IJIDEM}, journal = {INTERNATIONAL JOURNAL ON INTERACTIVE DESIGN AND MANUFACTURING}, volume = {16}, unique-id = {33092323}, issn = {1955-2513}, year = {2022}, eissn = {1955-2505}, pages = {1-25} } @article{MTMT:32764404, title = {Evaluation of transducer signature selections on machine learning performance in cutting tool wear prognosis}, url = {https://m2.mtmt.hu/api/publication/32764404}, author = {Sun, I-Chun and Cheng, Ren-Chi and Chen, Kuo-Shen}, doi = {10.1007/s00170-021-08526-w}, journal-iso = {INT J ADV MANUFACT TECHNOL}, journal = {INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY}, volume = {119}, unique-id = {32764404}, issn = {0268-3768}, abstract = {Machine learning has been widely used in diagnosing system faults as an integration part in modern intelligent manufacturing. However, sensor selection and index for machine tools are versatile and not standardized at this moment for manufacturing equipment. Without supporting of appropriate domain knowledge for selecting appropriate sensors and adequate performance index, pure data-driven approach might suffer from unsatisfied prediction accuracy and needing of excessive training data, as well as the possibility of misjudgment. As a result, a thoughtful flow for identifying key sensor index and to evaluate its impact on the performance of subsequent machine learning scheme would be essential. In this work, the status monitoring and prediction of a milling cutter wear problem is investigated as an example to address the above concerns and to demonstrate the possible solutions by hiring a 5-axis machine center equipped with milling cutters of different wear levels. In parallel, the well-used multilayer perception (MLP) artificial neural network (ANN) models are also used to elucidate the importance of the problem. Transducers including accelerometers, microphones, current transformer, and acoustic emission sensors are mounted on the spindle, fixture, and nearby structures to monitor the milling process. The collected data are processed to extract various signatures. A procedure is developed to evaluate the sensitivity of each index and the key dominated indexes are eventually identified. To elucidate the importance of proper sensor index selection, three MLP ANN models are established based on different sensor features to examine the influence of selected sensors indexes on the prediction accuracy. The results show that with appropriate sensors signatures, even with less amount of experimental data, the model can indeed achieve a better prediction (98.7%) in comparison with that without proper sensor index selection (90.3). This implies that a rigorous process for identifying key feature is essential for system diagnosis in future intelligent manufacturing.}, keywords = {ENTROPY; Artificial intelligence; Feature extraction; diagnosis; NEURAL-NETWORKS; SIGNALS; ONLINE; FAULT-DETECTION; Automation & Control Systems; domain knowledge; Spectral kurtosis; Sensor index evaluation}, year = {2022}, eissn = {1433-3015}, pages = {6451-6468} } @article{MTMT:33029111, title = {On-line monitoring method for tool wear based on image coding technology and convolutional neural network}, url = {https://m2.mtmt.hu/api/publication/33029111}, author = {Teng, R. and Huang, H. and Yang, K. and Chen, Q. and Xiong, Q. and Xie, Q.}, doi = {10.13196/j.cims.2022.04.008}, journal-iso = {JISUANJI JICHENG ZHIZAO XITONG/COMPUTER INTEGRATED MANUFACTURING SYSTEMS, CIMS}, journal = {JISUANJI JICHENG ZHIZAO XITONG / COMPUTER INTEGRATED MANUFACTURING SYSTEMS, CIMS}, volume = {28}, unique-id = {33029111}, issn = {1006-5911}, year = {2022}, pages = {1042-1051} } @article{MTMT:33324329, title = {Process monitoring of machining}, url = {https://m2.mtmt.hu/api/publication/33324329}, author = {Teti, R. and Mourtzis, D. and D'Addona, D. M. and Caggiano, A.}, doi = {10.1016/j.cirp.2022.05.009}, journal-iso = {CIRP ANN-MANUF TECHN}, journal = {CIRP ANNALS-MANUFACTURING TECHNOLOGY}, volume = {71}, unique-id = {33324329}, issn = {0007-8506}, abstract = {This keynote paper mainly focuses on advancements of machining technology and systems for enhanced performance, increased system integration and augmented machine intelligence, critically hinging on new sensors, sensor systems and sensing methodologies being robust, reconfigurable and intelligent, while providing direct adoption and plug-and-play use in industrial practice. One chief novelty is given by the key enabling technologies of Industry 4.0 where integration of sensing systems in manufacturing plants is a cornerstone for transforming conventional manufacturing concepts into digital manufacturing paradigms. Application examples to industrial processes, future challenges and coming trends in machining monitoring are shown. (c) 2022 CIRP. Published by Elsevier Ltd. All rights reserved.}, keywords = {Machining; Advanced signal processing; Sensor monitoring}, year = {2022}, eissn = {1726-0604}, pages = {529-552} } @inproceedings{MTMT:33324328, title = {A Review: Sensors Used in Tool Wear Monitoring and Prediction}, url = {https://m2.mtmt.hu/api/publication/33324328}, author = {Unal, Perin and Deveci, Bilgin Umut and Ozbayoglu, Ahmet Murat}, booktitle = {MOBILE WEB AND INTELLIGENT INFORMATION SYSTEMS, MOBIWIS 2022}, doi = {10.1007/978-3-031-14391-5_15}, unique-id = {33324328}, abstract = {Tool wear prediction/monitoring of CNCs is crucial for improving manufacturing efficiency, guaranteeing product quality, and minimizing tool costs. As a computer-aided application, it has a significant role in the future and development of Industry 4.0. Sensors are the key piece of hardware used by data-driven enterprises to predict/monitor tool wear. The purpose of this study is to inform about the predominant types of sensors used for tool wear monitoring/prediction. This study serves as a resource for researchers and manufacturers by providing the recent trends in sensors for tool wear monitoring. Thus, it may help reduce the time spent on sensor selection.}, keywords = {sensors; Accelerometer; Acoustic emission; INDUSTRY 4.0; dynamometer; Microphone; Current sensor}, year = {2022}, pages = {193-205} } @article{MTMT:33036156, title = {Construction and implementation of music recommendation model utilising deep learning artificial neural network and mobile edge computing}, url = {https://m2.mtmt.hu/api/publication/33036156}, author = {Xia, Juan}, doi = {10.1504/IJGUC.2022.124405}, journal-iso = {IJGUC}, journal = {INTERNATIONAL JOURNAL OF GRID AND UTILITY COMPUTING}, volume = {13}, unique-id = {33036156}, issn = {1741-847X}, year = {2022}, eissn = {1741-8488}, pages = {183} } @{MTMT:32508631, title = {Machine Vision Based Smart Machining System Monitoring}, url = {https://m2.mtmt.hu/api/publication/32508631}, author = {Zhu, Kunpeng}, booktitle = {Smart Machining Systems}, doi = {10.1007/978-3-030-87878-8_8}, unique-id = {32508631}, year = {2022}, pages = {267-295} } @inproceedings{MTMT:31893062, title = {Twist Drilling FEM Simulation for Thrust Force and Torque Prediction}, url = {https://m2.mtmt.hu/api/publication/31893062}, author = {Boldyrev, I. S. and Topolov, D. Y.}, booktitle = {Proceedings of the 6th International Conference on Industrial Engineering (ICIE 2020)}, doi = {10.1007/978-3-030-54817-9_109}, unique-id = {31893062}, year = {2021}, pages = {946-952} } @article{MTMT:33029112, title = {Chip Formation in Drilling}, url = {https://m2.mtmt.hu/api/publication/33029112}, author = {Boldyrev, I.S. and Smetanin, S.D. and Topolov, D.Y.}, doi = {10.3103/S1068798X2111006X}, journal-iso = {Russian Engineering Research}, journal = {Russian Engineering Research}, volume = {41}, unique-id = {33029112}, issn = {1934-8088}, year = {2021}, pages = {1091-1093} } @article{MTMT:32029124, title = {Industry 4.0 Machine Learning to Monitor the Life Span of Cutting Tools in an Automotive Production Line}, url = {https://m2.mtmt.hu/api/publication/32029124}, author = {Carvalho, Cleginaldo Pereira de and Bittencourt, Priscila de Moraes}, doi = {10.22161/ijaers.85.25}, journal-iso = {INT J ADV ENG RES SCI}, journal = {INTERNATIONAL JOURNAL OF ADVANCED ENGINEERING RESEARCH AND SCIENCE}, volume = {8}, unique-id = {32029124}, issn = {2349-6495}, year = {2021}, eissn = {2456-1908}, pages = {220-228} } @article{MTMT:32764410, title = {A Hybrid Finite Element-Machine Learning Backward Training Approach to Analyze the Optimal Machining Conditions}, url = {https://m2.mtmt.hu/api/publication/32764410}, author = {George, Kriz and Kannan, Sathish and Raza, Ali and Pervaiz, Salman}, doi = {10.3390/ma14216717}, journal-iso = {MATERIALS}, journal = {MATERIALS}, volume = {14}, unique-id = {32764410}, abstract = {As machining processes are complex in nature due to the involvement of large plastic strains occurring at higher strain rates, and simultaneous thermal softening of material, it is necessary for manufacturers to have some manner of determining whether the inputs will achieve the desired outputs within the limitations of available resources. However, finite element simulations-the most common means to analyze and understand the machining of high-performance materials under various cutting conditions and environments-require high amounts of processing power and time in order to output reliable and accurate results which can lead to delays in the initiation of manufacture. The objective of this study is to reduce the time required prior to fabrication to determine how available inputs will affect the desired outputs and machining parameters. This study proposes a hybrid predictive methodology where finite element simulation data and machine learning are combined by feeding the time series output data generated by Finite Element Modeling to an Artificial Neural Network in order to acquire reliable predictions of optimal and/or expected machining inputs (depending on the application of the proposed approach) using what we describe as a backwards training model. The trained network was then fed a test dataset from the simulations, and the results acquired show a high degree of accuracy with regards to cutting force and depth of cut, whereas the predicted/expected feed rate was wildly inaccurate. This is believed to be due to either a limited dataset or the much stronger effect that cutting speed and depth of cut have on power, cutting forces, etc., as opposed to the feed rate. It shows great promise for further research to be performed for implementation in manufacturing facilities for the generation of optimal inputs or the real-time monitoring of input conditions to ensure machining conditions do not vary beyond the norm during the machining process.}, keywords = {PERFORMANCE; Machining; Chemistry, Physical; machine learning; force; Materials Science, Multidisciplinary; Physics, Applied; Metallurgy & Metallurgical Engineering; AISI 630}, year = {2021}, eissn = {1996-1944}, orcid-numbers = {Pervaiz, Salman/0000-0002-2425-5441} } @article{MTMT:32351396, title = {Tool breakage monitoring based on sequential hypothesis test in ultrasonic vibration-assisted drilling of CFRP}, url = {https://m2.mtmt.hu/api/publication/32351396}, author = {Huang, Wenjian and Cao, Shiyu and Zhou, Qi and Wu, Chaoqun}, doi = {10.1007/s00170-021-08050-x}, journal-iso = {INT J ADV MANUFACT TECHNOL}, journal = {INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY}, unique-id = {32351396}, issn = {0268-3768}, abstract = {Tool condition is highly relative to the productivity, quality, and safety of ultrasonic vibration-assisted drilling (UVAD) of carbon fiber-reinforced polymer (CFRP). Tool breakage can cause the degradation of drilling quality and maybe even lead to unexpected machine downtime. Therefore, tool breakage monitoring is the key technique of ensuring drilling quality and realizing fully automated drilling. However, existing tool breakage monitoring methods based on machine learning need training model previously, which is impractical for the actual drilling process. In this work, a novel tool breakage monitoring method based on a sequential probability ratio test (SPRT) in UVAD of CFRP is proposed. Three different damage levels are introduced to simulate the tool breakage in the drilling process. The vibration signals collected under different tool damage levels in the experiment are preprocessed by low-pass filtering to remove the disturbance frequency generated by the ultrasonic spindle system. To reduce data redundancy, the signals are downsampled according to the useful frequency band and the feature parameter extracted from test signals is finally fed into the SPRT model as a test sequence to recognize tool damage levels. Root mean square error (RMSE) between the same conditions and between different types of conditions was selected as the criteria to evaluate the reliability of the method. The test results and error analysis show that the method is effective and reliable to classify different tool breakage conditions during UVAD of CFRP.}, keywords = {CFRP; sequential probability ratio test; Tool breakage monitoring; Ultrasonic vibration-assisted drilling}, year = {2021}, eissn = {1433-3015} } @article{MTMT:32351399, title = {Sustainable hole-making in a titanium alloy using throttle and evaporative cryogenic cooling and micro-lubrication}, url = {https://m2.mtmt.hu/api/publication/32351399}, author = {Iqbal, Asif and Zhao, Guolong and Zaini, Juliana and He, Ning and Nauman, Malik M. and Jamil, Muhammad and Suhaimi, Hazwani}, doi = {10.1016/j.jmapro.2021.04.072}, journal-iso = {J MANUFACT PROCES}, journal = {JOURNAL OF MANUFACTURING PROCESSES}, volume = {67}, unique-id = {32351399}, issn = {1526-6125}, abstract = {Titanium, being a structural material, undergoes drilling process frequently for its engineering applications. The superior mechanical properties of titanium alloys make hole-making a highly unsustainable process. The process is marred by high cutting forces, intense tool damage, high energy consumption, poor hole quality, and high process cost. The work presents an approach for viable and cleaner drilling of the difficult-to-cut material by investigating the effects of micro-lubrication and the following two options of cryogenic cooling: (1) evaporative cooling using liquid nitrogen and (2) throttle cooling using compressed carbon dioxide gas. Additionally, the effects of cutting speed and pecking - a technique actualized by rapidly retracting the twist drill by 2 mm at two levels of depth during thru-cutting of the holes - are also quantified. Pecking is not found to be favorable to any of the evaluated sustainability measures. Of the three cutting fluids testes, throttle cryogenic cooling yielded the most advantageous results. The coolant, because of its effective heat dissipation capability, yielded superior outcomes with respect to all the sustainability measures except surface quality. Micro-lubrication proved to be beneficial, at the low level of cutting speed, to specific cutting energy, surface quality, and process cost. Evaporative cryogenic cooling did not yield promising results. The runs employing evaporative coolant or the high level of cutting speed experienced thicker tool adhesions whereas those utilizing pecking showed signs of intense progressive wear. Moreover, the thrust force data indicated occurrence of thermal softening of the work material as the drills progressed through the hole-cutting process. From the holistic perspective of sustainability, it is recommended to adopt throttle cryogenic cooling, a medium-to-high level of cutting speed, and no-pecking for hole-making in the titanium alloy.}, keywords = {Machining; Liquid nitrogen; TOOL WEAR; cutting energy; compressed CO2}, year = {2021}, eissn = {2212-4616}, pages = {212-225}, orcid-numbers = {Iqbal, Asif/0000-0002-4372-8179} } @article{MTMT:32351398, title = {A state-of-the-art review on sensors and signal processing systems in mechanical machining processes}, url = {https://m2.mtmt.hu/api/publication/32351398}, author = {Kuntoglu, Mustafa and Salur, Emin and Gupta, Munish Kumar and Sarikaya, Murat and Pimenov, Danil Yu}, doi = {10.1007/s00170-021-07425-4}, journal-iso = {INT J ADV MANUFACT TECHNOL}, journal = {INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY}, volume = {116}, unique-id = {32351398}, issn = {0268-3768}, abstract = {Sensors are the main equipment of the data-based enterprises for diagnosis of the health of system. Offering time- or frequency-dependent systemic information provides prognosis with the help of early-warning system using intelligent signal processing systems. Therefore, a chain of data-based information improves the efficiency especially focusing on the determination of remaining useful life of a machine or tool. A broad utilization of sensors in machining processes and artificial intelligence-supported data analysis and signal processing systems are prominent technological tools in the way of Industry 4.0. Therefore, this paper outlines the state of the art of the mentioned systems encountered in the open literature. As a result, existing studies using sensor systems including signal processing facilities in machining processes provide important contribution for error minimization and productivity maximization. However, there is a need for improved adaptive control systems for faster convergence and physical intervention in case of possible problems and failures. On the other hand, sensor fusion is an innovative new technology that makes decisions using multi-sensor information to determine tool status and predict system stability. It is currently not a fully accepted and practiced method. In a nutshell, despite their numerous advantages in terms of efficiency, time saving, and cost, the current situation of sensors used in the industry is not a sufficient level due to the investment cost and its increase with additional signal acquisition hardware and software equipment. Therefore, more studies that can contribute to the literature are needed.}, keywords = {Machining; Artificial intelligence; sensors; Signal processing; 0; Industry 4}, year = {2021}, eissn = {1433-3015}, pages = {2711-2735}, orcid-numbers = {Gupta, Munish Kumar/0000-0002-0777-1559; Sarikaya, Murat/0000-0001-6100-0731} } @article{MTMT:32764411, title = {Fuzzy c-means clustering based colour image segmentation for tool wear monitoring in micro-milling}, url = {https://m2.mtmt.hu/api/publication/32764411}, author = {Malhotra, Jitin and Jha, Sunil}, doi = {10.1016/j.precisioneng.2021.07.013}, journal-iso = {PRECIS ENG}, journal = {PRECISION ENGINEERING-JOURNAL OF THE INTERNATIONAL SOCIETIES FOR PRECISION ENGINEERING AND NANOTECHNOLOGY}, volume = {72}, unique-id = {32764411}, issn = {0141-6359}, abstract = {Micro-milling is an extensively used micro-machining process for producing high precision 3D components from varied materials. However, tool wear in micro-tools is a big concern, as component accuracy directly depends on it. Also, size effects limit the monitoring by the naked eye, but it can be compensated by implying a proper wear monitoring mechanism. Various direct and indirect methods have earlier been used for monitoring purposes, and considering the needs of the fourth industrial revolution, one of the direct methods, machine vision, when combined with image processing algorithms, can play a more prominent role. Current work focuses on creating a wear monitoring algorithm based on fuzzy c-means clustering technique directly implied on acquired colour micro-tool images. The proposed algorithm has three steps: the first step is Region of Interest (ROI) extraction, where the background is removed, orientation correction is done, and ROI on each tooth is extracted from microtool colour images. The second uses the fuzzy c-means technique on ROI to cluster them, from which wear cluster is chosen and morphologically enhanced. The last step performs pixel level measurement and results in numerical wear width. Overall, quantitative results at each step are correlation coefficient of 99 % after image registration, segmentation accuracy of 92 % and wear measurement accuracy of 97 %. A comparison is also made between the proposed algorithm, k-means clustering and RGB thresholding technique, where the proposed algorithm outshines. Lastly, the wear measurement error of the proposed algorithm is less than 5 %, indicating its repeatable, reliable, and robust nature.}, keywords = {ALGORITHM; ACOUSTIC-EMISSION; SURFACE-ROUGHNESS; DESCRIPTORS; Machine vision; Image registration; Fuzzy C-means clustering; TOOL WEAR; Nanoscience & Nanotechnology; Engineering, Multidisciplinary; Engineering, Manufacturing; validity index; Micro-milling}, year = {2021}, eissn = {1873-2372}, pages = {690-705}, orcid-numbers = {Malhotra, Jitin/0000-0003-3591-389X; Jha, Sunil/0000-0002-4100-1320} } @article{MTMT:32351401, title = {Correlating tool wear and surface integrity of a CNC turning process using Naive based classifiers}, url = {https://m2.mtmt.hu/api/publication/32351401}, author = {Mandal, Nirmal Kumar and Singh, Nirmal Kumar and Tarafdar, Najimul Hosen and Hazra, Anirban}, doi = {10.1177/0954405420972980}, journal-iso = {P I MECH ENG B-J ENG}, journal = {PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE}, volume = {235}, unique-id = {32351401}, issn = {0954-4054}, abstract = {Surface finish is an important phenomenon in hard turning. There are many factors which can influence the finishing of a product. Literature review reveals that substantial research has been performed on hard machining, still relationship of tool wear and surface finish parameters like R-a, R-t and R-z is not established as the process is so dynamic and transient in nature. As a result, most of the responses like tool wear, surface integrity parameters, cutting force, and vibration are random in nature. In this investigation, Topic Modelling (TM), a relatively new topic particularly used in machine learning is applied to determine a particular stage of tool wear. Tool wear is divided into three distinct groups namely initial stage (IS), progressive stage (PS), and exponential stage (ES) from a number of experimental observations. Then, surface parameters namely R-a, R-t and R-z are measured. A probabilistic model consisting of tool wear and surface parameters is developed using Naive based classifier. This model is capable to predict a particular stage of tool wear given randomly selected values of R-a, R-t and R-z: To validate this probabilistic model, an alternative machine learning method called multinomial logistic regression is used. Each of this method indicates that the tool has reached to exponential stage when R-a= 1:98, R-t= 17:17 and R-z =. 18:75}, keywords = {Probability; Gaussian distribution; surface integrity; TOOL WEAR; Topic modelling; Naive based classifier}, year = {2021}, eissn = {2041-1975}, pages = {772-781} } @article{MTMT:32351402, title = {Intelligent analysis of tool wear state using stacked denoising autoencoder with online sequential-extreme learning machine}, url = {https://m2.mtmt.hu/api/publication/32351402}, author = {Ou, Jiayu and Li, Hongkun and Huang, Gangjin and Yang, Guowei}, doi = {10.1016/j.measurement.2020.108153}, journal-iso = {MEASUREMENT}, journal = {MEASUREMENT}, volume = {167}, unique-id = {32351402}, issn = {0263-2241}, abstract = {Impeller is a critical component of much large equipment, such as hydropower, nuclear pump, and so on. Its processing quality seriously affects the operation states and service life span of the equipment, while the milling cutter wear determines the processing accuracy of the impeller. Therefore, it is of great important to investigate an intelligent recognition method of tool wear state during the processing. In this research, a new method named stacked denoising autoencoder (SDAE) with online sequential extreme learning machine (OS-ELM) is put forward for intelligent recognition of tool wear states. Firstly, three current signals of the spindle of CNC machine tool are collected during the cutting process and the effective values are synthesized. Then, a new SDAE neural network is trained to acquire the low dimensional features using raw current signals. Finally, OS-ELM is used to realize recognition and classification of the milling cutter, and compared the accuracy with other methods. The method proposed in this paper was verified by both the laboratory signals and the actual engineering signals. The results for spindle current signals show that the developed model has achieved effective performance on tool wear recognition. (C) 2020 Elsevier Ltd. All rights reserved.}, keywords = {online sequential extreme learning machine; stacked denoising autoencoder; spindle current signals; Tool wear states recognition}, year = {2021}, eissn = {1873-412X} } @inproceedings{MTMT:32019363, title = {Adaptive Architecture for Fault Diagnosis of Rotating Machinery}, url = {https://m2.mtmt.hu/api/publication/32019363}, author = {Rodríguez-Jorge, Ricardo and Sánchez-Pérez, Laura and Bíla, Jiří and Škvor, Jiří}, booktitle = {Advanced Information Networking and Applications}, doi = {10.1007/978-3-030-75078-7_5}, unique-id = {32019363}, year = {2021}, pages = {41-51} } @article{MTMT:32764408, title = {Characterization of Printed Circuit Board Micro-Holes Drilling Process by Accurate Analysis of Drilling Force Signal}, url = {https://m2.mtmt.hu/api/publication/32764408}, author = {Tao, Sha and Gao, Zhisen and Shi, Hongyan}, doi = {10.1007/s12541-021-00603-0}, journal-iso = {INT J PRECIS ENG MAN}, journal = {INTERNATIONAL JOURNAL OF PRECISION ENGINEERING AND MANUFACTURING}, volume = {23}, unique-id = {32764408}, issn = {2234-7593}, abstract = {Drilling force directly affects the micro drill life and micro hole quality in the micro hole drilling of printed circuit board (PCB). But in the micro hole drilling process, the signal-to-noise ratio (SNR) of drilling force signal is low. Drilling force signal often submerged by noise signal, these brings great difficulty to measurement during PCB drilling process. Therefore, it is urgent to improve the SNR of drilling force signal in PCB drilling process. The observed signal of drilling force is obtained by PCB micro hole drilling experiment. Based on the cyclostationary and time domain accumulation theory, the drilling force signal is quadratic filtered, and the filtering effect of the filter on the drilling force signal is evaluated. In this paper, a composite multiple filter is designed to improve the SNR of drilling force signal rapidly and efficiently (SNR increased by 11.76 dB), realize the accurate description of the PCB micro hole drilling process.}, keywords = {Printed Circuit Board; Engineering, Manufacturing; Wiener filter; Drilling force}, year = {2021}, eissn = {2005-4602}, pages = {131-138}, orcid-numbers = {Shi, Hongyan/0000-0001-8318-3305} } @article{MTMT:32351400, title = {Special functions for the extended calibration of charge-mode accelerometers}, url = {https://m2.mtmt.hu/api/publication/32351400}, author = {Tomczyk, Krzysztof and Piekarczyk, Marcin and Sieja, Marek and Sokal, Grzegorz}, doi = {10.1016/j.precisioneng.2021.02.002}, journal-iso = {PRECIS ENG}, journal = {PRECISION ENGINEERING-JOURNAL OF THE INTERNATIONAL SOCIETIES FOR PRECISION ENGINEERING AND NANOTECHNOLOGY}, volume = {71}, unique-id = {32351400}, issn = {0141-6359}, abstract = {In this paper, we propose a new procedure for the extended calibration of charge-mode accelerometers. This procedure covers two main stages. The first one follows the general guidelines of international guides that relate to calibrating accelerometers in the frequency domain and are implemented using a weighted-least-squares method. These guidelines are modified herein for the advanced modelling of the charge-mode accelerometer. The second stage provides a new solution which is an extension of the standard calibration using the upper bound of the dynamic error (UBDE) according to the integer-square criterion and a fixed-point algorithm that enables this error to be determined. Additionally, the special functions, representing the values of the dynamic error for the predetermined ranges of the parameters associated with the mathematical model of the charge-mode accelerometer, are determined. Such functions ensure an easy and rapid execution of the second stage of calibration without conducting complicated procedures to determine the value of the UBDE.The extended procedure proposed here enables the comparison of accelerometers with similar technical parameters, but produced by different manufacturers of measuring sensors that frequently compete with each other. In this way, we can select the accelerometer that will produce the lower value of UBDE.}, keywords = {Accelerometer calibration; Integral-square error; Radial basic function}, year = {2021}, eissn = {1873-2372}, pages = {153-169}, orcid-numbers = {Tomczyk, Krzysztof/0000-0002-8922-6529; Sieja, Marek/0000-0001-8229-0598} } @article{MTMT:32351397, title = {A method for predicting hobbing tool wear based on CNC real-time monitoring data and deep learning}, url = {https://m2.mtmt.hu/api/publication/32351397}, author = {Wang, Dashuang and Hong, Rongjing and Lin, Xiaochuan}, doi = {10.1016/j.precisioneng.2021.08.010}, journal-iso = {PRECIS ENG}, journal = {PRECISION ENGINEERING-JOURNAL OF THE INTERNATIONAL SOCIETIES FOR PRECISION ENGINEERING AND NANOTECHNOLOGY}, volume = {72}, unique-id = {32351397}, issn = {0141-6359}, abstract = {Intelligent monitoring and diagnosis of tool status are of great significance for improving the manufacturing efficiency and accuracy of the workpiece. It is difficult to quickly and accurately predict the wear state of worm gear hob under different working conditions. This paper proposes a novel approach to predict hob wear status based on CNC real-time monitoring data. Based on the open platform communication unified architecture (OPC UA) technology and orthogonal test, the machine data of motor power, current, etc. related to tool wear are collected online in the worm gear machining process. And then, an improved deep belief network (DBN) is used to generate a tool wear model by training data. A growing DBN with transfer learning is introduced to automatically decide its best model structure, which can accelerate its learning process, improve training efficiency and model performance. The experiment results show that the proposed method can effectively predict hob wear status under multi-cutting conditions. To show the advantages of the proposed approach, the performance of the DBN is compared with the traditional back propagation neural network (BP) method in terms of the mean squared error (MSE). The compared results show that this tool wear prediction method has better prediction accuracy than the traditional BP method during worm gear hobbing.}, keywords = {TOOL WEAR; Deep belief network; OPC UA; Transfer learning; Worm gear hobbing}, year = {2021}, eissn = {1873-2372}, pages = {847-857} } @article{MTMT:32059442, title = {Predicting the tool wear of a drilling process using novel machine learning XGBoost-SDA}, url = {https://m2.mtmt.hu/api/publication/32059442}, author = {Alajmi, M.S. and Almeshal, A.M.}, doi = {10.3390/ma13214952}, journal-iso = {MATERIALS}, journal = {MATERIALS}, volume = {13}, unique-id = {32059442}, year = {2020}, eissn = {1996-1944} } @article{MTMT:31681058, title = {Twist drilling SPH simulation for thrust force and torque prediction}, url = {https://m2.mtmt.hu/api/publication/31681058}, author = {Boldyrev, I S and Topolov, D I}, doi = {10.1088/1757-899x/971/2/022044}, journal-iso = {IOP CONF SER MATER SCI ENG}, journal = {IOP CONFERENCE SERIES: MATERIALS SCIENCE AND ENGINEERING}, volume = {971}, unique-id = {31681058}, issn = {1757-8981}, abstract = {Drilling is one of the most common processes in metalworking. The cutting forces that occur during the drilling process have a significant impact on the accuracy and quality of the holes. Uncompensated radial cutting forces lead to an increase in the diameter of the hole being machined, which reduces its accuracy. And when machining laminated materials, excessive axial cutting force leads to a stratification of the composite and reduces the quality of the hole. In this regard, the task of determining or predicting cutting forces is currently quite relevant. This article proposes a method for calculating cutting forces when drilling aluminum homogeneous and isotropic alloy 6061-T6 using smoothed particle hydrodynamics method (SPH). The calculation results are compared with calculations using empirical formulas and the results of experiments of other authors. The influence of the chip separation criterion type and material model on cutting forces during drilling were also investigated.}, year = {2020}, eissn = {1757-899X} } @article{MTMT:32059445, title = {In-process tool condition monitoring based on convolution neural network}, url = {https://m2.mtmt.hu/api/publication/32059445}, author = {Cao, D. and Sun, H. and Zhang, J. and Mo, R.}, doi = {10.13196/j.cims.2020.01.008}, journal-iso = {JISUANJI JICHENG ZHIZAO XITONG/COMPUTER INTEGRATED MANUFACTURING SYSTEMS, CIMS}, journal = {JISUANJI JICHENG ZHIZAO XITONG / COMPUTER INTEGRATED MANUFACTURING SYSTEMS, CIMS}, volume = {26}, unique-id = {32059445}, issn = {1006-5911}, year = {2020}, pages = {74-80} } @article{MTMT:32059443, title = {Analysis in the field of manufacturing processes of energy for titanium alloy drilling}, url = {https://m2.mtmt.hu/api/publication/32059443}, author = {Chakravarthy, V.J. and Hakkim, Devan Mydeen P. and Rajarajan, G. and Seenivasan, M.}, journal-iso = {Journal of Green Engineering}, journal = {Journal of Green Engineering}, volume = {10}, unique-id = {32059443}, issn = {1904-4720}, year = {2020}, eissn = {2245-4586}, pages = {2323-2337} } @inproceedings{MTMT:31604398, title = {A Self-Evolving Mutually-Operative Recurrent Network-based Model for Online Tool Condition Monitoring in Delay Scenario}, url = {https://m2.mtmt.hu/api/publication/31604398}, author = {Das, Monidipa and Pratama, Mahardhika and Tjahjowidodo, Tegoeh}, booktitle = {Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining}, doi = {10.1145/3394486.3403328}, unique-id = {31604398}, year = {2020}, pages = {2775-2783} } @mastersthesis{MTMT:31621230, title = {CORRELATION BETWEEN ELECTROMECHANICAL IMPEDANCE AND SURFACE QUALITY OF GROUND WORKPIECES}, url = {https://m2.mtmt.hu/api/publication/31621230}, author = {FABIO, ISAAC FERREIRA}, unique-id = {31621230}, year = {2020} } @article{MTMT:31487044, title = {Electromechanical impedance (EMI) measurements to infer features from the grinding process}, url = {https://m2.mtmt.hu/api/publication/31487044}, author = {Ferreira, Fabio Isaac and de Aguiar, Paulo Roberto and da Silva, Rosemar Batista and Jackson, Mark James and Ruzzi, Rodrigo de Souza and Baptista, Fabricio Guimaraes and Bianchi, Eduardo Carlos}, doi = {10.1007/s00170-019-04733-8}, journal-iso = {INT J ADV MANUFACT TECHNOL}, journal = {INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY}, volume = {106}, unique-id = {31487044}, issn = {0268-3768}, abstract = {This paper discusses the correlations between the electromechanical impedance (EMI) technique and grinding parameters. The EMI technique applied in grinding is novel and has the advantage of employing cheaper equipment and requiring a simpler monitoring system when compared to traditional techniques, such as acoustic emission. Experimental tests were conducted in a controlled environment to isolate the variables of interest, and real and imaginary parts of the impedance were investigated for several frequency bands. Strong correlations among EMI and equivalent chip thickness, roughness, and microhardness of the workpiece, as well as power signals, were found. The RMSD (root-mean-square deviation) index for the real part of the signature in the band 80-85 kHz showed good correlation with roughness and power, while the CCDM (correlation coefficient deviation metric) index for the imaginary part of 50-55 kHz showed good correlation with microhardness. Those correlations allow the user to infer information about the grinding process through indirect monitoring.}, keywords = {grinding; surface quality; structural health monitoring; Electromechanical impedance; Piezoelectric transducer}, year = {2020}, eissn = {1433-3015}, pages = {2035-2048}, orcid-numbers = {Baptista, Fabricio Guimaraes/0000-0002-1200-4354} } @article{MTMT:31736855, title = {A smart tool wear prediction model in drilling of woven composites}, url = {https://m2.mtmt.hu/api/publication/31736855}, author = {Hegab, H. and Hassan, M. and Rawat, S. and Sadek, A. and Attia, H.}, doi = {10.1007/s00170-020-06049-4}, journal-iso = {INT J ADV MANUFACT TECHNOL}, journal = {INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY}, volume = {110}, unique-id = {31736855}, issn = {0268-3768}, abstract = {Undetected tool wear during drilling of woven composites can cause laminate damage and fiber pull-out and fuzzing, causing subsurface damage. This diminishes the life of the produced part under fatigue loads. Thus, the producing of proper and reliable holes in woven composites requires accurate monitoring of the cutting tool wear level to safeguard the machined parts and increase process productivity and profitability. Available tool condition monitoring (TCM) systems mainly require long development lead time and extensive experimental efforts to predict the tool wear within predefined values of cutting conditions. The changes in these values require system relearning. Therefore, developing of a smart generalized TCM system that can accurately predict tool wear based on unlearned data during drilling of woven composite plates is crucial. In this work, an attempt was presented and discussed to predict the tool wear in drilling of woven composite plates at different and wide range of cutting conditions based on the drilling forces using biased learning data. A generalized heuristic model was proposed to accurately predict tool wear value. The performance of the proposed model was benchmarked with respect to four machine learning techniques namely regression tree, support vector machine (SVM), Gaussian process regression (GPR), and artificial neural network (ANN). Extensive experimental validation tests have showed that the GPR model has offered the lowest prediction error based on a reduced biased learning dataset, which represents 50% reduction in learning efforts compared with available literature. However, the developed heuristic model showed a comparable accuracy using significantly less learning efforts.}, keywords = {Modeling; machine learning; Drilling; TOOL WEAR; WOVEN COMPOSITES}, year = {2020}, eissn = {1433-3015}, pages = {2881-2892} } @article{MTMT:31736860, title = {Indirect tool monitoring in drilling based on gap sensor signal and multilayer perceptron feed forward neural network}, url = {https://m2.mtmt.hu/api/publication/31736860}, author = {Jaini, Siti Nurfadilah Binti and Lee, Deug-Woo and Lee, Seung-Jun and Kim, Mi-Ru and Son, Gil-Ho}, doi = {10.1007/s10845-020-01635-5}, journal-iso = {J INTELL MANUF}, journal = {JOURNAL OF INTELLIGENT MANUFACTURING}, unique-id = {31736860}, issn = {0956-5515}, abstract = {In this study, an indirect tool monitoring was developed based on the installation of a gap sensor in measuring the signal related to the tool behavior during the drilling process. Eleven types of twist drills with different tool conditions were utilized to differentiate the sensorial signals based on the tool states. A statistical analysis was conducted in the signal processing, by extracting the gap sensor signal associates from each tool condition, using the skewness and kurtosis features. Multi-class classification was conducted using the multilayer perceptron (MLP) feed forward neural network (FF-NN) model to classify and predict the tool condition based on the skewness and kurtosis data. The architectures of the MLP FF-NN models were varied to optimize the classification accuracy. This study found that the tool condition was correlated to the displacement of the drill machine spindle because the runout occurred when the sensor signal displayed fluctuation and irregularity trends. The peak intensity of the gap sensor signals increased with increasing wear severity of the twist drill. An ideal MLP FF-NN structure was achieved when the classification performance was optimized to be consistent with the learning curve.}, keywords = {statistical analysis; Supervised learning; Drilling; Indirect tool monitoring; Multilayer perceptron feed forward neural network}, year = {2020}, eissn = {1572-8145} } @article{MTMT:32059446, title = {Application of optimization techniques in metal cutting operations: A bibliometric analysis}, url = {https://m2.mtmt.hu/api/publication/32059446}, author = {Jamwal, A. and Agrawal, R. and Sharma, M. and Dangayach, G.S. and Gupta, S.}, doi = {10.1016/j.matpr.2020.07.425}, journal-iso = {MATER TOD PROC}, journal = {MATERIALS TODAY: PROCEEDINGS}, volume = {38}, unique-id = {32059446}, issn = {2214-7853}, abstract = {Bibliometric analysis focuses on the statistical analysis of publications published in a particular area. This method is used to classify the information with variables i.e. journals, institutions, authors and countries. This paper present the general overview of research that has been reported in the optimization techniques in various metal cutting operations. Optimization is becoming popular concept in the present time with its most common goal of optimizing the system by smarter use of both products and services. Optimization techniques are very popular in manufacturing industries as it is leads to time-cost savings, waste reduction and increased the quality level with higher customer satisfaction. These days optimization with the help of traditional approaches and machine learning approaches have become popular to achieve the sustainability in the manufacturing practices. The aim of present research work is to investigate the systematic literature review on optimization techniques applications in the cutting processes within the sustainable manufacturing context. This study reports the 20 years of bibliometric analysis of optimization techniques used in the metal cutting operations. The bibliometric analysis is done by using Scopus database with from the time period of 2000-2020. Keyword co-occurrence is found out with the help of network analysis. Top authors, institutes, countries and publication trends in cutting processes are investigated. It is found that majority of machine learning techniques have been applied in milling and turning applications. Optimization with machine learning techniques has enhanced the research area of metal cutting in last five years. Emerging economies like India and China are more focused towards the adoption of new optimization techniques in the machining area. (C) 2020 Elsevier Ltd. All rights reserved.}, keywords = {Optimization; QUALITY; bibliometric analysis; machine learning; VIBRATION; Multiobjective optimization; RESPONSE-SURFACE METHODOLOGY; TOOL WEAR; Machining parameters; ARTIFICIAL NEURAL-NETWORK; cutting processes; Spindle power; ROUGHNESS PREDICTION}, year = {2020}, pages = {365-370} } @article{MTMT:31487049, title = {A Novel Order Analysis and Stacked Sparse Auto-Encoder Feature Learning Method for Milling Tool Wear Condition Monitoring}, url = {https://m2.mtmt.hu/api/publication/31487049}, author = {Ou, Jiayu and Li, Hongkun and Huang, Gangjin and Zhou, Qiang}, doi = {10.3390/s20102878}, journal-iso = {SENSORS-BASEL}, journal = {SENSORS}, volume = {20}, unique-id = {31487049}, abstract = {Milling is a main processing mode of the modern manufacturing industry, which seriously affects the quality and precision of the machined workpiece. However, it is difficult to monitor the tool wear condition in the continuous cutting process, especially under a variable speed condition. The existing tool wear condition monitoring methods only carry out analysis with a constant engine speed. Different from the general monitoring methods, this paper put forward a milling cutter wear condition monitoring method based on order analysis (OA) and stacked sparse autoencoder (SSAE). The methodology in the research include signals feature extraction and tool wear state monitoring and were designed to analyze the three-phase spindle current signals instead of the traditional force signals and vibration signals. The variable speed signals were transformed into angle domain stationary signals by order analysis, and the SSAE neural network was used to monitor the tool wear state. The proposed method was verified on the laboratory signals and the results showed a better performance than the other methods and a better applicability in actual industrial manufacturing.}, keywords = {order analysis; stacked sparse autoencoder; spindle current signals; tool wear condition monitoring}, year = {2020}, eissn = {1424-8220} } @article{MTMT:31604414, title = {Tool Condition Monitoring Using Deep Learning in Machining Process}, url = {https://m2.mtmt.hu/api/publication/31604414}, author = {Park, Byeonghui and Lee, Yoonjae and Lee, Changwoo}, doi = {10.7736/JKSPE.020.040}, journal-iso = {JKSPE}, journal = {JOURNAL OF THE KOREAN SOCIETY FOR PRECISION ENGINEERING}, volume = {37}, unique-id = {31604414}, issn = {1225-9071}, year = {2020}, eissn = {2287-8769}, pages = {415-420} } @article{MTMT:31172672, title = {Artificial Intelligence-Based Hole Quality Prediction in Micro-Drilling Using Multiple Sensors}, url = {https://m2.mtmt.hu/api/publication/31172672}, author = {Ranjan, Jitesh and Patra, Karali and Szalay, Tibor and Mia, Mozammel and Gupta, Munish Kumar and Song, Qinghua and Krolczyk, Grzegorz and Chudy, Roman and Pashnyov, Vladislav Alievich and Pimenov, Danil Yurievich}, doi = {10.3390/s20030885}, journal-iso = {SENSORS-BASEL}, journal = {SENSORS}, volume = {20}, unique-id = {31172672}, year = {2020}, eissn = {1424-8220}, orcid-numbers = {Szalay, Tibor/0000-0003-3446-2898} } @article{MTMT:31736859, title = {A Novel Approach to Condition Monitoring of the Cutting Process Using Recurrent Neural Networks}, url = {https://m2.mtmt.hu/api/publication/31736859}, author = {Silva, Rui and Araujo, Antonio}, doi = {10.3390/s20164493}, journal-iso = {SENSORS-BASEL}, journal = {SENSORS}, volume = {20}, unique-id = {31736859}, abstract = {Condition monitoring is a fundamental part of machining, as well as other manufacturing processes where, generally, there are parts that wear out and have to be replaced. Devising proper condition monitoring has been a concern of many researchers, but there is still a lack of robustness and efficiency, most often hindered by the system's complexity or otherwise limited by the inherent noisy signals, a characteristic of industrial processes. The vast majority of condition monitoring approaches do not take into account the temporal sequence when modelling and hence lose an intrinsic part of the context of an actual time-dependent process, fundamental to processes such as cutting. The proposed system uses a multisensory approach to gather information from the cutting process, which is then modelled by a recurrent neural network, capturing the evolutive pattern of wear over time. The system was tested with realistic cutting conditions, and the results show great effectiveness and accuracy with just a few cutting tests. The use of recurrent neural networks demonstrates the potential of such an approach for other time-dependent industrial processes under noisy conditions.}, keywords = {Recurrent neural networks; TOOL WEAR; Condition monitoring}, year = {2020}, eissn = {1424-8220}, orcid-numbers = {Silva, Rui/0000-0002-7929-0367; Araujo, Antonio/0000-0002-2879-1225} } @article{MTMT:31736857, title = {Development of family of artificial neural networks for the prediction of cutting tool condition}, url = {https://m2.mtmt.hu/api/publication/31736857}, author = {Spaic, O. and Krivokapic, Z. and Kramar, D.}, doi = {10.14743/apem2020.2.356}, journal-iso = {APEM}, journal = {ADVANCES IN PRODUCTION ENGINEERING & MANAGEMENT}, volume = {15}, unique-id = {31736857}, issn = {1854-6250}, abstract = {Recently, besides regression analysis, artificial neural networks (ANNs) are increasingly used to predict the state of tools. Nevertheless, simulations trained by cutting modes, material type and the method of sharpening twist drills (TD) and the drilling length from sharp to blunt as input parameters and axial drilling force and torque as output ANN parameters did not achieve the expected results. Therefore, in this paper a family of artificial neural networks (FANN) was developed to predict the axial force and drilling torque as a function of a number of influencing factors. The formation of the FANN took place in three phases, in each phase the neural networks formed were trained by drilling lengths until the drill bit was worn out and by a variable parameter, while the combinations of the other influencing parameters were taken as constant values. The results of the prediction obtained by applying the FANN were compared with the results obtained by regression analysis at the points of experimental results. The comparison confirmed that the FANN can be used as a very reliable method for predicting tool condition. (C) 2020 CPE, University of Maribor. All rights reserved.}, keywords = {PREDICTION; Artificial neural networks; Cutting tool; Drilling; TOOL WEAR; back propagation; axial force; Twist drill bits}, year = {2020}, eissn = {1855-6531}, pages = {164-178} } @article{MTMT:30936344, title = {Tool wear prediction in hard turning of EN8 steel using cutting force and surface roughness with artificial neural network}, url = {https://m2.mtmt.hu/api/publication/30936344}, author = {Thangarasu, S.K. and Shankar, S. and Mohanraj, T. and Devendran, K.}, doi = {10.1177/0954406219873932}, journal-iso = {P I MECH ENG C-J MEC}, journal = {PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE}, volume = {234}, unique-id = {30936344}, issn = {0954-4062}, year = {2020}, eissn = {2041-2983}, pages = {329-342} } @article{MTMT:32059444, title = {Wear monitoring of helical milling tool based on one-dimensional convolutional neural network}, url = {https://m2.mtmt.hu/api/publication/32059444}, author = {Wang, H.-J. and Yin, Z.-Y. and Ke, Z.-Z. and Guo, Y.-J. and Dong, H.-Y.}, doi = {10.3785/j.issn.1008-973X.2020.05.010}, journal-iso = {ZHEIJANG DAXUE XUEBAO}, journal = {ZHEJIANG DAXUE XUEBAO (GONGXUE BAN)/JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE)}, volume = {54}, unique-id = {32059444}, issn = {1008-973X}, year = {2020}, pages = {931-939} } @article{MTMT:31487043, title = {Prediction and optimization of machining results and parameters in drilling by using Bayesian networks}, url = {https://m2.mtmt.hu/api/publication/31487043}, author = {Wang, X. and Eisseler, R. and Moehring, H-C}, doi = {10.1007/s11740-020-00965-w}, journal-iso = {PROD ENG RES DEV}, journal = {PRODUCTION ENGINEERING: RESEARCH AND DEVELOPMENT}, volume = {14}, unique-id = {31487043}, issn = {0944-6524}, abstract = {Tool wear and borehole quality are two critical issues for high precision drilling processes. In this paper, several drilling experiments in terms of different drilling parameters and drill bit with and without coating are conducted according to the Taguchi orthogonal arrays. Thrust force and moment were measured during the drilling process. The cutting edge radius depending on the wear, roughness and roundness of the borehole were also aquired. By combining the experiment dataset with the expert knowledge, a Bayesian prediction network of tool wear radius, surface roughness and borehole roundness is established through structure learning and parameter learning algorithms based on GeNIe, a disposable software to create Bayesian networks. Up to 89% accuracy were achieved using this approach. The research described in this paper can provide a new approach to multivariate prediction and parameter optimization in drilling.}, keywords = {Surface roughness; Predictive models; Bayesian network; Drilling process; Wear radius}, year = {2020}, eissn = {1863-7353}, pages = {373-383} } @article{MTMT:31487047, title = {Modeling and analysis of tool wear prediction based on SVD and BiLSTM}, url = {https://m2.mtmt.hu/api/publication/31487047}, author = {Wu, Xiaoqiang and Li, Jia and Jin, Yongquan and Zheng, Shuxian}, doi = {10.1007/s00170-019-04916-3}, journal-iso = {INT J ADV MANUFACT TECHNOL}, journal = {INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY}, volume = {106}, unique-id = {31487047}, issn = {0268-3768}, abstract = {Wear is one of the main forms of tool failure during machining. The prediction of tool wear is of great significance for ensuring the high quality of the workpiece. In order to improve prediction accuracy of tool wear, a tool wear prediction model based on singular value decomposition (SVD) and bidirectional long short-term memory neural network (BiLSTM) is proposed. The cutting force signal is taken as the monitoring signal. Firstly, the raw cutting force signal is reconstructed by Hankle matrix, and the SVD of the reconstructed matrix is performed to extract the signal features. Then, SVD features of the current sampling period and the previous four sampling periods are taken as the input, and the tool wear prediction value at the current time is obtained based on the BiLSTM. The experimental results show that the proposed SVD-BiLSTM model can effectively predict the tool wear and obtain higher prediction accuracy than other comparison models.}, keywords = {SVD; RNN; Tool wear prediction; BiLSTM}, year = {2020}, eissn = {1433-3015}, pages = {4391-4399} } @article{MTMT:31736856, title = {Tool Wear Monitoring for Complex Part Milling Based on Deep Learning}, url = {https://m2.mtmt.hu/api/publication/31736856}, author = {Zhang, Xiaodong and Han, Ce and Luo, Ming and Zhang, Dinghua}, doi = {10.3390/app10196916}, journal-iso = {APPL SCI-BASEL}, journal = {APPLIED SCIENCES-BASEL}, volume = {10}, unique-id = {31736856}, abstract = {Tool wear monitoring is necessary for cost reduction and productivity improvement in the machining industry. Machine learning has been proven to be an effective means of tool wear monitoring. Feature engineering is the core of the machining learning model. In complex parts milling, cutting conditions are time-varying due to the variable engagement between cutting tool and the complex geometric features of the workpiece. In such cases, the features for accurate tool wear monitoring are tricky to select. Besides, usually few sensors are available in an actual machining situation. This causes a high correlation between the hand-designed features, leading to the low accuracy and weak generalization ability of the machine learning model. This paper presents a tool wear monitoring method for complex part milling based on deep learning. The features are pre-selected based on cutting force model and wavelet packet decomposition. The pre-selected cutting forces, cutting vibration and cutting condition features are input to a deep autoencoder for dimension reduction. Then, a deep multi-layer perceptron is developed to estimate the tool wear. The dataset is obtained with a carefully designed varying cutting depth milling experiment. The proposed method works well, with an error of 8.2% on testing samples, which shows an obvious advantage over the classic machine learning method.}, keywords = {Milling; Deep learning; autoencoder; Tool wear monitoring; complex part; deep multi-layer perceptron}, year = {2020}, eissn = {2076-3417} } @article{MTMT:30704243, title = {Tool life prediction based on Gauss importance resampling particle filter}, url = {https://m2.mtmt.hu/api/publication/30704243}, author = {An, Hua and Wang, Guofeng and Dong, Yi and Yang, Kai and Sang, Lingling}, doi = {10.1007/s00170-019-03934-5}, journal-iso = {INT J ADV MANUFACT TECHNOL}, journal = {INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY}, volume = {103}, unique-id = {30704243}, issn = {0268-3768}, year = {2019}, eissn = {1433-3015}, pages = {4627-4634} } @article{MTMT:30662409, title = {A Review on Recent Trends and Challenges in Micromachining and Machinability of Ti-6Al-4V}, url = {https://m2.mtmt.hu/api/publication/30662409}, author = {Bammidi, Roopsandeep and Prasad, K. Siva and Rao, P. Srinivasa}, journal = {Trends in Mechanical Engineering & Technology (TMET)}, volume = {9}, unique-id = {30662409}, issn = {2231-1793}, year = {2019}, pages = {7-31} } @article{MTMT:30936340, title = {Combining translation-invariant wavelet frames and convolutional neural network for intelligent tool wear state identification}, url = {https://m2.mtmt.hu/api/publication/30936340}, author = {Cao, X.-C. and Chen, B.-Q. and Yao, B. and He, W.-P.}, doi = {10.1016/j.compind.2018.12.018}, journal-iso = {COMPUT IND}, journal = {COMPUTERS IN INDUSTRY}, volume = {106}, unique-id = {30936340}, issn = {0166-3615}, abstract = {On-machine monitoring of tool wear in machining processes has found its importance to reduce equipment downtime and reduce tooling costs. As the tool wears out gradually, the contact state of the cutting edge and the workpiece changes, which has a significant influence on the vibration state of the spindle. The performance of traditional intelligent fault diagnosis methods depend on feature extraction of dynamic signals, which requires expert knowledge and human labor. Recently, deep learning algorithms have been applied widely in machine health monitoring. In this paper, we present a novel intelligent technique for tool wear state recognition using machine spindle vibration signals. The proposed technique combines derived wavelet frames (DWFs) and convolutional neural network (CNN). Constructed based on dual tree wavelets, DWF are equipped with merits of centralized multiresolution and nearly translation-invariance. In this method, DWFs are employed to decompose the original signal into frequency bands of different bandwidths and different center frequencies, which are more pronounced as the tool wears. Further, the reconstructed sub-signals are stacked into a 2-D signal matrix to match the structure of 2-D CNN while retaining more dynamic information. The 2-D convolutional neural network is utilized to automatically recognize features from the multiscale 2-D signal matrix. End-milling experiments were performed on a S45C steel workpiece at different machining parameters. The experiment results of the recognition for tool wear state show the feasibility and effectiveness of the proposed method.}, keywords = {Tool wear state monitoring; Spindle vibration; End milling; Wavelet frame; Convolutional neural network (CNN)}, year = {2019}, eissn = {1872-6194}, pages = {71-84} } @article{MTMT:30309453, title = {High-aspect ratio mechanical microdrilling process for a microhole array of nitride ceramics}, url = {https://m2.mtmt.hu/api/publication/30309453}, author = {Chang, Dar-Yuan and Lin, Chien-Hung}, doi = {10.1007/s00170-018-2882-0}, journal-iso = {INT J ADV MANUFACT TECHNOL}, journal = {INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY}, volume = {100}, unique-id = {30309453}, issn = {0268-3768}, abstract = {In semiconductor industry, wafer testing requires a microhole array constructed by high-density holes below ϕ 100 μm for stabilizing the microprobe used in conduction testing. This study conducted mechanical microdrilling experiments of a nitride ceramic sheet to investigate the effects of drilling parameters on quality characteristics of the microhole drilled. Fabrications of a high-aspect ratio microhole must be implemented by segmented machining. A center pilot hole was first made and then drilled the microhole by a two-segment process. Drilling factors analyzed in this study included depth of the center pilot hole, depth ratio of the hole segments, and machining parameters of cutting speed (spindle rotation rate), tool feed rate, and step in peck drilling in the microdrilling. Because both diameter and position of the microhole affect the functionality of hole array directly, this is a multi-objective problem. This study proposes a new decision method for deriving the optimal parameter level set in the multi-object problem based on the level effects obtained from Taguchi’s analyses. In addition, this study used a scanning electron microscopy (SEM) to observe the influences of drilling stroke on flank wear of the microdrill. This study implemented two series experiments of ϕ 69 μm and ϕ 55 μm with aspect ratios of 15.36 and 11.64, respectively. Experimental results indicate that applying the optimal parameter level set derived in ϕ 55 μm experiment could obtain excellent performances after the drilling stroke of 384 mm, 600 holes drilled. The microdrills have fulfilled a high use efficiency.}, year = {2019}, eissn = {1433-3015}, pages = {2867-2883} } @article{MTMT:30410221, title = {Experimental investigation of support plates’ influences on tool wear in micro-drilling of CFRP laminates}, url = {https://m2.mtmt.hu/api/publication/30410221}, author = {Dogrusadik, Ahmet and Kentli, Aykut}, doi = {10.1016/j.jmapro.2019.01.018}, journal-iso = {J MANUFACT PROCES}, journal = {JOURNAL OF MANUFACTURING PROCESSES}, volume = {38}, unique-id = {30410221}, issn = {1526-6125}, abstract = {Drilling induced delamination and tool wear are two major problems in micro-drilling of CFRP laminates. Delamination is concerning the strength of the structure and must be avoided. One of the methods which is used as a preventive measure is utilization of the support plates. In this study, wear of the micro drill was investigated by taken into account the effects of support plates. Experiments with three levels of the spindle speed and feed were performed to provide the comparison between the supported and unsupported cases. Flank wear areas of the worn micro drills were used for the evaluation. It was revealed that feed was more effective on flank wear than spindle speed for both unsupported and supported cases, materials of the support plates had an influence on the flank wear, and cutting parameters were more effective on flank wear for the supported cases.}, keywords = {WEAR; Micro-drilling; CFRP laminate}, year = {2019}, eissn = {2212-4616}, pages = {214-222} } @article{MTMT:30309468, title = {Monitoring the drilling process of GFRP laminates with carbon nanotube buckypaper sensor}, url = {https://m2.mtmt.hu/api/publication/30309468}, author = {Dong, Wang Gong and Li, Nan and Kirwa, Melly Stephen and Peng, Tian and chi, Li Ying and Di, Zhao Qi and De, Ji Shu}, doi = {10.1016/j.compstruct.2018.10.016}, journal-iso = {COMPOS STRUCT}, journal = {COMPOSITE STRUCTURES}, volume = {208}, unique-id = {30309468}, issn = {0263-8223}, abstract = {The present study presents an experimental investigation into the real-time monitoring of the drilling process of Glass Fiber Reinforced Polymer (GFRP) composite with Carbon Nanotubes (CNTs) buckypaper sensor. The spray-vacuum filtration method was employed to synthesize CNTs buckypaper sensor and then embedded into the GFRP to serve two purposes namely interlaminar enhancement and sensor monitoring the drilling process of the GFRP. Both modes I and II interlaminar fracture toughness tests were conducted to ascertain the enhancement ability of the buckypaper. Considerable improvements in both modes of fracture toughness were recorded in the specimens with CNTs buckypaper interlayer. For the CNTs buckypaper acting as a sensor, drilling experiments were carried out on the GFRP where real-time information of the drilling process particularly the drilling tool position could be predicted. This can be crucial in cases where drilling parameters like the feed rate have to be changed at a certain drilling depth in order to reduce or eliminate the exit delamination. The Scanning Electron Microscope (SEM) was finally employed to study the enhancement ability of the CNTs buckypaper and the microstructure of the drilled holes. The current work has substantiated the possibility of using CNT buckypaper both as an interlaminar enhancement and as a sensor to monitor the drilling process.}, keywords = {CARBON NANOTUBES; SENSOR; mechanical properties; GFRP; Drill monitoring}, year = {2019}, eissn = {1879-1085}, pages = {114-126} } @article{MTMT:31577374, title = {Machine learning in cutting processes as enabler for smart sustainable manufacturing}, url = {https://m2.mtmt.hu/api/publication/31577374}, author = {du Preez, Anli and Oosthuizen, Gert Adriaan}, doi = {10.1016/j.promfg.2019.04.102}, journal-iso = {PROCEDIA MANUFACT}, journal = {PROCEDIA MANUFACTURING}, volume = {33}, unique-id = {31577374}, issn = {2351-9789}, keywords = {machine learning; manufacturing; cutting processes}, year = {2019}, pages = {810-817} } @CONFERENCE{MTMT:30753270, title = {Tool condition monitoring method in milling process using wavelet transform and long short-term memory}, url = {https://m2.mtmt.hu/api/publication/30753270}, author = {Fatemeh, Aghazadeh and Antoine, S. Tahan and Thomas, Marc}, booktitle = {Proceedings of Surveillance, Vishno and AVE}, unique-id = {30753270}, year = {2019}, pages = {1-10} } @article{MTMT:30936341, title = {Tool wear monitoring of a retrofitted CNC milling machine using artificial neural networks}, url = {https://m2.mtmt.hu/api/publication/30936341}, author = {Hesser, D.F. and Markert, B.}, doi = {10.1016/j.mfglet.2018.11.001}, journal-iso = {Manufacturing Letters}, journal = {Manufacturing Letters}, volume = {19}, unique-id = {30936341}, issn = {2213-8463}, keywords = {computational intelligence; Vibration measurement; SUPERVISED CLASSIFICATION; Predictive maintenance; INDUSTRY 4.0}, year = {2019}, pages = {1-4} } @article{MTMT:30719621, title = {Research on a Tool Wear Monitoring Algorithm Based on Residual Dense Network}, url = {https://m2.mtmt.hu/api/publication/30719621}, author = {Li, Yiting and Xie, Qingsheng and Huang, Haisong and Chen, Qipeng}, doi = {10.3390/sym11060809}, journal-iso = {SYMMETRY-BASEL}, journal = {SYMMETRY (BASEL)}, volume = {11}, unique-id = {30719621}, year = {2019}, eissn = {2073-8994}, pages = {809} } @article{MTMT:30936343, title = {Comparative study of theoretical and experimental forces in micro drilling of aluminium 6061-T6}, url = {https://m2.mtmt.hu/api/publication/30936343}, author = {Ravisubramanian, S. and Shunmugam, M.S.}, doi = {10.1504/IJMMM.2019.103136}, journal-iso = {INT J MACHINING MACHINABILITY MATER}, journal = {INTERNATIONAL JOURNAL OF MACHINING AND MACHINABILITY OF MATERIALS (IJMMM)}, volume = {21}, unique-id = {30936343}, issn = {1748-5711}, year = {2019}, eissn = {1748-572X}, pages = {437-458} } @article{MTMT:31662961, title = {Prediction of cutting tool wear during milling process using artificial intelligence techniques}, url = {https://m2.mtmt.hu/api/publication/31662961}, author = {Shankar, S. and Mohanraj, T. and Rajasekar, R.}, doi = {10.1080/0951192X.2018.1550681}, journal-iso = {INT J COMPUT INTEG M}, journal = {INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING}, volume = {32}, unique-id = {31662961}, issn = {0951-192X}, abstract = {An efficient tool condition monitoring system was designed for keyway milling of 7075-T6 hybrid aluminium alloy composite with resultant machining force and sound acquired while the milling process. During the milling process, sound pressure and machining force were measured using a microphone and milling tool dynamometer with NI USB 6221 DAQ card and monitored using LabVIEW. The resultant cutting force for fresh and dull tool varies up to 1 kN and 1.8 kN respectively. The sound pressure for fresh, working and dull tool varies up to 1.9 Pa, 2 Pa and 2.5 Pa respectively. The tool condition was estimated from the Artificial Intelligence techniques based on the acquired signals. The acquired signals were given as an input signal to the expert system. The predictor output varies from 0 to 3 to indicate the progression of flank wear and it was utilised to evaluate the tool condition. When the output exceeds the value of 3, it indicates that the tool has to be replaced for the machining process. The Mean Squared Error (MSE) for a feedforward backpropagation neural network and ANFIS model were 2.06517e-9 mm and 0.487505e-3 mm respectively. The neural network had the regression coefficient of 0.99 which shows the accuracy of the model.}, keywords = {PERFORMANCE; Optimization; Neural network; SURFACE-ROUGHNESS; NEURAL-NETWORKS; SOUND; SIGNALS; Milling; OPERATIONS; Turning process; Cutting force; Computer Science, Interdisciplinary Applications; Engineering, Manufacturing; Tool condition monitoring system; sound pressure; MULTISENSOR INTEGRATION}, year = {2019}, eissn = {1362-3052}, pages = {174-182} } @article{MTMT:30338184, title = {Modeling and drilling parameters optimization on burr height using harmony search algorithm in low-frequency vibration-assisted drilling}, url = {https://m2.mtmt.hu/api/publication/30338184}, author = {Shaomin, Li and Deyuan, Zhang and Daxi, Geng and Zhenyu, Shao and Hui, Tang}, doi = {10.1007/s00170-018-2997-3}, journal-iso = {INT J ADV MANUFACT TECHNOL}, journal = {INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY}, volume = {101}, unique-id = {30338184}, issn = {0268-3768}, abstract = {Increasing demands call for the burr-free workpiece in precision manufacturing. Low-frequency vibration-assisted drilling (LFVAD) has been applied to improve the fabrication process. Prediction and minimization of burr size are one of the major research topics in precision machining. In this paper, an LFVAD parameters optimization model was proposed including harmony search (HS) algorithm and a modified LFVAD burr height analytical model. The burr height model of LFVAD was developed using existing analytical burr height model for conventional drilling (CD) and vibration-assisted drilling (VAD). The developed burr height models were then employed with HS algorithm, which is a new meta-heuristic optimization method based on the imitation of music improvisation process, to determine the optimal machining parameters for a given twist drill that results in minimum exit burr height. Experimental results show that the burr height of the optimized LFVAD decreased by 52.75% compared with the CD, and decreased by 17.59% compared with the un-optimized LFVAD. The simulation and experimental results demonstrate that under suitable LFVAD parameters, the burr height could be reduced.}, year = {2019}, eissn = {1433-3015}, pages = {2313-2325} } @article{MTMT:30936339, title = {Modeling and evolutionary computation on drilling of carbon fiber-reinforced polymer nanocomposite: an integrated approach using RSM based PSO}, url = {https://m2.mtmt.hu/api/publication/30936339}, author = {Vijayan, D. and Rajmohan, T.}, doi = {10.1007/s40430-019-1892-7}, journal-iso = {J BRAZ SOC MECH SCI}, journal = {JOURNAL OF THE BRAZILIAN SOCIETY OF MECHANICAL SCIENCES AND ENGINEERING}, volume = {41}, unique-id = {30936339}, issn = {1678-5878}, year = {2019}, eissn = {1806-3691} } @article{MTMT:30684506, title = {Feature Enhancement Method for Drilling Vibration Signal by Using Wavelet Packet Multi-band Spectral Subtraction}, url = {https://m2.mtmt.hu/api/publication/30684506}, author = {Zhou, Youhang and Li, Yong and Liu, Hanjiang}, doi = {10.5545/sv-jme.2018.5726}, journal-iso = {STROJ VESTN-J MECH E}, journal = {STROJNISKI VESTNIK-JOURNAL OF MECHANICAL ENGINEERING}, volume = {65}, unique-id = {30684506}, issn = {0039-2480}, year = {2019}, eissn = {2536-3948}, pages = {219-229} } @article{MTMT:27479338, title = {Tool condition monitoring using spectral subtraction and convolutional neural networks in milling process}, url = {https://m2.mtmt.hu/api/publication/27479338}, author = {Aghazadeh, Fatemeh and Tahan, Antoine and Thomas, Marc}, doi = {10.1007/s00170-018-2420-0}, journal-iso = {INT J ADV MANUFACT TECHNOL}, journal = {INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY}, volume = {98}, unique-id = {27479338}, issn = {0268-3768}, year = {2018}, eissn = {1433-3015}, pages = {3217-3227} } @article{MTMT:27478380, title = {Chip evacuation force modelling for deep hole drilling with twist drills}, url = {https://m2.mtmt.hu/api/publication/27478380}, author = {Ce, Han and Dinghua, Zhang and Ming, Luo and Baohai, Wu}, doi = {10.1007/s00170-018-2488-6}, journal-iso = {INT J ADV MANUFACT TECHNOL}, journal = {INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY}, volume = {98}, unique-id = {27478380}, issn = {0268-3768}, year = {2018}, eissn = {1433-3015}, pages = {3091-3103} } @article{MTMT:27002019, title = {A machine vision system for micro-milling tool condition monitoring}, url = {https://m2.mtmt.hu/api/publication/27002019}, author = {Dai, Yiquan and Zhu, Kunpeng}, doi = {10.1016/j.precisioneng.2017.12.006}, journal-iso = {PRECIS ENG}, journal = {PRECISION ENGINEERING-JOURNAL OF THE INTERNATIONAL SOCIETIES FOR PRECISION ENGINEERING AND NANOTECHNOLOGY}, volume = {52}, unique-id = {27002019}, issn = {0141-6359}, year = {2018}, eissn = {1873-2372}, pages = {183-191} } @mastersthesis{MTMT:30699490, title = {Development of Sustainable Methodologies in Product Design, Manufacturing and Education}, url = {https://m2.mtmt.hu/api/publication/30699490}, author = {Efkolidis, Nikolaos}, unique-id = {30699490}, year = {2018} } @mastersthesis{MTMT:30410960, title = {Intègration de modèles numériques réduits dans l'architecture de pilotage de moyens robotisés possedant des flexibilites importants}, url = {https://m2.mtmt.hu/api/publication/30410960}, author = {Itzel, de jesus GONZALEZ OJEDA}, unique-id = {30410960}, year = {2018} } @article{MTMT:30363315, title = {Dressing Tool Condition Monitoring through Impedance-Based Sensors: Part 1—PZT Diaphragm Transducer Response and EMI Sensing Technique}, url = {https://m2.mtmt.hu/api/publication/30363315}, author = {Junior, Pedro and D’Addona, Doriana M. and Aguiar, Paulo R.}, doi = {10.3390/s18124455}, journal-iso = {SENSORS-BASEL}, journal = {SENSORS}, volume = {18}, unique-id = {30363315}, year = {2018}, eissn = {1424-8220} } @article{MTMT:27430283, title = {Dynamic Bayesian Network-based Approach by Integrating Sensor Deployment for Machining Process Monitoring}, url = {https://m2.mtmt.hu/api/publication/27430283}, author = {K, He and Z, Zhao and M, Jia and C, Liu}, doi = {10.1109/ACCESS.2018.2846251}, journal-iso = {IEEE ACCESS}, journal = {IEEE ACCESS}, volume = {6}, unique-id = {27430283}, issn = {2169-3536}, year = {2018}, eissn = {2169-3536}, pages = {33362-33375} } @article{MTMT:27523089, title = {Machine health management in smart factory: A review}, url = {https://m2.mtmt.hu/api/publication/27523089}, author = {Lee, Gil-Yong and Kim, Mincheol and Quan, Ying-Jun and Kim, Min-Sik and Kim, Thomas Joon Young and Yoon, Hae-Sung and Min, Sangkee and Kim, Dong-Hyeon and Mun, Jeong-Wook and Oh, Jin Woo and Choi, In Gyu and Kim, Chung-Soo and Chu, Won-Shik and Yang, Jinkyu and Bhandari, Binayak and Lee, Choon-Man and Ihn, Jeong-Beom and Ahn, Sung-Hoon}, doi = {10.1007/s12206-018-0201-1}, journal-iso = {J MECH SCI TECHNOL}, journal = {JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY}, volume = {32}, unique-id = {27523089}, issn = {1738-494X}, year = {2018}, eissn = {1976-3824}, pages = {987-1009}, orcid-numbers = {Yoon, Hae-Sung/0000-0002-9430-3541} } @article{MTMT:27473094, title = {Modelling and Prediction of Thrust Force and Torque in Drilling Operations of Al7075 Using ANN and RSM Methodologies}, url = {https://m2.mtmt.hu/api/publication/27473094}, author = {Nikolaos, Efkolidis and César, García Hernández and José, Luis Huertas Talón and Panagiotis, Kyratsis}, doi = {10.5545/sv-jme.2017.5188}, journal-iso = {STROJ VESTN-J MECH E}, journal = {STROJNISKI VESTNIK-JOURNAL OF MECHANICAL ENGINEERING}, volume = {64}, unique-id = {27473094}, issn = {0039-2480}, year = {2018}, eissn = {2536-3948}, pages = {351-361} } @CONFERENCE{MTMT:27474872, title = {Using artificial neural network models for the prediction of thrust force and torque in drilling operation of Al7075}, url = {https://m2.mtmt.hu/api/publication/27474872}, author = {Panagiotis, Kyratsis and Nikolaos, Efkolidis and Daniel, Ghiculescu and Konstantinos, Kakoulis}, booktitle = {22nd International Conference on Innovative Manufacturing Engineering and Energy - IManE&E 2018}, doi = {10.1051/matecconf/201817801008}, unique-id = {27474872}, year = {2018} } @{MTMT:32764427, title = {Soft Computing Techniques and Applications in Mechanical Engineering Preface}, url = {https://m2.mtmt.hu/api/publication/32764427}, booktitle = {Soft Computing Techniques and Applications in Mechanical Engineering}, unique-id = {32764427}, keywords = {Supply chain management; Material removal rate; Computer Science, Interdisciplinary Applications; ARTIFICIAL NEURAL-NETWORK; SOLID TRANSPORTATION PROBLEM; SHOP SCHEDULING PROBLEM; EDM PROCESS PARAMETERS; PAIRWISE LIKELIHOOD INFERENCE; SCATTER SEARCH APPROACH; TYPE-2 FUZZY VARIABLES}, year = {2018}, pages = {XV-X+} } @article{MTMT:30509789, title = {Size effects in Micro End-Milling of Hardened P-20 Steel}, url = {https://m2.mtmt.hu/api/publication/30509789}, author = {Sahoo, Priyabrata and Pratap, Tej and Patra, Karali and Dyakonov, A. A.}, doi = {10.1016/j.matpr.2018.10.163}, journal-iso = {MATER TOD PROC}, journal = {MATERIALS TODAY: PROCEEDINGS}, volume = {5}, unique-id = {30509789}, issn = {2214-7853}, abstract = {Micro machining of hardened tool steel is challenging as compared to macro machining due to unpredictable tool life and size effect. Size effect is usually addressed by the ratio of undeformed chip thickness to edge radius. An attempt has been made to obtain the critical ratio of undeformed chip thickness to edge radius where transition between ploughing and shearing take place. The size effect has been observed from cutting force, surface roughness and micro hardness results. The critical value of the ratio of undeformed chip thickness to edge radius is found to be 0.5 for P-20 steel. (C) 2018 Elsevier Ltd. All rights reserved. Selection and/or Peer-review under responsibility of International Conference on Advances in Materials and Manufacturing Applications [IConAMMA 2017].}, keywords = {Size effect; Micro milling, Cutting force; Surface roughness, Micro hardness; Ploughing}, year = {2018}, pages = {23726-23732} } @article{MTMT:30363322, title = {A Model for Predicting Dynamic Cutting Forces in Sand Mould Milling with Orthogonal Cutting}, url = {https://m2.mtmt.hu/api/publication/30363322}, author = {Shan, Zhong-De and Zhu, Fu-Xian}, doi = {10.1186/s10033-018-0306-6}, journal-iso = {CHIN J MECH ENG-EN}, journal = {CHINESE JOURNAL OF MECHANICAL ENGINEERING}, volume = {31}, unique-id = {30363322}, issn = {1000-9345}, abstract = {Cutting force is one of the research hotspots in direct sand mould milling because the cutting force directly affects the machining quality and tool wear. Unlike metals, sand mould is a heterogeneous discrete deposition material. There is still a lack of theoretical research on the cutting force. In order to realize the prediction and control of the cutting force in the sand mould milling process, an analytical model of cutting force is proposed based on the unequal division shear zone model of orthogonal cutting. The deformation velocity relations of the chip within the orthogonal cutting shear zone are analyzed first. According to the flow behavior of granular, the unequal division shear zone model of sand mould is presented, in which the governing equations of shear strain rate, strain and velocity are established. The constitutive relationship of quasi-solid–liquid transition is introduced to build the 2D constitutive equation and deduce the cutting stress in the mould shear zone. According to the cutting geometric relations of up milling with straight cutting edge and the transformation relationship between cutting stress and cutting force, the dynamic cutting forces are predicted for different milling conditions. Compared with the experimental results, the predicted results show good agreement, indicating that the predictive model of cutting force in milling sand mould is validated. Therefore, the proposed model can provide the theoretical guidance for cutting force control in high efficiency milling sand mould.}, year = {2018}, eissn = {2192-8258}, pages = {103} } @inproceedings{MTMT:33029121, title = {On-line Tool Wear Monitoring via Sparse Coding Based on DCT and WPD}, url = {https://m2.mtmt.hu/api/publication/33029121}, author = {Yu, X. and Wang, R. and Shi, Y. and Zhu, K.}, booktitle = {2018 IEEE 14th International Conference on Automation Science and Engineering (CASE)}, doi = {10.1109/COASE.2018.8560437}, volume = {2018-August}, unique-id = {33029121}, year = {2018}, pages = {1046-1051} } @article{MTMT:30371837, title = {Prediction of cutting forces and instantaneous tool deflection in micro end milling by considering tool run-out}, url = {https://m2.mtmt.hu/api/publication/30371837}, author = {Zhang, Xuewei and Yu, Tianbiao and Wang, Wanshan}, doi = {10.1016/j.ijmecsci.2017.12.019}, journal-iso = {INT J MECH SCI}, journal = {INTERNATIONAL JOURNAL OF MECHANICAL SCIENCES}, volume = {136}, unique-id = {30371837}, issn = {0020-7403}, year = {2018}, eissn = {1879-2162}, pages = {124-133} } @{MTMT:27002004, title = {Identification of Optimal Process Parameters in Electro-Discharge Machining Using ANN and PSO}, url = {https://m2.mtmt.hu/api/publication/27002004}, author = {Kumar, Kaushik and Davim, J Paulo}, booktitle = {Soft Computing Techniques and Applications in Mechanical Engineering}, doi = {10.4018/978-1-5225-3035-0.ch003}, publisher = {IGI Global}, unique-id = {27002004}, year = {2017}, pages = {72-90} }