Industrial IoT (IIoT) has revolutionized production by making data available to stakeholders
at many levels much faster, with much greater granularity than ever before. When it
comes to smart production, the aim of analyzing the collected data is usually to achieve
greater efficiency in general, which includes increasing production but decreasing
waste and using less energy. Furthermore, the boost in communication provided by IIoT
requires special attention to increased levels of safety and security. The growth
in machine learning (ML) capabilities in the last few years has affected smart production
in many ways. The current paper provides an overview of applying various machine learning
techniques for IIoT, smart production, and maintenance, especially in terms of safety,
security, asset localization, quality assurance and sustainability aspects. The approach
of the paper is to provide a comprehensive overview on the ML methods from an application
point of view, hence each domain—namely security and safety, asset localization, quality
control, maintenance—has a dedicated chapter, with a concluding table on the typical
ML techniques and the related references. The paper summarizes lessons learned, and
identifies research gaps and directions for future work.
