Techniques to Enhance Production Quality, Safety, and Sustainability through the Use of Machine Learning in IIOT and Smart Production

Authors: Research Scholar Vennila P, Associate Professor Maniraj V

Abstract: Production has been transformed by Industrial IoT (IIoT), which makes data faster and more granularly available to stakeholders at various levels. The goal of evaluating the data gathered in smart manufacturing is often to increase overall efficiency, which entails raising output while reducing waste and energy consumption. Additionally, the IIoT's connectivity rise necessitates extra consideration for higher safety and security standards. Smart production has been impacted by the recent expansion of machine learning (ML) capabilities in a number of ways. The application of various machine learning approaches for IIoT, smart production, and maintenance is summarized in the current study, with a focus on safety, security, asset localization, quality assurance, and sustainability. Each domain—security and safety, asset localization, quality control, and maintenance—has its own chapter, with a final table on common ML techniques and the relevant references. This is because the paper's approach is to give a thorough overview of ML methods from an application point of view. Lessons learned are outlined in the study along with research gaps and future work areas.