Applied Machine Learning for IIoT and Smart Production-Methods to Improve Production Quality, Safety and...

Area of Science:

• Engineering
• Computer Science
• Data Science

Background:

• Industrial Internet of Things (IIoT) enables faster, more granular data access in production.
• Smart production aims to boost efficiency, reduce waste, and conserve energy.
• IIoT communication advancements necessitate enhanced safety and security measures.

Purpose of the Study:

• To provide a comprehensive overview of machine learning (ML) applications in Industrial Internet of Things (IIoT) and smart production.
• To explore ML's role in safety, security, asset localization, quality assurance, and sustainability within smart manufacturing.
• To offer an application-focused perspective on ML techniques relevant to IIoT and maintenance.

Main Methods:

• Review and synthesis of existing literature on ML techniques applied to IIoT and smart production.
• Categorization of ML applications by domain: security and safety, asset localization, quality control, and maintenance.
• Compilation of typical ML techniques and references for each application area.

Main Results:

• Machine learning offers diverse applications for enhancing smart production environments.
• Specific ML techniques are identified for addressing challenges in IIoT safety, security, asset tracking, quality control, and predictive maintenance.
• The paper provides a structured overview linking ML methods to practical industrial applications.

Conclusions:

• ML is a key enabler for advancing smart production and Industrial Internet of Things.
• Further research is needed to address identified gaps in ML application for IIoT and smart manufacturing.
• The study highlights future research directions for optimizing ML in industrial contexts.