Internet of Things and machine learning for energy saving in advanced manufacturing processes: A review

Optimizing energy utilization in industrial processes has become critically important due to growing concerns regarding energy consumption and its environmental impact. In recent years, the integration of the Internet of Things (IoT) with machine learning (ML) techniques has emerged as a viable strategy for enhancing energy efficiency across numerous industrial sectors. As a significant global consumer of energy resources, the manufacturing sector faces pressing sustainability challenges. IoT enables real-time monitoring and data collection from manufacturing systems, providing valuable insights into energy usage patterns. When combined with ML, this integration facilitates automated decision-making systems capable of dynamically adjusting processes to minimize energy consumption without human intervention. This paper provides a comprehensive overview of the application of ML methods for energy saving in manufacturing processes. It examines notable case studies and diverse methodologies to demonstrate the efficacy of ML-based energy conservation in advanced manufacturing. This paper also addresses challenges and limitations associated with implementing ML models in industrial settings, including data quality, model interpretability, and scalability. The findings underscore the potential of these technologies to drive significant energy savings, thereby contributing to more sustainable and efficient manufacturing processes in the Industry 4.0 era.