Intelligent Maintenance and Health Management in Smart Manufacturing

Dear Colleagues,

The advent of Industry 4.0 and smart manufacturing has placed unprecedented demands regarding the reliability, availability, and efficiency of industrial systems. Unexpected equipment failures lead to significant economic losses, safety hazards, and operational downtime. To address these challenges, intelligent maintenance and Prognostics and Health Management (PHM) have emerged as critical paradigms, shifting from traditional reactive or schedule-based maintenance to data-driven, predictive, and proactive strategies.

This Topic aims to explore cutting-edge research and innovative applications at the intersection of advanced data analytics and industrial systems. We welcome contributions that leverage modern techniques such as deep learning, signal processing, and large language models to enhance condition monitoring, anomaly detection, fault diagnosis, and remaining useful life (RUL) prediction. In particular, we focus on the development and implementation of digital twins as a core enabler for real-time system simulation, health assessment, and decision-making. We seek high-quality original research and review articles that demonstrate novel methodologies, frameworks, or case studies applied to key components and systems in smart manufacturing, including but not limited to bearings, wind turbines, gearboxes, and batteries. The goal is to compile a collection of works that bridge the gap between theoretical advancements and practical, scalable solutions for the next generation of industrial maintenance.

The Topic will cover, but is not limited to, the following topics:

• Multi-sensor fusion and signal processing for comprehensive condition monitoring in dynamic environments;
• Advanced vibration and thermal imaging analysis for early-stage fault detection in industrial machinery;
• Deep Learning for fault classification, incipient fault identification, and RUL prediction in complex systems;
• Physics-Informed Neural Networks (PINNs) integrating mechanistic knowledge with data-driven approaches;
• Large Models (LMs) for processing maintenance logs, technical reports, and multimodal industrial data;
• Digital Twin frameworks for real-time simulation and virtual sensing;
• Optimization of operational workflows through AI-driven predictive analytics to minimize downtime;
• Uncertainty quantification and robust decision-making in complex systems.

Dr. Zhuyun Chen
Dr. Junyu Qi
Dr. Yafei Xu
Dr. Fei Jiang
Dr. Dimitrios Alexios Karras
Dr. Chong Chen
Dr. Yujie Zhang
Topic Editors