Special Session-3

Special Session Organizers:

Prof. Yi Yang, National University of Defense Technology, China

Prof. Liang Guo, Southwest Jiaotong University, China

Postdoc. Wenyang Hu, Tsinghua University, China

Introduction and Topics:

Modern industrial systems grow increasingly complex, raising unprecedented demands for the operational reliability, safety, and cost efficiency of critical components. Failures of core parts such as turbine blades, gearbox bearings, and robotic reducers may cause severe operational disruptions, safety incidents, and even catastrophic consequences. Thus, accurate health assessment, timely fault diagnosis, and reliable remaining useful life prediction of components have become key industrial challenges.

Traditional maintenance strategies struggle to address the complex degradation mechanisms and variable operating conditions of critical components. Reactive maintenance leads to unplanned downtime and secondary damage, while scheduled maintenance causes unnecessary resource consumption or premature failures. Health monitoring, fault diagnosis, and life prediction integration has thus become the core paradigm for predictive maintenance and health management of complex equipment.

Digital twin technology acts as a transformative approach to integrate these core tasks via high-fidelity virtual replicas of physical assets, yet multiple challenges remain in practical application. This session explores theoretical advances and engineering practices of predictive maintenance and health management for critical components. We invite contributions advancing asset management toward predictability, diagnosability, and prognosticability.

Topics of interest include but are not limited to:

• Dynamic modeling and fault mechanism research of critical components
• Condition monitoring and intelligent fault diagnosis of complex equipment
• Remaining useful life prediction for key components of industrial systems
• Digital twin–enabled integrated PHM frameworks for complex equipment