Associate Professor Quan Qian  Website  E-Mail: qian_1998@uestc.edu.cn
School of Automation Engineering, University of Electronic Science and Technology of China
Interests: transfer learning, process control, intelligent fault diagnosis and RUL prediction

Chao He  Website  E-Mail: choahe@bjtu.edu.cn
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University
Interests: transfer learning, process control, intelligent fault diagnosis and RUL prediction

Zhenxi Wang  Website  E-Mail: zhenxi23@mails.jlu.edu.cn
Department of Control Science and Engineering, Jilin University
Interests: Deep learning, machinie learning, large language model, intelligent prognostics and health management

Special Issue Information

Dear Colleagues,

With the increasing scale and operational complexity of modern industrial systems, ensuring reliability and safety has become a critical challenge. Equipment such as rotating machinery and energy systems often operate under harsh and time-varying conditions, where nonlinearity and uncertainty complicate condition monitoring and maintenance. Fault diagnosis and prognostics are therefore essential for condition-based maintenance and performance optimization.

Recent advances in sensing technologies and computational methods have enabled data-driven and model-based health assessment approaches. However, practical applications still face challenges arising from complex operating conditions, limited fault data, distribution shifts, and poor generalization. Addressing these issues requires robust computational frameworks that integrate signal analysis, intelligent learning, and degradation modeling.

This Special Issue aims to present recent theoretical advances, computational methods, and practical applications in fault diagnosis and prognostics for complex industrial systems, with an emphasis on real-world engineering scenarios. This Special Issue welcomes original research articles, methodological studies, and application-oriented contributions. Suggested themes include, but are not limited to:

• Intelligent fault diagnosis methods
• Remaining useful life prediction
• Advanced signal processing and feature extraction for condition monitoring
• Domain adaptation and domain generalization for cross-condition or cross-system diagnosis
• Health indicator construction and degradation modeling
• Data-driven and hybrid modeling approaches
• Robust diagnosis under nonstationary and time-varying operating conditions
• Multi-sensor data fusion and representation learning
• Data cleaning and selection in massive industrial data
• Application of large language models in industrial fields
• Industrial case studies and real-world applications of fault diagnosis and prognostics

Quan Qian, Chao He, Zhenxi Wang

Keywords

• Fault diagnosis
• Fault prognostics
• RUL prediction
• Signal processing
• Deep learning
• Transfer learning
• Health indicator construction
• Large language model