ICIEA 2026 Special Session
SS34: Fault Diagnosis and Reliability Assessment
Organized by:
Organizer 1: Xingjian Wang
Email: wangxj@buaa.edu.cn
Affiliation: Beihang University, China
Organizer 2: Chao Zhang
Email: cz@buaa.edu.cn
Affiliation: Beihang University, China
This session focuses on data-driven intelligence for fault diagnosis, degradation prediction, and predictive maintenance in complex engineering systems. The contributions emphasize the integration of machine learning, physics-informed modeling, and digital twin concepts to address challenges such as small-sample learning, multi-source data fusion, and uncertainty-aware diagnosis. Typical application domains include hydraulic systems, power electronics, aerospace components, and industrial equipment operating under harsh or extreme conditions. The session highlights methodologies that improve reliability assessment, fault interpretability, and system-level health management, supporting the transition from reactive maintenance toward intelligent, predictive decision-making frameworks. Topics related to system control and modeling, including but not limited to: