Special Session-6

Special Session Organizers:

Prof. Chenyu Liu, Northwestern Polytechnical University, China

Prof. Dandan Peng, Northwestern Polytechnical University, China

Assoc. Prof. Yun Kong, Beijing Institute of Technology, China

Introduction and Topics:

Aerospace systems demand exceptionally high levels of reliability, safety, and performance. While significant progress has been made in operational condition monitoring and fault diagnosis, increasing attention is now being directed toward earlier lifecycle stages, including manufacturing processes, assembly quality, and system integration. Defects or uncertainties introduced during these stages can propagate and significantly impact system reliability during operation. This special session aims to bring together researchers and industry practitioners to explore advanced intelligent methodologies for Prognostics and Health Management (PHM) across the full lifecycle of aerospace systems, with particular emphasis on manufacturing, process monitoring, assembly integrity, and their interactions with operational performance. By integrating data-driven approaches with domain knowledge, this session seeks to enable early fault detection, improve quality assurance, and support predictive maintenance strategies. We encourage contributions that address challenges such as heterogeneous data sources, limited labeled data, complex system interactions, and stringent safety requirements. The session will provide a platform for discussing emerging techniques that bridge manufacturing and operational PHM, contributing to more reliable and cost-effective aerospace systems.

The topics include, but are not limited to: 

• Intelligent monitoring and anomaly detection in aerospace manufacturing processes
• Quality assessment and defect detection during assembly and integration
• Multi-source data fusion across manufacturing and operational stages
• Transfer learning and domain adaptation across lifecycle phases
• Physics-informed and hybrid modeling for degradation and reliability prediction
• Digital twin for manufacturing-process-aware PHM
• Explainable AI for safety-critical decision-making
• Remaining useful life (RUL) prediction considering manufacturing-induced variability
• Uncertainty quantification in manufacturing and operational PHM
• Lifecycle-oriented predictive maintenance and decision-making