Special Session-7

Special Session Organizers:

Assoc. Prof. (Dr.) Anil Kumar, College of Mechanical and Electrical Engineering, Wenzhou University, China

Assoc. Prof. (Dr.) Zijian Qiao, School of Mechanical Engineering and Intelligent Manufacturing, Ningbo University, China

Introduction and Topics:

The integration of Artificial Intelligence (AI) into industrial systems, healthcare, and critical infrastructure has significantly enhanced condition monitoring, fault diagnosis, and prognostics. Advanced models such as deep learning and ensemble techniques achieve high accuracy, but their “black-box” nature limits trust, transparency, and real-world adoption—especially in safety-critical environments.

Explainable Artificial Intelligence (XAI) addresses these challenges by providing interpretable and transparent insights into model decisions. In condition-based maintenance, XAI enables stakeholders to understand why a fault is predicted, which features contribute to it, and how remaining useful life (RUL) is estimated.

This special session focuses on advancing trustworthy, interpretable, and human-centric AI frameworks for condition monitoring and prognostics. It aims to bring together researchers and practitioners to explore innovative XAI techniques that enhance reliability, decision-making, and deployment in real-world systems, supporting the transition toward Industry 5.0.

The topics include, but are not limited to: 

•  Explainable AI Techniques for Fault Diagnosis and Anomaly Detection in Industrial Systems
•  Explainable Prognostics and Health Management for Reliable Remaining Useful Life Prediction
•  Human-Centered Explainable AI for Decision Support in Maintenance and Operations
•  Causal and Physics-Informed Explainable AI for Root Cause Analysis
•  Evaluation, Robustness, and Trustworthiness in Explainable AI Systems
•  Generative and Multimodal Explainable AI for Intelligent Condition Monitoring