This PhD-level excellence course provides an advanced overview of Fault Diagnosis and Prognostics (FDP) methodologies for intelligent and sustainable engineering systems. It combines model-based reasoning, data-driven learning, and AI-enhanced diagnostic tools to address the challenges of modern cyber-physical, automotive, and industrial systems. Participants will explore both theoretical foundations and practical implementations of fault detection, isolation, and health management strategies. The course emphasizes how FDP contributes to system reliability, safety, and life-cycle optimization, aligning with the goals of Industry 4.0 and AI-driven maintenance.

Guest Lecture: Marjan Alavi is an Assistant Professor Lead at McMaster University. She holds a Ph.D. in Electrical Engineering and has an international academic background, with experience in both academia and industry. She is a licensed Professional Engineer in Ontario and an active Senior Member of IEEE, with a strong focus on engineering education and applied systems and technology. 1. Introduction to Fault Detection, Isolation, Diagnostics, and Prognostics 2. Fundamentals of Model-based Diagnosis 3. Signal Processing and Feature Extraction for Condition Monitoring 4. Data-Driven Fault Diagnosis and Machine Learning Approaches 5. Prognostics: Remaining Useful Life (RUL) Estimation and Health Forecasting 6. Research Trends and Emerging Topics 7. Case Studies in Fault Diagnosis and Prognostics

In presenza

Sviluppo di project work in team

P.D.2-2 - Marzo