Condition monitoring, Fault diagnosis, Electrical machines and drives, Advanced signal and image processing, Artificial intelligence

The use of advanced signal processing tools and techniques in the electrical machines and drives condition monitoring area has drawn the attention of many researchers over recent years. Conventional diagnosis techniques relying on classical tools such as the Fast Fourier Transform are being complemented, or even replaced, by new methods based on modern signal processing tools suited for the analysis of non-stationary signals. This Special Session is intended to attract research papers showing novel applications of these signal analysis techniques in the electric machines and drives condition monitoring area. The scope also covers papers including applications of pattern recognition algorithms or image processing techniques for diagnostic or prognostic purposes, both in electrical machines and drives, whatever the application (power generation, drive systems, transportation electrification, renewable energy conversion, industrial processes, etc.).

The topic is directly aligned with the theme of IEEE ISIE 2027, “Industrial Electronics at the Crossroads of Energy and Digital Transitions”: the reliability of the electrical machines and drives that underpin an electrified industry depends on the early detection of incipient faults, while the diagnostic methods themselves are being reshaped by data-driven intelligence. Contributions combining physical insight into failure mechanisms with modern computational tools — deep learning, transfer learning, infrared thermography and multi-sensor fusion — are particularly welcome, as are experimentally validated works and industrial case studies. The Special Session is supported by the IEEE IES Technical Committee on Electrical Machines.

• Time-frequency decomposition tools
• Pattern recognition algorithms
• Signal analysis techniques
• Novel image processing tools
• Classification methods
• Deep learning
• Artificial intelligence for condition monitoring
• Transfer learning techniques for electric machine condition monitoring
• Infrared thermography for condition monitoring