Tutorial I

                                                                                                  Yunhong Che

                                                                          MIT & Aalborg University

Bio: Dr Yunhong Che is a Research Fellow in Chemical Engineering at MIT and an Assistant Professor of Energy at Aalborg University (joint appointment). His work sits at the intersection of AI and electrochemistry, developing physics-informed models and diagnostics for batteries and energy systems. He earned his PhD from Aalborg University (2024) and previously visited EPFL and Stanford in 2023.

Title: Beyond Black Boxes: Physics-Guided AI for Battery Health in Electric Transportation

Abstract: Accurate and reliable state monitoring, health diagnosis, and lifetime prediction are critical to ensure the safe operation of batteries in energy storage systems. Factors such as different battery types, varying battery pack topologies, diverse user scenarios, and regional characteristics contribute to significant pattern differences, thus challenging optimal management. Integrating artificial intelligence technologies has brought new opportunities for the intelligent management of batteries. However, existing battery system management still faces challenges such as low model generalizability, poor generalization capability, and weak mechanistic interpretability. This seminar will introduce three main topics to address the above challenges. The first part of this seminar focuses on the development of algorithms for dynamic state estimation and prediction throughout the entire lifecycle of battery systems. An integrated multi-state estimation and prediction framework applicable to battery systems under varying operating conditions across their full lifecycle will be illustrated. Then, focusing on battery health prediction research tailored to practical applications with limited labeled data and model adaptability requirements, transfer learning-based model enhancement strategies suitable for variable data conditions will be introduced. Finally, targeting the development of interpretable models that integrate mechanism-based and data-driven approaches, as well as online non-destructive health diagnostics for batteries, a multi-source information fusion and mechanism-data-coupled interpretable battery health diagnosis and prognosis technology will be presented.

Tutorial II

                                                                                           Xiao Chen

                                                                            University of Sheffield

Bio: Dr. Xiao Chen is a senior lecturer in electrical machines at University of Sheffield. He led various research projects / work packages on bearing currents, high frequency effects and manufacturing effects in electrical machines, high-fidelity modelling of electrical machines, and high-speed machines, funded by EPSRC, ORE CATAPULT, Royal Society, ATI, and Rolls-Royce.

Title: Bearing currents in electrical machines

Abstract: Bearing problems contribute to at least 20% of electrical machine failures, and this figure goes even higher for large machines (e.g. machines in wind turbines, more electric aircraft, etc). This tutorial will first introduce the mechanism of bearing currents in electrical machines driven by voltage source inverters, followed by a literature review of bearing current modelling approaches and mitigation techniques. Then, the bearing current research activities at University of Sheffield will be presented, including bearing impedance modelling, parasitic capacitance modelling, common mode, stator and rotor impedance modelling, combined electrical discharge machining and circulating bearing current modelling and validation, and zig-zag slot opening technique for bearing current mitigation.