In this talk, I will introduce our recent outcomes in improving the health monitoring of energy systems networks. The lithium-ion batteries in electric vehicles and energy storage systems are selected for illustration. We will present the advanced AI framework we have developed, which integrates cloud and ECU levels to effectively monitor battery health, addressing challenges such as data heterogeneity, AI explainability, concept drift and privacy concerns. The key methodologies include the development of the new ECU-Edge-Cloud architecture with personalized federated learning and local self-knowledge distillation, the development of trustworthy multitask learning to enable online battery health assessment and the development of dynamic transfer learning to provide robust machine learning models under concept drift.

Dr. Huadong Mo joined the University of New South Wales in Australia as a lecturer in 2019 and was promoted to senior lecturer in 2021. He is currently the coordinator of the Systems Engineering Discipline under the School of Systems and Computing. He was previously a postdoctoral fellow at the Swiss Federal Institute of Technology Zurich. Dr. Mo obtained a bachelor’s degree in Automation from the University of Science and Technology of China in 2012 and a Ph.D. in Industrial Engineering and Engineering Management from the City University of Hong Kong in 2016. Dr. Mo has been engaged in research on enhancing better resilience, performance, and security of complex systems with learning-based algorithms, which primarily lay in the emerging field of power and energy systems, cyber-physical systems, and manufacturing systems, leveraging the capacity to collect and analyze data to reveal patterns of system evolution against uncertainties for many years, publishing over 60 SCI and conference papers, as well as one monograph. Dr. Mo is currently the IEEE Senior Member and Chair of the IEEE SMC ACT Chapter.