Ir CHAN Pak-cheung, Deputy Director, the Electrical & Mechanical Services Department, The HKSAR Government

Bio:   Ir CHAN Pak-cheung is the Deputy Director of the Electrical and Mechanical Services Department.  He is responsible for overseeing the enforcement of legislations in ensuring public safety on using electricity, gas, lifts and escalators, railway and other electrical and mechanical installations, and promoting energy efficiency and conservation.

Ir CHAN has been working in the government for over 30 years and taken up professional and managerial roles in the areas of engineering services, project management and regulatory enforcement.  He is a fellow member of the Hong Kong Institution of Engineers in the building services, electrical and energy disciplines.  He received his bachelor degree in electrical and electronics engineering and master degree in building services engineering from the University of Hong Kong.

Prof. Chau Yuen, Associate Professor, School of Electrical & Electronic Engineering, Nanyang Technological University, Singapore

Bio: Chau Yuen (S02-M06-SM12-F21) received the B.Eng. and Ph.D. degrees from Nanyang Technological University, Singapore, in 2000 and 2004, respectively. Since 2023, he has been with the School of Electrical and Electronic Engineering, Nanyang Technological University, currently he is Assistant Dean in Graduate College, and Cluster Director for Sustainable Built Environment at ER@IN. Dr Yuen current serves as an Editor-in-Chief for Springer Nature Computer Science, IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, and IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING. He is listed as Top 2% Scientists by Stanford University, and also a Highly Cited Researcher by Clarivate Web of Science from 2022.

Topic: Transfer Learning for Battery Health Evaluation

Abstract: The energy crisis and climate change have stimulated the rapid progress of Lithium-ion batteries (LIBs), which are superior power storage device with the advantages of small volume, rechargeable, and high energy density. To ensure a stable and efficient environment for its powered devices, accurate and reliable prognostics and health management of LIBs, including state of charge estimation, state of health estimation, and remaining useful life estimation, are becoming increasingly important. Nowadays, thanks to Big Data and Artificial Intelligence technologies, data-driven LIBs health prognostics have garnered considerable attention in academia and industry. However, one of the most significant challenges in developing reliable health prognostics is the requirement of a sufficient amount of data for model training, which is a barrier to new working conditions, different battery types or fabrication, and so on. Transfer learning aims at improving the performance of target learners on target domains by transferring the knowledge contained in different but related source domains. As a result, transfer learning offers a chance to save time and labour through enabling rapid modelling of health assessment with a small amount of data from the target task. To better understand the current research trend, this presentation reviews the research progress of transfer learning for LIBs health prognostics applications, including state of charge estimation between different ambient temperatures, state of health estimation between different batteries, the multi-stage aging mechanisms, etc. Following that, the key ingredients of transfer learning to achieve good performance are discussed, including “when to transfer,” “what to transfer,” and “how to transfer.” Third, the advantages and disadvantages of typical machine learning approaches that are applicable to LIBs health prognostics are summarized and compared. Lastly, the technical challenges and relevant recommendations for battery transfer learning technologies are summarized.