时间：2024年 4月26日 15:00-16:30（北京时间）

地点：线下会场：主楼3楼，A301教室

          线下会场：腾讯会议号:514338508  密码:516504

报告人简介

Dr. Zou is an Associate Professor in Automatic Control at Chalmers University of Technology, Sweden. His research focuses on modeling and automatic control of energy storage systems, particularly batteries. He obtained a PhD degree from the University of Melbourne, Australia, and was a visiting researcher at the University of California, Berkeley, USA. He has received several prestigious research grants from the Swedish Research Council (incl. the Starting Grant and Project Grant), European Commission, Swedish Energy Agency, etc., and keeps close collaboration with industrial partners, e.g., Volvo, Polestar, and Scania. He has hosted four researchers to achieve the Marie Skłodowska-Curie Fellowships, which are among Europe’s most competitive and prestigious research and innovation fellowships. He currently serves as an associate editor/editorial board member for journals including IEEE TVT, IEEE TTE, IEEE T-ITS, and Cell Press journal iScience. Dr. Zou has been a recipient of awards, such as the Best Vehicular Electronics Paper Award of IEEE Vehicular Technology Society, the Scholarship of Australia National Information and Communication Technology, and the Melbourne Research Scholarship.

报告摘要

In this presentation, we will discuss how machine learning (ML) can be harnessed to advance battery modelling, diagnosis and prognosis. The first part will be model-integrated neural networks (MINN) for battery modelling. While existing models for battery management often trade accuracy or physical insights for computational efficiency, we propose a new physics-based learning architecture, termed MINN, to develop battery models that are physically insightful, numerically accurate, and computationally tractable. The second part will be ML-based diagnosis and prognosis of battery ageing under arbitrary vehicle usage conditions. We introduce a joint health-lifetime estimation framework that incorporates offline-developed global models, an online adaptation algorithm, and Kalman filter-based model fusion. This framework is designed to work with both time-series and histogram data, and offers a more accurate and practical approach to battery ageing estimation.