Abstract

This talk focuses on learning, estimation, and control methods to enhance electrochemical battery performance. We begin by providing an overview of mathematical models for batteries and the key challenges that motivate new paradigms for learning, estimation and control. Then we focus on “hybrid” models that combine physics with data-driven approaches. Next, we examine the challenge of predicting the remaining energy within a battery, a type of state estimation and prediction problem. The third part focuses on utilizing reinforcement learning for fast charging batteries. Finally, we close the talk by showcasing how machine learning can be utilized to predict battery health degradation.

Bio

Scott Moura is a Professor in Civil & Environmental Engineering and Director of the Energy, Controls, & Applications Lab (eCAL). He is also the Acting Director of the Berkeley Institute of Transportation Studies. He recently stepped aside as PATH Faculty Director, and Chair of Engineering Science at the University of California, Berkeley. He received the B.S. degree from the University of California, Berkeley, CA, USA, and the M.S. and Ph.D. degrees from the University of Michigan, Ann Arbor, in 2006, 2008, and 2011, respectively, all in mechanical engineering. From 2011 to 2013, he was a Post-Doctoral Fellow at the Cymer Center for Control Systems and Dynamics, University of California, San Diego. In 2013, he was a Visiting Researcher at the Centre Automatique et Systèmes, MINES ParisTech, Paris, France. His research interests include control, optimization, and machine learning for batteries, electrified vehicles, and distributed energy resources.

Dr. Moura is a recipient of the National Science Foundation (NSF) CAREER Award, ASME Dynamic Systems and Control Divisoin Young Investigator Award, Carol D. Soc Distinguished Graduate Student Mentor Award, the Hellman Fellowship, the O. Hugo Shuck Best Paper Award, the ACC Best Student Paper Award (as advisor), the ACC and ASME Dynamic Systems and Control Conference Best Student Paper Finalist (as student and advisor), the UC Presidential Postdoctoral Fellowship, the NSF Graduate Research Fellowship, the University of Michigan Distinguished ProQuest Dissertation Honorable Mention, the University of Michigan Rackham Merit Fellowship, and the College of Engineering Distinguished Leadership Award.

Relevant Papers

M. Borah, Q. Wang, S. J. Moura, D. U. Sauer, W. Li, “Synergizing physics and machine learning for advanced battery management,” Communications Engineering, v3, n134, Sep 2024. DOI: 10.1038/s44172-024-00273-6

H. Tu, M. Borah, S. J. Moura, Y. Wang, H. Fang, “Remaining Energy Prediction for Lithium-Ion Batteries: A Machine Learning Approach,” Applied Energy, v376, Part A, pp. 124086, Dec 2024. DOI: 10.1016/j.apenergy.2024.124086.

A. Pozzi, S. J. Moura, D. Toti, “A Deep Learning-Based Predictive Controller for the Optimal Charging of a Lithium-Ion Cell with Non-Measurable States,” Computers and Chemical Engineering, v172, pp. 10822, May 2023. DOI: 10.1016/j.compchemeng.2023.108222

S. Tao, M. Zhang, Z. Zhao, H. Li, R. Ma, Y. Che, X. Sun, L. Su, C. Sun, X. Chen, H. Chang, S. Zhou, Z. Li, H. Lin, Y. Liu, W. Yu, Z. Xu, H. Hao, S. J. Moura, X. Zhang, Y. Li, X. Hu, G. Zhou, “Non-destructive degradation pattern decoupling for early battery trajectory prediction via physics-informed learning,” Energy & Environmental Science, v18, n3, pp. 1544-1559, Feb 2025. DOI: 10.1039/D4EE03839H. E&ES HOT Articles, 2025.