EvoSim self improves AI to build better physics models for batteries
EvoSim: Learning to Model, Modeling to Learn
Artificial IntelligenceComputational Engineering, Finance, and Science
Summary
Building physics-based models to explain and predict how things work is hard because it requires choosing the right processes and equations. The authors introduce EvoSim, an AI that learns from experiments to improve these models automatically by revising mechanisms and equations when predictions don't match reality. EvoSim also tests its models against separate data to make sure its physics make sense. They tested EvoSim on battery tasks and found it predicts battery behavior more accurately than expert-designed models.
What this means in practice
- •For battery engineers: Automatically improve battery physics models to better predict performance and failure across temperature and charge rates.
- •For automotive system designers: Obtain more accurate voltage predictions under driving conditions for electric vehicle battery management.
Authors
Yun-Wei Song, Jinkai Tao, Jun-Dong Zhang, Rui Zhang, Yi-Min Wu, Qiang Zhang
Abstract
Physics-based models connect scientific explanation with quantitative prediction. Constructing them requires selecting physical processes, defining states and governing equations, specifying couplings, and identifying parameters from experiments. Existing AI systems remain limited in making these model structure decisions autonomously. We introduce EvoSim, a self-evolving AI scientist for physical modeling. It uses experimental discrepancies to drive mechanism and equation revisions and held-out experimental data to test physical plausibility. Exploration traces make updates to knowledge, skills, and multi-agent orchestration. This co-evolution improves physics-based models and EvoSim's ability to select mechanisms, diagnose failures, and coordinate research. We evaluate EvoSim on two industrial battery modeling tasks. It predicts lithium-metal-plating onset from 25 to 45 degrees Celsius and 2 C to 6 C with a mean absolute error of 1.79% in state of charge. Dynamic voltage prediction under vehicle driving conditions achieves a root mean square error of 7.62 mV, surpassing the reported accuracy of models developed by human experts. Self-evolution reduces model and physics errors by approximately 36% relative to baseline, demonstrating improved scientific modeling capability. EvoSim turns experimental observations into validated models and cumulative research expertise.