Using Data Science to Improve Battery Performance: How Data Analytics Can Help Drive Design and Use Decisions

Abstract

Batteries are complex electrochemical devices whose short-term and long-term operational lives are highly dependent on their construction, materials, and use cases. Models have been developed and used to improve the performance of batteries by providing different material design, model based control and model based battery management systems1. There is a recent trend in data-science-based approaches for modeling different devices and processes2,3. In this talk, we will review different data science methods and approaches in the context of parameter estimation, optimal control and mechanism elucidation for lithium-ion batteries. In particular, we will discuss opportunities and challenges in applying the same for battery models – for model reduction, data set training, online estimation and control. It has been demonstrated that using machine learning techniques can retain 99.9% of the accuracy of a complex model while improving solve time by four orders of magnitude, which can allow for the use of high accuracy models in a real-time control scenario3. We will be attempting to demonstrate that this is true for battery models as well, which typically have large cpu time requirements. Real-time model-based control has demonstrated significant improvements in time remaining, state of charge, and state of health, even using simple equivalent circuit models4. By reducing the order and solve time of higher complexity models, we believe that better predictability is possible. Acknowledgments The authors thank the United States Department of Energy (DOE) for the financial support for this work though the Advanced Research Projects Agency – Energy (ARPA-E) award #DEAR0000275.