Khoo, E. Early prediction of battery remaining useful life using AI and physics. 10th International Congress on Industrial and Applied Mathematics.
Abstract:
Accurate prediction of the remaining useful life (RUL) of a lithium-ion battery (LIB) using early cycle data aids in scheduling predictive maintenance, avoiding catastrophic failure during operation and optimizing battery manufacturing. In this talk, we discuss our recent work in building a hybrid deep learning model that combines physics-informed features with statistical features to achieve better generalization performance in early RUL prediction when benchmarked against several AI models. If time permits, we will also discuss our recent parametric study of LIB capacity fade using a cell OCV model.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Agency for Science, Technology and Research (A*STAR) - Career Development Fund (CDF)
Grant Reference no. : C210112037