Physics-informed Neural Network For Lithium-ion Battery Degradation Stable Modeling And Prognosis

This article discusses the challenges of accurately estimating the state-of-health (SOH) of lithium-ion batteries and proposes a physics-informed neural network (PINN) as a solution. The PINN uses neural networks to capture battery degradation dynamics and a feature extraction method to make it applicable to different battery types and charge/discharge protocols. The proposed method is validated using a comprehensive dataset of 387 batteries and has shown remarkable performance in various experiments. This study highlights the potential of physics-informed machine learning for battery degradation modeling and SOH estimation.