A Self-Adaptive Physics-Informed Gated Recurrent Unit Neural Networks Model for Estimating the Lifetime of Li-Ion Batteries

The physics-informed neural networks (PINNs) have recently emerged as a promising approach for applying deep neural networks to solve partial differential equations. However, accurately addressing challenging regions in the solutions of stiff partial differential equations necessitates adaptive methods. Additionally, the inherent limitations of baseline PINNs in handling sequential or time-series data significantly constrain their applicability. In light of this, this article introduces a self-adaptive (SA) physics-informed attention-based gated recurrent unit (GRU) model, which enhances the baseline PINNs framework to address these critical issues. The proposed model represents a significant advancement in PINNs by integrating an attention-based GRU (AGRU) layer, thereby enabling more effective modeling of sequential data than the existing physics-informed models. Moreover, this article jointly minimizes the prediction error between the estimated and measured outputs (data-fit loss) and the residual associated with the governing degradation physics (physics-residual loss), while learning adaptive weights to balance both objectives during training. The efficacy of the proposed model is demonstrated through an essential case study, which is to predict the state of health (SOH) of lithium-ion batteries (LIBs), utilizing four battery datasets from different sources, namely, the NASA, MIT, XJTU, and HUST battery datasets. The proposed model is compared with the baseline PINNs and other benchmark models to demonstrate improvements in predictive accuracy and network initialization capabilities.