PDFusion: A domain-adaptive incremental learning model based on Physical-Data Fusion for lithium-ion battery state estimation

Abstract

Accurate estimation of battery state is crucial for ensuring the safe, stable, and efficient operation of lithium-ion batteries. State of Charge (SOC) and State of Energy (SOE) are critical parameters for assessing battery health, but accurately estimating them remains challenging due to the nonlinear, non-stationary and strong coupling characteristics of complex battery charging and discharging processes. To address these issues, a novel domain-adaptive incremental learning model driven by both physical and data is proposed. To reduce state noise and covariance, a novel Kalman Filtering method is used for primary trend prediction. However, physics-based models fail to estimate the seasonal components that contain time-frequency patterns. To overcome the limitation, a data-driven model with Time-frequency Interactive Attention (TIA) is proposed to accurately capture the temporal relationships and effectively compensate for peak errors. To make the model operate across different temperature conditions, a domain-adaptive incremental learning strategy is employed. The results on Lithium iron phosphate (LFP) and Nickel Cobalt Manganese (NCM) batteries show that the proposed model outperforms current state-of-the-art (SOTAs), with the average Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) of 0.048 and 0.021 for LFP under two operating conditions, and 0.060 and 0.023 for NCM. Under Beijing Dynamic Stress test (BJDST) conditions, RMSE and MAE are reduced by 22.69% and 28.56% respectively. Under US06 Highway Driving Schedule (US06) conditions, these metrics are reduced by 41.02% and 49.09%, respectively. The algorithm exhibits high robustness to temperature, enabling precise estimation of the lithium-ion battery states.