Source-Free Cross-Domain State of Charge Estimation of Lithium-Ion Batteries at Different Ambient Temperatures

Abstract

Machine learning methods for state of charge (SOC) estimation of lithium-ion batteries (LiBs) face the problem of domain shift. Varying conditions such as different ambient temperatures can cause performance degradation of the estimators due to data distribution discrepancy. Some transfer learning methods have been utilized to tackle the problem. At real-time transfer, the source model is supposed to keep updating itself online. In the process, source domain data are usually absent because the storage and acquisition of all historical running data can involve violating the privacy of users. However, existing methods require coexistence of source and target samples. In this paper, we discuss a more difficult yet more practical source-free setting where there are only the models pre-trained in source domain and limited target data can be available. To address the challenges of the absence of source data and distribution discrepancy in cross-domain SOC estimation, we propose a novel source-free temperature transfer network (SFTTN), which can mitigate domain shift adaptively. In this paper, cross-domain SOC estimation under source-free transfer setting is discussed for the first time. To this end, we define an effective approach named minimum estimation discrepancy (MED), which attempts to align domain distributions by minimizing the estimation discrepancy of target samples. Extensive transfer experiments and online testing at fixed and changing ambient temperatures are performed to verify the effectiveness of SFTTN. The experiment results indicate that SFTTN can achieve robust and accurate SOC estimation at different ambient temperatures under source-free scenario.