Self-attention network-based state of charge estimation for lithium-ion batteries with gapped temperature data

Abstract

The accurate estimation of the state of charge (SOC), a critical indicator of the energy stored in lithium-ion batteries, is essential for ensuring reliable and safe battery management. The influence of temperature on the battery characteristics substantially affects the SOC estimation accuracy. Owing to the broad operational temperature range of batteries, it is vital to address the various temperature conditions. This study proposes a model structure for data-driven SOC estimation to enhance accuracy under diverse temperature conditions. The model leverages the analysis of the SOC characteristics derived from the measured data. The proposed structure incorporates parallel-connected self-attention and long-short-term memory modules, thus providing an innovative approach for effectively capturing intricate features in SOC estimation. This study primarily focused on evaluating the capability of the proposed model to achieve satisfactory SOC estimation for untrained temperature conditions when trained with gapped temperature data, thus emphasizing its practicality. To assess the feasibility of the proposed method, experiments were performed under a broad range of fixed and varying temperature conditions, including seasonal and daily changes. The experimental results demonstrated that the root-mean-square errors of the estimated SOC were 0.4101% and 1.5611% at fixed and time-varying temperatures, respectively, including the subzero ranges. These results highlight the robustness of the proposed model under various temperature conditions and its applicability to real-world battery operational temperatures.