电源技术2025，Vol.49Issue(4)：740-749,10.DOI:10.3969/j.issn.1002-087X.2025.04.009
基于GRU软测量与卡尔曼滤波的电池SOC快速估计
Fast estimation of battery SOC based on GRU soft sensing and Kalman filter
摘要
Abstract
The state of charge(SOC)of lithium-ion battery plays a crucial role in battery balancing,energy usage optimizing,etc.To address the issue of heavy computational burden caused by the non-linearity of state-space equations in model-based SOC estimation methods,gated recurrent units(GRU)was used for soft sensing of SOC.Then linear state-space equations were constructed by using the measured SOC as an output variable and the Kalman filter(KF)was applied to estimate SOC.Under random driving cycles,the proposed method achieves a maximum absolute error of 0.017 in SOC estimation,while also offering fast estimation speed.Further study indicates that there are sig-nificant differences in the parameters of battery models under different charging and discharging rates,leading to lower SOC estimation accuracy of model-based methods in complex conditions.In contrast,the proposed GRU-KF method,due to its independence from precise battery models,dem-onstrates better adaptability to complex conditions.关键词
锂离子电池/SOC估计/门控循环单元/软测量/卡尔曼滤波Key words
lithium-ion battery/SOC estimation/gated recurrent unit/soft sensing/Kalman filter分类
信息技术与安全科学引用本文复制引用
陈志宣,王浩,陆玲霞,华思聪,和嘉睿,于淼..基于GRU软测量与卡尔曼滤波的电池SOC快速估计[J].电源技术,2025,49(4):740-749,10.基金项目
浙江省2024年度"尖兵""领雁"研发计划项目[2024C01237(SD2)] （SD2）
