考虑应力特征的锂离子电池SOC估算  

SOC estimation of Li-ion battery with a focus on force features

作　　者：徐元中[1] 章俊 常春[1] 姜久春 XU Yuanzhong;ZHANG Jun;CHANG Chun;JIANG Jiuchun(Hubei Key Laboratory for High-Efficiency Utilization of Solar Energy and Operation Control of Energy Storage System,Hubei University of Technology,Wuhan,Hubei 430068,China)

机构地区：[1]湖北工业大学太阳能高效利用及储能运行控制湖北省重点实验室,湖北武汉430068

出　　处：《电池》2024年第4期477-481,共5页Battery Bimonthly

基　　金：国家自然科学基金(52177212);湖北省自然科学基金创新群体(2023AFA033);湖北省教育厅科学研究计划(T2021005)。

摘　　要：准确估计荷电状态(SOC)是保证锂离子电池可靠运行的基础。提出基于多维特征特别是结合力信号的数据驱动的SOC估算方法,对锂离子电池应力特征进行Savitzky-Golay(S-G)滤波,形成优化重构后的应力信号。提出基于麻雀搜索算法(SSA)改进的反向传播(BP)神经网络,提高神经网络的全局寻优能力。用恒流(CC)、联邦城市驾驶工况(FUDS)进行评估。在BP神经网络中,相比于单纯使用电信号,考虑应力特征的SOC估算的均方根误差(RMSE)降低89.1%,平均绝对误差(MAE)降低88.8%,考虑应力特征的SSA-BP神经网络的SOC估算误差在0.3%以内,鲁棒性和精确性更高。Accurately estimating the state of charge(SOC)is crucial for ensuring the reliable operation of Li-ion battery.A data-driven SOC estimation method based on multidimensional features,with a specific focus on integrating force signals is introduced.The stress characteristics of Li-ion battery undergo Savitzky-Golay(S-G)filtering,forming in an optimized and reconstructed stress signal.A back propagation(BP)neural network,incorporating the sparrow search algorithm(SSA),is proposed,elevating the global optimization capability of the neural network.The method is evaluated under constant current(CC)and federal urban driving schedule(FUDS)conditions.Within the BP neural network,SOC estimation considering stress features reduces the root mean square error(RMSE)by 89.1%and the mean absolute error(MAE)by 88.8%compared to solely based on electrical signals.The SSA-BP neural network,considering stress features in SOC estimation,maintains error within 0.3%,showcasing higher robustness and precision.

关 键 词：荷电状态(SOC) 锂离子电池 应力 神经网络 麻雀搜索算法(SSA) 

分 类 号：TM912.9[电气工程—电力电子与电力传动]