张彬桥,邹霖,万刚
ZHANG Binqiao,ZOU Lin,WAN Gang

• 1:三峡大学电气与新能源学院
• 2:梯级水电站运行与控制湖北省重点实验室
• 3:中国长江电力股份有限公司检修厂

摘要(Abstract)：

为提高锂离子电池SOH（健康状态）估计精度，提出一种基于SAO-BiLSTM-KAN（雪消融优化-双向长短期记忆神经网络-柯尔莫哥洛夫-阿诺德网络）的电池SOH估计方法。首先从电池充电过程中提取数据，并通过容量增量分析提取健康特征；然后将特征输入BiLSTM网络以捕捉时间序列中的长期依赖关系，进一步将BiLSTM输出传入KAN网络，以挖掘特征间的复杂非线性关系，从而提升估计性能。为达到更好的效果，引入SAO对模型超参数进行寻优。实验结果表明，所提模型在各类对比实验中均表现出优异性能，SOH估计的RMSE（均方根误差）与MAE（平均绝对误差）均低于0.919%，验证了该方法在预测精度和泛化能力方面的优势。
To improve the estimation accuracy of the state of health(SOH) for lithium-ion batteries, a novel estimation method based on snow ablation optimization, bidirectional long short-term memory network and KolmogorovArnold networks(SAO-BiLSTM-KAN) is proposed. Firstly, data is extracted from the battery charging process, and health features are derived through incremental capacity analysis. These features are then fed into a BiLSTM network to capture long-term dependencies within the time series. Subsequently, the outputs from the BiLSTM are passed to the KAN to explore complex nonlinear relationships among the features, thereby enhancing estimation performance. To achieve optimal results, the SAO algorithm is introduced to optimize the model's hyperparameters. Experimental results demonstrate that the proposed model delivers outstanding performance across various comparative tests, with both the root mean square error(RMSE) and mean absolute error(MAE) for SOH estimation remaining below 0.919%, validating the method's superior prediction accuracy and generalization capability.

关键词(KeyWords)： 锂离子电池;健康状态;BiLSTM;KAN;雪消融优化算法
lithium-ion battery;SOH;BiLSTM;KAN;SAO

Abstract:

Keywords:

基金项目(Foundation): 湖北省自然科学基金（2022CFD167）

作者(Author): 张彬桥,邹霖,万刚
ZHANG Binqiao,ZOU Lin,WAN Gang

DOI: 10.19585/j.zjdl.202601006

参考文献(References)：

• [1]费陈，赵亮，王云恪，等.基于XGBoost算法的锂离子电池健康状态估算[J].浙江电力，2022,41(5):14-21.FEI Chen,ZHAO Liang,WANG Yunke,et al.SOH estimation of Li-ion battery based on XGBoost algorithm[J].Zhejiang Electric Power,2022,41(5):14-21.
• [2]李卓昊，石琼林，王康丽，等.锂离子电池健康状态估计方法研究现状与展望[J].电力系统自动化，2024,48(20):109-129.LI Zhuohao,SHI Qionglin,WANG Kangli,et al.Research status and prospects of state of health estimation methods for lithium-ion batteries[J].Automation of Electric Power Systems,2024,48(20):109-129.
• [3]方斯顿，刘龙真，孔赖强，等.基于双向长短期记忆网络含间接健康指标的锂电池SOH估计[J].电力系统自动化，2024,48(4):160-168.FANG Sidun,LIU Longzhen,KONG Laiqiang,et al.State-of-health estimation for lithium-ion batteries incorporating indirect health indicators based on bi-directional long short-term memory networks[J].Automation of Electric Power Systems,2024,48(4):160-168.
• [4]孙静，翟千淳.基于融合特征和OOA-BiGRU的锂离子电池剩余使用寿命预测方法[J].电工技术学报，2025,40(9):2996-3012.SUN Jing,ZHAI Qianchun.A novel remaining useful life prediction method based on fusion feature and OOABiGRU for lithium-ion batteries[J].Transactions of China Electrotechnical Society,2025,40(9):2996-3012.
• [5]张朝龙，陈阳，刘梦玲，等.一种基于ICA-T特征和CNNLA-BiLSTM的锂离子电池健康状态估计方法[J].储能科学与技术，2025,14(3):1258-1269.ZHANG Chaolong,CHEN Yang,LIU Mengling,et al.A state of health estimation method for lithium-ion batteries using ICA-T features and CNN-LA-BiLSTM[J].Energy Storage Science and Technology,2025,14(3):1258-1269.
• [6]顾菊平，蒋凌，张新松，等.基于特征提取的锂离子电池健康状态评估及影响因素分析[J].电工技术学报，2023,38(19):5330-5342.GU Juping,JIANG Ling,ZHANG Xinsong,et al.Estimation and influencing factor analysis of lithium-ion batteries state of health based on features extraction[J]. Transactions of China Electrotechnical Society,2023,38(19):5330-5342.
• [7]AMIR S,GULZAR M,TARAR M O,et al. Dynamic equivalent circuit model to estimate state-of-health of lithium-ion batteries[J]. IEEE Access,2022,10:18279-18288.
• [8]GAO Y Z,LIU K L,ZHU C,et al.Co-estimation of stateof-charge and state-of-health for lithium-ion batteries using an enhanced electrochemical model[J].IEEE Transactions on Industrial Electronics,2022,69(3):2684-2696.
• [9]王君瑞，李进，季长江，等.基于DMIAUKF算法的锂离子电池SOC和SOH联合估算[J/OL].电源学报，2025:1-15.(2025-03-28)[2025-05-02]. https：//kns. cnki. net/kcms/detail/12.1420.TM.20250328.1105.006.html.WANG Junrui,LI Jin,JI Changjiang, et al. Joint estimation of SOC and SOH of lithium-ion battery based on DMIAUKF algorithm[J/OL].Journal of Power Supply,2025:1-15.(2025-03-28)[2025-05-02].https：//kns.cnki.net/kcms/detail/12.1420.TM.20250328.1105.006.html.
• [10]巫春玲，王立顶，卢勇，等.基于白鹭群优化高斯过程回归的锂电池SOH估计方法[J].储能科学与技术，2025,14(6):2498-2511.WU Chunling,WANG Liding,LU Yong,et al.Lithiumion batteries SOH estimation based on Gaussian processed regression optimized by egret swarm optimization[J].Energy Storage Science and Technology,2025,14(6):2498-2511.
• [11]朱永茂，吕印，邵建伟，等.基于容量增量曲线的QGABP锂电池SOH在线估计[J/OL].电源学报，2025:1-18.(2025-03-06)[2025-05-02]. https：//kns. cnki. net/kcms/detail/12.1420.TM.20250306.1202.003.html.ZHU Yongmao,LYU Yin,SHAO Jianwei,et al.On-line estimation of SOH of QGA-BP lithium battery based on capacity increment curve[J/OL]. Journal of Power Supply,2025:1-18.(2025-03-06)[2025-05-02]. https：//kns.cnki. net/kcms/detail/12.1420. TM. 20250306.1202.003.html.
• [12]李珺，陈小然，徐亮.基于多健康因子和IPSO-LSTM模型的锂电池健康估计[J].车用发动机，2025(1):39-46.LI Jun,CHEN Xiaoran,XU Liang.Lithium battery health estimation based on multiple health factors and IPSOLSTM model[J].Vehicle Engine,2025(1):39-46.
• [13]陆继忠，彭思敏，李晓宇.基于多特征量分析和LSTMXGBoost模型的锂离子电池SOH估计方法[J].储能科学与技术，2024,13(9):2972-2982.LU Jizhong,PENG Simin,LI Xiaoyu.State-of-health estimation of lithium-ion batteries based on multifeature analysis and LSTM-XGBoost model[J]. Energy Storage Science and Technology,2024,13(9):2972-2982.
• [14]吴铁洲，朱俊超，成雄帆，等.基于充电阶段数据与GWOBiLSTM模型的锂电池SOH估计方法[J].电源技术，2024,48(11):2184-2194.WU Tiezhou,ZHU Junchao,CHENG Xiongfan,et al.SOH estimation method of lithium-ion batteries based on charging stage data and GWO-BiLSTM model[J]. Chinese Journal of Power Sources,2024,48(11):2184-2194.
• [15]李习龙，张涌，张伟，等.基于健康因子和CNN-BiLSTM的锂离子电池健康状态预测[J/OL].南京信息工程大学学报，2024:1-12.(2024-07-19)[2025-05-07]. https：//link.cnki.net/doi/10.13878/j.cnki.jnuist.20240514002.LI Xilong,ZHANG Yong,ZHANG Wei,et al. Health state prediction of lithium-ion battery based on health factors and CNN-BiLSTM[J/OL]. Journal of Nanjing University of Information Science&Technology(Natural Science Edition),2024:1-12.(2024-07-19)[2025-05-07].https：//link. cnki. net/doi/10.13878/j. cnki. jnuist.20240514002.
• [16]盛雷，李丽娟，付西红，等.基于KAN-Transformer的离轴三反装调仿真技术[J].光学学报，2025,45(5):157-169.SHENG Lei,LI Lijuan,FU Xihong,et al.Simulation technology for assembly of off-axis three-mirror optical systems based on KAN-transformer[J]. Acta Optica Sinica,2025,45(5):157-169.
• [17]LIU Z,WANG Y,VAIDYA S,et al.Kan:Kolmogorovarnold networks[J]. arXiv preprint arXiv:2404.19756,2024.
• [18]DENG L Y,LIU S Y. Snow ablation optimizer:a novel metaheuristic technique for numerical optimization and engineering design[J]. Expert Systems with Applications,2023,225:120069.