多特征数据驱动的锂金属电池健康状态估计方法研究

doi:10.3901/JME.260198

摘要/Abstract

摘要： 锂金属电池(Lithium metal batteries，LMBs)因其超高的能量密度有望成为下一代储能装置。然而，由于退化机制复杂，准确预测其健康状态(State of health，SOH)仍然具有挑战性。因此提出一种基于电化学阻抗谱(Electrochemical impedance spectroscopy，EIS)的跨频段多源特征提取方法，通过灰色关联分析(Grey relational analysis，GRA)量化EIS特征与SOH的非线性关联度，筛选出中高频区5个关键频域特征，同时构建简化等效电路模型(Simplified equivalent circuit model，SECM)提取低频区5个反映固相扩散与电荷转移过程的物理参数特征。并结合高斯过程回归(Gaussian process regression，GPR)模型开发了多条件变量耦合下的锂金属电池EIS-SOH估计模型。所提出的方法对不同的预紧力，充放电倍率及电池荷电状态(States of charge，SOC)下的锂金属电池SOH估计有良好的准确性和鲁棒性。该方法在12种不同变量组合条件下的SOH预测结果的平均均方根误差可以达到1.65%。且在极端条件下的均方根误差也可以控制在3%之内。

关键词: 锂金属电池, 健康状态估计, 电化学阻抗谱, 多源特征提取, 高斯过程回归

Abstract: Lithium metal batteries(LMBs) have emerged as a promising next-generation energy storage equipment due to their ultra-high energy density. However, accurately predicting their state of health(SOH) remains challenging owing to complex degradation mechanisms. An electrochemical impedance spectroscopy(EIS)-based cross-frequency-band multi-source feature extraction methodology is proposed. By leveraging grey relational analysis(GRA) to quantify the nonlinear correlation between EIS characteristics and SOH, five critical frequency-domain features in the mid-to-high-frequency region were screened. Concurrently, a simplified equivalent circuit model was constructed to extract five physical parameter features from the low-frequency region, reflecting solid-phase diffusion and charge-transfer processes. Integrated with a Gaussian process regression(GPR) model, an EIS-SOH estimation framework for LMBs under multi-condition variable coupling was developed. The proposed method demonstrates strong accuracy and robustness for SOH estimation across diverse mechanical preload forces, charge/discharge C-rates, and battery states of charge(SOC). Experimental validation under 12 distinct variable combination scenarios yielded an average root mean square error(RMSE) of 1.65% for SOH prediction, while the RMSE remains below 3% even under extreme operating conditions.

Key words: lithium metal batteries, state of health estimation, electrochemical impedance spectroscopy, multi-source feature extraction, Gaussian process regression

中图分类号:

TM912

刘宁宁, 王榘, 王炤东, 呼文韬, 刘兴江. 多特征数据驱动的锂金属电池健康状态估计方法研究[J]. 机械工程学报, 2025, 62(6): 346-358.

LIU Ningning, WANG Ju, WANG Zhaodong, HU Wentao, LIU Xingjiang. Multi-feature Fusion Approach for Data-driven State of Health Estimation in Lithium-metal Batteries[J]. Journal of Mechanical Engineering, 2025, 62(6): 346-358.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://www.cjmenet.com.cn/CN/10.3901/JME.260198

http://www.cjmenet.com.cn/CN/Y2025/V62/I6/346

参考文献

[1] KANG H，KANG H，LYU M，et al. A review of recent developments in the design of electrolytes and solid electrolyte interphase for lithium metal batteries[J]. EcoMat，2024，6(12)：e12498.
[2] ZHANG Shuoqing，LI Ruhong，DENG Tao，et al. Oscillatory solvation chemistry for a 500 Wh kg–1 Li-metal pouch cell[J]. Nature Energy，2024，9(10)：1285-1296.
[3] XIAO Jie. How lithium dendrites form in liquid batteries[J]. Science，2019，366(6464)：426-427.
[4] JAGGER B，PASTA M. Solid electrolyte interphases in lithium metal batteries[J]. Joule，2023，7(10)：2228-2244.
[5] CHEN Xiaoru，YAN Chong，DING Junfan，et al. New insights into “dead lithium” during stripping in lithium metal batteries[J]. Journal of Energy Chemistry，2021，62：289-294.
[6] SONI R，ROBINSON J B，SHEARING P R，et al. Lithium-sulfur battery diagnostics through distribution of relaxation times analysis[J]. Energy Storage Materials，2022，53：97-107.
[7] KIM J，KOWAL J. Development of a Matlab/Simulink model for monitoring cell state-of-health and state-of-charge via impedance of lithium-ion battery cells[J]. Batteries，2022，8(2)：8.
[8] ZHANG Qunming，HUANG Chenggeng，LI He，et al. Electrochemical impedance spectroscopy based state- of-health estimation for lithium-ion battery considering temperature and state-of-charge effect[J]. IEEE Transactions on Transportation Electrification，2022，8(4)：4633-4645.
[9] AGUILAR BOJ E，AZIZIGHALEHSARI S，VENUGOPAL P，et al. A distribution of relaxation time approach on equivalent circuit model parameterization to analyse Li-ion battery degradation[C]//202311th International Conference on Power Electronics and ECCE Asia，Jeju Island，Republic of Korea. IEEE，2023：1403-1409.
[10] XU Zhicheng，WANG Jun，LUND P D，et al. Co-estimating the state of charge and health of lithium batteries through combining a minimalist electrochemical model and an equivalent circuit model[J]. Energy，2022，240：122815.
[11] SUN Jinghua，LIU Yixin，KAINZ J. A comparative study of parameter identification methods for equivalent circuit models for lithium-ion batteries and their application to state of health estimation[J]. Journal of Energy Storage，2025，114：115707.
[12] JONES P K，STIMMING U，LEE A A. Impedance-based forecasting of lithium-ion battery performance amid uneven usage[J]. Nature Communications，2022，13：4806.
[13] LI Zuxin，ZHANG Fengying，CAI Zhiduan，et al. State of health estimation of lithium-ion batteries based on interval voltage features[J]. Journal of Energy Storage，2024，102：114112.
[14] XU Ziyong，LI He，YAZDI M，et al. Aging characteristics and state-of-health estimation of retired batteries：An electrochemical impedance spectroscopy perspective[J]. Electronics，2022，11(23)：3863.
[15] NICODEMO N，DI RIENZO R，LAGNONI M，et al. Estimation of lithium-ion battery electrochemical properties from equivalent circuit model parameters using machine learning[J]. Journal of Energy Storage，2024，99：113257.
[16] LI Chaofan，YANG Lin，LI Qiang，et al. SOH estimation method for lithium-ion batteries based on an improved equivalent circuit model via electrochemical impedance spectroscopy[J]. Journal of Energy Storage，2024，86：111167.
[17] ZHANG Ming，LIU Yanshuo，LI Dezhi，et al. Electrochemical impedance spectroscopy：A new chapter in the fast and accurate estimation of the state of health for lithium-ion batteries[J]. Energies，2023，16(4)：1599.
[18] SI Qianli，MATSUDA S，ANDO Y，et al. Capacity estimation and knee point prediction using electrochemical impedance spectroscopy for lithium metal battery degradation via machine learning[J]. Advanced Science，2025，12(27)：2502336.
[19] ZHANG Wencan，LI Taotao，WU Weixiong，et al. Data-driven state of health estimation in retired battery base on low and medium-frequency electrochemical impedance spectroscopy[J]. Measurement，2023，211：112597.
[20] CHANG Chun，WANG Shaojin，TAO Chen，et al. An improvement of equivalent circuit model for state of health estimation of lithium-ion batteries based on mid-frequency and low-frequency electrochemical impedance spectroscopy[J]. Measurement，2022，202：111795.
[21] 朱建功，戴海峰，王学远，等. 从电池管理到电化学数字电源[J]. 电气工程学报，2024，19(1)：3-22. ZHU Jiangong，DAI Haifeng，WANG Xueyuan，et al. Battery management towards the digitalized electrochemical power source[J]. Journal of Electrical Engineering，2024，19(1)：3-22.
[22] 于淼，朱昱豪，顾鑫，等. 基于膨胀应力的锂离子电池剩余使用寿命预测[J]. 电气工程学报，2024，19(1)：49-56. YU Miao，ZHU Yuhao，GU Xin，et al. Remaining useful life prediction of lithium-ion batteries based on expansion stress[J]. Journal of Electrical Engineering，2024，19(1)：49-56.
[23] MC CARTHY K，GULLAPALLI H，KENNEDY T. Online state of health estimation of Li-ion polymer batteries using real time impedance measurements[J]. Applied Energy，2022，307：118210.
[24] SUN Bingxiang，JIANG Jiuchun，ZHENG Fangdan，et al. Practical state of health estimation of power batteries based on Delphi method and grey relational grade analysis[J]. Journal of Power Sources，2015，282：146-157.
[25] LI Yuanyuan，STROE D I，CHENG Yuhua，et al. On the feature selection for battery state of health estimation based on charging–discharging profiles[J]. Journal of Energy Storage，2021，33：102122.
[26] WU Peihao，LYU Nawei，SONG Yuhang，et al. Li-ion battery failure warning methods for energy-storage systems[J]. Chinese Journal of Electrical Engineering，2024，10(1)：86-100.
[27] SHAO Meng，ZHANG Qianfan，WEI Zhen，et al. A method for suppressing leakage current of non-isolated integrated on-board EV battery charger[J]. Chinese Journal of Electrical Engineering，2024，10(4)：47-59.
[28] 龚奕畅，朱昱豪，顾鑫，等. 基于多参量的动力电池剩余使用价值定义与评价方法[J]. 电气工程学报，2024，19(1)：117-123. GONG Yichang，ZHU Yuhao，GU Xin，et al. Definition and evaluation method of surplus use value of power battery based on multi-parameters[J]. Journal of Electrical Engineering，2024，19(1)：117-123.
[29] 吕东祯，张斌，向家伟. 基于勒贝格采样的锂电池“单体→成组”迁移驱动寿命预测[J]. 机械工程学报，2025，61(16)：40-56. Lü Dongzhen，ZHANG Bin，XIANG Jiawei. Battery life prediction through “Cell→Pack” transfer pipeline using lebesgue sampling[J]. Journal of Mechanical Engineering，2025，61(16)：40-56.
[30] 巫春玲，徐晨峰，张湧，等. 退役动力锂离子电池分选方法研究综述[J]. 电气工程学报，2025，20(2)：310-322. WU Chunling，XU Chenfeng，ZHANG Yong，et al. Review of research methods on sorting of power lithium-ion retired batteries[J]. Journal of Electrical Engineering，2025，20(2)：310-322.
[31] 于全庆，王灿，李建明，等. 多拓扑结构锂电池组外短路特性分析及模型评价[J]. 机械工程学报，2023，59(6)：159-172. YU Quanqing，WANG Can，LI Jianming，et al. Model evaluation and analysis for multi-topology lithium battery pack external short circuit characteristics[J]. Journal of Mechanical Engineering，2023，59(6)：159-172.
[32] 樊磊，杨添强，游静溦，等. 液态金属电池状态估计与成组管理技术研究进展[J]. 电气工程学报，2025，20(4)：297-311. FAN Lei，YANG Tianqiang，YOU Jingwei，et al. Research progress of liquid metal battery state estimation and pack management technology[J]. Journal of Electrical Engineering，2025，20(4)：297-311.
[33] 汤勇，赵威，尹树彬，等. 基于相变传热的动力电池高效复合热控技术研究综述[J]. 机械工程学报，2025，61(4)：176-194. TANG Yong，ZHAO Wei，YIN Shubin，et al. Review on phase change heat transfer based high efficiency composite thermal control technology for power battery[J]. Journal of Mechanical Engineering，2025，61(4)：176-194.
[34] WANG Lulu，ZHENG Kun，LI Yijing，et al. A multitime-scale deep learning model for lithium-ion battery health assessment using soft parameter-sharing mechanism[J]. Chinese Journal of Electrical Engineering，2024，10(3)：1-11.
[35] 熊瑞，张凯旋，李海龙. 锂离子电池热-电特性耦合建模与可视化研究[J]. 机械工程学报，2025，61(2)：268-280. XIONG Rui，ZHANG Kaixuan，LI Hailong. Thermo-electric coupling modeling and visual characterization of lithium-ion batteries[J]. Journal of Mechanical Engineering，2025，61(2)：268-280.