基于勒贝格采样的锂电池“单体→成组”迁移驱动寿命预测

doi:10.3901/JME.2025.16.040

摘要/Abstract

摘要： 单体电池寿命预测研究是当前的热点，而电池组的退化过程由于涉及多个单体电池的叠加效应，进一步增加了预测的复杂性。一方面，现有电池组寿命预测研究的样本数量较为有限，且过度依赖于对未来电流和电压信息的提前获取，难以实现真正的寿命预测，无法满足实际应用需求。另一方面，随着机器学习方法的广泛应用，计算资源日益紧张，因此在保证预测准确性的前提下，如何大幅提升预测方法的计算效率成为一项亟待解决的重要课题。为此，首先设计试验对单体电池和电池组之间的退化过程进行了研究。然后，提出一种基于勒贝格采样的锂电池“单体→成组”迁移驱动寿命预测方法。该方法引入勒贝格采样技术，实现时间空间特征的提取以及差分模型的构建，优化目标域和源域之间的邻域差异，快速精准地计算勒贝格抵达时间的概率分布。在仅采用单体电池的退化数据进行训练后就成功预测电池组的失效寿命。所提出的方法在早期预测场景以及实时预测场景均获得了1.5%左右的寿命预测误差，在此基础上还实现了毫秒级至秒级的计算效率，整体的预测精度以及计算效率均大幅领先现有诸多成熟的寿命预测方法。

关键词: 勒贝格采样, 寿命预测, 电池组, 剩余寿命, 计算效率

Abstract: Research on lithium-ion battery lifetime prediction is a hot topic, but the complex degradation process involving multiple cells complicates the task. Current studies often have limited sample sizes and rely heavily on future current and voltage data, making true prediction impractical for real-world applications. Additionally, the extensive use of machine learning methods has caused a significant strain on computational resources. Therefore, significantly reducing the computational cost of prediction methods while ensuring prediction accuracy is of great practical significance. To address this, we first designed experiments to study the degradation process between individual batteries and battery packs. Then, we proposed a Lebesgue sampling-based migration-driven lifetime prediction method for lithium batteries, transitioning from individual cells to groups. This method introduces Lebesgue sampling techniques to extract features and construct differential models, optimizing neighborhood differences between the target domain and the source domain, and efficiently computing the probability distribution of the arrival time at the Lebesgue limit. The method trains on degradation data from individual batteries, successfully predicting the failure life of the battery pack. The proposed method achieved a prediction error of around 1.5% in both early and real-time prediction scenarios, while also achieving computational efficiency in the millisecond to second range, significantly surpassing many existing mature lifetime prediction methods in both accuracy and efficiency.

Key words: lebesgue sampling, life time prediction, battery packs, remaining useful life, computing efficient

中图分类号:

TM912

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.

参考文献

[1] 吕东祯. 基于差分建模分析的锂离子电池寿命预测方法研究[D]. 武汉:华中科技大学, 2023. LÜ Dongzhen. Research on lithium-ion battery life prediction method based on differential modeling analysis[D]. Wuhan: Huazhong University of Science and Technology, 2023.
[2] ZIO Enrico. Prognostics and health management (PHM): Where are we and where do we (need to) go in theory and practice[J]. Reliability Engineering and System Safety, 2022, 218: 108119.
[3] LYU Dongzhen, ZHANG Bin, ZIO Enrico, et al. The explainable uncertainty in degradation process : A discovery from non-accelerated batteries degradation experiment[C]// 48th Annual Conference of the IEEE Industrial Electronics Society, 2022, Brussels, Belgium: IEEE, 2022: 1-6.
[4] LYU Dongzhen, ZHANG Bin, LIU Enhui, et al. Prognosisenabled battery SOC estimation using a closed-loop approach with consideration of SOH degradation[J]. Journal of Energy Storage, 2025, 110: 113713.
[5] ZHANG Jinrui, LYU Dongzhen, XIANG Jiawei. A model-data-fusion method for real-time continuous remaining useful life prediction of lithium batteries[J]. Measurement, 2024, 238: 115312.
[6] 庞哲楠,裴洪,李天梅. 考虑不完美维修的随机退化设备剩余寿命自适应预测方法[J]. 机械工程学报, 2023, 59(2): 14-29. PANG Zhenan , PEI Hong , LI Tianmei. Adaptive prediction method for remaining useful life of stochastic degradation equipment considering imperfect maintenance[J]. Journal of Mechanical Engineering, 2023, 59(2): 14-29.
[7] LI Penghua, ZHANG Zijian, XIONG Qingyu, et al. State-of-health estimation and remaining useful life prediction for the lithium-ion battery based on a variant long short term memory neural network[J]. Journal of Power Sources, 2020, 459: 228069.
[8] ZHAO Fuqiong, TIAN Zhigang, ZENG Yong. Uncertainty quantification in gear remaining useful life prediction through an integrated prognostics method[J]. IEEE Transactions on Reliability, 2013, 62(1): 146-159.
[9] SEVERSON KRISTEN A, ATTIA PETER M, JIN NORMAN, et al. Data-driven prediction of battery cycle life before capacity degradation[J]. Nature Energy, 2019, 4(5): 383-391.
[10] ATTIA PETER M , GROVER A , JIN N , et al. Closed-loop optimization of fast-charging protocols for batteries with machine learning[J]. Nature , 2020 , 578(7795): 397-402.
[11] ROMAN D, SAXENA S, ROBU V, et al. Machine learning pipeline for battery state-of-health estimation[J]. Nature Machine Intelligence, 2021, 3(5): 447-456.
[12] LU Jiahuan, XIONG Rui, TIAN Jinpeng, et al. Battery degradation prediction against uncertain future conditions with recurrent neural network enabled deep learning[J]. Energy Storage Materials, 2022, 50: 139-151.
[13] LÜ Nawei, JIN Yang, XIONG Rui, et al. Real-time overcharge warning and early thermal runaway prediction of li-ion battery by online impedance measurement[J]. IEEE Transactions on Industrial Electronics, 2022, 69(2): 1929-1936.
[14] 何晋,马睿飞,蔡琦琳,等. 基于递推最小二乘法的锂电池内短路全寿命周期辨识[J]. 机械工程学报, 2022, 58(17): 96-104. HE Jin, MA Ruifei, CAI Qilin, et al. Identification of lithium battery internal short circuit over the full life cycle based on recursive least squares method[J]. Journal of Mechanical Engineering, 2022, 58(17): 96-104.
[15] TIAN Jiaqiang, LIU Xinghua, LI Siqi, et al. Lithium-ion battery health estimation with real-world data for electric vehicles[J]. Energy, 2023, 270: 126855.
[16] 孙誉宁,毛磊,黄伟国,等. 基于磁场的质子交换膜燃料电池故障诊断方法[J]. 机械工程学报, 2022, 58(22): 106-114. SUN Yuning, MAO Lei, HUANG Weiguo, et al. Fault diagnosis method for proton exchange membrane fuel cells based on magnetic field[J]. Journal of Mechanical Engineering, 2022, 58(22): 106-114.
[17] THELEN A, LUI Yuhui, SHEN Sheng, et al. Integrating physics-based modeling and machine learning for degradation diagnostics of lithium-ion batteries[J]. Energy Storage Materials, 2022, 50: 668-695.
[18] SAXENA S, WARD L, KUBAL J, et al. A convolutional neural network model for battery capacity fade curve prediction using early life data[J]. Journal of Power Sources, 2022, 542: 231736.
[19] LI Tingkai, ZHOU Zihao, THELEN A, et al. Predicting battery lifetime under varying usage conditions from early aging data[J]. Cell Reports Physical Science, 2024, 5(4): 101891.
[20] YAN Wuzhao, ZHANG Bin, DOU Wanchun, et al. Low-cost adaptive lebesgue sampling particle filtering approach for real-time Li-Ion battery diagnosis and prognosis[J]. IEEE Transactions on Automation Science and Engineering, 2017, 14(4): 1601-1611.
[21] ZHANG Heng, NIU Guangxing, ZHANG Bin, et al. Cost-effective lebesgue sampling long short-term memory networks for Lithium-Ion batteries diagnosis and prognosis[J]. IEEE Transactions on Industrial Electronics, 2022, 69(2): 1958-1967.
[22] LYU Dongzhen, NIU Guangxing, LIU Enhui, et al. Time space modelling for fault diagnosis and prognosis with uncertainty management: A general theoretical formulation[J]. Reliability Engineering and System Safety, 2022, 226: 108686.
[23] LYU Dongzhen, NIU Guangxing, ZHANG Bin, et al. Lebesgue-time-space-model-based diagnosis and prognosis for multiple mode systems[J]. IEEE Transactions on Industrial Electronics, 2021, 68(2): 1591-1603.
[24] LIU Enhui, NIU Guangxing, LYU Dongzhen, et al. Low-cost adaptive LS-DEKF for SOC estimation and RDT prediction with SFP model[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-9.
[25] LIU Enhui, WANG Xuan, NIU Guangxing, et al. Uncertainty management in lebesgue-sampling-based LiIon Battery SFP model for SOC estimation and RDT prediction[J]. IEEE/ASME Transactions on Mechatronics, 2023, 28(2): 611-620.
[26] LIU Enhui, WANG Xuan, NIU Guangxing, et al. Lebesgue sampling-based li-ion battery simplified first principle model for SOC estimation and RDT prediction[J]. IEEE Transactions on Industrial Electronics, 2022, 69(9): 9524-9534.
[27] SONG Yuchen, PENG Yu, LIU Datong. Model-based health diagnosis for lithium-ion battery pack in space applications[J]. IEEE Transactions on Industrial Electronics, 2021, 68(12): 12375-12384.
[28] KONG Jinzhen, LIU Jie, ZHU Jingzhe, et al. Review on lithium-ion battery PHM from the perspective of key PHM steps[J]. Chinese Journal of Mechanical Engineering, 2024, 37(1): 71.
[29] KONG Jinzhen, YANG Fangfang, ZHANG Xi, et al. Voltage-temperature health feature extraction to improve prognostics and health management of lithium-ion batteries[J]. Energy, 2021, 223: 120114.
[30] ZHANG Chaolong, ZHAO Shaishai, HE Yigang. An integrated method of the future capacity and RUL prediction for Lithium-Ion battery pack[J]. IEEE Transactions on Vehicular Technology, 2022, 71(3): 2601-2613.
[31] HU Xiaosong, CHE Yunhong, LIN Xianke, et al. Health prognosis for electric vehicle battery packs: A data-driven approach[J]. IEEE/ASME Transactions on Mechatronics, 2020, 25(6): 2622-2632.
[32] 吕东祯,崔跃芹. 一种基于累计耗损量的充电电池寿命预测方法和装置: 中国, CN114460484B[P]. 2024-01-09. LYU Dongzhen, CUI Yueqin. A method and device for lifetime prognosis of rechargeable batteries based on cumulative consumption indicators: China, CN114460484 B[P]. 2024-01-09
[33] 吕东祯,崔跃芹. 一种考虑运行工况的充电电池累计损耗寿命预测方法、装置、电子设备及可读存储介质:中国, CN114444370B[P]. 2023-10-10. LÜ Dongzhen, CUI Yueqin. A method, device, electronic equipment, and computer-readable storage medium for cumulative lifetime prognosis of rechargeable batteries considering operational conditions: China, CN114444370 B[P]. 2023-10-10.
[34] 吕东祯,崔跃芹. 一种采用复合寿命指标的充电电池寿命预测方法、装置、电子设备及可读存储介质:中国, CN116774081B[P]. 2024-02-09. LÜ Dongzhen, CUI Yueqin. A method, device, electronic equipment, and computer-readable storage medium for lifetime prognosis of rechargeable batteries using composite lifetime indicators: China, CN116774081 B[J]. 2024-02-09.
[35] CUI Yueqin, LYU Dongzhen. Procédé et appareil de prédiction de durée de vie de batterie rechargeable basée sur la consommation cumulée, dispositif électronique et support de stockage lisible: PCT, Wo2023284453 a1[P]. 2023-01-19. CUI Yueqin , LYU Dongzhen. Cumulative consumption-based rechargeable battery life prediction method and apparatus, electronic device, and readable storage medium: PCT, Wo2023284453a1[P]. 2023-01-19.
[36] LYU Dongzhen, CUI Yueqin. Method, device, electronic equipment and computer-readable storage medium for lifetime prognosis of rechargeable-battery based on cumulative-consumption-indicators: United States, US 20240054269[P]. 2024-02-15.
[37] LYU Dongzhen, ZHANG Bin, ZIO Enrico, et al. Battery cumulative lifetime prognostics to bridge laboratory and real-life scenarios[J]. Cell Reports Physical Science, 2024, 5(9): 102164.
[38] LYU Dongzhen, LIU Enhui, CHEN Huiling, et al. Transfer-driven prognosis from battery cells to packs: An application with adaptive differential model decomposition[J]. Applied Energy, 2025, 377: 124290.
[39] LYU Dongzhen, NIU Guangxing, LIU Enhui, et al. Uncertainty management and differential model decomposition for fault diagnosis and prognosis[J]. IEEE Transactions on Industrial Electronics, 2022, 69(5): 5235-5246.