基于迁移学习的锂电池不可逆析锂监测方法

doi:10.19799/j.cnki.2095-4239.2025.0049

摘要/Abstract

摘要：

析锂是引发储能锂离子电池内短路故障的重要原因之一，对析锂过程的在线监测是当前保障电池安全的主流研究方向。然而在工程应用中，现有方法局限于对可逆析锂的监测，并且由于缺乏电池的析锂数据，基于机器学习的在线监测算法存在模型训练上的困难。为解决这些问题，本工作提出了一种基于无监督领域自适应迁移学习的不可逆析锂监测方法。首先通过基于锂离子电池电化学-热-老化耦合模型的仿真和锂离子电池低温析锂老化实验生成不可逆析锂监测模型的源域数据和目标域数据，然后从放电曲线中提取析锂数据特征，在无监督领域自适应迁移学习的框架下构建了基于多层感知机的不可逆析锂监测模型，最后实现了将电池不可逆析锂监测模型从源域数据到目标域数据的迁移。结果表明，对于仿真数据，算法对是否发生不可逆析锂的判断准确率超过99%，对于实验数据，算法对电池不可逆析理的定性判断与实际情况相符，说明本工作提出的方法能够有效监测电池的不可逆析锂，为储能锂离子电池不可逆析锂的在线监测方法提供了新思路。

关键词: 锂离子电池, 析锂监测, 伪二维模型, 多层感知机, 迁移学习

Abstract:

Lithium plating is one of the main causes of internal short-circuit failures in energy storage lithium-ion batteries, and online monitoring of the lithium plating process is a key research direction for ensuring battery safety. However, in engineering applications, existing methods are limited to monitoring reversible lithium plating, and machine learning-based online monitoring algorithms face challenges in model training due to the lack of lithium plating data from actual batteries. To address these issues, this work proposes a monitoring method for irreversible lithium plating based on unsupervised domain adaptive transfer learning. The source and target domain data for the irreversible lithium plating monitoring model are generated through simulation using an electrochemical-thermal-aging model and low-temperature lithium plating aging experiments. Features related to lithium plating are extracted from discharge curves, and an irreversible lithium plating monitoring model based on multilayer perceptron is developed within the framework of unsupervised domain adaptive transfer learning. This allows for the transfer of the irreversible lithium plating monitoring model from the source domain data to the target domain data. The results show that for simulated data, the algorithm achieves an accuracy rate exceeding 99% in determining the occurrence of irreversible lithium plating. For experimental data, the qualitative judgements of the algorithm on the irreversible lithium plating are consistent with the actual conditions. This demonstrates that the proposed method can effectively monitor irreversible lithium plating in batteries and provides a new approach for the online monitoring of irreversible lithium plating in energy storage lithium-ion batteries.

Key words: Lithium-ion batteries, Lithium plating monitoring, Pseudo two-dimensional model, Multilayer perceptron, Transfer learning

中图分类号:

TM 911

王薇, 梁惠施, 李棉刚, 周奎, 王薇, 王姿尧, 史梓男. 基于迁移学习的锂电池不可逆析锂监测方法[J]. 储能科学与技术, doi: 10.19799/j.cnki.2095-4239.2025.0049.

Wei WANG, Huishi LIANG, Miangang LI, Kui ZHOU, Wei WANG, Ziyao WANG, Zinan SHI. The Monitoring Method of Irreversible Lithium Plating in Lithium Batteries Based on Transfer Learning[J]. Energy Storage Science and Technology, doi: 10.19799/j.cnki.2095-4239.2025.0049.

图/表 13

图1

表1

图2

表2

表3

图3

图4

图5

图6

图7

表4

图8

图9

参考文献 22

1	樊亚平,晏莉琴,简德超,等.锂离子电池失效中析锂现象的原位检测方法综述[J].储能科学与技术,2019,8(06):1040-1049.
	FAN Yaping, YAN Liqin, JIAN Dechao, et al. In situ detection of lithium dendrite in the failure of lithium-ion batteries[J]. Energy Storage Science and Technology,2019,8(06):1040-1049.
2	LIN Xianke, KHOSRAVINIA Kavian, HU Xiaosong, et al. Lithium Plating Mechanism, Detection, and Mitigation in Lithium-Ion Batteries[J]. Progress in Energy and Combustion Science,2021,87:100953.
3	STEIGER J, KRAMER D, MOENIG R. Microscopic observations of the formation, growth and shrinkage of lithium moss during electrodeposition and dissolution[J]. Electrochimica Acta, 2014, 136: 529-536.
4	CHENG J, ASSEGIE A, HUANG C, et al. Visualization of Lithium Plating and Stripping via in Operando Transmission X-ray Microscopy[J]. Journal of Physical Chemistry C, 2017, 121(14): 7761-7766.
5	BOMMIER C, CHANG W, LU Y, et al. In Operando Acoustic Detection of Lithium Metal Plating in Commercial LiCoO2/Graphite Pouch Cells[J]. Cell Reports Physical Science, 2020, 1(4): 100035.
6	JUNG M J, BAKTIYAR A, LEE Y N, et al. Experimental Analysis for Fast Lithium Plating Detection in Voltage Relaxation Profile of Lithium-Ion Batteries[C]. IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society, 2023:1-6.
7	VENNAM G, TANIM T R, TODD J T, et al. Advancing Li-plating detection: Motivating a multi-signal correlation approach [J]. Journal of Energy Storage, 2024, 98: 112869.
8	CHEN Y, TORRES-CASTRO L, CHEN K H, et al. Operando detection of Li plating during fast charging of Li-ion batteries using incremental capacity analysis[J]. Journal of Power Sources, 2022, 539: 231601.
9	BURNS J, STEVENS D, DAHN J. In-Situ Detection of Lithium Plating Using High Precision Coulometry[J]. Journal of the Electrochemical Society, 2015, 162(6): A959-A964.
10	RANGARAJAN S, BARSUKOV Y, MUKHERJEE P. In operando signature and quantification of lithium plating[J]. Journal of Materials Chemistry A, 2019, 7(36): 20683-20695.
11	董鹏, 张剑波, 王震坡. 基于电化学阻抗谱的锂离子电池析锂检测方法[J]. 汽车安全与节能学报, 2021, 12(04): 570-579.
	DONG Peng, ZHANG Jianbo, WANG Zhenpo. Lithium plating identification based on electrochemical impedance spectra of lithium ion batteries[J]. Journal of Automotive Safety and Energy, 2021, 12(04): 570-579.
12	SUN J, LYU K, WANG R, et al. A multistage constant current charging optimization control strategy based on lithium plating fast detection[J]. Journal of Energy Storage, 2025, 109: 115189.
13	CHEN B R, KUNZ M R, TANIM T R, et al. A machine learning framework for early detection of lithium plating combining multiple physics-based electrochemical signatures[J]. Cell Reports Physical Science, 2021, 2(3): 100352.
14	CHEN B R, WALKER C M, KIM S, et al. Battery aging mode identification across NMC compositions and designs using machine learning[J]. Joule, 2022, 6(12): 2776-2793.
15	TIAN Y, LIN C, LI H, et al. Deep neural network-driven in-situ detection and quantification of lithium plating on anodes in commercial lithium-ion batteries[J]. Ecomat, 2023, 5(1): e11280.
16	WANG Han, SONG Yajie, SUN Xue, et al. Onboard in-situ warning and detection of Li plating for fast-charging batteries with deep learning[J]. Energy Storage Materials, 2024, 71: 103585.
17	DOYLE M, FULLER T, NEWMAN J. Modeling of Galvanostatic Charge and Discharge of the Lithium/Polymer/Insertion Cell[J]. Journal of the Electrochemical Society, 1993, 140(6): 1526-1533.
18	李超. 基于电化学-热耦合模型的析锂特性研究[D]. 江苏大学, 2022.
	LI Chao. Study on lithium plating characteristics based on electrochemical-thermal coupling model[D]. Jiangsu University, 2022.
19	KEIL Jonas, JOSSEN Andreas. Electrochemical Modeling of Linear and Nonlinear Aging of Lithium-Ion Cells[J]. Journal of the Electrochemical Society,2020,167:110535.
20	李义函,卢世刚,王晶,等.磷酸铁锂锂离子电池低温不可逆析锂及其对电池性能衰减的影响[J].储能科学与技术,2024,13(10):3656-3665.
	LI Yihan, LU Shigang, WANG Jing, et al. Effect of irreversible lithium plating at low temperature on the performance degradation of LiFePO4 lithium-ion batteries[J]. Energy Storage Science and Technology,2024,13(10):3656-3665.
21	GANIN Yaroslav, LEMPITSKY Victor. Unsupervised Domain Adaptation by Backpropagation[C]. Proceedings of Machine Learning Research,2015,37: 1180-1189.
22	HE Zhihai, YANG Bo, CHEN Chaoxian, et al. CLDA an adversarial unsupervised domain adaptation method with classifier-level adaptation[J]. Multimedia Tools and Applications,2020,79(45-46):33973–33991.

温度	充电倍率	放电倍率
-10℃、-5℃、0℃、10℃、25℃	2C	1C
-10℃、-5℃、0℃、10℃、25℃	1C	0.05C
-10℃、-5℃、0℃、10℃、25℃	2C	0.5C

组号	电池编号	温度	充电倍率	放电倍率
1	1-3	25℃	2C	1C
2	4-6	35℃	2C	1C
3	7-9	-11℃	0.2C	0.1C
4	10-12	-16℃	0.1C	0.05C

电池编号	温度	充电倍率	放电倍率	循环老化圈数	容量保持率	常温容量保持率
1	25℃	2C	1C	1000	72.99%	94.10%
2	25℃	2C	1C	1000	85.92%	97.29%
3	25℃	2C	1C	1000	85.12%	96.92%
4	35℃	2C	1C	1000	82.52%	94.28%
5	35℃	2C	1C	1000	83.82%	94.75%
6	35℃	2C	1C	1000	83.34%	92.31%
7	-11℃	0.2C	0.1C	83	53.41%	73.12%
8	-11℃	0.2C	0.1C	178	33.22%	65.83%
9	-11℃	0.2C	0.1C	182	38.75%	72.52%
10	-16℃	0.1C	0.05C	67	54.38%	63.98%
11	-16℃	0.1C	0.05C	76	60.65%	88.64%
12	-16℃	0.1C	0.05C	68	59.46%	84.10%

算法	准确率	精确率	召回率
SVM	98.31%	96.98%	96.98%
KNN	99.16%	99.13%	97.84%
MLP	99.28%	98.29%	99.14%

[1]	曹巍, 陈飞, 孔祥栋, 朱志成, 韩雪冰, 卢兰光, 郑岳久. 锂离子电池极片涂布工艺研究进展[J]. 储能科学与技术, 2025, 14(1): 90-103.
[2]	张建茹, 王其钰, 李庆浩, 张献英, 王碧童, 禹习谦, 李泓. 锂离子电池失效分析中的几种物性表征技术及其应用[J]. 储能科学与技术, 2025, 14(1): 286-309.
[3]	邢远秀, 刘颛玮, 邢玉峰, 王文波. BDD-DETR：高效感知小目标的锂电池表面缺陷检测[J]. 储能科学与技术, 2025, 14(1): 370-379.
[4]	李建萱, 林琛, 周忠凯. 基于减平均优化算法与双向长短期记忆网络的锂离子电池健康状态估算[J]. 储能科学与技术, 2025, 14(1): 358-369.
[5]	叶石丰, 洪朝锋, 綦晓, 吴伟雄, 谭子健, 周奇, 张兆阳. 基于EEMD-GRU-NN锂离子电池表面温度预测方法研究[J]. 储能科学与技术, 2025, 14(1): 380-387.
[6]	刘通, 杨瑰婷, 毕辉, 梅悦旎, 刘硕, 宫勇吉, 罗文雷. 高能量密度与高功率密度兼顾型锂离子电池研究现状与展望[J]. 储能科学与技术, 2025, 14(1): 54-76.
[7]	李可, 朱顺兵, 陶致格, 王赫. 复合水系灭火剂抑制磷酸铁锂电池火灾实验[J]. 储能科学与技术, 2025, 14(1): 140-151.
[8]	张文婧, 肖伟, 伊亚辉, 钱利勤. 锂离子电池安全改性策略研究进展[J]. 储能科学与技术, 2025, 14(1): 104-123.
[9]	刘勇, 于怀汶, 刘大鹏, 穆勇, 王瀛洲, 张秀宇. 基于ABC-LSTM模型的锂离子电池剩余使用寿命预测[J]. 储能科学与技术, 2025, 14(1): 331-345.
[10]	陈峥, 彭月, 胡竞元, 申江卫, 肖仁鑫, 夏雪磊. 基于短期充电数据和增强鲸鱼优化算法的锂离子电池容量预测[J]. 储能科学与技术, 2025, 14(1): 319-330.
[11]	梅悦旎, 屈雯洁, 程广玉, 向永贵, 陆海燕, 邵晓丹, 张益明, 王可. 锂离子电池正极补锂技术研究进展[J]. 储能科学与技术, 2025, 14(1): 77-89.
[12]	孙中麟, 李嘉波, 田迪, 王志璇, 邢晓静. 基于COA-LSTM和VMD的锂离子电池剩余寿命预测[J]. 储能科学与技术, 2024, 13(9): 3254-3265.
[13]	陆继忠, 彭思敏, 李晓宇. 基于多特征量分析和LSTM-XGBoost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.
[14]	胡雪峰, 常先雷, 刘肖肖, 徐威, 张文彬. 适用于宽温度范围的锂离子电池SOC估计方法[J]. 储能科学与技术, 2024, 13(9): 2983-2994.
[15]	沈思远, 刘亚坤, 罗栋煌, 李雨珺, 郝伟. 储能锂离子电池模组暂态过电压防护设计与电路研发[J]. 储能科学与技术, 2024, 13(9): 3277-3286.