基于孤立森林算法的锂离子电池微内短路故障诊断方法

doi:10.19799/j.cnki.2095-4239.2024.0509

储能科学与技术 ›› 2024, Vol. 13 ›› Issue (11): 4102-4112.doi: 10.19799/j.cnki.2095-4239.2024.0509

基于孤立森林算法的锂离子电池微内短路故障诊断方法

郭煜¹^,²^,³^,⁴(), 王亦伟¹^,³^,⁴, 彭鹏¹^,³^,⁴, 王银飞¹^,³^,⁴^,⁵, 丘意书¹^,³^,⁴(), 蒋方明¹^,³^,⁴()

^1.中国科学院广州能源研究所，广东广州 510640
^2.东风汽车集团有限公司研发总院，湖北武汉 430056
^3.中国科学院可再生能源重点实验室
^4.广东省新能源和可再生能源研究开发与应用重点实验室，广东广州 510640
^5.沈阳化工大学机械与动力工程学院，辽宁沈阳 110142

收稿日期:2024-06-06 修回日期:2024-08-07 出版日期:2024-11-28 发布日期:2024-11-27
通讯作者: 丘意书,蒋方明 E-mail:shiyanguo@mail.ustc.edu.cn;qiuys@ms.giec.ac.cn;jiangfm@ms.giec.ac.cn
作者简介:郭煜（1999—），男，硕士研究生，研究方向为锂离子电池故障诊断与电池热管理，E-mail：shiyanguo@mail.ustc.edu.cn；
基金资助:
广州市科技计划(202201010418)

Fault diagnosis of micro-internal short circuits in lithium-ion battery using the isolated forest algorithm

Yu GUO¹^,²^,³^,⁴(), Yiwei WANG¹^,³^,⁴, Peng PENG¹^,³^,⁴, Yinfei WANG¹^,³^,⁴^,⁵, Yishu QIU¹^,³^,⁴(), Fangming JIANG¹^,³^,⁴()

^1.Guangzhou Institute of Energy Conversion, Chinese Academy of Sciences, Guangzhou 510640, Guangdong, China
^2.Dongfeng Motor Corporation Research and Development Institute, Wuhan 430056, Hubei, China
^3.CAS Key Laboratory of Renewable Energy
^4.Guangdong Provincial Key Laboratory of New and Renewable Energy Research and Development, Guangzhou 510640, Guangdong, China
^4.School of Mechanical and Power Engineering, Shenyang University of Chemical Technology, Shenyang 110142, Liaoning, China

Received:2024-06-06 Revised:2024-08-07 Online:2024-11-28 Published:2024-11-27
Contact: Yishu QIU, Fangming JIANG E-mail:shiyanguo@mail.ustc.edu.cn;qiuys@ms.giec.ac.cn;jiangfm@ms.giec.ac.cn

摘要/Abstract

摘要：

电池系统的内短路故障是造成电池热失控和火灾事故的主要原因之一，因此有必要对电池内短路故障进行诊断对事故做出早期预警。孤立森林算法是一种无监督的异常检测算法，被广泛应用于异常数据识别领域。根据串联电池组中内短路电池的电压会与正常电池发生偏离的特点，本文提出了基于孤立森林算法的锂离子电池微内短路故障诊断方法。为了对方法进行验证，本文构建了串联电池组进行了不同短路电阻和充放电工况的短路实验，并在实际运行工况下对一个锂离子电池储能系统进行了电池短路实验，然后利用孤立森林算法对实验数据进行分析诊断。结果表明，对于循环充放电工况，孤立森林算法对短路电阻为1000 Ω的短路故障诊断精准率超过了74%，召回率超过了76%，准确率超过了91%；在模拟电动汽车实际驾驶的动态工况中，算法对300 Ω的短路故障诊断精准率和召回率超过了86%，准确率超过了95%；算法对电池储能系统在实际运行工况下25 Ω的内短路故障检测召回率大于98%。实验结果表明，孤立森林算法可以在多种工况下对锂离子电池微内短路故障进行有效检测，被检测出的锂离子电池内短路电阻达到了千欧姆数量级。

关键词: 锂离子电池, 孤立森林算法, 微内短路故障, 电池储能系统

Abstract:

Internal short-circuit (ISC) faults in lithium-ion battery (LIB) systems are major contributors to thermal runaway and fire incidents. Diagnosing ISC faults is crucial for early warning of potential accidents and ensuring the safe operation of LIB systems. The isolated forest algorithm, an unsupervised anomaly detection method, is widely utilized in identifying anomalous data. Leveraging the characteristic voltage deviation of ISC-affected LIBs within a series-connected LIB pack, this study proposes an ISC fault diagnosis method based on the isolated forest algorithm. To validate the proposed method, a series-connected LIB module was constructed to perform ISC experiments under various short-circuit resistance conditions. ISC experiments were also conducted in an echelon-utilized LIB energy storage system (ESS) under real-world operating conditions. The isolated forest algorithm was then applied to analyze the experimental data. Results indicate that, under cyclic charging and discharging conditions, the algorithm achieved an accuracy rate of over 74%, a recall rate exceeding 76%, and a precision rate above 91% for a 1000 Ω ISC fault. For dynamic driving conditions of electric vehicles, the algorithm demonstrated an accuracy rate above 86% and a recall rate over 95% for a 300 Ω ISC fault. In the ESS's actual operating conditions, the recall rate for detecting a 25 Ω ISC fault exceeded 98%. The experimental outcomes confirm that the isolated forest algorithm effectively detects micro-ISC faults in LIBs across various operational scenarios, with detected ISC resistance reaching the magnitude of thousands of ohms.

Key words: lithium-ion batteries, isolation forest algorithm, micro internal short circuit fault, energy storage system

中图分类号:

TM 912

郭煜, 王亦伟, 彭鹏, 王银飞, 丘意书, 蒋方明. 基于孤立森林算法的锂离子电池微内短路故障诊断方法[J]. 储能科学与技术, 2024, 13(11): 4102-4112.

Yu GUO, Yiwei WANG, Peng PENG, Yinfei WANG, Yishu QIU, Fangming JIANG. Fault diagnosis of micro-internal short circuits in lithium-ion battery using the isolated forest algorithm[J]. Energy Storage Science and Technology, 2024, 13(11): 4102-4112.

图/表 17

图1

图　2

表 1

图3

图 4

图 5

图 6

图 7

图 8

表2

图 9

图 10

图 11

图 12

图 13

表3

表4

参考文献 18

1	MOY K, LEE S B, HARRIS S, et al. Design and validation of synthetic duty cycles for grid energy storage dispatch using lithium-ion batteries[J]. Advances in Applied Energy, 2021, 4: 100065. DOI: 10.1016/j.adapen.2021.100065.
2	ZHAO G L, BAKER J. Effects on environmental impacts of introducing electric vehicle batteries as storage - A case study of the United Kingdom[J]. Energy Strategy Reviews, 2022, 40: 100819. DOI: 10.1016/j.esr.2022.100819.
3	HU X J, GAO F F, XIAO Y, et al. Advancements in the safety of Lithium-Ion Battery: The Trigger, consequence and mitigation method of thermal runaway[J]. Chemical Engineering Journal, 2024, 481: 148450. DOI: 10.1016/j.cej.2023.148450.
4	ZHOU G, NIU C X, KONG Y, et al. Research on stimulation responsive electrolytes from the perspective of thermal runaway in lithium-ion batteries: A review[J]. Fuel, 2024, 368: 131599. DOI: 10.1016/j.fuel.2024.131599.
5	WU X G, WEI Z X, WEN T, et al. Research on short-circuit fault-diagnosis strategy of lithium-ion battery in an energy-storage system based on voltage cosine similarity[J]. Journal of Energy Storage, 2023, 71: 108012. DOI: 10.1016/j.est.2023.108012.
6	OUYANG M G, ZHANG M X, FENG X N, et al. Internal short circuit detection for battery pack using equivalent parameter and consistency method[J]. Journal of Power Sources, 2015, 294: 272-283. DOI: 10.1016/j.jpowsour.2015.06.087.
7	LAI X, JIN C Y, YI W, et al. Mechanism, modeling, detection, and prevention of the internal short circuit in lithium-ion batteries: Recent advances and perspectives[J]. Energy Storage Materials, 2021, 35: 470-499. DOI: 10.1016/j.ensm.2020.11.026.
8	FENG X N, OUYANG M G, LIU X, et al. Thermal runaway mechanism of lithium ion battery for electric vehicles: A review[J]. Energy Storage Materials, 2018, 10: 246-267. DOI: 10.1016/j.ensm.2017.05.013.
9	LIU F T, TING K M, ZHOU Z H. Isolation forest[C]//2008 Eighth IEEE International Conference on Data Mining. December 15-19, 2008, Pisa, Italy. IEEE, 2008: 413-422. DOI: 10.1109/ICDM. 2008.17.
10	LIU T, ZHOU Z, YANG L J. Layered isolation forest: A multi-level subspace algorithm for improving isolation forest[J]. Neurocomputing, 2024, 581: 127525. DOI: 10.1016/j.neucom. 2024.127525.
11	程贤福, 马晓冬, 曾建邦, 等. 基于孤立森林算法的动力电池不一致单体识别与预警方法[J]. 华东交通大学学报, 2023, 40(2): 95-102. DOI: 10.16749/j.cnki.jecjtu.2023.02.002.
	CHENG X F, MA X D, ZENG J B, et al. Inconsistent monomer identification and warning method for power batteries based on isolated forests[J]. Journal of East China Jiaotong University, 2023, 40(2): 95-102. DOI: 10.16749/j.cnki.jecjtu.2023.02.002.
12	JIANG J C, LI T Y, CHANG C, et al. Fault diagnosis method for lithium-ion batteries in electric vehicles based on isolated forest algorithm[J]. Journal of Energy Storage, 2022, 50: 104177. DOI: 10.1016/j.est.2022.104177.
13	杨双齐. 基于机器学习的舰船轮机设备多发故障信号监测[J]. 舰船科学技术, 2023, 45(16): 100-103. DOI: 10.3404/j.issn.1672-7649.2023.16.020.
	YANG S Q. Machine learning based monitoring of multiple fault signals in marine engine equipment[J]. Ship Science and Technology, 2023, 45(16): 100-103. DOI: 10.3404/j.issn.1672-7649.2023.16.020.
14	PEDREGOSA F, VAROQUAUX G, GRAMFORT A, et al. Scikit-learn: Machine learning in python[J]. Journal of Machine Learning Research, 2011, 12: 2825-2830. DOI: 10.48550/arXiv.1201.0490.
15	郗婕, 傅微. 基于机器学习的流域尺度森林火灾灾害风险预测[J]. 自然灾害学报, 2024, 33(1): 89-98. DOI: 10.13577/j.jnd.2024.0108.
	XI J, FU W. Watershed-scale forest fire risk prediction based on machine learning[J]. Journal of Natural Disasters, 2024, 33(1): 89-98. DOI: 10.13577/j.jnd.2024.0108.
16	QIAO D D, WANG X Y, LAI X, et al. Online quantitative diagnosis of internal short circuit for lithium-ion batteries using incremental capacity method[J]. Energy, 2022, 243: 123082. DOI: 10.1016/j.energy.2021.123082.
17	MA M N, DUAN Q L, LI X Y, et al. Fault diagnosis of external soft-short circuit for series connected lithium-ion battery pack based on modified dual extended Kalman filter[J]. Journal of Energy Storage, 2021, 41: 102902. DOI: 10.1016/j.est.2021.102902.
18	王君瑞, 吴新举, 赵东琦, 等. 基于 WOA-VMD 与 PSO-SVM 的锂离子电池内短路故障诊断方法[J]. 工程科学学报, 2023, 45(12): 2162-2172. DOI:10.13374/j.issn2095-9389.2022.10.04.004.
	WANG J R,WU X J,ZHAO D Q, et al. Research on internal short-circuit fault diagnosis methods for lithium-ion batteries based on WOA-VMD and PSO-SVM[J]. Chinese Journal of Engineering, 2023, 45(12): 2162-2172. DOI:10.13374/j.issn2095-9389. 2022. 10.04.004.

实际数据情况	算法检测结果
实际数据情况	异常	正常
异常	TP	FN
正常	FP	TN

电池序号(在第2簇中)	R_isc/Ω	故障电池位置
77	25	第2簇7号模块5号电池
80	100	第2簇7号模块8号电池
89	500	第2簇8号模块5号电池

工况	短路阻值	精准率	召回率	准确率
循环充放电工况	R_isc=300 Ω	0.9583	0.9547	0.9855
	R_isc=510 Ω	0.9151	0.9151	0.9717
	R_isc=710 Ω	0.8634	0.8603	0.9540
	R_isc=1000 Ω	0.7490	0.7608	0.9176
	R_isc=2000 Ω	0.5676	0.5787	0.8563
	R_isc=3000 Ω	0.4205	0.4370	0.8058
	R_isc=4000 Ω	0.0996	0.1055	0.6921

DST工况	R_isc=100 Ω	1	1	1
DST工况	R_isc=300 Ω	0.8671	0.8671	0.9557

数据日期	召回率
数据日期	R_isc=25 Ω	R_isc=100 Ω
2021-12-23	0.9966	0.2075
2021-12-27	0.9898	0.6052

[1]	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.
[2]	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.
[3]	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.
[4]	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.
[5]	陈媛, 章思源, 蔡宇晶, 黄小贺, 刘炎忠. 融合多项式特征扩展与CNN-Transformer模型的锂电池SOH估计[J]. 储能科学与技术, 2024, 13(9): 2995-3005.
[6]	邢瑞鹤, 翁素婷, 李叶晶, 张佳怡, 张浩, 王雪锋. AI辅助电池材料表征与数据分析[J]. 储能科学与技术, 2024, 13(9): 2839-2863.
[7]	何宁, 杨芳芳. 考虑能量和温度特征的锂离子电池早期寿命预测[J]. 储能科学与技术, 2024, 13(9): 3016-3029.
[8]	管鸿盛, 钱诚, 孙博, 任羿. 贫数据条件下锂离子电池容量退化轨迹预测方法[J]. 储能科学与技术, 2024, 13(9): 3084-3093.
[9]	柯学, 洪华伟, 郑鹏, 李智诚, 范培潇, 杨军, 郭宇铮, 蒯春光. 基于多时间尺度建模自动特征提取和通道注意力机制的锂离子电池健康状态估计[J]. 储能科学与技术, 2024, 13(9): 3059-3071.
[10]	田成文, 孙丙香, 赵鑫泽, 付智城, 马仕昌, 赵博, 张旭博. 基于数据驱动的锂离子电池快速寿命预测[J]. 储能科学与技术, 2024, 13(9): 3103-3111.
[11]	李清波, 张懋慧, 罗英, 吕桃林, 解晶莹. 基于等效电路模型融合电化学原理的锂离子电池荷电状态估计[J]. 储能科学与技术, 2024, 13(9): 3072-3083.
[12]	何智峰, 陶远哲, 胡泳钢, 王其聪, 杨勇. 机器学习强化的电化学阻抗谱技术及其在锂离子电池研究中的应用[J]. 储能科学与技术, 2024, 13(9): 2933-2951.
[13]	孙丙香, 杨鑫, 周兴振, 马仕昌, 王志豪, 张维戈. 基于简化阻抗模型和比较元启发式算法的锂离子电池参数辨识方法[J]. 储能科学与技术, 2024, 13(9): 2952-2962.
[14]	黄煜峰, 梁焕超, 许磊. 基于卡尔曼滤波算法优化Transformer模型的锂离子电池健康状态预测方法[J]. 储能科学与技术, 2024, 13(8): 2791-2802.
[15]	王志勇, 蔡君瑶, 佘英奇, 钟树林, 潘康华. 氮杂环导电高分子改性锂离子电池石墨负极材料[J]. 储能科学与技术, 2024, 13(8): 2511-2518.

基于孤立森林算法的锂离子电池微内短路故障诊断方法

Fault diagnosis of micro-internal short circuits in lithium-ion battery using the isolated forest algorithm

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 17

参考文献 18

相关文章 15

编辑推荐

Metrics

本文评价