基于SOM+SVM的退役锂离子电池分选

doi:10.19799/j.cnki.2095-4239.2022.0336

储能科学与技术 ›› 2022, Vol. 11 ›› Issue (11): 3623-3630.doi: 10.19799/j.cnki.2095-4239.2022.0336

基于SOM+SVM的退役锂离子电池分选

王鲁(), 王峰(), 徐竞, 赵延鹏, 李玮, 王艳艳, 王应彪

西南林业大学机械与交通学院，云南昆明 650224

收稿日期:2022-06-17 修回日期:2022-07-05 出版日期:2022-11-05 发布日期:2022-11-09
通讯作者: 王峰 E-mail:1105331851@qq.com;wangf@swfu.edu.cn
作者简介:王鲁（1996—），男，硕士研究生，研究方向为电力电子与电力传动，E-mail：1105331851@qq.com；
基金资助:
国家自然科学基金(52165038);云南省教育厅科学研究基金(2020J0417);西南林业大学科研启动基金(01102-111928)

Sorting of retired lithium-ion batteries based on SOM+SVM

Lu WANG(), Feng WANG(), Jing XU, Yanpeng ZHAO, Wei LI, Yanyan WANG, Yingbiao WANG

School of Machinery and Transportation, Southwest Forestry University, Kunming 650224, Yunnan, China

Received:2022-06-17 Revised:2022-07-05 Online:2022-11-05 Published:2022-11-09
Contact: Feng WANG E-mail:1105331851@qq.com;wangf@swfu.edu.cn

摘要/Abstract

摘要：

针对退役动力电池分选方法匮乏的问题，提出一种基于SOM(自组织特征映射网络)+SVM(支持向量机)的退役锂离子电池分选方法。对退役电池进行电池测试，通过电池测试系统记录电池的电流、电压、温度和放电容量的变化，进行电池PNGV(新一代汽车合作伙伴)模型参数辨识，并依据电池容量、等压降时间等特征参数与模型参数对电池进行多参数聚类与分选归类。将分选归类结果中的退役电池单体进行并联重组，进行一致性实验，并对实验结果进行比较分析。实验结果表明：该方法下的退役电池参数在经过重组循环运算后，极化内阻、剩余容量、等压降时间、温度转换速率一致性变化程度较小，欧姆内阻离散度明显减小，在退役电池分选工作中具有实际意义。

关键词: SOM神经网络, 支持向量机, PNGV模型, 退役电池, 电池分选

Abstract:

A retired lithium-ion battery-sorting approach based on SOM (self-organizing feature mapping network)+SVM (support vector machine) is proposed to address the shortage of sorting methods for retired power batteries. A battery test was performed on retired batteries. Battery test systems were used to record the changes in battery current, voltage, temperature, and discharge capacity. The battery PNGV (new generation automotive partner) model parameters were identified. Furthermore, the batteries were grouped and sorted according to the characteristics and model parameters, including battery capacity and constant voltage drop time. The retired battery cells in the sorting and classification results were reorganized in parallel, the consistency experiment was performed, and the experimental results were compared and analyzed. The results revealed that the consistency of polarization internal resistance, residual capacity, constant pressure drop time, and temperature conversion rate changed slightly after the recombination cycle operation of the retired battery parameters under this method, and the dispersion of internal ohmic resistance decreased significantly, which is of practical significance in the sorting of retired batteries.

Key words: SOM, SVM, PNGV model, retired battery, battery sorting

中图分类号:

TM 911.1

王鲁, 王峰, 徐竞, 赵延鹏, 李玮, 王艳艳, 王应彪. 基于SOM+SVM的退役锂离子电池分选[J]. 储能科学与技术, 2022, 11(11): 3623-3630.

Lu WANG, Feng WANG, Jing XU, Yanpeng ZHAO, Wei LI, Yanyan WANG, Yingbiao WANG. Sorting of retired lithium-ion batteries based on SOM+SVM[J]. Energy Storage Science and Technology, 2022, 11(11): 3623-3630.

图/表 14

图1

图2

图3

图4

图5

图6

表1

图7

图8

表2

图9

图10

表3

表4

参考文献 17

1	孟高军, 苏令, 孙玉坤, 等. 退役电池梯次利用的一致性管理研究综述[J]. 电源技术, 2021, 45(10): 1376-1379.
	MENG G J, SU L, SUN Y K, et al. Review on consistency management of echelon use of retired battery[J]. Chinese Journal of Power Sources, 2021, 45(10): 1376-1379.
2	李建林, 李雅欣, 吕超, 等. 退役动力电池梯次利用关键技术及现状分析[J]. 电力系统自动化, 2020, 44(13): 172-183.
	LI J L, LI Y X, LYU C, et al. Key technology and research status of cascaded utilization in decommissioned power battery[J]. Automation of Electric Power Systems, 2020, 44(13): 172-183.
3	王东梅, 冯伟峰, 白红燕, 等. 基于电压平台的电池聚类分选算法研究[J]. 电源技术, 2016, 40(5): 994-996, 1007.
	WANG D M, FENG W F, BAI H Y, et al. Research on clustering algorithm based on voltage platform for cells classification[J]. Chinese Journal of Power Sources, 2016, 40(5): 994-996, 1007.
4	FANG K Z, CHEN S, MU D B, et al. Investigation of nickel-metal hydride battery sorting based on charging thermal behavior[J]. Journal of Power Sources, 2013, 224: 120-124.
5	沈景凤, 瞿亚浩, 李富生. 一种基于PLC的新型锂离子电池分选机开发[J]. 电子科技, 2015, 28(12): 14-17, 21.
	SHEN J F, QU Y H, LI F S. A new lithium-ion battery separator based on PLC[J]. Electronic Science and Technology, 2015, 28(12): 14-17, 21.
6	ZHU Z W, ZHENGB Y J, LAI X, et al. A novel fast estimation and regroup method of retired lithium‐ion battery cells[J]. International Journal of Energy Research, 2020, 44(14): 11985-11997.
7	薛金花, 陶以彬, 杨波, 等. 基于老化机理分析退役磷酸铁锂电池分选方法[J]. 电源技术, 2020, 44(5): 660-665.
	XUE J H, TAO Y B, YANG B, et al. Screening method of retired LiFePO₄ batteries based on aging mechanism analysis[J]. Chinese Journal of Power Sources, 2020, 44(5): 660-665.
8	王焰辉, 黄志福, 林宇星, 等. 基于聚类分析算法的锂离子电芯一致性分选[J]. 电池, 2021, 51(3): 247-251.
	WANG Y H, HUANG Z F, LIN Y X, et al. Consistency sorting of Li-ion cell based on clustering analysis algorithm[J]. Battery Bimonthly, 2021, 51(3): 247-251.
9	郑岳久, 李家琦, 朱志伟, 等. 基于快速充电曲线的退役锂电池模块快速分选技术[J]. 电网技术, 2020, 44(5): 1664-1673.
	ZHENG Y J, LI J Q, ZHU Z W, et al. Rapid classification based on fast charging curves for reuse of retired lithium-ion battery modules[J]. Power System Technology, 2020, 44(5): 1664-1673.
10	KOHONEN T. Self-organized formation of topologically correct feature maps[J]. Biological Cybernetics, 1982, 43(1): 59-69.
11	胡乙丹, 姜吉祥, 董霞. 基于结合聚类与SVM参数寻优的短期电力负荷预测方法[J]. 电力信息与通信技术, 2022, 20(5): 54-60.
	HU Y D, JIANG J X, DONG X. A short-term power load forecasting method based on combining clustering and SVM parameter optimization[J]. Electric Power Information and Communication Technology, 2022, 20(5): 54-60.
12	INEEL, United States Idaho National Engineering & Environmental Laboratory. Freedom CAR battery test manual [M]. USA: INEEL, 2001: 6-30.
13	杨阳, 汤桃峰, 秦大同, 等. 电动汽车锂电池PNGV等效电路模型与SOC估算方法[J]. 系统仿真学报, 2012, 24(4): 938-942.
	YANG Y, TANG T F, QIN D T, et al. PNGV equivalent circuit model and SOC estimation algorithm of lithium batteries for electric vehicle[J]. Journal of System Simulation, 2012, 24(4): 938-942.
14	谌虹静. 锂离子动力电池剩余寿命预测与退役电池分选方法研究[D]. 南京: 东南大学, 2019.
	CHEN H J. Research on remaining useful life prediction of lithium-ion battery and screening method of recycling battery[D]. Nanjing: Southeast University, 2019.
15	黄保帅, 张巍. 基于单体一致性对动力锂电池性能的影响研究[J]. 电源技术, 2018, 42(9): 1310-1311, 1320.
	HUANG B S, ZHANG W. Influence of cell consistency on performance of power lithium battery[J]. Chinese Journal of Power Sources, 2018, 42(9): 1310-1311, 1320.
16	高洋. 三元材料锂离子电池老化诊断、评估与建模方法[D]. 北京: 北京交通大学, 2019.
	GAO Y. Aging diagnosis, evaluation and modeling method of ternary lithium ion battery[D]. Beijing: Beijing Jiaotong University, 2019.
17	张朝龙, 赵筛筛, 章博. 基于因子分析与K-means聚类的退役动力电池快速分选方法[J]. 电力系统保护与控制, 2021, 49(12): 41-47.
	ZHANG C L, ZHAO S S, ZHANG B. A fast classification method based on factor analysis and K-means clustering for retired electric vehicle batteries[J]. Power System Protection and Control, 2021, 49(12): 41-47.

参数	R₀₁/Ω	R₀₂/Ω	R₀₃/Ω	C_b1/F	C_b2/F	C_b3/F	R_a1/Ω	R_a2/Ω
数值	0.149～0.024	0.142～0.024	0.139～0.024	1.718～4.221	1.869～5.689	1.748～6.405	0.020～0.075	0.019～0.092
参数	R_a3/Ω	C_a1/F	C_a2/F	C_a3/F	C/Ah	t_D/s	T_R	C_a2/F
数值	0.021～0.126	13.04～1696.66	227.54～1483.42	147.16～1188.76	0.606～0.947	258～1511.9	0.00271～0.00691	227.54～1483.42

特征参数	R₀₁	R₀₂	R₀₃	R_a1	R_a2	R_a3	C	t_D	T_R
循环前离散度	0.195	0.186	0.157	0.182	0.190	0.117	0.480	0.202	0.112
循环后离散度	0.099	0.117	0.133	0.216	0.223	0.112	0.501	0.225	0.128

[1]	韦荣阳, 毛阗, 高晗, 彭建仁, 杨健. 基于TWP-SVR的锂离子电池健康状态估计[J]. 储能科学与技术, 2022, 11(8): 2585-2599.
[2]	耿萌萌, 范茂松, 杨凯, 赵光金, 谭震, 高飞, 张明杰. 基于EIS和神经网络的退役电池SOH快速估计[J]. 储能科学与技术, 2022, 11(2): 673-678.
[3]	刘雨洋, 王顺利, 谢滟馨, 吉伟康, 张一兴. 基于在线参数辨识和改进2RC-PNGV模型的锂离子电池建模与SOC估算研究[J]. 储能科学与技术, 2021, 10(6): 2312-2317.
[4]	杜帮华, 张宇, 吴铁洲, 何衍林, 李子龙. 梯次利用锂离子电池等效模型参数在线辨识方法[J]. 储能科学与技术, 2021, 10(1): 342-348.
[5]	解坤, 姜成龙, 吴亮璇, 常宏, 樊彬, 陈立铎, 温浩然. 基于退役电池梯次利用的源-储容量优化配置[J]. 储能科学与技术, 2020, 9(S1): 23-30.
[6]	成文晶, 潘庭龙. 基于分布估计算法LSSVM的锂电池SOC预测[J]. 储能科学与技术, 2020, 9(6): 1948-1953.
[7]	王语园, 李嘉波, 张福. 基于粒子群算法的最小二乘支持向量机电池状态估计[J]. 储能科学与技术, 2020, 9(4): 1153-1158.
[8]	李嘉波, 李忠玉, 焦生杰, 叶敏, 徐信芯. 基于反馈最小二乘支持向量机锂离子状态估计[J]. 储能科学与技术, 2020, 9(3): 951-957.
[9]	范茂松, 金翼, 杨凯, 高飞, 李相俊, 来小康. 退役LiFePO₄电池性能测评及储能应用[J]. 储能科学与技术, 2019, 8(2): 408-415.
[10]	刘坚. 电动汽车退役电池储能应用潜力及成本分析[J]. 储能科学与技术, 2017, 6(2): 243-249.

基于SOM+SVM的退役锂离子电池分选

Sorting of retired lithium-ion batteries based on SOM+SVM

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 17

相关文章 10

编辑推荐

Metrics

本文评价