融合聚类与分类的退役锂离子电池快速分选

doi:10.19562/j.chinasae.qcgc.2025.06.004

摘要/Abstract

摘要：

为提高退役电池分选效率并减少数据采集成本，本文旨在通过使用不完备数据来实现接近完备数据的分选效果，由此提出了一种融合聚类和分类的退役电池快速分选方法。首先通过完备数据进行聚类分析，对电池进行初步分组，将分组结果作为电池标签；其次从不完备数据集中挑选最有价值片段，训练双层分类模型进行分类拟合，从而实现退役锂离子电池的快速分选；最后对235块锂离子电池进行了验证实验。结果表明所提出的方法具有95.1%的分类检测精度，并且显著减少分选所需时间。

关键词: 锂离子电池, 退役电池, 电池分选, 聚类, 电化学阻抗谱

Abstract:

In order to improve the sorting efficiency of retired batteries and reduce data collection cost， to achieve a sorting effect close to complete data by using incomplete data， in this paper， a fast sorting method for retired batteries that integrates clustering and classification is proposed. Firstly， cluster analysis is conducted on complete data to preliminarily group the batteries， and the grouping results are used as battery labels. Secondly， the most valuable segments are selected from incomplete datasets， and a two-layer classification model is trained for classification fitting， thereby achieving rapid sorting of retired lithium-ion batteries. Finally， a validation experiment is conducted on 235 lithium-ion batteries， and the results show that the proposed method has a classification detection accuracy of 95.1% and significantly reduces the time required for sorting.

Key words: lithium-ion battery, retired batteries, battery sorting, clustering, electrochemical impedance spectroscopy

唐汉青,王丽,林名强,武骥. 融合聚类与分类的退役锂离子电池快速分选[J]. 汽车工程, 2025, 47(6): 1048-1059.

Hanqing Tang,Li Wang,Mingqiang Lin,Ji Wu. Rapid Sorting of Retired Lithium-Ion Batteries by Integrating Clustering and Classification[J]. Automotive Engineering, 2025, 47(6): 1048-1059.

图/表 16

表1

图1

图2

图3

图4

表2

图5

图6

表3

图7

图8

表 4

表5

图9

图10

表6

参考文献 28

1	LU L， HAN X， LI J， et al. A review on the key issues for lithium-ion battery management in electric vehicles［J/OL］. Journal of Power Sources， 2013， 226： 272-288.
2	JIANG Y， JIANG J， ZHANG C， et al. State of health estimation of second-life LiFePO₄ batteries for energy storage applications［J/OL］. Journal of Cleaner Production， 2018， 205： 754-762.
3	CUSENZA M A， GUARINO F， LONGO S， et al. Reuse of electric vehicle batteries in buildings： an integrated load match analysis and life cycle assessment approach［J/OL］. Energy and Buildings， 2019， 186： 339-354.
4	HUANG Z， XIE Z， ZHANG C， et al. Modeling and multi-objective optimization of a stand-alone PV-hydrogen-retired EV battery hybrid energy system［J/OL］. Energy Conversion and Management， 2019， 181： 80-92.
5	HUA Y， ZHOU S， HUANG Y， et al. Sustainable value chain of retired lithium-ion batteries for electric vehicles［J/OL］. Journal of Power Sources， 2020， 478： 228753.
6	NEUBAUER J， PESARAN A. The ability of battery second use strategies to impact plug-in electric vehicle prices and serve utility energy storage applications［J/OL］. Journal of Power Sources， 2011， 196（23）： 10351-10358.
7	LAI X， HUANG Y， GU H， et al. Turning waste into wealth： a systematic review on echelon utilization and material recycling of retired lithium-ion batteries［J/OL］. Energy Storage Materials， 2021， 40： 96-123.
8	XU Z， WANG J， LUND P D， et al. A novel clustering algorithm for grouping and cascade utilization of retired Li-ion batteries［J/OL］. Journal of Energy Storage， 2020， 29： 101303.
9	PENG S， SUN Y， LIU D， et al. State of health estimation of lithium-ion batteries based on multi-health features extraction and improved long short-term memory neural network ［J/OL］. Energy， 2023， 282： 128956.
10	LIN M， WU J， ZOU J， et al. Retired battery screening based on Markov transition field and swin transformer［J/OL］. IEEE Transactions on Transportation Electrification， 2024， 10（2）： 4217-4227.
11	陈琳，何熳平，吴淑孝，等. 基于自适应模糊C-均值算法的退役锂离子电池快速聚类［J］. 汽车工程， 2024， 46（4）： 643-651.
	CHEN L， HE M P， WU S X， et al. Fast clustering of retired lithium-ion batteries based on adaptive fuzzy C-means algorithm［J］. Automotive Engineering， 2024， 46（4）： 643-651.
12	LIU X， TANG Q， FENG Y， et al. Fast sorting method of retired batteries based on multi-feature extraction from partial charging segment［J/OL］. Applied Energy， 2023， 351： 121930.
13	来鑫，陈权威，邓聪，等. 一种基于电化学阻抗谱的大规模退役锂离子电池的软聚类方法［J］. 电工技术学报， 2022， 37（23）： 6054-6064.
	LAI X， CHEN Q W， DENG C， et al. A soft clustering method for the large-scale retired lithium-ion batteries based on electro‐ chemical impedance spectroscopy［J］. Transactions of China Electrotechnical Society， 2022， 37（23）：6054-6064.
14	范茂松，耿萌萌，赵光金，等. 基于多频点阻抗的梯次利用电池分选技术研究［J］. 储能科学与技术， 2023， 12（7）： 2202-2210.
	FAN M S， GENG M M， ZHAO G J， et al. Research on battery sorting technology for echelon utilization based onmultifrequency impedance［J］. Energy Storage Science and Technology，2023， 12 （7）： 2202-2210.
15	WANG Y， HUANG H， WANG H. Rapid-regroup strategy for retired batteries based on short-time dynamic voltage and electrochemical impedance spectroscopy［J/OL］. Journal of Energy Storage， 2023， 63： 107102.
16	CHOI W， SHIN H C， KIM J M， et al. Modeling and applications of electrochemical impedance spectroscopy （EIS） for lithium-ion batteries［J/OL］. Journal of Electrochemical Science and Technology， 2020， 11（1）： 1-13.
17	BARAI A， CHOUCHELAMANE G H， GUO Y， et al. A study on the impact of lithium-ion cell relaxation on electrochemical impedance spectroscopy ［J/OL］. Journal of Power Sources， 2015， 280： 74-80.
18	LOU F， CHEN D. Aligned carbon nanostructures based 3D electrodes for energy storage ［J/OL］. Journal of Energy Chemistry， 2015， 24（5）： 559-586.
19	ZHU J， DEWI DARMA M S， KNAPP M， et al. Investigation of lithium-ion battery degradation mechanisms by combining differential voltage analysis and alternating current impedance ［J/OL］. Journal of Power Sources， 2020， 448： 227575.
20	ECKER M， NIETO N， KÄBITZ S， et al. Calendar and cycle life study of Li（NiMnCo）O₂-based 18650 lithium-ion batteries Li（NiMnCo）O₂ ［J/OL］. Journal of Power Sources， 2014， 248： 839-851.
21	DUBARRY M， LIAW B Y. Identify capacity fading mechanism in a commercial LiFePO4 cell ［J/OL］. Journal of Power Sources， 2009， 194（1）： 541-549.
22	DOLLÉ M， GRUGEON S， BEAUDOIN B， et al. In situ TEM study of the interface carbon/electrolyte［J/OL］. Journal of Power Sources， 2001， 97-98： 104-106.
23	LEE S B， PYUN S I. The effect of electrolyte temperature on the passivity of solid electrolyte interphase formed on a graphite electrode［J/OL］. Carbon， 2002， 40（13）： 2333-2339.
24	刘万里，李子涵，梁宏毅，等.基于相似性优化模型样本的实车锂电池健康状态分析［J］. 汽车工程， 2024， 46（3）： 489-497.
	LIU W L， LI Z H， LIANG H Y， et al. Real vehicle battery health state estimation based on similarity optimization model samples［J］. Automotive Engineering， 2024， 46（3）： 489-497.
25	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.
26	LI Q， LU T， LAI C， et al. Lithium-ion battery capacity estimation based on fragment charging data using deep residual shrinkage networks and uncertainty evaluation ［J/OL］. Energy， 2024， 290： 130208.
27	ZHANG L， ZHANG J， GAO T， et al. Improved LSTM based state of health estimation using random segments of the charging curves for lithium-ion batteries［J/OL］. Journal of Energy Storage， 2023， 74： 109370.
28	TAN C W， DEMPSTER A， BERGMEIR C， et al. MultiRocket： multiple pooling operators and transformations for fast and effective time series classification［J/OL］. arXiv， 2022. http：//arxiv.org/abs/2102.00457.

标签	5簇
SC	0.545
CHI	379.45
DBI	0.593 3

模型	准确率	精确率	召回率	F1分数
CNN	0.875	0.607	0.7	0.632
GRU	0.906	0.679	0.833	0.724
SVM	0.937	0.469	0.5	0.483 8
Multirocket	0.984	0.8	1	0.889

模型	准确率	精确率	召回率	F1分数
Multirocket	0.95	0.970 1	0.854 2	0.898 9
CNN	0.867 2	0.726 7	0.724 7	0.736 3
GRU	0.867	0.924 6	0.659 7	0.694 2
SVM	0.6	0.15	0.25	0.187

模型	准确率	精确率	召回率	F1分数
双层分类	0.951 4	0.928	0.95	0.93
单次分类	0.843	0.833 33	0.698 3	0.711 2
CNN	0.765 6	0.646	0.547	0.547
GRU	0.75	0.583 3	0.638	0.594

模型	准确率	精确率	召回率	F1分数
充电数据	0.796 8	0.646 8	0.646 8	0.609 8
EIS数据	0.75	0.667	0.683	0.653
两种数据	0.951 4	0.928	0.95	0.93