面向变工况条件的锂离子电池寿命退化预测方法

doi:10.19799/j.cnki.2095-4239.2023.0233

摘要/Abstract

摘要：

准确地预测锂离子电池寿命退化对保障电动汽车及电化学储能系统的安全可靠运行具有重要意义。然而，面向变工况条件的锂离子电池寿命预测仍具有较大的挑战。本文提出了一种新型特征矩阵的建立方法以及基于深度卷积神经网络的电池寿命预测方法。首先，以容量衰减来定义电池寿命退化，根据变工况公开数据集的特点，结合历史容量信息、循环次数信息和工况信息建立了多维度特征参量矩阵。然后，以特征参量矩阵为输入，待预测电池容量为输出，构建了一步预测的映射关系。为获取该映射关系，采用了具有强非线性能力的深度学习方法，通过空洞卷积模块、残差模块和回归模块的叠加建立了空洞残差回归网络(dilated residual regression network，DRRN)。进一步地，在训练所构建的网络时使用贝叶斯优化(Bayesian optimization，BO)寻找最佳的超参数组合，使模型达到最优效果。实验结果表明，相比于目前常用于电池剩余寿命预测的粒子滤波算法和长短时记忆神经网络算法，所提方法至少可减少相对均方根误差42.8%，具有明显优势。在不同的预测起点下，证明了所提方法具有较鲁棒的预测能力。

关键词: 锂离子电池, 变工况条件, 寿命预测, 卷积神经网络, 贝叶斯优化

Abstract:

Accurately predicting the degradation of lithium-ion battery life is crucial to ensure the safe and reliable operation of electric vehicles and electrochemical energy storage systems. However, predicting the life of lithium-ion batteries under various operating conditions remains a major challenge. This article presents a novel approach to construct feature matrices and predict battery life using deep convolutional neural networks. First, battery life degradation is defined in terms of capacity decay. A multidimensional feature parametric matrix is then built based on the dataset's characteristics, including variable operating conditions. This matrix combines historical capacity information, cycle count information, and operating conditions information. Next, a one-step ahead mapping relationship is established using the feature parameter matrix as input and the battery capacity to be predicted as output. To achieve this mapping relationship, a deep learning method with strong nonlinear capability is employed. It builds a dilated residual regression network by combining a dilated convolution module, a residual module, and a regression module. Furthermore, Bayesian Optimization is used to train the proposed network and find the best combination of hyperparameters, ensuring the model's optimality. Experimental results demonstrate that the proposed method significantly enhances prediction accuracy compared to commonly used model- and data-driven methods for the battery life prediction. Moreover, the proposed method exhibits robust prediction capability across different prediction starting points.

Key words: lithium-ion battery, varied working conditions, lifetime prediction, convolutional neural network, bayesian optimalization

中图分类号:

TM 912.9

张宇波, 王有元, 黄洞宁, 王子懿, 陈伟根. 面向变工况条件的锂离子电池寿命退化预测方法[J]. 储能科学与技术, 2023, 12(7): 2238-2245.

Yubo ZHANG, Youyuan WANG, Dongning HUANG, Ziyi WANG, Weigen CHEN. Prognostic method of lithium-ion battery lifetime degradation under various working conditions[J]. Energy Storage Science and Technology, 2023, 12(7): 2238-2245.

图/表 6

图1

图2

表1

表2

图3

表3

参考文献 15

1	韩乔妮, 姜帆, 程泽. 变温度下IHF-IGPR框架的锂离子电池健康状态预测方法[J]. 电工技术学报, 2021, 36(17): 3705-3720.
	HAN Q N, JIANG F, CHENG Z. State of health estimation for lithium-ion batteries based on the framework of IHF-IGPR under variable temperature[J]. Transactions of China Electrotechnical Society, 2021, 36(17): 3705-3720.
2	武龙星, 庞辉, 晋佳敏, 等. 基于电化学模型的锂离子电池荷电状态估计方法综述[J]. 电工技术学报, 2022, 37(7): 1703-1725.
	WU L X, PANG H, JIN J M, et al. A review of SOC estimation methods for lithium-ion batteries based on electrochemical model[J]. Transactions of China Electrotechnical Society, 2022, 37(7): 1703-1725.
3	TIAN H X, QIN P L, LI K, et al. A review of the state of health for lithium-ion batteries: Research status and suggestions[J]. Journal of Cleaner Production, 2020, 261: doi: 10.1016/j.jclepro.2020.120813.
4	卢婷, 杨文强. 锂离子电池全生命周期内评估参数及评估方法综述[J]. 储能科学与技术, 2020, 9(3): 657-669.
	LU T, YANG W Q. Review of evaluation parameters and methods of lithium batteries throughout its life cycle[J]. Energy Storage Science and Technology, 2020, 9(3): 657-669.
5	LU J H, XIONG R, TIAN J P, et al. Battery degradation prediction against uncertain future conditions with recurrent neural network enabled deep learning[J]. Energy Storage Materials, 2022, 50: 139-151.
6	谭必蓉,杜建华,叶祥虎等.基于模型的锂离子电池SOC估计方法综述[J].储能科学与技术,2023,12(06):1995-2010.
	TAN B R, DU J H, YE X H, et al. Overview of SOC estimation methods of lithium-ion batteries based on model[J]. Energy Storage Science and Technology, 2023,12(06):1995-2010.
7	CHO S, JEONG H, HAN C H, et al. State-of-charge estimation for lithium-ion batteries under various operating conditions using an equivalent circuit model[J]. Computers & Chemical Engineering, 2012, 41: 1-9.
8	杨杰, 王婷, 杜春雨, 等. 锂离子电池模型研究综述[J]. 储能科学与技术, 2019, 8(1): 58-64.
	YANG J, WANG T, DU C Y, et al. Overview of the modeling of lithium-ion batteries[J]. Energy Storage Science and Technology, 2019, 8(1): 58-64.
9	李练兵, 李思佳, 李洁, 等. 基于差分电压和Elman神经网络的锂离子电池RUL预测方法[J]. 储能科学与技术, 2021, 10(6): 2373-2384.
	LI L B, LI S J, LI J, et al. RUL prediction method of lithium ion battery based on differential voltage and Elman neural network[J]. Energy Storage Science and Technology, 2021, 10(6): 2373-2384.
10	HE W, WILLIARD N, OSTERMAN M, et al. Prognostics of lithium-ion batteries based on Dempster-Shafer theory and the Bayesian Monte Carlo method[J]. Journal of Power Sources, 2011, 196(23): 10314-10321.
11	ZHANG Y Z, XIONG R, HE H W, et al. Long short-term memory recurrent neural network for remaining useful life prediction of lithium-ion batteries[J]. IEEE Transactions on Vehicular Technology, 2018, 67(7): 5695-5705.
12	ZHANG Y B, WANG Y Y, XIA Y, et al. A deep learning approach to estimate the state of health of lithium-ion batteries under varied and incomplete working conditions[J]. Journal of Energy Storage, 2023, 58: doi: 10.1016/j.est.2022.106323.
13	ARAUJO A, NORRIS W, SIM J. Computing receptive fields of convolutional neural networks[J]. Distill, 2019, 4(11): doi: 10.23915/distill.00021.
14	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June 27-30, 2016, Las Vegas, NV, USA. IEEE, 2016: 770-778.
15	周志华. 机器学习[M]. 北京: 清华大学出版社, 2016: 25-26.
	ZHOU Z H. Machine learning[M]. Beijing: Tsinghua University Press, 2016: 25-26.

预测起点	方法	评价指标	测试集电芯
预测起点	方法	评价指标	46^#	15^#	3^#	61^#	20^#
30 (预测长度70)	PF	MAE	0.739	0.886	0.951	0.289	2.520
	PF	RMSE	0.895	1.018	1.056	0.376	2.995
	LSTM	MAE	0.198	0.267	0.311	0.367	0.179
	LSTM	RMSE	0.259	0.315	0.357	0.427	0.224
	DRRN	MAE	0.031	0.029	0.076	0.092	0.047
	DRRN	RMSE	0.039	0.035	0.087	0.105	0.056
50 (预测长度50)	PF	MAE	0.588	0.277	0.301	0.330	0.375
	PF	RMSE	0.694	0.345	0.348	0.387	0.484
	LSTM	MAE	0.210	0.298	0.343	0.429	0.195
	LSTM	RMSE	0.278	0.346	0.370	0.485	0.235
	DRRN	MAE	0.026	0.024	0.069	0.102	0.048
	DRRN	RMSE	0.031	0.032	0.074	0.117	0.057
70 (预测长度30)	PF	MAE	0.415	0.259	0.098	0.295	0.455
	PF	RMSE	1.518	0.290	0.119	0.320	0.564
	LSTM	MAE	0.228	0.334	0.370	0.520	0.227
	LSTM	RMSE	0.295	0.389	0.381	0.559	0.272
	DRRN	MAE	0.021	0.024	0.056	0.110	0.043
	DRRN	RMSE	0.026	0.030	0.066	0.125	0.051

[1]	张青松, 包防卫, 牛江昊. 环境压力对锂电池热失控产气及爆炸风险的影响[J]. 储能科学与技术, 2023, 12(7): 2263-2270.
[2]	陈智伟, 张维戈, 张珺玮, 张言茹. 基于视觉特征的动力电池组综合健康评估及分筛方法[J]. 储能科学与技术, 2023, 12(7): 2211-2219.
[3]	徐冲, 徐宁, 蒋志敏, 李中凯, 胡洋, 严红, 马国强. 锂离子电池产气机制及基于电解液的抑制策略[J]. 储能科学与技术, 2023, 12(7): 2119-2133.
[4]	陈钦佩, 王学辉, 米文忠. 电动汽车锂离子电池系统热失控气体毒害及爆炸特性研究[J]. 储能科学与技术, 2023, 12(7): 2256-2262.
[5]	昝文达, 张睿, 丁飞. 锂离子电池电化学模型发展与应用[J]. 储能科学与技术, 2023, 12(7): 2302-2318.
[6]	吴宜琨, 何杰, 杨乐, 宋维力, 陈浩森. 锂离子电池多物理场多尺度变形理论模型与计算方法[J]. 储能科学与技术, 2023, 12(7): 2141-2154.
[7]	管鸿盛, 钱诚, 徐炳辉, 孙博, 任羿. 融合自注意力机制与门控循环单元网络的宽工况锂离子电池SOC估计[J]. 储能科学与技术, 2023, 12(7): 2229-2237.
[8]	范茂松, 耿萌萌, 赵光金, 杨凯, 王放放, 刘皓. 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.
[9]	李晋, 王青松, 孔得朋, 王晓冬, 俞振华, 乐艳飞, 黄鑫炎, 胡振恺, 吴候福, 方华斌, 曹伟, 张少禹, 卓萍, 陈晔, 李紫婷, 梅文昕, 张越, 赵丽香, 唐亮, 黄宗侯, 陈篪, 刘彦辉, 储玉喜, 许晓元, 张晋, 李贻恺, 冯蓉, 杨标, 户波, 杨晓滢. 锂离子电池储能安全评价研究进展[J]. 储能科学与技术, 2023, 12(7): 2282-2301.
[10]	张佳怡, 翁素婷, 王兆翔, 王雪锋. 石墨负极界面SEI膜与锂离子电池热失控[J]. 储能科学与技术, 2023, 12(7): 2105-2118.
[11]	郝增辉, 刘训良, 孟缘, 孟楠, 温治. 电极界面微观结构对固态锂离子电池性能的影响[J]. 储能科学与技术, 2023, 12(7): 2095-2104.
[12]	刘书琴, 王小燕, 张振东, 段振霞. 锂离子电池组液冷式热管理系统的设计及优化[J]. 储能科学与技术, 2023, 12(7): 2155-2165.
[13]	陈育新, 杨家沐, 练成, 刘洪来. 基于相场模型的锂电池电极浆料稳定涂布窗口分析[J]. 储能科学与技术, 2023, 12(7): 2185-2193.
[14]	杲齐新, 赵景腾, 李国兴. 锂离子电池快速充电研究进展[J]. 储能科学与技术, 2023, 12(7): 2166-2184.
[15]	黄凌锋, 韩东梅, 黄盛, 王拴紧, 肖敏, 孟跃中. 含有机硼的锂离子电池聚合物电解质的研究进展[J]. 储能科学与技术, 2023, 12(6): 1815-1830.