基于CEEMDAN和ISOA-ELM的锂电池荷电状态预测

doi:10.19799/j.cnki.2095-4239.2022.0708

摘要/Abstract

摘要：

锂电池具有能量密度高、输出电压高、无记忆效应等优点，但过充过放电易引发安全事故，精确预测锂电池荷电状态(SOC)让其工作在最佳状态，具有重要现实意义，本文提出了一种基于自适应噪声集成经验模态分解(CEEMDAN)和数据驱动模型组合预测锂离子电池荷电状态的方法，对锂电池原始电流数据进行模态分解，得到多个子序列模态分量，提出一种基于惯性权重与Levy飞行机制的改进海鸥算法(ISOA)，对极限学习机预测模型(ELM)参数进行优化，构建ISOA-ELM锂电池预测模型；训练模型得到锂电池SOC预测结果。实验结果表明，该模型在实际工作中能够更贴合实际SOC，更有利于锂电池工作在最佳状态。

关键词: 锂离子电池, 荷电状态, 自适应噪声经验模态分解, 极限学习机, 海鸥优化算法

Abstract:

Lithium batteries have high energy density, high output voltage, and no memory effect, but their overcharge and over-discharge can cause accidents. In this regard, accurate prediction of the state of charge (SOC) of lithium batteries serves as the best condition. In this paper, a method based on an adaptive noise integrated Empirical Mode decomposition (CEEMDAN) and data-driven model is proposed to predict the state of charge of lithium-ion batteries. The original voltage data of lithium-ion batteries were modally decomposed to obtain the modal components of multiple sub-sequences. An improved Seagull algorithm (ISOA) based on the inertia weight and the Levy flight mechanism was proposed. The parameters of the extreme learning machine prediction model were optimized, and ISOA-ELM lithium battery prediction model was built. The SOC prediction results of the lithium batteries were obtained by training the model. The experimental results show that the model can better fit the actual SOC in practice and is more conducive to the lithium battery working in the best state.

Key words: lithium-ion batteries, state of charge, complete ensemble empirical mode decomposition with adaptive noise, extreme learning machine, seagull optimization algorithm

中图分类号:

TM 911

刘峰, 陈海忠. 基于CEEMDAN和ISOA-ELM的锂电池荷电状态预测[J]. 储能科学与技术, 2023, 12(4): 1244-1256.

Feng LIU, Haizhong CHEN. Lithium-ion battery state prediction based on CEEMDAN and ISOA-ELM[J]. Energy Storage Science and Technology, 2023, 12(4): 1244-1256.

图/表 13

图1

图2

图3

图4

图5

图6

图7

图8

表1

图9

图10

图11

图12

参考文献 23

1	李军, 李虎林. 电动汽车锂离子电池荷电状态估算方法综述[J]. 科学技术与工程, 2022, 22(6): 2147-2158.
	LI J, LI H L. Review of state of charge estimation methods for electric vehicle lithium-ion batteries[J]. Science Technology and Engineering, 2022, 22(6): 2147-2158.
2	程麒豫, 张希, 高一钊, 等. 基于降阶电化学模型估算锂离子电池状态[J]. 电池, 2021, 51(2): 110-113.
	CHENG Q Y, ZHANG X, GAO Y Z, et al. Estimating state of Li-ion battery based on reduced-order electrochemical model[J]. Battery Bimonthly, 2021, 51(2): 110-113.
3	袁宏亮, 刘莉, 吕桃林, 等. 基于改进模型的锂离子电池SOC估计[J]. 电池, 2021, 51(5): 445-449.
	YUAN H L, LIU L, LÜ T L, et al. SOC estimation for Li-ion battery based on improved model[J]. Battery Bimonthly, 2021, 51(5): 445-449.
4	付诗意, 吕桃林, 闵凡奇, 等. 电动汽车用锂离子电池SOC估算方法综述[J]. 储能科学与技术, 2021, 10(3): 1127-1136.
	FU S Y, LÜ T L, MIN F Q, et al. Review of estimation methods on SOC of lithium-ion batteries in electric vehicles[J]. Energy Storage Science and Technology, 2021, 10(3): 1127-1136.
5	郑永飞, 文怀兴, 韩昉, 等. 基于LSTM神经网络的动力电池SOC估算研究[J]. 计算机应用与软件, 2020, 37(3): 78-81, 88.
	ZHENG Y F, WEN H X, HAN F, et al. Soc estimation of power battery based on lstm neural network[J]. Computer Applications and Software, 2020, 37(3): 78-81, 88.
6	HUANG Z L, YANG F F, XU F, et al. Convolutional gated recurrent unit-recurrent neural network for state-of-charge estimation of lithium-ion batteries[J]. IEEE Access, 2019, 7: 93139-93149.
7	李泱, 张营, 邹博雨, 等. 基于EMD-GPR的锂离子电池剩余寿命预测方法研究[J]. 农业装备与车辆工程, 2021, 59(11): 60-63.
	LI Y, ZHANG Y, ZOU B Y, et al. Research on residual life prediction method of lithium ion battery based on EMD-GPR[J]. Agricultural Equipment & Vehicle Engineering, 2021, 59(11): 60-63.
8	易灵芝, 张宗光, 范朝冬, 等. 基于EEMD-GSGRU的锂电池寿命预测[J]. 储能科学与技术, 2020, 9(5): 1566-1573.
	YI L Z, ZHANG Z G, FAN C D, et al. Life prediction of lithium battery based on EEMD-GSGRU[J]. Energy Storage Science and Technology, 2020, 9(5): 1566-1573.
9	杨彦茹, 温杰, 史元浩, 等. 基于CEEMDAN和SVR的锂离子电池剩余使用寿命预测[J]. 电子测量与仪器学报, 2020, 34(12): 197-205.
	YANG Y R, WEN J, SHI Y H, et al. Remaining useful life prediction for lithium-ion battery based on CEEMDAN and SVR[J]. Journal of Electronic Measurement and Instrumentation, 2020, 34(12): 197-205.
10	宋绍剑, 王志浩, 林小峰. 基于极限学习机的磷酸铁锂电池SOC估算研究[J]. 电源技术, 2018, 42(6): 806-808, 881.
	SONG S J, WANG Z H, LIN X F. Research on SOC estimation of LiFePO₄ batteries based on ELM[J]. Chinese Journal of Power Sources, 2018, 42(6): 806-808, 881.
11	缪家森, 成丽珉, 吕宏水. 基于PSO-ELM的储能锂电池荷电状态估算[J]. 电力工程技术, 2020, 39(1): 165-169, 199.
	MIAO J S, CHENG L M, LÜ H S. Estimation of state of charge of energy storage lithium battery based on PSO-ELM[J]. Electric Power Engineering Technology, 2020, 39(1): 165-169, 199.
12	LI C Q, ZHOU J, TAO M, et al. Developing hybrid ELM-ALO, ELM-LSO and ELM-SOA models for predicting advance rate of TBM[J]. Transportation Geotechnics, 2022, 36: doi:10.1016/j.trgeo.2022.100819.
13	戴婷, 张榆锋, 章克信, 等. 经验模态分解及其模态混叠消除的研究进展[J]. 电子技术应用, 2019, 45(3): 7-12.
	DAI T, ZHANG Y F, ZHANG K X, et al. The research progress of empirical mode decomposition and mode mixing elimination[J]. Application of Electronic Technique, 2019, 45(3): 7-12.
14	李昌明. 经验模态分解融合深度学习的时间序列预测模型[J]. 辽宁工程技术大学学报(自然科学版), 2022, 41(2): 175-183.
	LI C M. Time series prediction model fusing empirical mode decomposition and deep learning[J]. Journal of Liaoning Technical University (Natural Science), 2022, 41(2): 175-183.
15	万磊, 余飞, 鲁统伟, 等. 基于CEEMDAN-CNN-GRU组合模型的短期负荷预测方法[J]. 河北科技大学学报, 2022, 43(2): 154-161.
	WAN L, YU F, LU T W, et al. Short-term load forecasting based on CEEMDAN-CNN-GRU combined model[J]. Journal of Hebei University of Science and Technology, 2022, 43(2): 154-161.
16	赵凌云, 刘友波, 沈晓东, 等. 基于CEEMDAN和改进时间卷积网络的短期风电功率预测模型[J]. 电力系统保护与控制, 2022, 50(1): 42-50.
	ZHAO L Y, LIU Y B, SHEN X D, et al. Short-term wind power prediction model based on CEEMDAN and an improved time convolutional network[J]. Power System Protection and Control, 2022, 50(1): 42-50.
17	HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: Theory and applications[J]. Neurocomputing, 2006, 70(1/2/3): 489-501.
18	丁阳征. 基于ELM的锂离子电池剩余寿命预测方法研究[D]. 太原: 中北大学, 2019.DING Y Z. Remaining useful life prediction method of lithium ion batteries based on extreme learning machine[D]. Taiyuan: North University of China, 2019.
19	王亦乐, 黄宏成, 杨健, 等. 基于SSA-ELM的动力电池健康状况预测研究[J]. 传动技术, 2022, 36(2): 3-6, 13.
	WANG Y L, HUANG H C, YANG J, et al. Prediction of power battery health state based on SSA-ELM[J]. Drive System Technique, 2022, 36(2): 3-6, 13.
20	吴婧睿. 基于GSO-ELM的锂离子电池剩余寿命间接预测方法研究[D]. 大连: 大连海事大学, 2017.
	WU J R. Research on indirect prediction method of remaining life based on GSO-ELM for lithium-ion battery[D]. Dalian: Dalian Maritime University, 2017.
21	周召娣. 极限学习机相关算法的优化及应用研究[D]. 南京: 南京信息工程大学, 2016.
	ZHOU Z D. Research on optimization and application of extreme learning machine[D]. Nanjing: Nanjing University of Information Science & Technology, 2016.
22	DHIMAN G, KUMAR V. Seagull optimization algorithm: Theory and its applications for large-scale industrial engineering problems[J]. Knowledge-Based Systems, 2019, 165: 169-196.
23	毛玲, 胡慧仲, 赵晋斌, 等. 一种多时间尺度下的锂离子电池剩余寿命混合预测方法[J]. 供用电, 2021, 38(6): 7-13.
	MAO L, HU H Z, ZHAO J B, et al. A hybrid prediction method of lithium-ion battery remaining useful life under multiple time scales[J]. Distribution & Utilization, 2021, 38(6): 7-13.

工况	预测模型	平均绝对误差MAE	均方根误差RMSE	绝对相关系数R²	运行时间/s
DST	CEEMDAN-ISOA-ELM	0.0033653	0.0048175	0.9949	24.785
	PSO-ELM	0.0051031	0.0067167	0.9891	16.066
	SOA-ELM	0.0061713	0.0077381	0.9806	19.427
	LSTM	0.032081	0.036609	0.6476	70
	CNN-GRU	0.012798	0.014423	0.9650	99
FUDS	CEEMDAN-ISOA-ELM	0.0051382	0.0061629	0.9912	28.998
	PSO-ELM	0.0089028	0.011362	0.9763	19.474
	SOA-ELM	0.010233	0.014265	0.9672	20.597
	LSTM	0.024916	0.033485	0.5548	72
	CNN-GRU	0.030218	0.033868	0.6756	68
US06	CEEMDAN-ISOA-ELM	0.0062962	0.0076641	0.9863	23.761
	PSO-ELM	0.0072198	0.0084125	0.9837	19.894
	SOA-ELM	0.012482	0.015775	0.9597	19.532
	LSTM	0.043681	0.056403	0.0945	69
	CNN-GRU	0.032721	0.036823	0.6643	35
1 A循环测试	CEEMDAN-ISOA-ELM	0.011061	0.021227	0.9445	21.641
	PSO-ELM	0.037605	0.067052	0.7332	16.868
	SOA-ELM	0.027703	0.052061	0.8175	13.237
	LSTM	0.021475	0.036256	0.7320	91
	CNN-GRU	0.017286	0.021406	0.9235	65

[1]	管敏渊, 沈建良, 徐国华, 汤舜, 张炜鑫, 曹元成. 锂离子电池储能系统靶向消防装备设计与性能[J]. 储能科学与技术, 2023, 12(4): 1131-1138.
[2]	宋缙华, 张兴浩, 丰震河, 程广玉, 顾洪汇, 顾海涛, 王可. 基于原位参比的氧化亚硅-石墨复合负极循环衰减机制[J]. 储能科学与技术, 2023, 12(4): 1059-1065.
[3]	胡力月, 姚行艳. 基于正交试验的锂离子电池热失控仿真[J]. 储能科学与技术, 2023, 12(4): 1268-1277.
[4]	王朋凯, 张新燕, 张光昊. 基于ResNet-Bi-LSTM-Attention的锂离子电池剩余使用寿命预测[J]. 储能科学与技术, 2023, 12(4): 1215-1222.
[5]	翟智, 王福金, 邸一, 马珮羽, 赵志斌, 陈雪峰. 基于分层对齐迁移学习的锂离子电池容量估计[J]. 储能科学与技术, 2023, 12(4): 1223-1233.
[6]	武鸿鑫, 李爱魁, 董存, 孙树敏, 李广磊, 王士柏. 计及调频备用的储能平抑风电功率波动控制策略[J]. 储能科学与技术, 2023, 12(4): 1194-1203.
[7]	赵立禹, 孙桓五, 刘世闯, 闫志远. 重卡辅助动力电池加热系统能耗对比及优化[J]. 储能科学与技术, 2023, 12(4): 1139-1147.
[8]	杨妮, 苏岳锋, 王联, 李宁, 马亮, 朱晨. 聚焦离子束显微镜技术在锂离子电池领域的研究进展[J]. 储能科学与技术, 2023, 12(4): 1283-1294.
[9]	寇发荣, 罗希, 门浩, 郭杨娟, 杨天祥. 基于特征优选与改进极限学习机的锂电池SOC估计[J]. 储能科学与技术, 2023, 12(4): 1234-1243.
[10]	成雪莉, 张维福, 罗城城, 袁小亚. 一步水热法制备三维石墨烯/Fe₃O₄ 复合材料及其储锂性能[J]. 储能科学与技术, 2023, 12(4): 1066-1074.
[11]	李奇松, 陈荣, 李慧芳. 阻抗分析法在锂离子电池析锂阈值检测中的应用[J]. 储能科学与技术, 2023, 12(4): 1278-1282.
[12]	董渊昌, 庞晓琼, 贾建芳, 史元浩, 温杰, 李笑, 张鑫. 基于SVD-SAE-GPR的锂离子电池RUL预测[J]. 储能科学与技术, 2023, 12(4): 1257-1267.
[13]	刘树港, 蒙波, 李政隆, 杨亚雄, 陈建. Li _x （Mg， Ni， Zn， Cu， Co） ₁_-_x O高熵氧化物负极材料电化学储锂特性[J]. 储能科学与技术, 2023, 12(3): 743-753.
[14]	常修亮, 李希超, 贾隆舟, 韦守李, 王敬豪, 戴作强, 郑莉莉. 过充循环老化电池产热特性[J]. 储能科学与技术, 2023, 12(3): 685-697.
[15]	李奎杰, 楼平, 管敏渊, 莫金龙, 张炜鑫, 曹元成, 程时杰. 锂离子电池热失控多维信号演化及耦合机制研究综述[J]. 储能科学与技术, 2023, 12(3): 899-912.