改进的萤火虫算法优化反向传播神经网络动力锂离子电池健康状态估计

doi:10.19799/j.cnki.2095-4239.2022.0668

摘要/Abstract

摘要：

为保证电池的正常运行，对电池的健康状态进行估计是非常重要的工作。针对传统建模方法估计精度差、参数众多计算复杂且耗时长等缺点，本工作构建了基于改进的萤火虫算法(firefly algorithm，FA)优化的反向传播(back propagation，BP)神经网络，对锂离子电池的健康状态(state of health，SOH)进行估计，利用萤火虫算法的全局优化能力和收敛速度快的特点对BP神经网络的权值和阈值进行优化，并引入莱维飞行(Levy flight)，提升全局搜索能力，扩大搜索范围，提高了估计精度。采用NASA艾姆斯研究中心的锂离子电池数据集，对改进优化前后的算法进行训练与估计，对比各算法之间的优劣程度。结果表明，莱维飞行改进萤火虫算法优化反向传播神经网络(LFFA-BP)算法相比于BP神经网络算法与萤火虫算法优化反向传播神经网络(FA-BP)算法，决定系数更高，误差波动范围更小，具有较高的估计精度。

关键词: 锂电池, 健康状态, 莱维飞行, 萤火虫算法, BP神经网络

Abstract:

It is essential to estimate a battery's state of health. This paper constructs a back propagation (BP) neural network optimized based on the improved firefly algorithm (FA) to estimate the state of health of lithium-ion batteries. The aim is to address the shortcomings of traditional modeling methods, such as poor estimation accuracy, numerous parameters, complex calculation, and longtime consumption. The weights and thresholds of the BP neural network are optimized using the FA's global optimization ability and fast convergence speed. Levy flight is introduced to improve the global search ability, expand the search range, and improve the estimation accuracy. The lithium-ion battery dataset of NASA Ames Research Center is used to train and estimate the algorithms before and after improvement and optimization and compare the advantages and disadvantages of each algorithm. Results show that compared with the BP neural network algorithm and FA for optimizing the BP neural network (FA-BP) algorithm, Levy flight improved firefly algorithm to optimize the BP neural network (LFFA-BP) algorithm has a higher determination coefficient, smaller error fluctuation range, higher estimation accuracy, and specific practical value.

Key words: lithium battery, state of health, Levy flight, firefly algorithm, BP neural network

中图分类号:

U 461.7

赵鑫浩, 许亮. 改进的萤火虫算法优化反向传播神经网络动力锂离子电池健康状态估计[J]. 储能科学与技术, 2023, 12(3): 934-940.

Xinhao ZHAO, Liang XU. Improved firefly optimization algorithm to optimize back propagation neural network for state of health estimation of power lithium ion batteries[J]. Energy Storage Science and Technology, 2023, 12(3): 934-940.

图/表 7

图1

图2

图3

图4

表1

图5

图6

参考文献 20

1	黎冲, 王成辉, 王高, 等. 锂电池SOC估计的实现方法分析与性能对比[J]. 储能科学与技术, 2022, 11(10): 3328-3344.
	LI C, WANG C H, WANG G, et al. Review on implementation method analysis and performance comparison of lithium battery state of charge estimation[J]. Energy Storage Science and Technology, 2022, 11(10): 3328-3344.
2	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.
3	GUHA A, PATRA A. State of health estimation of lithium-ion batteries using capacity fade and internal resistance growth models[J]. IEEE Transactions on Transportation Electrification, 2018, 4(1): 135-146.
4	高昕, 韩嵩. 基于分数阶模型的锂离子电池SOC与SOH协同估计[J]. 电源技术, 2021, 45(9): 1140-1143, 1208.
	GAO X, HAN S. Collaborative estimation of SOC and SOH of Li-ion battery based on fractional order model[J]. Chinese Journal of Power Sources, 2021, 45(9): 1140-1143, 1208.
5	常春, 王少晋, 苏广伟, 等. 改进模型的锂离子电池健康状态估计[J]. 电池, 2022, 52(6): 646-650.
	CHANG C, WANG S J, SU G W, et al. State of health estimation of Li-ion battery based on improved model[J/OL]. Battery Bimonthly, 2022, 52(6): 646-650.
6	高仁璟, 吕治强, 赵帅, 等. 基于电化学模型的锂离子电池健康状态估算[J]. 北京理工大学学报, 2022, 42(8): 791-797.
	GAO R J, LÜ Z Q, ZHAO S, et al. Health state estimation of Li-ion batteries based on electrochemical model[J]. Transactions of Beijing Institute of Technology, 2022, 42(8): 791-797.
7	刘晓悦, 魏宇册. 优化神经网络的锂电池SOC估算[J]. 机械设计与制造, 2021(11): 83-86.
	LIU X Y, WEI Y C. Optimization of neural network for lithium nattery SOC estimation[J]. Machinery Design & Manufacture, 2021(11): 83-86.
8	李旭东, 张向文. 基于主成分分析与WOA-Elman的锂离子电池SOH估计[J]. 储能科学与技术, 2022, 11(12): 4010-4021.
	LI X D, ZHANG X W. State of health estimation method for lithium-ion batteries based on principal component analysis and whale optimization algorithm-Elman model[J]. Energy Storage Science and Technology, 2022, 11(12): 4010-4021.
9	王雪, 游国栋, 房成信, 等. 基于IMOCS-BP神经网络的锂离子电池SOH估计[J/OL]. 电源学报: 1-11[2023-01-31]. http://kns.cnki.net/kcms/detail/12.1420.TM.20210823.0917.002.html.
	WANG X, YOU G D, FANG C X, et al. SOH estimation of lithium-ion battery based on IMOCS-BP neural network[J/OL]. Journal of Power Supply: 1-11[2023-01-31]. http://kns.cnki.net/kcms/detail/12.1420.TM.20210823.0917.002.html.
10	YANG B, WANG Y S, GAO H. State-of-charge estimation of lithium-ion batteries based on PSO-BP neural network[J]. International Journal of Energy and Power Engineering, 2021, 10(6): doi: 10.11648/j.ijepe.20211006.13.
11	吴铁洲, 刘思哲, 张晓星, 等. 基于FA-BP神经网络的锂离子电池SOH估算[J]. 电池, 2021, 51(1): 21-25.
	WU T Z, LIU S Z, ZHANG X X, et al. SOH estimation of Li-ion battery based on FA-BP neural network[J]. Battery Bimonthly, 2021, 51(1): 21-25.
12	FISTER I, FISTER I J, YANG X S, et al. A comprehensive review of firefly algorithms[J]. Swarm and Evolutionary Computation, 2013, 13: 34-46.
13	程美英, 倪志伟, 朱旭辉. 萤火虫优化算法理论研究综述[J]. 计算机科学, 2015, 42(4): 19-24.
	CHENG M Y, NI Z W, ZHU X H. Overview on glowworm swarm optimization or firefly algorithm[J]. Computer Science, 2015, 42(4): 19-24.
14	雍欣, 高岳林, 赫亚华, 等. 多策略融合的改进萤火虫算法[J]. 计算机应用, 2022, 42(12): 3847-3855.
	YONG X, GAO Y L, HE Y H, et al. Improved firefly optimization algorithm based on multi-strategy fusion[J]. Journal of Computer Applications, 2022, 42(12): 3847-3855.
15	张远进, 吴华伟, 叶从进. 基于IFA-EKF的锂电池SOC估算[J]. 储能科学与技术, 2020, 9(1): 117-123.
	ZHANG Y J, WU H W, YE C J. Estimation of SOC of lithium batteries based on IFA-EKF[J]. Energy Storage Science and Technology, 2020, 9(1): 117-123.
16	王艳. 改进的萤火虫算法及其应用研究[D]. 西安: 西安理工大学, 2018.
	WANG Y. Research on improved firefly algorithm and its application[D]. Xi'an: Xi'an University of Technology, 2018.
17	WU J R, WANG Y G, BURRAGE K, et al. An improved firefly algorithm for global continuous optimization problems[J]. Expert Systems With Applications, 2020, 149: doi: 10.1016/j.eswa.2020.113340.
18	张吉宣. 锂离子电池剩余寿命预测方法研究[D]. 太原: 中北大学, 2018.
	ZHANG J X. Research on remaining useful life prediction of lithium ion batteries[D]. Taiyuan: North University of China, 2018.
19	王震坡, 王秋诗, 刘鹏, 等. 大数据驱动的动力电池健康状态估计方法综述[J/OL]. 机械工程学报, 2022: 1-18 [2022-04-16]. https://kns.cnki.net/kcms/detail/11.2187.TH.20220414.1102.102.html.
	WANG Z P, WANG Q S, LIU P, et al. Review on techniques for power battery state of health estimation driven by big data methods[J/OL]. Journal of Mechanical Engineering, 2022: 1-18 [2022-04-16]. https://kns.cnki.net/kcms/detail/11.2187.TH.20220414. 1102.102.html.
20	赵沁峰, 蔡艳平, 王新军. 基于WOA-ELM的锂离子电池剩余寿命间接预测[J]. 中国测试, 2021, 47(9): 138-145.
	ZHAO Q F, CAI Y P, WANG X J. WOA-ELM based indirect prediction of remaining useful life of lithium-ion battery[J]. China Measurement & Test, 2021, 47(9): 138-145.

数据集	算法	均方差(MSE)	决定系数(R²)
B0006	BP	0.0872	0.9306
B0007	BP	0.0942	0.9188
B0006	FA-BP	0.0293	0.9872
B0007	FA-BP	0.0342	0.9714
B0006	LFFA-BP	0.0170	0.9973
B0007	LFFA-BP	0.0138	0.9950
B0006	PSO-BP	0.0200	0.9946
B0007	PSO-BP	0.0185	0.9917

[1]	程志翔, 曹伟, 户波, 程云芳, 李鑫, 姜丽华, 金凯强, 王青松. 储能用大容量磷酸铁锂电池热失控行为及燃爆传播特性[J]. 储能科学与技术, 2023, 12(3): 923-933.
[2]	申晓宇, 朱璟, 岑官骏, 乔荣涵, 郝峻丰, 田孟羽, 季洪祥, 金周, 武怿达, 詹元杰, 闫勇, 贲留斌, 俞海龙, 刘燕燕, 黄学杰. 锂电池百篇论文点评（2022.12.1—2023.1.31）[J]. 储能科学与技术, 2023, 12(3): 639-653.
[3]	蒋龙进, 张顺, 乔羽, 刘臣臻, 饶中浩. 废旧锂电池负极石墨失效机制及回收利用研究进展[J]. 储能科学与技术, 2023, 12(3): 822-834.
[4]	李路路, 陶正顺, 潘庭龙, 杨玮林, 胡官洋. 锂电池分数阶建模及SOC估计策略[J]. 储能科学与技术, 2023, 12(2): 544-551.
[5]	杨帆, 和嘉睿, 陆鸣, 陆玲霞, 于淼. 基于BP-UKF算法的锂离子电池SOC估计[J]. 储能科学与技术, 2023, 12(2): 552-559.
[6]	王瑞洁, 惠周利, 杨明. 基于间接健康指标的高斯过程回归对锂电池SOH预测[J]. 储能科学与技术, 2023, 12(2): 560-569.
[7]	周宇昊, 徐椤赟, 张钟平, 刘灵冲, 南斌, 赵海祺. 基于数字孪生的锂电池热电耦合模型构建与仿真分析[J]. 储能科学与技术, 2023, 12(2): 536-543.
[8]	刘芊彤, 邢远秀. 基于VMD-PSO-GRU模型的锂离子电池剩余寿命预测[J]. 储能科学与技术, 2023, 12(1): 236-246.
[9]	陈清炀, 何映晖, 余官定, 刘铭扬, 徐翀, 李振明. 模型与数据双驱动的锂电池状态精准估计[J]. 储能科学与技术, 2023, 12(1): 209-217.
[10]	田孟羽, 武怿达, 郝峻丰, 朱璟, 岑官骏, 乔荣涵, 申晓宇, 季洪祥, 金周, 詹元杰, 闫勇, 贲留斌, 俞海龙, 刘燕燕, 黄学杰. 锂电池百篇论文点评（2022.10.01—2022.11.30）[J]. 储能科学与技术, 2023, 12(1): 1-15.
[11]	陈淼淼, 邵钦君, 陈剑. 锂电池高比能量正极材料Cr₈O₂₁ 的制备及应用[J]. 储能科学与技术, 2022, 11(9): 3011-3020.
[12]	朱璟, 武怿达, 郝峻丰, 岑官骏, 乔荣涵, 申晓宇, 田孟羽, 季洪祥, 金周, 詹元杰, 闫勇, 贲留斌, 俞海龙, 刘燕燕, 黄学杰. 锂电池百篇论文点评（2022.6.1—2022.7.31）[J]. 储能科学与技术, 2022, 11(9): 3035-3050.
[13]	翟朋博, 常冬梅, 毕志杰, 赵宁, 郭向欣. 锂镧锆氧（LLZO）基固态锂电池界面关键问题研究进展[J]. 储能科学与技术, 2022, 11(9): 2847-2865.
[14]	陈晓宇, 耿萌萌, 王乾坤, 沈佳妮, 贺益君, 马紫峰. 基于电化学阻抗特征选择和高斯过程回归的锂离子电池健康状态估计方法[J]. 储能科学与技术, 2022, 11(9): 2995-3002.
[15]	沈馨, 张睿, 赵辰孜, 武鹏, 张羽彤, 张俊东, 范丽珍, 刘全兵, 陈爱兵, 张强. 金属锂电池中力-电化学机制研究进展[J]. 储能科学与技术, 2022, 11(9): 2781-2797.