基于GA-ELM的锂电池SOC估计及主动均衡*

doi:10.11985/2024.01.035

摘要/Abstract

摘要：

锂电池的状态估计和主动均衡是提高电池性能和延长使用寿命的关键技术，针对参数模型的荷电状态(State of charge，SOC)估计方法忽略电动汽车实际工况而导致的估计偏差较大的问题，提出一种基于遗传算法的极限学习机(GA-ELM)神经网络算法来估计电池的荷电状态SOC，通过遗传算法优化了ELM的参数，提高估计精度和泛化能力，并在UDDS工况数据下进行训练与测试。同时采用双向Buck-Boost均衡拓扑结构，该拓扑结构能够快速实现电池间的能量传递，同时又降低了传递路径的复杂性。通过遗传算法的极限学习机估计出的SOC作为均衡变量，利用Matlab/Simulink仿真平台进行试验。结果表明，提出的GA-ELM神经网络平均误差为0.15%，而传统的ELM神经网络平均误差为0.56%，因此提出的神经网络能够更精确地估计SOC；同时电池组之间能够快速完成能量均衡，证明了所提方案的可行性。

关键词: 遗传算法, Buck-Boost电路, SOC估计, 极限学习机, 电池均衡

Abstract:

State estimation and active equalization of lithium batteries are key technologies to improve battery performance and extend service life. Aiming at the problem that state of charge(SOC) estimation method of parameter model ignores the actual working conditions of electric vehicles and causes large estimation deviation, an extreme learning machine(GA-ELM) neural network algorithm is proposed based on genetic algorithm to estimate SOC of battery. The parameters of ELM are optimized by genetic algorithm to improve the estimation accuracy and generalization ability, and the training and testing are carried out under UDDS working condition data. At the same time, the bidirectional Buck-Boost balanced topology can quickly transfer energy between cells, while reducing the complexity of the transfer path. The SOC estimated by the extreme learning machine of genetic algorithm is used as the equilibrium variable, and the experiment is carried out by Matlab/Simulink simulation platform. The results show that the average error of the GA-ELM neural network proposed in this paper is 0.15%, while that of the traditional ELM neural network is 0.56%. Therefore, the neural network proposed can estimate SOC more accurately. At the same time, the energy balance between the battery pack can be quickly completed, which proves the feasibility of the scheme.

Key words: Genetic algorithm, Buck-Boost circuit, SOC estimation, extreme learning machine, battery equalization

中图分类号:

TM910

于仲安, 张军令, 陈可怡. 基于GA-ELM的锂电池SOC估计及主动均衡^*[J]. 电气工程学报, 2024, 19(1): 326-333.

YU Zhongan, ZHANG Junling, CHEN Keyi. SOC Estimation and Active Equalization of Lithium Battery Based on GA-ELM[J]. Journal of Electrical Engineering, 2024, 19(1): 326-333.

图/表 10

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

参考文献 20

[1]	卢兰光, 李建秋, 华剑锋, 等. 电动汽车锂离子电池管理系统的关键技术[J]. 科技导报, 2016, 34(6):39-51. doi: 10.3981/j.issn.1000-7857.2016.06.004
	LU Languang, LI Jianqiu, HUA Jianfeng, et al. Key technologies of lithium-ion battery management system for electric vehicles[J]. Science & Technology Review, 2016, 34(6):39-51.
[2]	ZHANG Yongzhi, XIONG Rui, HE Hongwen, et al. Lithium-ion battery pack state of charge and state of energy estimation algorithms using a hardware-in-the-loop validation[J]. IEEE Transactions on Power Electronics, 2017, 32(6):4421-4431. doi: 10.1109/TPEL.2016.2603229
[3]	AL-HAJ HUSSEIN A, BATARSEH I. A review of charging algorithms for nickel and lithium battery chargers[J]. IEEE Transactions on Vehicular Technology, 2011, 60(3):830-838. doi: 10.1109/TVT.2011.2106527
[4]	ASHIQUE R H, SALAM Z, et al. Integrated photovoltaic-grid DC fast charging system for electric vehicle:A review of the architecture and control[J]. Renewable and Sustainable Energy Reviews, 2017,69:1243-1257.
[5]	ARIAS M, SEBASTI´AN J, HERNANDO M M, et al. Practical application of the wave-trap concept in battery-cell equalizers[J]. IEEE Transactions on Power Electronics, 2015, 30(10):5616-5631. doi: 10.1109/TPEL.2014.2373435
[6]	PEREZ H E, DEY S, HU X, et al. Optimal charging of Li-ion batteries via a single particle model with electrolyte and thermal dynamics[J]. Journal of the Electrochemical Society, 2017, 164(7):A1679-A1687.
[7]	刘晓康, 詹琼华, 何葵, 等. 电动汽车用电池管理系统的研究[J]. 华中科技大学学报, 2007, 284(8):83-86.
	LIU Xiaokang, ZHAN Qionghua, HE Kui, et al. Electric vehicle battery management system research[J]. Journal of Huazhong University of Science and Technology, 2007, 284(8):83-86.
[8]	沈维祥. 基于开路电压和环境温度的铅酸蓄电池充电状态的数学模型[J]. 太阳能学报, 1997(3):92-97.
	SHEN Weixiang. Mathematical model of lead acid battery charging state based on open circuit voltage and ambient temperature[J]. Acta Energiae Solaris Sinica, 1997(3):92-97.
[9]	魏克新, 陈峭岩. 基于自适应无迹卡尔曼滤波算法的锂离子动力电池状态估计[J]. 中国电机工程学报, 2014, 34(3):445-452.
	WEI Kexin, CHEN Qiaoyan. State estimation of lithium ion battery based on adaptive unscented Kalman filter algorithm[J]. Proceedings of the CSEE, 2014, 34(3):445-452.
[10]	李贵海. 电池SOC估算策略研究[D]. 杭州: 浙江大学, 2006.
	LI Guihai. Research on battery SOC estimation strategy[D]. Hangzhou: Zhejiang University, 2006.
[11]	孙志军, 薛磊, 许阳明, 等. 深度学习研究综述[J]. 计算机应用研究, 2012, 29(8):2806-2810.
	SUN Zhijun, XUE Lei, XU Yangming, et al. A review of deep learning research[J]. Application Research of Computers, 2012, 29(8):2806-2810.
[12]	杨建新, 兰小平, 赵振, 等. 基于改进郊狼算法与极限学习机的工业金刚石检测[J]. 计算机集成制造系统, 2023, 29(2):449-459.
	YANG Jianxin, LAN Xiaoping, ZHAO Zhen, et al. Industrial diamond detection based on improved coyote algorithm and extreme learning machine[J]. Computer Integrated Manufacturing Systems, 2023, 29(2):449-459.
[13]	戴震宇, 刘志茹, 贾金环, 等. 基于容量和电压的混合最优控制均衡[J]. 电子技术应用, 2019, 45(3):108-112.
	DAI Zhenyu, LIU Zhiru, JIA Jinhuan, et al. Hybrid optimal control equilibrium based on capacity and voltage[J]. Application of Electronic Technique, 2019, 45(3):108-112.
[14]	宋绍剑, 王志浩, 林小峰. 基于SOC的锂动力电池组双向主动均衡控制[J]. 系统仿真学报, 2017, 29(3):609-617. doi: 10.16182/j.issn1004731x.joss.201703019
	SONG Shaojian, WANG Zhihao, LIN Xiaofeng. Bidirectional active equalization control of lithium battery pack based on SOC[J]. Journal of System Simulation, 2017, 29(3):609-617.
[15]	蔡敏怡, 张娥, 林靖, 等. 串联锂离子电池组均衡拓扑综述[J]. 中国电机工程学报, 2021, 41(15):5294-5311.
	CAI Minyi, ZHANG E, LIN Jing, et al. Series of lithium ion battery equalization topology review[J]. Proceedings of the CSEE, 2021, 41(15):5294-5311.
[16]	张赟, 王琛, 王毅, 等. 基于自适应下垂控制的直流微电网多储能SOC动态均衡策略[J]. 华北电力大学学报, 2020, 47(5):21-29.
	ZHANG Yun, WANG Chen, WANG Yi, et al. Dynamic balancing strategy of DC microgrid multi-energy storage SOC based on adaptive sag control[J]. Journal of North China Electric Power University, 2020, 47(5):21-29.
[17]	李敏强, 徐博艺, 寇纪淞. 遗传算法与神经网络的结合[J]. 系统工程理论与实践, 1999(2):66-70.
	LI Minqiang, XU Boyi, KOU Jisong. Combination of genetic algorithm and neural network[J]. Systems Engineering Theory and Practice, 1999(2):66-70.
[18]	张铃, 张钹. 遗传算法机理的研究[J]. 软件学报, 2000(7):945-952.
	ZHANG Ling, ZHANG Ba. The researches on the mechanism of the genetic algorithm[J]. Journal of Software, 2000(7):945-952.
[19]	刘柱, 姜媛媛, 罗慧, 等. 基于最优权阈值ELM算法的锂离子电池RUL预测[J]. 电源学报, 2018, 16(4):168-173. doi: 10.13234/j.issn.2095-2805.2018.4.168
	LIU Zhu, JIANG Yuanyuan, LUO Hui, et al. ELM threshold algorithm based on the optimal weight of lithium ion battery URL prediction[J]. Journal of Power Supply, 2018, 16(4):168-173. doi: 10.13234/j.issn.2095-2805.2018.4.168
[20]	冯飞, 宋凯, 逯仁贵, 等. 磷酸铁锂电池组均衡控制策略及荷电状态估计算法[J]. 电工技术学报, 2015, 30(1):22-29.
	FENG Fei, SONG Kai, LU Rengui, et al. Equalization control strategy and SOC estimation for LiFePO₄ battery pack[J]. Transactions of China Electrotechnical Society, 2015, 30(1):22-29.