Li-ion Battery SOH Prediction Based on PSO-RBF Neural Network

Abstract

Abstract: Key Laboratory of E&M, Ministry of Education & Zhejiang Province，Zhejiang University of Technology，Hangzhou，310014
For the traditional method to hardly estimate the internal parameters of Li-ion battery SOH, a PSO algorithm based on RBF neural network for SOH prediction of Li-ion batteries was proposed. Based on the Li-ion battery equivalent model, several key parameters which affected the SOH characteristics of the battery were determined by experimental data of the charged and discharged processes. The test data were input simulation model for network training and verification. Simulation results show that, compared to the BP neural network and the general RBF neural network, the algorithm may increase 20% of prediction accuracy, save more than 66.7% of the optimization time.

Key words: Li-ion battery, SOH(state of health), particle swarm optimization, radical basis function(RBF)

摘要： 针对传统方法估计锂离子电池健康状态(SOH)时内部参数测量困难等问题，提出一种基于粒子群优化径向基函数神经网络的锂离子电池SOH预测方法。通过对锂离子等效模型的研究，结合充放电过程的实验数据，确定了影响锂离子电池SOH特性的几个关键参数。将试验数据输入仿真模型进行网络训练和校验。仿真证明，相比BP神经网络和普通RBF神经网络，该算法的预测精度可提高20%，节省66.7%以上的优化时间。

关键词: 锂离子电池, 健康状况, 粒子群优先, 径向基函数

CLC Number:

TM912

Zhang Ren, Xu Fang, Chen Jiaoliao, Pan Guobing. Li-ion Battery SOH Prediction Based on PSO-RBF Neural Network[J]. China Mechanical Engineering.

张任, 胥芳, 陈教料, 潘国兵. 基于PSO-RBF神经网络的锂离子电池健康状态预测[J]. 中国机械工程.

References

[1]王成山，武震，李鹏.分布式电能存储技术的应用前景与挑战[J].电力系统自动化，2014，38(16)：1-8.

Wang Chengshan，Wu Zhen，Li Peng.Application Prospect and Challenge of Distributed Energy Storage Technology[J].Automation of Electric Power System，2014，38(16)：1-8.

[2]丁明，陈忠，苏建徽，等.可再生能源发电中的电池储能系统综述[J].电力系统自动化，2013，37(1)：19-25.

Ding Ming，Chen Zhong，Su Jianhui，et al.Overview of Battery Energy Storage System in Renewable Energy Power Generation[J]. Automation of Electric Power System，2013，37(1)：19-25.

[3]李逢兵，谢开贵，张雪松，等.基于锂电池充放电状态的混合储能系统控制策略设计[J].电力系统自动化，2013，37(1)：70-75.

Li Fengbing，Xie Kaigui，Zhang Xuesong，et al.Control Strategy Design of Hybrid Energy Storage System Based on Lithium Battery Charge and Discharge State[J]. Automation of Electric Power System，2013，37(1)：70-75.

[4]李勇，王丽芳，廖承林.电动车锂离子电池健康状态模型研究进展[J].电源技术，2013，37(5)：863-866.

Li Yong，Wang Lifang，Liao Chenglin.Electric Car Li-ion Battery State Model of Health Research Progress[J].Power Technology，2013，37(5)：863-866.

[5]李相哲，苏芳，林道勇.电动汽车动力电源系统[M].北京：化学工业出版社，2011.

[6]Ning G，White R E，Popov B N.A Generalized Cycle Life Model of Rechargeable Li-ion Batteries[J].Electrochimica Acta，2006，51(10)：2012-2022.

[7]徐睿.锂离子电池劣化程度与阻抗模型相关性研究[D].哈尔滨：哈尔滨理工大学，2010.

[8]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.Lithium-ion Battery Status Unscented Kalman Filter-based Adaptive Estimation Algorithm[J].Proceedings of the CSEE，2014，34(3)：445-452.

[9]黄伟昭，李小平，张栋省，等.基于开路电压回升速率和交流阻抗相结合的一种锂离子电池SOH算法[J].新能源进展，2014，2(1)：43-48.

Huang Weizhao，Li Xiaoping，Zhang Dongsheng，et al.SOH Algorithm for a Kind of Li-ion Battery Based on the Combination of Open Circuit Voltage Recovery Rate and AC Impedance[J].New Energy Development，2014，2(1)：43-48.

[10]Lin H T，Liang T J，Chen S M. Estimation of Battery State of Health Using Probabilistic Neural Network[J].IEEE Transactions on Industrial Informatics，2013，9(2)：679-685.

[11]Jeon D H，Beak S M.Thermal Modeling of Cylindrical Lithium-ion Battery during Discharge Cycle[J].Energy Conversion and Management，2011，52(8)：2973-2981.

[12]Chen Z，Mi C C，Fu Y，et al.Online Battery State of Health Estimation Based on Genetic Algorithm for Electric and Hybrid Vehicle Applications[J].Journal of Power Sources，2013，240：184-192.

[13]Tan Y K，Mao J C，Tseng K J.Modelling of Battery Temperature Effect on Electrical Characteristics of Li-ion Battery in Hybrid Electric Vehicle[C]// 2011 IEEE Ninth International Conference on Power Electronics and Drive Systems (PEDS).Singapore：IEEE，2011：637-642.

[14]Zhang C，Li K，Deng J.Real-time Estimation of Battery Internal Temperature Based on a Simplified Thermoelectric Model[J].Journal of Power Sources，2016，302：146-154.

[15]裴锋，黄向东，罗玉涛，等.电动汽车动力电池变流放电特性与荷电状态实时估计[J].中国电机工程学报，2005，25(9)：164-168.

Pei Feng，Huang Xiangdong，Luo Yutao，et al.Electric Vehicle Battery Discharge Characteristics of the Converter and the Real-time Estimate of the State of Charge[J].Proceedings of the CSEE，2005，25(9)：164-168.

[16]Salking A J，Fennie C，Singh P，et al.Determination of State-of-charge and State-of-health of Batteries by Fuzzy Logic Methodology[J].Journal of Power Sources，1999，80(1)：293-300.

[17]赵又群，周晓凤，刘英杰.基于扩展卡尔曼粒子滤波算法的锂电池SOC估计[J].中国机械工程，2015，26(3)：394-397.

Zhao Youqun，Zhou Xiaofeng，Liu Yingjie.SOC Estimation of Lithium Battery Based on Extended Calman Particle Filtering Algorithm[J].China Mechanical Engineering，2015，26(3)：394-397.

[18]叶志锋，孙健国.基于概率神经网络的发动机故障诊断[J].航空学报，2002，23(2)：155-157.

Ye Zhifeng，Sun Jianguo.The Engine Fault Diagn-osis Based on Probabilistic Neural Network[J].Chinese Journal of Aeronautics，2002，23(2)：155-157.

[19]胥芳，张任，吴乐彬，等.自适应BP神经网络在光伏MPPT中的应用[J].太阳能学报，2012，33(3)：468-472.

Xu Fang，Zhang Ren，Wu Lebin，et al.Self-adaption BP Neural Network for the MPPT Tracking in Photovoltaic[J].Journal of Solar Energy，2012，33(3)：468-472.

[20]乔良，宋小欣，谢延敏，等.基于PSO-RBF代理模型的板料成形本构参数反求优化研究[J].中国机械工程，2014，25(19)：2680-2685.

Qiao Liang，Song Xiaoxin，Xie Yanmin，et al.Study on the Optimization of Constitutive Parameters of Sheet Metal Forming Based on PSO-RBF Proxy Model[J].China Mechanical Engineering，2014，25(19)：2680-2685.

[21]陈波，潘海鹏，邓志辉.基于PSO优化RBF神经网络的反应釜故障诊断[J].中国机械工程，2012，23(18)：2204-2207.

Chen Bo，Pan Haipeng，Deng Zhihui.Fault Diagnosis of RBF Neural Network Based on PSO[J].China Mechanical Engineering，2012，23(18)：2204-2207.