电网技术2017，Vol.41Issue(12)：4038-4044,7.DOI:10.13335/j.1000-3673.pst.2017.0522
灰色神经网络模型在线估算锂离子电池SOH
Online Estimation of Lithium-Ion Battery State of Health Using Grey Neural Network
摘要
Abstract
Lithium-ion battery is a complex electrochemical dynamic system. It is difficult to achieve online estimation of state of health (SOH) by single monitoring of physical and chemical properties of the battery. In this paper, increases of internal resistance and polarization resistance and decrease of polarization capacitance are proposed as new health indicators (HIs) of the battery. Grey neural network is used to train the HIs as input for grey neural network model and battery capacity degradation as its output. Finally, battery SOH estimates are achieved through online construction of battery HIs. Experimental results show that the proposed HIs can effectively characterize battery health state. The grey neural network degradation model has higher online SOH estimation accuracy with estimation error less than 2％, lower than that obtained with BP neural network model.关键词
灰色神经网络/锂离子电池/SOH 估算/健康因子Key words
grey neural network/lithium ion battery/SOH estimation/health indicator分类
信息技术与安全科学引用本文复制引用
韦海燕,陈孝杰,吕治强,王峥峥,潘海鸿,陈琳..灰色神经网络模型在线估算锂离子电池SOH[J].电网技术,2017,41(12):4038-4044,7.基金项目
国家自然科学基金项目(51267002,51667006) （51267002,51667006）
广西自然科学基金资助项目(2015GXNSFAA139287) （2015GXNSFAA139287）
广西制造系统与先进制造技术重点实验室项目(1514030S002) （1514030S002）
广西研究生教育创新计划项目(YCSW2017038).Project Supported by National Natural Science Foundation of China (NSFC) (51267002, 51667006) （YCSW2017038）
Guangxi Natural Science Foundation (2015GXNSFAA139287) （2015GXNSFAA139287）
Supported by Guangxi Key Laboratory of Manufacturing System & Advanced Manufacturing Technology (1514030S002) （1514030S002）
Innovation Project of Guangxi Graduate Education (YCSW2017038). （YCSW2017038）
