储能科学与技术 ›› 2019, Vol. 8 ›› Issue (3): 575-579.doi: 10.12028/j.issn.2095-4239.2018.0230

• 研究开发 • 上一篇    下一篇

基于萤火虫神经网络的动力电池SOC估算

吴华伟1,2, 张远进1,2, 叶从进1,2   

  1. 1 湖北文理学院纯电动汽车动力系统设计与测试湖北省重点实验室, 湖北 襄阳 441053;
    2 湖北文理学院汽车与交通工程学院, 湖北 襄阳 441053
  • 收稿日期:2018-11-21 修回日期:2018-12-17 出版日期:2019-05-01 发布日期:2019-01-22
  • 通讯作者: 张远进,助理实验师,主要研究方向为混合动力汽车能量管理,E-mail:394296412@qq.com
  • 作者简介:吴华伟(1979-),男,博士,副教授,主要研究方向为新能源汽车电驱控制及故障诊断,E-mail:9438043@qq.com
  • 基金资助:
    湖北省技术创新专项重大项目（2017AAA133），“机电汽车”湖北省优势特色学科群开放基金（XKQ2019010、XKQ2019020），中央引导地方科技发展财政专项（鄂财政2017[80]号文）。

Estimation of power battery SOC based on firefly BP neural network

WU Huawei1,2, ZHANG Yuanjin1,2, YE Congjin1,2   

  1. 1 Hubei Key Laboratory of Power System Design and Test for Electrical Vehicle, Hubei University of Arts and Science, Xiangyang 441053, Hubei, China;
    2 School of Automotive and Traffic Engineering, Hubei University of Arts and Science, Xiangyang 441053, Hubei, China
  • Received:2018-11-21 Revised:2018-12-17 Online:2019-05-01 Published:2019-01-22

PDF

275

摘要： 针对BP神经网络算法对电动汽车电池荷电状态（state of charge，SOC）估算的缺陷，提出一种基于萤火虫（firefly algorithm，FA）神经网络的SOC估算方法。以磷酸铁锂电池为测试对象，在ARBIN公司生产的EVTS电动车动力电池测试系统装置上进行测试，收集锂电池的各项性能参数。采用端电压和放电电流作为输入参数，SOC作为输出参数，建立FA-BP神经网络模型，用于估算锂离子电池充放电过程中的任一状态下的SOC。仿真实验结果表明，与现有的BP神经网络估算方法相比，基于FA-BP神经网络的锂电池SOC估算方法准确度高，具备很好的实用性。

关键词: 锂离子电池, 荷电状态, 萤火虫算法, BP神经网络

Abstract: In view of the defect of BP (back propagation) neural network algorithm of clectric vehicle battery charge state SOC (state of charge) estimation. Taking lithium iron phosphate battery as the test object, the performance parameters of lithium battery were collected on the power battery test system of EVTS electric vehicle manufactured by ARBIN Company. Using terminal voltage and discharge current as input parameters and SOC as output parameters, fa-bp neural network model was established to estimate SOC in any state during charging and discharging of lithium ion batteries. The simulation results show that compared with the existing BP neural network estimation method, the method based on FA-BP neural network has high accuracy and good practicability.

Key words: lithium ion battery, state of charge, firefly algorithm, BP neural network

中图分类号: