华电技术 ›› 2021, Vol. 43 ›› Issue (7): 42-46.doi: 10.3969/j.issn.1674-1951.2021.07.007

• 电化学储能 • 上一篇    下一篇

基于BP神经网络的梯次利用电池健康状态诊断

李勇琦1,2(), 雷旗开1,2, 王浩3, 华思聪3   

  1. 1.南方电网调峰调频发电有限公司,广州 510630
    2.先进储能技术联合实验室,广州 510630
    3.杭州高特电子设备股份有限公司,杭州 310012
  • 收稿日期:2021-02-22 修回日期:2021-05-15 出版日期:2021-07-25 发布日期:2021-07-27
  • 作者简介:李勇琦(1979—),男,广东乐昌人,正高级工程师,工学硕士,从事电池储能技术研究与应用的相关工作(E-mail: 253432239@qq.com)。
  • 基金资助:
    国家重点研发计划项目(2018YFB0905300);国家重点研发计划项目(2018YFB0905305)

State of health estimation for echelon-used batteries based on BP neural network

LI Yongqi1,2(), LEI Qikai1,2, WANG Hao3, HUA Sicong3   

  1. 1. CSG Power Generation Company, Guangzhou 510630, China
    2. CSG Joint Laboratory of Advanced Energy Storage Technology, Guangzhou 510630, China
    3. Gold Electronic Equipment Incorporated Limited, Hangzhou 310012, China
  • Received:2021-02-22 Revised:2021-05-15 Online:2021-07-25 Published:2021-07-27

摘要:

在大规模储能产业迅猛发展及退役车用动力电池数量逐年增长的背景下,阐述了梯次利用电池及其储能应用场景,以及梯次利用电池健康状态估算的重要性。介绍了影响电池健康状态的几种因素,将电池直流内阻、放电倍率及表面温度作为输入构建了3层反向传播(BP)神经网络。试验表明:在30块梯次利用电池的样本训练下,网络能够有效收敛且对梯次利用电池健康状态的计算误差在3%内,根据BP神经网络估算电池健康状态具有一定的可行性,该方法对梯次利用电池的分选以及储能应用具有重大意义。

关键词: 梯次利用电池, 健康状态, BP神经网络, 电池直流内阻, 放电倍率, 退役动力电池, 锂电池, 调峰调频, 储能

Abstract:

In the context of rapid developing energy storage industry and the gradually increasing decommissioned power batteries for vehicles, the echelon-used batteries and their application scenarios in energy storage are introduced, and the necessity of their state of health is expounded. Influence factors for battery state of health are discussed. A three-layer BP neural network is constructed by taking battery DC resistance, discharge rate and surface temperature as inputs. Experiment results show that trained by 30 echelon-used batteries, the network can effectively converge and keep the health state estimation errors of echelon-used batteries within 3%. Estimating battery state of health of batteries with BP neural network is feasibility and of great significance in sorting as well as energy storage for echelon-used batteries.

Key words: echelon-used battery, state of health, BP neural network, battery DC resistance, discharge rate, decommissioned power battery, lithium battery, peak regulation and frequency modulation, energy storage

中图分类号: