基于模糊C均值算法的电池组一致性分析方法  

Consistency analysis method for batterypacks based on fuzzy C-means algorithm

作　　者：张庆平 田佳强 高博 霍耀佳 ZHANG Qingping;TIAN Jiaqiang;GAO Bo;HUO Yaojia(Electric Power Research Institute of State Grid Ningxia Electric Power Co.,Ltd.,Yinchuan Ningxia 750011,China;School of Electrical Engineering and Automation,Anhui University,Hefei Anhui 230601,China)

机构地区：[1]国网宁夏电力有限公司电力科学研究院,宁夏银川750011 [2]安徽大学电气工程与自动化学院,安徽合肥230601

出　　处：《宁夏电力》2023年第6期8-13,33,共7页Ningxia Electric Power

基　　金：国网宁夏电力有限公司科技项目(5229DK23000N)。

摘　　要：受限于电池系统电芯初始性能和环境工况差异,电池组性能的不一致性将严重降低电池组整体使用水平,增加系统的安全隐患,因此,提出一种基于模糊C均值(fuzzy C-means, FCM)算法的锂离子电池组一致性分析方法。该方法基于戴维南等效电路模型,利用递归最小二乘(RLS)算法实现特征参数的在线辨识,并将提取的特征参数作为FCM算法的输入,从而实现对电池组一致性聚类评估。通过对电动汽车9个月的实车数据进行验证,证明了所提出方法的有效性。分析结果表明该方法能够准确地评估电池组的一致性水平,并且在长时间的使用中保持较高的预测精度。Due to variations in the initial performance of battery cells and environmental conditions,inconsistency in battery packs seriously reduces the overall efficiency and increases system safety risks.To tackle this problem,this study proposes a consistency analysis method for battery packs using the fuzzy C-means(FCM)algorithm.This approach is based on the Thevenin equivalent circuit model,the recursive least squares algorithm is employed for real-time identification of these parameters.The extracted feature parameters are then inputted into the FCM algorithm for clustering consistency evaluation of battery packs.The effectiveness of the proposed method is validated using 9 months of actual vehicle data.The experimental results highlight the accurate evaluation of the consistency of battery packs,maintaining high predictive accuracy over prolonged usage.

关 键 词：电池组 一致性 FCM算法 聚类分析 

分 类 号：TM715[电气工程—电力系统及自动化]