基于自适应LTTB与DTW-DBA-Means的动力电池组不一致性评估方法  

An Inconsistency Assessment Method for Power Battery Pack Based on Adaptive LTTB and DTW-DBA-Means

作　　者：吴凤和[1] 柴海宁 章正柱 张宁 王正明 蒋展鹏 郭保苏[1] WU Fenghe;CHAI Haining;ZHANG Zhengzhu;ZHANG Ning;WANG Zhengming;JIANG Zhanpeng;GUO Baosu(Mechanical Engineering College,Yanshan University,Qinhuangdao,Hebei 066004,China;Geely Holding Group,Hangzhou,Zhejiang 310051,China)

机构地区：[1]燕山大学机械工程学院,河北秦皇岛066004 [2]吉利控股集团,浙江杭州310051

出　　处：《计量学报》2024年第6期890-898,共9页Acta Metrologica Sinica

基　　金：国家重点研发计划(2020YFB1711803);国家自然科学基金(92266203);河北省高等学校科学技术研究重点项目(ZD2020156)。

摘　　要：针对电动汽车动力电池组不一致性难以通过外部参数有效评估问题,在对电池组电压数据进行分析时,引入轮廓系数作为不一致性评价指标,并融合自适应降采样(LTTB)与时序聚类(DTW-DBA-Means)算法,提出一种新的动力电池组不一致性评估方法。自适应LTTB能够根据电池组电压序列特点自适应分配压缩区间采样点数目并调整压缩比,可提高DTW-DBA-Means运算效率的同时保证聚类效果。通过运行9个月的实车数据进行实验验证,结果表明,自适应LTTB降采样效果优于动态LTTB与LTTB,且DTW-DBA-Means时序聚类效果优于k-Shape,所提方法在保证评估准确性同时可节省约96.7%的运算时间。Aiming at the problem that the inconsistency of electric vehicle power battery pack is difficult to be effectively evaluated through external parameters,when analyzing the battery pack voltage data,the Silhouette Coefficient is introduced as the inconsistency evaluation index,and a new inconsistency evaluation method for power battery pack is proposed by integrating adaptive down-sampling(LTTB)and time-series clustering(DTW-DBA-Means)algorithms.Adaptive LTTB can adaptively adjust the compression ratio and sample point allocation in compression intervals according to the characteristics of the battery pack voltage sequence,which can improve the DTW-DBA-Means operation efficiency and ensure the clustering effect.Experiments is conducted based on the real vehicle data running for nine months,the results show that the adaptive LTTB down-sampling effect is better than dynamic LTTB and LTTB,and the DTW-DBA-Means time-series clustering effect is better than k-Shape,and the proposed method can save about 96.7%operation time while ensuring the accuracy of evaluation.

关 键 词：电学计量 动力电池组 不一致性评估 轮廓系数 降采样 时序数据聚类 

分 类 号：TB971[一般工业技术—计量学]