基于改进CART算法的退役动力电池等级筛选方法  

Grade classification method of decommissioned power battery based on improved CART algorithm

作　　者：刘永成 刘杰文 杨茜 宋汶秦 郭永吉[2] 王兴贵[2] LIU Yongcheng;LIU Jiewen;YANG Qian;SONG Wenqin;GUO Yongji;WANG Xinggui(Economics and Technology Research Institute of State Grid Gansu Electric Power Company,Lanzhou,Gansu 730050,China;College of Electrical and Information Engineering,Lanzhou University of Technology,Lanzhou,Gansu 730050,China)

机构地区：[1]国网甘肃省电力公司经济技术研究院,甘肃兰州730050 [2]兰州理工大学电气工程与信息工程学院,甘肃兰州730050

出　　处：《燕山大学学报》2024年第1期48-53,76,共7页Journal of Yanshan University

基　　金：国网甘肃省电力公司科技项目(W21FZ2730244);甘肃省自然科学基金资助项目(21JR7RA205)。

摘　　要：针对退役动力电池存在一致性差、等级筛选效率低的难题,提出了一种基于改进CART算法的退役动力电池等级筛选方法。首先,分析了传统CART算法的基本原理,为克服算法计算量大的缺陷,将Fayyad边界点判定定理与CART算法相结合,通过选取属性最优阈值点来减少计算量,提高分类效率;其次,基于代价复杂度后剪枝算法,采用交叉验证法对算法进行进一步优化;最后,将改进CART算法用于退役动力电池筛选分类,实验结果表明改进CART算法在保持较高准确率的情况下,可以有效提高退役动力电池的等级筛选效率。Aiming at the problems of poor consistency and low efficiency of grade classification of decommissioned power battery,a grade classification method of decommissioned power battery based on improved CART algorithm is proposed.Firstly,the basic principle of the traditional CART algorithm is analyzed.In order to overcome the defect of large amount of computation,Fayyad boundary point determination theorem is combined with the CART algorithm,and the optimal threshold point of attributes is selected to reduce the amount of computation and improve the classification efficiency.Secondly,based on the cost complexity post pruning algorithm,the cross validation method is used to further optimize the algorithm。Finally,the improved CART algorithm is applied to the screening and classification of decommissioned power batteries.The experimental results show that the improved CART algorithm can effectively improve the grade classification efficiency of decommissioned power battery while maintaining a high accuracy.

关 键 词：退役动力电池 等级筛选 改进CART算法 最优阈值点 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]