摘要
提出了一种对锂离子电池衰退模式进行分类的新方法。引用L2距离的概念代表衰退曲线的相关程度,通过均匀B-样条曲线函数建立锂电池衰退曲线与聚类算法之间的联系,大大减少衰退模式的种类。最后搭建了锂离子动力电池实验平台,借助实验数据建立模型,验证了算法的准确性。
A new method for lithium-ion batteries recession pattern classification was presented. The degree of L2 distance was used as a measure of closeness and the function expansion was described in the uniform B-spline, the curve information was introduced into the clustering algorithm, and the recession mode species was greatly reduced.Finally, a lithium-ion battery test platform was built, with experimental data model to verify the accuracy of the algorithm.
引文
[1]CHANTELOU D,H魪BRAIL G,MULLER C.Visualizing 2 665electric power load curves on a single A4 sheet of paper[C]//Proceedings of International Conference on Intelligent Systems Applications to Power Systems(ISAP'96).Orlando,USA:IEEE,1996.
[2]DEBREGEAS A,HEBRAIL G.Interactive interpretation of Kohonen maps applied to curves[C]//Proceedings of International Conference on Knowledge Discovery and Data Mining(KDD'08).New York:International Conference on Knowledge Discovery and Data Mining,2008.
[3]VERBRUGGE M,FRISCH D,KOCH B.Adaptive energy management of electric and hybrid electric vehicles[J].J Electrochem Soc,2011,15:333-342.
[4]叶明.中国加工贸易商品演变过程分析—基于曲线聚类方法研究[J].世界经济研究,2006,28(8):49-54.
[5]叶明,王惠文.大规模曲线的自动分类方法及其应用[J].系统管理学报,2005,9(6):650-644.
[6]DEBOOR C.A Practical Guideto Splines[M].New York:Springer,2010.