An improved model based on artificial neural networks and Thevenin model for nickel metal hydride power battery

作     者：Changhao Piao1,2,Xiaoyong Yang1,3 1Ministry of Education Key Lab of Network Control Tech.& Intelligent Instruments,Chongqing University of Posts and Communications,Chongqing,ChinaCong Teng 3,HuiQian Yang2 2Chongqing ChangAn New Energy Automobile Co.,Ltd.Chongqing,China 3Research Center of Energy Electronics,Chongqing University of Posts and Communications 

会议名称：《2010 International Conference on Optics, Photonics and Energy Engineering (OPEE 2010)》

会议日期：2010年

学科分类：0808[工学-电气工程] 08[工学] 

基　　金：Supported by Natural Science Foundation Project of CQ CSTC 2008BB6084 and 2008AA6025 

关 键 词：nickel metal hydride power battery state of charge artificial neural networks Thevenin model 

摘      要：Based on artificial neural networks and Thenvenin model,this paper uses an improved model predicting state of *** combine artificial neural networks model with Thevenin model,and predict state of charge in real time at the same *** the difference between the predictive value of artificial neural networks model and the predictive value of Thevenin model is more than 10%,we revised the predictive value of artificial neural networks model by weighted average *** results show that it can reduce the error of artificial neural networks model obvious and the average error is 4.72%.It is lower independence on initial state of charge than artificial neural networks model.