Application of Matter Element Information Entropy and SVM in Lithium Battery Efficiency Evaluation and Prediction

Abstract

The state of health (SOH) of the power batteries is one of the most important performances of the electric vehicle power batteries system. In order to comprehensively evaluate the health of the batteries, the stereoscopic cross compound matter element is used in parameters of batteries charging and discharging, the joint weight of the evaluation index is determined by the analytic hierarchy process(AHP) and the maximum entropy method, and the matter element-maximum information entropy is used to carry out the quantitative calculation analysis for the health index of the lithium batteries. Parameter-optimizing Support Vector Machine is used to predict the health index of lithium batteries. The experimental results show that this method has a good guiding function for the state of health analysis, it provides a theoretical basis for the use of the power batteries.