Development of driving condition classification based adaptive optimal control strategy for PHEV. (26th July 2019)

• Record Type: Journal Article
• Authors: Ma, Chao; Yang, Kun; Miao, Lidong; Chen, Meiqi; Gao, Song
• Is Part Of: International journal of electric and hybrid vehicles. Volume 11:Number 3(2019)
• Page Start: 235
• Page End: 254
• Publication Date: 2019-07-26
• Subjects: driving condition classification -- SVM -- support vector machine -- RBF -- radical basis function -- driving cost -- adaptive optimal control strategy; Electric vehicles -- Periodicals; 629.229305
• Languages: English
• ISSNs: 1751-4088

Abstract

In this study, driving condition classification and recognition based adaptive optimal control strategy is developed for new type four wheel drive plug-in hybrid electric vehicle (PHEV). First, power characteristics of the proposed PHEV are analysed. The basic rule based and adaptive optimal control strategies are developed. According to the support vector machine (SVM) based classification theory, the RBF neural network kernel function is introduced and the multi classification SVM with the one-against-one method is selected. The feature parameters are then determined and extracted using real road experiment data. It is seen from the classification results that RBF kernel function based SVM has relatively high accuracy of 93.2%. Based on the developed energy management strategy library and driving cost theory, adaptive optimal control strategy is developed using Matlab/Simulink. It is found from the simulation results that the adaptive optimal control achieves the efficiency increase of 13.4%, which implies validity of the proposed adaptive optimal control strategy.