Neural Network Self-adaptive PID Control for Driving and Regenerative Braking of Electric Vehicle
In order to deal with the main problems of electric vehicle (EV), such as the short driving range, the short life of batteries, the variation of the road state and driving mode and so on, based on constructing the main circuit diagram of the EV’s control system and researching driving and regenerative braking process, the mathematical model of the system was established, driving and regenerative braking controller was designed for the EV. To improve the stability and reliability of the system, neural network (NN) self-adaptive PID control algorithm was researched and applied to the system. The controller comprises a back propagation (BP) NN and a radial basis function (RBF) NN. The former is used to adaptively adjust the parameters of the PID controller on line. The later is used to establish nonlinear prediction model and perform parameter prediction. The experimental results show that the NN self-adaptive PID controller is superior to traditional PID controller at response speed, steady-state tracking error and resisting perturbation. Additionally, it can recover more energy, lengthen batteries’ life, and increase the driving range than PID controller by 5.3％.
Electric vehicle Driving control Regenerative braking Neural network Self-adaptive PID control
Jianbo Cao Binggang Gao Wenzhi Chen Peng Xu
R&D Center of Electric Vehicle Xian Jiaotong University Xian, Shaanxi Province, China
国际会议
2007 IEEE International Conference on Automation and Lofistics
山东济南
英文
2007-08-18（万方平台首次上网日期，不代表论文的发表时间）