Research On Control Strategy Of Battery Electric Vehicle Based On Driving Intention Recognition

The automobile industry is an essential industry of the national economy and important for China’s dream of a strong country.With the increasing shortage of global energy and improvement of environmental protection in various countries,new energy vehicles have become the focus of research and development at home and abroad,especially battery electric vehicles.The Vehicle Control Unit(VCU)is the upper-level decision unit for battery electric vehicles and has a decisive influence on the vehicle performance.This article took a certain battery electric vehicle as the research object,and conducted research on the vehicle control strategy combined with the driver’s driving intention.Firstly,based on the d SPACE real-time simulation system,a driving simulator platform was built to collect the experimental data of the opening of accelerator pedal and its rate of change under different acceleration intentions.The support vector machine(SVM)algorithm was used to recognize and classify the driver’s acceleration intentions.In order to improve the classification accuracy of support vector machine(SVM)and reduce model training time,an adaptive genetic algorithm was proposed to optimize SVM parameters,and the optimization range of parameters could be determined according to different data sets.The compensation coefficient of the driver’s braking intention was determined by using the brake pedal’s opening and its rate of change,which properly compensated the conventional braking efficiency factor to obtain the desired braking efficiency factor that met the driver’s intention,and classify the driver’s braking intention.Secondly,this paper analyzed the structure and functions of the battery electric vehicle control system,and defined the CAN communication protocol of the power system of the battery electric vehicle based on SAEJ1939,and developed the whole vehicle control strategy according to the functional requirements of the vehicle controller,including mode judgment,drive control,Energy management,high-voltage power management,and fault diagnosis and processing.The basic torque of the motor is determined according to the driver’s different acceleration intentions,and the compensation torque of the motor under different acceleration intentions and different vehicle speeds is determined by the fuzzy control algorithm.At the same time,in order to ensure the safety of braking during energy recovery,the reasonable change of the distribution coefficient of braking force after the motor participates in braking was determined according to ECE regulations,and the power ratio of the electrical mechanism was calculated under different braking intentions to recovery braking energy.Completed the model development of the vehicle control strategy in Matlab/Simulink.Thirdly,combined with theoretical and experimental data,the simulation model of the battery electric vehicle was built in Simulink software,including motor control system model,battery system model,drive train model,vehicle dynamics model,and driver model,by which the offline simulation of the control strategy in this paper was conducted.The simulation results show that the drive control strategy formulated in this paper can accurately identify the driver’s acceleration intention and improve the acceleration performance of the whole vehicle;under the cycle conditions,the vehicle control strategy can make the vehicle accurately follow the target speed,recover the braking energy,and improve the vehicle’s recharge mileage.Finally,the hardware-in-the-loop test platform of d SPACE was built,and the vehicle control strategy was downloaded to the rapid control prototype-Mico Auto Box.The hardware-in-the-loop test of the vehicle control strategy was conducted to verify the effectiveness and reliability of the vehicle control strategy.