基于ANFIS的电动赛车加速驱动控制的优化

为提高赛车在中低速下的加速能力，针对传统模糊控制依赖操作人员的经验、控制精度较低等缺点，提出一种基于自适应神经模糊推理系统的电动赛车加速驱动控制优化方法。该方法以当前加速踏板开度对应的最高车速为驾驶员期望车速，以驾驶员期望车速与实际车速的偏差及其变化率为输入变量，以加速踏板修正系数为输出变量，将加速踏板修正系数与当前加速踏板开度相乘得到修正后的加速踏板开度。Matlab/Simulink仿真与实车测试结果表明:在对加速踏板采用相同的操作控制下，优化后的驱动控制方法增加了赛车加速踏板的开度；在加速结束时刻，赛车车速的仿真值较优化前提高209%，实测值较优化前提高174%。

Optimization of Acceleration Driving Control Strategy for Electric Racing Cars

An optimization method of acceleration drive control for electric racing cars based on adaptive neuro fuzzy inference system is proposed aiming at enhancing the acceleration performance of electric racing cars at medium and low speed by improving the traditional fuzzy control which relies heavily on the experience of operators and has low control accuracy.In this method,the maximum speed corresponding to the current accelerator pedal opening is taken as the driver′s expected speed,the deviation between the driver′s expected speed and the actual speed and its change rate as the input variables,and the accelerator pedal correction coefficient as the output variable.The modified accelerator pedal opening is obtained by multiplying the accelerator pedal correction coefficient with the current accelerator pedal opening.The results of MATLAB/Simulink simulation and real vehicle test show that under the same operation control for the accelerator pedal,the optimized drive control method has an increased opening of the accelerator pedal,and a corresponding increase of the car speed by 20.9% and 17.4% respectively at the end of acceleration compared with that before optimization.