基于BP神经网络的电动车电子差速器设计

Design of Electronic Differential for Electric Vehicle Based on BP Neural Network

针对双电机独立轮式驱动电动汽车,介绍了一种汽车行驶数据测量系统;考虑汽车转向行驶时内、外侧车轮转速与转向角和车体速度之间的非线性关系,提出了一种新型结构的基于BP神经网络原理的电子差速方案;设计了训练和在线计算算法,并编写了C语言计算机程序;仿真验证了该差速器的可行性。

A vehicle driving data acquisition system for an electric vehicle with dual in-wheel motors drive is presented. Considering the nonlinear feature of the rotation speeds of the inner and outer wheels in relation to the vehicle speed and steering angle, a new structure of electronic differential based on BP neural network is proposed. Accordingly, the calculation and training algorithms are designed with a program in C language developed. Simulation results verify the feasibility of the differential.