【摘要】 研究电动汽车的电子差速控制器,可有效的提高电动汽车行驶的稳定性,难点在于如何改进电动汽车的电子差速控制算法。针对经典的电子差速控制算法——BP神经网络算法收敛速度慢和易陷入局部最优解的缺陷,提出了PSO-BP神经网络的电子差速控制算法,并设计了基于该算法的电子差速控制模型。通过将采用BP神经网络算法和PSO-BP神经网络算法的电子差速控制结果进行比较,结果表明,利用PSO-BP神经网络算法解决了BP神经网络算法的固有缺陷,算法的收敛速度更快,电子差速模型的训练验证样本均方误差和转速的预测误差更小,优化了电动汽车的差速控制。更多还原

【Abstract】 The study on electronic differential controller of electric vehicle can effectively improve the stability of electric vehicle. The difficulty is how to improve the electronic differential control algorithm of electric vehicle. Aiming at,the defects of the convergence speed and the local optimum solution of BP neural network algorithm,an electronic differential control algorithm for PSO-BP neural networks was proposed,and the electronic differential control model based on the algorithm was designed. The results of electronic differential control were compared with BP neural network algorithm and PSO-BP Neural network algorithm. The results show that the inherent defects of BP neural network algorithm are solved by using PSO-BP neural network algorithm,and the convergence speed of the algorithm is faster,the training of electronic differential model validates that the mean square error and the prediction error of rotational speed of sample are smaller. The differential control of EV is optimized.更多还原