改进型BP神经网络无刷直流电机速度控制方法

Speed Control Method of Brushless DC Motor Based on Improved BP Neural Network

针对传统PID算法控制的无刷直流电机调速系统存在控制精度低、抗干扰能力差等问题,提出一种在线调整学习速率的BP神经网络PID控制算法,有效克服了前者陷入局部最小和收敛速度慢等缺陷。建立无刷直流电机转速、电流双闭环调速系统数学模型,对其转速环进行BP神经网络PID控制;应用Matlab/Simulink设计与仿真,并将之安装在电动代步车上进行道路实际测试。结果表明:改进后的BP神经网络PID控制算法使无刷直流电机调速系统具有更好的稳定性和鲁棒性。

Aiming at the problems of low control accuracy and poor anti - jamming ability of the speed control system of brushless DC motor controlled by traditional PID algorithm , a BP neural network PID control algorithm with on - line learning rate adjustment is proposed , which effectively overcomes the problems of local minimum and slow convergence speed existing in ordinary BP neural network algorithm.The mathe - matical model of speed and current double closed - loop speed regulation system of BLDCM is established , and the BP neural network PID control is applied to the speed loop of BLDCM.The design and simulation of matlab / Simulink and the actual road test of electric bicycle are carried out.The results show that the improved BP neural network PID control algorithm makes the speed control system of BLDCM have better stability and robustness.