基于BP神经网络的BLDCM换相控制系统设计

Design of BLDCM Commutation Control System Based on BP Neural Network

直流无刷电机是一个多变量、强耦合的非线性系统,针对直流无刷电机换相时抖动比较明显、速度调节时的准确性也存在误差等缺点,通过无线传输模块实现了Matlab与stm32之间的通讯,建立了基于Matlab与stm32的电机远程控制系统,实现了上位机对电机的远程控制。与此同时,还采用对直流无刷电机换相时间采样与样本训练分离的策略,解决了stm32的运算能力差的问题,并利用Matlab的强大运算能力,实现了BP神经网络在BLDCM换相控制系统中的应用。实验表明,基于BP神经网络的BLDCM换相控制系统有利于提高电机的控制精度及动态性能。该系统将在智能化的控制领域拥有更广阔的空间。

Brushless DC motor is a multi variable and strong coupling nonlinear system. For the brushless DC motor, the commutation is obvious and the accuracy of speed regulation is also error. This paper realizes the Motor remote control system based on Matlab and STM32 through the wireless transmission module. The method of motor control system based on Matlab and STM32 is established, and the remote control of the motor is realized. At the same time,The strategy of separation sampling and training of motor phase change time is adopted to solve the difference of STM32＇s computing ability. Realized the application of BP neural network in BLDCM phase change control system. The experimental results show that the BLDCM commutation control system based on BP neural network is beneficial to improve the control accuracy and dynamic performance of the motor.