BP神经网络在永磁同步电机中的应用

Application of BP neural network in PMSM

永磁同步电机是一个多变量、非线性、强耦合的系统,传统PID速度控制效果不理想。在分析永磁同步电机数学模型的基础上,采用改进型BP神经网络与传统PID控制相结合作为速度控制器,应用于永磁同步电机调速系统中。在电机初始运行阶段采用传统PID控制,网络学习一段时间后,切换到经过改进的BP神经网络在线自整定PID控制,实现了电机速度的自适应控制。仿真结果表明:应用这种新型控制方式的永磁同步电机调速系统具有良好的动态性能和稳态精度。

Permanent magnet synchronous motor is a multi - variable, non - linear and strong - coupling system, the traditional PID control is not effective. Based on the mathematic model of PMSM, a combination of an improved BP neural network and a general PID controller is used in its speed control system. The general PID controller is used in the initial several seconds, and then it will be weitched to another adaptive PID controller based on neural network after training for seconds. Simulation results show that this control method can improve the dynamical performance and enhance the static precision of the speed system.