基于单神经元算法的内嵌式永磁同步电机智能驱动控制

基于人工神经网络的内嵌式永磁同步电机(IPMSM)智能驱动控制性能要明显优于传统控制方法,但是存在计算量大和离线训练时间长的问题。针对该问题,提出了一种基于单神经元算法的IPMSM智能驱动控制策略。阐述了永磁同步电机的数学模型及电流转矩控制规律；并基于单神经元的控制原理,推导了驱动控制律,由于采用的是单神经元结构并设置了迭代算法的边界,因此达到了计算量减小和训练较少的效果。最后,搭建了小功率电机驱动试验平台开展了试验研究,并通过与传统PID控制的对比试验,验证了新型控制器的性能。

Intelligent Drive Control of Interior Permanent Magnet SynchronousMotor Based on Single Artificial Neuron Algorithm

The performance of the controller for interior permanent magnet synchronous motor based on artificial neural network is superior to the traditional control method, but it has the problems of large amount of computation and long training time. Aiming at it, an intelligent drive control of interior permanent magnet synchronous motor based on a single artificial neuron algorithm was presented. At first, the mathematical model of the motor and the principles of the current torque control law had been described. Then, the driving controller for the motor based on single artificial neuron had been designed, and the computation and training time had been reduced due to the use of the single neuron and set the iterative boundary. Finally, a small power motor drive test platform was built, and the performance of the new controller was verified by comparing with the traditional PID control.