自回归神经网络稳定性的超声波电机伺服控制

Servo Control Research of Ultrasonic Motor Based on Regression Neural Network

针对超声波电机的速度/位置伺服控制,提出使用基于自回归神经网络和Lyapunov稳定性的控制算法,可以在一定程度上反映超声波电机的输入输出非线性关系。由于自回归神经网络可以在线调整其参数值,因此当电机运行参数发生变化时,可以通过改变神经网络辨识参数来实现速度和位置的快速跟踪,并通过Lyapunov稳定性进行控制参数调整。研究表明,使用此算法的伺服系统对超声波电机进行伺服控制,可以达到快速响应和良好的控制效果。

Ultrasonic motor(USM)is a system of severe non-linearity and parameter variations.Due to that,common PID control methods can′t meet practical demands.This paper introduces a novel control system which is based on autoregression neuron network and combined with theory of Lyapunov stability. Because neuron controller can change its parameters online when operation conditions are changed,it can also change its control characteristic automatically to realize speed and position control by Lyapunov stability.The research results show that USM can complete rapid response speed and high precise position control while using this kind of controller based on neuron algorithm.