中文摘要：

超声波电动机是一个高度非线性系统,采用传统控制方法无法取得良好的控制效果.为了研究超声波电动机在有负载工况下的性能并实现其在工程领域的推广应用,必须找到一种有效的控制方法.BP神经网络PID控制器非常适合非线性系统的控制,具有结构简单、鲁棒性好、PID参数能在线实时调整的优点,设计了一种BP神经网络PID控制器,用于旋转型超声波电动机的转速控制研究.控制器的输入层节点数为3,隐含层点数为5,输出层节点数为3.通过一系列试验研究,发现采用BP神经网络PID控制取得了较好的控制效果,为超声波电动机的工程应用找到一种有效可行的控制方法.

英文摘要：

Ultrasonic motor is a highly nonlinear system,using the traditional control method can not obtain good effect.In order to research the properties of ultrasonic motor with load condition and realize the application of ultrasonic motor in the engineering field,we should find a better control method.BP neural network PID controller is very suitable for the control of nonlinear systems,and it has a simple structure,good robustness,real-time adjustment of PID parameters.A BP neural network PID controller was designed to study the speed control of rotary ultrasonic motor.Input layer node number is 3,hidden layer node number is 5,and output layer node number is 3.BP neural network PID control achieves good control effect by a series of experimental study,and is an effective and reliable control method for the engineering application of ultrasonic motor.