带补偿的神经网络辩识器在异步电机调速系统中的应用

Neural Network Identifier with Fuzzy Logic Compensation Applied to Induction Motor Dynamic System

本文提出了一种带模糊补偿的神经网络算法并应用在异步电机速度控制系统中。一个动态神经网络用于被控装置的在线辨识 ,然后根据被控装置的输出和参考模型的响应迭代出控制信号 ,具有四条简单规则的模糊逻辑块用于提高整个系统的闭环特性。仿真结果显示 ,对比传统的最优PID控制器 ,本文提出的控制策略具有更好的瞬变特性及抗干扰特性。

This paper presents a new neural network algorithm with fuzzy logic compensation applied to induction motor drive speed control system. A dynamic neural network is used to identify the plant on-line. The control signal is then calculated iteratively according to the responses of a reference model and the output of identified plant. A fuzzy logic block with four very simple rules is added to the loop to improve the overall loop properties. Simulation demonstrates the proposed control strategy provides better disturbance rejection and transient properties than those achieved by a conventional optimally tuned PID controller.