改进模糊神经网络无刷直流电机控制系统设计  

Design of Brushless DC Motor Control System Based on Improved Fuzzy Neural Network

作　　者：李世超[1] 石秀华[1] 孙希通[1] 魏照宇[1] 

机构地区：[1]西北工业大学航海学院,陕西西安710072

出　　处：《计算机仿真》2009年第10期153-156,165,共5页Computer Simulation

基　　金：西北工业大学研究生创新种子基金(Z200705)

摘　　要：针对现实应用中对无刷直流电机速度控制的极高精度要求,设计了一种改进的自适应遗传算法优化的模糊神经网络控制系统,并采用离线和在线两种学习方法,实现了对无刷直流电机转速的精确控制。系统融合了模糊逻辑、神经网络和遗传算法三大智能控制理论的优点,适合于无刷直流电机这样的多变量、强耦合、非线性、时变的复杂系统。通过仿真和在某型水下航行器DSP推进控制系统上的实验表明,方法响应快、超调量小、鲁棒性强,动态特性明显优于传统PID控制。This paper proposes an improved fuzzy neural network controller system based on adaptive genetic algorithms aiming at extreme precision demand of actual brushless DC motor speed control. By means of offline and online learning methods, the rotating speed of brushless DC motor can be precisely controlled. This system combines the merits of fuzzy logic, neural network as well as genetic algorithm together, and is suitable for the complicated brush- less DC motor system which contains many variants, strong coupling, non - linear and time variable characteristics. The results of simulation and experiment of AUV impetus system with DSP illustrate that rapid response and robustness can be achieved by this method, and the dynamic characteristic of this method is much better than that of traditional PID controler.

关 键 词：模糊控制 神经网络 无刷直流电机 遗传算法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP273[自动化与计算机技术—控制科学与工程]