基于神经网络的无刷直流电机调速系统的仿真  

Simulation of Speed-adjustment System on Neural Network Self-tuning Control for Brushless DC Motor

作　　者：罗有明[1] 张春喜[1] 

机构地区：[1]哈尔滨理工大学电气与电子工程学院,哈尔滨150040

出　　处：《黑龙江水专学报》2006年第4期72-74,共3页Journal of Heilongjiang Hydraulic Engineering College

基　　金：黑龙江省自然科学基金资助项目(E0022)

摘　　要：针对无刷直流电机调速系统性能和精度的要求,提出基于神经网络的自校正控制方法。设计了一个多层神经网络控制器。这个神经网络控制器既能辩识系统的动态性能,又能控制无刷直流电机使转速跟踪预先的轨迹,且跟踪精度高。在Matlab/Simulink环境下建立了模型并进行了仿真,结果表明该方法可改善调速系统的性能。An approach of brush-less DC motor speed-adjustment system is presented in this paper based on Neural network self-tuning control for the requirement of performance and precision. A multilevel Neural network is designed in this paper. The Neural network can distinguish the dynamic performances of the system and control brush-less DC motor to make speed follow the orbit that is choosen in advance, and the following precision is high. The system is modelled and simulated in Matlab/Simulink. The result shows that the system using the approach can greatly improve the performance of speed-adjustment system.

关 键 词：无刷直流电机 神经网络 白校正控制 Mathb/Simulink 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]