无刷直流电机直接转矩神经模糊控制研究

Research of DTC for BLDCM Based on Neural Network and Fuzzy Control

为简化无刷直流电机控制系统结构的同时又能使其具有较快的转矩响应速度,提出一种适用于无刷直流电机直接转矩控制的神经网络模糊推理控制方案,用神经网络定子磁链观测器取代传统的定子磁链观测器,采用模糊控制算法设计逆变器开关状态选择器。利用MATLAB对系统两种不同控制方法的仿真实验结果进行比较,通过比较得出,本文的控制方法转矩、转速、磁链响应快、脉动小,具有优良的稳定跟踪性能和较快的动态响应,具有一定的工程研究价值。

For enable it during simplification BLDCM control system structure to have the quick torque speed of response, the DTC strategy for BLDCM based on fuzzy logic and neural network was proposed. With the trained neural network, the stator flux observer was established, and the fuzzy control algorithm was applicated with state switch selector. Simulation experiment results for two kinds of different control methods was comparde using MATLAB. Through comparison discovery, the control torque, speed and flux response was fast, and response fluctuating was small, it had a good steady-state tracking performance and dynamic response.