摘要
常规速度辨识器中的辨识模型易受到积分初值和漂移问题的影响,产生辨识结果不准确的问题。本文在研究模型参考自适应和直接转矩控制理论的基础上,设计了基于神经网络的无速度传感器模型。仿真结果表明,与传统速度辨识模型相比,神经网络辨识系统有较好的性能。
The normal model can always be affected because of the initial value and excursion of integral calculation in traditional speed identifier,which leads to the wrong result of identifying.This paper based on model reference adaptive system and the direct torque control,design speed sensorless model based on neural network.Simulation results show that compare to traditional speed identifier,the system with neural network identification has better performance.
出处
《机床电器》
2010年第3期7-9,共3页
Machine Tool Electric Apparatus
