摘要
利用交流电动机的磁链方程和定子电压方程构造神经网络速度观测器来获得电动机的转速,观测器简单易行,通过遗传算法来优化神经网络的权值,使神经网络的权值达到最优。最后通过Matlab/Simulink仿真和实验研究,验证了系统设计的有效性和可行性。
The speed of induction motor was acquired using neural network speed sensorless constructed from the flux equation and stator voltage equation. The observer is simple and obtains the neural networks global optimization by optimizeining the right value of the neural network by using the genetic algorithm. Matlab/Simulink simulation and experiments verify the efficiency and feasibility of the system design.
出处
《盐城工学院学报（自然科学版）》
CAS
2009年第3期47-50,共4页
Journal of Yancheng Institute of Technology:Natural Science Edition
关键词
直接转矩控制
无速度传感器
遗传算法
神经网络
direct torque control
speed sensor - less
genetic algorithm
neural network
