摘要
利用人工神经网络在处理非线性、不确定问题上的优势,提出一种基于FRA优化的RBF神经网络实现无刷直流电机的无位置传感器控制,通过对电机相电压和相电流的映射,估算出准确的电机换相信号。实验结果验证了本文方法的有效性。
In order to obtain the position information of brushless DC motor for position sensorless control,and to take advantage of neural network which is excellent for nonlinear and indeterminate problem,a sensorless control strategy of brushless DC motor based on RBF neural network optimized by fast recursive algorithm is proposed in this paper.The strategy estimated the commutation signals by mapping phase currents and phase voltages of motor through RBFNN,and experimental results validates the proposed control method in this paper.
出处
《船电技术》
2010年第10期33-35,38,共4页
Marine Electric & Electronic Engineering
关键词
无刷直流电机
无位置传感器
径向基
快速回归算法
神经网络
brushless DC motor
sensorless
radial basis function
fast recursive algorithm
neural network