基于神经网络的开关磁阻电机转子位置在线检测技术

Rotor position estimation of switched reluctance motor based on neural network

提出了一种基于BP神经网络的开关磁阻电机转子位置在线检测方法.该方法将训练数据实时更新的思想引入到神经网络的输入向量中,利用大量实时更新的电机数据作为神经网络的训练样本在网络进行在线训练,修正网络参数,使检测结果不受渐变因素的影响.仿真结果表明,该方法能够准确地检测转子位置,鲁棒性和适应性强.

An approach of detecting the rotor position for Switched Reluctance Motors （SRM） based on BP neural network is presented. The method introduces the idea of real-time training data updating into the input vector of neural network. The neural network is trained with the SRM ＇s real-time updating samples to modify the parameters of the neural network. Results of simulation show that this scheme not only can acquire the rotor position timely and exactly but has great robustness and adaptability.