摘要
针对永磁同步电机控制系统中电流反馈环路的噪声问题,提出一个信号预分类的ANN方法。该方法通过使用三层BP神经网络对反馈信号的采样空间进行充分训练,进而建立反馈信号的ANN分类模型。使用该模型可判明每种噪声类型,为不同种类的噪声选择不同的滤波器(或截止频率)进行细致化滤波处理提供了有力的科学依据。实验结果表明该方法具有良好的效果。
The current feedback of PMSM control system has lots of noise,it causes the PMSM does not work properly. This paper proposes an ANN model to classify the current feedback to normal signal or noise. The model trains a three layers BP ANN in sample set to generate the model parameter set. The model is used to recognize the types of different noises and the results can be used as a basis for guiding the selection of filters. The experimental results show that the effect of the method is good.
出处
《智能计算机与应用》
2017年第6期39-41,46,共4页
Intelligent Computer and Applications
基金
黑龙江省教育厅科学研究项目(12541239)
