Three-phase asynchronous motor fault diagnosis based on sparse self-coding neural network
暂无分享,去创建一个
Aiming at the problems of poor anti-interference ability, high false alarm rate and difficulty in extracting fault feature frequency in traditional motor fault diagnosis methods, this paper presents a three-phase asynchronous motor fault diagnosis model based on sparse auto-encoding neural network. First of all, using ANSOFT software to simulate four different faults of the motor, select ABC three-phase current as the input signal. Then, the fault features are extracted from the three-phase input current by means of sparse self-coding neural network. Finally, using support vector machine (SVM) for classification. The experimental results show that the method based on sparse self-coding neural network can extract the fault characteristics well and complete the fault diagnosis of Asynchronous motor.
[1] David J. Field,et al. Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.
[2] Simon J. Doran,et al. Stacked Autoencoders for Unsupervised Feature Learning and Multiple Organ Detection in a Pilot Study Using 4D Patient Data , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.