Fault Diagnosis Method of Rotating Machinery Based on Contractive Autoencoder

As one of the essential equipment in the industrial production process, rotating machinery usually works in complex environments such as high temperature and heavy load. Critical components such as gears and bearings are very likely to fail. This will affect the stable operation of the entire rotating machinery. Therefore, we designed a method for diagnosing faults in rotating machinery based on contractive autoencoder in this paper. First, the loss function of the contractive autoencoder is designed. Using a lot of vibration signal fragments combined with a gradient descent algorithm to optimize network parameters. Then, slice a newly collected vibration signal. And use the trained contractive autoencoder to calculate the feature vector of each segment. Next, the feature vectors of all segments are averaged and pooled to obtain the feature vector of the vibration signal sample. Finally, the extracted feature vectors are used to train a Softmax regression classifier to achieve fault identification of key parts of rotating machinery. The experimental results show that the method in this paper can accurately and effectively diagnose motor bearing faults, which is better than traditional method.