Rotating Machinery Fault Diagnosis Method by Combining Time-Frequency Domain Features and CNN Knowledge Transfer

Abstract

Aiming at the problem of fault diagnosis when there are only a few labeled samples in the large amount of data collected during the operation of rotating machinery, this paper proposes a fault diagnosis method based on knowledge transfer in deep learning. First, we describe the data collected during the operation as a two-dimensional image with both time and frequency-domain characteristics. Second, we transform the trained source domain model into a shallow model suitable for small samples in the target domain, and we train the shallow model with small samples with labels. Third, we input a large number of unlabeled samples into the shallow model, and the output result of the system is regarded as the label of the input sample. Fourth, we combine the original data and the data annotated by the shallow model to train the new deep CNN fault diagnosis model so as to realize the migration of knowledge from the expert system to the deep CNN. The newly built deep CNN model is used for the online fault diagnosis of rotating machinery. The FFCNN-SVM shallow model tagger method proposed in this paper compares the fault diagnosis results with other transfer learning methods at this stage, and its correct rate has been greatly improved. This method provides new ideas for future fault diagnosis under small samples.

Keywords

• fault diagnosis
• transfer learning
• knowledge transferring
• model transferring
• deep CNN