Migration fault diagnosis method based on deep joint distribution alignment

Abstract

The invention relates to a migration fault diagnosis method based on deep joint distribution alignment, and belongs to the technical field of mechanical fault diagnosis. The method comprises the following steps: S1, collecting vibration signals of different working conditions and different measuring points on the mechanical equipment; carrying out sample data set expansion on the collected vibration signals, and dividing the expanded data set into a training set and a test set; S2, constructing a deep joint distribution alignment migration diagnosis model; S3, inputting the training set into the constructed migration diagnosis model, and performing iterative updating training on the deep joint distribution alignment migration diagnosis model by using a source domain labeled sample classification loss function and a joint distribution alignment loss function between the source domain and the target domain; S4, after repeated iterative training, enabling the error curve tend to be stable, and completing model training; and S5, applying the trained migration diagnosis model to planetary gearbox fault migration diagnosis at different measuring points and under different working conditions. According to the invention, the migration diagnosis precision is improved.

Description

technical field [0001] The invention belongs to the technical field of mechanical fault diagnosis and relates to a migration fault diagnosis method based on deep joint distribution alignment. Background technique [0002] Under the premise of a large number of labeled samples and no data set bias, the intelligent fault diagnosis model based on deep learning has attracted the attention of a large number of researchers. In recent years, in order to expand the application range of deep learning, intelligent fault diagnosis methods based on deep transfer learning have been proposed, and have achieved certain success under non-ideal data conditions such as imbalance and small samples. However, traditional transfer learning algorithms mainly focus on the study of marginal distribution alignment, but ignore the inter-class conditional distribution alignment between target and source domains. Therefore, the diagnostic accuracy of the existing intelligent migration fault diagnosis m...

AI Technical Summary

Problems solved by technology

However, traditional transfer learning algorithms mainly focus on the study of marginal distribution alignment, but ignore the inter-class conditional distribution alignment of target domain and source domain.

Therefore, the diagnostic accuracy of the existing intelligent migration fault diagnosis model is not high enough, and a new migration fault diagnosis method with higher accuracy is urgently needed

Images