Keywords: deep transfer learning, domain adaptation, variable working conditions diagnosis, high-speed train bogie, axle bearing diagnosis, deep learning.

Due to the increasing speed of high-speed trains, intelligent fault diagnosis of train bogies is facing new problems: the diagnostic model for lower speeds is no longer applicable, and the lack of fault labels for high speed data makes the training of deep learning diagnostic models even more difficult. In order to be able to reliably diagnose unlabeled signals of different speeds using a limited number of labeled fault samples, this paper conducts an experiment and comparison of the effects of transfer learning on bearing faults of a real train. experiments and migration learning effects are compared. The axle bearing failure simulation experiment was conducted on a real high-speed train car using a rolling test bed, and the monitoring data with fault labels at different speeds were obtained, then the cross-migration was conducted using multiple speed monitoring data and multiple migration learning methods to obtain the cross-speed migration learning fault diagnosis effect, finally, the comparison of the distributional differences and the migration learning effect dataset was used to ensure the migration learning model could accomplish the monitoring at higher speeds. model can accomplish higher speed monitoring data migration diagnosis. At the same time, this paper uses a variety of signal pre-processing methods, network models and migration learning methods in the proposed framework for comparison, further verifying the feasibility and stability of the prediction method, and gives the optimal application of reference suggestions.

download the full-text of this paper (PDF, 12 pages, 1027 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description