Fault Diagnosis of the Traction System Based on Wavelet Analysis and Deep Belief Network
A novel fault diagnosis method based on wavelet analysis and deep belief network was proposed to locate faults of traction system accurately. Locomotive traction system data was collected and preprocessed, including those under normal and failure mode. Then, a wavelet analysis technology was applied...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Control and Information Technology
2019-01-01
|
| Series: | Kongzhi Yu Xinxi Jishu |
| Subjects: | |
| Online Access: | http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2019.05.400 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | A novel fault diagnosis method based on wavelet analysis and deep belief network was proposed to locate faults of traction system accurately. Locomotive traction system data was collected and preprocessed, including those under normal and failure mode. Then, a wavelet analysis technology was applied to extract feature vectors of signals. The wavelet energy distribution and wavelet entropy of signals were calculated and composed as the feature vectors. Based on the vectors which were regarded as the training data, a deep belief network model for fault diagnosis of locomotive traction system was established. Finally, the recording off-line fault data of locomotive was used to test and verify the performance of our model. Results suggest that our method enables diagnosing the fault of locomotive traction system with high accuracy. |
|---|---|
| ISSN: | 2096-5427 |