Fault Diagnosis of Doubly-Fed Induction Generators Based on Electromechanical Signal Fusion
The diagnosis of inter-turn short circuits and air-gap eccentricity faults in doubly-fed generators typically relies on analyses based on a single type of signal. However, due to the complex operating environment of generators, this practice often struggles to accurately reflect their actual operati...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Control and Information Technology
2025-02-01
|
| Series: | Kongzhi Yu Xinxi Jishu |
| Subjects: | |
| Online Access: | http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2025.01.005 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The diagnosis of inter-turn short circuits and air-gap eccentricity faults in doubly-fed generators typically relies on analyses based on a single type of signal. However, due to the complex operating environment of generators, this practice often struggles to accurately reflect their actual operating state. This paper proposes a fault diagnosis method for doubly-fed generators based on the fusion of electromechanical signals. Firstly, rotor current, stator voltage, and stator vibration signals under various operating conditions are collected. Secondly, these current, voltage, and stator radial vibration signals are separately classified leveraging a multi-scale convolutional neural network (CNN). Then, the diagnosis of inter-turn short circuits and air-gap eccentricity faults in doubly-fed generators is implemented at the decision-making stage, through signal fusion based on dempster-shafer (DS) evidence theory, which improves both training speed and recognition accuracy. The results indicated that this method achieved a fault recognition accuracy of 99% for inter-turn short circuits and static air-gap eccentricity faults in generators. |
|---|---|
| ISSN: | 2096-5427 |