Skip to content
2000
Volume 15, Issue 1
  • ISSN: 2352-0965
  • E-ISSN: 2352-0973

Abstract

Background: The generator is a mechanical device that converts other forms of energy into electrical energy. It is widely used in industrial and agricultural production and daily life. Methods: To improve the accuracy of generator fault diagnosis, a fault classification method based on the Bare-bones Cuckoo Search (BBCS) algorithm combined with an artificial neural network is proposed. For this BBCS method, the bare-bones strategy and the modified Levy flight are combined to alleviate premature convergence. After that, the typical fault features are obtained according to the vibration signal and current signal of the generator, and a hybrid diagnosis model based on the Back- Propagation (BP) neural network optimized by the proposed BBCS algorithm is established. Results: Experimental results indicate that BBCS exhibits better convergence performance in terms of solution quality and convergence rate. Furthermore, the hybrid diagnosis method has higher classification accuracy and can effectively identify generator faults. Conclusion: The proposed method seems effective for generator fault diagnosis.

Loading

Article metrics loading...

/content/journals/raeeng/10.2174/2352096514666211215143628
2022-02-01
2025-06-01
Loading full text...

Full text loading...

/content/journals/raeeng/10.2174/2352096514666211215143628
Loading
This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test