Abstract In order to achieve the detection for the fault diagnosis of the wind turbine generator bearing, firstly, the transformation of the wavelet packet is adopted to decompose the vibration signal into several layers, and denoise and reconstruct it. Secondly, this paper takes the combination of the wavelet node energy and the characteristic parameters of the denoised signal both in the time and frequency domain as the input feature vector to BP neural network with the function of self- determining hidden layer neurons. Finally, the results of the fault diagnosis are regarded as the output. The experimental data demonstrate that this method can effectively diagnose the fault types of the wind turbine generator bearing.
Analysis of the Fault Diagnosis Method for Wind Turbine Generator Bearing Based on Improved Wavelet Packet-BP Neural Network
01.01.2014
8 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
British Library Conference Proceedings | 2014
|Roller Bearing Fault Diagnosis Model with Harmonic Wavelet Packet and DT-RVM
British Library Conference Proceedings | 2015
|Europäisches Patentamt | 2024
|Improved Convolution-Type Wavelet Packet Decomposition with Applications to Fault Diagnosis
British Library Online Contents | 2014
|Fault Diagnosis Based on Optimized Wavelet Packet Transform and Time Domain Convolution Network
BASE | 2023
|