Application research on fault diagnosis of double fed wind turbine bearings based on improved generative adversarial networks
HU Weijun
LI Daoquan
HU Jijun
Abstract：Aiming at the problem of the low fault diagnosis accuracy caused by the lack of fault samples for the rolling bearings of doubly fed wind turbines under normal conditions for a long time,an improved generative adversarial network fault diagnosis method based on expanding high-quality fault samples and using dual feature extraction was proposed.Firstly,a finite number of rolling bearing fault samples were expanded through a Wasserstein type generative adversarial network with maximum mean discrepancy and penalty constraints.Secondly,based on the dual feature extraction model,the time-frequency converted temporal features and local features were extracted separately.Finally,the fault diagnosis of the rolling bearing balance data was completed through a classifier.The standard dataset and test results show that the proposed method improves the fault diagnosis performance while lacking fault samples.
Keywords：Generative adversarial networkBidirectional gated recurrent unitDouble fed wind turbineFault diagnosis
Publication Date：2025-10-15
Online Publishing Date：2026-09-12(First online date of this platform, not the publication date of the document)
Pages：10( 26-35 )