Bearing Fault Diagnosis Method of Wind Turbine Based on Improved Anti-Noise Residual Shrinkage Network

Abstract

Aiming at the difficulty of rolling bearing fault diagnosis of wind turbine under noise environment, a new bearing fault identification method based on the Improved Anti-noise Residual Shrinkage Network (IADRSN) is proposed. Firstly, the vibration signals of wind turbine rolling bearings were preprocessed to obtain data samples divided into training and test sets. Then, a bearing fault diagnosis model based on the improved anti-noise residual shrinkage network was established. To improve the ability of fault feature extraction of the model, the convolution layer in the deep residual shrinkage network was replaced with a Dense-Net layer. To further improve the anti-noise ability of the model, the first layer of the model was set as the Drop-block layer. Finally, the labeled data samples were used for training model and the trained model was applied to the test set to output the fault diagnosis results. The results showed that the proposed method could achieve the fault diagnosis of wind turbine bearing more accurately in the high noise environment through comparison and verification.

An evaluation method of health condition for wind turbine based on asymmetric proximity

“…To address the bearing fault diagnosis, the methods based on current-demodulated signals and SCADA data respectively were proposed in Gong et al (2013) and Encalada-Dávila et al (2021). In Li et al (2022), an Improved Anti-Noise Residual Shrinkage Network was proposed to bearing fault diagnosis issue. Li et al (2021) proposed a data-driven approach to monitor and identify the wind turbine generator bearing faults.…”