Fault Diagnosis of Bearing in Wind Turbine Gearbox Under Actual Operating Conditions Driven by Limited Data With Noise Labels

Abstract

The fault characteristics of the rolling bearings of wind turbine gearboxes are unstable under actual operating conditions. Problems such as inadequate fault sample data, imbalanced data types, and noise labels (error labels) in historical data occur. Consequently, the accuracy of wind turbine gearbox bearing fault diagnosis under actual operating conditions is insufficient. Hence, a new method for the fault diagnosis of wind turbine gearbox bearings under actual operating conditions is proposed. It uses an improved label-noise robust auxiliary classifier generative adversarial network (rAC-GAN) driven by the limited data. The improved rAC-GAN realizes a batch comparison between the generated and real data to ensure the quality of the generated data and improve the generalization capability of the model in scenarios of actual operating conditions. It can be used to generate a large number of multitype fault data that satisfy the characteristics of the probability distribution of real samples and display higher robustness to label noises. Experiments indicate that, compared with other methods, the new method exhibits a higher accuracy in the multistate classification of rolling bearings under actual operating conditions when driven by the limited data with noise labels.