Fault Diagnosis of Wind Turbine Drivetrains Using XGBoost-Assisted Feature Selection and a CNN-Transformer Network

Conventional vibration-based condition monitoring of wind turbine drivetrains typically relies on feature extraction guided by expert experience and prior knowledge. However, the effectiveness of this approach is often limited when such knowledge is insufficient or when fault features are obscured by high levels of ambient noise. To address these challenges, this paper proposes an innovative data-driven framework that integrates intelligent feature extraction with a deep learning architecture. In the proposed approach, bearing vibration signals are converted into the frequency domain, and the frequency spectrum is divided into multiple frequency bands. The relative importance of each band is evaluated and ranked using XGBoost, enabling the selection of the most informative features and significant dimensionality reduction. A hybrid CNN–Transformer model is then employed to combine local feature extraction with global attention mechanisms for accurate fault classification. Experimental evaluations using two open-source datasets demonstrate that the proposed framework achieves high classification accuracy and rapid convergence, offering a robust and computationally efficient solution for wind turbine drivetrain fault diagnosis.