Failure classification of wind turbine operational conditions using hybrid machine learning
Abstract. Wind turbines are complex electromechanical systems that require continuous monitoring to ensure operational efficiency, reduce maintenance costs, and prevent critical failures. Machine learning has shown great promise in structural health monitoring (SHM) by enabling automated fault detection through data-driven approaches. However, challenges remain in adapting SHM methods to complex environmental conditions while maintaining reliable fault detection and classification. This work proposes a hybrid model that combines supervised and unsupervised learning techniques for classifying operational failures in wind turbines. The proposed framework integrates multiphysics data, combining structural and environmental information, to monitor four distinct operational states. The approach begins with the analysis of sensor signals and the extraction of descriptive features that capture the dynamic behaviour of the turbine. The k-means algorithm is applied to label and cluster the dataset, while feature and sensor selection are performed using canonical correlation analysis to rank the most informative variables. A novel relative change damage index is introduced to normalise and scale features based on their relative variability, enhancing the accuracy of clustering and fault classification. Classification is conducted using six different machine learning algorithms. Experimental results demonstrate strong performance in both binary and multiclass tasks, including the detection of pitch drive faults and the accurate identification of rotor icing and aerodynamic imbalance. The model achieved up to 100 % classification accuracy, highlighting its effectiveness in diagnosing wind turbine conditions and improving the overall reliability and operational safety of these systems.