Data-driven fault detection of a 10 MW floating offshore wind turbine benchmark using kernel canonical variate analysis

Floating offshore wind turbines (FOWTs) can harvest more wind energy in deep water. However, due to their complex mechanical structure and harsh working conditions, various sensors, actuators, and components of FOWTs can malfunction and fail. To avoid serious accidents and reduce operation and maintenance costs, fault detection plays a critical role in wind-energy engineering, particularly for offshore wind energy. Because of complex characteristics, such as dynamics and nonlinearity, an accurate mathematical model cannot be easily obtained from first principles for FOWTs. In this paper, a new data-driven fault-detection method based on kernel canonical variable analysis (KCVA) is proposed for FOWTs. In the proposed method, the collected measurements are first augmented into time-lagged variables to capture the dynamics of FOWTs. The time-lagged variables are then mapped to a high-dimensional feature space to extract nonlinear features. Specifically, canonical variable analysis (CVA) is carried out to explore the correlations in high-dimensional feature space. For fault detection, two monitoring indexes including T 2 and squared prediction error ( S P E ) statistics are established. To verify the performance of the proposed KCVA-based fault-detection method, experiments on a high-fidelity FOWT benchmark, which was created from the National Renewable Energy Laboratory Fatigue, Aerodynamics, Structures, and Turbulence v8.0 simulator, were carried out. The results show the capability and efficiency of the proposed KCVA-based fault-detection method in comparison with other related methods.