A Mechanical Impact Fault Detection Method Based on PCA for Marine Current Turbine

Marine life and Marine Current Turbine (MCT) have been colliding since the commercialization of marine power generation. Affected by the fluctuation of seawater velocity, the mechanical impact fault of blade is submerged, which is not conducive to the maintenance of MCT. Thus, a mechanical impact fault detection method based on Principal Component Analysis (PCA) for MCT is proposed in the paper. Firstly, the fault characteristics of mechanical impact and water flow impact are compared. Then, according to the different statistical characteristics, process variables with significant information are selected for PCA detection. At the end, underwater experiments with different impact fault frequency and degree are presented. The fault detection tests on MCT show that the proposed method can effectively improve the diagnosis rate.