AN IMPACT FAULT DETECTION METHOD OF MARINE CURRENT TURBINE BLADE VIA EGK-MEANS AND PCA
The operating conditions of MCTs are affected by varying water velocity and random turbulence.The blades of the MCT s are prone to cracks due to long-term exposure to sea water and are quickly impacted by fish or seabed creatures.Frequent changes in marine currents lead to variable working conditions.A detection method based on envelop geometrical K-means(EGK-means)to divide the stator current signals generated under variable conditions and establish fault detection models is proposed.First,construct the envelope geometric feature based on the sample matrix,use the geometric feature matrix to select the initial clustering center for clustering,perform PCA modelling based on the current data under each working condition to reduce the data dimension.Finally,the T2 and SPE statistics are calculated for real-time fault detection.A prototype MCT and supporting circulating water tank were built to verify the proposed method.The diagnostic results verify that the proposed method has significant recognition ability and detection accuracy for the impact faults of MCTs under variable marine conditions.
万方数据
维普
