Fault Diagnosis of Gearbox Based on Complementary Ensemble Empirical Mode Decomposition and Kernel Fuzzy Clustering Algorithm

A bearing fault diagnosis method based on complementary ensemble empirical mode decomposition (EEMD) and kernel fuzzy c-means (KFCM) algorithm is proposed to address the difficulties in feature extraction and fault diagnosis of wind turbine gearbox vibration signals. Based on empirical mode decomposition method, complementary ensemble empirical mode decomposition is proposed for the decomposition of gearbox vibration signals, obtaining multiple intrinsic mode functions. By calculating the sample entropy of the intrinsic mode function components as feature vectors, the kernel fuzzy c-means algorithm is used to achieve gearbox fault diagnosis. The experimental results show that the proposed method can effectively identify gearbox faults. In order to verify the progressiveness of the proposed method, the proposed method is compared with other methods. The experimental results show that the proposed method has higher fault diagnosis accuracy, which verifies the progressiveness of the proposed method.