Feature extraction for engine fault diagnosis by utilizing adaptive multi-scale morphological gradient and non-negative matrix factorization

Signal processing and feature extraction are key steps for gear fault diagnosis. The morphological gradient (MG) algorithm, which can enhance the impulsive components and depress noise in the signal, is employed to extract the useful signal components hiding in the original signal with strong noise. Furthermore, non-negative matrix factorization technology is utilized to calculate the features of the signal processed by MG for gear fault diagnosis. The application results in practical gear fault diagnosis have demonstrated the superiority of the proposed feature extraction scheme over the traditional signal processing and feature extraction methods.