A New Method of Aero-engine Bearing Fault Diagnosis Based on EMD Decomposition

Traditional vibration fault diagnosis methods include wavelet transform, modal analysis and so on. It is found that the instantaneous impact components associated with the fault in the engine bearing vibration signals are sparse in the time-frequency transform domain. For this property, a sparse signal representation using dictionary learning based on EMD decomposition and a sparse signal reconstruction method based on orthogonal matching pursuit (OMP) algorithm are proposed in this paper. Firstly, empirical mode decomposition (EMD) and wavelet denoising methods are used to pre-process the vibration signal to eliminate the harmonic and noise interference; Secondly, a super complete dictionary is constructed by using singular value decomposition algorithm to achieve the sparse representation of the signal; Finally, the sparse reconstruction of fault features is realized by using orthogonal matching pursuit algorithm. Simulation and experimental results show that the proposed method can reduce the interference of background noise and impurity frequency more effectively, and verify the effectiveness and applicability of the proposed method for aero-engine bearing fault feature extraction.