Signal feature extraction based on wavelet fuzzy network with application to mechanical fault diagnosis

摘要

To improve the performance of fault diagnosis technology for vibrant faults of aeroengine, a novel approach combining the wavelet transform with fuzzy theory is proposed. The method with statistic rule is used to determine the threshold of each order of wavelet space and the decomposition level adaptively, increasing the signal-noise-ratio. The effective eigenvectors are acquired by wavelet transform and the fault patterns are classified by fuzzy diagnosis equation based on correlation matrix. The fault diagnosis model of aeroengine is established and the extended Kalman filter algorithm is used to fulfill the network structure. Also the robustness of fault diagnosis equation is discussed. By means of choosing enough samples to train the fault diagnosis equation, the type of fault can be determined on basis of the input information representing the faults. The actual applications show that the proposed method can effectively diagnose vibration fault of aeroengine.