A Mechanical Fault Diagnosis Method Based on Planar Clustering and Frequency-Domain Compressed Sensing Reconstruction

Abstract

The invention relates to a plane clustering and frequency-domain compressed sensing reconstruction based mechanical fault diagnosis method and belongs to the technical field of mechanical equipment state monitoring and fault diagnosis. The method includes: collecting observation signals of mechanical vibration; subjecting the observation signals to equalization, then creating a triangular structure and semicircular structure element set, then constructing an improved multi-structured generalized closing-opening combined morphological filter, and filtering observation signal equalization results to obtain filter signals; estimating a hybrid matrix for the filter signals through a plane clustering algorithm; constructing a sensing matrix, applying orthogonal matching pursuit based frequency-domain compressed sensing reconstruction to estimate source signals, performing FFT (fast Fourier transform) on the estimated source signals, and then analyzing frequency domain on the transformed signals to finally realize fault diagnosis. The signals are not required to fully meet sparsity, influence on fault recognition of the separated source signals due to other interference signals can be fully weakened, and underdetermined blind separation of combined faults of bearings is realized.

Description

technical field [0001] The invention relates to a mechanical fault diagnosis method based on plane clustering and frequency domain compressed sensing reconstruction, and belongs to the technical field of mechanical equipment state monitoring and fault diagnosis. Background technique [0002] Due to the complex mechanical structure and the observation signal picked up by the industrial field test sensor is often a mixed signal of the fault source signal and other noise signals. In recent years, blind signal processing techniques, which can recover or estimate the source signal from the mixed signal with almost no prior knowledge, have provided a powerful solution to the extraction of mechanical fault signals. However, when the traditional SCA algorithm is applied to mechanical vibration signal processing, it often cannot meet the actual situation, and cannot effectively identify and extract mechanical fault features; while the improved SCA algorithm is more suitable for the a...

AI Technical Summary

Problems solved by technology

[0006] In addition, most of the existing SCA algorithms estimate the source signal through the mixing matrix when the number of sources is known. However, the industrial site background noise is strong and there are many interference sources, so the number of fault sources in the actual test process is not clear in advance.

Images