Mechanical bearing fault diagnosis method based on time-frequency spectrogram and two-dimensional principal component analysis

• Main Authors: YU HONG, SU ZUQIANG, LUO ZI'AO, LUO JIUFEI, XIAO HONG
• Format: Patent
• Language: Chinese; English
• Published: 17.09.2019
• Subjects: CALCULATING; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; MEASURING; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; TESTING; TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES; TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR

The invention relates to the technical fields of mechanical fault diagnosis, pattern recognition and the like, in particular to a mechanical bearing fault diagnosis method based on a time-frequency spectrogram and two-dimensional principal component analysis, which comprises the following steps of receiving and preprocessing the original signal data to obtain an initial vector of the original signal data; performing the short-time Fourier transform time-frequency analysis on the initial vector to obtain a short-time Fourier transform three-dimensional time-frequency spectrogram corresponding to the original signal; carrying out the gray-scale map conversion on the short-time Fourier transform three-dimensional time-frequency spectrogram to obtain a two-dimensional time-frequency spectrogram; performing the dimensionality reduction on the two-dimensional time-frequency spectrogram, and extracting to obtain a low-dimensional characteristic matrix corresponding to the two-dimensional time-frequency spectrogram;