Abstract :
With the improvement of equipment intricacy and automation, it is more important for equipment failure diagnosis. In this paper, we propose a diagnostic model to automatically detect and identify faults in manufacturing processes by using a wavelet-based method. The idea behind our method is to use an image processing system that performs the following phases: image capturing, image preprocessing, determination of region of interest, object segmentation, computations of object features and decision-making. Moreover, the frequency spectrum analysis method and the gear, automatic monitoring system are introduced. Afterwards, the wavelet transform is used to decompose the vibration acceleration signals of ball bearing faults to different scales, and the resonance frequency band is extracted. Finally, the analysis and validation have been done by using the gear box fault data. The results show that the method is very effective.
Keywords :
ball bearings; condition monitoring; decision making; failure analysis; fault diagnosis; feature extraction; gears; image segmentation; spectral analysis; vibrations; wavelet transforms; automatic monitoring system; ball bearing; decision-making; equipment failure diagnosis; feature extraction; frequency spectrum analysis method; gear fault detection; image capturing; image preprocessing; manufacturing processes; object segmentation; resonance frequency band; vibration acceleration signal decomposition; wavelet transform; wavelet-based method; Decision making; Equipment failure; Fault detection; Fault diagnosis; Gears; Image processing; Manufacturing automation; Manufacturing processes; Object segmentation; Wavelet transforms; fault diagnosis; gear box; wavelet transformt;
