eduzhai > Applied Sciences > Engineering >

Fault Diagnosis of Overflow Valve Based on Trispectrum

  • KanKan
  • (0) Download
  • 20210225
  • Save

... pages left unread,continue reading

Document pages: 9 pages

Abstract: Thehigh-order spectrum can effectively remove Gaussian noise. The three-spectrumand its slices represent random signals from a higher probability structure. Itcan not only qualitatively describe the linearity and nonlinearity of vibrationsignals closely related to mechanical failures, Gaussian and non-GaussianPerformance, and can greatly improve the accuracy of mechanical faultdiagnosis. The two-dimensional slices of trispectrum in normal and fault statesshow different peak characteristics. 2-D wavelet multi-level decomposition caneffectively compress 2-D array information. Least squares support vectormachine can obtain the global optimum under limited samples, thus avoiding thelocal optimum problem, and has the advantage of reducing computationalcomplexity. In this paper, 2-D wavelet multi-level decomposition is used toextract features of trispectrum 2-D slices, and input LSSVM to diagnose thefault of the pressure reducing valve, which has achieved good results.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...