Abstract
The high-order spectrum can effectively remove Gaussian noise. The three-spectrum and its slices represent random signals from a higher probability structure. It can not only qualitatively describe the linearity and nonlinearity of vibration signals closely related to mechanical failures, Gaussian and non-Gaussian Performance, and can greatly improve the accuracy of mechanical fault diagnosis. The two-dimensional slices of trispectrum in normal and fault states show different peak characteristics. 2-D wavelet multi-level decomposition can effectively compress 2-D array information. Least squares support vector machine can obtain the global optimum under limited samples, thus avoiding the local optimum problem, and has the advantage of reducing computational complexity. In this paper, 2-D wavelet multi-level decomposition is used to extract features of trispectrum 2-D slices, and input LSSVM to diagnose the fault of the pressure reducing valve, which has achieved good results.
Highlights
High-order spectra can effectively remove Gaussian noise
The three-spectrum and its slices represent random signals from a higher probability structure. It can qualitatively describe the linearity and nonlinearity of vibration signals closely related to mechanical failures, Gaussian and non-Gaussian Performance, and can greatly improve the accuracy of mechanical fault diagnosis
2-D wavelet multi-level decomposition is used to extract features of trispectrum 2-D slices, and input LSSVM to diagnose the fault of the pressure reducing valve, which has achieved good results
Summary
High-order spectra can effectively remove Gaussian noise. The trispectrum and its slices can qualitatively describe the linearity and nonlinearity of vibration signals closely related to mechanical faults, and the performance of Gaussian and non-Gaussian, and greatly improve the diagnosis accuracy of mechanical faults [1]. On the basis of obtaining the trispectrum 2-D slice spectrum of the vibration signal of the speed control valve, the 2-D wavelet multi-level decomposition is used to extract the features of the bi-coherent spec-. The least square support vector machine is input to judge the faults
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have