Fault Diagnosis of Overflow Valve Based on Trispectrum

Wenbing Wu

doi:10.4236/wjet.2020.84055

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

Introduction

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

Data Acquisition and Dynamic Test Program

Two-Dimensional Slice of Trispectrum

Multi-Scale Decomposition of Two-Dimensional Wavelet

Analysis of Results

Findings

Conclusion