Mechanical Fault Analysis Method Based on Wavelet Fuzzy Recognition and Image Analysis Theory

Abstract

The invention, which belongs to the technical field of signal processing, relates to a mechanical failure analysis method based on wavelet fuzzy recognition and an image analysis theory. The method comprises the following steps: collecting vibration signals, being a plurality of groups of vibration signals of a rotating machine at different positions, of the rotating machine as to-be-analyzed signals and carrying out wavelet packet decomposition on the vibration signals to obtain component amounts; determining whether the rotating machine has a fault and if so, determining an abnormal state; under the condition of the abnormal state of the rotating machine, determining a fault type and acquiring a dynamic image by using an image sensor in an abnormal state of the rotating machine; and thenon the basis of an image theory, analyzing the obtained dynamic image and determining a fault occurrence position and a fault degree. According to the invention, the rotating machine fault can be diagnosed rapidly in real time; and the specific position of the machine fault can be determined accurately based on the e correlation analysis theory of the image.

Description

technical field [0001] The invention belongs to the technical field of signal processing, and relates to a mechanical fault detection and diagnosis analysis method, in particular to a mechanical fault analysis method based on wavelet fuzzy identification and image analysis theory. Background technique [0002] Rotating machinery plays an important role in the production of electric power, chemical industry and other industries. Condition monitoring and fault diagnosis of rotating machinery equipment have important practical significance and economic value to ensure the safe operation of the equipment. The vibration signal of the rotating machinery is the carrier of the characteristic signal of the equipment failure. Most of the failures of the rotating machinery system are reflected in the vibration signal. The monitoring of the vibration signal of the rotating machinery is a practical way to realize the diagnosis of the mechanical failure. effective method. The vibration ...

AI Technical Summary

Problems solved by technology

The vibration signals of faulty machinery are often non-stationary signals. Although the traditional Fourier transform is an important signal analysis method, it is difficult to deal with non-stationary signals. Traditional diagnostic techniques have been unable to meet the diagnostic requirements of current complex mechanical equipment.

Images