A Fault Prediction Feature Selection Method Based on Fault Evolution Analysis

Abstract

The invention discloses a fault predicting characteristic selecting method based on fault evolution analysis. The fault predicting characteristic selecting method based on the fault evolution analysis solves the problem that the existing fault characteristic selecting method cannot effectively improve the efficiency and the accuracy of a fault predicting technology. The fault predicting characteristic selecting method based on fault evolution analysis comprises the steps of (1) selecting a fault simulation model, obtaining output responding data of a system under different severity degree states in a whole fault evolution process from a non-fault state, an early fault state to an invalid state of a typical fault in an electromechanical system, (2) using a commonly-used characteristic extraction method in a project and building fault evolution trend curves of the characteristic descriptions, (3) analyzing the fault evolution trend of the characteristic descriptions and calculating the tracking ability of the characteristics to the fault evolution process, and (4) comparing and selecting the biggest tracking ability characteristic in the fault evolution process as a fault predicting characteristic. The fault predicting characteristic selecting method based on the fault evolution analysis can effectively detect the early state of a fault and the evolution process of tracking the fault.

Description

technical field [0001] The invention relates to a method for selecting fault prediction features, in particular to a method for selecting fault prediction features based on fault evolution analysis. Background technique [0002] At present, the known fault feature extraction methods are mainly time domain methods (such as root mean square, kurtosis factor, energy ratio, kurtosis, standard deviation, etc.), frequency domain methods (Fourier transform, fast Fourier transform, etc.), and time-frequency Domain method (such as wavelet transform), using these fault feature extraction methods mainly focuses on two aspects: one is to extract fault features that are different from the normal state from strong environmental noise to drive fault alarms; the other is to extract fault features from strong background noise Characterization of different faults in electromechanical systems, providing data input for fault diagnosis or identification. However, the fault features extracted by...

AI Technical Summary

Problems solved by technology

However, the fault features extracted by the current method cannot well describe the trend of the entire fault evolution (that is, the gradual growth process of the electromechanical components from the normal state to the functional failure state), which leads to the inefficiency and accuracy of the electromechanical system fault prediction technology. high

Images