A Visual Cognition Based Fault Diagnosis Method for Rolling Bearings under Variable Working Conditions

Abstract

The invention discloses a visual cognition-based fault diagnosis method for rolling bearings under variable working conditions, and relates to a rolling bearing fault diagnosis technology for variable working conditions. The method includes: converting the rolling bearing vibration signals under variable working conditions into a two-dimensional image; use the accelerated robust feature SURF algorithm to perform feature extraction on the two-dimensional image to obtain a high-dimensional fault feature vector with visual invariance; use the isometric mapping Isomap algorithm to perform dimensionality reduction on the high-dimensional fault feature vector Process to obtain a low-dimensional stable feature vector; utilize the singular value decomposition SVD algorithm to extract the singular values ​​of the feature matrix constructed by the low-dimensional stable feature vector to form the final feature vector; use the trained classifier to perform the final feature vector Carry out fault classification and carry out fault diagnosis for rolling bearings under variable working conditions. The invention provides a new solution idea for the rolling bearing fault diagnosis.

Description

technical field [0001] The invention relates to a rolling bearing variable working condition fault diagnosis technology, in particular to a visual cognition-based rolling bearing variable working condition fault diagnosis method. Background technique [0002] Rolling bearings are the most widely used components in the industry. Rolling bearing failures may cause machine system failures, resulting in huge economic losses. Fault diagnosis is one of the research hotspots in many fields, and it helps to reduce losses that may be caused by component and system failures , so it is of great significance. [0003] Among many signal acquisition methods, the measurement method based on vibration signal is widely used due to its high correlation with faults, easy acquisition and non-destructiveness. However, the working environment of rolling bearings is usually complex, harsh and changing, and the current fault diagnosis of rolling bearings is often studied under the assumption that ...

AI Technical Summary

Problems solved by technology

Based on the above ideas, researchers have proposed many bearing signal fault feature extraction methods, such as empirical mode decomposition (Empirical Mode Decomposition, EMD), short-time Fourier transform (Short-Time Fourier Transform, STFT), LMD and wavelet packet decomposition ( Wavelet Packet Decomposition, WPD), etc., however, EMD has shortcomings such as over-envelope, under-envelope, endpoint effect and frequency confusion; STFT cannot meet the requirements of resolution and time at the same time; LMD also has frequency confusion and endpoint effects; For WPD, the wavelet decomposition has a strong dependence on the prior knowledge of the signal when choosing the wavelet basis

Images