Rolling bearing variable-work-condition fault diagnosis method based on visual cognition

Abstract

The invention discloses a rolling bearing variable-work-condition fault diagnosis method based on visual cognition, and relates to a rolling bearing variable-work-condition fault diagnosis technology. The method comprises the following steps of converting rolling bearing vibration signals under the variable work conditions into a two-dimensional image by using a recurrence plot technology; performing feature extraction on the two-dimensional image by utilizing an SURF (speed up robust features) algorithm to obtain the vision invariability high-dimension fault feature vector; performing dimension reduction processing on the high-dimension feature vector by using an equal-distance mapping Isomap algorithm to obtain the low-dimension stable feature vector; using an SVD (singular value decomposition) algorithm for extracting the feature matrix singular value built by the low-dimension stable feature vector to form the final feature vector; performing fault classification on the final feature vector by using the trained classifier; performing fault diagnosis on the rolling bearing under the variable work conditions. The invention provides a novel solution 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