Bearing fault detection method and device and equipment

Abstract

The invention discloses a bearing fault detection method and device and equipment. The method comprises the steps that a vibration signal of a bearing is collected; signal segment division is performed on the vibration signal, and a dictionary learning sample set is obtained, wherein the dictionary learning sample set comprises signal segments obtained through division, and each signal segment contains at least one impact attenuation signal; non-correlation dictionary learning is performed on each signal segment in the dictionary learning sample set to obtain a vibration waveform dictionary, wherein the vibration waveform dictionary is composed of all the signal segments subjected to non-correlation dictionary learning; envelope demodulation processing is performed on the vibration waveform dictionary to obtain an envelope demodulation spectrum; and according to bearing fault feature frequency displayed in the envelope demodulation spectrum, a fault detection result of the bearing is determined. According to the method, non-correlation dictionary learning is utilized to process the signal segments obtained through division of the vibration signal, weak fault features can be extracted, and the method is suitable for early fault detection and diagnosis.

Description

technical field [0001] The present application relates to the field of fault diagnosis, in particular to a bearing fault detection method, device and equipment. Background technique [0002] Rolling bearings are important supporting parts of rotating machinery and are also vulnerable parts. They are widely used in various large-scale industrial equipment, such as wind turbines, aeroengines, and high-speed trains. Rolling bearing faults can cause equipment downtime to affect operation and production, and serious accidents can cause catastrophic accidents. Therefore, early fault monitoring and diagnosis of rolling bearings is an effective way to reduce operation and maintenance losses and ensure the safety of equipment operation, which has important engineering significance. [0003] Vibration monitoring is one of the most effective ways to diagnose bearing faults. Traditional methods for analyzing bearing vibration signals are mostly based on fixed basis functions to decompo...

AI Technical Summary

Problems solved by technology

[0003] Vibration monitoring is one of the most effective ways to diagnose bearing faults. Traditional methods for analyzing bearing vibration signals are mostly based on fixed basis functions to decompose signals, and generally lack the ability to adaptively extract various fault characteristics of bearings, making rolling bearings The early weak fault features are submerged in other vibration components and difficult to extract

Images