A bearing fault early warning method based on the characteristic amplitude of high frequency signal

Abstract

The invention discloses a bearing fault early warning method based on the characteristic amplitude of high-frequency signals, which belongs to the field of rolling bearing fault early warning. The method includes: collecting vibration signals of training bearings at equal intervals; performing discrete wavelet transformation on the vibration signals and extracting high-frequency components ;Sort the absolute value of the high-frequency components to obtain the enhanced impact amplitude LR and the carpet impact amplitude HR; use the corresponding LR-HR value at the same time as the early warning feature at this time; according to the LR-HR value of the training bearing's entire life cycle, the training bearing Divide the normal stage and the fault stage; respectively perform Weibull distribution fitting on the early warning features of each stage to obtain the probability distribution; collect the LR‑HR value of the test bearing in operation; calculate the probability that the test bearing is in the normal stage and the fault stage based on the probability distribution . The invention utilizes the high-frequency noise signal for fault early warning, avoids complicated denoising and signal enhancement processes, and the fault early warning feature will increase with the severity of degradation, and the early warning speed is fast, which is suitable for practical application.

Description

technical field [0001] The invention belongs to the field of rolling bearing operating state monitoring and fault early warning, and more specifically relates to a bearing fault early warning method based on the characteristic amplitude of high-frequency signals. Background technique [0002] Rolling bearings are widely used in the industrial field and are called the joints of industry. The normal operation of rolling bearings is related to the production quality and the safety of personnel and property in the entire industrial production process. During the operation process, the rolling bearings will degrade with the operation time due to environmental factors, wear factors and human factors, and the faults of the inner ring, outer ring and rotor will occur after accumulating for a certain period of time. In order to avoid economic and safety problems caused by major bearing failures, online monitoring and early warning of rolling bearings are very necessary, which is the...

AI Technical Summary

Problems solved by technology

[0005] In view of the above defects or improvement needs of the prior art, the present invention provides a bearing fault early warning method based on the characteristic amplitude of high-frequency signals, and its purpose is to solve the problem that the existing rolling bearing fault detection method cannot detect the fault feature when the bearing is seriously degraded The frequency, the extracted degraded features fluctuate greatly, and the technical problems of high false alarm rate

Images