Method and equipment for extracting weak fault signal features of rolling bearings

Abstract

The present invention discloses a method and equipment for signal features in the state of rolling bearing in a state of weak failures.This method includes: first obtain the rolling bearing vibration signal, and the collected vibration signal continuously transforms the frequency frequency diagram; then, the frequency of the frequency on the time frequency diagram corresponds to the small wave coefficient, filtering the noise interference and extracting the period of the cycleSexual fault ingredients; Finally, use the Hilbert transformation for packaging and demodulation, and then the Fourier transformation finds the power spectrum of the package to obtain the frequency of fault characteristics.The signal feature extraction method of the present invention can effectively extract the weak periodic impact component of the early failure of the rolling bearings, thereby providing key support for the state monitoring and fault diagnosis of the machine.

Description

technical field [0001] The invention belongs to the field of mechanical equipment signal processing, and in particular relates to a feature extraction method and equipment for weak fault signals of rolling bearings. Background technique [0002] Rolling bearings are one of the most widely used and most critical parts in rotating machinery. Its operating status often determines the performance of the whole machine. Any slight fault will have a great impact on the stability of the machine. Rolling bearings are easily damaged during operation. If the weak fault signal of the bearing can be extracted in the early stage of the fault, the signal can be analyzed and processed, and the accurate diagnosis result can be given in time, so that the maintenance personnel can formulate effective and reasonable solutions for the fault. Maintenance plan, thereby prolonging the life of the machine and greatly reducing the harm caused by failure. [0003] When the rolling bearing is partiall...

AI Technical Summary

Problems solved by technology

However, during the early fault diagnosis of the bearing, especially in the weak fault diagnosis, the local defects and damage of the bearing are very small, and the shock vibration caused by it is very weak, and the fault features extracted on different frequency band components are easily detected by frequency conversion and machine operation In addition, the discrete intervals of frequency band division methods such as discrete wavelet or wavelet packet transform and empirical mode decomposition are too large and too rough, which will also affect the extraction of fault features, and it is difficult to achieve ideal results in early weak fault diagnosis.

Images