Bearing compound fault diagnosis method based on EEMD (ensemble empirical mode decomposition) multi-feature fusion

Abstract

The invention discloses a bearing compound fault diagnosis method based on EEMD (ensemble empirical mode decomposition) multi-feature fusion. A fault bearing is taken out and installed on an MFS mechanical fault simulation test bed, the test bed is connected with an upper computer, the upper computer controls the rotating speed of a motor through a controller, the motor is started after the rotating speed is selected, fault vibration signals are collected through an acceleration sensor, digital signals are obtained through analog-to-digital conversion, and the digital signals are transmitted to the upper computer. The collected bearing fault vibration signals are continuously decomposed into a plurality of IMFs through EEMD, and a correlation coefficient is calculated to obtain a component having strong correlation with the original vibration signals. According to the scheme, the bearing composite fault is simulated, the bearing operation environment and the fault type can be accurately simulated, various feature extraction methods can be adopted to consider different feature representation capabilities from multiple aspects, multi-feature fusion is carried out to construct a composite fault feature set, fault features are represented comprehensively, and the problem that the bearing composite fault is difficult to diagnose accurately can be effectively improved.

Description

technical field [0001] The invention relates to the field of fan bearing fault diagnosis. Aiming at the problem that fault features are coupled with each other and feature values ​​overlap, a composite fault diagnosis method for rolling bearings based on EEMD multi-feature fusion is proposed. Specifically, the MFS mechanical fault simulation test bench manufactured by SpectraQuest Company of the United States is used to collect signals and simulate the fault diagnosis of fan bearing faults, and use the EEMD multi-feature fusion algorithm to diagnose the fault of fan bearings, analyze the experimental results and calculate the diagnostic accuracy . Background technique [0002] With the development of human science and technology and the advancement of civilization, the safe service of aircraft, ships, vehicles, generator sets and other major mechanical equipment and infrastructure is of great significance to the development of the national economy and national defense constr...

AI Technical Summary

Problems solved by technology

[0006] A bearing compound fault diagnosis method based on EEMD multi-feature fusion, its advantage lies in overcoming the incomplete characterization of single feature extraction method and the inability to accurately extract fault features of compound faults, considering the feature fusion of dynamic method and time domain index, constructing Eigenvectors, increasing the ability to identify complex faults

Images