A Fault Fusion Diagnosis Method for Rolling Bearings Based on Improved d-s Evidence Theory

Abstract

The present invention provides a rolling bearing fault fusion diagnosis method based on the improved D-S evidence theory. Firstly, multiple fault diagnosis methods are used to classify and identify the data of different fault states, so as to reflect the different fault characteristics of rolling bearings from multiple angles, and obtain multiple Then, use the conflict factor in the D-S evidence theory to construct the correlation matrix between each evidence, and calculate the reliability of each evidence; according to the reliability of each evidence, use the nearest neighbor criterion to classify similar evidence and conflict evidence ; The probability distribution of similar evidence is retained, while the basic probability distribution of conflicting evidence is modified; finally, the D‑S combination rule is used to fuse the similar evidence and the modified conflicting evidence to obtain the final diagnosis result. The method conducts fault diagnosis from multiple angles, and then performs multi-decision fusion, fully retains the advantages of each diagnosis method, reduces the one-sidedness caused by a single diagnosis method, and improves the fault diagnosis rate and diagnosis reliability.

Description

technical field [0001] The invention relates to the technical field of bearing detection, in particular to a rolling bearing fault fusion diagnosis method based on the improved D-S evidence theory. Background technique [0002] The generator is the core component of the wind power generating set, and its operation reliability directly affects the stability of the generating set, and the rolling bearing is a key part of the generator, so it is of great significance to carry out fault diagnosis on the rolling bearing. At present, for rolling bearing fault diagnosis, different signal processing techniques (such as Fourier transform, wavelet transform, EMD decomposition, etc.) are usually used to extract features to construct fault feature sets, and then different pattern recognition algorithms are used to identify and realize automatic diagnosis. This fault diagnosis method of constructing feature sets first and then pattern recognition has achieved good diagnostic results, but...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the defects in the prior art, the present invention provides a rolling bearing fault fusion diagnosis method based on the improved D-S evidence theory, which solves the problem in the prior art that the fault classification method can only be sought from a single perspective

Images