Rolling bearing fault diagnosis method based on harmonic wavelet packet and IAGA-SVM

Abstract

The invention discloses a rolling bearing fault diagnosis system based on a harmonic wavelet packet and an IAGA-SVM. The rolling bearing fault diagnosis system based on the harmonic wavelet packet andthe IAGA-SVM comprises a harmonic wavelet packet module, a SVM modeling module and a fault identification module, and the harmonic wavelet packet module includes a signal acquisition module, a signaldecomposition module, a signal reconstruction module and a signal feature extraction module, wherein the SVM modeling module includes a SVM model initial module, a self-adaptive training module, a model testing module and a self-adaptive supporting vector module. The invention further discloses a rolling bearing fault diagnosis method based on the harmonic wavelet packet and the IAGA-SVM. The rolling bearing fault diagnosis method and system based on the harmonic wavelet packet and the IAGA-SVM have the advantages that the deviation of diagnosis results cannot occur, fault types of a rollingelement, an outer ring and an inner ring of a ball bearing can be judged accurately, the processes of complete model establishment and training in the judgment process of the ball bearing is relatively simple and convenient, and the ball bearing can be diagnosed under the condition that the original equipment is not disassembled in the diagnosis process.

Description

technical field [0001] The invention relates to the technical field of ball bearing detection, in particular to a rolling bearing fault diagnosis method based on harmonic wavelet packets and IAGA-SVM. Background technique [0002] Due to the continuous development of industrial production, the safe and reliable operation of large-scale and complex mechanical equipment has gradually attracted the attention of the society, and the related fault diagnosis technology has also made rapid progress. Rolling bearings are the key components of large-scale mechanical equipment. The technology related to feature diagnosis plays a very important role, and this is a problem of pattern recognition. The safety faults that occur during high-load operation mainly include three types of faults: cracks on the outer ring, pitting on the inner ring, and pitting on rolling elements. The above faults are caused by the joint action of many factors, but the faults and their causes are not in one-to-...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is that the diagnosis results will produce a certain degree of deviation, and the fault types of the rolling elements, outer ring and inner ring of the ball bearing cannot be accurately judged. In the ball bearing judgment process, complete model establishment and training The process is relatively complicated, and the problem that the ball bearing cannot be diagnosed without dismantling the original equipment during the diagnosis process

Images