Bearing fault diagnosis method and system under variable working condition based on Gaussian Noise CNN model

Abstract

The invention provides a bearing fault diagnosis method and system under a variable working condition based on a Gaussian Noise CNN model, and the method comprises the steps: collecting a fault bearing vibration signal through a vibration sensor, and carrying out the segmentation of the fault bearing vibration signal through a fixed-length random segmentation method, and obtaining a data sample; after labels corresponding to all types are pasted on the data samples according to the state types of the rolling bearing, the data samples are divided into a training set, a verification set and a test set according to a certain proportion; according to data in the training set and the verification set, various bearing fault data sets in an unbalanced state are manufactured, and all the manufactured bearing fault data sets form an unbalanced data set; constructing the above model, and training the above model by using different bearing fault data sets to obtain the above training model; and performing real-time fault detection on the rolling bearing by using the training model. According to the invention, the operation state of the bearing can be accurately and automatically identified in real time, so that the normal operation of mechanical equipment is effectively maintained.

Description

technical field [0001] The invention relates to the technical field of equipment health management, in particular to a bearing fault diagnosis method and system based on a Gaussian Noise CNN model under variable working conditions. Background technique [0002] Bearings are a key part of modern industrial equipment. The working scene of bearings is complex. Once a fault occurs, it may cause serious safety accidents, resulting in a large number of casualties and huge economic losses. [0003] Traditional signal-based fault diagnosis methods mainly use time domain information or frequency domain information to extract fault features. [0004] Machine learning methods are also widely used in the field of fault diagnosis. Compared with traditional signal-based processing methods, machine learning methods do not require extensive expert experience. The fault diagnosis method of machine learning is usually to collect the vibration signal during the operation of the machine, then ...

AI Technical Summary

Problems solved by technology

[0008] Aiming at the problem that most of the bearing fault detection models in the prior art are trained and detected under a single working condition, when the

Images