Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Bearing fault diagnosis method and system based on improved deep residual algorithm

A fault diagnosis and fault diagnosis model technology, applied in mechanical bearing testing, neural learning methods, calculations, etc., can solve problems such as low precision and low efficiency, and achieve the effects of good extraction, strong generalization ability, and low time cost

Pending Publication Date: 2022-08-05
HEFEI UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the prior art, the present invention provides a bearing fault diagnosis method and system based on the improved depth residual algorithm, which solves the problems of low precision and low efficiency in the existing bearing fault diagnosis technology

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Bearing fault diagnosis method and system based on improved deep residual algorithm
  • Bearing fault diagnosis method and system based on improved deep residual algorithm
  • Bearing fault diagnosis method and system based on improved deep residual algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] In the first aspect, the present invention first proposes a bearing fault diagnosis method based on an improved depth residual algorithm, see figure 1 , the method includes:

[0054] S1. Convert the acquired one-dimensional time series signal of bearing fault into two-dimensional image data, and form a fault data set based on the two-dimensional image data;

[0055] S2. A Resnet-SK bearing fault diagnosis model constructed based on the fault data set training;

[0056] The Resnet-SK bearing fault diagnosis model includes: adding an improved SK attention mechanism to the shortcut branch of the BasicBlock structure of the deep residual network, and modifying the second conventional convolution on the residual branch of the BasicBlock structure to A dilated convolution with an expansion rate of 2; the improved SK attention mechanism includes: using a multi-scale dilated convolution group to replace the two branch convolutions in the split stage of the SK attention mechani...

Embodiment 2

[0085] In a second aspect, the present invention also provides a bearing fault diagnosis system based on an improved depth residual algorithm, the system comprising:

[0086] a data set acquisition module, configured to convert the acquired one-dimensional time series signal of bearing fault into two-dimensional image data, and form a fault data set based on the two-dimensional image data;

[0087] A model training module, which is used to train the Resnet-SK bearing fault diagnosis model constructed based on the fault data set;

[0088] The Resnet-SK bearing fault diagnosis model includes: adding an improved SK attention mechanism to the shortcut branch of the BasicBlock structure of the deep residual network, and replacing the second conventional convolution on the residual branch of the BasicBlock structure with A dilated convolution with an expansion rate of 2; the improved SK attention mechanism includes: using a multi-scale dilated convolution group to replace the two br...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a bearing fault diagnosis method and system based on an improved deep residual algorithm, and relates to the technical field of equipment fault detection. The method comprises the following steps: converting bearing fault data of an obtained one-dimensional time sequence signal into two-dimensional image data and forming a fault data set; and then training a constructed Resnet-SK bearing fault diagnosis model formed by combining an improved deep residual network and an improved SK attention mechanism by using the fault data set, and finally performing bearing fault diagnosis of equipment by using the trained Resnet-SK bearing fault diagnosis model. According to the bearing fault diagnosis method, high equipment bearing fault diagnosis precision can be achieved, and low time cost can be guaranteed.

Description

technical field [0001] The invention relates to equipment fault detection technology, in particular to a bearing fault diagnosis method and system based on an improved depth residual algorithm. Background technique [0002] In modern industrial production, when detecting the failure of precision equipment, it is found that about 30%-40% of the equipment failure is caused by bearing failure. Therefore, monitoring and diagnosing bearing status to ensure production safety and reduce production costs has been a hot issue and challenge in this field in recent years. Bearing fault diagnosis mainly realizes the detection of fault data by preprocessing the collected bearing fault data (mainly one-dimensional time series signal) and extracting data features. [0003] At present, in this field, the powerful feature learning ability of deep learning is often applied to the detection and diagnosis of fault data. For bearing fault data of one-dimensional time series signals, recurrent n...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08G01M13/04
CPCG06N3/08G01M13/04G06N3/048G06N3/045G06F2218/00G06F18/214
Inventor 钱晓飞方鸿雨刘心报韩蔚陆少军周谧胡俊迎胡朝明
Owner HEFEI UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com