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

A vibration sensing method for longitudinal damage of conveyor belt based on infrared computer vision

A technology of computer vision and conveyor belts, which is applied to computer parts, calculations, neural learning methods, etc., and can solve problems such as semi-contact, easy interference of mathematical models, and poor practicability

Active Publication Date: 2022-08-02
TAIYUAN UNIV OF TECH
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The above-mentioned model substitution method is easily affected by the noise of the environment, equipment components, personnel, etc., which leads to the problem of "easy to interfere, poor practicability, and semi-contact" in the mathematical model established between the two

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
  • A vibration sensing method for longitudinal damage of conveyor belt based on infrared computer vision
  • A vibration sensing method for longitudinal damage of conveyor belt based on infrared computer vision
  • A vibration sensing method for longitudinal damage of conveyor belt based on infrared computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] like Figure 1 to Figure 7 As shown, a method for perceiving longitudinal damage and vibration of a conveyor belt based on infrared computer vision of the present invention includes the following steps:

[0030] Step 1: Build an image data set: Set a high-speed camera above the mining conveyor belt to collect the micro-vibration images of the conveyor belt in normal, worn, scratched, and torn states, and store them on the tower server. The dataset is used to initially train the convolutional neural network, and the other part of the dataset is used to further train the convolutional neural network;

[0031] Step 2: Use the convolutional neural network with variable convolution kernel to train and test the vibration frequency signals of the mining conveyor belt in the normal state, wear state, scratch state and tear state respectively, and obtain the initially trained convolutional neural network. network;

[0032] Step 3: Apply the initially trained convolutional neur...

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 present invention is a method for perceiving longitudinal damage and vibration of conveyor belt based on infrared computer vision, which belongs to the technical field of computer vision; The technical solution adopted in the technical problem is: set a high-speed camera above the mining conveyor belt to collect the micro-vibration images of the conveyor belt in the normal state, wear state, scratch state and tear state; use convolutional neural networks with variable convolution kernels The network trains and tests the vibration frequency signal of the conveyor belt respectively, and obtains a preliminarily trained convolutional neural network; obtains a further trained convolutional neural network model through transfer learning; input the collected image data into the convolutional neural network model. , according to the longitudinal damage information of the mining conveyor belt corresponding to the amplitudes of different bands, output the diagnosis result of the damage of the conveyor belt; the invention is applied to the judgment of the damage of the conveyor belt.

Description

technical field [0001] The invention relates to a method for perceiving longitudinal damage and vibration of conveyor belts based on infrared computer vision, and belongs to the technical field of methods for perceiving longitudinal damage and vibration of conveyor belts based on infrared computer vision. Background technique [0002] In 2020, the average daily output of raw coal in my country is 11.35 million tons, and mining conveyor belts play a crucial role in the efficient transportation of coal. In the process of transportation, the mining conveyor belt is prone to longitudinal wear and scratches, and will be torn for a long time. Once torn, the economic cost caused cannot be underestimated. These longitudinal damages are mainly due to the fact that the raw coal contains iron tools, wooden sticks and other sundries, which cause local damage to the belt body when it falls. When these sundries are stuck on the frame or idler, the conveyor belt will be torn longitudinall...

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 Patents(China)
IPC IPC(8): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F2218/08
Inventor 乔铁柱付杰阎高伟
Owner TAIYUAN 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