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

Online weld joint tracking method and system based on vision

A visual and instant technology, applied in the direction of welding equipment, welding equipment, arc welding equipment, etc., can solve the problems of sparse noise, Kalman filter method can not deal with noise time-varying, etc., to improve accuracy, easy to use and popularize Effect

Inactive Publication Date: 2016-11-16
GUILIN UNIV OF AEROSPACE TECH
View PDF6 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is that the existing Kalman filter method cannot deal with the time-varying noise and sparse noise in the welding process, and provides a vision-based online weld seam tracking method and system

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
  • Online weld joint tracking method and system based on vision
  • Online weld joint tracking method and system based on vision
  • Online weld joint tracking method and system based on vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] A vision-based online seam tracking method such as figure 1 shown, including the following steps:

[0044] Step (1) Melt pool image acquisition.

[0045] A high-speed camera is used to obtain the image of the molten pool shape during the welding process and transmit it to the FPGA, and the FPGA transmits the acquired image to the PC (ie, the upper computer).

[0046] Step (2) Melt pool image preprocessing.

[0047] The preprocessing of molten pool image mainly includes image binarization and feature value selection of weld seam tracking.

[0048] Let f(i,j) be the gray value of the melt pool image at pixel (i,j), where i and j are the row and column of the pixel, respectively. Select the binarization threshold γ, the binarized image can be expressed as:

[0049] g ( i , j ) = f ( ...

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 discloses an online weld joint tracking method and system based on vision. The online weld joint tracking method and system based on vision aim at solving the problems that in the weld joint tracking process, Gaussian noise has time variability, and sparse noise in weld joint tracking cannot be treated by a traditional Kalman filter algorithm. An online Kalman filtering frame is put forward; real-time estimation is performed on noise parameters of a welding track through an online Kalman filter based on convex optimization; in a weld joint tracking model, the items of the Gaussian noise and the sparse noise are added in the measurement process at the same time; and by establishing a reasonable optimization model, the Gaussian noise and the sparse noise can be accurately estimated online, and therefore the weld joint tracking accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of intelligent welding, in particular to a vision-based online welding seam tracking method and system. Background technique [0002] In the intelligent welding process, it is necessary to use visual sensors to build a weld seam tracking system based on molten pool image processing, so as to guide the welding torch to always align and accurately track the weld seam position. The accuracy of seam tracking is an important prerequisite for ensuring welding quality. However, in the actual molten pool image acquisition, the image collected by the visual sensor is inevitably affected by various types of noise such as arc light, smoke, spatter, etc., which greatly reduces the accuracy of weld seam tracking. How to accurately predict the position of the weld seam in the presence of different types of noise is one of the difficulties in seam tracking. [0003] Kalman filtering is a widely used seam tracking method....

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): B23K37/00B23K9/127G06T7/00
CPCB23K9/127B23K37/00G06T7/0004G06T2207/30152
Inventor 冯宝刘国巍
Owner GUILIN UNIV OF AEROSPACE 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