Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

An embedded device and method for real-time detection of welding quality of keyhole tig welding

An embedded device, real-time detection technology, applied in welding equipment, welding accessories, arc welding equipment, etc., can solve the problems of real-time identification and remote monitoring of difficult welding quality, and achieve the effect of wide application, low cost and small size

Active Publication Date: 2022-07-22
SOUTH CHINA UNIV OF TECH
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It is difficult to apply real-time identification and remote monitoring of welding quality on long welds on curved surfaces that need to move or crawl

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
  • An embedded device and method for real-time detection of welding quality of keyhole tig welding
  • An embedded device and method for real-time detection of welding quality of keyhole tig welding
  • An embedded device and method for real-time detection of welding quality of keyhole tig welding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0062] like figure 1 As shown, the embedded device for real-time detection of keyhole TIG welding welding quality includes:

[0063] CMOS camera, connected to the AI ​​core board, is used to collect the welding scene images of keyhole TIG welding in real time, and transmit the image data to the AI ​​core board; the CMOS camera has the functions of software triggering and exposure time setting, and the exposure time range is within 100us- 50ms, the dynamic range is greater than 60dB, and the frame rate is greater than 60 frames / s;

[0064] The AI ​​core board communicates data with other components of the embedded device, and integrates the real-time detection software package of keyhole TIG welding welding quality; the PCB size of the AI ​​core board is 40mmx55mm, adopts RK1808K wide temperature AI chip, and has a memory of 2GB DDR4 SDRAM, storage is 8GB eMMC 1 channel, equipped with LVDS LCD screen interface, 1 channel Gigabit Ethernet interface, 1 channel USB3.0Host interfa...

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 embedded device and method for real-time detection of keyhole TIG welding welding quality, including a CMOS camera, an AI core board, a wireless module, a welding current sensing module, a welding voltage sensing module, a crawling robot controller and a deep Fusion keyhole TIG welding power source. The calibration exposure sequence is determined by the test welding calibration, the multi-exposure mode of the CMOS camera is set, and the welding area is monitored by the multi-exposure fusion technology. Using the AI ​​core board, CNN technology is used to segment the keyhole and molten pool, and the size and Hu invariant rectangular state features are extracted, combined with the welding current and voltage features as input, and the constructed BP neural network is used to identify the penetration state in real time. Upload images, welding status and early warning information to a remote server through a wireless module. The invention is suitable for the keyhole TIG welding of the long surface welding seam of the medium and thick plate, and the embedded device can be installed on the crawling robot to realize the real-time identification and remote monitoring of the welding quality.

Description

technical field [0001] The invention relates to the technical field of welding monitoring and image processing, in particular to an embedded device and method for real-time detection of keyhole TIG welding welding quality. Background technique [0002] In recent years, with the development of advanced manufacturing technology and the continuous improvement of the domestic market environment, the heavy machinery industry, which occupies an extremely important position in the manufacturing industry, has developed rapidly. come bigger. At present, medium and heavy plate welded structures are widely used in shipbuilding, large bridges, petrochemicals, boiler vessels, heavy machinery and other industrial sectors. However, these large-scale weldments have a large number of large curved and long welds, and most of them can only use manual multi-layer multi-pass welding, which has many auxiliary processes, poor weld quality stability, low one-time welding qualification rate, large ...

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): B23K31/12B23K9/095B23K9/32B23K9/167
CPCB23K31/125B23K9/095B23K9/32B23K9/167
Inventor 石永华陈熙引王子顺
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
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