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

Cooperative Prediction Method of Reinforcement and Melting Depth Based on Melting Pool Image and Deep Residual Network

A prediction method and molten pool technology, applied in the field of image analysis, can solve problems such as the decline in the ability of the weld to withstand dynamic loads, and achieve the effect of real-time control of welding quality

Active Publication Date: 2021-02-02
南京知谱光电科技有限公司
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the reinforcement height causes stress concentration at the weld toe, and the ability of the weld to withstand dynamic loads decreases.

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
  • Cooperative Prediction Method of Reinforcement and Melting Depth Based on Melting Pool Image and Deep Residual Network
  • Cooperative Prediction Method of Reinforcement and Melting Depth Based on Melting Pool Image and Deep Residual Network
  • Cooperative Prediction Method of Reinforcement and Melting Depth Based on Melting Pool Image and Deep Residual Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] The experimental data acquisition device for reinforcement and penetration depth of the present invention is a CMT welding experimental platform. CMT welding experiment platform is mainly composed of welding power supply, mobile robot and vision sensor system. The vision system sensor system is placed on a flat workbench 6, and the workbench 6 places the motherboard 1 to be welded. The visual sensor system includes a welding torch 3 fixed on the robot. The welding torch 3 faces the motherboard 1. A CCD color camera 2 is also installed on the robot. Its model is Basler acA640-750uc. In order to correspond the collected image of the molten pool 7 to the actual position of the weld 8, a laser 4 is used for auxiliary positioning, and a laser 4 with a center wavelength of 450nm is used to irradiate the upper edge of the welding wire, and a model of Basler ace acA1920 is placed at the same time -155um CCD black and white camera 5 to capture laser points, such as figure 2 s...

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 relates to a collaborative prediction method of reinforcement and penetration depth based on a molten pool image and a depth residual network, which belongs to the field of image analysis technology, and accurately predicts the trend of penetration depth and reinforcement in the future development of welds, thereby improving welding quality. It includes the following steps: 1. Restore the variation of reinforcement and penetration depth along the weld length, 2. Image processing framework, 3. Determine the basic network, 4. Determine the network input end, 5. Determine the network output end, 6. Evaluation of network learning ability, 7. Residual height and deep network prediction. The present invention is based on the fusion depth and reinforcement collaborative prediction of the molten pool image and the depth residual network. Accurately predict the future development of weld depth and reinforcement trends, applicable to different welding parameters and different weldments, real-time control of welding quality.

Description

technical field [0001] The invention relates to a collaborative prediction method for reinforcement and fusion depth based on fusion pool images and depth residual networks, and belongs to the technical field of image analysis. Background technique [0002] The image characteristics of the molten pool and the changes of the penetration and reinforcement of the weld have a decisive effect on the quality of the welding. On the cross-section of the weld, the melting depth of the base metal is called the penetration depth, which directly determines the bonding strength between the weld and the base metal, and also determines the bearing capacity of the weld to a large extent; The maximum height of that part of the weld is called the reinforcement, that is, the distance from the top of the weld to the line connecting the two welding toes. The reinforcement of the weld increases the cross-sectional area of ​​the weld and improves the static load carrying capacity. However, the re...

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): G06T7/00G06T7/181G06T7/246G06N3/04G06N3/08
CPCG06T7/0004G06T7/181G06T7/246G06N3/08G06T2207/30152G06T2207/10061G06N3/045
Inventor 赵壮韩静陆骏张毅
Owner 南京知谱光电科技有限公司
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