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

Additive manufacturing excess weld metal prediction method based on molten pool image and deep residual network

A prediction method and molten pool technology, applied in the field of image processing, can solve the problem of difficulty in monitoring the penetration depth of the additive process, and achieve the effect of facilitating real-time control and welding quality

Inactive Publication Date: 2020-12-01
南京知谱光电科技有限公司
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The general welding process focuses on welding penetration and good penetration, but due to the influence of the remelting zone of the cladding layer, it is difficult to monitor the penetration during the additive process

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
  • Additive manufacturing excess weld metal prediction method based on molten pool image and deep residual network
  • Additive manufacturing excess weld metal prediction method based on molten pool image and deep residual network
  • Additive manufacturing excess weld metal prediction method based on molten pool image and deep residual network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] This embodiment is based on the cold metal transition method, that is, the CMT single-pass multi-layer additive manufacturing of stainless steel as the background, and monitors the change of the cladding layer residual height in the arc additive manufacturing process. The process is monofilament CMT, the welding current is 130A, the welding speed is 5mm / s, and the shielding gas is argon-oxygen mixed gas (98.5%Ar 2 +1.5%O 2 ), the gas flow rate is 25L / min, the welding length is 80mm, the number of welding layers is 10, the height of the welding torch 4 is 1mm, the welding wire grade is ER316L, the base material is 304 stainless steel, the camera acquisition frequency is 1000Hz, and the exposure time is 100us. CMT is a special MIG / MAG welding. When the droplet is short-circuited, the welder receives a short-circuit signal, cuts off the welding power supply, and draws back the welding wire to help the droplet fall off and realize the cold transfer of the droplet. This hot...

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 an additive manufacturing excess weld metal prediction method based on a molten pool image and a deep residual network, belongs to the technical field of image processing, andaims to realize welding quality control. The method comprises the following steps: 1, building monitoring equipment, 2, carrying out image processing, 3, simplifying network learning difficulty, 4, integrating local information, 5, improving network performance, and 6, carrying out prediction calculation. According to the method, the additive manufacturing excess weld metal is accurately predicted based on the molten pool image and the deep residual network, the change of the cladding layer excess weld metal reflects the change of the fusion depth to a certain extent during additive manufacturing, the quality control of an additive manufacturing process is realized by monitoring the excess weld metal, the future excess weld metal development trend of a weld joint is accurately predicted,and the welding quality is conveniently controlled in real time.

Description

technical field [0001] The invention relates to a method for predicting the reinforcement height of an additive material based on a molten pool image and a deep residual network, and belongs to the technical field of image processing. Background technique [0002] The general welding process focuses on welding penetration and good penetration, but due to the influence of the remelting zone of the cladding layer, it is difficult to monitor the penetration during the additive process. The change of the reinforcement of the cladding layer during the additive process reflects the change of the penetration depth to a certain extent, so the quality control of the additive manufacturing process can be realized by monitoring the reinforcement. In fact, the accumulation of parts is formed by a series of single-layer single-pass accumulation, so the forming size and quality of these single-layer single-pass directly determine the forming quality of the stacked parts. The welding proc...

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
IPC IPC(8): G06T7/00G06N3/04G06K9/62B23K9/16B23K9/04B33Y50/00
CPCG06T7/0004B23K9/16B23K9/04G06T2207/10004G06T2207/20081G06T2207/20084G06T2207/30152B33Y50/00G06N3/045G06F18/213
Inventor 陆骏赵壮韩静张毅
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