AI-based automatic weld path identification method

A path recognition and automatic technology, applied in welding equipment, auxiliary welding equipment, welding/cutting auxiliary equipment, etc., can solve the problems of high manpower cost and time cost, inability to effectively guarantee welding quality, adjust welding parameters, etc., and achieve reduction The effect of design link, reducing programming and teaching process, and improving production efficiency

Active Publication Date: 2020-07-10
上海智殷自动化科技有限公司
View PDF9 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, when using a welding robot for welding, it is necessary to manually teach the entire robot movement and weld trajectory. Therefore, when the structure of the welding workpiece or the shape and position of the weld change greatly, manual teaching will consume a lot of labor cost and time cost; due to the existence of processing errors, there are certain differences between the same structural workpiece and weld seam, and the use of the original manual teaching trajectory may affect the welding quality
At the same time, due to the lack of welding seam parameter detection equipment, traditional welding robots cannot adjust welding parameters according to different weld seams, and cannot effectively guarantee welding quality

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
  • AI-based automatic weld path identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0016] Concrete operation method when the present invention uses is:

[0017] 1. Import the 3D model data of the workpiece to be welded into the welding robot controller. The 3D model data of the imported workpiece includes the overall structure of the workpiece to be welded and the position information of the weld in the workpiece;

[0018] 2. Install the workpiece to be welded on the welding tooling table, and take an overall photo of the workpiece through the stereo camera fixed above the table to detect whether the position and posture of the welding workpiece on the table are correct, which requires on-site manual confirmation All equipment is securely in place.

[0019] 3. The automatic programming controller of the welding robot generates offline the movement trajectory of the welding robot to complete the entire welding process of the workpiece according to the three-dimensional model data of the equipment, the welding seam position information and the model of the wel...

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 AI-based automatic weld path identification method. Three-dimensional model data of a workpiece needing to be welded is imported into a welding robot controller, and the imported three-dimensional model data of the workpiece comprises the overall structure of the workpiece needing to be welded and position information of a weld in the workpiece. Compared with a traditional automatic welding technology, the method has the advantages that a large amount of programming demonstration time can be shortened, and the production efficiency is improved; welding paths can be rapidly generated for different workpieces, and the link of designing complex tools is reduced; the problem of machining errors or position deviation existing in discharging of the workpiece can be well solved by using the method; and different welding modes such as fillet welding, vertical welding and lap welding can be automatically adjusted by applying the method for different welding types.

Description

technical field [0001] The invention relates to the field of robot welding, in particular to an AI-based automatic welding seam path identification method. Background technique [0002] At present, when using a welding robot for welding, it is necessary to manually teach the entire robot movement and weld trajectory. Therefore, when the structure of the welding workpiece or the shape and position of the weld change greatly, manual teaching will consume a lot of Due to the existence of processing errors, there are certain differences in the workpieces and welds of the same structure, and the use of the original manual teaching trajectory may affect the welding quality. At the same time, due to the lack of welding seam parameter detection equipment, traditional welding robots cannot adjust welding parameters according to different weld seams, and cannot effectively guarantee welding quality. In recent years, deep learning has made rapid progress in the fields of image recogni...

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): B25J9/16B25J11/00B23K37/02
CPCB25J9/1664B25J11/005B23K37/02
Inventor 王坤
Owner 上海智殷自动化科技有限公司
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap