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

Three-dimensional detection and welding seam inflection point identifying method for multilayer multiple welding seams of robot

A multi-layer, multi-channel, identification method technology, applied in the field of weld detection of robot automatic welding, can solve the problems of low precision, poor real-time performance, low reliability, etc., and meet the requirements of ensuring accuracy, removing influence, and efficient denoising processing method Effect

Active Publication Date: 2018-04-06
ZHEJIANG UNIV OF TECH
View PDF6 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the defects of low accuracy, low reliability, and poor real-time performance of the three-dimensional real-time detection of the weld due to welding interference in the existing multi-layer and multi-pass welding, the present invention provides a high-precision, high-reliability High and real-time performance of three-dimensional inspection of robot multi-layer multi-pass welding seam and identification method of weld inflection point

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
  • Three-dimensional detection and welding seam inflection point identifying method for multilayer multiple welding seams of robot
  • Three-dimensional detection and welding seam inflection point identifying method for multilayer multiple welding seams of robot
  • Three-dimensional detection and welding seam inflection point identifying method for multilayer multiple welding seams of robot

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0147] Example 1: First, calibrate the single-line structured light and the camera, and then calibrate the camera and the robot. Any common calibration method can be used for calibration. In this embodiment 1, the plane template calibration method of Professor Zhang Zhengyou was used to calibrate the camera. The calibration results are shown in Table 1:

[0148]

[0149] Table 1

[0150] At the same time, the points of the line structured light on the plane template are obtained, and the light plane equation is fitted by the SVD method to obtain the parameters of the structured light plane. The light plane is as follows Figure 6 shown.

[0151] Finally, use the "two-step method" to obtain the pose relationship between the camera and the end effector of the robot, as follows:

[0152]

[0153] After the calibration, use the camera to obtain the structured light fringe image on the weld surface, such as Figure 7 As shown, then use the method described above for denois...

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 a three-dimensional morphology detection and welding seam inflection point identifying method for multilayer multiple welding seams of a robot. The three-dimensional detectionand welding seam inflection point identifying method comprises the following steps that 1, a camera, line structural light and the robot are calibrated; 2, a welding seam structure light image is obtained and processed; and 3, the three-dimensional spatial morphology of the multilayer multiple welding seams is obtained, and inflection point characteristics are identified, specifically, the processcomprises the following steps that 3.1, the eigenvector of a calculated hessian matrix during extraction of a center line is recorded; 3.2, according to the direction of the eigenvector, the threshold value of the eigenvector difference is set to identify inflection points of the multilayer multiple welding seams; and 3.3, according to model data calculated in the step 1, the sub-pixel coordinatevalue of the center line under a camera coordinate system is converted to be under a robot coordinate system and serves as the three-dimensional data of the welding seam surface for being used for robot welding. According to the three-dimensional detection and welding seam inflection point identifying method for the multilayer multiple welding seams of the robot, the precision is high, the reliability is high, and real-time performance is good.

Description

technical field [0001] The invention relates to the field of weld seam detection for robotic automatic welding, in particular to a method for real-time detection of three-dimensional weld seam appearance in multi-layer multi-pass welding, which provides a basis for welding automation. Background technique [0002] Welding is an important material forming and processing technology in the field of contemporary manufacturing, and it has been widely used in industrial manufacturing fields such as construction engineering, aerospace, machinery manufacturing, and electronics. The development of welding and related industries is of great significance to my country's transformation from a manufacturing power to a manufacturing power. However, with the development of manufacturing equipment, single-layer single-pass welding and single-layer multi-pass welding have been unable to meet their requirements in the process of equipment manufacturing. Due to the influence of welding power a...

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): B23K26/03B23K26/08B23K26/24B25J9/16
CPCB23K26/032B23K26/0884B23K26/24B23K26/32B25J9/1602B25J9/1697
Inventor 鲍官军庞加庆黄锦成李玉蔡世波杨庆华胥芳
Owner ZHEJIANG UNIV OF 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