A robotic welding system using image processing techniques and a CAD model to provide information to a multi‐intelligent decision module

David A. Sanders, Gareth Lambert, Jasper Graham‐jones, Giles E. Tewkesbury, Spencer Onuh, David Ndzi, Carl Ross

Research output: Contribution to journalArticle

Abstract

Purpose
– The paper aims to propose a system that uses a combination of techniques to suggest weld requirements for ships parts. These suggestions are evaluated, decisions are made and then weld parameters are sent to a program generator.

Design/methodology/approach
– A pattern recognition system recognizes shipbuilding parts using shape contour information. Fourier‐descriptors provide information and neural networks make decisions about shapes.

Findings
– The system has distinguished between various parts and programs have been generated so that the methods have proved to be valid approaches.

Practical implications
– The new system used a rudimentary curvature metric that measured Euclidean distance between two points in a window but the improved accuracy and ease of implementation can benefit other applications concerning curve approximation, node tracing, and image processing, but especially in identifying images of manufactured parts with distinct corners.

Originality/value
– A new proposed system has been presented that uses image processing techniques in combination with a computer‐aided design model to provide information to a multi‐intelligent decision module. This module will use different criteria to determine a best weld path. Once the weld path has been determined then the program generator and post‐processor can be used to send a compatible program to the robot controller. The progress so far is described.
Original languageEnglish
Pages (from-to)323-332
JournalAssembly Automation
Volume30
Issue number4
DOIs
Publication statusPublished - 28 Sep 2010
Externally publishedYes

Fingerprint

Computer aided design
Welding
Welds
Robotics
Image processing
Automatic programming
Pattern recognition systems
Shipbuilding
Ships
Robots
Neural networks
Controllers

Cite this

Sanders, David A. ; Lambert, Gareth ; Graham‐jones, Jasper ; Tewkesbury, Giles E. ; Onuh, Spencer ; Ndzi, David ; Ross, Carl. / A robotic welding system using image processing techniques and a CAD model to provide information to a multi‐intelligent decision module. In: Assembly Automation. 2010 ; Vol. 30, No. 4. pp. 323-332.
@article{edcdf2e06aff446497a4eb8016f9c7f0,
title = "A robotic welding system using image processing techniques and a CAD model to provide information to a multi‐intelligent decision module",
abstract = "Purpose– The paper aims to propose a system that uses a combination of techniques to suggest weld requirements for ships parts. These suggestions are evaluated, decisions are made and then weld parameters are sent to a program generator.Design/methodology/approach– A pattern recognition system recognizes shipbuilding parts using shape contour information. Fourier‐descriptors provide information and neural networks make decisions about shapes.Findings– The system has distinguished between various parts and programs have been generated so that the methods have proved to be valid approaches.Practical implications– The new system used a rudimentary curvature metric that measured Euclidean distance between two points in a window but the improved accuracy and ease of implementation can benefit other applications concerning curve approximation, node tracing, and image processing, but especially in identifying images of manufactured parts with distinct corners.Originality/value– A new proposed system has been presented that uses image processing techniques in combination with a computer‐aided design model to provide information to a multi‐intelligent decision module. This module will use different criteria to determine a best weld path. Once the weld path has been determined then the program generator and post‐processor can be used to send a compatible program to the robot controller. The progress so far is described.",
author = "Sanders, {David A.} and Gareth Lambert and Jasper Graham‐jones and Tewkesbury, {Giles E.} and Spencer Onuh and David Ndzi and Carl Ross",
year = "2010",
month = "9",
day = "28",
doi = "10.1108/01445151011075780",
language = "English",
volume = "30",
pages = "323--332",
journal = "Assembly Automation",
issn = "0144-5154",
publisher = "Emerald Publishing Limited",
number = "4",

}

A robotic welding system using image processing techniques and a CAD model to provide information to a multi‐intelligent decision module. / Sanders, David A.; Lambert, Gareth; Graham‐jones, Jasper; Tewkesbury, Giles E.; Onuh, Spencer; Ndzi, David; Ross, Carl.

In: Assembly Automation, Vol. 30, No. 4, 28.09.2010, p. 323-332.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A robotic welding system using image processing techniques and a CAD model to provide information to a multi‐intelligent decision module

AU - Sanders, David A.

AU - Lambert, Gareth

AU - Graham‐jones, Jasper

AU - Tewkesbury, Giles E.

AU - Onuh, Spencer

AU - Ndzi, David

AU - Ross, Carl

PY - 2010/9/28

Y1 - 2010/9/28

N2 - Purpose– The paper aims to propose a system that uses a combination of techniques to suggest weld requirements for ships parts. These suggestions are evaluated, decisions are made and then weld parameters are sent to a program generator.Design/methodology/approach– A pattern recognition system recognizes shipbuilding parts using shape contour information. Fourier‐descriptors provide information and neural networks make decisions about shapes.Findings– The system has distinguished between various parts and programs have been generated so that the methods have proved to be valid approaches.Practical implications– The new system used a rudimentary curvature metric that measured Euclidean distance between two points in a window but the improved accuracy and ease of implementation can benefit other applications concerning curve approximation, node tracing, and image processing, but especially in identifying images of manufactured parts with distinct corners.Originality/value– A new proposed system has been presented that uses image processing techniques in combination with a computer‐aided design model to provide information to a multi‐intelligent decision module. This module will use different criteria to determine a best weld path. Once the weld path has been determined then the program generator and post‐processor can be used to send a compatible program to the robot controller. The progress so far is described.

AB - Purpose– The paper aims to propose a system that uses a combination of techniques to suggest weld requirements for ships parts. These suggestions are evaluated, decisions are made and then weld parameters are sent to a program generator.Design/methodology/approach– A pattern recognition system recognizes shipbuilding parts using shape contour information. Fourier‐descriptors provide information and neural networks make decisions about shapes.Findings– The system has distinguished between various parts and programs have been generated so that the methods have proved to be valid approaches.Practical implications– The new system used a rudimentary curvature metric that measured Euclidean distance between two points in a window but the improved accuracy and ease of implementation can benefit other applications concerning curve approximation, node tracing, and image processing, but especially in identifying images of manufactured parts with distinct corners.Originality/value– A new proposed system has been presented that uses image processing techniques in combination with a computer‐aided design model to provide information to a multi‐intelligent decision module. This module will use different criteria to determine a best weld path. Once the weld path has been determined then the program generator and post‐processor can be used to send a compatible program to the robot controller. The progress so far is described.

U2 - 10.1108/01445151011075780

DO - 10.1108/01445151011075780

M3 - Article

VL - 30

SP - 323

EP - 332

JO - Assembly Automation

JF - Assembly Automation

SN - 0144-5154

IS - 4

ER -