Automated defect classification of SS304 TIG welding process using visible spectrum camera and machine learning
Authors:
- Daniel BacioiuDBDaniel Bacioiu
- Geoff MeltonGMGeoff Melton
- Mayorkinos PapaeliasMayorkinos Papaelias
- Rob ShawRSRob Shaw
- 1 October 2019
- journal article
- research article
- Published by Elsevier in NDT & E International
- Vol. 107
Abstract
No abstract availableKeywords
Funding Information
- Engineering and Physical Sciences Council (EPSRC)
- TWI Limited
- National Structural Integrity Research Centre
- School of Metallurgy and Materials
- University of Birmingham
This publication has 8 references indexed in Scilit:
- Monitoring weld pool oscillation using reflected laser pattern in gas tungsten arc weldingJournal of Materials Processing Technology, 2018
- Boosting Active Contours for Weld Pool Visual Tracking in Automatic Arc WeldingIEEE Transactions on Automation Science and Engineering, 2015
- Real-time vision-based control of weld pool sizeWelding International, 2012
- Real-Time Monitoring of Weld Pool during GTAW using Infra-Red Thermography and analysis of Infra-Red thermal imagesWelding in the World, 2011
- Three-dimensional reconstruction of specular surface for a gas tungsten arc weld poolMeasurement Science and Technology, 2007
- Real-time arc-welding defect detection and classification with principal component analysis and artificial neural networksNDT & E International, 2007
- A study on automatic seam tracking in pulsed laser edge welding by using a vision sensor without an auxiliary light sourceJournal of Manufacturing Systems, 2002
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998