Grant: Engage Grants Program
University of Waterloo
$25,000.00
Computer vision for real-time welding feedback
EF 2016-17
Résumé
Industrial real-time monitoring has become commonplace, however the specific context of arc welding offers unique challenges to imaging, since the exceptionally bright welding plasma causes conventional CCD or CMOS cameras to saturate and fail to produce meaningful images. In response to this limitation, Xiris Automation has developed a camera which incorporates specialized sensors to offer unusually high dynamic range of 140dB, higher than most other high dynamic range cameras on the market. Thus, in the context of welding applications, typically having rapidly changing light levels and hot spots, the Xiris camera becomes an ideal choice for inspection, allowing the features of a surface to be captured simultaneously with images of the arc and liquid metal.The Xiris system is hardware based (thus faster than software-based high-dynamic range solutions), so the video stream captured by a Xiris camera could, in principle, be used to monitor and control a welding process in real-time, to allow for real-time adjustment of the welding process (weld tip location, for example) to optimize welding accuracy and quality. To that end, Xiris seeks the assistance of the University of Waterloo to assist in articulating a strategy for welding inspection, taking advantage of the company's hardware solutions. The proposed project at the University of Waterloo will focus on research to exploit the image quality of the Xiris hardware. A tangible goal has been identified, which is to develop image-based seam tracking of the welding arc during automated continuous pipe welding. The research will focus on real-time algorithms for video analysis to identify and locate the pipe seam, the welding tip, and the actual centre of the arc relative to the seam, allowing Xiris to offer feedback and control signals in seam-tracking welding equipment.The proposed project experience will introduce both partners to challenges encountered in welding and image processing, and open the door for future collaborations involving more complex, challenging, valued-added applications for Xiris systems.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
493178-2015
Name nom
Fieguth, Paul
Department département
Systems Design Engineering
Organization id
33
Institution établissement
University of Waterloo
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2016
Competition year année de concours
2015
Award amount
25000
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1553
Committee name en
Ontario Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Ontario
Area of application code
500
Area of application group en
Manufacturing processes and products
Area of application group fr
Procédés et produits industriels
Area of application en
Manufacturing processes and products
Area of application fr
Procédés et produits industriels
Research subject code
2708
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Image processing
Research subject fr
Traitement des images
Partie
1
Nb partie
1
Application title
Computer vision for real-time welding feedback
Keyword
NSERC
Application summary
Industrial real-time monitoring has become commonplace, however the specific context of arc welding offers unique challenges to imaging, since the exceptionally bright welding plasma causes conventional CCD or CMOS cameras to saturate and fail to produce meaningful images. In response to this limitation, Xiris Automation has developed a camera which incorporates specialized sensors to offer unusually high dynamic range of 140dB, higher than most other high dynamic range cameras on the market. Thus, in the context of welding applications, typically having rapidly changing light levels and hot spots, the Xiris camera becomes an ideal choice for inspection, allowing the features of a surface to be captured simultaneously with images of the arc and liquid metal.The Xiris system is hardware based (thus faster than software-based high-dynamic range solutions), so the video stream captured by a Xiris camera could, in principle, be used to monitor and control a welding process in real-time, to allow for real-time adjustment of the welding process (weld tip location, for example) to optimize welding accuracy and quality. To that end, Xiris seeks the assistance of the University of Waterloo to assist in articulating a strategy for welding inspection, taking advantage of the company's hardware solutions. The proposed project at the University of Waterloo will focus on research to exploit the image quality of the Xiris hardware. A tangible goal has been identified, which is to develop image-based seam tracking of the welding arc during automated continuous pipe welding. The research will focus on real-time algorithms for video analysis to identify and locate the pipe seam, the welding tip, and the actual centre of the arc relative to the seam, allowing Xiris to offer feedback and control signals in seam-tracking welding equipment.The proposed project experience will introduce both partners to challenges encountered in welding and image processing, and open the door for future collaborations involving more complex, challenging, valued-added applications for Xiris systems.