Paper
2 July 2007 Arc-welding quality assurance by means of embedded fiber sensor and spectral processing combining feature selection and neural networks
Author Affiliations +
Proceedings Volume 6619, Third European Workshop on Optical Fibre Sensors; 66193P (2007) https://doi.org/10.1117/12.738765
Event: Third European Workshop on Optical Fibre Sensors, 2007, Napoli, Italy
Abstract
A new spectral processing technique designed for its application in the on-line detection and classification of arc-welding defects is presented in this paper. A non-invasive fiber sensor embedded within a TIG torch collects the plasma radiation originated during the welding process. The spectral information is then processed by means of two consecutive stages. A compression algorithm is first applied to the data allowing real-time analysis. The selected spectral bands are then used to feed a classification algorithm, which will be demonstrated to provide an efficient weld defect detection and classification. The results obtained with the proposed technique are compared to a similar processing scheme presented in a previous paper, giving rise to an improvement in the performance of the monitoring system.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
J. Mirapeix, P. B. García-Allende, A. Cobo, O. Conde, and J. M. López-Higuera "Arc-welding quality assurance by means of embedded fiber sensor and spectral processing combining feature selection and neural networks", Proc. SPIE 6619, Third European Workshop on Optical Fibre Sensors, 66193P (2 July 2007); https://doi.org/10.1117/12.738765
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Plasma

Feature selection

Fiber optics sensors

Principal component analysis

Neurons

Sensors

Artificial neural networks

Back to Top