Quantcast

Arc-Welding Spectroscopic Monitoring based on Feature Selection and Neural Networks.

Research paper by P Beatriz PB Garcia-Allende, Jesus J Mirapeix, Olga M OM Conde, Adolfo A Cobo, Jose M JM Lopez-Higuera

Indexed on: 21 Oct '08Published on: 21 Oct '08Published in: Sensors (Basel, Switzerland)



Abstract

A new spectral processing technique designed for application in the on-line detection and classification of arc-welding defects is presented in this paper. A noninvasive fiber sensor embedded within a TIG torch collects the plasma radiation originated during the welding process. The spectral information is then processed in 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 previous works, giving rise to an improvement in the performance of the monitoring system.