Automatic classification of steel plates based on laser induced breakdown spectroscopy and support vector machines

Abstract

Welding processes are one of the most widely spread industrial activities, and their quality control is an important area of research. The presence of residual traces from the protective antioxidant coating, is a problematic issue since it causes a significant reduction in the welding seam strength. In this work, a solution based on a Laser Induced Breakdown Spectroscopy (LIBS) setup and a Support Vector Machines (SVMs) classifier to detect and discriminate antioxidant coating residues in the welding area without destroying the sample before the welding procedure is proposed. This system could be an interesting and fast tool to detect aluminium impurities.