Laser-induced breakdown spectroscopy and stoichiometry to identify various types of defects in metal-additive manufacturing parts

Abstract

Various defects of additive manufacturing (AM) components seriously impact their performance, which restricts the industry's development process. Therefore, component defects should be classified quickly and treated in different ways. The aim of this study was to develop a methodology to be able to quickly distinguish the defect categories of AM components by using laser-induced breakdown spectroscopy (LIBS) and the support vector machine model (SVM). Samples of AM parts without defects (control group) and with cracks, bulges, and holes were studied. Different data preprocessing methods and model evaluation criteria were used for comparison. The LIBS spectrum with the first derivative as the input variable was used to construct the SVM model without defects, cracks, bulges, and holes, and the effect was then the best. The accuracy, Kappa coefficient, and Jaccard coefficient were 0.9922, 0.9896, and 0.9846, respectively. The results show that LIBS technology combined with the SVM algorithm can be well applied for the defect classification of AM parts.