Validation of a Machine Learning–Assisted LIBS Model for Quantitative Steel Analysis

Abstract

Laser-induced breakdown spectroscopy (LIBS) shows great promise for the rapid chemical characterization of materials. However, quantitative analysis of elements remains challenging due to strong matrix effects and the predominance of emission lines. In the present study, a machine learning–assisted LIBS model (LIBS-ML pipeline) was employed to analyze carbon, medium-alloy, and high-alloy steels. A total of 900 spectra from 18 reference specimens were used to train Random Forest (RF), Gradient Boosting (GB), and Extremely Randomized Trees (ET) ensemble models, while five independent steel specimens were reserved for prediction evaluation. The ET model demonstrated the best training performance (MSE = 0.1551; R² = 0.9435), while the RF model exhibited greater stability during independent validation. Low prediction errors were obtained for carbon steels, with mean absolute error (MAE) values as low as 0.0142 wt% for C and 0.0178 wt% for Mn. In medium-alloy steel, the predicted values of Cr and Ni remained close to the nominal compositions. Higher deviations were observed in high-alloy steel, with MAE reaching 1.1191 wt% for Ni and 1.0919 wt% for Mo, reflecting the increased complexity of the matrix. The obtained results confirmed the LIBS–ML pipeline applicability for quantitative steel analysis and highlight its potential as a rapid tool for metallurgical monitoring and alloy characterization.