Accuracy improvement for multimetal analysis by laser‐induced breakdown spectroscopy with least squares support vector machine

Abstract

An efficient method has been developed to analyze metal species by using laser‐induced breakdown spectroscopy (LIBS). A least squares support vector machine (LSSVM) was applied to quantitative analysis of multimetal samples with different matrix content, as LSSVM can select the input variables and convert the mapping to the feature space to obtain the linear performance. In this work, three kinds of metal species (alloy steel, ferrochromium alloy, and ferromanganese alloy) were used to construct the LSSVM model. The correlation coefficients (R2), the root‐mean‐square error of prediction (RMSEP), and the average relative error (ARE) were calculated according to the estimated concentrations of chromium (Cr), manganese (Mn), titanium (Ti), and molubdenum (Mo) using the LSSVM model. The results showed that RMSEP decreased from 1.7047%, 1.3453%, 1.9253%, and 2.9431% to 0.0747%, 0.0942%, 0.0192%, and 0.0809%. The ARE of Cr, Mn, Ti, and Mo decreased from 10.2370, 9.8276%, 13.2460%, and 16.2386% to 1.0179%, 1.3937%, 2.1228%, and 1.6257%, respectively. This study demonstrated that LSSVM is an effective algorithm to improve both the accuracy and stability for metal analysis using LIBS.

Quantitative analysis of Cu in Traditional Chinese medicinal materials using laser‐induced breakdown spectroscopy

“…Che et al 15 improve the accuracy of multitetal analysis with LIBS and least squares support vector machines. Dai et al 16 identified aluminum alloy by LIBS combined with machine algorithm. Sirven et al 17 used LIBS combined with neural networks to perform qualitative and quantitative analysis of chromium-contaminated soil.…”

Determining the temperature of aluminum plasma produced by laser‐induced breakdown spectroscopy based on its ultraviolet emission spectra

“…It is widely used in qualitative elemental analysis. 7,8 However, its reliability is relevant to the laser properties, substrates, and ambient surroundings. 9 Furthermore, it is important to measure accurate temperature for improving the application of LIBS.…”

Research on a LIBS-based detection method of medium-and-low alloy steel hardness

“…where b refers to the regression coefficient, and e refers to the residual matrix of the model. The least squares support vector machine (LS-SVM) 23,24 is a machine learning method developed on the basis of statistical learning theory. The key parameter indexes of LS-SVM are input vectors, kernel function types, and corresponding parameters.…”