Coal Analysis by Single-Beam-Splitting Laser-Induced Breakdown Spectroscopy (LIBS) with Support Vector Machine (SVM). (13th June 2023)

• Record Type: Journal Article
• Authors: Cheng, Junjie; Cao, Zhi; Han, Xiaodan; Li, Lianshun; Wang, Jian; Fan, Qingwen; Lin, Qingyu
• Is Part Of: Analytical letters. Volume 56:Number 9(2023)
• Page Start: 1399
• Page End: 1409
• Publication Date: 2023-06-13
• Subjects: Coal analysis -- laser-induced breakdown spectroscopy (LIBS) -- single-beam-splitting (SBS) -- support vector machine (SVM); Chemistry, Analytic -- Periodicals; Chemistry, Analytic -- Abstracts; 543
• DOI: 10.1080/00032719.2022.2132401
• Languages: English
• ISSNs: 0003-2719

Abstract

Abstract: Laser-induced breakdown spectroscopy (LIBS) has been widely used in coal analysis. In this work, single-beam-splitting LIBS (SBS-LIBS) was used to quantitatively analyze coal. This technique was performed by adding a beam splitter to a conventional single-pulse LIBS (SP-LIBS) set-up. The laser light was split into two beams and focused upon the same point on the sample surface. Carbon, hydrogen, nitrogen, ash, and volatile components were determined in this work. A support vector machine (SVM) model was constructed for quantitative analysis. The root mean square error of prediction (RMSEP), average relation error of prediction (AREP), and average absolute error of prediction (AAEP) were employed to evaluate the accuracy of the SVM with SBS-LIBS and SP-LIBS. The results showed an overall improvement in SBS-LIBS for coal analysis, in which the AAEP of carbon, hydrogen, nitrogen, ash and volatile components were decreased to 1.04%, 0.18% 0.08%, 1.80%, and 4.30% from 3.70%, 0.27%, 0.09%, 3.06%, and 7.99%, respectively.