Accuracy improvement of iron ore analysis using laser-induced breakdown spectroscopy with a hybrid sparse partial least squares and least-squares support vector machine model,Journal of Analytical Atomic Spectrometry

当前位置： X-MOL 学术 › J. Anal. At. Spectrom. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Accuracy improvement of iron ore analysis using laser-induced breakdown spectroscopy with a hybrid sparse partial least squares and least-squares support vector machine model
Journal of Analytical Atomic Spectrometry ( IF 3.1 ) Pub Date : 2018-06-08 00:00:00 , DOI: 10.1039/c8ja00119g
Y. M. Guo _{1,

2,

3,

4} , L. B. Guo _{1,

2,

3,

4} , Z. Q. Hao _{1,

2,

3,

4} , Y. Tang _{1,

2,

3,

4} , S. X. Ma _{1,

2,

3,

4} , Q. D. Zeng _{1,

2,

3,

4,

5} , S. S. Tang _{1,

2,

3,

4} , X. Y. Li _{1,

2,

3,

4} , Y. F. Lu _{1,

2,

3,

4} , X. Y. Zeng _{1,

2,

3,

4}

Affiliation

The quantitative analysis of iron ore by laser-induced breakdown spectroscopy (LIBS) is usually complicated due to nonlinear self-absorption and matrix effects. To overcome this challenge, a hybrid sparse partial least squares (SPLS) and least-squares support vector machine (LS-SVM) model was proposed to analyze the content of total iron (TFe) and oxides SiO₂, Al₂O₃, CaO, and MgO in iron ore. In this study, 24 samples were used for calibration and 12 for prediction. Sparse partial least squares was used for variable selection and establishing the multilinear regression model between spectral data and concentrations; LS-SVM was used to fit the residual errors of the SPLS regression model to compensate for the nonlinear effects. The model parameters were determined by using the tenfold cross-validation (CV) method. With the hybrid model, the root-mean-square-error of prediction (RMSEP) values of TFe, SiO₂, Al₂O₃, CaO, and MgO were 0.6242, 0.3569, 0.0456, 0.0962, and 0.2157 wt%, respectively. The results showed that the hybrid model yielded better performance than only the conventional SPLS or LS-SVM model. This study demonstrated that the hybrid model is a competitive data processing method for iron ore analysis using LIBS.

中文翻译：

混合稀疏最小二乘和最小二乘支持向量机模型的激光诱导击穿光谱法提高铁矿石分析的准确性

由于非线性自吸收和基体效应，通过激光诱导击穿光谱法（LIBS）对铁矿石进行定量分析通常很复杂。为了克服这一挑战，提出了一种混合稀疏偏最小二乘（SPLS）和最小二乘支持向量机（LS-SVM）模型来分析总铁（TFe）和氧化物SiO ₂，Al ₂ O ₃的含量，铁矿石中的CaO和MgO。在这项研究中，使用24个样本进行校准，使用12个样本进行预测。稀疏偏最小二乘用于变量选择并建立光谱数据与浓度之间的多元线性回归模型；LS-SVM用于拟合SPLS回归模型的残差，以补偿非线性影响。通过使用十倍交叉验证（CV）方法确定模型参数。使用混合模型，可以得出TFe，SiO ₂，Al ₂ O ₃的预测均方根误差（RMSEP）值，CaO和MgO分别为0.6242、0.3569、0.0456、0.0962和0.2157wt％。结果表明，混合模型比仅传统的SPLS或LS-SVM模型产生更好的性能。这项研究表明，混合模型是一种使用LIBS进行铁矿石分析的竞争性数据处理方法。

更新日期：2018-06-08

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11