A laser-induced breakdown spectroscopy multi-component quantitative analytical method based on a deep convolutional neural network
A laser-induced breakdown spectroscopy multi-component quantitative analytical method based on a deep convolutional neural network
复制标题
基于深度卷积神经网络的激光诱导击穿光谱多组分定量分析方法
DOI：
10.1016/j.sab.2020.105850
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Rong Shu
中科院分区：
文献类型：
--
作者：
Lu-Ning Li;Xiang-Feng Liu;Wei-Ming Xu;Jian-Yu Wang;Rong Shu
激光诱导击穿光谱（LIBS）的一个主要技术难点在于实现目标样品中多种化学成分的定量测定的理想准确度。在这项研究中，我们提出了一种基于深度卷积神经网络（CNN）构建的LIBS多组分定量分析方法。利用23个国家标准物质的1400多个LIBS光谱数据对CNN进行训练，并验证其预测能力。该实验由MarSCoDe中的LIBS系统实施，该系统将是2020年中国首次火星探测使命火星车上的火星表面成分探测器。为了评估CNN的性能，我们检查了预测的均方根误差（RMSE）值，同时考虑了整体RMSE和分量RMSE，并进一步研究了每个分量的预测相对误差。我们比较了CNN的性能与两种替代方案的基础上反向传播神经网络（BPNN）和偏最小二乘（PLS）回归，与PLS计划实际上包含两种方法，即。e. PLS 1和PLS 2。除了对RMSE的具体值和相对误差进行检验外，还进行了统计分析，使比较结果具有统计学意义。此外，我们调查基线去除预处理后的预测能力的每一种方法。结果表明，无论基于基线去除与否的光谱，CNN方法的整体精度均优于其他三种方法，且后者优于其他三种方法。由于样本数量相对较少，本工作中所展示的结果是初步的，不适合立即推广，但它们表明基于CNN的方法是一种有前途的工具，具有良好的准确性和高效率的LIBS定量分析。
One major technical difficulty of laser-induced breakdown spectroscopy (LIBS) lies in achieving ideal accuracy of quantitative determination of the multiple chemical components in a target sample. In this study, we propose a LIBS multi-component quantitative analytical method based on the construction of a deep convolutional neural network (CNN). More than 1400 LIBS spectra, collected from 23 China national standard reference materials, were utilized to train the CNN and validate its predictive ability as well. The experiment was implemented by the LIBS system in MarSCoDe, which would be the Mars Surface Composition Detector on the rover of China's first Mars exploration mission in 2020. To evaluate the performance of the CNN, we inspect the root mean square error (RMSE) value of the prediction, with both overall RMSE and component-wise RMSE considered, and we further look into the prediction relative error of each component. We compare the performance of the CNN with that of two alternative schemes based on back-propagation neural network (BPNN) and partial least squares (PLS) regression respectively, with the PLS scheme actually containing two methods, i. e. PLS1 and PLS2. Besides the examination of the specific values of RMSE and relative error, we have also carried out some statistical analysis to endow the comparison with statistical significance. Moreover, we investigate the effect of baseline removal preprocessing upon the predictive ability of each method. The results show that the CNN method has the best performance among the four methods in terms of overall accuracy, no matter the test is based on the spectra with or without baseline removal, and the superiority of the CNN over the other three methods is more significant in the latter case. Since the number of samples is relatively small, the results demonstrated in this work are preliminary and unsuitable for immediate generalization, but they indicate that the CNN-based methodology is a promising tool for LIBS quantitative analysis with good accuracy and high efficiency.
登录
查看更多内容
影响因子：
3.2
作者：
F. Rivera‐Hernández;D. Sumner;N. Mangold;K. Stack;O. Forni;H. Newsom;A. Williams;M. Nachon;J. L'Haridon;O. Gasnault;R. Wiens;S. Maurice
通讯作者：
F. Rivera‐Hernández;D. Sumner;N. Mangold;K. Stack;O. Forni;H. Newsom;A. Williams;M. Nachon;J. L'Haridon;O. Gasnault;R. Wiens;S. Maurice
影响因子：
3.5
作者：
K. Lepore;C. Fassett;E. Breves;S. Byrne;S. Giguere;T. Boucher;J. M. Rhodes;M. Vollinger;C. Anderson;R. Murray;M. Dyar
通讯作者：
K. Lepore;C. Fassett;E. Breves;S. Byrne;S. Giguere;T. Boucher;J. M. Rhodes;M. Vollinger;C. Anderson;R. Murray;M. Dyar
DOI：
10.3390/s100504907
发表时间：
2010
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Effenberger AJ Jr;Scott JR
通讯作者：
Scott JR
DOI：
10.1016/j.sab.2014.06.012
发表时间：
2014-09
期刊：
Spectrochimica Acta Part B: Atomic Spectroscopy
影响因子：
--
作者：
Eleonora D'Andrea;Stefano Pagnotta;E. Grifoni;G. Lorenzetti;S. Legnaioli;V. Palleschi;B. Lazzerini
通讯作者：
Eleonora D'Andrea;Stefano Pagnotta;E. Grifoni;G. Lorenzetti;S. Legnaioli;V. Palleschi;B. Lazzerini
影响因子：
3.3
作者：
Clegg, Samuel M.;Wiens, Roger C.;Maurice, Sylvestre
通讯作者：
Maurice, Sylvestre