An artificial neural network approach to laser-induced breakdown spectroscopy quantitative analysis ☆
An artificial neural network approach to laser-induced breakdown spectroscopy quantitative analysis ☆
复制标题
DOI：
10.1016/j.sab.2014.06.012
复制
发表时间：
2014-09
期刊：
影响因子：
--
通讯作者：
Eleonora D'Andrea;Stefano Pagnotta;E. Grifoni;G. Lorenzetti;S. Legnaioli;V. Palleschi;B. Lazzerini
中科院分区：
文献类型：
--
作者：
Eleonora D'Andrea;Stefano Pagnotta;E. Grifoni;G. Lorenzetti;S. Legnaioli;V. Palleschi;B. Lazzerini
激光诱导击穿光谱 (LIBS) 定量分析的常用方法是基于校准曲线的使用，并使用适当的参考标准适当构建。最近，越来越多地使用依赖人工神经网络（ANN）原理的统计方法。然而，ANN 分析经常被用作“黑匣子”系统，并且 LIBS 光谱的特性没有得到充分利用。通过神经网络对 LIBS 光谱中包含的原始数据进行先验探索，以了解光谱中哪些重要区域将用于委托给后续神经网络进行校准，从而能够揭示最初未知的重要信息，尽管这些信息已经包含在光谱中。此次交流将证明，一种基于专门用于处理 LIBS 光谱的神经网络的方法将为 LIBS 定量分析提供可行、快速且稳健的方法。相对于当前的方法，这将允许使用相对有限数量的参考样本来训练网络，并为分析大量样本提供完全自动化的方法。
The usual approach to laser-induced breakdown spectroscopy (LIBS) quantitative analysis is based on the use of calibration curves, suitably built using appropriate reference standards. More recently, statistical methods relying on the principles of artificial neural networks (ANN) are increasingly used. However, ANN analysis is often used as a ‘black box’ system and the peculiarities of the LIBS spectra are not exploited fully. Ana prioriexploration of the raw data contained in the LIBS spectra, carried out by a neural network to learn what are the significant areas of the spectrum to be used for a subsequent neural network delegated to the calibration, is able to throw light upon important information initially unknown, although already contained within the spectrum. This communication will demonstrate that an approach based on neural networks specially taylored for dealing with LIBS spectra would provide a viable, fast and robust method for LIBS quantitative analysis. This would allow the use of a relatively limited number of reference samples for the training of the network, with respect to the current approaches, and provide a fully automatizable approach for the analysis of a large number of samples.