Quantitative Analysis of Ca and Mg in Slag with Artificial Neural Networks

Abstract

Abstract:

Back-propagation neural network combining with laser-induced breakdown spectroscopy (LIBS), are used to calibrate and quantify the contents of Ca and Mg of different kinds of slag. The networks were trained by means of a gradient descent with momentum and adaptive learning rate back-propagation algorithm. The performance of the neural networks with different inputs is studied, so as its predictive performances to be improved, and the effect of the presence of matrix-specific information in the inputs was studied. Higher performance is obtained when the network was fed with one matrix-specific spectral window than only with the areas of selected peaks. The network is fed with one matrix-specific spectral window can utilize more information of spectra, and better correct the matrix effect and line interference. The inputs of the neural networks, however, need serious consideration, since they have a good effect on the measurement reproducibility and accuracy.

Key words: laser-induced breakdown spectroscopy; quantitative analysis; neural network; slag

LIANG Yun-Xian, CHEN Xing-Long, WANG Qi, WANG Jing-Ge, YANG Yang, NI Zhi-Bo, DONG Feng-Zhong. Quantitative Analysis of Ca and Mg in Slag with Artificial Neural Networks[J]. Journal of Atmospheric and Environmental Optics, 2012, (2): 124-130.

References

[1] Cremers D A, Radziemski L J. Handbook of Laser-induced Breakdown Spectroscopy [M]. John Wiley & Sons Ltd, Chichester, 2006.
[2] Gaudiuso R, Dell'Aglio M, Pascale O D. Laser induced breakdown spectroscopy for elemental analysis in environmental, cultural heritage and space applications: a review of methods and results [J]. Sensors, 2010, 10(8): 7434-7468.
[3] Ciucci A, Corsi M, Palleschi V, et al. A new procedure for quantitative analysis by laser induced breakdown spectroscopy [M]. Appl. Spectrosc., 1999, 53(8): 960–964.
[4]Chen Xinglong, Dong Fengzhong, Wang Qi. Quantitative analysis of slag by calibration-free laser-induced breakdown spectroscopy [J]. Spectroscopy and Spectral Analysis, 2011, 31(2): 3289-3293(in Chinese).
陈兴龙, 董凤忠, 王琦, 等. 自由定标激光诱导击穿光谱技术在炉渣成分定量分析中的应用[J] 光谱学与光谱分析, 2011, 31(2): 3289-3293.
[5] Sturm V, Peter L, Noll R, et al. Steel analysis with laser-induced breakdown spectrometry in the vacuum ultraviolet [J].Appl. Spectrosc, 2000,54(9): 1275-1278.
[6] Robert H N. Theory of the back-propagation neural network [C]. Proe. UCNN, Washington DC, 1989, (1): 593-605.
[7] Ferreira E C, Milori D M B P, Ferreira E J. Artificial neural networks for Cu quantitative determination in siol using a portable laser induced breakdown spectroscopy system [J]. Spectrochimica Acta Part B, 2008, 63(10): 1216-1220.
[8] Shen Qinmei, Zhou Weidong, Li Kexue, et al. Determination of Cr and Ba in soil using laser induced breakdown spectroscopy with artificial neural networks [J]. Acta Photonica Sinica, 2010, 39(12): 2134-2138(in Chinese).
沈沁梅, 周卫东, 李科学, 等. 激光诱导击穿光谱结合神经网络测定土壤中的Cr和Ba [J]. 光子学报, 2010, 39(12): 2134-2138.
[9] Inakollu P, Philip T, Rai A K, et al. A comparative study of laser induced breakdown spectroscopy analysis for element concentration in aluminum alloy using atificial neural networks and calibration methods [J]. Spectrochimica Acta Part B, 2009, 64(1): 99-104.
[10] Motto-Ros V, Koujelev A.S, Osinski G.R. Quantitative multi-elemental laser-induced breakdown spectroscopy using artificial neural networks [J]. Journal of the European Optical Society-Rapid Publications, 2008, 3: 08011-1-08011-5.
[11] Sirven J B, Bousquet B, Canioni L, et al. Qualitative and quantitative investigation of chromium-polluted soils by laser-induced breakdown spectroscopy combined with neural networks analysis [J]. Anal. Bioanal. Chem., 2006, 385(2): 256-262.
[12] Wang Qi, Chen Xinglong. Quantitative analysis of Mn, Cr in steel based on laser-induced breakdown spectroscopy [J]. Spectroscopy and Spectral Analysis, 2011, 31(9): 2546-2551(in Chinese).
王琦, 陈兴龙. 基于激光诱导击穿光谱技术对钢中Mn、Cr元素的定量分析 [J]. 光谱学与光谱分析, 2011, 31(9): 2546-2551.
[13] Sun Lanxiang, Yu Haibin, Cong Zhibo, et al. Quantitative analysis of Mn and Si of steels by laser- induced breakdown spectroscopy combined with neural networks [J]. Acta Optica Sinica, 2010, 30(9): 2757-2765(in Chinese).
孙兰香, 于海斌, 丛智博, 等. 激光诱导击穿光谱技术结合神经网络定量分析钢中的Mn和Si [J]. 光学学报, 2010,30(9): 2757-2765.