神经网络在测定炉渣中Ca和Mg含量的应用

大气与环境光学学报 ›› 2012, Vol. ›› Issue (2): 124-130.

神经网络在测定炉渣中Ca和Mg含量的应用

梁云仙1, 陈兴龙1,2, 王琦1, 王静鸽1, 杨阳1, 倪志波1, 董凤忠1

（1 中国科学院安徽光学精密机械研究所，安徽合肥 230031;
2 合肥工业大学仪器科学与光电工程学院，安徽合肥 230009）

出版日期:2012-03-28 发布日期:2012-03-29
通讯作者: 梁云仙（1987-），女，山东邹城人，研究生，研究方向为激光光谱技术及其应用。 E-mail:liangyunxian2005@126.com
作者简介:梁云仙（1987-），女，山东邹城人，研究生，研究方向为激光光谱技术及其应用。
基金资助:
国家自然科学基金(11075184)、中科院合肥物质科学研究院知识创新工程领域前沿项目资助

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

LIANG Yun-xian1, CHEN Xing-long1,2, WANG Qi1, WANG Jing-ge1, YANG Yang1, NI Zhi-bo1, DONG Feng-zhong1

Published:2012-03-28 Online:2012-03-29

摘要/Abstract

摘要：

为对炉渣中的Ca、Mg含量进行定量分析，将反向传播神经网络与激光诱导击穿光谱技术相结合，采用自适应学习速率结合附加动量的方法对25种样品进行网络仿真训练，建立了定标模型。鉴于网络输入对提高测量结果重复性和准确性的影响，训练过程中着重研究了仅使用元素谱线积分强度及将一段背景谱线强度与元素谱线积分强度相结合的两种网络输入对网络性能的影响，并在非训练样品中任意抽取5种样品，对定标模型进行了验证。结果表明，在分析成分复杂的炉渣中的Ca、Mg含量时，采用加入一段背景谱线积分强度的网络输入，神经网络能够更充分的利用光谱中的信息，对消除基体效应和谱线之间的干扰具有较好的预测效果。

关键词: 激光诱导击穿光谱, 定量分析, 神经网络, 炉渣

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

梁云仙陈兴龙王琦王静鸽杨阳倪志波董凤忠. 神经网络在测定炉渣中Ca和Mg含量的应用[J]. 大气与环境光学学报, 2012, (2): 124-130.

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.

参考文献

[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.

[1]	张琦锦, 郭映映, 李素文, ∗, 牟福生, ∗. 基于主成分分析的 RBF 神经网络预测 SO2 浓度[J]. 大气与环境光学学报, 2022, 17(5): 550-557.
[2]	许镇义, 王瑞宾, 康宇, ∗, 曹洋, 张聪, 王仁军, . 移动源排放遥测主要影响因素分析及预测[J]. 大气与环境光学学报, 2022, 17(2): 220-229.
[3]	郭映映, 齐贺香, 李素文∗, 牟福生∗. 基于粒子群算法的BP 神经网络在大气 NO2 浓度预测中的应用研究[J]. 大气与环境光学学报, 2022, 17(2): 230-240.
[4]	金钊, 邱康俊∗, 张苗苗. 基于BP 神经网络的能见度估测研究[J]. 大气与环境光学学报, 2021, 16(5): 415-423.
[5]	张怡文, 袁宏武∗, 孙鑫, 吴海龙, 董云春. 基于Adam 注意力机制的PM2:5浓度预测方法[J]. 大气与环境光学学报, 2021, 16(2): 117-126.
[6]	李佳欣, 赵鹏, 方薇∗, 宋尚香, . 基于深度学习的多角度遥感影像云检测方法[J]. 大气与环境光学学报, 2020, 15(5): 380-392.
[7]	傅院霞, 王莉, 徐丽, 周彧. 三种感冒药片微量元素的LIBS 检测[J]. 大气与环境光学学报, 2020, 15(4): 305-313.
[8]	王莉, 周彧, 宫昊, 傅院霞, 徐丽. 样品温度对激光诱导黄铜等离子体辐射特性的影响[J]. 大气与环境光学学报, 2020, 15(2): 110-116.
[9]	郭金家, 卢渊, 李楠, 刘春昊, 田野, 薛博洋, 张超, 郑荣儿. LIBS水下原位探测技术研究进展[J]. 大气与环境光学学报, 2020, 15(1): 13-22.
[10]	杨丽超1,杨瑞兆2,苏雪娇1,於有利1,周卫东1. 铝合金中元素Cr和Cu的双脉冲激光诱导击穿光谱检测[J]. 大气与环境光学学报, 2019, 14(5): 345-350.
[11]	赵敏杰,司福祺,周海金,汪世美,江宇. 星载大气痕量气体差分吸收光谱仪0~1数据处理研究[J]. 大气与环境光学学报, 2019, 14(1): 66-73.
[12]	张恺张玉钧何莹尤坤刘国华陈晨高彦伟贺春贵鲁一冰刘文清. 基于Fast ICA及神经网络的机动车尾气NO和NO2定量分析研究[J]. 大气与环境光学学报, 2016, 11(6): 435-441.
[13]	尹华亮侯宗余袁廷璧王哲. 激光诱导击穿光谱技术在环境监测中的应用综述[J]. 大气与环境光学学报, 2016, 11(5): 322-337.
[14]	张磊王哲丁洪斌. LIBS在气溶胶诊断方面的应用[J]. 大气与环境光学学报, 2016, 11(5): 338-346.
[15]	王华东倪志波付洪波贾军伟 Markus W. Sigrist 董凤忠. LIBS用于气溶胶分析的研究与应用进展[J]. 大气与环境光学学报, 2016, 11(5): 347-360.