光学学报, 2010, 30 (9): 2757, 网络出版: 2014-05-15   

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 下载: 510次

Quantitative Analysis of Mn and Si of Steels by LaserInduced Breakdown Spectroscopy Combined with Neural Networks
孙兰香 1,2,*于海斌 1,2丛智博 1,2辛勇 1,2
作者单位
1 中国科学院沈阳自动化研究所工业信息学重点实验室, 辽宁 沈阳 110016
2 2中国科学院研究生院, 北京 100049
摘要
激光诱导击穿光谱(LIBS)作为一种快速的化学组成分析技术,在冶金过程的原位、在线及远程分析方面展现了突出的应用前景和研究价值。利用神经网络建立定标模型,结合LIBS技术对不同品种钢中的Mn和Si组分进行定量分析,研究了不同输入方式对神经网络性能的影响,并与光谱分析中常用的内标法进行对比。结果表明,对于化学体系复杂的多基体钢的定量分析,神经网络定标法能够更充分利用光谱中的信息,有利于校正基体效应和谱线之间的干扰;但是,神经网络的输入方式对网络性能具有重要影响,只有在合理选择输入方式下才能有效提高测量重复性和准确性。
Abstract
As a speedy analytical technique of chemical compositions, laserinduced breakdown spectroscopy (LIBS) is appealing in metallurgical industry for insitu, online or longrange applications. Combined with LIBS, neural networks are used to calibrate and quantify the concentration of Mn and Si of different kinds of steels. The performance of the neural networks with different inputs is studied. Compared with the common internal calibration methods, neural networks 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 great effect on the measurement reproducibility and accuracy.
参考文献

[1] E. Tognoni, G. Cristoforetti, S. Legnaioli et al.. A numerical study of expected accuracy and precision in calibrationfree laserinduced breakdown spectroscopy in the assumption of ideal analytical plasma [J]. Spectrochim. Acta B, 2007, 62(12): 1287~1302

[2] B. Sallé, P. Mauchien, S. Maurice. Laserinduced breakdown spectroscopy in openpath configuration for the analysis of distant objects [J]. Spectrochim. Acta B, 2007, 62(8): 739~768

[3] R. S. Harmon, F. C. DeLucia, C. E. McManus et al.. Laserinduced breakdown spectroscopyan emerging chemical sensor technology for realtime fieldportable, geochemical, mineralogical, and environmental applications [J]. Appl. Geochem., 2006, 21(5): 730~747

[4] 李捷, 陆继东, 林兆祥 等. 激光诱导击穿固体样品中金属元素光谱的实验研究[J]. 中国激光, 2009, 36(11): 2882~2887

    Li Jie, Lu Jidong, Lin Zhaoxiang et al.. Experimental analysis of spectra of metallic elements in solid samples by laserinduced breakdown spectroscopy[J]. Chinese J. Lasers, 2009, 36(11): 2882~2887

[5] 从然, 张保华, 樊建梅 等. 激光诱导等离子体中Al原子发射光谱的时间、空间演化特性实验研究[J]. 光学学报, 2009, 29(9): 2594~2600

    Cong Ran, Zhang Baohua, Fan Jianmei et al.. Experimental investigation on time and spatial evolution of emission spectra of Al atom in laserinduced plasmas [J]. Acta Optica Sinica, 2009, 29(9): 2594~2600

[6] Rong Shu, Hongxing Qi, Gang Lü et al.. Laserinduced breakdown spectroscopy based detection of lunar soil simulants for moon exploration [J]. Chin. Opt. Lett., 2007, 5(1): 58~59

[7] 谢承利, 陆继东, 姚顺春 等. 激光诱导击穿光谱物质辨识与定量分析[J]. 激光与光电子学进展, 2009, 46(11): 65~72

    Xie Chengli, Lu Jidong, Yao Shunchun et al.. Quantitative analysis and material identification by laser induced breakdown spectroscopy [J]. Laser & Optoelectronics Progress, 2009, 46(11): 65~72

[8] V. Sturm, L. Peter, R. Noll. Steel analysis with laserinduced breakdown spectrometry in the vacuum ultraviolet [J]. Appl. Spectrosc., 2000, 54(9): 1275~1278

[9] 姚宁娟, 陈吉文, 杨志军 等. 一种用于冶金炉前快速分析的新仪器〖CD2〗激光诱导击穿光谱仪[J]. 光谱学与光谱分析, 2007, 27(7): 1452~1454

    Yao Ningjuan, Chen Jiwen, Yang Zhijun et al.. Laserinduced breakdown spectrometer〖CD2〗 a new tool for quick analysis of onthespot sample in metallurgy [J]. Spectroscopy and Spectral Analysis, 2007, 27(7): 1452~1454

[10] V. Sturm, H. U. Schmitz, T. Reuter et al.. Fast vacuum slag analysis in a steel works by laserinduced breakdown spectroscopy [J]. Spectrochim. Acta B, 2008, 63(10): 1167~1170

[11] R. Noll, V. Sturm, U. Aydin et al.. Laserinduced breakdown spectroscopyfrom research to industry, new frontiers for process control [J]. Spectrochim. Acta B, 2008, 63(10): 1159~1166

[12] S. Laville, M. Sabsabi, F. R. Doucet. Multielemental analysis of solidified mineral melt samples by laserinduced breakdown spectroscopy coupled with a linear multivariate calibration [J]. Spectrochim. Acta B, 2007, 62(12): 1557~1566

[13] S. M. Clegg, E. Sklute, M. D. Dyar et al.. Multivariate analysis of remote laserinduced breakdown spectroscopy spectra using partial least squares, principal component analysis, and related techniques [J]. Spectrochim. Acta B, 2009, 64(1): 79~88

[14] P. Inakollu, T. Philip, A. K. Rai et al.. A comparative study of laser induced breakdown spectroscopy analysis for element concentrations in aluminum alloy using artificial neural networks and calibration methods [J]. Spectrochim. Acta B, 2009, 64(1): 99~104

[15] J.B. Sirven, B. Bousquet, L. Canioni et al.. Qualitative and quantitative investigation of chromiumpolluted soils by laserinduced breakdown spectroscopy combined with neural networks analysis [J]. Anal. Bioanal. Chem., 2006, 385(2): 256~262

孙兰香, 于海斌, 丛智博, 辛勇. 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. Sun Lanxiang, Yu Haibin, Cong Zhibo, Xin Yong. Quantitative Analysis of Mn and Si of Steels by LaserInduced Breakdown Spectroscopy Combined with Neural Networks[J]. Acta Optica Sinica, 2010, 30(9): 2757.

本文已被 30 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!