首页 > 论文 > 激光与光电子学进展 > 57卷 > 19期(pp:193002--1)

基于激光诱导击穿光谱与径向基函数神经网络的铝合金定量分析

Quantitative Analysis of Aluminum Alloy Based on Laser-Induced Breakdown Spectroscopy and Radial Basis Function Neural Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

采用激光诱导击穿光谱(LIBS)技术激发铝合金标样表面的不同位置,得到320组光谱数据;然后对原始光谱数据进行预处理,并选取铝合金中6种主要元素的20条特征谱线构成320×20光谱数据矩阵;再采用主成分分析法对光谱矩阵进行降维,使模型输入变量从20个降至6个;最后,将经过主成分降维的光谱数据作为径向基函数神经网络的输入量,对铝合金中5种主要非铝元素(Si、Fe、Cu、Mn和Mg)建立多元定标模型。结果表明:该模型的拟合优度均值为0.978,均方根误差均值为0.31%;主成分分析结合径向基函数神经网络的方法能够有效减小参数波动,并能校正基体效应,提高模型定量分析的精度和稳定性,尤其是对于Fe、Si和Cu等低含量元素的分析精度具有明显的提升作用。

Abstract

In this paper, laser-induced breakdown spectroscopy (LIBS) was used to obtain 320 sets of spectral data at different positions on the surfaces of aluminum alloy samples. Then, these spectral data were preprocessed, and 20 characteristic spectral lines of the six main elements in aluminum alloy were selected to form a 320×20 spectral data matrix. Next, the 20 variables that were inputted into the model were reduced to 6 through principal component analysis. Finally, the reduced-dimensional spectral data were inputted into the radial basis function neural network model to establish multivariate calibration models for five main nonaluminum elements (Si, Fe, Cu, Mn, and Mg) in aluminum alloy. The results revealed that the mean goodness of fit of the model was 0.978 and its mean root mean square error was 0.31%. Principal component analysis combined with a radial basis function neural network can effectively reduce parameter fluctuations, correct matrix effects, and improve the accuracy and stability of the model quantitative analysis; in particular, this combination can significantly improve the accuracy of analysis of elements with relatively low content, such as Fe, Si, and Cu.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:O433.5; TN247

DOI:10.3788/LOP57.193002

所属栏目:光谱学

基金项目:江苏省重点研发计划、南京航空航天大学研究生创新基地开放基金;

收稿日期:2020-01-02

修改稿日期:2020-02-24

网络出版日期:2020-10-01

作者单位    点击查看

潘立剑:南京航空航天大学机电学院, 江苏 南京 210001
陈蔚芳:南京航空航天大学机电学院, 江苏 南京 210001
崔榕芳:南京航空航天大学机电学院, 江苏 南京 210001
李苗苗:南京航空航天大学机电学院, 江苏 南京 210001

联系人作者:陈蔚芳(meewfchen@nuaa.edu.cn)

备注:江苏省重点研发计划、南京航空航天大学研究生创新基地开放基金;

【1】Gao A J, Wang G, Qu X L, et al. The research on impurities separating and sorting technology in the pretreatment process of the aluminum scrap recycling [J]. Recyclable Resources and Circular Economy. 2015, 8(2): 33-36.
高安江, 王刚, 曲信磊, 等. 废铝再生预处理过程中的杂质分离和分类分选技术研究 [J]. 再生资源与循环经济. 2015, 8(2): 33-36.
Gao A J, Wang G, Qu X L, et al. The research on impurities separating and sorting technology in the pretreatment process of the aluminum scrap recycling [J]. Recyclable Resources and Circular Economy. 2015, 8(2): 33-36.
高安江, 王刚, 曲信磊, 等. 废铝再生预处理过程中的杂质分离和分类分选技术研究 [J]. 再生资源与循环经济. 2015, 8(2): 33-36.

【2】Qiu H O, Zheng H T, Tang Z Y. Analysis of rocks and minerals [J]. Chinese Journal of Analysis Laboratory. 2014, 33(11): 1349-1364.
邱海鸥, 郑洪涛, 汤志勇. 岩石矿物分析 [J]. 分析试验室. 2014, 33(11): 1349-1364.

【3】Chen N, Liu Y X, Du S Z, et al. Research progress in applications of nanosecond and femtosecond laser-induced breakdown spectroscopy [J]. Laser & Optoelectronics Progress. 2016, 53(5): 050003.
陈娜, 刘尧香, 杜盛喆, 等. 纳秒、飞秒激光诱导击穿光谱技术的应用研究进展 [J]. 激光与光电子学进展. 2016, 53(5): 050003.

【4】Feng W L, Wang F J, Zeng W Q, et al. CCD spectrum measurement system for laser induced breakdown spectroscopy [J]. Laser & Optoelectronics Progress. 2013, 50(1): 013002.
冯为蕾, 王福娟, 曾万祺, 等. 应用于LIBS的CCD光谱测量系统 [J]. 激光与光电子学进展. 2013, 50(1): 013002.

【5】Hu Y, Li Z H, Lü T. Quantitative measurement of iron content in geological standard samples by laser-induced breakdown spectroscopy combined with artificial neural network [J]. Laser & Optoelectronics Progress. 2017, 54(5): 053003.
胡杨, 李子涵, 吕涛. 激光诱导击穿光谱结合人工神经网络测定地质标样中的铁含量 [J]. 激光与光电子学进展. 2017, 54(5): 053003.

【6】Lin Y Z, Yao M Y, Chen T B, et al. Detection of Cu and Cr in the soil of navel orange plantation in Gannan by LIBS [J]. Laser & Optoelectronics Progress. 2013, 50(5): 053002.
林永增, 姚明印, 陈添兵, 等. 激光诱导击穿光谱检测赣南脐橙种植土壤的Cu和Cr [J]. 激光与光电子学进展. 2013, 50(5): 053002.

【7】Li J X, Yang Y L, Meng F W, et al. Matrix correction method used for liquid steel online quantitative analysis by LIBS [J]. Laser & Optoelectronics Progress. 2013, 50(3): 031406.
李俊香, 杨友良, 孟凡伟, 等. 用于LIBS钢液在线定量分析的基体校正方法 [J]. 激光与光电子学进展. 2013, 50(3): 031406.

【8】Kotzagianni M, Kakkava E, Couris S. Laser-induced breakdown spectroscopy (LIBS) for the measurement of spatial structures and fuel distribution in flames [J]. Applied Spectroscopy. 2016, 70(4): 627-634.

【9】Yaroshchyk P, Death D L, Spencer S J. Comparison of principal components regression, partial least squares regression, multi-block partial least squares regression, and serial partial least squares regression algorithms for the analysis of Fe in iron ore using LIBS [J]. Journal of Analytical Atomic Spectrometry. 2012, 27(1): 92-98.

【10】Yu Y, Zhao N J, Wang Y, et al. Research on univariate and multiple linear regression calibration methods by laser induced breakdown spectroscopy [J]. Laser & Optoelectronics Progress. 2015, 52(9): 093001.
余洋, 赵南京, 王寅, 等. 激光诱导击穿光谱单变量及多元线性回归方法研究 [J]. 激光与光电子学进展. 2015, 52(9): 093001.

【11】Li Y S, Lu W Y, Zhao J B, et al. Detection of caloric value of coal using laser-induced breakdown spectroscopy combined with BP neural networks [J]. Spectroscopy and Spectral Analysis. 2017, 37(8): 2575-2579.
李越胜, 卢伟业, 赵静波, 等. 基于BP神经网络和激光诱导击穿光谱的燃煤热值快速测量方法研究 [J]. 光谱学与光谱分析. 2017, 37(8): 2575-2579.

【12】Sun L X, Yu H B, Cong Z B, 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.
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.

【13】Gu Y H, Zhao N J, Ma M J, et al. Quantitative analysis of Cr in soils using LIBS with principal components regression [J]. Journal of Optoelectronics·Laser. 2016, 27(7): 748-753.
谷艳红, 赵南京, 马明俊, 等. 基于主成分回归的土壤重金属LIBS定量分析方法研究 [J]. 光电子·激光. 2016, 27(7): 748-753.

【14】Han X H, Zhang Y H, Sun F J, et al. Method for determining index weight based on principal component analysis [J]. Journal of Sichuan Ordnance. 2012, 33(10): 124-126.
韩小孩, 张耀辉, 孙福军, 等. 基于主成分分析的指标权重确定方法 [J]. 四川兵工学报. 2012, 33(10): 124-126.

【15】Qiao J F, Han H G. Optimal structure design for RBFNN structure [J]. Acta Automatica Sinica. 2010, 36(6): 865-872.
乔俊飞, 韩红桂. RBF神经网络的结构动态优化设计 [J]. 自动化学报. 2010, 36(6): 865-872.

引用该论文

Pan Lijian,Chen Weifang,Cui Rongfang,Li Miaomiao. Quantitative Analysis of Aluminum Alloy Based on Laser-Induced Breakdown Spectroscopy and Radial Basis Function Neural Network[J]. Laser & Optoelectronics Progress, 2020, 57(19): 193002

潘立剑,陈蔚芳,崔榕芳,李苗苗. 基于激光诱导击穿光谱与径向基函数神经网络的铝合金定量分析[J]. 激光与光电子学进展, 2020, 57(19): 193002

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF