Abstract：The selection of characteristic wavelength is the important factor to influence the calculation precision during simultaneous determination of multi-components due to the interaction effect among components. Sn(IV), Mo(VI) and Sb(III) can all react with salicyl fluorone (SAF) and cetyltriethylammnonium bromide (CTMAB) to form stable ternary micellar compounds. The sensitivity of reactons are high. However, the ultraviolet absorption spectrua were seriously overlapped. In this study, the combination of Kohonen neural network with Elman network was proposed to establish the quantitative analysis method for the simultaneous determination of three metal elements in cast iron. In this method, the characteristic wavelength point was firstly selected based on the clustering ability of Kohonen neural network. Then, the absorbance data at optimized characteristic wavelength were used to establish prediction model using the optimized Elman neural network. The results showed that the whole prediction results were best when the model was created by the absorbance data at 26 characteristic wavelength points from the whole spectra. The experimental method was applied to the determination of synthetic sample. The absolute values of average relative error between prediction results and actual concentrations were between 2.24% and 3.10%. The proposed method was applied to the simultaneous determination of tin, molybdenum and antimony in cast iron sample, and the found results were consistent with those obtained by atomic absorption spectrometry (AAS). The relative standard deviations (RSD, n=7) were between 1.2% and 2.7%.
方洪壮,吴刚,孙长海.RBF网络光度法与BP网络光度法的比较[J].计算机与应用化学,2002,19(4):415-418.FANG Hong-zhuang,WU Gang,SUN Chang-hai.Comparision between RBF network spectrophotometry and BP network spectrophotometry[J].Computers and Applied Chemistry,2002,19(4):415-418.
[2]
曾庆慧,金继红,龚成勇,等.径向基函数神经网络荧光光度法同时测定痕量铝、镓、铟、铊[J].分析科学学报,2006,22(1):93-95.ZENG Qing-hui,JIN Ji-hong,GONG Cheng-yong,et al.Simultaneous determination of trace aluminum,gallium,indium and thallium by molecule fluorescence photometry with radial basis function neural networks[J].Journal of Analytical Science,2006,22(1):93-95.
[3]
高玲,任守信.吸收光谱Elman回归神经网络同时测定CuⅡ,NiⅡ,CrⅢ3组分混合物[J].冶金分析,2004,24(5):1-4.GAO Ling,REN Shou-xin.Simultaneousdetermination of CuⅡ,NiⅡ,CrⅢ three components mixtureby Elman recurrent neural network in absorption spectra[J].Metallurgical Analysis,2004,24(5):1-4.
[4]
鲍峰伟,彭黔荣,刘景艳,等.潜变量聚类分析法在近红外光谱波长范围选择中的应用研究[J].光谱学与光谱分析,2008,28(5):1057-1061.BAO Feng-wei,PENG Qian-rong,LIU Jing-yan,et al.Applied study on clustering of variables around latent componentsmethod in wavelength region selection with near-Infrared spectroscopy[J].Spectroscopy and Spectral Analysis,2008,28(5):1057-1061.
[5]
赵安新,汤晓君,张钟华,等.利用Tikhonov正则化算法进行光谱特征波长的选择及其参数优化[J].光谱学与光谱分析,2014,34(7):1836-1839.ZHAO An-xin,TANG Xiao-jun,ZHANG Zhong-hua,et al.The spectral characteristic wavelength selection and parameter optimization based on tikhonov regularization[J].Spectroscopy and Spectral Analysis,2014,34(7):1836-1839.
[6]
刘小洪,冯明友,杨午阳,等.利用Kohonen神经网络划分二维地震相-以柴达木盆地E区风险勘探为例[J].岩性油气藏,2011,23(4):115-118.LIU Xiao-hong,FENG Ming-you,YANG Wu-yang,et al.Application of Kohonen neural network to 2D seismic facies division in E area of Qaidam Basin[J].Lithologic Reservoirs,2011,23(4):115-118.
[7]
王中,肖克炎,丁建华.Kohonen人工神经网络在新疆东天山地区斑岩型钼矿资源预测中的应用[J].地质学刊,2015,39(2):231-235.WANG Zhong,XIAO Ke-yan,DING Jian-hua.Application of Kohonen artificial neural networks to the prediction of porphyry molybdenum resources in East Tian Shan,Xinjiang[J].Journal of Geology,2015,39(2):231-235.
[8]
马小慧,阳育德,龚利武.基于Kohonen聚类和SVM算法的电网日最大负荷预测[J].电网与清洁能源,2014,30(2):7-11.MA Xiao-hui,YANG Yu-de,GONG Li-wu.Forecasting of the daily maximum load based on a combined model of kohonen clustering and SVM[J].Power System and Clean Energy,2014,30(2):7-11.
[9]
邵珊珊,孙丽君.基于Elman神经网络的燃气轮机功率预测方法研究[J].计算机科学与探索,2014,8(11):1358-1364.SHAO Shan-shan,SUN Li-jun.Gas turbine power prediction based on Elman neural network[J].Journal of Frontiers of Computer Science and Technology,2014,8(11):1358-1364.
[10]
郭斌,许菲菲,陆艺,等.Elman网络温度预测气密性检测研究[J].中国测试,2015,41(7):119-123.GUO Bin,XU Fei-fei,LU Yi,et al.The research of air tightness detection based on Elman network temperature prediction[J].China Measurement & Test,2015,41(7):119-123.
[11]
其木格,马成有,张玉玲.系统聚类-BP神经网络分光光度法同时测定地质样品中的钼钨锡锑[J].内蒙古师范大学学报:自然科学汉文版,2004,33(1):59-62.Qimuge,MA Cheng-you,ZHANG Yu-ling.The study of hierchical clustering method back propagation neural network spectrophotometry simultaneous determination of Mo,W,Sn and Sb in geological samples[J].Journal of Inner Mongolia Normal University:Natural Science Edition,2004,33(1):59-62.
[12]
陈国松,王镇浦,侯晋.吸光光度法同时测定痕量钼锡和锑[J].理化检验:化学分册,1998,34(6):243-245.CHEN Guo-song,WANG Zheng-pu,HOU Jin.Simultaneous spectrophotometric determination of traces of molybdenum tin and antimony[J].Physical Testing and Chemical Analysis Part B:Chemical Analysis,1998,34(6):243-245.
[13]
王进平,孙晓波,李井会,等.Kohonen网络与BP网络用于钨和钼的同时测定[J].光谱学与光谱分析,2006,26(12):2319-2322.WANG Jin-ping,SUN Xiao-bo,LI Jing-hui,et al.Application of kohonen and BP neural networks to simultaneous determination of tungsten and molybdenum[J].Spectroscopy and Spectral Analysis,2006,26(12):2319-2322.
[14]
高玲,任守信.Elman回归神经网络研究同时定量分析紫外重叠光谱[J].石油化工,2004,33(3):266-269.GAO Ling,REN Shou-xin.Study of simultaneous quantitative analysis of overlapping UV spectra by Elman recurrent neural network[J].Petrochemical Technology,2004,33(3):266-269.
[15]
王英华,王淑兰,王洪艳.光度法同时测定地质样品中的钼钨锡锑[J].分析试验室,1999,18(5):53-55.WANG Ying-hua,WANG Shu-lan,WANG Hong-yan.Study of spectrophotometric simultaneous determination of Mo,W,Sn and Sb in geological samples[J].Analytical Laboratory,1999,18(5):53-55.
[16]
唐华应,方艳.柠檬酸掩蔽钨硫氰酸盐光度法测定钨铁中钼量[J].云南冶金,2004,33(10):53-55.TANG Hua-ying,FANG Yan.Determination of molybdenum in ferro-tungsten with citric acid masked tungsten thiocyanate spectrometric method[J].Yunnan Metallurgy,2004,33(10):53-55.
[17]
陶丘博,申琦,张小亚,等.基于粒子群优化的波段选择方法在多组分同时测定中的应用[J].分析化学,2009,37(8):1197-1200.TAO Qiu-Bo,SHEN Qi,ZHANG Xiao-ya,et al.Simultaneous determination of multicomponent by wavelength selection using particle swarm optimization algorithm[J].Chinese Journal of Analytical Chemistry,2009,37(8):1197-1200.
