径向基函数神经网络荧光光度法同时测定痕量铝、镓、铟、铊  

Simultaneous Determination of Trace Aluminum,Gallium, Indium and Thallium by Molecule Fluorescence Photometry with Radial Basis Function Neural Networks

作　　者：曾庆慧[1] 金继红[1] 龚成勇[1] 宫晓英[1] 

机构地区：[1]中国地质大学材料科学与化学工程学院,武汉430074

出　　处：《分析科学学报》2006年第1期93-95,共3页Journal of Analytical Science

摘　　要：以径向基网络（RBF）对荧光光谱严重重叠的Al^3＋、Ga^3＋、In^3＋、Tl^3＋四组分混合体系同时进行测定。通过正交设计安排样本，在激发波长390mn下，测定446～615nm的发射光谱。以34个特征波长处的荧光强度值作为网络特征参数，经网络训练和计算得出Al^3＋、Ga^3＋、In^3＋、Tl^3＋四者的平均回收率分别为99．07％、103．49％、98．72％、95．04％，在时间和精度上都比LMBP网络优越。By the means of Radial Basis Function Neural Networks and Molecule Fluorescence Photometry , the four components of, Al, Ga, In and Tl in which the fluorescence spectra were overlapped, were determined simultaneously. The excitation wavelength was 390 nm and the emission wavelength varied from 446 nm to 615 nm, and samples were arranged by method of orthogonal design. The fluorescence intensity at 34 wavelengths were taken as character of artificial neural network and the mean recoveries of Al,Ga,ln and Tl were 99.07%, 103.49% ,98.72 % and 95.04%, respectively. The results obtained with radial basis function network are better than those provided with the LMBP network in training time and determination precision.

关 键 词：径向基函数神经网络 荧光光度法 铝 镓 铟 铊 

分 类 号：O657.3[理学—分析化学]