人工神经网络法校正ICP┐AES中重叠光谱干扰  

ARTIFICIAL NEURAL NETWORK APPLIED FOR SPECTRAL OVERLAP INTERFERENCE CORRECTION IN ICP AES

作　　者：张卓勇[1] 刘思东[1] 曾宪津[2] 

机构地区：[1]东北师范大学化学系 [2]中国科学院长春应用化学研究所

出　　处：《光谱学与光谱分析》1997年第5期77-81,共5页Spectroscopy and Spectral Analysis

基　　金：国家自然科学基金;吉林省科技发展项目

摘　　要：本文将反向传播人工神经网络（ＢＰ－ＡＮＮ）用于ＩＣＰ－ＡＥＳ中重叠光谱干扰的校正。利用模拟的Ｃｅ４１３．３８０ｎｍ和Ｐｒ４１３．３６１ｎｍ光谱对神经网络的训练方式、输入值范围、噪声影响等作了较详细的讨论。A back propagation artificial neural network (BP ANN) has been applied to correcting spectral overlap interference in inductively coupled plasma atomic emission spectrometry(ICP AES).Some network parameters including the range of input values and training sequence for training patterns presented to the network were discussed using simulated Ce 413 380nm and Pr 413 380nm line profiles.Results show that the noise in simulated mixture spectra will slow down the network convergence and has more influence on network prediction.

关 键 词：人工神经网络 光谱干扰校正 ICP AES 

分 类 号：O657.31[理学—分析化学]