摘要
本文将反向传播人工神经网络（ＢＰ－ＡＮＮ）用于导数脉冲伏安法（ＤＰＶ）和电感耦合等离子体原子发射光谱分析（ＩＣＰ－ＡＥＳ）中重叠信号解析。详细地讨论了增益、学习速率、动量等网络参数对神经网络收敛速度和导数脉冲伏安法计算结果的影响。利用Ｖｏｉｇｔ线型函数模拟ＩＣＰ发射光谱，并用人工神经网络方法对模拟的光谱重叠干扰作了研究，得到了满意的结果。
Back-propagation artificial neural network (BP-ANN) has been used to resolve overlapped signals in differential pulse voltammetry (DPV) and inductively coupled plasma atomic emission spectrometry (ICP-AES). The effects of neural network parameters including gain, learning rate, and momentum on network convergence and DPV computation results have been investigated. The voigt profile function has been used to simulate ICP emission spectra. Artificial neural network has been used to correct simulated spectral overlap interference and satisfactory results have been obtained.
出处
《抚顺石油学院学报》
1996年第3期17-20,共4页
Journal of Fushun Petroleum Institute
基金
国家教委和吉林省科技发展资助
关键词
神经网络
原子发射光谱
光谱分析
分析化学
Artificial neural network
Chemometrics
Differential pulse voltammdtry
Inductively coupled plasma atomic emission spectrometry
