人工神经网络用于光度法同时测定三组分染料混合物

应用人工神经网络原理,以快速BP算法,对紫外可见吸收光谱严重重叠的三组分的染料溶液同时进行含量测定。在200～590nm的范围内,以7个特征波长处的吸收值作为网络特征参数,通过网络训练,复品红、结晶紫、藏红T的相对标准偏差分别为0.34％,0.67％,1.03％,三者的回收率在95.5％～104％之间。实验表明,该算法速度快,预测结果准确,可望用人工神经网络和光度法结合定量测定混合染料。

Application of Artificial Neural Network to Simultaneous Spectrophotometric Determination of Three Components Dyestuff

Principle and application of typical model neural network system combined with artificial neural network to spectral analysis. By means of artificial neural network and back-propagation train algorithm, the three-components dyestuff was determined simulta- neously, in which the ultraviolet-visible spectra overlapped. In the range of 200-590 nm, the absorbance (A) at 7 wavelengths was taken as a character of the artificial neural network. The mean RSD of carbol fuchsin powder, crystal violet and safranine T were 0.34 % , 0.67 % , 1.03 % , respectively. The recoveries of the results were between 99.5 % -102 % . The results were better in training speed and the accuracy. In conclusion, the artificial neural network combined with spectrophotometer is a good method for the determination of multi-components dyestuff.