摘要
本文采用 PAR- Zn、 Cu、 Co显色体系 ,应用人工神经网络原理 ,通过误差反向传播方法 ,对于紫外吸收重叠的三组分金属配合物体系同时进行含量测定。在 5 80～ 44 0 nm的范围内 ,以 14个特定波长处的吸收值作为网络特征参数 ,并通过均匀设计安排样本。Zn、Cu、Co三者的平均回收率分别为 95 .2 2 %、95 .98%、10 0 .5 %。实验表明 ,其结果准确 ,性能良好。
By means of artificial neural network and back- propagation train algorithm,the three-component metal coordinate compounds of P AR-Zn,Cu,Co were determined simultaneously,in which the spectra overlapped.In 5 80—440 nm,the absorbance(A)at 14 wavelength were taken as character parameter o f artificial neural network,and samples were arranged by method of uniformity de sign.The mean recovery of Zn,Cu,Co were 95.22%,95.98% and 100.5%.The experime nt results show that the determination is accurate,and the method has good perfo rmance.
出处
《光谱学与光谱分析》
SCIE
EI
CAS
CSCD
北大核心
2000年第3期409-411,共3页
Spectroscopy and Spectral Analysis
关键词
人工神经网络
紫外光谱
锌
铜
钴
三组分配合物
Artificial neural network, Coordinate compound, Ultraviolet spectrum, Zinc, Copper, Chromiun
