Search

A simultaneous catalytic effect copper (II) and iron (III) on the oxidation of acid chrome blue K by potassium bromate in dilute sulfuric acid medium was observed. But there was an obvious difference in their reaction rates, and the ratio of the reaction constant changed with time. And their spectral addiitive properties were not satisfactory. The simultaneous determination of copper and iron by catalytic kinetic spectrophotometric method was realized by using a three-layer Levenberg-Marquardt BP neural network to cope with the experimental data. The optimum conditions of reaction and determination were studied. The calculation results of the determination in synthetic samples and human hair were satisfactory.

By means of artificial neural network and Levenberg-Marquardt back-propagation training algorithm, the three components of vitamin B1, B2, B6 were determined simultaneously, in which the spectra overlapped. In the range of 390-520 nm, the fluorescence intensities at 15 wavelengths were taken as a character of the artificial neural network, and samples were arranged by the method of equality design. The mean recoveries of vitamin B1, vitamin B2, and vitamin B6 were 99.86%, 99.60% and 99.49% respectively. The RSDs of the results were 1.7%, 1.6%, and 1.7%.

A new fluorescence method by artificial neural network for the simultaneous determination of tryptophan and tyrosine was developed. The determination was carried out in the KH2PO4-K2HPO4 buffer solution (pH = 7.15) and at the EX (excitation) wavelength of 224 nm. In the range of 290-400 nm, the fluorescence intensities at fourteen wavelengths were taken as characteristic parameters of the artificial neural network, and the samples were arranged by the method of equality design. The mean recoveries of tryptophan and tyrosine were 100.9% and 101.6% respectively. The RSDs of the results were 4.18% and 4.17%. The method has been applied to the determination of tryptophan and tyrosine in compound amino acid injection, and the relative errors were 4.0% and 2.6%, respectively. The results were better than those of other networks in training speed and accuracy. In conclusion, the new network spectrofluorimetry is a good choice for multicomponent resolving analysis.

By the means of artificial neural network and Levenberg-Marquardt back-propagation train algorithm, the two components of phenol, resorcinol were determined simultaneously, in which the fluorescence spectra overlapped. In 290-345 nm, the fluorescence intensity at 14 wavelengths were taken as character of artificial neural network, and samples were arranged by method of equality design. The mean recovery of phenol and resorcinol were 100.2%, 99.99% respectively. The RSD of the results were 0.4% and 1.3%.