ARTIFICIAL NEURAL NETWORK FOR THE QUANTITATIVE ANALYSIS OF AIR TOXIC VOCs

Abstract

A 23-6-10 artificial neural network system (ANNs) with three layers has been developed in this paper. The simultaneous concentration analysis of ten air toxic volatile organic compounds (VOCs) was resolved. The net was trained with a back- propagation algorithm. The input signals were the absorbance values at the selected peak wavenumbers and a series of equispaced wavenumbers. The output is the predicted concentration for each component in the prediction samples. Several parameters were optimized to ensure convergence and to speed up learning. The comparison of prediction results at the characteristic peak wavenumbers and the series of equispaced wavenumbers showed that results obtained at the peak absorption wavenumbers were superior to that at the equispaced wavenumbers. The results also showed that ANN can successfully resolve the concentration analysis problem when the FTIR spectra of several constituents in the mixture interfere with each other.

Keywords:

• VOCs
• FTIR
• Multicomponent analysis
• Artificial neural network

ACKNOWLEDGMENTS

This project was supported by National Science Foundation of China, The Research Fund for the Doctoral Program of Higher Education, and Science and Technology Committee of Jiangsu Province.