Analysis of Infrared Spectra of Liquid Crystal Mixtures by Neural Networks Methods

Abstract

We have used neural network approach to the classification of infrared spectra of binary mixtures of 4-n-nonyl-4′-cyanobiphenyl (9CB) and 4-n-pentylphenyl-trans-4′-pentylcyclohexane-1-carboxylate (5H5). We built the neural networks, using nonlinear back propagation algorithm (BPN). The input neurons represent selected spectral intensities in the range of 1000–40000 wave numberskm. The output neurons represent the concentrations of the mixtures, the phases (isotropic, nematic and smectic) at the experimental temperatures. In the classifier mode, the network correctly classifies the smectic liquid crystal phases.¹ The training of the neural networks was carried out fairly well. The predictions of compositions of the mixtures agree qualitatively.