Using hybrid neural models to describe supercritical fluid extraction processes

Abstract

This work presents the results of a hybrid neural model (HNM) technique as applied to modeling supercritical fluid extraction (SCFE) curves obtained from two Brazilian vegetable matrices. The serial HNM employed uses a neural network to estimate parameters of a phenomenological model. A small set of SCFE data for each vegetable was used to generate a semi-empirical extended data set, large enough for efficient network training, using three different approaches. Afterwards, other sets of experimental data, not used during the training procedure, were used to validate each approach. The HNM correlates well withthe experimental data, and it is shown that the predictions accomplished with this technique may be promising for SCFE purposes

Error Entropy and Mean Square Error Minimization Algorithms for Neural Identification of Supercritical Extraction Process

“…These types of models are based on phenomenological and simplified description of the process, using rigid restrictions [1]. In Fonseca et al [2], the results of a hybrid neural model of the curves of the supercritical extraction of two Brazilian vegetal matrices were presented. In this approach, an artificial neural net is used to identify parameters for a phenomenological model, minimizing some restrictions of neural nets.…”