Using Artificial Neural Network for Prediction of Red and Blue Dyes in Supercritical Carbon Dioxide

摘要

On environmental and economic point of view, having an estimation of solubility of dyes in supercritical dyeing is very important. In this paper an artificial neural network (ANN) with 2 hidden layers and 10 neurons on each layer has been used for prediction of dyes solubility in supercritical carbon dioxide. Temperature and pressure were used as input of the network which gives solubility of solutes as its output. Obtained results show good agreement with collected experimental data. The simple network is able to reproduce the solubility of dyes with desired accuracy.