Prediction of Vapour-Liquid Equilibrium Data Using Neural Network for Hydrocarbon Ternary System. ethane-propane-n-butane
I. A.Daniyan , A. O.Adeodu , O. L.Daniyan
Corresponding Author : I. A. Daniyan
Department of Mechanical &Mechatronics Engineering, Afe Babalola University, Ado Ekiti, Nigeria.
Email ID : email@example.com
Received : 2014-01-06 Accepted : 2014-01-14 Published : 2014-01-14
Abstract : The prediction of vapour- liquid equilibrium is useful in process simulation and control as well making process engineering design decisions. Prediction of vapour-liquid equilibrium data was carried out using MATLAB software. Pre-existing data of hydrocarbon ternary system (ethane-propane-n-butane) in terms of phase composition, temperature and pressure was trained by iteratively adjusting networks, initializing weights and biases to minimize the network performance function net. MATLAB a software package containing artificial neural network was employed to predict the point where there is no change in composition of both liquid and vapour formed when liquid mixtures of ethane-propane-n-butane vapourises. Predicted values show reasonable and good correlation results when compared to the experimental data thus indicating that the network is an efficient and a good prediction tool for vapour-liquid equilibrium ternary systems.
Keywords : artificial neural network, biases, correlation, performance function net, vapour-liquid
Citation : I. A. Daniyan(2014) Prediction of Vapour-Liquid Equilibrium Data Using Neural Network for Hydrocarbon Ternary System (ethane-propane-n-butane). J. of Computation in Biosciences and Engineering. V1I1. DOI : 10.5281/zenodo.999784
Copyright : © 2014 I. A. Daniyan, et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Journal of Computation in Biosciences and Engineering
ISSN : 2348-7321
Volume 1 / Issue 1
ScienceQ Publishing GroupDownload Article