AN ARTIFICIAL NEURAL NETWORK MODEL FOR THE PREDICTION OF COMPRESIBILITYFACTOR FOR GENERALIZED EQUATION OF STATE

M.Ravi Kumar, Ermias Girma Aklilu

Abstract: In recent years, modeling using Artificial Neural Networks is attracting a lot of attention among scientists and engineers, and is being hailed as one of the greatest computational tools ever developed. This is due to the apparent ability of Neural Networks to emulate the brains ability to learn by examples, which in turn enables the networks to make decisions and draw conclusions when presented with complex, noisy and/or incomplete information. The functional relationship among reduced pressure, compressibility, accentric factor, and reduced temperature of a gas is known as generalized equation of state (EOS). Though several generalized equations of state are available in literature each equation has its inherent disadvantages. There is no single generalized equation of state, which is mathematically friendly and can satisfy the experimental compressibility data with engineering accuracy. Hence a two parameter of generalized EOS model is developed using Artificial Neural Network in the present work. A feed forward network with back propagation of errors algorithm is used in training the network. In this work the supervised learning, sum squared error is used as lapnov function. The model is found to be in good agreement with the experimental results

Keywords: Artificial Neural Network, Compressibility Factor, Sum Squared Error, Acentric Factor.

DOI: https://doi.org/10.15623/ijret.2016.0512003