Toggle Main Menu Toggle Search

Open Access padlockePrints

Prediction of absorption and stripping factors in natural gas processing industries using feed forward artificial neural network

Lookup NU author(s): Dr Zainal Ahmad, Dr Jie ZhangORCiD



This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND).


In dynamic simulators, mathematical models are applied in order to study the time dependentbehaviour of a system, meaning the system process units and the corresponding control units. Absorption and stripping are the unit operations which are widely used in the natural gas processing industries. Many attempts have been made to define an average absorption factor method to short-cut the time consuming rigorous calculation procedures. One of the options for this complex engineering modelling problem is artificial intelligent (AI) approach. Artificial neural networks (ANN) havebeen shown to be able to approximate any continuous non-linear functions and have been used to build data base empirical models for non-linear processes. In this study, feedforward neural networks (FANN) models were used to model the absorption efficiency. The mean square error (MSE), residue analysis and coefficient determination based on the observed and prediction output is chosen as the performance criteria of model. It was found that the developed feedforward neural networks (FANN) models provided satisfactory model with the MSE and coefficient determination of 0.0003 and0.9998 for new unseen data from literature respectively.

Publication metadata

Author(s): Ahmad Z, Zhang J, Kashiwao T, Bahadori A

Publication type: Article

Publication status: Published

Journal: Petroleum Science and Technology

Year: 2016

Volume: 34

Issue: 2

Pages: 105-113

Online publication date: 22/02/2016

Acceptance date: 17/11/2015

Date deposited: 15/12/2015

ISSN (print): 1091-6466

ISSN (electronic): 1532-2459

Publisher: Taylor & Francis Inc.


DOI: 10.1080/10916466.2015.1122628


Altmetrics provided by Altmetric