Neural computing approach for estimation of natural gas dew point temperature in glycol dehydration plant

ABSTRACT

Hydrate formation and water accumulation during transmission process can be prevented by effective dehydration of gas streams. This study investigates the application of multi-layer perceptron artificial neural network to estimate natural gas dew point temperature using contactor temperature and TEG purity as independent variables. A dataset comprised of 173 data points is extracted from the literature. The proposed model is considered a great help for engineers to have precise dew point temperature predictive tool in wide ranges of concerning variables. Results obtained from the proposed model show R-squared and mean square error of 1.000 and 0.156, respectively. Accordingly, the remarkable agreement between predicted and experimental values is observed.

KEYWORDS:

• Gas dehydration
• equilibrium water dew point
• artificial neural network
• modelling

Disclosure statement

No potential conflict of interest was reported by the authors.

ORCID

Alireza Baghban http://orcid.org/0000-0002-7224-4704