Development of a Prediction Model for Gas Hydrate Formation in Multiphase Pipelines by Artificial Intelligence. Issue 8 (10th June 2022)

• Record Type: Journal Article
• Authors: Sayani, Jai Krishna Sahith; Sivabalan, Vinayagam; Foo, Khor Siak; Pedapati, Srinivasa Rao; Lal, Bhajan
• Is Part Of: Chemical engineering & technology. Volume 45:Issue 8(2022)
• Page Start: 1482
• Page End: 1488
• Publication Date: 2022-06-10
• Subjects: Artificial intelligence -- Artificial neural networks -- Gas hydrate formation -- Multiphase flow behavior -- Multiphase pipelines; Chemical engineering -- Periodicals; Chemical processes -- Periodicals; 660.05
• DOI: 10.1002/ceat.202100359
• Languages: English
• ISSNs: 0930-7516

Abstract

Abstract: A prediction model is developed by means of artificial neural networks (ANNs) to determine the gas hydrate formation kinetics in multiphase gas dominant pipelines with crude oil. Experiments are conducted to determine the rate of formation and reaction kinetics of hydrates formation in multiphase systems. Based on the results, an artificial intelligence model is proposed to predict the gas hydrate formation rate in multiphase transmission pipelines. Two ANN models are suggested with single‐layer perceptron (SLP) and multilayer perceptron (MLP). The MLP shows more accurate prediction when compared to SLP. The models were predicted accurately with high prediction accuracy both for the pure and multiphase systems. Abstract : A prediction model was developed by means of artificial neural networks (ANNs) to determine the gas hydrate formation kinetics in multiphase gas dominant pipelines with crude oil. The results let conclude that the application of ANNs could be a potential solution for the accurate prediction model development to forecast the reaction kinetics of gas hydrate formation and dissociation.