Experimental investigation and ANN modelling on CO2 hydrate kinetics in multiphase pipeline systems

Abstract

Gas hydrates are progressively becoming a key concern when determining the economics of a reservoir due to flow interruptions, as offshore reserves are produced in ever deeper and colder waters. The creation of a hydrate plug poses equipment and safety risks. No current existing models have the feature of accurately predicting the kinetics of gas hydrates when a multiphase system is encountered. In this work, Artificial Neural Networks (ANN) are developed to study and predict the effect of the multiphase system on the kinetics of gas hydrates formation. Primarily, a pure system and multiphase system containing crude oil are used to conduct experiments. The details of the rate of formation for both systems are found. Then, these results are used to develop an A.I. model that can be helpful in predicting the rate of hydrate formation in both pure and multiphase systems. To forecast the kinetics of gas hydrate formation, two ANN models with single layer perceptron are presented for the two combinations of gas hydrates. The results indicated that the prediction models developed are satisfactory as R2 values are close to 1 and M.S.E. values are close to 0. This study serves as a framework to examine hydrate formation in multiphase systems.

Behavior of Gas Hydrate Formation in Long-Distance Pipelines for CO2 Transportation

“…At low pressures, a higher N 2 content necessitates more heat for water molecules to combine with N 2 molecules and form hydrates due to the larger size of N 2 molecules and weaker interaction forces with water molecules . Conversely, when the N 2 content is low, the reduced intermolecular forces between gas molecules make it more likely for water molecules to combine with CO 2 molecules and form hydrates, resulting in greater hydrate production …”

“…23 Conversely, when the N 2 content is low, the reduced intermolecular forces between gas molecules make it more likely for water molecules to combine with CO 2 molecules and form hydrates, resulting in greater hydrate production. 24 From a kinetic perspective, a higher N 2 content at low pressure increases the proportion of nitrogen molecules, leading to more competition between N 2 molecules and CO 2 molecules for water molecules to form hydrates. Additionally, the lower frequency of intermolecular collisions at low pressure slows down the rate at which water molecules combine with gas molecules to form hydrates, resulting in reduced hydrate production.…”

Machine Learning an Intelligent Approach in Process Industries: A Perspective and Overview

“…The following section includes a widespread review in the field of AI and ML to solve the relevant issues. It also unfolds several types of ML and AI techniques which are used for data cleaning, management [64], interpretation [65], parameter prediction [66][67][68], estimation [69], controlling [70], and decision making [71,72]. The achievements and developments have proved the advantages of ML and AI for large data storage capabilities and highly efficient estimations.…”

CO2 Hydrate Formation Kinetics in the Presence of a Layered Double Hydroxide Nanofluid

“…The chemical affinity model requires only macroscopic properties like the temperature and pressure and can also be used in the presence of additives. Several researchers have used artificial neural network (ANN)‐based predictive models for different fields of applications such as gas hydrates 29–31, the mechanical properties of metal matrix composites 32, building energy consumption prediction 33, nanofluid properties 34, 35, and petroleum quality measurements 36.…”