| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 691486 | Journal of the Taiwan Institute of Chemical Engineers | 2014 | 7 Pages |
•Understanding the relationship of kinetic conditions for natural gas hydrate formation is a challengeable issue among researchers.•Relationship of growth rate of methane hydrate with temperature and pressure using Artificial intelligence (AI) methods has been modeled.•Artificial neural network and adaptive neuro-fuzzy inference system as important sub-branches of AI methods had been utilized in the current paper.•Results show that ANIFS is a more potential tool in predication of kinetic conditions for natural gas hydrate formation than ANN.
This paper aims to present a kinetic study of formation of methane gas hydrate (GH) using artificial intelligence (AI) tools. Generally, study of the kinetics of GH formation will help to better understand this process in order to control it favorably. However, due to its complexity, this process is not fully understood yet. More studies in the literature are considering the thermodynamics of gas hydrate formation both experimentally and mathematically. However, there is no sufficient studies regarding the kinetics of gas hydrates and most of the experimental data and specifically the kinetic models in the literature are incomplete. That may be due to inherent stochastic behavior of GHs which makes it difficult to develop a deterministic model for it. Nowadays, Artificial Intelligence (AI) methods including Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) have been proved as a novel and potential tools with acceptable accuracy for modeling of engineering systems. Therefore, this paper aims to investigate the kinetics of gas hydrate formation using ANN and ANFIS when the relation between growth rate of methane hydrate, temperature and pressure has been modeled. Moreover, this can also be achieved using complicated governing equations but AI provides a less complex and easier way to accomplish this goal. Experimental data considering the methane hydrate growth rate as a function of pressure and temperature were used and ANFIS as well as ANN were employed to duplicate them. In this study, the results reveal that ANIFS could better predict the methane hydrate growth rate in the prevailing pressure and temperature conditions compared to ANN. Generally this study shows the effectiveness of AI based techniques for kinetics modeling of gas hydrates formation.
