Comparative analysis of hydrate formation pressure applying cubic Equations of State (EoS), Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS)

Authors : Nassim Zeinali, Azadeh Ameri, Mohammad Saber

Pages : 91-101

View : 9 | Download : 4

Publication Date : 2012-05-17

Article Type : Other

Abstract :Normal 0 false false false EN-US X-NONE AR-SA /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Table Normal"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-qformat:yes; mso-style-parent:""; mso-padding-alt:0cm 5.4pt 0cm 5.4pt; mso-para-margin-top:0cm; mso-para-margin-right:0cm; mso-para-margin-bottom:10.0pt; mso-para-margin-left:0cm; line-height:115%; mso-pagination:widow-orphan; font-size:11.0pt; font-family:"Calibri","sans-serif"; mso-ascii-font-family:Calibri; mso-ascii-theme-font:minor-latin; mso-fareast-font-family:"Times New Roman"; mso-fareast-theme-font:minor-fareast; mso-hansi-font-family:Calibri; mso-hansi-theme-font:minor-latin;} The objective of this work is making comparison between thermodynamic models and data-driven techniques accuracy in prediction of hydrate formation pressure as a function of temperature and composition of gas mixtures. T he Peng-Rabinson (PR) and Patel-Teja (PT) equations of state are used for thermodynamic modeling and Artificial Neural Networks (ANNs) and Adaptive Neuro-Fuzzy Inference System (ANFIS) are used as data-driven models. The capability of each method is evaluated by comparison with the experimental data collected from literature. It is shown that there is a good agreement between thermodynamic modeling and the experimental data in most of the cases; however, the prediction relative errors are more than 10% in some cases. The data-driven models are trained and tested using a set of experimental data and their optimum structures are selected based on the prediction error of the test data set. The accuracy of ANN for prediction of hydrate formation pressure is slightly better than those of PR and PT. The prediction errors of ANFIS for all cases are less than 1% which is very promising and proves the potential of ANFIS as a capable tool for prediction of the hydrate formation pressure.
Keywords : Thermodynamics