No abstract

No abstract

No abstract

In recent years, formation of gas hydrate has been considered as a suitable method for brine water desalination. In this study, for saline produced water treatment, design of experiment with two factors, the type of gas and electrical conductivity of initial brine solution (EC0) as a measure of salinity, were applied and removal efficiencies were analyzed. For this purpose, two different hydrate formers, CO2 and natural gas (NG) were separately mixed with different produced water samples. The hydrate formation reactions were carried out at 274.2 K in 35 and 95 bar, respectively, and removal efficiencies of produced water samples were tested. It has been found that with a three-stage hydrate process, 86% of dissolved minerals can be removed by the desalination process using CO2 hydrate formation gas while this amount will be 82% when NG is applied as hydrate former. Analysis of experiments indicated that the desalting efficiency depends on the hydrate-forming gas (CO2 > NG) as well as the amount of EC0 (high EC0 > low EC0).

In this study, two artificial intelligence models based on an adaptive neuro-fuzzy inference system (ANFIS) and a support vector machine (SVM) technique have been successfully developed to predict the desalination efficiency of produced water through a hydrate-based desalination treatment process. A genetic algorithm as an evolutionary optimization method has been used to determine the optimal values of SVM model coefficients. To this end, compressed natural gas and CO2 hydrate formation experiments were carried out, and the desalination efficiency of produced water was measured and utilized for model training and validation. After model development, graphical and statistical analysis approaches have been applied to evaluate the performance of suggested models by a comparison of model predictions with measured experimental data. For the ANFIS model, the coefficient of determination (R2) and average absolute relative error (AARE) are 0.9927 and 0.58%, respectively. The values of AARE and R2 for the SVM model are obtained 0.35% and 0.9985, respectively. These statistical criteria confirm excellent accuracy and robustness of intelligent models in predicting the desalination efficiency of produced water through the hydrate-based desalination treatment process. Furthermore, the Leverage statistical technique has been carried out to define the outliers. The obtained results demonstrate that all experimental data are reliable and both ANFIS and SVM models are statistically valid.