Application of Adaptive Neuro Fuzzy Inference System to Predict Desalination Efficiency of Produced Water using Gas Hydrate

فاقد چكيده فارسي

Hydrate-based desalination treatment process has been introduced as a new method in recent years. In this study, adaptive neuro fuzzy inference system (ANFIS) has been successfully developed to predict desalination efficiency of produced water using gas hydrate by considering initial salinity of produced water and gas equilibrium pressure as input parameters. The experimental data measured in a custom built set-up, have been divided into training and testing subsets. The training set has been applied to predict model coefficients and the testing subset has been used for model validation. After developing ANFIS structure, the capability and accuracy of the proposed neuro fuzzy model has been evaluated by comparison of model predictions with experimental data and calculation of statistical parameters such as coefficient of determination (R2) and root mean square error (RMSE). The RMSE of ANFIS model in prediction of desalination efficincy of produced water is 0.5198, with a high R2 of 0.9943, which indicate a satisfactory degree of accuracy for the developed model.