Application of Artificial Neural Network in Prediction of Methane Gas Hydrate Formation Rate

This work aims to use Artificial Neural Network (ANN) in prediction of methane gas hydrate formation. There are a lot of thermodynamic modelling have been developed and applied in prediction of the formation gas hydrate however there is still none yet proven model that can predict the formation rate of methane gas hydrate. This study emerges as to build a kinetic model consume time and are very complex due to stochastic behavior of gas hydrate. Therefore, ANN methods show the best potential technology to be used for development of model to predict the formation rate of gas hydrate. The aims of this study are to develop artificial kinetic models by using ANN that can predict the growth rate of formation of methane gas hydrate. To determine the best configuration to be used in ANN involving the number of layers and number of hidden neurons to be used in ANN models. In this study, pressure and temperature are used as the model’s input with the growth rate of methane gas hydrate as the model’s output. The result shows every ANN model has different best configuration in prediction of methane gas hydrate. From the study also few limitation of ANN also addressed