Prediction of methane hydrate formation pressure: learning data under conditions of different temperature and salinity

Artificial Neural Network (ANN) and Bayesian Belief Network (BBN) were used in this study such as an artificial intelligence modelling tools to investigate the different variables (pressure,temperateure and solinity)on methane hydrate formation. The predicted results of methane hydrate formation condition from ANN model was also compared with the result of BBN mo el.By comparing average coefficient of determination (r2)regression coefficient (r) and mean square error (MSE) values of the ANN models and BBN model, one can conclude that ANN predicted methane hydrate formation condition better than the other.

Keywords:

methane hydrate , phase equilibria with inhibitors , salinity , artificial neural network , bayesian belief network