Accurate prediction of sour gas hydrate equilibrium dissociation conditions by using an adaptive neuro fuzzy inference system

An adaptive neuro fuzzy inference system (ANFIS) has been proposed for predicting the sour gas hydrate equilibrium dissociation conditions. The proposed model predictions have been compared with those of the available thermodynamic models at different operating conditions. It is found that at all H2S concentrations especially at the concentrations higher than 10 mol%, the developed ANFIS model outperforms the existing thermodynamic models with the average absolute deviation of 2.18%. The proposed ANFIS model can be used for accurate and reliable predictions of sour gas hydrate equilibrium conditions over wide ranges of temperatures and acid gas concentrations and is a useful tool for proper design of sour natural gas flow assurance systems and gas hydrate energy storage processes in oil and gas industries.

► An ANFIS model is developed for predicting sour gas hydrate dissociation conditions.
► It can be used over wide ranges of operating conditions.
► At all H2S concentrations, the developed model outperforms the thermodynamic models.
► The presented model is useful for design of industrial sour gas handling systems.