Hydrate Risk Management and Evaluation for Gas-Dominated Systems Using Machine Learning

Advancements in oil and gas production have led to the exploration and production of hydrocarbons in unstable regions including offshore (deep & ultra-deep) reservoirs. As production increases, flow assurance continues to be a prevalent problem in wells and flowlines. It is necessary to develop flow assurance analysis models for hydrate formation in gas pipelines. Analyses have shown the difference in thermodynamic and kinetic behaviors in the different hydrate phase systems (water, gas, oil). This study presents a data-driven gas hydrate diagnosis model for monitoring and risk evaluation in gas pipelines by performing, hydrate growth rate diagnosis for flow assurance in gas-dominated flow systems. Data used for learning was obtained from hydrate flow loop experiments performed under controlled gas-dominated flow conditions where thermodynamic conditions were obtained at each time step. Regression Algorithms were applied to develop a fit for a model to predict the hydrate risk level given thermodynamic conditions alongside the flow rate. The developed hydrate model was also applied to study the performance in flow operations. The ridge regression model showed the best performance among the models with a root mean squared error of 0.1682 and a correlation coefficient of 0.9595. The results obtained showed that the model can be deployed for use in a hydrate risk analysis endeavor, and the algorithm used in development can be further improved.