Abstract
Optimization and monitoring schemes for oil well and reservoir system require accurate estimation of production rate. Real-time monitoring is conducted typically using flow transmitters that contain their own inherent uncertainties due to flow of multiple fluids. Because of these limitations, industrial practices involve the usage of wellhead conditions and intermittent well test data to estimate well flow rates through certain established correlations such as Gilbert's empirical model. These correlations, however, have become ineffective due to inadequate well test data and associated operational and cost-intensive commitments. The main objective of this work was to utilize artificial intelligence (AI) techniques to develop robust correlation to predict oil rates in gas-lift wells. The AI techniques implemented in this study are artificial neural network (ANN), artificial neuro-fuzzy inference systems, support vector machines, and functional networks. In addition, ANN was used to develop physical equation to predict oil flow rate. Separator test dataset from multiple wells of an oil field operating on continuous gas lift was collected. Extensive data analytics were performed before feeding it in the algorithms. The inputs consisted of only the easily available surface parameters. All the developed AI models were compared among themselves as well as with conventionally used empirical models. The comparison was conducted based on average absolute error percentage and coefficient of determination. The newly developed AI model can predict oil rates with accuracy exceeding 98% that is extremely efficient, and examples of such results have not been reported previously.