Adaptive neuro-fuzzy approach for prediction of dewpoint pressure for gas condensate reservoirs

Abstract

Dewpoint pressure is an important parameter for reservoir management and characterization. Gas condensate reservoirs experience significant reduction in productivity when initial reservoir pressure decreases below the dewpoint pressure. As such, an effective and efficient methods for prediction of this thermodynamic quantity are crucial for operational plans. In this article, a hybrid artificial intelligence model, based on adaptive neuro-fuzzy approach, for the prediction of gas condensate dewpoint pressure is presented. The proposed model combines the learning ability of artificial neural network and the capability of rule-based fuzzy inference system. First, fuzzy subtractive clustering technique is applied to a set of measured input/output data to identify an initial system based on extracted set of rules. The generated system is then trained using adaptive neuro-fuzzy inference system after which model validation and testing were performed. The performance of the proposed model is compared with existing methods. The results show that our proposed model outperforms the previous and existing methods with 99% accuracy and with the least root mean square error of 2.188 for some selected fluid sample.