PVT properties prediction using hybrid genetic-neuro-fuzzy systems

Pressure-volume-temperature (PVT) properties are very important in reservoir engineering computations. There are many approaches for predicting various PVT properties based on empirical correlations, statistical regression and artificial neural networks (ANNs). Unfortunately, the developed correlations are often limited and global correlations are usually less accurate compared to local correlations. In this paper, a genetic-neuro-fuzzy inference system (GANFIS) is proposed for crude oil PVT properties prediction. Simulation experiments show that the proposed technique outperforms up-to-date methods.