A Novel Non-Iterative Method for the Prediction of the PVT Behavior of Reservoir Fluids

Abstract

Abstract This paper presents a novel approach for the prediction of the complete PVT behavior of reservoir oils and gas condensates. The method uses key measurements that can be performed rapidly either in the lab or at the well site as input to an Artificial Neural Network (ANN) architecture. The ANN architecture has been trained by a PVT studies database of over 650 reservoir fluids originating from all parts of the world. Tests of the trained ANN architecture utilizing a validation set of PVT studies indicate that, for all fluid types, most PVT property estimates can be obtained with a very low mean relative error of 0.5–2.5%, with no data set having a relative error in excess of 5%. This level of error is considered better than that provided by tuned Equation of State (EOS) models, which are currently in common use for the estimation of reservoir fluid properties. In addition to improved accuracy, the proposed ANN architecture avoids the ambiguity and numerical difficulties inherent to EOS models and provides for continuous improvements by the enrichment of the ANN training database with additional data. The developed model has been named PVT Expert*, and is shown to be a robust, accurate and quick prediction tool that can be used for estimating reservoir fluid properties over the entire range of operating conditions and fluid types. The main application of the model is envisaged to be the rapid generation of PVT data based on field generated measurements. The results show that these reports will be of comparable accuracy to a full PVT study generated in the laboratory. In addition to this, other applications are seen in providing accurate estimates of physical properties for use in well test validation and reservoir/production engineering calculations as well as providing for the quality assurance of laboratory generated fluid property data.