Using Artificial Neural Networks to Develop New PVT Correlations for Saudi Crude Oils

Abstract

Abstract Reservoir fluid properties data are very important in reservoir engineering computations such as material balance calculations, well testing, reserve estimates, and numerical reservoir simulations. Ideally, those data should be obtained experimentally. On some occasions, these data are not either available or reliable; then, empirically derived correlations are used to predict PVT properties. However, the success of such correlations in prediction depends mainly on the range of data at which they were originally developed. These correlations were developed using linear, non-linear, multiple regression or graphical techniques. Recently, researchers utilized artificial neural networks (ANN) to develop more accurate PVT correlations. ANNs are biologically inspired non-algorithmic, non-digital, massively parallel distributive and adaptive information processing systems. They resemble the brain in acquiring knowledge through learning process, and storing knowledge in interneuron connection strengths. The present study presents new models developed to predict the bubble point pressure and, the formation volume factor at the bubble point pressure. The models were developed using 283 data sets collected from Saudi reservoirs. These data were divided into three groups: the first was used to train the ANN models, the second was used to crossvalidate the relationships established during the training process and, the last was used to test the models to evaluate their accuracy and trend stability. Trend tests were performed to ensure that the developed model would follow the physical laws. Results show that the developed models outperform the published correlations in terms of absolute average percent relative error, and standard deviation. Introduction PVT properties are very important in almost all reservoir engineering computations. These include material balance calculations, well testing, reserve estimates, and numerical reservoir simulations. Ideally, those data should be obtained from laboratory studies on bottom-hole collected samples. However, in some instances, these data are either not available or reliable; then, empirically derived correlations are used to predict PVT properties. There are many empirical correlations for predicting different PVT properties, they were developed using linear or non-linear multiple regression or graphical techniques. Recently, researchers utilized artificial neural networks (ANN) to develop more accurate PVT correlations. The developed correlations have some limitations as they were originally developed for certain range of reservoir fluid characteristics and geographical area with similar fluid compositions. Thus, the accuracy of such correlations is critical and local correlations are found to be more accurate when compared to global correlations. Bubble point pressure (Pb) and Bubble point Oil Formation Volume Factor (Bob), are very important PVT properties. Bubble point pressure is defined as the pressure at which the first gas bubble evolves from liquid phase, thus differentiating between single and multi-phase state of reservoir fluids. Also, Bob is defined as the volume of reservoir oil that would be occupied by one stock tank barrel oil plus any dissolved gas at the bubble point pressure and reservoir temperature. Precise prediction of Pb and Bob is very important in reservoir and production computations. The objective of this study is to develop new predictive models for Pb and Bob based on Artificial Neural Networks (ANN) using field data collected from Saudi reservoirs. ANNs are biologically inspired non-algorithmic, nondigital, massively parallel distributive and adaptive information processing systems. They resemble the brain in acquiring knowledge through learning process, and storing knowledge in inter-neuron connection strengths.