This paper proposes and implements a new approach for predicting Pressure -Volume-Temperature (PVT) properties of crude oils. Instead of the usual single or multi-data point prediction for any crude oil PVT property that is described by a curve, the approach in this study predicts such a property over a specified range of required reservoir pressures. Moreover, the shapes of the predicted curves are smooth and consistent with the experimental curves. Prediction models based on Artificial Neural Networks (ANN) and two of its advances; Support Vector Regression (SVR) and Functional Networks (FN), have been developed to execute the formulated approach. The approach has been demonstrated for viscosity and solution gas/oil ratio (GOR) curves. These two properties vary with reservoir pressures and they are often required to be estimated over a specified range of pressures. In this study, three different data sets have been used. The first Data set consists of 12 variables which are the predictors, including crude oil hydrocarbon and non-hydrocarbon compositions and some reservoir properties. The other two data sets consist of laboratory viscosity-pressure measurements and laboratory gas/oil ratio-pressure measurements for plotting the viscosity and solution GOR curves respectively. In the simulation results, SVR and FN give better performances than the conventional ANN technique. Graphical plots and two common statistical measures (root mean square error, RMSE, and absolute percent relative error, AAPRE) have been used to evaluate the performances of all the developed models. Introduction In petroleum engineering, characterization of reservoir fluids plays an important role of developing strategies for operating and managing existing reservoirs and development of new ones. These reservoir fluid properties are important in petroleum engineering computations for: simulating reservoirs, evaluating reserves, forecasting production, designing production facilities and transportation systems. Crude oil viscosity and GOR are two of these important PVT properties which are required to be calculated or estimated at different stages of crude oil exploration. These properties are traditionally determined from laboratory analyses on samples collected from the bottom of the wellbore or after recombining the liquid and vapour samples collected from the separator at the surface. To solve the problem of going through the rigorous laboratory experimentations which consume valuable production resources: time and money, equations of states (EOS) and empirically derived correlations have been used to predict these reservoir fluid properties. The two methods were used for a long period of time until Soft Computing (SC) techniques were introduced to improve the prediction performances. The mostly used SC technique in solving Petroleum Engineering is ANN. Although SC techniques have not being widely-utilised in the Petroleum Industries compared with some other fields, they have been applied successfully in some Petroleum Engineering problems with exceptional and acceptable performances. A review of applications of some of these intelligent systems and their potentials in oil and gas industry can be found in (Mohaghegh 2005). In this study, we introduce a new approach for predicting any PVT property that can be represented as a curve. All predictions have been done using ANN as well as two of its advanced algorithms: SVR and FN.
This paper develops ensemble machine learning model for the prediction of dead oil, saturated and undersaturated viscosities. Easily acquired field data have been used as the input parameters for the machine learning process. Different functional forms for each property have been considered in the simulation. Prediction performance of the ensemble model is better than the compared commonly used correlations based on the error statistical analysis. This work also gives insight into the reliability and performance of different functional forms that have been used in the literature to formulate these viscosities. As the improved predictions of viscosity are always craved for, the developed ensemble support vector regression models could potentially replace the empirical correlation for viscosity prediction.
In oil and gas industry, prior prediction of certain properties is needed ahead of exploration and facility design. Viscosity and gas/oil ratio (GOR) are among those properties described through curves with their values varying over a specific range of reservoir pressures. However, the usual single point prediction approach could result into curves that are inconsistent, exhibiting scattered behavior as compared to the real curves. Support Vector Regressors and Functional Networks are explored in this paper to solve this problem. Inputs into the developed models include hydrocarbon and non-hydrocarbon crude oil compositions and other strongly correlating reservoir parameters. Graphical plots and statistical error measures, including root mean square error and average absolute percent relative error, have been used to evaluate the performance of the models. A comparative study is performed between the two techniques and with the conventional feed forward artificial neural networks. Most importantly, the predicted curves are consistent with the shapes of the physical curves of the mentioned oil properties, preserving the need of such curves for interpolation and ensuring conformity of the predicted curves with the conventional properties.
In reservoir engineering, there is always a need to estimate crude oil Pressure, Volume and Temperature (PVT) properties for many critical calculations and decisions such as reserve estimate, material balance design and oil recovery strategy, among others. Empirical correlation are often used instead of costly laboratory experiments to estimate these properties. However, these correlations do not always give sufficient accuracy. This paper develops ensemble support vector regression and ensemble regression tree models to predict two important crude oil PVT properties: bubblepoint pressure and oil formation volume factor at bubblepoint. The developed ensemble models are compared with standalone support vector machine (SVM) and regression tree models, and commonly used empirical correlations .The ensemble models give better accuracy when compared to correlations from the literature and more consistent results than the standalone SVM and regression tree models.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.