Laboratory experiment ideally, is the main method to obtain PVT properties of the oil and gas reservoir fluids. The alternative two methods widely used when laboratory experiments are not available are: equation of state (EOS) and empirical PVT correlations. The EOS requires lots of numerical computations based on identifying the full compositions of the reservoir fluids properties. The measurement and calculation of these properties are very expensive and time consuming. On the other hand, using of PVT correlations which are based on easily measured field data such as reservoir pressure and temperature, and gas and oil density is reliable and more economic. In this work, three artificial intelligence (AI) technique models were developed to predict the oil-gas ratio (R v ) for volatile oil and gas condensate reservoirs. Thirteen actual reservoir fluid samples (five volatile oils and eight gas condensates) covering a wide range of fluid behavior and characteristics were used. Whitson and Torp three parameters EOS were used to generate modified black oil (MBO) PVT properties that were used as a data set for model development. The MBO PVT data points were extracted for each sample using commercial PVT software at five different separator conditions. The nature of the input data was studied showing that data type is clustered. In addition, the correlations between the input parameters were checked. This preprocessed is helpful in selecting the best method to deal with the input parameters that will be fed to the developed models. According to this analysis and since the input parameters have different ranges, normalization of these parameters is vital to improve the accuracy of the models and to get the solution quickly and efficiently. Results showed that taking the log for the input parameters is the best among the other normalization techniques. The AI techniques that have been implemented in this research are; Artificial Neural Network (ANN) models, Functional Networks (FNs) and Support Vector Machines (SVMs). Models developed based on these techniques used 17,941 data points and a ratio of 70% for training, 15% for validation, and 15% for testing. To develop these models, three Matlab codes were written for each tool where the provided input data in excel format were read and prepressed before implementation. Results obtained using these techniques showed that the ANN model predicted R v with an average square correlation coefficient of 0.9999 and an average relative error of 0.15% while FNs predicted R v with an average correlation coefficient of 0.9635 and an average relative error of 27.6%. It was noted that SVMs gave the best results with an average correlation coefficient of 0.9990 and an average relative error of 0.12%. The results concluded that ANN and SVM accurately predicted such data since this type of data are clustered and these two models can handle this kind of data. The newly developed models depend only on easily obtainable parameters in the field and can have varied applications when t...
Polymer injection is one of the most applications used in enhanced oil recovery. In order to achieve better sweeping efficiency, polymer is added to the injected water to increase its viscosity and ultimately minimize the viscous fingering. Partially hydrolyzed polyacrylamide (HPAM) is one of the polyacrylamide groups. It is characterized by the shape of straight chain polymer of acrylamide monomers in which some of it has been hydrolyzed. The viscosity of the polymer solution should be maintained in order to keep better sweep efficiency. Salinity, polymer concentration and temperature are the most important factors that strongly affect the polymer viscosity and behavior. The aim objective of this study is to estimate the optimum polymer concentration based on the suitable polymer solution viscosity. This viscosity will be suitable for preferable mobility ratio. In this work, five groups of polymer solutions were prepared with different salinities. In each group, several polymer solutions were prepared at different polymer concentration. The viscosity of prepared solutions was measured at different temperatures. New models correlate the flow behavior index (n) and flow consistency index (k) with polymer salinity, polymer concentration and temperature were developed and validated using the experimental data. In order to estimate the required optimum polymer concentration, the developed models were combined with other developed models that describe the polymer shear rate in porous media. Results show that, the cross plots of the measured and corresponded calculated (n) and (k) values indicated better prediction compared with the latest published correlations with a squared correlation coefficient of 0.9912 and 0.9962 respectively. In addition, the calculated average relative error of the predicted (n) and (k) were 0.97 % and 6.07% correspondingly. Using these models, the power law viscosity equation and shear rate in porous media equation, the required polymer concentration can be estimated with high accuracy. Consequently the required optimum polymer concentration needed to achieve better sweeping efficiency can be determined and therefore enhance the oil recovery. This technique will save time and effort spent to find the optimum polymer concentration using the traditional methods.
Understanding the formation behavior and the drilling operation is essential to optimize the performance of drilling systems. Several studies were conducted to improve the drilling operation in real time basis utilizing different approaches. Numerous mathematical models (analytical or empirical) were developed to relate the drilling parameters with the rate of penetrations and to predict the drilling efficiency. However, these models are arrived at by ignoring some parameters or employing simplifying assumption(s), which may lead to over or under optimistic drilling performance. The main objective of this research is to investigate the analytical and numerical approaches to calculate the torque and drag in drilling operations and produce a simple and robust model using artificial intelligent techniques. More than 22,000 data point from several wells for depth up to 18,000 ft. was used to develop and validate the model reliability. The full profiles of torque and rate of penetrations was determined, also the required energy for drilling each section has been estimated. The developed model could be utilized to define the optimum range for torque, which leads consequently to generate an efficient drilling system and reduce the drilling cost. In this study, rate of penetration (ROP) was determined using the torque profile and mechanical specific energy (MSE) based on real time and rig-site data. Statistical analysis was conducted to understand the importance of drilling parameters on the variations of torque and rate of penetration. Drilling parameters such as weight on bit (WOB), revolution per minute (RPM), fluid circulation rate (Q), and bit hydraulic horse power (HPb) has been studied. Thereafter, artificial neural network (ANN) model was developed to predict the torque and ROP profiles. The suggested models enable the drilling engineers to optimize the drilling parameters in a real-time manner, by changing the surface and controllable parameters in such a way that maintains the drilling operations within the optimum conditions. This research will assist in improving the operations efficiency through optimizing the drilling parameters. A strong robust model was developed which yields high accuracy results when compared with actual field measurements, average absolute percentage error of less than 6.5% was achieved.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations鈥揷itations 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 漏 2024 scite LLC. All rights reserved.
Made with 馃挋 for researchers
Part of the Research Solutions Family.