|Theme||Visible||Selectable||Appearance||Zoom Range (now: 0)|
In the realm of reservoir engineering, we are categorized to be in the
We use the classical problem of drainage of gas into a water-filled porous medium to test our implementation. The analytical solutions obtained using the method of characteristics are compared with solutions obtained using the
Several cases are presented that highlight the importance of the coupling between observed data and physics-informed neural networks for different parameter space. The cases demonstrate the capability of PINNs to augment data-driven solutions. Our results indicate that PINNs are capable of capturing the overall trend of the solution even without observed data but the resolution and accuracy of the solution are improved tremendously once the augmentation of data and physics is implemented. Even with a large mobility ratio, the predicted solution of the PINNs seems promising. The results in our paper indicate that such methods can be utilized to train models that could be used estimate a well-informed initial guess in a reservoir simulator because they capture the overall behavior but miss the intricate details that could be circumvented with conventional reservoir simulation.
The work presented in the paper demonstrates the importance and the capability of applying machine learning approaches in reservoir engineering problems. Additionally, it gives a forward-looking approach for the future of reservoir simulation techniques that could augment data with the physics.
An increasing interest in gas hydrates as a potential energy source gave reason for numerous field studies, laboratory and numerical experiments, that have revealed some interesting aspects of sediments containing gas hydrates. While there exist several models explaining observed increased seismic velocities, the mechanism of formation of gas hydrates and the reasons for observed strong attenuation are not fully understood. Two rock physical models are controversly debated: one attributes occurrence of hydrates to the properties of the rock's matrix, the other relates presence of hydrates to the properties of the pore fluid. In our approach we assume, that an occurrence of hydrates affects the properties of the fluid and the solid phase of the host sediment. A poroelastic generalization of the O'Doherty-Anstey theory indicates that this would result in increased values for attenuation. To work with realistic models of multilayered, poroelastic media and to account for observed strong fluctuations in hydrate-bearing sedimentary layers we investigate exponentially correlated, random media. Numerical and analytical results confirm, that correlated fluctuations in properties of the frame, grain and fluid cause significant attenuation values. Especially in the lower seismic frequency range they are comparable to those observed in field measurements.
The fluid transfer parameters between matrix and fracture are not well known. Consequently, simulation of fractured reservoirs uses, in general, very crude and unproved hypothesis such as zero capillary pressure in the fracture and/or relative permeability functions that are linear with saturation. In order to improve the understanding of flow in fractured media, an experimental study was conducted and numerical simulation used to interpret experimental results. A laboratory flow apparatus was built to obtain data on water-air imbibition and oil-water drainage displacements in fractured sandstone systems. During the experiments, porosity and saturation were measured along the core utilizing a Computerized Tomography (CT) scanner. Saturation images were reconstructed in 3-D to observe how matrix-fracture interaction occurred. Differences in fluid saturations and relative permeabilities caused by changes of fracture width have also been analyzed. In the case of water-air imbibition, fracture systems with narrower fracture apertures showed more stable fronts and slower water breakthrough than the wide fracture systems. However, the final water saturation was higher in wide fracture systems, thus showing that capillary pressure in the narrow fracture has more effect on fluid distribution in the matrix. During oil-water drainage, oil saturations were higher in the blocks near the thin fracture, again showing the effect of fracture capillary pressure. Oil fingering was observed in the wide fracture. Fine-grid simulations of the experiments using a commercial reservoir simulator were performed. Relative permeability and capillary pressure curves were obtained by history matching the experiments. The results showed that the assumption of fracture relative permeability equal to phase saturation is incorrect. We found that both capillary and viscous forces affect the process. The matrix capillary pressure obtained by matching an experiment showed lower values than reported in the literature.
Multiphase flowrate measurements play an important role during the reservoir characterization and production optimization phase of reservoir management. Accurate multiphase flow rate measurement is an indispensable tool for production optimization from oil and gas fields. One of the industry's accepted solutions is the use of multiphase flow meters, which are expensive, have a limited operational envelope, and are exposed to erosion and failures. This can limit the applicability of physical metering devices due to frequent calibration, transportation issues, space, safety, security, and possible high costs.
Virtual flow metering (VFM) is a method for estimating oil, gas and water flowrates produced from wells without measuring them directly. The method uses data available from the field, such as downhole pressure and temperature measurements as well as a choke position and ESP operational parameters, to estimate the flowrates by implementing hydrodynamic multiphase models, measurement data, and a reconciliation algorithm. In this paper, an overview of the conventional multiphase flow metering solutions is presented, which is followed by application of some advanced artificial intelligence and data analytics techniques for a specific case of multiphase production monitoring in a highly dynamic wellbore.
The considered case refers to a typical scenario, where the measurements of oil, gas, and water flow rates are obtained in real time using a topside multiphase flow meter. Alternatively, the values of these multiphase rates are estimated using a data-driven dynamic flow model obtained using a dynamic mode decomposition technique. The results obtained with this method are compared with another VFM approach, where the rates are obtained using deep LSTM neural network.
Chen, Xuehua (Chengdu University of Technology) | Li, Yijia (Chengdu University of Technology) | Xu, Di (Chengdu University of Technology) | Li, Bin (Chengdu University of Technology) | He, Xilei (Chengdu University of Technology) | He, Zhenhua (Chengdu University of Technology) | Zou, Wen (Chuangqing Drilling Engineering Co. Ltd.)
The fluid content and saturation in porous media can cause the anomalous attenuation and contribute to the frequency-dependent reflections of compressional wave in seismic frequency range. We present a method and workflow to numerically simulate the frequency-dependent attenuation and the corresponding seismic reflection behavior by taking into account the comprehensive effects of the multi-phase fluid on the wave-induced fluid flow in porous reservoir. The numerical results indicate that the frequency-dependent attenuation of compressional wave and seismic reflection signatures show significant dependence on hydrocarbon saturation, both in terms of the amplitudes as well as with regard to the traveltime of the reflection from the bottom of the saturated reservoirs and the underlying layers.