Recent advances in deep learning have expanded new possibilities for fluid flow simulation in petroleum reservoirs.However,the predominant approach in existing research is to train neural networks using high-fidelity ...Recent advances in deep learning have expanded new possibilities for fluid flow simulation in petroleum reservoirs.However,the predominant approach in existing research is to train neural networks using high-fidelity numerical simulation data.This presents a significant challenge because the sole source of authentic wellbore production data for training is sparse.In response to this challenge,this work introduces a novel architecture called physics-informed neural network based on domain decomposition(PINN-DD),aiming to effectively utilize the sparse production data of wells for reservoir simulation with large-scale systems.To harness the capabilities of physics-informed neural networks(PINNs)in handling small-scale spatial-temporal domain while addressing the challenges of large-scale systems with sparse labeled data,the computational domain is divided into two distinct sub-domains:the well-containing and the well-free sub-domain.Moreover,the two sub-domains and the interface are rigorously constrained by the governing equations,data matching,and boundary conditions.The accuracy of the proposed method is evaluated on two problems,and its performance is compared against state-of-the-art PINNs through numerical analysis as a benchmark.The results demonstrate the superiority of PINN-DD in handling large-scale reservoir simulation with limited data and show its potential to outperform conventional PINNs in such scenarios.展开更多
Direct numerical simulations（DNSs） of purely elastic turbulence in rectilinear shear flows in a three-dimensional（3D） parallel plate channel were carried out,by which numerical databases were established.Based on ...Direct numerical simulations（DNSs） of purely elastic turbulence in rectilinear shear flows in a three-dimensional（3D） parallel plate channel were carried out,by which numerical databases were established.Based on the numerical databases,the present paper analyzed the structural and statistical characteristics of the elastic turbulence including flow patterns,the wall effect on the turbulent kinetic energy spectrum,and the local relationship between the flow motion and the microstructures＇ behavior.Moreover,to address the underlying physical mechanism of elastic turbulence,its generation was presented in terms of the global energy budget.The results showed that the flow structures in elastic turbulence were 3D with spatial scales on the order of the geometrical characteristic length,and vortex tubes were more likely to be embedded in the regions where the polymers were strongly stretched.In addition,the patterns of microstructures＇ elongation behave like a filament.From the results of the turbulent kinetic energy budget,it was found that the continuous energy releasing from the polymers into the main flow was the main source of the generation and maintenance of the elastic turbulent status.展开更多
One of the key challenges in largescale network simulation is the huge computation demand in fine-grained traffic simulation.Apart from using high-performance computing facilities and parallelism techniques,an alterna...One of the key challenges in largescale network simulation is the huge computation demand in fine-grained traffic simulation.Apart from using high-performance computing facilities and parallelism techniques,an alternative is to replace the background traffic by simplified abstract models such as fluid flows.This paper suggests a hybrid modeling approach for background traffic,which combines ON/OFF model with TCP activities.The ON/OFF model is to characterize the application activities,and the ordinary differential equations(ODEs) based on fluid flows is to describe the TCP congestion avoidance functionality.The apparent merits of this approach are(1) to accurately capture the traffic self-similarity at source level,(2) properly reflect the network dynamics,and(3) efficiently decrease the computational complexity.The experimental results show that the approach perfectly makes a proper trade-off between accuracy and complexity in background traffic simulation.展开更多
基金funded by the National Natural Science Foundation of China(Grant No.52274048)Beijing Natural Science Foundation(Grant No.3222037)+1 种基金the CNPC 14th Five-Year Perspective Fundamental Research Project(Grant No.2021DJ2104)the Science Foundation of China University of Petroleum-Beijing(No.2462021YXZZ010).
文摘Recent advances in deep learning have expanded new possibilities for fluid flow simulation in petroleum reservoirs.However,the predominant approach in existing research is to train neural networks using high-fidelity numerical simulation data.This presents a significant challenge because the sole source of authentic wellbore production data for training is sparse.In response to this challenge,this work introduces a novel architecture called physics-informed neural network based on domain decomposition(PINN-DD),aiming to effectively utilize the sparse production data of wells for reservoir simulation with large-scale systems.To harness the capabilities of physics-informed neural networks(PINNs)in handling small-scale spatial-temporal domain while addressing the challenges of large-scale systems with sparse labeled data,the computational domain is divided into two distinct sub-domains:the well-containing and the well-free sub-domain.Moreover,the two sub-domains and the interface are rigorously constrained by the governing equations,data matching,and boundary conditions.The accuracy of the proposed method is evaluated on two problems,and its performance is compared against state-of-the-art PINNs through numerical analysis as a benchmark.The results demonstrate the superiority of PINN-DD in handling large-scale reservoir simulation with limited data and show its potential to outperform conventional PINNs in such scenarios.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.51276046 and 51506037)the Foundation for Innovative Research Groups of the National Natural Science Foundation of China(Grant No.51421063)+2 种基金the China Postdoctoral Science Foundation(Grant No.2016M591526)the Heilongjiang Postdoctoral Fund,China(Grant No.LBH-Z15063)the China Postdoctoral International Exchange Program
文摘Direct numerical simulations（DNSs） of purely elastic turbulence in rectilinear shear flows in a three-dimensional（3D） parallel plate channel were carried out,by which numerical databases were established.Based on the numerical databases,the present paper analyzed the structural and statistical characteristics of the elastic turbulence including flow patterns,the wall effect on the turbulent kinetic energy spectrum,and the local relationship between the flow motion and the microstructures＇ behavior.Moreover,to address the underlying physical mechanism of elastic turbulence,its generation was presented in terms of the global energy budget.The results showed that the flow structures in elastic turbulence were 3D with spatial scales on the order of the geometrical characteristic length,and vortex tubes were more likely to be embedded in the regions where the polymers were strongly stretched.In addition,the patterns of microstructures＇ elongation behave like a filament.From the results of the turbulent kinetic energy budget,it was found that the continuous energy releasing from the polymers into the main flow was the main source of the generation and maintenance of the elastic turbulent status.
基金supported by the Science and Technology Project of Zhejiang Province(No. 2014C01051)the National High Technology Development 863 Program of China( No.2015AA011901)
文摘One of the key challenges in largescale network simulation is the huge computation demand in fine-grained traffic simulation.Apart from using high-performance computing facilities and parallelism techniques,an alternative is to replace the background traffic by simplified abstract models such as fluid flows.This paper suggests a hybrid modeling approach for background traffic,which combines ON/OFF model with TCP activities.The ON/OFF model is to characterize the application activities,and the ordinary differential equations(ODEs) based on fluid flows is to describe the TCP congestion avoidance functionality.The apparent merits of this approach are(1) to accurately capture the traffic self-similarity at source level,(2) properly reflect the network dynamics,and(3) efficiently decrease the computational complexity.The experimental results show that the approach perfectly makes a proper trade-off between accuracy and complexity in background traffic simulation.
