检索结果-南通市图书馆

Prediction of porous media Fluid flow with Spatial Heterogeneity Using Criss-Cross Physics-Informed Convolutional Neural Networks

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第2期138卷 1323-1340页

作者： Jiangxia Han Liang Xue Ying Jia Mpoki Sam Mwasamwasa Felix Nanguka Charles Sangweni Hailong Liu Qian Li State Key Laboratory of Petroleum Resources and Prospecting China University of PetroleumBeijing102249China Department of Oil-Gas Field Development Engineering College of Petroleum EngineeringChina University of PetroleumBeijing102249China Exploration Production Research Institute SinopecBeijing102249China Ministry of Energy Tanzania Petroleum Development CorporationTowerDar es Salaam2774Tanzania Ministry of Energy Building Petroleum Upstream Regulatory Authority in Tanzania(PURA)Dar es Salaam11439Tanzania

Recent advances in deep neural networks have shed new light on physics,engineering,and scientific *** the data-centered viewpoint with physical simulation is one of the research *** physicsinformedneural network(PINN)is currently the most general framework,which is more popular due to theconvenience of constructing NNs and excellent generalization *** automatic differentiation(AD)-basedPINN model is suitable for the homogeneous scientific problem;however,it is unclear how AD can enforce fluxcontinuity across boundaries between cells of different properties where spatial heterogeneity is represented bygrid cells with different physical *** this work,we propose a criss-cross physics-informed convolutionalneural network(CC-PINN)learning architecture,aiming to learn the solution of parametric PDEs with spatialheterogeneity of physical *** achieve the seamless enforcement of flux continuity and integration ofphysicalmeaning into CNN,a predefined 2D convolutional layer is proposed to accurately express transmissibilitybetween adjacent *** efficacy of the proposedmethodwas evaluated through predictions of several petroleumreservoir problems with spatial heterogeneity and compared against state-of-the-art(PINN)through numericalanalysis as a benchmark,which demonstrated the superiority of the proposed method over the PINN.

关键词： Physical-informed neural networks(PINN) flow in porous media convolutional neural networks spatial heterogeneity machine learning

Ethoxylated molybdenum disulphide based nanofluid for enhanced oil recovery

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Petroleum Science 2024年第5期21卷 3417-3427页

作者： Infant Raj Zhuo Lu Ji-Rui Hou Yu-Chen Wen Li-Xiao Xiao Unconventional Petroleum Research Institute China University of Petroleum(Beijing)Beijing102249China

Despite advances in renewable energy sources, the world's current infrastructure and consumption patterns still heavily depend on crude oil. Enhanced oil recovery(EOR) is a crucial method for significantly increasing the amount of crude oil extracted from mature and declining oil fields. Nanomaterials have shown great potential in improving EOR methods due to their unique properties, such as high surface area, tunable surface chemistry, and the ability to interact at the molecular level with fluids and rock surfaces. This study examines the potential use of incorporating ethoxylated molybdenum disulfide with a unique three-dimensional flower-like morphology for overcoming the challenges associated with oil recovery from reservoirs characterized by complex pore structures and low permeability. The synthesized nanomaterial features a chemical composition that encompasses a polar ethoxy group linking molybdenum disulfide nanosheets and an alkylamine chain. The ethoxy group promotes interactions with water molecules through hydrogen bonding and electrostatic forces, disrupting the cohesive forces among water molecules and reduction surface tension at the oil-water interface. As a result, the nanomaterial achieves an ultra-low interfacial tension of 10^(-3) mN/m. Core flooding experiments demonstrate a significant oil recovery of approximately 70% at a concentration as low as 50 ppm. This research paves the way for the design and synthesis of advanced extended surfactant-like nanomaterials,offering a promising avenue for enhancing oil recovery efficiency.

关键词： Molybdenum disulfide Nanofluid flow in porous media Core flooding Interfacial tension

Prediction of Low-Permeability Reservoirs Performances Using Long and Short-Term Memory Machine Learning

在线全文

学校读者我要写书评

暂无评论

Fluid Dynamics & Materials Processing 2022年第5期18卷 1521-1528页

作者： Guowei Zhu Kangliang Guo Haoran Yang Xinchen Gao Shuangshuang Zhang School of Geosciences Yangtze UniversityWuhan430100China

In order to overcome the typical limitations of numerical simulation methods used to estimate the production of low-permeability reservoirs,in this study,a new data-driven approach is proposed for the case of water-driven hypo-permeable *** particular,given the bottlenecks of traditional recurrent neural networks in handling time series data,a neural network with long and short-term memory is used for such a *** method can reduce the time required to solve a large number of partial differential *** such,it can therefore significantly improve the efficiency in predicting the needed production *** examples about water-driven hypotonic reservoirs are provided to demonstrate the correctness of the method and its ability to meet the requirements for practical reservoir applications.

关键词： Water flooding flow in porous media data-driven LSTM CFD

NUMERICAL SIMULATION FOR A PROCESS ANALYSIS OF A COKE OVEN

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Particuology 2005年第6期3卷 373-378页

作者： Zhancheng Guo Huiqing Tang Institute of Process Engineering Chinese Academy of Sciences Beijing 100080 P.R. China

A computational fluid dynamic model is established for a coking process analysis of a coke oven using PHOENICS CFD package. The model simultaneously calculates the transient composition, temperatures of the gas and the solid phases, velocity of the gas phase and porosity and density of the semi-coke phase. Numerical simulation is illustrated in predicting the evolution of volatile gases, gas flow paths, profiles of density, porosity of the coke oven charge, profiles of temperatures of the coke oven gas and the semi-coke bed. On the basis of above modeling, the flow of coke oven gas （COG） blown from the bottom of the coke oven into the porous semi-coke bed is simulated to reveal whether or not and when the blown COG can uniformly flow through the porous semi-coke bed for the purpose of desulfurizing the semi-coke by recycling the COG. The simulation results show that the blown COG can uniformly flow through the semi-coke bed only after the temDerature at the center of the semi-coke bed has risen to above 900℃.

关键词： coal carbonization flow in porous media desulfurization of coke

Simulation of flow through porous anode in MFC at higher power density

在线全文

学校读者我要写书评

暂无评论

Theoretical & Applied Mechanics Letters 2012年第2期2卷 49-53页

作者： Weiwei Su Weiwei Yan Zhongdi Su Yang Liu Yousheng Xu Department of Physics Zhejiang Normal UniversityJinhua 321003China College of Metrology&Measurement Engineering China Jiliang UniversityHangzhou 310018China Department of Mechanical Engineering The Hong Kong Polytechnic UniversityKowloonHong KongChina

Microbial fuel cell （MFC） is a novel environmental friendly energy device which has received great attention due to its technology for producing electricity directly fi-om organic or inorganic matter by using bacteria as catalyst. To date, many experiments have been carried out to achieve the maximum power output with advective flow through porous anode to the cathode in the MFC. However, the precise mechanical mechanism of flow through anode and the quantified relationship between electrode spacing and MFC performance are not yet clearly understood. It hasbeen found experimentally that the power output can be increased apparently at certain electrode spacing configuration. Based on these available experimental data, this paper investigates the effect of spacing between electrodes, the Darcy number of porous anode and the Reynolds number on the power production performance of MFC by using lattice Boltzmann method. The numerical simulation results present that the distance between electrodes significantly influences the flow velocity and residence time of the organic matter attached to the anode in the MFC. Moreover, it is found that the Darey number of porous anode and the Reynolds number can regulate the output efficiency of MFC. These results perform better understanding of the complex phenomena of MFC and will be helpful to optimize MFC design.

关键词： microbial fuel cell lattice Boltzmann method flow in porous media