Special Issue "Numerical Fluid Flow Simulation Using Artificial Intelligence and Machine Learning"

A special issue of Fluids (ISSN 2311-5521).

Deadline for manuscript submissions: closed (30 April 2019).

Special Issue Editor

Guest Editor
Prof. Shahab D. Mohaghegh

Department of Petroleum and Natural Gas Engineering, West Virginia University, 325B Mineral Resources Building, Morgantown, WV 26506, USA
Website | E-Mail
Interests: Artificial Neural Networks, Evolutionary Computing and Fuzzy Logic in earth science, Reservoir Engineering, Natural Gas Engineering, Simulation and Modeling

Special Issue Information

Dear Colleagues,

The massive computational footprint of numerical simulation models limits their practical use for objectives such as detail analyses, uncertainty quantification, and process optimization. To overcome such limitations, proxy models have been developed in the past several decades. The traditional approaches to developing proxy models include reduced order models (ROM) and statistical response surfaces.

Utilizing the pattern recognition capabilities of artificial intelligence and machine learning introduces a paradigm shift on how proxy models are developed. These smart proxy models accurately mimic the performance of highly complex numerical simulation models at speeds that are multiple orders of magnitude faster. Modelling fluid flow that is of high interest in many industries can immensely benefit from smart proxy modelling. The focus of this Special Issue is on the application of smart proxy modelling in computational fluid dynamics (CFD) and numerical reservoir simulation. 

Prof. Shahab D. Mohaghegh
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Fluids is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Artificial Intelligence
  • Machine Learning
  • Numerical Simulation
  • Reservoir Simulation
  • Computational Fluid Dynamics (CFD)
  • Proxy Modeling
  • Smart Proxy

Published Papers (7 papers)

View options order results:
result details:
Displaying articles 1-7
Export citation of selected articles as:

Research

Open AccessArticle
Data-Driven Model Reduction for Coupled Flow and Geomechanics Based on DMD Methods
Received: 3 May 2019 / Revised: 2 July 2019 / Accepted: 12 July 2019 / Published: 19 July 2019
PDF Full-text (8003 KB) | HTML Full-text | XML Full-text
Abstract
Learning reservoir flow dynamics is of primary importance in creating robust predictive models for reservoir management including hydraulic fracturing processes. Physics-based models are to a certain extent exact, but they entail heavy computational infrastructure for simulating a wide variety of parameters and production [...] Read more.
Learning reservoir flow dynamics is of primary importance in creating robust predictive models for reservoir management including hydraulic fracturing processes. Physics-based models are to a certain extent exact, but they entail heavy computational infrastructure for simulating a wide variety of parameters and production scenarios. Reduced-order models offer computational advantages without compromising solution accuracy, especially if they can assimilate large volumes of production data without having to reconstruct the original model (data-driven models). Dynamic mode decomposition (DMD) entails the extraction of relevant spatial structure (modes) based on data (snapshots) that can be used to predict the behavior of reservoir fluid flow in porous media. In this paper, we will further enhance the application of the DMD, by introducing sparse DMD and local DMD. The former is particularly useful when there is a limited number of sparse measurements as in the case of reservoir simulation, and the latter can improve the accuracy of developed DMD models when the process dynamics show a moving boundary behavior like hydraulic fracturing. For demonstration purposes, we first show the methodology applied to (flow only) single- and two-phase reservoir models using the SPE10 benchmark. Both online and offline processes will be used for evaluation. We observe that we only require a few DMD modes, which are determined by the sparse DMD structure, to capture the behavior of the reservoir models. Then, we applied the local DMDc for creating a proxy for application in a hydraulic fracturing process. We also assessed the trade-offs between problem size and computational time for each reservoir model. The novelty of our method is the application of sparse DMD and local DMDc, which is a data-driven technique for fast and accurate simulations. Full article
Figures

Figure 1

Open AccessArticle
Application of Machine Learning and Artificial Intelligence in Proxy Modeling for Fluid Flow in Porous Media
Received: 1 May 2019 / Revised: 1 July 2019 / Accepted: 3 July 2019 / Published: 9 July 2019
PDF Full-text (7955 KB) | HTML Full-text | XML Full-text
Abstract
Reservoir simulation models are the major tools for studying fluid flow behavior in hydrocarbon reservoirs. These models are constructed based on geological models, which are developed by integrating data from geology, geophysics, and petro-physics. As the complexity of a reservoir simulation model increases, [...] Read more.
Reservoir simulation models are the major tools for studying fluid flow behavior in hydrocarbon reservoirs. These models are constructed based on geological models, which are developed by integrating data from geology, geophysics, and petro-physics. As the complexity of a reservoir simulation model increases, so does the computation time. Therefore, to perform any comprehensive study which involves thousands of simulation runs, a very long period of time is required. Several efforts have been made to develop proxy models that can be used as a substitute for complex reservoir simulation models. These proxy models aim at generating the outputs of the numerical fluid flow models in a very short period of time. This research is focused on developing a proxy fluid flow model using artificial intelligence and machine learning techniques. In this work, the proxy model is developed for a real case CO2 sequestration project in which the objective is to evaluate the dynamic reservoir parameters (pressure, saturation, and CO2 mole fraction) under various CO2 injection scenarios. The data-driven model that is developed is able to generate pressure, saturation, and CO2 mole fraction throughout the reservoir with significantly less computational effort and considerably shorter period of time compared to the numerical reservoir simulation model. Full article
Figures

Figure 1

Open AccessArticle
Modeling Average Pressure and Volume Fraction of a Fluidized Bed Using Data-Driven Smart Proxy
Received: 15 April 2019 / Revised: 28 June 2019 / Accepted: 1 July 2019 / Published: 5 July 2019
PDF Full-text (13458 KB) | HTML Full-text | XML Full-text
Abstract
Simulations can reduce the time and cost to develop and deploy advanced technologies and enable their rapid scale-up for fossil fuel-based energy systems. However, to ensure their usefulness in practice, the credibility of the simulations needs to be established with uncertainty quantification (UQ) [...] Read more.
Simulations can reduce the time and cost to develop and deploy advanced technologies and enable their rapid scale-up for fossil fuel-based energy systems. However, to ensure their usefulness in practice, the credibility of the simulations needs to be established with uncertainty quantification (UQ) methods. The National Energy Technology Laboratory (NETL) has been applying non-intrusive UQ methodologies to categorize and quantify uncertainties in computational fluid dynamics (CFD) simulations of gas-solid multiphase flows. To reduce the computational cost associated with gas-solid flow simulations required for UQ analysis, techniques commonly used in the area of artificial intelligence (AI) and data mining are used to construct smart proxy models, which can reduce the computational cost of conducting large numbers of multiphase CFD simulations. The feasibility of using AI and machine learning to construct a smart proxy for a gas-solid multiphase flow has been investigated by looking at the flow and particle behavior in a non-reacting rectangular fluidized bed. The NETL’s in house multiphase solver, Multiphase Flow with Interphase eXchanges (MFiX), was used to generate simulation data for the rectangular fluidized bed. The artificial neural network (ANN) was used to construct a CFD smart proxy, which is able to reproduce the CFD results with reasonable error (about 10%). Several blind cases were used to validate this technology. The results show a good agreement with CFD runs while the approach is less computationally expensive. The developed model can be used to generate the time averaged results of any given fluidized bed with the same geometry with different inlet velocity in couple of minutes. Full article
Figures

Figure 1

Open AccessArticle
Equation Discovery Using Fast Function Extraction: a Deterministic Symbolic Regression Approach
Received: 27 April 2019 / Revised: 29 May 2019 / Accepted: 12 June 2019 / Published: 15 June 2019
PDF Full-text (3765 KB) | HTML Full-text | XML Full-text
Abstract
Advances in machine learning (ML) coupled with increased computational power have enabled identification of patterns in data extracted from complex systems. ML algorithms are actively being sought in recovering physical models or mathematical equations from data. This is a highly valuable technique where [...] Read more.
Advances in machine learning (ML) coupled with increased computational power have enabled identification of patterns in data extracted from complex systems. ML algorithms are actively being sought in recovering physical models or mathematical equations from data. This is a highly valuable technique where models cannot be built using physical reasoning alone. In this paper, we investigate the application of fast function extraction (FFX), a fast, scalable, deterministic symbolic regression algorithm to recover partial differential equations (PDEs). FFX identifies active bases among a huge set of candidate basis functions and their corresponding coefficients from recorded snapshot data. This approach uses a sparsity-promoting technique from compressive sensing and sparse optimization called pathwise regularized learning to perform feature selection and parameter estimation. Furthermore, it recovers several models of varying complexity (number of basis terms). FFX finally filters out many identified models using non-dominated sorting and forms a Pareto front consisting of optimal models with respect to minimizing complexity and test accuracy. Numerical experiments are carried out to recover several ubiquitous PDEs such as wave and heat equations among linear PDEs and Burgers, Korteweg–de Vries (KdV), and Kawahara equations among higher-order nonlinear PDEs. Additional simulations are conducted on the same PDEs under noisy conditions to test the robustness of the proposed approach. Full article
Figures

Figure 1

Open AccessArticle
Interplay of Sensor Quantity, Placement and System Dimension in POD-Based Sparse Reconstruction of Fluid Flows
Received: 5 February 2019 / Revised: 22 May 2019 / Accepted: 10 June 2019 / Published: 13 June 2019
PDF Full-text (14495 KB) | HTML Full-text | XML Full-text
Abstract
Sparse linear estimation of fluid flows using data-driven proper orthogonal decomposition (POD) basis is systematically explored in this work. Fluid flows are manifestations of nonlinear multiscale partial differential equations (PDE) dynamical systems with inherent scale separation that impact the system dimensionality. Given that [...] Read more.
Sparse linear estimation of fluid flows using data-driven proper orthogonal decomposition (POD) basis is systematically explored in this work. Fluid flows are manifestations of nonlinear multiscale partial differential equations (PDE) dynamical systems with inherent scale separation that impact the system dimensionality. Given that sparse reconstruction is inherently an ill-posed problem, the most successful approaches require the knowledge of the underlying low-dimensional space spanning the manifold in which the system resides. In this paper, we adopt an approach that learns basis from singular value decomposition (SVD) of training data to recover sparse information. This results in a set of four design parameters for sparse recovery, namely, the choice of basis, system dimension required for sufficiently accurate reconstruction, sensor budget and their placement. The choice of design parameters implicitly determines the choice of algorithm as either l 2 minimization reconstruction or sparsity promoting l 1 minimization reconstruction. In this work, we systematically explore the implications of these design parameters on reconstruction accuracy so that practical recommendations can be identified. We observe that greedy-smart sensor placement, particularly interpolation points from the discrete empirical interpolation method (DEIM), provide the best balance of computational complexity and accurate reconstruction. Full article
Figures

Figure 1

Open AccessArticle
Smart Proxy Modeling of SACROC CO2-EOR
Received: 26 February 2019 / Revised: 17 April 2019 / Accepted: 26 April 2019 / Published: 3 May 2019
PDF Full-text (15856 KB) | HTML Full-text | XML Full-text
Abstract
Large CO2-enhanced oil recovery (EOR) projects usually contain an abundance of geological and good performance data. While this volume of data leads to robust models, it often results in difficult to manage, slow-running numerical flow models. To dramatically reduce the numerical [...] Read more.
Large CO2-enhanced oil recovery (EOR) projects usually contain an abundance of geological and good performance data. While this volume of data leads to robust models, it often results in difficult to manage, slow-running numerical flow models. To dramatically reduce the numerical run-times associated with the traditional simulation techniques, this work investigated the feasibility of using artificial intelligence and machine learning technologies to develop a smart proxy model of the Scurry Area Canyon Reef Operators Committee (SACROC) oilfield, located in the Permian Basin, TX, USA. Smart proxy models can be used to facilitate injection-production optimization for CO2-EOR projects. The use of a coupled grid-based, and well-based surrogate reservoir model (SRM) (also known as smart proxy modeling) was investigated as the base of the optimization. A fit-for-purpose coupled SRM, which executes in seconds, was built based on high-resolution numerical reservoir simulation models of the northern platform of the SACROC oilfield. This study is unique as it is the first application of coupled SRM at a large oilfield. The developed SRM was able to identify the dynamic reservoir properties (pressure, saturations, and component mole-fraction) at every grid-block, along with the production characteristics (pressure and rate) at each well. Recent attempts to use machine learning and pattern recognition to build proxy models have been simplistic, with limited predictive capabilities. The geological model used in this study is comprised of more than nine million grid blocks. The high correlation between the actual component and SRM, which can be visualized by mapping the properties, along with the fast footprint of the developed model demonstrate the successful application of this methodology. Full article
Figures

Figure 1

Open AccessArticle
Predicting the Dynamic Parameters of Multiphase Flow in CFD (Dam-Break Simulation) Using Artificial Intelligence-(Cascading Deployment)
Received: 17 January 2019 / Revised: 19 February 2019 / Accepted: 4 March 2019 / Published: 7 March 2019
Cited by 1 | PDF Full-text (21290 KB) | HTML Full-text | XML Full-text
Abstract
Multiphase flow of oil, gas, and water occurs in a reservoir’s underground formation and also within the associated downstream pipeline and structures. Computer simulations of such phenomena are essential in order to achieve the behavior of parameters including but not limited to evolution [...] Read more.
Multiphase flow of oil, gas, and water occurs in a reservoir’s underground formation and also within the associated downstream pipeline and structures. Computer simulations of such phenomena are essential in order to achieve the behavior of parameters including but not limited to evolution of phase fractions, temperature, velocity, pressure, and flow regimes. However, within the oil and gas industry, due to the highly complex nature of such phenomena seen in unconventional assets, an accurate and fast calculation of the aforementioned parameters has not been successful using numerical simulation techniques, i.e., computational fluid dynamic (CFD). In this study, a fast-track data-driven method based on artificial intelligence (AI) is designed, applied, and investigated in one of the most well-known multiphase flow problems. This problem is a two-dimensional dam-break that consists of a rectangular tank with the fluid column at the left side of the tank behind the gate. Initially, the gate is opened, which leads to the collapse of the column of fluid and generates a complex flow structure, including water and captured bubbles. The necessary data were obtained from the experience and partially used in our fast-track data-driven model. We built our models using Levenberg Marquardt algorithm in a feed-forward back propagation technique. We combined our model with stochastic optimization in a way that it decreased the absolute error accumulated in following time-steps compared to numerical computation. First, we observed that our models predicted the dynamic behavior of multiphase flow at each time-step with higher speed, and hence lowered the run time when compared to the CFD numerical simulation. To be exact, the computations of our models were more than one hundred times faster than the CFD model, an order of 8 h to minutes using our models. Second, the accuracy of our predictions was within the limit of 10% in cascading condition compared to the numerical simulation. This was acceptable considering its application in underground formations with highly complex fluid flow phenomena. Our models help all engineering aspects of the oil and gas industry from drilling and well design to the future prediction of an efficient production. Full article
Figures

Figure 1

Fluids EISSN 2311-5521 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top