Download or read book Using Machine Learning to Detect and Reduce Uncertainty in Turbulent Flow Simulations written by and published by . This book was released on 2016 with total page 1 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Machine Learning for Uncertainty Quantification in Turbulent Flow Simulations written by and published by . This book was released on 2016 with total page 25 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Using Machine Learning for Error Detection in Turbulent Flow Simulations written by and published by . This book was released on 2015 with total page 1 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Turbulent Flow Simulations for Machine Learning written by and published by . This book was released on 2015 with total page 1 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Quantification of Modelling Uncertainties in Turbulent Flow Simulations written by Wouter Nico Edeling and published by . This book was released on 2015 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: The goal of this thesis is to make predictive simulations with Reynolds-Averaged Navier-Stokes (RANS) turbulence models, i.e. simulations with a systematic treatment of model and data uncertainties and their propagation through a computational model to produce predictions of quantities of interest with quantified uncertainty. To do so, we make use of the robust Bayesian statistical framework.The first step toward our goal concerned obtaining estimates for the error in RANS simulations based on the Launder-Sharma k-e turbulence closure model, for a limited class of flows. In particular we searched for estimates grounded in uncertainties in the space of model closure coefficients, for wall-bounded flows at a variety of favourable and adverse pressure gradients. In order to estimate the spread of closure coefficients which reproduces these flows accurately, we performed 13 separate Bayesian calibrations. Each calibration was at a different pressure gradient, using measured boundary-layer velocity profiles, and a statistical model containing a multiplicative model inadequacy term in the solution space. The results are 13 joint posterior distributions over coefficients and hyper-parameters. To summarize this information we compute Highest Posterior-Density (HPD) intervals, and subsequently represent the total solution uncertainty with a probability box (p-box). This p-box represents both parameter variability across flows, and epistemic uncertainty within each calibration. A prediction of a new boundary-layer flow is made with uncertainty bars generated from this uncertainty information, and the resulting error estimate is shown to be consistent with measurement data.However, although consistent with the data, the obtained error estimates were very large. This is due to the fact that a p-box constitutes a unweighted prediction. To improve upon this, we developed another approach still based on variability in model closure coefficients across multiple flow scenarios, but also across multiple closure models. The variability is again estimated using Bayesian calibration against experimental data for each scenario, but now Bayesian Model-Scenario Averaging (BMSA) is used to collate the resulting posteriors in an unmeasured (prediction) scenario. Unlike the p-boxes, this is a weighted approach involving turbulence model probabilities which are determined from the calibration data. The methodology was applied to the class of turbulent boundary-layers subject to various pressure gradients. For all considered prediction scenarios the standard-deviation of the stochastic estimate is consistent with the measurement ground truth.The BMSA approach results in reasonable error bars, which can also be decomposed into separate contributions. However, to apply it to more complex topologies outside the class of boundary-layer flows, surrogate modelling techniques must be applied. The Simplex-Stochastic Collocation (SSC) method is a robust surrogate modelling technique used to propagate uncertain input distributions through a computer code. However, its use of the Delaunay triangulation can become prohibitively expensive for problems with dimensions higher than 5. We therefore investigated means to improve upon this bad scalability. In order to do so, we first proposed an alternative interpolation stencil technique based upon the Set-Covering problem, which resulted in a significant speed up when sampling the full-dimensional stochastic space. Secondly, we integrated the SSC method into the High-Dimensional Model-Reduction framework in order to avoid sampling high-dimensional spaces all together.Finally, with the use of our efficient surrogate modelling technique, we applied the BMSA framework to the transonic flow over an airfoil. With this we are able to make predictive simulations of computationally expensive flow problems with quantified uncertainty due to various imperfections in the turbulence models.

Download or read book Data driven and Physics constrained Uncertainty Quantification for Turbulence Models written by Jan Felix Heyse and published by . This book was released on 2022 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt: Numerical simulations are an important tool for prediction of turbulent flows. Today, most simulations in real-world applications are Reynolds-averaged Navier-Stokes (RANS) simulations, which average the governing equations to solve for the mean flow quantities. RANS simulations require modeling of an unknown quantity, the Reynolds stress tensor, using turbulence models. These models are limited in their accuracy for many complex flows, such as those involving strong stream-line curvature or adverse pressure gradients, making RANS predictions less reliable for design decisions. For RANS predictions to be useful in engineering design practice, it is therefore important to quantify the uncertainty in the predictions. More specifically, in this dissertation the focus is on quantifying the model-form uncertainty associated with the turbulence model. A data-free eigenperturbation framework introduced in the past few years, allows to make quantitative uncertainty estimates for all quantities of interest. It relies on a linear mapping from the eigenvalues of the Reynolds stress into the barycentric domain. In this framework, perturbations are added to the eigenvalues in that barycentric domain by perturbing them towards limiting states of 1 component, 2 component, and 3 component turbulence. Eigenvectors are permuted to find the extreme states of the turbulence kinetic energy production term. These eigenperturbations allow to explore a range of shapes and alignments of the Reynolds stress tensor within constraints of physical realizability of the resulting Reynolds stresses. However, this framework is limited by the introduction of a uniform amount of perturbation throughout the domain and by the need to specify a parameter governing the amount of perturbation. Data-driven eigenvalue perturbations are therefore introduced in this work to address those limitations. They are built on the eigenperturbation framework, but use a data-driven approach to determine how much perturbation to impose locally at every cell. The target amount of perturbation is the expected distance between the RANS prediction and the true solution in the barycentric domain. A general set of features is introduced, computed from the RANS mean flow quantities. The periodic flow over a wavy wall (for which also a detailed high-fidelity simulation dataset is available) serves as training case. A random forest machine learning model is trained to predict the target distance from the features. A hyperparameter study is carried out to find the most appropriate hyperparameters for the random forest. Random forest feature importance estimates confirm general expectations from physical intuition. The framework is applied to two test cases, the flow over a backward-facing step and the flow in an asymmetric diffuser. Both test cases and the training case exhibit a flow separation where the cross sectional area increases. The distribution of key features is studied for these cases and compared against the one from the training case. It is found that the random forest is not extrapolating. The results on the two test cases show uncertainty estimates that are characteristic of the true error in the predictions and give more representative bounds than the data-free framework does. The sets of eigenvectors from the RANS prediction and the true solution can be connected through a rotation. The idea of data-driven eigenvector rotations as a data-driven extension to the eigenvectors is studied. However, continuousness of the prediction targets is not generally achievable because of the ambiguity of the eigenvector direction. The lack of smoothness prevents the machine learning models from learning the relationship between the features and the targets, making data-driven eigenvector rotations in the discussed setup not practical. The last chapter of this dissertation introduces a data-driven baseline simulation, which corresponds to the expected value in the data-driven eigenvalue perturbation framework. The Reynolds stress is a weighted sum of the Reynolds stresses from the extreme states. A random classification forest trained to predict which extreme state is closest to the true Reynolds stress is used to compute these weights. It does so by giving a probabilistic meaning to the raw predictions of the constituent decision trees. On the test cases, the data-driven baseline predictions are similar but not equal to the data-free baseline. They complement the uncertainty estimates from the data-driven eigenvalue perturbations.

Download or read book Machine Learning Methods for Modeling Turbulence in Large Eddy Simulations written by Marius Kurz and published by . This book was released on 2024 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: The reliable prediction of turbulent flows is of crucial importance since turbulence is prevalent in the majority of flows found in science and engineering. Turbulence is a multi-scale phenomenon, for which flow features can span several orders of magnitude in size. This results in enormous resolution requirements in numerical simulations of turbulent flow. The framework of large eddy simulation relaxes these resolution demands by resolving only the largest, most energetic features of the flow and approximating the dynamics of the smaller, unresolved scales with turbulence models. The goal of this thesis is to leverage the recent advances in machine learning methods to formulate data-driven modeling strategies for implicitly filtered large eddy simulation. To this end, two modeling strategies are devised based on the supervised and the reinforcement learning paradigms. First, artificial neural networks are trained using supervised learning to recover the unknown closure terms from the filtered flow field. It is demonstrated that recurrent neural networks can predict the unknown closure terms with excellent accuracy. The second modeling strategy is based on the reinforcement learning paradigm. For this, Relexi is introduced as a novel reinforcement learning framework that allows to employ legacy flow solvers as training environments at scale. With Relexi, artificial neural networks are trained within forced homogeneous isotropic turbulence to adapt the parameters of traditional turbulence models dynamically in space and time. The trained models provide accurate and stable simulations and generalize well to other resolutions and higher Reynolds numbers. It is demonstrated within this thesis that machine learning methods can be applied to derive data-driven turbulence models for implicitly filtered large eddy simulation and that these models can be trained and incorporated efficiently into practical simulations on high-performance computing systems.

Download or read book High Performance Computing written by Heike Jagode and published by Springer Nature. This book was released on 2020-10-19 with total page 382 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book constitutes the refereed post-conference proceedings of 10 workshops held at the 35th International ISC High Performance 2020 Conference, in Frankfurt, Germany, in June 2020: First Workshop on Compiler-assisted Correctness Checking and Performance Optimization for HPC (C3PO); First International Workshop on the Application of Machine Learning Techniques to Computational Fluid Dynamics Simulations and Analysis (CFDML); HPC I/O in the Data Center Workshop (HPC-IODC); First Workshop \Machine Learning on HPC Systems" (MLHPCS); First International Workshop on Monitoring and Data Analytics (MODA); 15th Workshop on Virtualization in High-Performance Cloud Computing (VHPC). The 25 full papers included in this volume were carefully reviewed and selected. They cover all aspects of research, development, and application of large-scale, high performance experimental and commercial systems. Topics include high-performance computing (HPC), computer architecture and hardware, programming models, system software, performance analysis and modeling, compiler analysis and optimization techniques, software sustainability, scientific applications, deep learning.

Download or read book Data Analysis for Direct Numerical Simulations of Turbulent Combustion written by Heinz Pitsch and published by Springer Nature. This book was released on 2020-05-28 with total page 294 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book presents methodologies for analysing large data sets produced by the direct numerical simulation (DNS) of turbulence and combustion. It describes the development of models that can be used to analyse large eddy simulations, and highlights both the most common techniques and newly emerging ones. The chapters, written by internationally respected experts, invite readers to consider DNS of turbulence and combustion from a formal, data-driven standpoint, rather than one led by experience and intuition. This perspective allows readers to recognise the shortcomings of existing models, with the ultimate goal of quantifying and reducing model-based uncertainty. In addition, recent advances in machine learning and statistical inferences offer new insights on the interpretation of DNS data. The book will especially benefit graduate-level students and researchers in mechanical and aerospace engineering, e.g. those with an interest in general fluid mechanics, applied mathematics, and the environmental and atmospheric sciences.

Download or read book Accelerating the Simulation of Chemically Reacting Turbulent Flows Via Machine Learning Techniques written by Opeoluwa Olawale Owoyele and published by . This book was released on 2018 with total page 205 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Modeling Complex Turbulent Flows written by Manuel D. Salas and published by Springer Science & Business Media. This book was released on 2012-12-06 with total page 385 pages. Available in PDF, EPUB and Kindle. Book excerpt: Turbulence modeling both addresses a fundamental problem in physics, 'the last great unsolved problem of classical physics,' and has far-reaching importance in the solution of difficult practical problems from aeronautical engineering to dynamic meteorology. However, the growth of supercom puter facilities has recently caused an apparent shift in the focus of tur bulence research from modeling to direct numerical simulation (DNS) and large eddy simulation (LES). This shift in emphasis comes at a time when claims are being made in the world around us that scientific analysis itself will shortly be transformed or replaced by a more powerful 'paradigm' based on massive computations and sophisticated visualization. Although this viewpoint has not lacked ar ticulate and influential advocates, these claims can at best only be judged premature. After all, as one computational researcher lamented, 'the com puter only does what I tell it to do, and not what I want it to do. ' In turbulence research, the initial speculation that computational meth ods would replace not only model-based computations but even experimen tal measurements, have not come close to fulfillment. It is becoming clear that computational methods and model development are equal partners in turbulence research: DNS and LES remain valuable tools for suggesting and validating models, while turbulence models continue to be the preferred tool for practical computations. We believed that a symposium which would reaffirm the practical and scientific importance of turbulence modeling was both necessary and timely.

Download or read book Numerical Simulation of Turbulent Flows and Noise Generation written by Christophe Brun and published by Springer. This book was released on 2010-10-22 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: Large Eddy Simulation (LES) is a high-fidelity approach to the numerical simulation of turbulent flows. Recent developments have shown LES to be able to predict aerodynamic noise generation and propagation as well as the turbulent flow, by means of either a hybrid or a direct approach. This book is based on the results of two French/German research groups working on LES simulations in complex geometries and noise generation in turbulent flows. The results provide insights into modern prediction approaches for turbulent flows and noise generation mechanisms as well as their use for novel noise reduction concepts.

Download or read book Turbulence Modelling Approaches written by Konstantin Volkov and published by BoD – Books on Demand. This book was released on 2017-07-26 with total page 252 pages. Available in PDF, EPUB and Kindle. Book excerpt: Accurate prediction of turbulent flows remains a challenging task despite considerable work in this area and the acceptance of CFD as a design tool. The quality of the CFD calculations of the flows in engineering applications strongly depends on the proper prediction of turbulence phenomena. Investigations of flow instability, heat transfer, skin friction, secondary flows, flow separation, and reattachment effects demand a reliable modelling and simulation of the turbulence, reliable methods, accurate programming, and robust working practices. The current scientific status of simulation of turbulent flows as well as some advances in computational techniques and practical applications of turbulence research is reviewed and considered in the book.

Download or read book Machine Learning Control Taming Nonlinear Dynamics and Turbulence written by Thomas Duriez and published by Springer. This book was released on 2016-11-02 with total page 229 pages. Available in PDF, EPUB and Kindle. Book excerpt: This is the first textbook on a generally applicable control strategy for turbulence and other complex nonlinear systems. The approach of the book employs powerful methods of machine learning for optimal nonlinear control laws. This machine learning control (MLC) is motivated and detailed in Chapters 1 and 2. In Chapter 3, methods of linear control theory are reviewed. In Chapter 4, MLC is shown to reproduce known optimal control laws for linear dynamics (LQR, LQG). In Chapter 5, MLC detects and exploits a strongly nonlinear actuation mechanism of a low-dimensional dynamical system when linear control methods are shown to fail. Experimental control demonstrations from a laminar shear-layer to turbulent boundary-layers are reviewed in Chapter 6, followed by general good practices for experiments in Chapter 7. The book concludes with an outlook on the vast future applications of MLC in Chapter 8. Matlab codes are provided for easy reproducibility of the presented results. The book includes interviews with leading researchers in turbulence control (S. Bagheri, B. Batten, M. Glauser, D. Williams) and machine learning (M. Schoenauer) for a broader perspective. All chapters have exercises and supplemental videos will be available through YouTube.

Download or read book Dynamic Mode Decomposition written by J. Nathan Kutz and published by SIAM. This book was released on 2016-11-23 with total page 241 pages. Available in PDF, EPUB and Kindle. Book excerpt: Data-driven dynamical systems is a burgeoning field?it connects how measurements of nonlinear dynamical systems and/or complex systems can be used with well-established methods in dynamical systems theory. This is a critically important new direction because the governing equations of many problems under consideration by practitioners in various scientific fields are not typically known. Thus, using data alone to help derive, in an optimal sense, the best dynamical system representation of a given application allows for important new insights. The recently developed dynamic mode decomposition (DMD) is an innovative tool for integrating data with dynamical systems theory. The DMD has deep connections with traditional dynamical systems theory and many recent innovations in compressed sensing and machine learning. Dynamic Mode Decomposition: Data-Driven Modeling of Complex Systems, the first book to address the DMD algorithm, presents a pedagogical and comprehensive approach to all aspects of DMD currently developed or under development; blends theoretical development, example codes, and applications to showcase the theory and its many innovations and uses; highlights the numerous innovations around the DMD algorithm and demonstrates its efficacy using example problems from engineering and the physical and biological sciences; and provides extensive MATLAB code, data for intuitive examples of key methods, and graphical presentations.

Download or read book Turbulent Flow Computation written by D. Drikakis and published by Springer. This book was released on 2014-03-14 with total page 376 pages. Available in PDF, EPUB and Kindle. Book excerpt: In various branches of fluid mechanics, our understanding is inhibited by the presence of turbulence. Although many experimental and theoretical studies have significantly helped to increase our physical understanding, a comp- hensive and predictive theory of turbulent flows has not yet been established. Therefore, the prediction of turbulent flow relies heavily on simulation stra- gies. The development of reliable methods for turbulent flow computation will have a significant impact on a variety of technological advancements. These range from aircraft and car design, to turbomachinery, combustors, and process engineering. Moreover, simulation approaches are important in materials - sign, prediction of biologically relevant flows, and also significantly contribute to the understanding of environmental processes including weather and climate forecasting. The material that is compiled in this book presents a coherent account of contemporary computational approaches for turbulent flows. It aims to p- vide the reader with information about the current state of the art as well as to stimulate directions for future research and development. The book puts part- ular emphasis on computational methods for incompressible and compressible turbulent flows as well as on methods for analysing and quantifying nume- cal errors in turbulent flow computations. In addition, it presents turbulence modelling approaches in the context of large eddy simulation, and unfolds the challenges in the field of simulations for multiphase flows and computational fluid dynamics (CFD) of engineering flows in complex geometries. Apart from reviewing main research developments, new material is also included in many of the chapters.

Download or read book Boosting written by Robert E. Schapire and published by MIT Press. This book was released on 2014-01-10 with total page 544 pages. Available in PDF, EPUB and Kindle. Book excerpt: An accessible introduction and essential reference for an approach to machine learning that creates highly accurate prediction rules by combining many weak and inaccurate ones. Boosting is an approach to machine learning based on the idea of creating a highly accurate predictor by combining many weak and inaccurate “rules of thumb.” A remarkably rich theory has evolved around boosting, with connections to a range of topics, including statistics, game theory, convex optimization, and information geometry. Boosting algorithms have also enjoyed practical success in such fields as biology, vision, and speech processing. At various times in its history, boosting has been perceived as mysterious, controversial, even paradoxical. This book, written by the inventors of the method, brings together, organizes, simplifies, and substantially extends two decades of research on boosting, presenting both theory and applications in a way that is accessible to readers from diverse backgrounds while also providing an authoritative reference for advanced researchers. With its introductory treatment of all material and its inclusion of exercises in every chapter, the book is appropriate for course use as well. The book begins with a general introduction to machine learning algorithms and their analysis; then explores the core theory of boosting, especially its ability to generalize; examines some of the myriad other theoretical viewpoints that help to explain and understand boosting; provides practical extensions of boosting for more complex learning problems; and finally presents a number of advanced theoretical topics. Numerous applications and practical illustrations are offered throughout.