Multi-mode reduced order models for real time simulations of monolith reactors with micro-kinetics

2021 ◽  
pp. 132532
Author(s):  
Mingjie Tu ◽  
Ram Ratnakar ◽  
Vemuri Balakotaiah
Keyword(s):  
Real Time ◽  
Reduced Order Models ◽  
Reduced Order ◽  
Monolith Reactors ◽  
Real Time Simulations ◽  
Multi Mode

scholarly journals POD-Enhanced Deep Learning-Based Reduced Order Models for the Real-Time Simulation of Cardiac Electrophysiology in the Left Atrium

2021 ◽  
Vol 12 ◽  
Author(s):  
Stefania Fresca ◽  
Andrea Manzoni ◽  
Luca Dedè ◽  
Alfio Quarteroni
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Left Atrium ◽  
Real Time ◽  
Cardiac Electrophysiology ◽  
Front Propagation ◽  
Reduced Order Models ◽  
Reduced Order ◽  
Training Costs ◽  
Speed Up

The numerical simulation of multiple scenarios easily becomes computationally prohibitive for cardiac electrophysiology (EP) problems if relying on usual high-fidelity, full order models (FOMs). Likewise, the use of traditional reduced order models (ROMs) for parametrized PDEs to speed up the solution of the aforementioned problems can be problematic. This is primarily due to the strong variability characterizing the solution set and to the nonlinear nature of the input-output maps that we intend to reconstruct numerically. To enhance ROM efficiency, we proposed a new generation of non-intrusive, nonlinear ROMs, based on deep learning (DL) algorithms, such as convolutional, feedforward, and autoencoder neural networks. In the proposed DL-ROM, both the nonlinear solution manifold and the nonlinear reduced dynamics used to model the system evolution on that manifold can be learnt in a non-intrusive way thanks to DL algorithms trained on a set of FOM snapshots. DL-ROMs were shown to be able to accurately capture complex front propagation processes, both in physiological and pathological cardiac EP, very rapidly once neural networks were trained, however, at the expense of huge training costs. In this study, we show that performing a prior dimensionality reduction on FOM snapshots through randomized proper orthogonal decomposition (POD) enables to speed up training times and to decrease networks complexity. Accuracy and efficiency of this strategy, which we refer to as POD-DL-ROM, are assessed in the context of cardiac EP on an idealized left atrium (LA) geometry and considering snapshots arising from a NURBS (non-uniform rational B-splines)-based isogeometric analysis (IGA) discretization. Once the ROMs have been trained, POD-DL-ROMs can efficiently solve both physiological and pathological cardiac EP problems, for any new scenario, in real-time, even in extremely challenging contexts such as those featuring circuit re-entries, that are among the factors triggering cardiac arrhythmias.

scholarly journals A machine learning framework for rapid forecasting and history matching in unconventional reservoirs

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Shriram Srinivasan ◽  
Daniel O’Malley ◽  
Maruti K. Mudunuru ◽  
Matthew R. Sweeney ◽  
Jeffrey D. Hyman ◽  
...  
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Transfer Learning ◽  
History Matching ◽  
Time History ◽  
Unconventional Reservoirs ◽  
Production Data ◽  
High Fidelity ◽  
Reduced Order Models ◽  
Reduced Order

AbstractWe present a novel workflow for forecasting production in unconventional reservoirs using reduced-order models and machine-learning. Our physics-informed machine-learning workflow addresses the challenges to real-time reservoir management in unconventionals, namely the lack of data (i.e., the time-frame for which the wells have been producing), and the significant computational expense of high-fidelity modeling. We do this by applying the machine-learning paradigm of transfer learning, where we combine fast, but less accurate reduced-order models with slow, but accurate high-fidelity models. We use the Patzek model (Proc Natl Acad Sci 11:19731–19736, 10.1073/pnas.1313380110, 2013) as the reduced-order model to generate synthetic production data and supplement this data with synthetic production data obtained from high-fidelity discrete fracture network simulations of the site of interest. Our results demonstrate that training with low-fidelity models is not sufficient for accurate forecasting, but transfer learning is able to augment the knowledge and perform well once trained with the small set of results from the high-fidelity model. Such a physics-informed machine-learning (PIML) workflow, grounded in physics, is a viable candidate for real-time history matching and production forecasting in a fractured shale gas reservoir.

Real time solutions of Thermo-Hydro Mechanical problems with application to the design of Engineered Barriers via Reduced Order Methods

2020 ◽  
Author(s):  
Arash Moaven ◽  
Thierry J. Massart ◽  
Sergio Zlotnik
Keyword(s):  
Real Time ◽  
Nuclear Power ◽  
Order Reduction ◽  
Model Order ◽  
Reduced Order ◽  
Environmental Interactions ◽  
Best Fitting ◽  
Synthesis Report ◽  
Real Time Simulations ◽  
Reduced Order Methods

<div><strong>Keywords:</strong> Thermo Hydro-Mechanical (THM), Model Order Reduction (MOR), Parametric solutions, Real time simulations.</div><div> </div><div>Radioactive waste is a by-product of nuclear power generation. It is hazardous to all forms of life and the environment. Its radioactive activity naturally decays over time, so waste has to be isolated and confined in appropriate disposal facilities for a sufficient period until it no longer poses a threat. Deep geological repositories constitute one of the most promising options for isolating this type of waste from human and environmental interactions. The analysis and prediction of the behaviour of such systems relies on coupled THM models [1]. The coupled nature of the problem is explained as follows [2]: i) a thermal part including the heat released by the wastes; ii) the mechanical behavior of the canister holding the wastes, the isolation system and the underground host rock; and, iii) the flow of natural water present in any underground porous media.</div><div><br>A coupled THM problem depends on space, time, and on material parameters (for instance, elastic modulus (E), heat conductivity (κ) and hydraulic conductivity (K)) and geometric parameters (for instance, the distance between canisters). We seek for families of solutions depending on these parameters. We would like to provide a real time numerical simulation of the THM problem for any value of the parameters within a range. Real time here, means a solution provided in a few seconds (instead of several hours). Such a solution can be used within an inversion problem, to obtain an best fitting value of the parameters based on some observations, or even in a control situation, where the prediction of the simulation is used to take some decision in the field.</div><div> </div><div>Reduced Order Methods (ROM)  are a family of numerical methods able to provide such a solutions. In this work we will present several parametric problems, and show how ROM  [3] can provide real time solution to (simple) THM problems.</div><div> </div><div> <p><strong>REFERENCES:</strong></p> <p>[1] Toprak, E.; Mokni, N.; Olivella, S.; Pintado, X.: Thermo-Hydro-Mechanical Modelling of Buffer. Synthesis Report. August 2013.</p> <p>[2] Selvadurai, A.P.S; Suvorov, A.P.: Thermo-Poroelasticity and Geomechanics.CAMBRIDGE UNIVERSITY PRESS, 2017.</p> <p>[3] Diez, P.; Zlotnik, S.; Garcia-Gonzalez, A.; Huerta, A.: Encapsulated PGD algebraic toolbox operating with high-dimensional data. Accepted In Archives of Computational Methods in Engineering, 2019.</p> </div>

On Real-Time Flight Simulation of Flexible Aircraft with Interpolated Reduced-Order Models

2019 ◽  
Author(s):  
Juliano Paulino ◽  
Flávio Silvestre ◽  
Antônio Bernardo Guimarães Neto ◽  
Andrea Da Ronch
Keyword(s):  
Real Time ◽  
Flight Simulation ◽  
Reduced Order Models ◽  
Flexible Aircraft ◽  
Reduced Order

scholarly journals Real-Time Simulation of Parameter-Dependent Fluid Flows through Deep Learning-Based Reduced Order Models

Fluids ◽  
2021 ◽  
Vol 6 (7) ◽  
pp. 259
Author(s):  
Stefania Fresca ◽  
Andrea Manzoni
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Elastic Beam ◽  
Fluid Flows ◽  
Reduced Order Models ◽  
Fluid Structure ◽  
Reduced Order ◽  
Reduction Strategies ◽  
Pressure Formulation ◽  
Parameter Dependent

Simulating fluid flows in different virtual scenarios is of key importance in engineering applications. However, high-fidelity, full-order models relying, e.g., on the finite element method, are unaffordable whenever fluid flows must be simulated in almost real-time. Reduced order models (ROMs) relying, e.g., on proper orthogonal decomposition (POD) provide reliable approximations to parameter-dependent fluid dynamics problems in rapid times. However, they might require expensive hyper-reduction strategies for handling parameterized nonlinear terms, and enriched reduced spaces (or Petrov–Galerkin projections) if a mixed velocity–pressure formulation is considered, possibly hampering the evaluation of reliable solutions in real-time. Dealing with fluid–structure interactions entails even greater difficulties. The proposed deep learning (DL)-based ROMs overcome all these limitations by learning, in a nonintrusive way, both the nonlinear trial manifold and the reduced dynamics. To do so, they rely on deep neural networks, after performing a former dimensionality reduction through POD, enhancing their training times substantially. The resulting POD-DL-ROMs are shown to provide accurate results in almost real-time for the flow around a cylinder benchmark, the fluid–structure interaction between an elastic beam attached to a fixed, rigid block and a laminar incompressible flow, and the blood flow in a cerebral aneurysm.

Sign in / Sign up

Export Citation Format

Share Document