scholarly journals An efficient computational framework for naval shape design and optimization problems by means of data-driven reduced order modeling techniques

2020 ◽  
Author(s):  
Nicola Demo ◽  
Giulio Ortali ◽  
Gianluca Gustin ◽  
Gianluigi Rozza ◽  
Gianpiero Lavini
Keyword(s):  
Optimization Problems ◽  
Computational Cost ◽  
Gaussian Process Regression ◽  
Dynamic Mode Decomposition ◽  
Data Driven ◽  
Free Form ◽  
Dynamic Mode ◽  
Two Phase ◽  
Initial Shape ◽  
Reduced Order

Abstract This contribution describes the implementation of a data-driven shape optimization pipeline in a naval architecture application. We adopt reduced order models in order to improve the efficiency of the overall optimization, keeping a modular and equation-free nature to target the industrial demand. We applied the above mentioned pipeline to a realistic cruise ship in order to reduce the total drag. We begin by defining the design space, generated by deforming an initial shape in a parametric way using free form deformation. The evaluation of the performance of each new hull is determined by simulating the flux via finite volume discretization of a two-phase (water and air) fluid. Since the fluid dynamics model can result very expensive—especially dealing with complex industrial geometries—we propose also a dynamic mode decomposition enhancement to reduce the computational cost of a single numerical simulation. The real-time computation is finally achieved by means of proper orthogonal decomposition with Gaussian process regression technique. Thanks to the quick approximation, a genetic optimization algorithm becomes feasible to converge towards the optimal shape.

Data-Driven Prediction of Unconventional Shale-Reservoir Dynamics

SPE Journal ◽  
2020 ◽  
Vol 25 (05) ◽  
pp. 2564-2581 ◽  
Author(s):  
Hector Klie ◽  
Horacio Florez
Keyword(s):  
Linear Operators ◽  
Dynamic Mode Decomposition ◽  
Data Driven ◽  
Production Data ◽  
Dynamic Mode ◽  
State Variables ◽  
Coupled Flow ◽  
Two Phase ◽  
Data Set ◽  
Well Production

Summary The present work introduces extended dynamic mode decomposition (EDMD) as a suitable data-driven framework for learning the reservoir dynamics entailed by flow/fracture interactions in unconventional shales. The proposed EDMD approach builds on the approximation of infinite-dimensional linear operators combined with the power of deep learning autoencoder networks to extract salient transient features from pressure/stress fields and bulks of production data. The data-driven model is demonstrated on three illustrative examples involving single- and two-phase coupled flow/geomechanics simulations and a real production data set from the Vaca Muerta unconventional shale formation in Argentina. We demonstrated that we could attain a high level of predictability from unseen field-state variables and well-production data given relatively moderate input requirements. As the main conclusion of this work, EDMD stands as a promising data-driven choice for efficiently reconstructing flow/fracture dynamics that are either partially or entirely unknown, or that are too complex to formulate using known simulation tools on unconventional plays.

scholarly journals Data-Driven Pulsatile Blood Flow Physics with Dynamic Mode Decomposition

Fluids ◽  
2020 ◽  
Vol 5 (3) ◽  
pp. 111
Author(s):  
Milad Habibi ◽  
Scott T. M. Dawson ◽  
Amirhossein Arzani
Keyword(s):  
Blood Flow ◽  
Flow Rate ◽  
Coherent Structures ◽  
Dynamic Mode Decomposition ◽  
Data Driven ◽  
Patient Specific ◽  
Dynamic Mode ◽  
Flow Data ◽  
Reduced Order ◽  
Mode Decomposition

Dynamic mode decomposition (DMD) is a purely data-driven and equation-free technique for reduced-order modeling of dynamical systems and fluid flow. DMD finds a best fit linear reduced-order model that represents any given spatiotemporal data. In DMD, each mode evolves with a fixed frequency and therefore DMD modes represent physically meaningful structures that are ranked based on their dynamics. The application of DMD to patient-specific cardiovascular flow data is challenging. First, the input flow rate is unsteady and pulsatile. Second, the flow topology can change significantly in different phases of the cardiac cycle. Finally, blood flow in patient-specific diseased arteries is complex and often chaotic. The objective of this study was to overcome these challenges using our proposed multistage dynamic mode decomposition with control (mDMDc) method and use this technique to study patient-specific blood flow physics. The inlet flow rate was considered as the controller input to the systems. Blood flow data were divided into different stages based on the inlet flow waveform and DMD with control was applied to each stage. The system was augmented to consider both velocity and wall shear stress (WSS) vector data, and therefore study the interaction between the coherent structures in velocity and near-wall coherent structures in WSS. First, it was shown that DMD modes can exactly represent the analytical Womersley solution for incompressible pulsatile flow in tubes. Next, our method was applied to image-based coronary artery stenosis and cerebral aneurysm models where complex blood flow patterns are anticipated. The flow patterns were studied using the mDMDc modes and the reconstruction errors were reported. Our augmented mDMDc framework could capture coherent structures in velocity and WSS with a fewer number of modes compared to the traditional DMD approach and demonstrated a close connection between the velocity and WSS modes.

scholarly journals Analyzing Nonlinear Dynamics via Data-Driven Dynamic Mode Decomposition-Like Methods

Complexity ◽  
2018 ◽  
Vol 2018 ◽  
pp. 1-21 ◽  
Author(s):  
Soledad Le Clainche ◽  
José M. Vega
Keyword(s):  
Nonlinear Dynamics ◽  
Growth Rates ◽  
Transient Behavior ◽  
Dynamic Mode Decomposition ◽  
Data Driven ◽  
Dynamic Mode ◽  
Reduced Order Models ◽  
Reduced Order ◽  
Mode Decomposition ◽  
The Given

This article presents a review on two methods based on dynamic mode decomposition and its multiple applications, focusing on higher order dynamic mode decomposition (which provides a purely temporal Fourier-like decomposition) and spatiotemporal Koopman decomposition (which gives a spatiotemporal Fourier-like decomposition). These methods are purely data-driven, using either numerical or experimental data, and permit reconstructing the given data and identifying the temporal growth rates and frequencies involved in the dynamics and the spatial growth rates and wavenumbers in the case of the spatiotemporal Koopman decomposition. Thus, they may be used to either identify and extrapolate the dynamics from transient behavior to permanent dynamics or construct efficient, purely data-driven reduced order models.

Modeling the Turbulent Wake Behind a Wall-Mounted Square Cylinder

2020 ◽  
Author(s):  
Christian Amor ◽  
José M Pérez ◽  
Philipp Schlatter ◽  
Ricardo Vinuesa ◽  
Soledad Le Clainche
Keyword(s):  
Proper Orthogonal Decomposition ◽  
Turbulent Wake ◽  
Orthogonal Decomposition ◽  
Dynamic Mode Decomposition ◽  
Dynamic Mode ◽  
Square Cylinder ◽  
Complex Flow ◽  
Reduced Order ◽  
Mode Decomposition ◽  
Proper Orthogonal

Abstract This article introduces some soft computing methods generally used for data analysis and flow pattern detection in fluid dynamics. These techniques decompose the original flow field as an expansion of modes, which can be either orthogonal in time (variants of dynamic mode decomposition), or in space (variants of proper orthogonal decomposition) or in time and space (spectral proper orthogonal decomposition), or they can simply be selected using some sophisticated statistical techniques (empirical mode decomposition). The performance of these methods is tested in the turbulent wake of a wall-mounted square cylinder. This highly complex flow is suitable to show the ability of the aforementioned methods to reduce the degrees of freedom of the original data by only retaining the large scales in the flow. The main result is a reduced-order model of the original flow case, based on a low number of modes. A deep discussion is carried out about how to choose the most computationally efficient method to obtain suitable reduced-order models of the flow. The techniques introduced in this article are data-driven methods that could be applied to model any type of non-linear dynamical system, including numerical and experimental databases.

Convolutional Neural Networks for the Localization of Plastic Velocity Gradient Tensor in Polycrystalline Microstructures

2021 ◽  
pp. 1-41
Author(s):  
David Montes de Oca Zapiain ◽  
Apaar Shanker ◽  
Surya Kalidindi
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Velocity Gradient ◽  
Optimization Problems ◽  
Computational Cost ◽  
Two Phase ◽  
Design And Optimization ◽  
Gradient Fields ◽  
Generalized Spherical Harmonics ◽  
New Research

Abstract Recent work has demonstrated the potential of convolutional neural networks (CNNs) in producing low-computational cost surrogate models for the localization of mechanical fields in two-phase microstructures. The extension of the same CNNs to polycrystalline microstructures is hindered by the lack of an efficient formalism for the representation of the crystal lattice orientation in the input channels of the CNNs. In this paper, we demonstrate the benefits of using generalized spherical harmonics (GSH) for addressing this challenge. A CNN model was successfully trained to predict the local plastic velocity gradient fields in polycrystalline microstructures subjected to a macroscopically imposed loading condition. Specifically, it is demonstrated that the proposed approach improves significantly the accuracy of the CNN models, when compared with the direct use of Bunge-Euler angles to represent the crystal orientations in the input channels. Since the proposed approach implicitly satisfies the expected crystal symmetries in the specification of the input microstructure to the CNN, it opens new research directions for the adoption of CNNs in addressing a broad range of polycrystalline microstructure design and optimization problems.

Sign in / Sign up

Export Citation Format

Share Document