Memory embedded non-intrusive reduced order modeling of non-ergodic flows

Abstract

Generating a digital twin of any complex system requires modeling and computational approaches that are efficient, accurate, and modular. Traditional reduced order modeling techniques are targeted at only the first two but the novel non-intrusive approach presented in this study is an attempt at taking all three into account effectively compared to their traditional counterparts. Based on dimensionality reduction using proper orthogonal decomposition (POD), we introduce a long short-term memory (LSTM) neural network architecture together with a principal interval decomposition (PID) framework as an enabler to account for localized modal deformation, which is a key element in accurate reduced order modeling of convective flows. Our applications for convection dominated systems governed by Burgers, Navier-Stokes, and Boussinesq equations demonstrate that the proposed approach yields significantly more accurate predictions than the POD-Galerkin method, and could be a key enabler towards near real-time predictions of unsteady flows.

References in corpus (27)

• Adam: A Method for Stochastic Optimization
• Machine Learning for Fluid Mechanics
• On Dynamic Mode Decomposition: Theory and Applications
• Turbulence Modeling in the Age of Data
• Proper Orthogonal Decomposition Closure Models For Turbulent Flows: A Numerical Comparison
• Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
• Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model
• Sparse reduced-order modeling : Sensor-based dynamics to full-state estimation
• Data-assisted reduced-order modeling of extreme events in complex dynamical systems
• A neural network approach for the blind deconvolution of turbulent flows
• A deep learning enabler for non-intrusive reduced order modeling of fluid flows
• Deep Learning for Time-Series Analysis
• Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems
• POD/DEIM Nonlinear model order reduction of an ADI implicit shallow water equations model
• A Deep Learning based Approach to Reduced Order Modeling for Turbulent Flow Control using LSTM Neural Networks
• Evaluating Data Assimilation Algorithms
• Deep learning algorithm for data-driven simulation of noisy dynamical system
• Comparison of POD reduced order strategies for the nonlinear 2D Shallow Water Equations
• pyMOR - Generic Algorithms and Interfaces for Model Order Reduction
• DR-RNN: A deep residual recurrent neural network for model reduction
• Proper orthogonal decomposition closure models for fluid flows: Burgers equation
• High-order methods for decaying two-dimensional homogeneous isotropic turbulence
• Reduced-order modeling for cardiac electrophysiology. Application to parameter identification
• POD/DEIM Reduced-Order Modeling of Time-Fractional Partial Differential Equations with Applications in Parameter Identification
• A coarse-grid projection method for accelerating incompressible flow computations
• Model Order Reduction by Proper Orthogonal Decomposition
• Efficient Construction of Local Parametric Reduced Order Models Using Machine Learning Techniques

Cited by in corpus (18)

• On closures for reduced order models $-$ A spectrum of first-principle to machine-learned avenues
• Data-driven recovery of hidden physics in reduced order modeling of fluid flows
• Digital Twins in Wind Energy: Emerging Technologies and Industry-Informed Future Directions
• An autoencoder-based reduced-order model for eigenvalue problems with application to neutron diffusion
• A long short-term memory embedding for hybrid uplifted reduced order models
• An AI-based Domain-Decomposition Non-Intrusive Reduced-Order Model for Extended Domains applied to Multiphase Flow in Pipes
• Lagrangian PINNs: A causality-conforming solution to failure modes of physics-informed neural networks
• Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression
• Multifidelity Computing for Coupling Full and Reduced Order Models
• Applying Convolutional Neural Networks to Data on Unstructured Meshes with Space-Filling Curves
• Non-intrusive reduced order modeling of poroelasticity of heterogeneous media based on a discontinuous Galerkin approximation
• A data driven reduced order model of fluid flow by Auto-Encoder and self-attention deep learning methods
• A Tailored Convolutional Neural Network for Nonlinear Manifold Learning of Computational Physics Data using Unstructured Spatial Discretizations
• Reduced order modelling of nonlinear cross-diffusion systems
• A deep learning approach to the measurement of long-lived memory kernels from Generalised Langevin Dynamics
• Prospects of federated machine learning in fluid dynamics
• Reduced order modeling of fluid flows: Machine learning, Kolmogorov barrier, closure modeling, and partitioning
• Generative Network-Based Reduced-Order Model for Prediction, Data Assimilation and Uncertainty Quantification