An autoencoder-based reduced-order model for eigenvalue problems with application to neutron diffusion

Abstract

Using an autoencoder for dimensionality reduction, this paper presents a novel projection-based reduced-order model for eigenvalue problems. Reduced-order modelling relies on finding suitable basis functions which define a low-dimensional space in which a high-dimensional system is approximated. Proper orthogonal decomposition (POD) and singular value decomposition (SVD) are often used for this purpose and yield an optimal linear subspace. Autoencoders provide a nonlinear alternative to POD/SVD, that may capture, more efficiently, features or patterns in the high-fidelity model results. Reduced-order models based on an autoencoder and a novel hybrid SVD-autoencoder are developed. These methods are compared with the standard POD-Galerkin approach and are applied to two test cases taken from the field of nuclear reactor physics.

arXiv comment35 pages, 33 figures

References in corpus (6)

• Machine Learning for Fluid Mechanics
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Local/global model order reduction strategy for the simulation of quasi-brittle fracture
• Deep convolutional recurrent autoencoders for learning low-dimensional feature dynamics of fluid systems
• Memory embedded non-intrusive reduced order modeling of non-ergodic flows
• Eigenvalue Solvers for Modeling Nuclear Reactors on Leadership Class Machines

Cited by in corpus (15)

• Non-intrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: comparison with linear subspace techniques
• An AI-based Domain-Decomposition Non-Intrusive Reduced-Order Model for Extended Domains applied to Multiphase Flow in Pipes
• Nonlinear proper orthogonal decomposition for convection-dominated flows
• Data-driven reduced order modelling for patient-specific hemodynamics of coronary artery bypass grafts with physical and geometrical parameters
• Solving the Discretised Neutron Diffusion Equations using Neural Networks
• 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
• Adversarial autoencoders and adversarial LSTM for improved forecasts of urban air pollution simulations
• A data driven reduced order model of fluid flow by Auto-Encoder and self-attention deep learning methods
• Data Assimilation Predictive GAN (DA-PredGAN): applied to determine the spread of COVID-19
• Polytopic Autoencoders with Smooth Clustering for Reduced-order Modelling of Flows
• Nonintrusive reduced order modeling of convective Boussinesq flows
• Surrogate models for Rock-Fluid Interaction: A Grid-Size-Invariant Approach
• Solving time-dependent parametric PDEs by multiclass classification-based reduced order model
• Generative Network-Based Reduced-Order Model for Prediction, Data Assimilation and Uncertainty Quantification