Solving and learning nonlinear PDEs with Gaussian processes
We introduce a simple, rigorous, and unified framework for solving nonlinear partial
differential equations (PDEs), and for solving inverse problems (IPs) involving the …
differential equations (PDEs), and for solving inverse problems (IPs) involving the …
DeepGreen: deep learning of Green's functions for nonlinear boundary value problems
Boundary value problems (BVPs) play a central role in the mathematical analysis of
constrained physical systems subjected to external forces. Consequently, BVPs frequently …
constrained physical systems subjected to external forces. Consequently, BVPs frequently …
[图书][B] Advanced reduced order methods and applications in computational fluid dynamics
Reduced order modeling is an important and fast-growing research field in computational
science and engineering, motivated by several reasons, of which we mention just a few …
science and engineering, motivated by several reasons, of which we mention just a few …
Active manifold and model-order reduction to accelerate multidisciplinary analysis and optimization
G Boncoraglio, C Farhat - AIAA Journal, 2021 - arc.aiaa.org
A computational framework is proposed for efficiently solving multidisciplinary analysis and
optimization (MDAO) problems in a relatively high-dimensional design parameter space. It …
optimization (MDAO) problems in a relatively high-dimensional design parameter space. It …
A multifidelity approach coupling parameter space reduction and nonintrusive POD with application to structural optimization of passenger ship hulls
Nowadays, the shipbuilding industry is facing a radical change toward solutions with a
smaller environmental impact. This can be achieved with low emissions engines, optimized …
smaller environmental impact. This can be achieved with low emissions engines, optimized …
Epistemic modeling uncertainty of rapid neural network ensembles for adaptive learning
A Beachy, H Bae, JA Camberos, RV Grandhi - Finite Elements in Analysis …, 2024 - Elsevier
Emulator embedded neural networks, which are closely related to physics informed neural
networks, leverage multi-fidelity data sources for efficient design exploration of aerospace …
networks, leverage multi-fidelity data sources for efficient design exploration of aerospace …
[图书][B] Model order reduction for multidisciplinary design optimization in higher-dimensional parameter spaces
G Boncoraglio - 2021 - search.proquest.com
This thesis introduces a new framework for solving optimization problems efficiently in
higher-dimensional parameter spaces constrained by partial differential equations (PDEs) …
higher-dimensional parameter spaces constrained by partial differential equations (PDEs) …
[图书][B] On Multiscale and Statistical Numerical Methods for PDEs and Inverse Problems
Y Chen - 2023 - search.proquest.com
This thesis is about numerical methods for scientific computing and scientific machine
learning, with a focus on solving partial differential equations (PDEs) and inverse problems …
learning, with a focus on solving partial differential equations (PDEs) and inverse problems …
A Machine Learning Framework for Hypersonic Vehicle Design Exploration
A Beachy - 2023 - rave.ohiolink.edu
Abstract The design of Hypersonic Vehicles (HVs) requires meeting multiple unconventional
and often conflicting design requirements in a hostile, high-energy environment. The most …
and often conflicting design requirements in a hostile, high-energy environment. The most …
Overview of computational methods to predict flutter in aircraft
E Antimirova, J Jung, Z Zhang… - Journal of Applied …, 2024 - asmedigitalcollection.asme.org
Aeroelastic flutter is a dynamically complex phenomenon that has adverse and unstable
effects on elastic structures. It is crucial to better predict the phenomenon of flutter within the …
effects on elastic structures. It is crucial to better predict the phenomenon of flutter within the …