Overview
- Shows how manifold learning uses model order reduction and deep learning for training models in continuum mechanics
- Discusses high dimensional input variables in mechanical models, in particular for image-based digital twining
- Proposes practical techniques such as data augmentation or hyper-reduction in order to reduce high dimensional models
- This book is open access, which means that you have free and unlimited access
Part of the book series: SpringerBriefs in Computer Science (BRIEFSCOMPUTER)
Buy print copy
Tax calculation will be finalised at checkout
Table of contents (6 chapters)
-
Front Matter
Keywords
About this book
Projection-based reduced order models are the projection of mechanical equations on a latent space that have been learnt from both synthetic data and experimental data. Various descriptions and representations of structured data for model reduction are presented in the applications and survey chapters. Image-based digital twins are developed in a reduced setting. Reduced order models of as-manufactured components predict the mechanical effects of shape variations. A similar workflow is extended to multiphysics or coupled problems, with high dimensional input fields. Practical techniques are proposed for data augmentation and also for hyper-reduction, which is a key point to speed up projection-based model order reduction of finite element models.
The book gives access to python libraries available on gitlab.com, which have been developed as part of the research program [FUI-25] MORDICUS funded by the French government. Similarly to deep learning for computer vision, deep learning for model order reduction circumvents the need to design parametric problems prior reducing models. Such an approach is highly relevant for image-base modelling or multiphysics modelling.
Authors and Affiliations
About the authors
Fabien Casenave is a research scientist at Safran Tech, the research center of Safran Group, a French multinational company that designs, develops and manufactures aircraft engines, rocket engines as well as various aerospace and defense-related equipment or their components. As head of the Physics-Informed AI and Numerical Experiments team, Fabien has been working on model-based/physics-based engineering assisted by machine learning applied to industrial design challenges in structural mechanics.
Nissrine Akkari is a research scientist at Safran Tech. She has been working on model-based/physics-based engineering assisted by machine learning applied to industrial design challenges in computational fluid dynamics.
Bibliographic Information
Book Title: Manifold Learning
Book Subtitle: Model Reduction in Engineering
Authors: David Ryckelynck, Fabien Casenave, Nissrine Akkari
Series Title: SpringerBriefs in Computer Science
DOI: https://doi.org/10.1007/978-3-031-52764-7
Publisher: Springer Cham
eBook Packages: Computer Science, Computer Science (R0)
Copyright Information: The Editor(s) (if applicable) and The Author(s) 2024
Softcover ISBN: 978-3-031-52766-1Published: 21 February 2024
eBook ISBN: 978-3-031-52764-7Published: 20 February 2024
Series ISSN: 2191-5768
Series E-ISSN: 2191-5776
Edition Number: 1
Number of Pages: X, 107
Number of Illustrations: 6 b/w illustrations, 25 illustrations in colour
Topics: Machine Learning, Statistics and Computing/Statistics Programs, Probability Theory and Stochastic Processes, Engineering Thermodynamics, Heat and Mass Transfer, Industrial and Production Engineering, Mathematical Methods in Physics