Physics-informed and graph neural networks for enhanced inverse analysis
Di Lorenzo, Daniele ; Champaney, Victor ; Ghnatios, Chady ; Cueto, Elías (Universidad de Zaragoza) ; Chinesta, Francisco
Resumen: Purpose : This paper presents an original approach for learning models, partially known, of particular interest when performing source identification or structural health monitoring. The proposed procedures employ some amount of knowledge on the system under scrutiny as well as a limited amount of data efficiently assimilated.
Design/methodology/approach : Two different formulations are explored. The first, based on the use of informed neural networks, leverages data collected at specific locations and times to determine the unknown source term of a parabolic partial differential equation. The second procedure, more challenging, involves learning the unknown model from a single measured field history, enabling the localization of a region where material properties differ.
Findings: Both procedures assume some kind of sparsity, either in the source distribution or in the region where physical properties differ. This paper proposed two different neural approaches able to learn models in order to perform efficient inverse analyses.Originality/valueTwo original methodologies are explored to identify hidden property that can be recovered with the right usage of data. Both methodologies are based on neural network architecture.
Originality/value : Two original methodologies are explored to identify hidden property that can be recovered with the right usage of data. Both methodologies are based on neural network architecture.
Idioma: Inglés
DOI: 10.1108/EC-12-2023-0958
Año: 2024
Publicado en: ENGINEERING COMPUTATIONS (2024), [29 pp.]
ISSN: 0264-4401
Financiación: info:eu-repo/grantAgreement/EC/H2020/956401/EU/Cross-scale concurrent material-structure design using functionally-graded 3D-printed matematerials/XS-Meta
Tipo y forma: Article (Published version)
Área (Departamento): Área Mec.Med.Cont. y Teor.Est. (Dpto. Ingeniería Mecánica)
You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
Exportado de SIDERAL (2024-11-29-13:24:33)
Visitas y descargas
Design/methodology/approach : Two different formulations are explored. The first, based on the use of informed neural networks, leverages data collected at specific locations and times to determine the unknown source term of a parabolic partial differential equation. The second procedure, more challenging, involves learning the unknown model from a single measured field history, enabling the localization of a region where material properties differ.
Findings: Both procedures assume some kind of sparsity, either in the source distribution or in the region where physical properties differ. This paper proposed two different neural approaches able to learn models in order to perform efficient inverse analyses.Originality/valueTwo original methodologies are explored to identify hidden property that can be recovered with the right usage of data. Both methodologies are based on neural network architecture.
Originality/value : Two original methodologies are explored to identify hidden property that can be recovered with the right usage of data. Both methodologies are based on neural network architecture.
Idioma: Inglés
DOI: 10.1108/EC-12-2023-0958
Año: 2024
Publicado en: ENGINEERING COMPUTATIONS (2024), [29 pp.]
ISSN: 0264-4401
Financiación: info:eu-repo/grantAgreement/EC/H2020/956401/EU/Cross-scale concurrent material-structure design using functionally-graded 3D-printed matematerials/XS-Meta
Tipo y forma: Article (Published version)
Área (Departamento): Área Mec.Med.Cont. y Teor.Est. (Dpto. Ingeniería Mecánica)
You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. Exportado de SIDERAL (2024-11-29-13:24:33)
Permalink:
Visitas y descargas
Este artículo se encuentra en las siguientes colecciones:
Articles > Artículos por área > Mec. de Medios Contínuos y Teor. de Estructuras
Record created 2024-11-29, last modified 2024-11-29