Ensemble of physics-informed neural networks for solving plane elasticity problems with examples

Two-dimensional (plane) elasticity equations in solid mechanics are solved numerically with the use of an ensemble of physics-informed neural networks (PINNs). The system of equations consists of the kinematic definitions, i.e. the strain–displacement relations, the equilibrium equations connecting...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Acta mechanica Jg. 235; H. 11; S. 6703 - 6722
Hauptverfasser: Mouratidou, Aliki D., Drosopoulos, Georgios A., Stavroulakis, Georgios E.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Vienna Springer Vienna 01.11.2024
Springer
Springer Nature B.V
Schlagworte:
Analysis
Application programming interface
Applications programming
Artificial intelligence
Boundary conditions
Classical and Continuum Physics
Commercial aircraft
Computer programs
Constitutive equations
Constitutive relationships
Control
Deep learning
Dynamical Systems
Elasticity
Engineering
Engineering Fluid Dynamics
Engineering Thermodynamics
Equilibrium equations
Exact solutions
Finite element method
Heat and Mass Transfer
Kinematics
Machine learning
Material properties
Mathematical analysis
Mathematical models
Neural networks
Original Paper
Physics
Plane stress
Python
Science
Software
Solid Mechanics
Strain
Tensors
Theoretical and Applied Mechanics
Vibration
ISSN:0001-5970, 1619-6937
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Two-dimensional (plane) elasticity equations in solid mechanics are solved numerically with the use of an ensemble of physics-informed neural networks (PINNs). The system of equations consists of the kinematic definitions, i.e. the strain–displacement relations, the equilibrium equations connecting a stress tensor with external loading forces and the isotropic constitutive relations for stress and strain tensors. Different boundary conditions for the strain tensor and displacements are considered. The proposed computational approach is based on principles of artificial intelligence and uses a developed open-source machine learning platform, scientific software Tensorflow, written in Python and Keras library, an application programming interface, intended for a deep learning. A deep learning is performed through training the physics-informed neural network model in order to fit the plain elasticity equations and given boundary conditions at collocation points. The numerical technique is tested on an example, where the exact solution is given. Two examples with plane stress problems are calculated with the proposed multi-PINN model. The numerical solution is compared with results obtained after using commercial finite element software. The numerical results have shown that an application of a multi-network approach is more beneficial in comparison with using a single PINN with many outputs. The derived results confirmed the efficiency of the introduced methodology. The proposed technique can be extended and applied to the structures with nonlinear material properties.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0001-5970
1619-6937
DOI:10.1007/s00707-024-04053-3