Calibration of a Fluid-Structure Problem with Keras

2019/09/09 by Olivier Pironneau, Pironneau, Olivier
Computer Science · #Classical Physics (physics.class-ph) #Computational Physics (physics.comp-ph) #FOS: Mathematics #FOS: Physical sciences #Numerical Analysis (math.NA) #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.1909.03708

openalex publication_date 2019/09/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this short paper we report on an inverse problem issued from a physical system, namely a fluid structure problem where the parameters are the rigidity constant, the solid-fluid density ratio and the fluid viscosity. We have chosen a simple geometry so that the numerical solution of the system is easy. We compare the solution of this inverse problem by a Neural Network with a more classical solution obtained with a genetic algorithm. The Neural Network does much better.

Citations

• Quantified advantage of discontinuous weight selection in approximations with deep neural networks

Related

• Transferable Model for Shape Optimization subject to Physical\n Constraints
• Physics Informed Neural Networks for Learning the Horizon Size in Bond-Based Peridynamic Models
• Learning Mesh Motion Techniques with Application to Fluid-Structure Interaction
• Using Computational Intelligence for solving the Ornstein-Zernike equation
• Physics-informed KAN PointNet: Deep learning for simultaneous solutions to inverse problems in incompressible flow on numerous irregular geometries