Researchpinnfluid structure interactionimmersed boundary methodb spline activations
Eulerian-Lagrangian PINN Improves FSI Pressure Accuracy
8.0
Researchers propose an Eulerian-Lagrangian physics-informed neural network (PINN) architecture to solve fluid-structure interaction (FSI) problems with moving boundaries. The model couples an Eulerian fluid network and a Lagrangian structural network, uses immersed-boundary principles and learnable B-spline+SiLU activations, and evaluates on a 2D cavity flow; it improves accuracy by 24.1–91.4% and reduces pressure error from 12.9% to 2.39%.
Key Points
- 1Introduces Eulerian-Lagrangian PINN coupling Eulerian fluid and Lagrangian structural networks via physics constraints
- 2Demonstrates substantial accuracy gains, reducing pressure error from 12.9% to 2.39% on 2D cavity FSI
- 3Suggests domain-specific networks and learnable B-spline activations enable accurate PINN-based FSI simulations
Scoring Rationale
Novel architecture and strong accuracy improvements, but limited to a single 2D benchmark and preprint validation.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
