Researchers have developed a novel framework utilizing physics-informed neural networks (PINNs) to model elastodynamic wave propagation in bimaterial systems. This approach embeds physical laws directly into the neural network, enabling accurate predictions of wave transmission and reflection across material interfaces. The framework was validated against high-fidelity finite-element simulations and demonstrated the ability to act as a continuous surrogate model, predicting responses for unseen conditions without additional computational expense. AI
IMPACT This framework offers a more efficient and accurate surrogate modeling approach for complex physical simulations in engineering.
RANK_REASON The cluster contains an academic paper detailing a new research framework for applying PINNs to a specific scientific problem.
- ANSYS Workbench Explicit Dynamics
- bimaterial systems
- Elastodynamic wave propagation in graded materials: simulations, experiments, phenomena, and applications.
- finite element method
- Finite element simulations of acetylcholine diffusion in neuromuscular junctions
- Finite element solutions for plane strain mode I crack with strain gradient effects
- high-rate solid mechanics
- impact engineering
- Physics-Informed Neural Network
- physics-informed neural networks
- Split-Hopkinson pressure bar
- steel-aluminum
- steel-aluminum specimen
AI-generated summary · Google Gemini · from 3 sources. How we write summaries →
