A Physics-Informed Neural Network Framework for Elastodynamic Wave Propagation in Bimaterial Systems

2026-07-07 · Source: Takara TLDR - Daily AI Papers · Field: Science & Research — Artificial Intelligence & Machine Learning, Engineering & Applied Sciences, Mathematics & Computational Sciences · Depth: Advanced, medium

Summary

A new physics-informed neural network (PINN) framework models transient elastodynamic wave propagation in bimaterial systems, specifically a steel-aluminum Split Hopkinson Pressure Bar configuration. This framework embeds axisymmetric equations of linear elasticity, along with initial, boundary, and interface conditions, directly into its loss function. Validated against high-fidelity finite-element simulations from ANSYS Workbench Explicit Dynamics, the PINN accurately predicts wave transmission and reflection, axial and radial displacement histories, face-averaged responses, and dominant stress and strain evolution. The trained network functions as a continuous surrogate model, capable of predicting wave responses at previously unseen time instants and for modified material properties without requiring additional finite-element simulations. Its robustness is confirmed by mesh-sensitivity studies, and its generality is demonstrated across various material combinations, offering an accurate and computationally efficient approach for high-rate solid mechanics and impact engineering.

Key takeaway

For research scientists developing computational models for high-rate solid mechanics, this PINN framework offers a significant efficiency gain. You can achieve accurate elastodynamic wave propagation predictions in bimaterial systems, reducing reliance on extensive finite-element simulations for new material properties or time instants. Consider integrating PINNs with existing explicit FEA workflows to create continuous surrogate models, accelerating design and optimization in impact engineering.

Key insights

PINNs combined with explicit FEA accurately model elastodynamic wave propagation in bimaterial systems.

Principles

• Physical laws can be directly embedded into neural network loss functions.
• Surrogate models can predict unseen conditions without re-simulation.
• Integrating PINNs with FEA enhances accuracy and efficiency.

Method

The framework incorporates elastodynamic equations, initial, boundary, and interface conditions into a physics-informed loss function. It uses high-fidelity finite-element simulations for validation and as supplementary data constraints during training.

In practice

• Model wave propagation in heterogeneous solids.
• Accelerate high-rate solid mechanics analysis.
• Optimize impact engineering applications.

Topics

• Physics-Informed Neural Networks
• Elastodynamics
• Bimaterial Systems
• Finite Element Analysis
• Surrogate Modeling
• Impact Engineering

Code references

• PredictiveIntelligenceLab/GradientPathologiesPINNs

Best for: AI Scientist, Research Scientist

Related on AIssential

• Differential Equations V — Physics Informed Neural Networks (PINNs) — Physics Informed Neural Networks embed physical laws into neural networks for fast, accurate, and physically consistent simulations.
• Mesh Graph Neural Network Framework for Accelerating Finite Element Simulation for Arbitrary Geometries — Mesh Graph Networks effectively generalize finite element analysis predictions across arbitrary structural geometries by encoding relative features.
• Material-Agnostic Zero-Shot Thermal Inference for Metal Additive Manufacturing via a Parametric PINN Framework — A parametric PINN framework enables zero-shot thermal modeling across diverse materials in metal AM with high efficiency.
• Finite Element-Based Material Learning via Automatic Differentiation: Learning constitutive neural network models from full-field deformation data — FE-MAD uses automatic differentiation within a JAX-FEM solver to learn constitutive neural network models from full-field deformation data.
• Physics-Informed Neural Network Modeling of Biodegradable Contaminant Transport through GCL/SL Composite Liners — Hard-constrained PINNs significantly improve accuracy and stability for modeling contaminant transport in composite liners.
• WaveGraphNet: Physics-Consistent Guided-Wave Damage Localization through Coupled Inverse-Forward Graph Learning — Coupling inverse graph localization with a physics-consistent forward model improves damage localization extrapolation in unseen regions.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Takara TLDR - Daily AI Papers.