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

Jul 16, 2026

Upload by Rowan

Physics-informed neural networks (PINNs) provide a learning framework for partial differential equations by embedding governing physical laws into the training process. This study develops a PINN-based model for transient elastodynamic wave propagation in axisymmetric linear-elastic bimaterial systems, using a steel–aluminum specimen representative of Split Hopkinson Pressure Bar configurations. Elastodynamic equations and initial, boundary, and interface conditions are enforced via physics-informed loss functions, validated with ANSYS Workbench Explicit Dynamics and shown to accurately predict transmission/reflection, displacement histories, face-averaged responses, and stress–strain evolution. The trained surrogate generalizes to unseen time instants and modified material properties without new finite-element simulations, with mesh robustness confirmed and extended material combinations demonstrating methodology generality for high-rate impact mechanics.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages18

Reading Time45 min

Abstract

Keywords

1 Introduction

Physics-informed neural networks for PDEs

Transient wave propagation in elastic solids and challenges in heterogeneous materials

Related work on elastic-wave modeling and SHPB testing

arXiv :2607 .06479v 1 [ cs .AI ] 7 Jul 2026 A Physics-Informed Neural Network Framework for Elastodynamic Wave Propagation in Bimaterial Systems Sonal Ankush Chibire 1 , Jenn-Terng Gau 1 , Bo Zhang 1* 1 Department of Mechanical Engineering, Northern Illinois University, 1425 W Lincoln Hwy, DeKalb, 60115, IL, USA. *Corresponding author(s). E-mail(s): [bzhang@niu.edu](bzhang@niu.edu) ; Contributing authors: [Z2018284@students.niu.edu](Z2018284@students.niu.edu) ; [jgau@niu.edu](jgau@niu.edu) ; Abstract Physics-informed neural networks (PINNs) provide a promising framework for solving partial differential equations while embedding the underlying physical laws directly into the learning process. This study presents a PINN-based framework for modeling transient elastodynamic wave propagation in bimaterial systems governed by the axisymmetric equations of linear elasticity. A steel-aluminum specimen representative of a Split Hopkinson Pressure Bar configuration is considered, and the governing elastodynamic equations, together with the corresponding initial, boundary, and interface conditions, are incorporated directly into the network through a physics-informed loss function. High-fidelity finite-element simulations performed using ANSYS Workbench Explicit Dynamics are used for validation and as supplementary data constraints during training. The proposed framework accurately predicts wave transmission and reflection across the bimaterial interface and reproduces axial and radial displacement histories, face-averaged responses, and the dominant stress and strain evolution with close agreement to the finite-element solutions. The trained network further demonstrates the ability to predict wave responses at previously unseen time instants and for modified material properties without requiring additional finiteelement simulations, providing a continuous surrogate model for elastodynamic analysis. Mesh-sensitivity studies confirm numerical robustness, while additional material combinations demonstrate the generality of the proposed methodology. The results show that integrating physics-informed neural networks with explicit finite-element analysis provides an accurate and computationally efficient framework for elastodynamic wave propagation in heterogeneous solids, offering an 1 effective surrogate modeling approach for high-rate solid mechanics and impact engineering applications. Keywords: Physics-Informed Neural Networks, Elastodynamic Wave Propagation, Bimaterial Systems, Split Hopkinson Pressure Bar, Finite Element Method, Surrogate Modeling 1 Introduction Recent advances in scientific machine learning [1–14] have created new opportunities for solving complex partial differential equations arising in computational mechanics and mechanical engineering. Among these developments, Physics-Informed Neural Networks (PINNs) [1, 4] have emerged as a promising computational framework by embedding governing equations, initial and boundary conditions directly into the neural-network training process. Unlike purely data-driven approaches, PINNs incorporate the underlying physical laws into the optimization procedure, enabling the solution of both forward problems governed by known equations and inverse problems in which unknown material properties or system parameters are inferred from limited experimental or numerical observations. Transient wave propagation in elastic solids plays a fundamental role in structural dynamics, impact engineering, and materials science. Accurate prediction of stress-wave transmission and reflection is essential for understanding the dynamic behavior of multilayer structures, protective systems, aerospace components, and other engineering systems subjected to high-rate loading. The problem becomes considerably more challenging in heterogeneous materials, where discontinuities in material properties and imperfect interfaces strongly influence wave propagation, stress redistribution, and

FAQs

How does the proposed PINN framework incorporate physical laws?

The framework embeds elastodynamic governing equations plus initial, boundary, and interface conditions directly into the neural-network training through a physics-informed loss function.

What system and governing assumptions are used for validation?

A steel–aluminum specimen representative of Split Hopkinson Pressure Bar configuration is modeled using axisymmetric equations of linear elasticity, and results are validated against high-fidelity ANSYS Workbench Explicit Dynamics simulations.

What benefits does the trained model provide after training?

After training, the network predicts wave responses at previously unseen time instants and for modified material properties without requiring additional finite-element simulations, acting as a continuous surrogate model.

Jul 16, 2026

Upload by Rowan