paper-with-me

홈 › Papers

A Constitutive Markov Physics-Informed Neural Operator (MPNO) for Autoregressive Stability in Transient Dynamics

2026-08-26 · Wenpu Du, Peng Zhou, Yunlong Xia, Sinuo Xin, Congcong Zhang, Boyang Zhang, Yi Zhang, Wenzheng Xu arxiv

Neural operators applied to transient-dynamics PDEs with strong discontinuities exhibit autoregressive instability: in concrete-penetration stress-field prediction, the wavelet neural operator (WNO) diverges in autoregressive rollout, while MeshGraphNets collapse to zero predictions. WNO's instability stems from the lack of a structural constraint on the spectral radius of its propagation operator; the Fourier neural operator (FNO) is stable in these measurements but only emergently, not by construction. We propose a constitutive Markov physics-informed neural operator (MPNO) modeling one-step evolution as a Markov (row-stochastic) propagation operator. Physics-coupled edge weights (acoustic-impedance harmonic mean, contact area, and traction amplitude) encode material-interface constitutive information into a nonnegative symmetric adjacency matrix W; after normalizing the graph Laplacian L = D - W by lambda_max, the propagator P = I - alpha*L~ is constructively constrained to spectral radius rho(P) <= 1, suppressing exponential amplification of autoregressive errors. Stability is thus a designable architectural property, not an optimized loss objective. On three PDEs (Burgers and two-dimensional transverse-section concrete penetration), MPNO rolls out stably with bounded error on all test seeds at 100/135/165 m/s; the single-step relative L2 error is 0.7304 +/- 0.0008, better than WNO and comparable to FNO at about one quarter of FNO's parameters. The edge-weight formula transfers across scenarios by replacing material-property variables. With about 20K parameters, MPNO delivers roughly 10^5x inference speedup over LS-DYNA.

📄 PDF Abstract BibTeX arXiv:2608.25744

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Monotone Peridynamic Neural Operator for Nonlinear Material Modeling with Conditionally Unique Solutions

2025-05-02 · Jihong Wang, Xiaochuan Tian, Zhongqiang Zhang, Stewart Silling 외

Data-driven methods have emerged as powerful tools for modeling the responses of complex nonlinear materials directly from experimental measurements. Among these methods, the data-driven constitutive models present advan…

Deterministic and statistical calibration of constitutive models from full-field data with parametric physics-informed neural networks

2024-05-28 · David Anton, Jendrik-Alexander Tröger, Henning Wessels, Ulrich Römer 외

The calibration of constitutive models from full-field data has recently gained increasing interest due to improvements in full-field measurement capabilities. In addition to the experimental characterization of novel ma…

Bayesian InferenceStructural Health Monitoring

EquiNO: A Physics-Informed Neural Operator for Multiscale Simulations

2025-03-27 · Hamidreza Eivazi, Jendrik-Alexander Tröger, Stefan Wittek, Stefan Hartmann 외

Multiscale problems are ubiquitous in physics. Numerical simulations of such problems by solving partial differential equations (PDEs) at high resolution are computationally too expensive for many-query scenarios, e.g., …

Operator learningUncertainty Quantification

Calibrating constitutive models with full-field data via physics informed neural networks

2022-03-30 · Craig M. Hamel, Kevin N. Long, Sharlotte L. B. Kramer

The calibration of solid constitutive models with full-field experimental data is a long-standing challenge, especially in materials which undergo large deformation. In this paper, we propose a physics-informed deep-lear…

Physics-informed machine learning

Identifying Constitutive Parameters for Complex Hyperelastic Materials using Physics-Informed Neural Networks

2023-08-29 · Siyuan Song, Hanxun Jin

Identifying constitutive parameters in engineering and biological materials, particularly those with intricate geometries and mechanical behaviors, remains a longstanding challenge. The recent advent of Physics-Informed …