Physics-informed operator learning for transferable energy-dissipative microstructure dynamics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiong, Jie, Wu, Yue, Zhou, Xuewei, Zhao, Peishuo, Zhu, Jiaming
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911661636452352
author Xiong, Jie
Wu, Yue
Zhou, Xuewei
Zhao, Peishuo
Zhu, Jiaming
author_facet Xiong, Jie
Wu, Yue
Zhou, Xuewei
Zhao, Peishuo
Zhu, Jiaming
contents Phase-field simulations provide mechanistic descriptions of microstructure evolution, but repeated high-fidelity integration over long horizons and broad parameter spaces remains computationally expensive. We present PFNet, a physics-informed neural operator framework that advances microstructural states by learning conditional evolution operators rather than direct correlations. PFNet combines a diffusion-inspired U-Net with periodic padding, entropy-based state conditioning and thermodynamic-parameter modulation to encode boundary consistency, instantaneous ordering state and changes in the free-energy landscape. For Cahn-Hilliard coarsening, PFNet achieves accurate one-step prediction and stable autoregressive rollouts across composition, gradient-energy coefficient, coarsening stage and morphology class, with errors concentrated near diffuse interfaces and topology-changing regions. The same framework extends to a four-channel martensitic-transformation benchmark without martensite-specific redesign. These results indicate that physics-informed operator learning can provide transferable surrogates for phase-field dynamics and broader energy-dissipative dynamical systems.
format Preprint
id arxiv_https___arxiv_org_abs_2605_07279
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Physics-informed operator learning for transferable energy-dissipative microstructure dynamics
Xiong, Jie
Wu, Yue
Zhou, Xuewei
Zhao, Peishuo
Zhu, Jiaming
Materials Science
Disordered Systems and Neural Networks
Phase-field simulations provide mechanistic descriptions of microstructure evolution, but repeated high-fidelity integration over long horizons and broad parameter spaces remains computationally expensive. We present PFNet, a physics-informed neural operator framework that advances microstructural states by learning conditional evolution operators rather than direct correlations. PFNet combines a diffusion-inspired U-Net with periodic padding, entropy-based state conditioning and thermodynamic-parameter modulation to encode boundary consistency, instantaneous ordering state and changes in the free-energy landscape. For Cahn-Hilliard coarsening, PFNet achieves accurate one-step prediction and stable autoregressive rollouts across composition, gradient-energy coefficient, coarsening stage and morphology class, with errors concentrated near diffuse interfaces and topology-changing regions. The same framework extends to a four-channel martensitic-transformation benchmark without martensite-specific redesign. These results indicate that physics-informed operator learning can provide transferable surrogates for phase-field dynamics and broader energy-dissipative dynamical systems.
title Physics-informed operator learning for transferable energy-dissipative microstructure dynamics
topic Materials Science
Disordered Systems and Neural Networks
url https://arxiv.org/abs/2605.07279