Interval and fuzzy physics-augmented neural networks (iPANN and fPANN) for uncertainty quantification and propagation in constitutive modeling
Abstract
Constitutive modeling under uncertainty remains a central challenge for reliable mechanics simulations, particularly when the available stress-deformation data are sparse, noisy, or heterogeneous. We propose interval and fuzzy physics-augmented neural networks (iPANNs and fPANNs) for uncertainty-aware hyperelastic constitutive modeling. iPANNs learn sparse lower, mean, and upper free energy density branches whose stresses, obtained by automatic differentiation, ultimately enclose noisy stress observations. In contrast to this deterministic interval description, fPANNs embed the learned iPANN branches into a fuzzy-set representation through membership-level (alpha-cut) interpolation, yielding a nested family of admissible responses. iPANNs and fPANNs encode mechanistic constraints by preserving objectivity, consistency and promoting polyconvexity and, smoothed L0 regularization promoting interpretable energy representations. The bound models are trained through a two-stage transfer-learning procedure in which a sparse mean constitutive response is learned first and then fine-tuned into lower and upper energy branches. We evaluate the framework on synthetic isotropic hyperelastic data with heteroscedastic noise, varying random realizations, shifted noise means, and varying noise magnitudes. The results show that the learned bounds enclose noisy stress observations while generalizing to the test set. Further, we examine the propagation of uncertainty through the mean, upper and lower bound predictions of the learned iPANN models in a finite element setting. The proposed framework provides a compact, physics-consistent route for distribution-free aleatoric uncertainty quantification in hyperelastic constitutive modeling, and propagation in downstream finite element simulations.
Related
- Rapid Uncertainty Quantification on a Latent Field using Fisher Information
- Does Your Self-Consistent Field Program Know How Wrong It Is? Introducing Quantum Chemistry Uncertainty Propagation.
- Reconstruction of Unobserved Core Electron Density in Tokamak Plasmas with a Neural Operator Transport Surrogate and Uncertainty Quantification
- OpenTURNS: A Python package for uncertainty quantification
- Bayesian bilevel operator learning with low-rank adaptation for efficient uncertainty quantification of PDE inverse problems.
BibTeX
@misc{singh2026interval,
title = {{Interval and fuzzy physics-augmented neural networks (iPANN and fPANN) for uncertainty quantification and propagation in constitutive modeling}},
author = {Somesh Pratap Singh and Govinda Anantha Padmanabha and Jingye Tan and Steven Yang and Reese E. Jones and D. Thomas Seidl and Nikolaos Bouklas},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2607.20339},
eprint = {2607.20339},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.20339},
}
RIS
TY - UNPB
TI - Interval and fuzzy physics-augmented neural networks (iPANN and fPANN) for uncertainty quantification and propagation in constitutive modeling
AU - Somesh Pratap Singh
AU - Govinda Anantha Padmanabha
AU - Jingye Tan
AU - Steven Yang
AU - Reese E. Jones
AU - D. Thomas Seidl
AU - Nikolaos Bouklas
PY - 2026
DA - 2026/09/26
PB - arXiv
DO - 10.48550/arxiv.2607.20339
UR - https://arxiv.org/abs/2607.20339
AB - Constitutive modeling under uncertainty remains a central challenge for reliable mechanics simulations, particularly when the available stress-deformation data are sparse, noisy, or heterogeneous. We propose interval and fuzzy physics-augmented neural networks (iPANNs and fPANNs) for uncertainty-aware hyperelastic constitutive modeling. iPANNs learn sparse lower, mean, and upper free energy density branches whose stresses, obtained by automatic differentiation, ultimately enclose noisy stress observations. In contrast to this deterministic interval description, fPANNs embed the learned iPANN branches into a fuzzy-set representation through membership-level (alpha-cut) interpolation, yielding a nested family of admissible responses. iPANNs and fPANNs encode mechanistic constraints by preserving objectivity, consistency and promoting polyconvexity and, smoothed L0 regularization promoting interpretable energy representations. The bound models are trained through a two-stage transfer-learning procedure in which a sparse mean constitutive response is learned first and then fine-tuned into lower and upper energy branches. We evaluate the framework on synthetic isotropic hyperelastic data with heteroscedastic noise, varying random realizations, shifted noise means, and varying noise magnitudes. The results show that the learned bounds enclose noisy stress observations while generalizing to the test set. Further, we examine the propagation of uncertainty through the mean, upper and lower bound predictions of the learned iPANN models in a finite element setting. The proposed framework provides a compact, physics-consistent route for distribution-free aleatoric uncertainty quantification in hyperelastic constitutive modeling, and propagation in downstream finite element simulations.
ER -