Interval and fuzzy physics-augmented neural networks (iPANN and fPANN) for uncertainty quantification and propagation in constitutive modeling

2026-07-22

AI Summary

This work addresses the challenge of uncertainty quantification and propagation in hyperelastic constitutive modeling under data scarcity, noise, or heterogeneity by proposing interval- and fuzzy-based physics-augmented neural networks (iPANN/fPANN). For the first time, interval and fuzzy set theories are integrated into physics-augmented neural networks to learn upper and lower bounds as well as the mean of the free energy density. By combining automatic differentiation, fuzzy α-cut interpolation, smooth L0 regularization, and a two-stage transfer learning strategy, the method constructs an interpretable energy model that inherently satisfies objectivity, consistency, and polyconvexity. Without requiring any distributional assumptions, the approach effectively envelopes noisy stress data, demonstrates strong generalization on test sets, and successfully propagates both mean and bound predictions through finite element simulations.

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 alpha-cut interpolation, yielding a nested family of admissible responses. iPANNs and fPANNs encode mechanistic constraints - preserving objectivity, consistency and promoting polyconvexity - and smoothed L0 regularization promotes 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.

Problem

• constitutive modeling
• uncertainty quantification
• hyperelasticity
• aleatoric uncertainty
• sparse data

Innovation

• physics-augmented neural networks
• uncertainty quantification
• interval modeling
• fuzzy sets
• constitutive modeling