Stable and Interpretable Multi-Mode Rheological Universal Differential Equations (mmRUDEs) for Data-Driven Constitutive Modeling
Abstract
The Rheological Universal Differential Equation (RUDE) framework embeds neural networks within a frame-indifferent tensorial constitutive backbone and so enables data-driven discovery of complex material rheological behavior. However, the flexibility that makes the RUDE framework attractive also makes it difficult to deploy: the learned neural network correction can make the constitutive equation numerically stiff during training, distribute corrections across non-unique combinations of tensor-basis terms, and extrapolate poorly with increasing nonlinearity, especially for industrially relevant materials with broad relaxation spectra. We develop a stability- and reliability-focused multi-mode RUDE framework that addresses three key challenges: thermodynamic admissibility, out-of-distribution prediction, and interpretability. Logarithmic compression of the input invariants and a split-network architecture improve numerical conditioning during training, while a differentiable projection layer enforces the Clausius--Duhem inequality at every time step. We illustrate the framework with both synthetic (a multi-mode Giesekus model) and experimental data on an entangled silicone polymer melt. Both models were trained on LAOS; they remain stable and accurate under unseen flow conditions, including steady shear, transient stress growth, and extensional flows, for which the unconstrained models may diverge numerically. To aid in interpretation of the contributions of each learned correction to the rheological behavior, we introduce the rheome, a compact way of representing the dominant weighted tensor-basis contributions to the overall rheological behavior. These improvements to the RUDE framework lead to stable and interpretable trained models, paving the way for implementation in computational fluid dynamics simulations and for guiding the rational design of soft material processing operations.
Related
- Generalized Constraint-Controlled Rheological Model: Two Constitutive Pathways under Sinusoidal Periodic Shear Deformation
- A Universal Constitutive Relation for Static Droplet Retention
- Inferring constitutive forces from noisy Allen-Cahn movies with moment equations
- General first-order constitutive equations for a relativistic dissipative multi-component fluid in the presence of a weak background electromagnetic field
- From the universal Lindblad equation to Boltzmann equations: in-QGP quarkonium dynamics
BibTeX
@misc{das2026stable,
title = {{Stable and Interpretable Multi-Mode Rheological Universal Differential Equations (mmRUDEs) for Data-Driven Constitutive Modeling}},
author = {Mohua Das and Nicholas King and Navid Azizan and Gareth H. McKinley},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.38470},
eprint = {2609.38470},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.38470},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Stable and Interpretable Multi-Mode Rheological Universal Differential Equations (mmRUDEs) for Data-Driven Constitutive Modeling
AU - Mohua Das
AU - Nicholas King
AU - Navid Azizan
AU - Gareth H. McKinley
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.38470
UR - https://arxiv.org/abs/2609.38470
AB - The Rheological Universal Differential Equation (RUDE) framework embeds neural networks within a frame-indifferent tensorial constitutive backbone and so enables data-driven discovery of complex material rheological behavior. However, the flexibility that makes the RUDE framework attractive also makes it difficult to deploy: the learned neural network correction can make the constitutive equation numerically stiff during training, distribute corrections across non-unique combinations of tensor-basis terms, and extrapolate poorly with increasing nonlinearity, especially for industrially relevant materials with broad relaxation spectra. We develop a stability- and reliability-focused multi-mode RUDE framework that addresses three key challenges: thermodynamic admissibility, out-of-distribution prediction, and interpretability. Logarithmic compression of the input invariants and a split-network architecture improve numerical conditioning during training, while a differentiable projection layer enforces the Clausius--Duhem inequality at every time step. We illustrate the framework with both synthetic (a multi-mode Giesekus model) and experimental data on an entangled silicone polymer melt. Both models were trained on LAOS; they remain stable and accurate under unseen flow conditions, including steady shear, transient stress growth, and extensional flows, for which the unconstrained models may diverge numerically. To aid in interpretation of the contributions of each learned correction to the rheological behavior, we introduce the rheome, a compact way of representing the dominant weighted tensor-basis contributions to the overall rheological behavior. These improvements to the RUDE framework lead to stable and interpretable trained models, paving the way for implementation in computational fluid dynamics simulations and for guiding the rational design of soft material processing operations.
ER -