arXiv subjects

Steven J. Yang

Publications and source records attributed to Steven J. Yang.

3 recordsLinked to original sources

arXiv2026

Mixture of Polyconvex Neural Potentials for Parametric Hyperelasticity: Towards Foundation Material Models

Hyperelastic constitutive models enable modeling large deformations in elastic solids. In common practice, a strain energy density function is prescribed in advance and model-specific parameters are calibrated from experiments. However, many applications require constitutive models for a family of related materials whose mechanical behavior varies with composition. A fixed constitutive model-form may not capture the full range of behavior across the family, while fitting separate forms does not provide a direct way to predict the response of new compositions. Recent work has developed data-driven constitutive models that learn flexible strain energy functions while incorporating key physical constraints. In this work, we propose using mixtures of convex neural potentials based on input convex neural networks as a modular and data efficient approach to modeling material families. Each potential is convex and monotonic with respect to polyconvex strain invariants, while a conditioning network maps material descriptors to mixture weights. We compare the approach with a monolithic partially input-convex neural network using experimental data from PolyJet 3D-printed materials and a synthetic Gent-type benchmark. Across both benchmarks, the mixture architecture generalized better to material descriptors not seen during training. In the PolyJet experimental benchmark, we showed that the mixture architecture is less sensitive to model hyperparameters, while in the Gent-type benchmark it generalized more reliably with sparse data in the material-descriptor space. These results suggest that representing a material family through a small set of shared convex neural potentials provides a useful structural prior for learning descriptor-dependent constitutive behavior from limited data.

physics.comp-ph↗

arXiv2026

Towards Rapid Constitutive Model Discovery from Multi-Modal Data: Physics Augmented Finite Element Model Updating (paFEMU)

Recent progress in AI-enabled constitutive modeling has concentrated on moving from a purely data-driven paradigm to the enforcement of physical constraints and mechanistic principles, a concept referred to as physics augmentation. Classical phenomenological approaches rely on selecting a pre-defined model and calibrating its parameters, while machine learning methods often focus on discovery of the model itself. Sparse regression approaches lie in between, where large libraries of pre-defined models are probed during calibration. Sparsification in the aforementioned paradigm, but also in the context of neural network architecture, has been shown to enable interpretability, uncertainty quantification, but also heterogeneous software integration due to the low-dimensional nature of the resulting models. Most works in AI-enabled constitutive modeling have also focused on data from a single source, but in reality, materials modeling workflows can contain data from many different sources (multi-modal data), and also from testing other materials within the same materials class (multi-fidelity data). In this work, we introduce physics augmented finite element model updating (paFEMU), as a transfer learning approach that combines AI-enabled constitutive modeling, sparsification for interpretable model discovery, and finite element-based adjoint optimization utilizing multi-modal data. This is achieved by combining simple mechanical testing data, potentially from a distinct material, with digital image correlation-type full-field data acquisition to ultimately enable rapid constitutive modeling discovery. The simplicity of the sparse representation enables easy integration of neural constitutive models in existing finite element workflows, and also enables low-dimensional updating during transfer learning.

cs.LG↗

arXiv2023

Elucidating the impact of microstructure on mechanical properties of phase-segregated polyurea: Finite element modeling of molecular dynamics derived microstructures

Phase-segregated polyureas (PU) have received considerable interest due to their use as tough, impact-resistant coatings. Polyureas are favored for these applications due to their mechanical strain rate sensitivity and energy dissipation. Predicting and tailoring the mechanical response of PU remains challenging due to the complex interaction between its elastomeric and glassy phases. To elucidate the role of PU microstructure on its mechanical properties, we developed a finite element modeling framework in which each phase is represented by a volume fraction within a representative volume element (RVE). Critically, we used separate constitutive models to describe the elastomeric and glassy phases. We developed a plasticity-driven breakdown process in which we model the glassy phase disaggregating into a new phase. The overall contribution of each phase at a material point is determined by their respective volume fractions within the RVE. We applied our modeling methods to two compositions of PU with differing elastomeric segment lengths derived from oligoether diamines, Versalink P650 and P1000. Our simulations show that a combination of microstructural differences and elastomeric phase properties accounts for the difference in mechanical response between P650 and P1000. We show our model's ability to predict PU behavior in various loading conditions, including low-rate cyclic loading and monotonic loading over a wide range of strain rates. Our model produces microstructure transformations that mirror those indicated by small-angle X-ray scattering (SAXS) experiments. Fourier transform analysis of our RVEs reveals glassy phase fibrillation due to deformation, a finding consistent with SAXS experiments.

cond-mat.mtrl-sci↗