Saved in:
Bibliographic Details
Main Authors: Thakolkaran, Prakash, Guo, Yaqi, Saini, Shivam, Peirlinck, Mathias, Alheit, Benjamin, Kumar, Siddhant
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.05617
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915323131723776
author Thakolkaran, Prakash
Guo, Yaqi
Saini, Shivam
Peirlinck, Mathias
Alheit, Benjamin
Kumar, Siddhant
author_facet Thakolkaran, Prakash
Guo, Yaqi
Saini, Shivam
Peirlinck, Mathias
Alheit, Benjamin
Kumar, Siddhant
contents Traditional constitutive models rely on hand-crafted parametric forms with limited expressivity and generalizability, while neural network-based models can capture complex material behavior but often lack interpretability. To balance these trade-offs, we present monotonic Input-Convex Kolmogorov-Arnold Networks (ICKANs) for learning polyconvex hyperelastic constitutive laws. ICKANs leverage the Kolmogorov-Arnold representation, decomposing the model into compositions of trainable univariate spline-based activation functions for rich expressivity. We introduce trainable monotonic input-convex splines within the KAN architecture, ensuring physically admissible polyconvex models for isotropic compressible hyperelasticity. The resulting models are both compact and interpretable, enabling explicit extraction of analytical constitutive relationships through a monotonic input-convex symbolic regression technique. Through unsupervised training on full-field strain data and limited global force measurements, ICKANs accurately capture nonlinear stress-strain behavior across diverse strain states. Finite element simulations of unseen geometries with trained ICKAN hyperelastic constitutive models confirm the framework's robustness and generalization capability.
format Preprint
id arxiv_https___arxiv_org_abs_2503_05617
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can KAN CANs? Input-convex Kolmogorov-Arnold Networks (KANs) as hyperelastic constitutive artificial neural networks (CANs)
Thakolkaran, Prakash
Guo, Yaqi
Saini, Shivam
Peirlinck, Mathias
Alheit, Benjamin
Kumar, Siddhant
Machine Learning
Traditional constitutive models rely on hand-crafted parametric forms with limited expressivity and generalizability, while neural network-based models can capture complex material behavior but often lack interpretability. To balance these trade-offs, we present monotonic Input-Convex Kolmogorov-Arnold Networks (ICKANs) for learning polyconvex hyperelastic constitutive laws. ICKANs leverage the Kolmogorov-Arnold representation, decomposing the model into compositions of trainable univariate spline-based activation functions for rich expressivity. We introduce trainable monotonic input-convex splines within the KAN architecture, ensuring physically admissible polyconvex models for isotropic compressible hyperelasticity. The resulting models are both compact and interpretable, enabling explicit extraction of analytical constitutive relationships through a monotonic input-convex symbolic regression technique. Through unsupervised training on full-field strain data and limited global force measurements, ICKANs accurately capture nonlinear stress-strain behavior across diverse strain states. Finite element simulations of unseen geometries with trained ICKAN hyperelastic constitutive models confirm the framework's robustness and generalization capability.
title Can KAN CANs? Input-convex Kolmogorov-Arnold Networks (KANs) as hyperelastic constitutive artificial neural networks (CANs)
topic Machine Learning
url https://arxiv.org/abs/2503.05617