Options
Constitutive Kolmogorov–Arnold Networks (CKANs): Combining accuracy and interpretability in data-driven material modeling
Citation Link: https://doi.org/10.15480/882.15357
Publikationstyp
Journal Article
Date Issued
2025-10-01
Sprache
English
TORE-DOI
Volume
203
Article Number
106212
Citation
Journal of the Mechanics and Physics of Solids 203: 106212 (2025)
Publisher DOI
Scopus ID
Publisher
Elsevier
Hybrid constitutive modeling integrates two complementary approaches for describing and predicting a material's mechanical behavior: purely data-driven black-box methods and physically constrained, theory-based models. While black-box methods offer high accuracy, they often lack interpretability and extrapolability. Conversely, physics-based models provide theoretical insight and generalizability but may not capture complex behaviors with the same accuracy. Traditionally, hybrid modeling has required a trade-off between these aspects. In this paper, we show how recent advances in symbolic machine learning — specifically Kolmogorov–Arnold Networks (KANs) — help to overcome this limitation. We introduce Constitutive Kolmogorov–Arnold Networks (CKANs) as a new class of hybrid constitutive models. By incorporating a post-processing symbolification step, CKANs combine the predictive accuracy of data-driven models with the interpretability and extrapolation capabilities of symbolic expressions, bridging the gap between machine learning and physical modeling.
Subjects
Constitutive Artificial Neural Networks
Data-driven mechanics
Interpretable machine learning
Kolmogorov–Arnold Networks
Physics-informed machine learning
Soft materials
Symbolic regression
DDC Class
620.1: Engineering Mechanics and Materials Science
006.3: Artificial Intelligence
Publication version
publishedVersion
Loading...
Name
1-s2.0-S0022509625001887-main.pdf
Size
3.21 MB
Format
Adobe PDF