Inelastic Constitutive Kolmogorov-Arnold Networks: A generalized framework for automated discovery of interpretable inelastic material models
arXiv:2602.17750v2 Announce Type: replace-cross Abstract: A key problem of solid mechanics is the identification of the constitutive law of a material, that is, the relation between strain history and stress. Machine learning has lead to considerable advances in this field lately. Here we introduce inelastic Constitutive Kolmogorov-Arnold Networks (iCKANs). This novel artificial neural network architecture can discover in an automated manner symbolic constitutive laws describing both the elastic and inelastic behavior of materials. That is, it can translate data from material testing into corr
The convergence of advanced AI architectures and the increasing availability of material testing data is enabling novel applications in materials science.
This development could significantly accelerate the discovery and optimization of new materials by automating the generation of complex, interpretable constitutive models, which are fundamental to engineering and design.
The process of identifying and modeling material properties, traditionally time-consuming and empirical, could become significantly faster, more automated, and more precise through AI-driven symbolic discovery.
- · Materials scientists and engineers
- · Manufacturing industries
- · Aerospace and automotive sectors
- · AI/ML research in scientific discovery
- · Traditional, manual constitutive modeling methods
- · Companies slow to adopt AI in R&D
Automated discovery of symbolic constitutive laws for inelastic materials will accelerate material design and understanding.
This could lead to a faster introduction of novel materials with enhanced properties across various industries, from composites to extreme-environment alloys.
The reduced time and cost of material development could democratize access to advanced materials, potentially shifting supply chains and industrial leadership.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI