New AI framework automates discovery of interpretable material models

Researchers have developed a novel artificial neural network architecture called inelastic Constitutive Kolmogorov-Arnold Networks (iCKANs) designed to automate the discovery of interpretable material models. This framework can translate material testing data into symbolic constitutive laws, capturing both elastic and inelastic behaviors in closed mathematical form. The iCKANs architecture has demonstrated its ability to accurately model complex viscoelastic properties of polymers like VHB 4910 and VHB 4905, while maintaining physical interpretability and the capacity to incorporate additional material information such as temperature-dependent behavior. AI

IMPACT This AI framework could accelerate the development of new materials by automating the discovery of their constitutive laws.

RANK_REASON The cluster contains an academic paper detailing a new AI methodology for material science. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Chenyi Ji
• inelastic Constitutive Kolmogorov-Arnold Networks
• Kolmogorov-Arnold Networks
• VHB 4905
• VHB 4910

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →