CANN-EUCLID: unsupervised constitutive artificial neural network model discovery from full-field data
arXiv:2606.14565v1 Announce Type: cross Abstract: Constitutive artificial neural networks (CANNs) provide interpretable material model discovery, but have so far been used in stress-supervised settings based on apparent stress-strain data from homogeneous tests. Because each test samples only a narrow loading path and provides homogenized rather than local stress information, robust discovery typically requires multiple loading modes to constrain the multidimensional response. This is challenging for soft biological tissues, where repeated testing, damage, and sample variability limit reliable
The continuous evolution of AI capabilities, particularly in unsupervised learning and scientific discovery, is enabling new approaches to complex material modeling.
This development allows for more accurate and efficient discovery of constitutive material models, crucial for advanced engineering, biomedicine, and defense applications.
Traditional stress-supervised material model discovery, which is often limited by testing complexity and data granularity, is being augmented or replaced by unsupervised methods leveraging full-field data.
- · Materials science and engineering
- · Biomedical research (e.g., soft biological tissues)
- · AI/ML researchers in scientific discovery
- · Advanced manufacturing
- · Traditional empirical material testing methods
- · Computational models reliant on limited, homogenized data
More precise and predictive digital twins of complex materials will become feasible.
Accelerated development of novel materials with tailored properties for various industries.
Enhanced simulation capabilities could reduce physical prototyping and testing across multiple engineering disciplines, leading to faster innovation cycles and cost reductions.
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.LG