Physics-Informed Discovery of Yield Functions in Plasticity via Convex Neural Representations
arXiv:2606.19375v1 Announce Type: new Abstract: Identifying anisotropic yield functions remains challenging since yielding is not directly observed in full-field mechanical measurements, directional calibration can require many loading directions, and selecting an appropriate analytical form is nontrivial. This study proposes a physics-informed framework for discovering yield functions from full-field displacement data and reaction force data, without stress observations, plastic strain measurements, direct yield surface data, or a prescribed parametric yield function. The framework identifies
Advances in AI, particularly physics-informed neural networks, are enabling more sophisticated material science discoveries without extensive direct experimental data. The increasing availability of full-field measurement data also contributes to this development.
This development could significantly accelerate the design and understanding of new materials with specific mechanical properties, reducing development costs and timelines across various engineering and manufacturing sectors. It opens new avenues for material innovation crucial for demanding applications.
Material scientists and engineers will have more efficient tools to characterize and predict material behavior, moving away from laborious, expensive, and often destructive empirical testing. This implies faster iteration cycles for material development in industries like aerospace, automotive, and defense.
- · Material Science R&D
- · Aerospace Industry
- · Automotive Industry
- · Manufacturing
- · Traditional materials testing labs (less complex testing)
- · Companies reliant on slow empirical material discovery
Faster and more efficient discovery of novel materials with specific mechanical properties.
Reduced material development costs and shortened time-to-market for advanced products across multiple industries.
Enhanced product performance and durability in sectors like defence and infrastructure, driven by optimized material selection and design.
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