{"slug": "physics-informed-discovery-of-yield-functions-in-plasticity-via-convex-neural", "title": "Physics-Informed Discovery of Yield Functions in Plasticity via Convex Neural Representations", "summary": "Researchers propose a physics-informed framework to discover anisotropic yield functions from full-field displacement and reaction force data, using a convex neural network representation. The method avoids direct stress observations or prescribed parametric forms, validated on FE benchmarks with von Mises, Hill 1948, and Yld2000-2d yield functions. This enables data-driven identification of yield surfaces while enforcing mechanical constraints.", "body_md": "arXiv:2606.19375v1 Announce Type: new\nAbstract: 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 the yield function as a mechanically constrained constitutive component inside elastoplastic stress integration, rather than through direct stress-space supervision. The yield function is represented by a convex neural network that enforces convexity and positive homogeneity of degree one while imposing the assumed tension-compression symmetry, and this neural yield function is trained with a differentiable stress update and a physics-informed force equilibrium loss across multiple loading cases. The proposed framework is validated using finite element (FE) benchmark studies with von Mises, Hill 1948, and Yld2000-2d yield functions, assessing yield contour agreement, displacement-noise sensitivity, identifiability through plastically active stress states, epistemic uncertainty, and polynomial-surrogate deployment. This study provides a mechanics-constrained pathway for discovering anisotropic yield functions from displacement and force data while keeping the identified component within the structure of elastoplastic stress integration.", "url": "https://wpnews.pro/news/physics-informed-discovery-of-yield-functions-in-plasticity-via-convex-neural", "canonical_source": "https://arxiv.org/abs/2606.19375", "published_at": "2026-06-19 04:00:00+00:00", "updated_at": "2026-06-19 04:08:44.956211+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks", "ai-research"], "entities": ["arXiv", "von Mises", "Hill 1948", "Yld2000-2d"], "alternates": {"html": "https://wpnews.pro/news/physics-informed-discovery-of-yield-functions-in-plasticity-via-convex-neural", "markdown": "https://wpnews.pro/news/physics-informed-discovery-of-yield-functions-in-plasticity-via-convex-neural.md", "text": "https://wpnews.pro/news/physics-informed-discovery-of-yield-functions-in-plasticity-via-convex-neural.txt", "jsonld": "https://wpnews.pro/news/physics-informed-discovery-of-yield-functions-in-plasticity-via-convex-neural.jsonld"}}