AI & ML
A locking-free enriched linearized neural network for linear elasticity
arXiv cs.NA0 views
arXiv:2611.22398v1 Announce Type: new Abstract: Neural-network Galerkin methods suffer from volumetric locking in nearly incompressible elasticity. We propose the locking-free enriched linearized neural network (LF-ENN), to the best of our knowledge, the first neural-network Galerkin method proved to be locking-free. Following the enriched Galerkin (EG) method of Yi, Lee and Zikatanov (2022), for finite $\lambda$ it admits a displacement-only formulation whose trial space is a linearized neural network enriched by one dilation field per element of an auxiliary mesh. The parameter $\lambda$ enters only through a piecewise constant discrete divergence, whose action on the dilation fields is the graph Laplacian of the dual graph of the mesh. Hence any conforming field can be made discretely divergence-free, and the error is bounded independently of $\lambda\in(0,\infty]$. The network needs no boundary factor: the Dirichlet condition is imposed weakly by Nitsche's method, and a Galerkin least-squares term on the shear part, as in ENN, together with a Hessian penalty on the elements along the traction boundary, replaces the trace inequality that networks lack. Under the stated approximation and quasi-uniformity assumptions, the discrete stability and error-estimate constants are independent of network width, mesh size, and $\lambda$, for both clamped and mixed boundary conditions. For solutions with reduced regularity, we establish an error estimate of order $h^s$ under the assumptions $u\in H^{1+s}(\Omega)^d$ and $p\in H^s(\Omega)$, with $s>1/2$. Numerical experiments, including Cook's membrane, demonstrate the effectiveness of the method in the presence of boundary singularities.
Source:https://arxiv.org/abs/2611.22398PreviousNonlocal regularization of sharp-crack energetics: a variational bridge from Griffith geometry to emergent constitutive degradationNextLocking-free numerical methods for poroelasticity optimal control problems with minimal regularities
Related posts

Parallels Desktop review
0TechRadar
How Far Behind Are Open Weights, Measured
0dev.to
Claude was trained on protein sequences at scale
0Hacker News
Pretraining vs post-training: one apple problem, four learning signals
0dev.to Beginners
Bitcoin Recovery Expert USA: Professional Crypto Asset Recovery with META TECH RETRIEVE PRO
0dev.to Beginners
Hugging Face Switches Its Inference Providers to OpenRouter Routing
0dev.to OpenSource