← Back to all news
arXiv Machine Learning By Miriam Goldack, Johann Gro{\ss}, Malte Krack, Merten Stender

AFT Neural Function Approximators for 1D Nonlinear Force Laws

Read the original on arXiv Machine Learning →

The paper proposes using neural networks to replace the iterative force evaluation in the harmonic balance method for systems with nonlinear contacts and friction. These networks map displacement Fourier coefficients directly to nonlinear force coefficients and supply Jacobians via automatic differentiation, allowing the existing solver and continuation algorithms to remain unchanged. By learning individual nonlinear elements—such as cubic, unilateral, and Jenkins springs—under physics‑based nondimensionalization and phase normalization, a single trained network can handle a wide range of parameters, enabling a reusable library of nonlinear‑element surrogates for complex mechanical systems.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 10

Hyperelastic constitutive model discovery with differentiable finite elements and structure-preserving neural networks

The paper introduces a differentiable finite element framework that discovers hyperelastic constitutive laws from limited experimental data, such as boundary-only displacement measurements and global reaction forces. By embedding the nonlinear finite element equilibrium problem into the learning loop, the method evaluates candidate strain‑energy densities through the deformation fields they produce, enforcing mechanical equilibrium as a constraint. The constitutive response is modeled with Hyperelastic Neural Networks, a structure‑preserving class that guarantees physical admissibility, including residual energy and stress‑free conditions, frame indifference, isotropic symmetry, polyconvexity, coercivity, and controlled volumetric growth. Numerical experiments in two and three dimensions show accurate recovery of hyperelastic isotropic responses, robustness to noise, and generalization across geometries, loading, and boundary conditions.

By Francesco Regazzoni
More like this →
arXiv AI
Jun 6

Finite Element-Based Material Learning via Automatic Differentiation: Learning constitutive neural network models from full-field deformation data

arXiv:2606. 05199v1 Announce Type: cross Abstract: The identification of constitutive neural network models from heterogeneous full-field deformation data provides a robust alternative to traditional calibration methods based on homogeneous stress-strain experiments, particularly given the high dimensionality of trainable parameters.

By Matthias Knipper, Chenyi Ji, Malte Brand, Kevin Linka
More like this →
arXiv Machine Learning
Sep 15

Linearized PINN with pretrained nonlinear layers

The paper introduces a linearized Physics-Informed Neural Network (lPINN), a reduced‑order neural basis approach for solving forward and inverse differential equations. In an offline phase, lPINN learns continuous, differentiable neural basis functions from numerical solutions, which are then frozen for new problem instances; the online solution is obtained by minimizing the governing‑equation residual with additional constraints. Experiments on advection‑diffusion, Burgers', and nonlinear pendulum equations show that lPINN achieves lower solution and parameter errors than vanilla PINNs while reducing online inference times by up to three orders of magnitude, and its continuous representation generalizes to finer meshes without retraining.

By Wenhao Chen, Alexandre M. Tartakovsky
diffusion
More like this →
arXiv Machine Learning
Jun 19

A Hybrid GNN-FEM Framework for Phase-Field Fracture Simulation. Physics-Preserving Hybridization for Generalizable Surrogate Modeling

arXiv:2606. 19378v1 Announce Type: new Abstract: Scientific machine learning (SciML) has emerged as a promising approach for accelerating simulations of complex physical systems, yet achieving physically consistent and generalizable predictions for nonlinear, history-dependent problems remains a central challenge.

By Hyeonbin Moon, Yongjin Choi, Seunghwa Ryu
More like this →