AFT Neural Function Approximators for 1D Nonlinear Force Laws
Abstract
Nonlinear contacts and friction strongly influence the vibration response of assembled structures, but their accurate numerical treatment is computationally demanding. The harmonic balance method is widely used to compute periodic steady-state responses, yet the required alternating frequency-time scheme becomes costly for nonsmooth and hysteretic nonlinearities and must be repeated throughout the nonlinear solution process. Here we show that this procedure can be replaced by neural networks that directly map displacement Fourier coefficients to nonlinear force coefficients and provide the corresponding Jacobian through automatic differentiation. The surrounding solver and continuation algorithms remain unchanged for the computation of frequency response curves. The neural networks exclusively learn individual nonlinear elements rather than complete system responses. Physics-based nondimensionalization and phase normalization facilitate the learning process and enable a single trained network to cover a wide range of parameter combinations. Building on the cubic spring, unilateral spring, and Jenkins elements considered here, the approach points toward a reusable library of nonlinear-element surrogates that can be combined in arbitrary number and location within a mechanical system. By bypassing the iterative force evaluation in time domain, the method offers favorable computational scaling for high-resolution analyses and systems with many nonlinear elements.
Related
- Noether symmetries and conservation laws of a class of time-dependent multidimensional nonlinear wave equations
- A class of high-order discontinuous-Galerkin methods satisfying infinitely many entropy conditions with provable error estimates and strong convergence for general nonlinear conservation laws
- Nonlinear Darcy Laws for Generalized Newtonian Fluids with Orlicz Growth and Oscillating Navier Slip in Periodic Porous Media
- Exact Tail Laws for Nonlinear SGD with Infinite-Variance Gradients
- Weakly nonlinear dynamics of follower-force-induced oscillations in Cosserat rods
BibTeX
@misc{goldack2026neural,
title = {{AFT Neural Function Approximators for 1D Nonlinear Force Laws}},
author = {Miriam Goldack and Johann Groß and Malte Krack and Merten Stender},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.29242},
eprint = {2609.29242},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.29242},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - AFT Neural Function Approximators for 1D Nonlinear Force Laws
AU - Miriam Goldack
AU - Johann Groß
AU - Malte Krack
AU - Merten Stender
PY - 2026
DA - 2026/09/24
PB - arXiv
DO - 10.48550/arxiv.2609.29242
UR - https://arxiv.org/abs/2609.29242
AB - Nonlinear contacts and friction strongly influence the vibration response of assembled structures, but their accurate numerical treatment is computationally demanding. The harmonic balance method is widely used to compute periodic steady-state responses, yet the required alternating frequency-time scheme becomes costly for nonsmooth and hysteretic nonlinearities and must be repeated throughout the nonlinear solution process. Here we show that this procedure can be replaced by neural networks that directly map displacement Fourier coefficients to nonlinear force coefficients and provide the corresponding Jacobian through automatic differentiation. The surrounding solver and continuation algorithms remain unchanged for the computation of frequency response curves. The neural networks exclusively learn individual nonlinear elements rather than complete system responses. Physics-based nondimensionalization and phase normalization facilitate the learning process and enable a single trained network to cover a wide range of parameter combinations. Building on the cubic spring, unilateral spring, and Jenkins elements considered here, the approach points toward a reusable library of nonlinear-element surrogates that can be combined in arbitrary number and location within a mechanical system. By bypassing the iterative force evaluation in time domain, the method offers favorable computational scaling for high-resolution analyses and systems with many nonlinear elements.
ER -