A hierarchy of physics-embedded neural operators for structural dynamic surrogate modelingA hierarchy of physics-embedded neural operators for structural dynamic surrogate modeling
Abstract
Structural-response surrogates must capture moving resonances, phase changes, and unequal-amplitude transfer channels during optimization or health-state changes. Physics-embedded learning seeks FEA-level accuracy at lower cost by embedding physics in inputs, forward passes, losses, and backpropagation. We propose Modal Rational (MR), mapping structural features to modal quantities for analytical frequency-response reconstruction. The Physics-Guided Modal Operator Network (PGMON) adds bounded frequency, damping, and residual-flexibility corrections. Modal Operator with Structural GELU and Anchored-SIREN Correction (MOSAIC) denotes the bounded spectral-discrepancy framework used here; MOSAIC-MR and MOSAIC-PGMON add such discrepancies. They support finite-dimensional maps and physical decoders for future neural operators; evidence is fixed-topology, not a completed operator comparison. Two 20,000-design populations are studied: an 80 m steel truss tower with variable member areas and attached masses, and a tapered shell beam with ten variable station masses. Archived tests cover ten designs and seven acceleration histories per structure; they are benchmarks, not seismic-design assessments. With 5% reference modal damping, MR, PGMON, and MOSAIC give mean displacement-history errors of 0.73-0.76% for the tower and 0.029-0.116% for the beam, against declared band-limited modal references. Supplied modal frequencies are distinguished from design-only use; unequal parameter counts and training settings are explicit. Error analysis separates learned modal discrepancies, truncation, and excitation weighting, explaining acceleration and difficult-tower limits and risks of blind use. Results support physically structured prediction but limit claims about generalization, computational savings, and added corrections. Next is developing and validating neural operators around these architectures.
Related
- Anchored Regularized Direct Least Squares (ARDLS): Integrating Established Prioritization Operators for Priority Elicitation in the Analytic Hierarchy Process
- A new hierarchy for automaton semigroups
- Interpolation in the Inquisitive Hierarchy
- Comment on "The polarization hierarchy for polynomial optimization over convex bodies, with applications to nonnegative matrix rank"
- Fredholm determinant solutions to the modified KP hierarchy and 2D Toda lattice: isospectral and non-isospectral reductions
BibTeX
@misc{ansrollahi2026hierarchy,
title = {{A hierarchy of physics-embedded neural operators for structural dynamic surrogate modelingA hierarchy of physics-embedded neural operators for structural dynamic surrogate modeling}},
author = {Amir Ansrollahi and Mehmet Sefa Orak},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.07059},
eprint = {2611.07059},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.07059},
}
RIS
TY - UNPB
TI - A hierarchy of physics-embedded neural operators for structural dynamic surrogate modelingA hierarchy of physics-embedded neural operators for structural dynamic surrogate modeling
AU - Amir Ansrollahi
AU - Mehmet Sefa Orak
PY - 2026
DA - 2026/11/04
PB - arXiv
DO - 10.48550/arxiv.2611.07059
UR - https://arxiv.org/abs/2611.07059
AB - Structural-response surrogates must capture moving resonances, phase changes, and unequal-amplitude transfer channels during optimization or health-state changes. Physics-embedded learning seeks FEA-level accuracy at lower cost by embedding physics in inputs, forward passes, losses, and backpropagation. We propose Modal Rational (MR), mapping structural features to modal quantities for analytical frequency-response reconstruction. The Physics-Guided Modal Operator Network (PGMON) adds bounded frequency, damping, and residual-flexibility corrections. Modal Operator with Structural GELU and Anchored-SIREN Correction (MOSAIC) denotes the bounded spectral-discrepancy framework used here; MOSAIC-MR and MOSAIC-PGMON add such discrepancies. They support finite-dimensional maps and physical decoders for future neural operators; evidence is fixed-topology, not a completed operator comparison. Two 20,000-design populations are studied: an 80 m steel truss tower with variable member areas and attached masses, and a tapered shell beam with ten variable station masses. Archived tests cover ten designs and seven acceleration histories per structure; they are benchmarks, not seismic-design assessments. With 5% reference modal damping, MR, PGMON, and MOSAIC give mean displacement-history errors of 0.73-0.76% for the tower and 0.029-0.116% for the beam, against declared band-limited modal references. Supplied modal frequencies are distinguished from design-only use; unequal parameter counts and training settings are explicit. Error analysis separates learned modal discrepancies, truncation, and excitation weighting, explaining acceleration and difficult-tower limits and risks of blind use. Results support physically structured prediction but limit claims about generalization, computational savings, and added corrections. Next is developing and validating neural operators around these architectures.
ER -