SpectONet: A Physics-Guided Spectral Deep Operator Network for Euler-Bernoulli Beam Dynamics
Abstract
This paper proposes a novel physics-guided spectral deep operator network, termed SpectONet, for solving Euler-Bernoulli beam (EBB) vibration problems. The proposed framework integrates the operator-learning capability of DeepONet with physics-informed constraints and Chebyshev-Gauss-Lobatto (CGL) sensor placement. Unlike conventional DeepONet frameworks, which commonly employ uniformly distributed sensors, SpectONet uses nonuniform spectral sensor locations with a higher concentration of points near the domain boundaries. This sampling strategy improves the finite-dimensional representation of boundary-sensitive structural responses while requiring only a limited number of branch-network inputs. The governing beam equation, together with the associated initial and boundary conditions, is incorporated into the training objective to promote physically consistent and generalizable predictions. Numerical experiments on three EBB vibration problems demonstrate the effectiveness of the proposed framework. Comparisons with strong baseline models such as Vanilla DeepONet, PI-DeepONet, PINN, and CNN-UNet show that SpectONet consistently achieves lower prediction errors across all considered evaluation metrics. In particular, SpectONet achieves an average reduction of approximately 79% in the mean relative ℒ2 error compared with the best-performing baseline across the three benchmark problems. These results demonstrate the effectiveness of SpectONet as an accurate physics-guided operator-learning framework for structural vibration analysis.
Related
- Riemann Hypothesis as a Physical Law: Operator‑Spectral Reconstruction of Time from Zeta Zero Dynamics
- A periodic Anderson--Bernoulli model with infinitely many spectral gaps
- Preconditioned Physics-Informed Neural Operator Training
- Inverse spectral results for the magnetic Schrödinger operator in low dimensions
- Elementary cellular automata: spectral properties of Koopman operator for finite periodic realizations
BibTeX
@misc{saini2026spectonet,
title = {{SpectONet: A Physics-Guided Spectral Deep Operator Network for Euler-Bernoulli Beam Dynamics}},
author = {Shivani Saini and Ramesh Kumar Vats and Arup Kumar Sahoo},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2607.25790},
eprint = {2607.25790},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.25790},
}
RIS
TY - UNPB
TI - SpectONet: A Physics-Guided Spectral Deep Operator Network for Euler-Bernoulli Beam Dynamics
AU - Shivani Saini
AU - Ramesh Kumar Vats
AU - Arup Kumar Sahoo
PY - 2026
DA - 2026/10/25
PB - arXiv
DO - 10.48550/arxiv.2607.25790
UR - https://arxiv.org/abs/2607.25790
AB - This paper proposes a novel physics-guided spectral deep operator network, termed SpectONet, for solving Euler-Bernoulli beam (EBB) vibration problems. The proposed framework integrates the operator-learning capability of DeepONet with physics-informed constraints and Chebyshev-Gauss-Lobatto (CGL) sensor placement. Unlike conventional DeepONet frameworks, which commonly employ uniformly distributed sensors, SpectONet uses nonuniform spectral sensor locations with a higher concentration of points near the domain boundaries. This sampling strategy improves the finite-dimensional representation of boundary-sensitive structural responses while requiring only a limited number of branch-network inputs. The governing beam equation, together with the associated initial and boundary conditions, is incorporated into the training objective to promote physically consistent and generalizable predictions. Numerical experiments on three EBB vibration problems demonstrate the effectiveness of the proposed framework. Comparisons with strong baseline models such as Vanilla DeepONet, PI-DeepONet, PINN, and CNN-UNet show that SpectONet consistently achieves lower prediction errors across all considered evaluation metrics. In particular, SpectONet achieves an average reduction of approximately 79% in the mean relative ℒ_2 error compared with the best-performing baseline across the three benchmark problems. These results demonstrate the effectiveness of SpectONet as an accurate physics-guided operator-learning framework for structural vibration analysis.
ER -