Deep Operator Network-Based Prediction Algorithm for Analyzing the Frequency Response of Linear Dynamical Systems

Hochul Shin; Jaehun Lee

doi:10.7734/COSEIK.2026.39.4.265

All Issue

2026 Vol.39, Issue 4 Preview Page Next Page

Deep Operator Network-Based Prediction Algorithm for Analyzing the Frequency Response of Linear Dynamical Systems 선형 동적 시스템의 주파수 응답 해석을 위한 심층 연산자 네트워크 기반 예측 알고리즘 응용

31 August 2026. pp. 265-272

PDF XML

Abstract

This paper proposes a deep operator network (DeepONet)-based model for predicting the frequency response of linear dynamic systems. The frequency response is a key quantity that directly reflects the dynamic characteristics of a structure, and its computation requires repeated solutions of the linear system equations at individual frequency points. This procedure incurs significant computational cost for large-scale finite element models and limits applications such as real-time vibration prediction and digital twin implementation. To address this problem, this paper proposes a frequency response prediction framework based on a DeepONet, in which the physical-coordinate response of a structure is transformed into the modal domain and the modal coordinates are predicted from the modal force input. Numerical experiments on a 16-degree-of-freedom mass-spring-damper system demonstrated that the proposed model achieves high prediction accuracy and can serve as an efficient surrogate model for repeated frequency response analyses. These results indicate that the proposed model can be effectively applied to real-time frequency response prediction of large-scale structures and digital twin-based vibration analysis.

Keywords

frequency response

deep operator network

structural dynamics

surrogate model

본 논문에서는 심층 연산자 네트워크를 활용하여 선형 동적 시스템의 주파수 응답을 예측하는 모델을 제안한다. 주파수 응답은 구조물의 동적 특성을 직접적으로 반영하는 핵심 지표로, 이를 계산하기 위해서는 선형 시스템의 반복적인 해석이 필요하다. 이는 대규모 유한요소 모델에서 상당한 계산 비용을 요구하며, 실시간 진동 예측, 디지털 트윈과 같은 응용에 제약으로 작용한다. 이를 해결하기 위해 본 연구에서는 구조물의 물리 좌표계를 모달 영역으로 변환하고, 모달 하중을 입력으로 받아 모드 좌표를 추론하는 심층 연산자 네트워크 기반 구조를 제안한다. 16자유도 질량-스프링-댐퍼 시스템에 대한 수치 실험을 통해 제안된 모델이 높은 정확도를 유지하면서도 빠른 추론 속도를 달성함을 확인하였다. 이러한 결과는 제안하는 모델이 대규모 구조물의 실시간 진동 예측 및 디지털 트윈 구현에 효과적으로 활용될 수 있음을 보여준다.

키워드

주파수 응답

심층 연산자 네트워크

구조 동역학

대체 모델

References

Ahmed, B., Qiu, Y., Abueidda, D.W., El-Sekelly, W., Abdoun, T., Mobasher, M.E. (2025a) Physics-Informed Multiple-Input Operators for Efficient Dynamic Response Prediction of Structures, Eng. Appl. Artif. Intell., 162, 112703.

10.1016/j.engappai.2025.112703

Ahmed, B., Qiu, Y., Abueidda, D.W., El-Sekelly, W., Garcia de Soto, B., Abdoun, T., Mobasher, M.E. (2025b) Physics-Informed Deep Operator Networks with Stiffness-Based Loss Functions for Structural Response Prediction, Eng. Appl. Artif. Intell., 144, 110097.

10.1016/j.engappai.2025.110097

Chen, X., Qu, Z., Wang, Y., Chen, Z., Chen, G., Kang, X., Li, Y. (2025) Prediction of Spectral Response for Explosion Separation Based on DeepONet, Aerospace, 12(4), 310.

10.3390/aerospace12040310

Craig Jr., R.R., Kurdila, A.J. (2006) Fundamentals of Structural Dynamics, 2nd Ed., John Wiley & Sons, Hoboken.

Hesthaven, J.S., Ubbiali, S. (2018) Non-Intrusive Reduced Order Modeling of Nonlinear Problems Using Neural Networks, Journal of Computational Physics, 363, pp.55~78.

10.1016/j.jcp.2018.02.037

Kerschen, G., Golinval, J.C., Vakakis, A.F., Bergman, L.A. (2005) The Method of Proper Orthogonal Decomposition for Dynamical Characterization and Order Reduction of Mechanical Systems: An Overview, Nonlinear Dyn., 41(1-3), pp.147~169.

10.1007/s11071-005-2803-2

Kovachki, N., Li, Z., Liu, B., Azizzadenesheli, K., Bhattacharya, K., Stuart, A.M., Anandkumar, A. (2023) Neural Operator: Learning Maps Between Function Spaces with Applications to PDEs, J. Mach. Learn. Res., 24(89), pp.1~97.

Lee, J., Cho, M. (2018) Efficient Design Optimization Strategy for Structural Dynamic Systems Using a Reduced Basis Method Combined with an Equivalent Static Load, Struct. & Multidiscip. Optim., 58(4), pp.1489~1504.

10.1007/s00158-018-1976-5

Lee, J., Lee, J., Cho, H., Kim, E., Cho, M. (2021) Reduced-Order Modeling of Nonlinear Structural Dynamical Systems via Element-Wise Stiffness Evaluation Procedure Combined with Hyper-Reduction, Comput. Mech., 67(2), pp.523~540.

10.1007/s00466-020-01946-7

Lee, J., Park, Y., Lee, J., Cho, M. (2024) Non-Intrusive Reduced-Order Modeling for Nonlinear Structural Systems via Radial Basis Function-Based Stiffness Evaluation Procedure, Comput. & Struct., 304, 107500.

10.1016/j.compstruc.2024.107500

Liu, E., Hedayatrasa, S., Zhu, Y., Cheng, L. (2024) A Case Study on Vibration Analysis using DeepONet, Proc. 11th European Workshop on Structural Health Monitoring, Media and Publishing Partner.

Lu, L., Jin, P., Pang, G., Zhang, Z., Karniadakis, G.E. (2021a) Learning Nonlinear Operators via DeepONet Based on the Universal Approximation Theorem of Operators, Nature Mach. Intell., 3(3), pp.218~229.

10.1038/s42256-021-00302-5

Lu, L., Meng, X., Cai, S., Mao, Z., Goswami, S., Zhang, Z., Karniadakis, G.E. (2022) A Comprehensive and Fair Comparison of Two Neural Operators (with Practical Extensions) Based on FAIR Data, Comput. Methods Appl. Mech. & Eng., 393, 114778.

10.1016/j.cma.2022.114778

Lu, L., Meng, X., Mao, Z., Karniadakis, G.E. (2021b) DeepXDE: A Deep Learning Library for Solving Differential Equations, SIAM Rev., 63(1), pp.208~228.

10.1137/19M1274067

So, Y., Lee, J. (2025) A Two-Step Sequential Hyper-Reduction Method for Efficient Concurrent Nonlinear FE2 Analyses, Math., 13(11), 1790.

10.3390/math13111790

Tancik, M., Srinivasan, P.P., Mildenhall, B., Fridovich-Keil, S., Raghavan, N., Singhal, U., Ramamoorthi, R., Barron, J.T., Ng, R. (2020) Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains, Adv. Neural Inform. Proc. Syst., 33, pp.7537~7547

van Delden, J., Schultz, J., Blech, C., Langer, S.C., Lüddecke, T. (2024) Learning to Predict Structural Vibrations, Adv. Neural Inform. Proc. Syst., 37, pp.103706~103736.

10.52202/079017-3294

Yang, J., Pavone, M., Wang, Y. (2023) FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization, Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.8254~8263.

10.1109/CVPR52729.2023.00798

Information

Publisher :Computational Structural Engineering Institute of Korea
Publisher(Ko) :한국전산구조공학회
Journal Title :Journal of the Computational Structural Engineering Institute of Korea
Journal Title(Ko) :한국전산구조공학회 논문집
Volume : 39
No :4
Pages :265-272
Received Date : 2026-06-01
Revised Date : 2026-06-04
Accepted Date : 2026-06-05
DOI :https://doi.org/10.7734/COSEIK.2026.39.4.265

Journal of the Computational Structural Engineering Institute of Korea ISSN:1229-3059(Print) 2287-2302(Online) 한국전산구조공학회 논문집

All Issue