PREDICTIVE REANALYSIS IN STRUCTURAL DYNAMICS

10th International Congress of the Serbian Society of Mechanics (18-20. 06. 2025, Niš) [pp. 159-166]

AUTHOR(S) / AUTOR(I): Nataša R. Trišović , Tamas Mankovits , Ana S. Petrović

Download Full Pdf   

DOI: 10.46793/ICSSM25.159T

ABSTRACT / SAŽETAK:

Predictive reanalysis has emerged as a vital computational strategy in structural dynamics, enabling efficient updates of structural response predictions following minor modifications in geometry, material properties, or boundary conditions, without resorting to full re-computation. Traditionally rooted in finite element methods, reanalysis techniques have evolved through the integration of Artificial Intelligence (AI) models, offering unprecedented speed and adaptability in dynamic system assessments. This paper provides a comprehensive overview of predictive reanalysis approaches, with an emphasis on recent AI-assisted methodologies. The synergy between data-driven models such as neural networks, decision trees and ensemble learning and physics-based simulations enables more accurate prediction of structural behavior under varying operational scenarios. The application of machine learning has demonstrated significant potential in reducing computational costs, increasing adaptability and enhancing real-time monitoring capabilities in engineering systems. A numerical case study is presented, involving a cantilever beam discretized into five finite elements. The analysis explores how changes in cross-sectional properties at various segments affect the first natural frequency. Predictive AI models are employed to estimate frequency shifts and their performance is compared against classical empirical formulas. The results validate the ability of trained AI models to generalize the influence of structural variations and support decision-making in early design or maintenance phases. The study also highlights current challenges in predictive reanalysis, including data scarcity, model interpretability and integration with real-time monitoring systems. Future directions are outlined, focusing on hybrid modeling techniques, improved data acquisition strategies and the development of standardized benchmarks for AI-assisted structural reanalysis. Ultimately, this work contributes to the growing body of research bridging computational mechanics and machine intelligence, fostering more resilient, adaptive and efficient structural systems.

KEYWORDS / KLJUČNE REČI:

natural frequency estimation, predictive reanalysis, artificial intelligence, FEM, structural dynamic

ACKNOWLEDGEMENT / PROJEKAT:

This research is supported by the Ministry of Science, Technological Development and Innovation of the Republic of Serbia, under the 2024 Agreement on Financing Scientific Research, No. 451-03-137/2025- 03/200105, dated February 4, 2025, Serbian-Hungarian Bilateral Cooperation for the Years 2025-2026: Structural optimization of additively manufactured cellular titanium implant using artificial intelligence. Additional support provided by COST (European Cooperation in Science and Technology) CA21155, CA23138, CA23109 and CA21106.

REFERENCES / LITERATURA:

  • Paridie, A. M., Ene, N. M., Mohamed, Y. S. (2022). Using neural networks to predict the effect of the preload location on the natural frequencies of a cantilever beam. Heliyon, 8(11), e11242. https://doi.org/10.1016/j.heliyon.2022.e11242
  • Cynthia, P., Ismanto, E., Arifandy, M. I., Sarbaini, S., Nazaruddin, N., Manuhutu, M. A., Akbar, M. A., Abdiyanto. (2022). Convolutional neural network and deep learning approach for image detection and identification. Journal of Physics: Conference Series, 2394(1), 012019. https://doi.org/10.1088/1742-6596/2394/1/012019
  • Rochefort-Beaudoin, , Vadean, A., Aage, N., Achiche, S. (2024). Structural design through reinforcement learning (arXiv:2407.07288). https://arxiv.org/abs/2407.07288
  • Bathe, J. (1982). Finite Element Procedures in Engineering Analysis. Prentice-Hall.
  • Sergeyev, O., Mroz, (2000). Sensitivity analysis and optimal design of 3D frame structures for stress and frequency constraints. Computers and Structures, 75(2), 167–185.
  • Tong, W. , Jiang, J. S., Liu, G. R. (2000). Solution existence of the optimization problem of truss structure with frequency constraints. International Journal of Solids and Structures, 37(30), 4043– 4060.
  • Siam, A., Ezzeldin, M., El-Dakhakhni, W. (2019). Machine learning algorithms for structural performance classifications and predictions: Application to reinforced masonry shear walls. Structures, 22, 252–265. https://doi.org/10.1016/j.istruc.2019.06.017
  • Thai, -T. (2022). Machine learning for structural engineering: A state-of-the-art review. Structures, 38, 448–491. https://doi.org/10.1016/j.istruc.2022.02.003
  • Shi, (2020). Enabling smart dynamical downscaling of extreme precipitation events with machine learning. Geophysical Research Letters, 47(19), e2020GL090309. https://doi.org/10.1029/2020GL090309
  • Mansour, , Fischer, G., Haensch, R., Hajnsek, I. (2025). Hybrid AI-physical modeling for penetration bias correction in X-band InSAR DEMs: A Greenland case study. arXiv. https://doi.org/10.48550/arXiv.2504.08909
  • Feng, , Wang, C., Briseghella, B., Fenu, L., Zordan, T. (2020). Structural optimization of a steel arch bridge with genetic algorithm. Structural Engineering International, 31(3), 347-356. https://doi.org/10.1080/10168664.2020.1773373
  • Brown, K., Garland, A. P., Fadel, G. M., Li, G. (2022). Deep reinforcement learning for engineering design through topology optimization of elementally discretized design domains. Materials & Design, 218, 110672. https://doi.org/10.1016/j.matdes.2022.110672
  • Nguyen, -H., Tuan, V. A. (2020). Application of artificial intelligence for structural optimization. In The International Conference on Modern Mechanics and Applications ICOMMA 2020 (pp. 82). https://doi.org/10.1007/978-981-16-3239-6_82
  • Zhou, J., Zhang, , & Qiu, Y. (2024). State-of-the-art review of machine learning and optimization algorithms applications in environmental effects of blasting. Artificial Intelligence Review, 57(5). https://doi.org/10.1007/s10462-023-10636-8
  • Ereiz, S., Duvnjak, , & Jiménez-Alonso, J. F. (2022). Review of finite element model updating methods for structural applications. Structures, 41, 684–723. https://doi.org/10.1016/j.istruc.2022.05.041
  • Lee, Y., Kim, , Min, S., et al. (2023). Structural damage detection using deep learning and FE model updating techniques. Scientific Reports, 13, 18694. https://doi.org/10.1038/s41598-023-46141-9
  • Ghadge, , Ghorpade, R., & Joshi, S. (2022). Multi-disciplinary design optimization of composite structures: A review. Composite Structures, 280, 114875. https://doi.org/10.1016/j.compstruct.2021.114875
  • Trišović, N. (2007). Developed procedure for dynamic reanalysis of structures. PhD Thesis, FMEUB, Belgrade