AN INTELLIGENT HYBRID FRAMEWORK FOR REDUCING COMPUTATIONAL COMPLEXITY IN HIGH-DIMENSIONAL OPTIMIZATION
DOI:
https://doi.org/10.9744/duts.13.1.36-51Keywords:
Metaheuristic, Structural Design Optimization, High-dimensional structural analysis, Dimensionality Reduction, ClassifierAbstract
This study proposes a hybrid framework that integrates structural analysis, dimensionality reduction (DR), and metaheuristic algorithms to enhance steel structure design optimization. Structural responses are extracted using ETABS, and high-dimensional design data are reduced via PCA, t-SNE, and deep Autoencoders. Classifiers such as XGBoost, LightGBM, and CatBoost are employed as diagnostic tools to verify that the reduced latent space preserves feasibility boundaries. Optimization is then performed using Particle Swarm Optimization (PSO) and Symbiotic Organisms Search (SOS) to minimize structural weight while meeting code requirements. The framework is validated on benchmark functions and a 20-story braced steel frame, showing that SOS consistently outperforms PSO and that MSE-based Autoencoders achieve superior convergence and solution quality compared to linear or shallow methods. The results highlight DR-integrated metaheuristics as a scalable and effective approach for large-scale optimization. Future work will extend the framework to predictive models and more complex structural systems.
References
1. American Institute of Steel Construction (AISC). (2017). Steel construction manual (15th ed.). Chicago, IL: AISC.
2. Aydoğdu, İ., Saka, M. P., & Hasançebi, O. (2016). Parameter-free metaheuristics for steel design. Advances in Engineering Software, 92, 1–14.
3. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). San Francisco, CA: ACM. https://doi.org/10.1145/2939672.2939785
4. Cheng, M. Y., & Prayogo, D. (2014). Symbiotic organisms search: A new metaheuristic optimization algorithm. Computers & Structures, 139, 98–112. https://doi.org/10.1016/j.compstruc.2014.03.007
5. Gandomi, A. H., Yang, X. S., & Talatahari, S. (2013). Metaheuristic algorithms in structural engineering. London: Springer.
6. Hasançebi, O., Çarbaş, S., Doğan, E., Erdal, F., & Saka, M. P. (2011). Performance evaluation of metaheuristic search techniques in the optimum design of real size pin jointed structures. Computer-Aided Civil and Infrastructure Engineering, 26(2), 135–147.
7. Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing dimensionality with neural networks. Science, 313(5786), 504–507. https://doi.org/10.1126/science.1127647
8. Kaveh, A., & Mahdavi, V. R. (2014). Optimal design of frames using PSO. Advances in Engineering Software, 76, 82–92.
9. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T. Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems (NeurIPS), 30 (pp. 3146–3154).
10. Kennedy, J., & Eberhart, R. (1995). Particle swarm optimization. In Proceedings of the IEEE International Conference on Neural Networks (ICNN) (pp. 1942–1948). Perth, Australia: IEEE. https://doi.org/10.1109/ICNN.1995.488968
11. McInnes, L., Healy, J., & Melville, J. (2018). UMAP: Uniform manifold approximation and projection. Journal of Open-Source Software, 3(29), 861. https://doi.org/10.21105/joss.00861
12. Pearson, K. (1901). On lines and planes of closest fit to systems of points. Philosophical Magazine, 2(11), 559–572. https://doi.org/10.1080/14786440109462720
13. Van der Maaten, L., & Hinton, G. (2008). Visualizing data using t-SNE. Journal of Machine Learning Research, 9, 2579–2605.
14. Yan, A. M., Kerschen, G., De Boe, P., & Golinval, J. C. (2005). Structural damage detection using PCA. Mechanical Systems and Signal Processing, 19(2), 341–356.
15. Zhang, Y., Li, X., Wang, L., & Zhou, Y. (2023). Autoencoder-based surrogate models in structural mechanics. Engineering Structures, 283, 115–232.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Steven Gaillard, Professor
This work is licensed under a Creative Commons Attribution 4.0 International License.
