Revisiting Classical Neural Architectures for Surrogate-Assisted Optimization of Space Trusses: Balancing Prediction Accuracy and Computational Efficiency

Authors

https://doi.org/10.48314/ijrceai.v2i3.51

Abstract

The optimization of trusses usually demands a number of structural analyses which leads to substantial computation cost and execution time, especially in case of large problems. Artificial Neural Networks (ANNs) have been proved as the effective surrogates for approximation of structural responses with acceptable accuracy and relatively low computational efforts. In this study, the efficacy of two different types of neural networks, Backpropagation Neural Network (BPNN) and Counterpropagation Neural Network (CPN), for the optimization of weights of truss structures is examined. The 52 membered space truss is used as the test problem where cross sections are used as the input data and the stresses of members as the outputs in order to train the neural networks. The performances of the models in respect of their accuracy and computational costs are investigated. It is found that whereas the backpropagation model performs better in respect of accuracy, the counterpropagation model performs much better in terms of the speed of the learning and computational costs. It is demonstrated that the proposed method is able to provide the capability of the surrogate modeling approach based on neural network models in accelerating the structural optimization process and minimizing the burden of the repetitive finite element.   

Keywords:

Structural optimization, Truss structures, Artificial neural networks, Backpropagation neural network, Counterpropagation neural network, Surrogate modeling

References

  1. [1] Vanderplaats, G. N. (2005). Numerical optimization techniques for engineering design. Vanderplaats Research and Development. https://books.google.com/books?id=F6yOOwAACAAJ
  2. [2] Arora, J. S. (2016). Introduction to optimum design. Academic Press. https://books.google.com/books?id=h-9eBwAAQBAJ
  3. [3] Rao, S. S. (2019). Engineering optimization: Theory and practice. John Wiley & Sons. https://doi.org/10.1002/9781119454816
  4. [4] Kaveh, A. (2014). Advances in metaheuristic algorithms for optimal design of structures. Springer. https://doi.org/10.1007/978-3-319-46173-1
  5. [5] Deb, K. (2001). Multi-objective optimization using evolutionary algorithms. Wiley. https://books.google.com/books?id=OSTn4GSy2uQC
  6. [6] Haykin, S. S. (2009). Neural networks and learning machines. Pearson. https://books.google.com/books?id=KCwWOAAACAAJ
  7. [7] Adeli, H. (1999). Machine learning ‐ neural networks, genetic algorithms and fuzzy systems. Kybernetes, 28(3), 317–318. https://doi.org/10.1108/k.1999.28.3.317.5
  8. [8] Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural networks, 2(5), 359–366. https://doi.org/10.1016/0893-6080(89)90020-8
  9. [9] Bishop, C. M. (1995). Neural networks for pattern recognition. Oxford university press. https://www.researchgate.net/publication/215721451
  10. [10] Kaveh, A., & Iranmanesh, A. (1998). Comparative study of backpropagation and improved counterpropagation neural nets in structural analysis and optimization. International journal of space structures, 13(4), 177–185. https://doi.org/10.1177/026635119801300401
  11. [11] Papadrakakis, M., Lagaros, N. D., & Tsompanakis, Y. (1998). Structural optimization using evolution strategies and neural networks. Computer methods in applied mechanics and engineering, 156(1), 309–333. https://doi.org/10.1016/S0045-7825(97)00215-6
  12. [12] Mai, H. T., Kang, J., & Lee, J. (2021). A machine learning-based surrogate model for optimization of truss structures with geometrically nonlinear behavior. Finite elements in analysis and design, 196, 103572. https://doi.org/10.1016/j.finel.2021.103572
  13. [13] Xia, Y., Liu, J., & Qi, H. (2024). A population-based DNN-augmented optimization method for designing truss structures. Swarm and evolutionary computation, 89, 101613. https://doi.org/10.1016/j.swevo.2024.101613
  14. [14] Kong, X., Wu, Y., Zhu, P., Zhi, P., & Yang, Q. (2024). Novel artificial neural network aided structural topology optimization. Applied sciences, 14(23), 11416. https://doi.org/10.3390/app142311416
  15. [15] Ariyasinghe, N., Wickremasinghe, T., Weeratunge, H., Mallikarachchi, C., & Herath, S. (2026). Topology and size optimization of trusses using graph neural networks: Towards efficient surrogate modeling. Structures, 88, 111934. https://doi.org/10.1016/j.istruc.2026.111934
  16. [16] Zhao, Y., Li, H., Zhou, H., Attar, H. R., Pfaff, T., & Li, N. (2024). A review of graph neural network applications in mechanics-related domains. Artificial intelligence review, 57(11), 315. https://doi.org/10.1007/s10462-024-10931-y
  17. [17] Đorđević, F., & Marinković, M. (2025). PINN surrogate model for nonlinear equilibrium path analysis of von Mises shallow truss. Journal of big data, 12(1), 103. https://doi.org/10.1186/s40537-025-01095-9
  18. [18] Wang, Y., Han, Z., An, Y., Xu, X., Du, W., & Luo, Y. (2026). Artificial intelligence for design of spatial structures and joints: A state-of-the-art review. Journal of building engineering, 120, 115266. https://doi.org/10.1016/j.jobe.2026.115266
  19. [19] Izumi, B., Luczkowski, M., Labonnote, N., Manum, B., & Rønnquist, A. (2024). A systematic mapping study and a review of the optimization methods of structures in architectural design. Buildings, 14(11), 1–20. https://doi.org/10.3390/buildings14113511
  20. [20] Papadrakakis, M., Lagaros, N. D., & Tsompanakis, Y. (1999). Optimization of large-scale 3-D trusses using evolution strategies and neural networks. International journal of space structures, 14(3), 211–223. https://doi.org/10.1260/0266351991494830

Downloads

Published

2025-09-15

Issue

Vol. 2 No. 3 (2025): International Journal of Researches on Civil Engineering with Artificial Intelligence (IJRCEAI)

Section

Articles

How to Cite

Gholizadeh Arat Bani, M. (2025). Revisiting Classical Neural Architectures for Surrogate-Assisted Optimization of Space Trusses: Balancing Prediction Accuracy and Computational Efficiency. International Journal of Researches on Civil Engineering With Artificial Intelligence , 2(3), 139-145. https://doi.org/10.48314/ijrceai.v2i3.51

Similar Articles

1-10 of 18

You may also start an advanced similarity search for this article.