Vol. 22, No. 1, pp. 105-115 (2026)
EFFICIENT PRESTRESS OPTIMIZATION OF SUSPEN-DOME USING
NSGA-III AND MACHINE LEARNING-BASED SURROGATE MODELS
Jin Wang, Ming-Liang Zhu * and Ze-Yun Jin
School of Civil Engineering, Southeast University, Nanjing 210096, China
*(Corresponding author: E-mail:This email address is being protected from spambots. You need JavaScript enabled to view it.)
Received: 9 December 2024; Revised: 20 June 2025; Accepted: 20 June 2025
DOI:10.18057/IJASC.2026.22.1.9
 View Article |
Export Citation: Plain Text | RIS | Endnote |
ABSTRACT
Prestress optimization is a critical step in the structural design of suspen-dome, often requiring extensive and time-consuming iterative computations. This study proposes a hybrid framework that integrates the NSGA-III algorithm with machine learning-based surrogate models to address the prestress multi-objective optimization problem of suspen-dome. A comparative analysis of three machine learning algorithms—Deep Belief Network (DBN), Sequence-to-Sequence (Seq2Seq), and Backpropagation Neural Network (BPNN)—is conducted to evaluate surrogate modeling performance. The multi-objective optimization considers four objective functions, and the NSGA-III algorithm is employed to effectively obtain the Pareto front. The optimal solution is selected using multi-criteria decision-making, and a case study is presented to validate the accuracy and efficiency of the proposed method. Results show that the BPNN-based surrogate-assisted optimization achieves the best overall efficiency. The introduction of surrogate models reduces computation time by 95% while maintaining optimization performance comparable to traditional finite element analysis (FEA)-based methods.
KEYWORDS
Suspen-dome, Prestress optimization, Multi-objective, Optimal solution, Finite element analysis (FEA)
REFERENCES
[1] Kawaguchi M, Abe M, Tatemichi I. Design, tests and realization of suspen-dome system. Journal of the International Association for Shell and Spatial Structures 1999;40:179–92.
[2] Liu X. Introduction of structures of some stadiums and gymnasiums for Beijing 2008 Olympic Games. Fourth International Conference on Advances in Steel Structures, vol. I, Elsevier; 2005, p. 361–8. https://doi.org/10.1016/B978-008044637-0/50052-4.
[3] Li Z Q, Zhang Z H, Dong S L, et al. Construction sequence simulation of a practical suspen-dome in Jinan Olympic Center. Advanced Steel Construction, 2012, 8(1): 38-53.
[4] Nie G, Fan F, Zhi X. Test on the Suspended Dome Structure and Joints of Dalian Gymnasium. Adv Struct Eng 2013;16:467–85. https://doi.org/10.1260/1369-4332.16.3.467.
[5] Gong S. The research of suspen-dome structure. IOP Conf Ser: Mater Sci Eng 2017;242:012050. https://doi.org/10.1088/1757-899X/242/1/012050.
[6] Yuan XF, Dong SL. Integral feasible prestress of cable domes. Comput Struct 2003;81:2111–9. https://doi.org/10.1016/S0045-7949(03)00254-2.
[7] Optimal Design of Cable-domes with Multi-overall Selfstress Modes-All Databases n.d. https://webofscience.clarivate.cn/wos/alldb/full-record/CSCD:3389260 (accessed September 2, 2024).
[8] Kitipornchai S, Kang W, Lam H-F, Albermani F. Factors affecting the design and construction of Lamella suspen-dome systems. Journal of Constructional Steel Research 2005;61:764–85. https://doi.org/10.1016/j.jcsr.2004.12.007.
[9] Zhang Z, Zhi X, Li Q, Fan F. Simlating the Stability and Pre-stressed Tension of a Single-Layer Spherical Reticulated Shell Supported by Cable. Int J Steel Struct 2019;19:618–34. https://doi.org/10.1007/s13296-018-0151-6.
[10] Kang W, Chen Z, Lam H-F, Zuo C. Analysis and design of the general and outmost-ring stiffened suspen-dome structures. Engineering Structures 2003;25:1685–95. https://doi.org/10.1016/S0141-0296(03)00149-4.
[11] Liang H Q, Dong S L, Miao F. Multi-objective optimization analysis of cable dome structures prestress based on niche genetric algorithm. J. Build. Struct, 2016, 37: 92-99.(in Chinese)
[12] Kaveh A, Rezaei M. Optimal Design of Double-Layer Domes Considering Different Mechanical Systems via ECBO. Iran J Sci Technol Trans Civ Eng 2018;42:333–44. https://doi.org/10.1007/s40996-018-0123-2.
[13] Olofin I, Liu R. Suspen-Dome System: A Fascinating Space Structure. TOCIEJ 2017;11:131–42. https://doi.org/10.2174/1874149501711010131.
[14] Lygoe RJ, Cary M, Fleming PJ. A Real-World Application of a Many-Objective Optimisation Complexity Reduction Process. In: Purshouse RC, Fleming PJ, Fonseca CM, Greco S, Shaw J, editors. Evolutionary Multi-Criterion Optimization, vol. 7811, Berlin, Heidelberg: Springer Berlin Heidelberg; 2013, p. 641–55. https://doi.org/10.1007/978-3-642-37140-0_48.
[15] Deb K, Jain H. An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part I: solving problems with box constraints. IEEE Transactions on Evolutionary Computation 2013;18:577–601. https://doi.org/10.1109/TEVC.2013.2281535.
[16] Hisao Ishibuchi, Noritaka Tsukamoto, Yusuke Nojima. Evolutionary many-objective optimization: A short review. 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence), Hong Kong, China: IEEE; 2008, p. 2419–26. https://doi.org/10.1109/CEC.2008.4631121.
[17] Ma Q, Ohsaki M, Chen Z, Yan X. Multi-objective optimization for prestress design of cable-strut structures. International Journal of Solids and Structures 2019;165:137–47. https://doi.org/10.1016/j.ijsolstr.2019.01.035.
[18] Chen Y, Yan J, Sareh P, Feng J. Feasible Prestress Modes for Cable-Strut Structures with Multiple Self-Stress States Using Particle Swarm Optimization. J Comput Civ Eng 2020;34:04020003. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000882.
[19] Deb K, Pratap A, Agarwal S, Meyarivan T. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans Evol Computat 2002;6:182–97. https://doi.org/10.1109/4235.996017.
[20] Zitzler E, Laumanns M, Thiele L. SPEA2: Improving the strength Pareto evolutionary algorithm. TIK Report 2001;103.
[21] Purshouse RC, Fleming PJ. Evolutionary many-objective optimisation: An exploratory analysis. The 2003 Congress on Evolutionary Computation, 2003. CEC’03., vol. 3, IEEE; 2003, p. 2066–73. https://doi.org/10.1109/CEC.2003.1299927.
[22] Hughes EJ. Evolutionary many-objective optimisation: many once or one many? 2005 IEEE congress on evolutionary computation, vol. 1, IEEE; 2005, p. 222–7. https://doi.org/10.1109/CEC.2005.1554688.
[23] Deb K, Mohan M, Mishra S. Evaluating the ϵ-domination based multi-objective evolutionary algorithm for a quick computation of Pareto-optimal solutions. Evolutionary Computation 2005;13:501–25. https://doi.org/10.1162/106365605774666895.
[24] Yang S, Li M, Liu X, Zheng J. A grid-based evolutionary algorithm for many-objective optimization. IEEE Transactions on Evolutionary Computation 2013;17:721–36. https://doi.org/10.1109/TEVC.2012.2227145.
[25] He Z, Yen GG, Zhang J. Fuzzy-based Pareto optimality for many-objective evolutionary algorithms. IEEE Transactions on Evolutionary Computation 2013;18:269–85. https://doi.org/10.1109/TEVC.2013.2258025.
[26] Carleo G, Cirac I, Cranmer K, Daudet L, Schuld M, Tishby N, et al. Machine learning and the physical sciences. Rev Mod Phys 2019;91:045002. https://doi.org/10.1103/RevModPhys.91.045002.
[27] Chang C-M, Lin T-K, Chang C-W. Applications of neural network models for structural health monitoring based on derived modal properties. Measurement 2018;129:457–70. https://doi.org/10.1016/j.measurement.2018.07.051.
[28] Amini K, Jalalpour M, Delatte N. Advancing concrete strength prediction using non-destructive testing: Development and verification of a generalizable model. Construction and Building Materials 2016;102:762–8. https://doi.org/10.1016/j.conbuildmat.2015.10.131.
[29] Zoph B. Neural architecture search with reinforcement learning. arXiv preprint arXiv: 1611.01578, 2016.
[30] Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative Adversarial Networks. Communications of the ACM, 2020, 63(11): 139-144.
[31] Tai L, Zhang J, Liu M, Boedecker J, Burgard W. A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation. arXiv preprint arXiv:1612.07139, 2016.
[32] Li Y, Hariri-Ardebili MA, Deng T, Wei Q, Cao M. A surrogate-assisted stochastic optimization inversion algorithm: Parameter identification of dams. Adv Eng Inform 2023;55:101853. https://doi.org/10.1016/j.aei.2022.101853.
[33] Zhou Y, Zheng S, Zhang G. Machine learning-based optimal design of a phase change material integrated renewable system with on-site PV, radiative cooling and hybrid ventilations—study of modelling and application in five climatic regions. Energy 2020;192:116608. https://doi.org/10.1016/j.energy.2019.116608.
[34] JGJ 7-2010. Technical Specification for Space Grid Structures, 2010.(in Chinese)
[35] Hinton GE, Osindero S, Teh Y-W. A Fast Learning Algorithm for Deep Belief Nets. Neural Computation 2006;18:1527–54. https://doi.org/10.1162/neco.2006.18.7.1527.
[36] Vinyals O, Le Q. A neural conversational model. arXiv preprint arXiv:1506.05869, 2015.
[37] Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature 1986;323:533–6. https://doi.org/10.1038/323533a0.
[38] Gu Q, Wang R, Xie H, Li X, Jiang S, Xiong N. Modified non-dominated sorting genetic algorithm III with fine final level selection. Appl Intell 2021;51:4236–69. https://doi.org/10.1007/s10489-020-02053-z.
[39] Deb K, Jain H. An Evolutionary Many-Objective Optimization Algorithm Using Reference-Point-Based Nondominated Sorting Approach, Part I: Solving Problems With Box Constraints. IEEE Trans Evol Computat 2014;18:577–601. https://doi.org/10.1109/TEVC.2013.2281535.