Constraint-Relaxation Multi-Objective Optimization for Layout Planning of Prefabricated Subway Stations under Extreme Spatial Constraints

Abstract

Subway Station Construction Site Layout Planning (SSCSLP) in dense urban cores is characterized by extreme spatial constraints. Conventional Constraint-Preserving Search (CPS) paradigms often exhibit significant limitations in such environments. Specifically, the strict rejection of infeasible solutions fragments the search space, frequently causing stagnation in local optima. To address these challenges, a novel Graph-based Dynamic Constraint-Relaxation Multi-Objective Optimization Framework is proposed. An Edge-Attributed Weighted Graph is utilized to capture complex spatial dependencies. Uniquely, the Graph-based Dynamic Constraint-Relaxation NSGA-II (GDCR-NSGA-II) is developed to overcome optimization bottlenecks. A Dynamic Constraint-Relaxation Strategy (DCRS) transforms hard constraints into a continuous penalty landscape. This mechanism establishes an infeasibility-driven search trajectory, guiding the population from the infeasible region toward the global optimum at the feasible boundary. The proposed framework was validated using a case study of Chongqing Rail Transit Line 27. Comparative analysis demonstrated that, when the single best feasible solution identified by the conventional method was strictly used as the benchmark, the proposed framework reduced the average construction cost by approximately 49.4% and improved average safety performance by 63.7%. Consequently, this study provides robust theoretical support for intelligent decision-making in ultra-constrained engineering scenarios.

Keywords

Prefabricated subway station / Construction site / Site layout / Constrained multi-objective optimization / Graph structure

References

[1] Yao Z, Chen Z, Lee Y. A construction site layout planning study for dust reduction. J Constr Eng Manag, 2025, 151. ArticleID: 04025066

[2] Yao G, Zhu M, Yang Y, Lei T, Zhou C, Men W. Stage interaction multi-objective optimization of dynamic layout planning for irregular prefabricated construction site. J Build Eng, 2025, 111. ArticleID: 113508

[3] Pham VHS, Pham DH. Advanced construction site layout planning for prefabricated projects: an application of the new algorithm. Eng Constr Archit Manag, 2025.

[4] Yang Y, Chen C, Li T. Automated construction site layout design system for prefabricated buildings using transformer based conditional GAN. Adv Eng Inform, 2024, 62. ArticleID: 102885

[5] Klar M, Schworm P, Wu X, Simon P, Glatt M, Ravani B, Aurich JC. Transferable multi-objective factory layout planning using simulation-based deep reinforcement learning. J Manuf Syst, 2024, 74: 487-511.

[6] Xu J, Liu Q, Lei X. A fuzzy multi-objective model and application for the discrete dynamic temporary facilities location planning problem. J Civ Eng Manag, 2016, 22: 357-372.

[7] Mawdesley MJ, Al-jibouri SH, Yang HB. Genetic algorithms for construction site layout in project planning. J Constr Eng Manag, 2002, 128: 418-426.

[8] Sanad HM, Ammar MA, Ibrahim ME. Optimal construction site layout considering safety and environmental aspects. J Constr Eng Manag, 2008, 134: 536-544.

[9] Abune’meh M, El Meouche R, Hijaze I, Mebarki A, Shahrour I. Optimal construction site layout based on risk spatial variability. Autom Constr, 2016, 70: 167-177.

[10] Ning X, Qi J, Wu C. A quantitative safety risk assessment model for construction site layout planning. Saf Sci, 2018, 104: 246-259.

[11] Wang J, Huang Z, Song Y. Intelligent planning of safe and economical construction sites: theory and practice of hybrid multi objective decision making. Front Eng Manag, 2024.

[12] Ji Y, Leite F. Optimized planning approach for multiple tower cranes and material supply points using mixed-integer programming. J Constr Eng Manag, 2020, 146. ArticleID: 04020007

[13] Kavita SSK (2023) Metaheuristic evolutionary algorithms: types, applications, future directions, and challenges. In: 2023 3rd Int. Conf. Intell. Technol. CONIT, pp 1–6. https://doi.org/10.1109/CONIT59222.2023.10205592

[14] Safarzadeh S, Koosha H. Solving an extended multi-row facility layout problem with fuzzy clearances using GA. Appl Soft Comput, 2017, 61: 819-831.

[15] Hawarneh AA, Bendak S, Ghanim F. Construction site layout planning problem: past, present and future. Expert Syst Appl, 2021, 168. ArticleID: 114247

[16] Li H, Love PED. Site-level facilities layout using genetic algorithms. J Comput Civ Eng, 1998, 12: 227-231.

[17] Lu Y, Zhu Y. Integrating hoisting efficiency into construction site layout plan model for prefabricated construction. J Constr Eng Manag, 2021, 147. ArticleID: 04021130

[18] Yao G, Li R, Yang Y. An improved multi-objective optimization and decision-making method on construction sites layout of prefabricated buildings. Sustainability, 2023, 15. ArticleID: 6279

[19] Wenjie M. Research on dynamic construction site layout planning of subway station based on BIM and genetic algorithm. Central South University, 2024.

[20] Ji H, Zhou J, Li L, Shi C, Lei T. Study on programming of subway station construction site based on dynamic site layout planning. J Railw Sci Eng, 2020, 17: 1865-1873.

[21] Zhang Y-G, Wang K, Lv S-k, Zhao C-N, He H-G. Multi-objective optimization of subway construction site layout based on Pareto. J Civ Eng Manag, 2020, 37: 142-148.

[22] Sheng T, Xiong Y, Wang H, Zhang Y, Wang S, Zhang W. Deep reinforcement learning for community architectural layout generation. Knowl Inf Syst, 2025, 67: 2453-2480.

[23] Ming M, Trivedi A, Wang R, Srinivasan D, Zhang T. A dual-population-based evolutionary algorithm for constrained multiobjective optimization. IEEE Trans Evol Comput, 2021, 25: 739-753.

[24] Tian Y, Zhang T, Xiao J, Zhang X, Jin Y. A coevolutionary framework for constrained multiobjective optimization problems. IEEE Trans Evol Comput, 2021, 25: 102-116.

[25] Yang X, Hao X, Chen L, Wang D, Zhou W, Liu W (2023) A novel two-stage evolutionary algorithm for constrained multiobjective optimization. In: 2023 5th Int. Conf. Data-Driven Optim. Complex Syst. DOCS, pp 1–8. https://doi.org/10.1109/DOCS60977.2023.10294922

[26] Al Hawarneh A, Bendak S, Ghanim F. Dynamic facilities planning model for large scale construction projects. Autom Constr, 2019, 98: 72-89.

[27] Ning X, Qi J, Wu C, Wang W. A tri-objective ant colony optimization based model for planning safe construction site layout. Autom Constr, 2018, 89: 1-12.

[28] Chen P. Effects of the entropy weight on TOPSIS. Expert Syst Appl, 2021, 168. ArticleID: 114186

[29] Zavari M, Shahhosseini V, Ardeshir A, Sebt MH. BIM-based estimation of inputs for site layout planning and locating irregularly shaped facilities. Autom Constr, 2022, 141. ArticleID: 104431

[30] Zavari M, Shahhosseini V, Ardeshir A, Sebt MH. Multi-objective optimization of dynamic construction site layout using BIM and GIS. J Build Eng, 2022, 52. ArticleID: 104518

[31] Deb K, Pratap A, Agarwal S, Meyarivan T. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans Evol Comput, 2002, 6: 182-197.

Funding

Chongqing Urban Rail Express Line Full Life Cycle CIM Technology Application Research and Demonstration Research Project by Ministry of Housing and Urban-Rural Development Technology Demonstration Project(Grant No.2022-S-062)

Chongqing Urban Railway Express Digital Construction Method and Control Research Project by Chongqing Construction Science and Technology Plan Project(Grant City Section 2023 No.5-1)

RIGHTS & PERMISSIONS

The Author(s)