With the acceleration of the modernization of the construction industry, prefabricated construction has become a key development direction due to its advantages of reducing construction waste, improving quality control, and saving time and costs. However, prefabricated construction sites face challenges such as limited space, high frequency of component hoisting, and prominent safety risks. Construction Site Layout Planning (CSLP) for prefabricated components is crucial to optimizing project efficiency and ensuring safety, yet existing research has shortcomings such as insufficient precision in optimization results, strict boundary constraints, and limited application in prefabricated construction. Traditional heuristic algorithms also need to be improved in regional search strategies and computational efficiency when dealing with multi-objective optimization problems.
Therefore, Junwu WANG, Zhihao HUANG, and Yinghui SONG from Wuhan University of Technology (including Sanya Science and Education Innovation Park) have conducted a research entitled “Intelligent Planning of Safe and Economical Construction Sites: Theory and Practice of Hybrid Multi-Objective Decision Making”.
This study focuses on optimizing the Prefabricated Component Construction Site Layout Planning (PCCSLP). It takes construction efficiency and safety risk as objectives to build a multi-objective CSLP model. A novel heuristic algorithm, the Hybrid Multi-Strategy Improvement Dung Beetle Optimizer (HMSIDBO), is applied to solve the model. This algorithm has balanced capabilities in global exploration and local development, effectively addressing the defects of the original Dung Beetle Optimizer (DBO) such as imbalance between global exploration and local exploitation and susceptibility to local optima through the Bernoulli mapping strategy, Levy flight strategy, and T-distribution perturbation strategy.
The research establishes a mathematical model for PCCSLP with three minimization objectives (horizontal transportation time of tower cranes, horizontal path length of component lifting, and overlapping working areas of multiple tower cranes) and seven constraints (including four boundary constraints and three overlapping constraints). Through a case study of prefabricated residential construction projects in Sanya, the practicality and effectiveness of the proposed method are verified.
The research findings indicate that compared with the original layout, the HMSIDBO-PCCSLP optimization scheme improves each objective by 18% to 75%. Compared with the Genetic Algorithm (GA), HMSIDBO demonstrates significantly faster computational speed and higher resolution accuracy. Additionally, in comparison with the Dung Beetle Optimizer (DBO), Particle Swarm Optimization (PSO), and Whale Optimization Algorithm (WOA), HMSIDBO exhibits superior iterative speed and an enhanced ability for global exploration. Specifically, the average horizontal transportation time for tower cranes is reduced by 18.3%, the hazardous areas affected by falling prefabricated components are reduced by an average of 23.4%, and the overlapping work areas of multiple tower cranes are decreased by an average of 74.3%. This study completes the framework from data collection to multi-objective optimization in site layout, laying the foundation for implementing intelligent construction site layout practices and providing scientific support for the efficient and safe management of prefabricated construction sites.
The paper “Intelligent Planning of Safe and Economical Construction Sites: Theory and Practice of Hybrid Multi-Objective Decision Making” is published in Front. Eng. Manag. 2025, 12(3): 487–509. Full text of the paper: https://doi.org/10.1007/s42524-024-4004-z.