Computational study demonstrates improved temporary facility placement and reduced functional costs in construction site planning, indicating enhanced efficiency over genetic algorithms.
Construction site layout planning (CSLP) is essential for optimizing the placement of temporary facilities (TFs), yet it inadequately integrates tower crane characteristics, causing inefficient material transportation and safety risk. Current decision-making relies on labor-intensive data extraction, complex mathematical models, and fragmented workflows incompatible with specialized software. This paper proposes an automated data-driven lifting-centered CSLP decision approach with building information modeling (BIM) and AI to enhance TF placement efficiency. The approach incorporates three stages: automated data extraction from the BIM model with users' promotion, development of data-driven lifting-based multi-objectives CSLP decision engines, and evaluation of generated TFs placement through BIM-based simulations. Validation indicates that over 92 % of AI-generated CSLP outcomes outperform traditional methods (genetic algorithm (GA)). Experiments on a real-world project demonstrate that this approach reduces processing time to 7.93 % of GA and lowers functional costs by 11.60 %. This method assists designers in expediting the CSLP decision-making process with BIM models.
No takes yet. Share an insight, caveat, or question.
Li et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: