Seungjun Ahn

Restricted viewpoints on construction sites often yield partial point clouds in which weld seams are partly or entirely occluded. This study proposes a non-learning BIM-guided method that localizes BIM-defined nominal weld seams by registering a known H-section beam–column joint model to the visible flange and web surfaces. Given an isolated point cloud and the acquisition side, finite analytic member surfaces and a BIM-derived Hesse atlas support multiple admissible initial poses. Each pose is refined using the same multiscale robust point-to-surface objective, and a deterministic terminal criterion selects the pose used to transfer nominal seam paths. Neither seam labels nor reconstruction of occluded geometry is required. On 402 synthetic observations, median seam RMSE, ADD-RMS, and relative rotation error were 1.110 mm, 1.249 mm, and 0.067 degrees, respectively; 89.05% had seam RMSE within 10 mm. On 180 laboratory observations, median point-to-surface distance and 5 mm attachment were 2.137 mm and 82.04%. Median warm processing times on a matched panel were 2.52 s and 3.18 s for synthetic and laboratory inputs, respectively. These findings support the applicability of the proposed method to nominal weld-seam localization under restricted partial-view conditions relevant to construction-site welding.

Efficient evacuation planning in subway stations is critical to ensuring passenger safety during emergencies. This study proposes a graph-theoretic framework to model and optimize pedestrian evacuation strategies based on realistic spatial and behavioral parameters. A detailed network of Seoul Guryong Station is constructed and used to simulate two routing strategies: a cost-aware shortest path algorithm and a greedy disjoint path algorithm. The former minimizes individual travel resistance, while the latter promotes dispersion to reduce congestion. Simulation results in AnyLogic show that the greedy strategy achieves more balanced exit usage and reduces total evacuation time from approximately 5.66 minutes to 5.18 minutes, a 10% improvement. These findings highlight the importance of incorporating flow distribution and pedestrian adaptability into routing design. The proposed approach offers a practical tool for subway operators and urban planners to enhance emergency preparedness and station design.

Due to its inherent complexities in the process and the dynamic interactions with external environmental factors, the construction industry is widely considered one of the most hazardous industries worldwide. With advancements in artificial intelligence (AI), construction safety management practices have increasingly used knowledge-driven approaches. Such incorporation of knowledge-based methods has led to significant improvements in various elements of construction safety management systems, including hazard identification and risk assessment, selection of risk mitigation strategies, analysis of accident information, sharing of health and safety knowledge, access to regulations, and identification of applicable safety requirements. Against this background, this paper presents a systematic literature review to provide an overview of the current state of the art in the use of knowledge-driven approaches in construction safety management. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) procedure, this study reviews how the knowledge-driven approach is utilized in the construction safety management field to automate different activities that come under it. Journal papers published from 2000 were considered for this review, and the analysis focused on the contributions of research, the evolution of knowledge-driven approaches, sources of incorporated knowledge, methods of system development, yearly publications, and publication by journals. The results provide a comparison of related studies over two decades and offer insights into trends and gaps in this research field. Notably, the trend analysis shows a dramatic increase in the number, as well as the depth, of research efforts utilizing AI techniques for analyzing unstructured data, such as construction images and texts from construction documents, and drawing data-based decisions for accident prevention.

The construction industry faces significant challenges with frequent accidents, largely due to the inefficient use of safety guidelines. These guidelines, which are often text and figure heavy, demand substantial human effort to identify the most relevant items for specific tasks and conditions. Additionally, the guidelines contain both central and peripheral elements, and central items are critical yet difficult to identify without extensive domain knowledge. This study proposes a novel recommendation framework to enhance the usability of these safety guidelines. By leveraging natural language processing (NLP) and knowledge graph (KG) modeling techniques, unstructured safety texts are transformed into a structured, interconnected KG. The PageRank and Louvain Clustering algorithm is then employed to rank guidelines by their relevance and importance. A case study on “High-rise Building Construction (General) Safety and Health Guidelines”, using ‘scaffolding’ as the keyword, demonstrates the framework’s effectiveness in improving retrieval efficiency and practical application. The analysis highlighted key clusters such as ‘fall’, ‘drop’, and ‘scaffolding’, with critical safety measures identified through their interconnections. This research not only overcomes the fragmentation of safety management documents but also contributes to advancing hazard analysis and risk prevention practices in construction management.