Hazard ontology and 4D benchmark model for facilitation of automated construction safety requirement analysis

Abstract

Over the last two decades, numerous approaches have been developed for automating construction safety assessment, that is, prevention through design and planning (PtD/P), that overcome the limitations of a purely manual safety assessment process. Despite this, such automated approaches are yet to be widely adopted in practice. Barriers include a lack of standardization of construction safety concepts within regulatory frameworks and a lack of confidence in automated approaches on the part of practitioners. This work presents a freely available 4D BIM‐based benchmark model (3D Building Information Model and 68 schedules) and construction safety ontology covering the two most frequent and severe construction site accidents: falls from height and struck‐by falling object hazards. The benchmark model and ontology enable the construction safety community to test and compare the performance of alternative automated approaches. Moreover, they are utilized in our PtD/P tool SafeConAI, and empirical evaluation results show how the safety situation changes among different construction schedules of the same project.

Integration of Industry Foundation Classes and Ontology: Data, Applications, Modes, Challenges, and Opportunities

“…Monitoring and management of quality, schedule, cost, and safety IFC data; construction specification; on-site records [26,57,70,73,81,85,89,95,112,133,135,[158][159][160] Operation and maintenance phase Building energy management, culture heritage maintenance, defect detection, etc.…”

An integration–competition network for bridge crack segmentation under complex scenes

“…Since the middle of the 20th century, the bridge construction scale has become larger (Johansen et al., 2023; Kaur et al., 2023; Ma et al., 2023; Rafiei & Adeli, 2017). It is vital to conduct periodical detections on the security and durability of bridges (Mirzaei & Adeli, 2019; Ni et al., 2018; Okazaki et al., 2023; Shim et al., 2023; Sirca & Adeli, 2018).…”

Brain‐regulated learning for classifying on‐site hazards with small datasets

“…However, the current challenge lies in the lack of robust perception capabilities in these systems, which raises significant safety concerns. Without the ability to accurately perceive and interpret hazards in the environment, there is a heightened risk of overlooking potential dangers, leading to accidents, injuries, and compromised safety measures (Johansen et al., 2023; Yan et al., 2020). Therefore, it is crucial to develop machine vision systems with robust perception capabilities to ensure effective hazard detection and prevention, ultimately enhancing overall safety on construction sites.…”