Hazard ontology and 4D benchmark model for facilitation of automated construction safety requirement analysis
Karsten Winther Johansen, Carl Schultz, Jochen Teizer
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.