Ontological Modeling of Tacit Knowledge for Automating Job Hazard Analysis in Construction

Abstract

Due to the dynamic nature of work environments and conditions in construction, it is necessary to perform a job hazard analysis (JHA) prior to the commencement of hazardous jobs, and regularly review and update it. JHA is considered an intellectual activity subject to substantial influence by the experience and knowledge of the individuals conducting the analysis. Given the manual nature of JHA in current practice, its thorough preparation and use are time-consuming and laborious; thus, there is a great need to automate it. Against this background, this research aimed to develop a conceptual ontological model that can support the automation of JHA processes, including the tacit knowledge possessed by experts to facilitate automation. A JHA document analysis and a qualitative Delphi study were adopted to identify the concepts and associations embedded in JHA. An abductive data analysis approach was used with the guidance of a theoretical understanding of the systems model of construction accident causation to analyze the data collected from JHA documents and interviews. The findings offer valuable insights into important entities, subentities, and relationships that are associated with hazard identification and risk assessment, which form the basis for developing a conceptual ontological model. Such an ontology can facilitate the automation of JHA with an enhanced level of reasoning capability, through which the efficiency and effectiveness of JHA on construction sites can be improved.