In this study, we investigate a novel idea of using synthetic images of bolts which are generated from a graphical model to train a deep learning model for loosened bolt detection. Firstly, a framework for bolt-loosening detection using image-based deep learning and computer graphics is proposed. Next, the feasibility of the proposed framework is demonstrated through the bolt-loosening monitoring of a lab-scaled bolted joint model. For practicality, the proposed idea is evaluated on the real-scale bolted connections of a historical truss bridge in Danang, Vietnam. The results show that the deep learning model trained by the synthesized images can achieve accurate bolt recognitions and looseness detections. The proposed methodology could help to reduce the time and cost associated with the collection of high-quality training data and further accelerate the applicability of vision-based deep learning models trained on synthetic data in practice.

Despite substantial efforts to improve construction safety training, the accident rate of migrant workers is still high. One of the primary factors contributing to the inefficacy of training includes information delivery gaps during training sessions (knowledge-transfer). In addition, there is insufficient evidence that these training programmes alone are effective enough to enable migrant workers to transfer their skills to the jobsite (training-transfer). This research attempts to identify and evaluate additional interventions to improve the transfer of acquired knowledge to the workplace. For this purpose, this study presents the first known experimental effort to assess the effect of interventions on migrant work groups in a multinational construction project in Qatar. Data analysis reveals that the adoption of training programmes with the inclusion of interventions significantly improves training-transfer. Construction safety experts can leverage the findings of this study to enhance training-transfer by increasing workers' safety performance and hazard identification ability.

Accident, injury, and fatality rates remain disproportionately high in the construction industry. Information from past mishaps provides an opportunity to acquire insights, gather lessons learned, and systematically improve safety outcomes. Advances in data science and industry 4.0 present new unprecedented opportunities for the industry to leverage, share, and reuse safety information more efficiently. However, potential benefits of information sharing are missed due to accident data being inconsistently formatted, non-machine-readable, and inaccessible. Hence, learning opportunities and insights cannot be captured and disseminated to proactively prevent accidents. To address these issues, a novel information sharing system is proposed utilizing linked data, ontologies, and knowledge graph technologies. An ontological approach is developed to semantically model safety information and formalize knowledge pertaining to accident cases. A multi-algorithmic approach is developed for automatically processing and converting accident case data to a resource description framework (RDF), and the SPARQL protocol is deployed to enable query functionalities. Trials and test scenarios utilizing a dataset of 200 real accident cases confirm the effectiveness and efficiency of the system in improving information access, retrieval, and reusability. The proposed development facilitates a new “open” information sharing paradigm with major implications for industry 4.0 and data-driven applications in construction safety management.

Construction safety education plays a crucial role in improving the safety performance in the construction industry. Many research works have successfully adopted computerized three-dimensional model-based virtual reality (3D-VR) to provide students with adequate safety knowledge and skills before they enter construction sites. Despite the advantages of improving learning outcomes, 3D-VR has limitations not only in reflecting real-world visibility but also in consuming significant energy and requiring strict user–device compatibility. Therefore, this research methodology was initiated with a thorough investigation of VR application in construction safety education. On the basis of a literature review, the study subsequently analyzes the energy-consumption problems of conventional VR systems. Initial findings motivate the development of an energy-efficient learning system (the interactive constructive safety education (eCSE)) using Web-based panoramic virtual photoreality technology for interactive construction safety education. The eCSE system provides three key interactive modules, namely, lesson delivery (LD), practical experience (PE), and knowledge assessment (KA), for use in mobile devices. The trial system has been developed and validated through scenarios derived from real construction sites. The preliminary evaluation reveals that the eCSE system not only overcomes the 3D-VR limitations in terms of energy efficiency, user device adaptability, and easy implementation, but also improves learning usability.

Construction jobsites remain among the most dangerous workplaces, with fatalities, accidents and injuries still plaguing the industry. Safety education is critical in fostering graduates capable of ensuring safe construction work; however, current learner assessment methods in pedagogy fail to ascertain the possession of safety knowledge and skills as they would be required in practice. This article aims to address this problem by proposing context-based learner assessment in construction safety education. A novel assessment system is developed and deployed with final-year construction management students, with learner testing through visualization-enhanced safety theory questions, site inspection scenario questions and job safety analysis review questions. The cognitive impact of the assessment approach is investigated through the NASA task load index, and its effectiveness is verified through educator and learner trials. Results demonstrate that the proposed system has significant potential as an innovative assessment tool for safety education.