Sandwich panels are widely used in industrial roofing due to their lightweight and thermal insulation properties; however, their structural fire resistance remains insufficiently understood. This study presents a data-driven approach to predict the mid-span deformation of glass wool-cored sandwich roof panels subjected to ISO 834-5 standard fire tests. A total of 39 full-scale furnace tests were conducted, yielding 1519 data points that were utilized to develop deep learning models. Feature selection identified nine key predictors: elapsed time, panel orientation, and seven unexposed-surface temperatures. Three deep learning architectures—convolutional neural network (CNN), multilayer perceptron (MLP), and long short-term memory (LSTM)—were trained and evaluated through rigorous 5-fold cross-validation and independent external testing. Among them, the CNN approach consistently achieved the highest accuracy, with an average cross-validation performance of R2=0.91(meanabsoluteerror(MAE)=4.40;rootmeansquareerror(RMSE)=6.42), and achieved R2=0.76(MAE=6.52,RMSE=8.62) on the external test set. These results highlight the robustness of CNN in capturing spatially ordered thermal–structural interactions while also demonstrating the limitations of MLP and LSTM regarding the same experimental data. The findings provide a foundation for integrating machine learning into performance-based fire safety engineering and suggest that data-driven prediction can complement traditional fire-resistance assessments of sandwich roofing systems.

Fire doors are installed between compartments to prevent the spread of fire. During a fire, the temperature difference between the exposed and unexposed surfaces induces bending deformation of the door, thereby reducing its fire resistance performance. Excessive deformation may further compromise the structural integrity of the door. This study presents a thermo-mechanical model that idealizes the bending behavior of double swing fire doors based on the deflection equation of a simply supported beam subjected to a thermal gradient between the tensile and compressive sides. A criterion of deformation, quantifying the relationship between the meeting stile gap and the resulting maximum deflection, is introduced and compared with the predicted values. The validity of the proposed model was confirmed through fire resistance tests conducted on both insulated and non-insulated fire door specimens, demonstrating strong agreement with experimental results. Furthermore, by comparing the predicted deformation with the deformation criterion, the impact of increasing gap sizes on the service life of fire doors on their fire resistance performance was evaluated. Based on this analysis, appropriate gap size limits for different door specifications are proposed to ensure reliable fire performance.

Point cloud data‐based edge line extraction is an important task for accurate geometrical inspection of precast concrete (PC) elements in the construction industry. Although a few edge extraction algorithms have been developed so far based on point cloud data, little attention has been paid on which edge extraction algorithm performs the best in terms of edge estimation accuracy. To tackle the research gap, this study aims to evaluate currently available edge extraction algorithms in order to determine optimal algorithm for precise geometrical inspection of PC elements. To do this, simulated scan points are first generated and used for algorithm performance analysis using a geometrical model and a measurement noise modeling that determine the coordinates of simulated scan points. For validation of the simulation approach, comparison tests with experimental data are performed and the results show that the simulation approach has a high similarity of more than 90% compared to experimental data in terms of the number of scan points, scan pattern, and scan density, proving the effectiveness of the simulation‐based evaluation method. In addition, it shows that a least square regression (LSR) algorithm provides the best performance with an edge extraction accuracy of 1.56 and 2.71 mm for simulated and experimental scan points, respectively. The contributions of this study are (1) development of the geometrical model and noise modeling based on actual scan data and (2) validation of simulated‐based evaluation method on the lab‐scale PC slabs.

Sandwich panels are widely used in industrial roofing due to their lightweight and thermal insulation properties; however, their structural fire resistance remains insufficiently understood. This study presents a data-driven approach to predict the mid-span deformation of glass wool-cored sandwich roof panels subjected to ISO 834-5 standard fire tests. A total of 39 full-scale furnace tests were conducted, yielding 1519 data points that were utilized to develop deep learning models. Feature selection identified nine key predictors: elapsed time, panel orientation, and seven unexposed-surface temperatures. Three deep learning architectures—convolutional neural network (CNN), multilayer perceptron (MLP), and long short-term memory (LSTM)—were trained and evaluated through rigorous 5-fold cross-validation and independent external testing. Among them, the CNN approach consistently achieved the highest accuracy, with an average cross-validation performance of R2=0.91(meanabsoluteerror(MAE)=4.40;rootmeansquareerror(RMSE)=6.42), and achieved R2=0.76(MAE=6.52,RMSE=8.62) on the external test set. These results highlight the robustness of CNN in capturing spatially ordered thermal–structural interactions while also demonstrating the limitations of MLP and LSTM regarding the same experimental data. The findings provide a foundation for integrating machine learning into performance-based fire safety engineering and suggest that data-driven prediction can complement traditional fire-resistance assessments of sandwich roofing systems.

Fire doors are installed between compartments to prevent the spread of fire. During a fire, the temperature difference between the exposed and unexposed surfaces induces bending deformation of the door, thereby reducing its fire resistance performance. Excessive deformation may further compromise the structural integrity of the door. This study presents a thermo-mechanical model that idealizes the bending behavior of double swing fire doors based on the deflection equation of a simply supported beam subjected to a thermal gradient between the tensile and compressive sides. A criterion of deformation, quantifying the relationship between the meeting stile gap and the resulting maximum deflection, is introduced and compared with the predicted values. The validity of the proposed model was confirmed through fire resistance tests conducted on both insulated and non-insulated fire door specimens, demonstrating strong agreement with experimental results. Furthermore, by comparing the predicted deformation with the deformation criterion, the impact of increasing gap sizes on the service life of fire doors on their fire resistance performance was evaluated. Based on this analysis, appropriate gap size limits for different door specifications are proposed to ensure reliable fire performance.

Point cloud data‐based edge line extraction is an important task for accurate geometrical inspection of precast concrete (PC) elements in the construction industry. Although a few edge extraction algorithms have been developed so far based on point cloud data, little attention has been paid on which edge extraction algorithm performs the best in terms of edge estimation accuracy. To tackle the research gap, this study aims to evaluate currently available edge extraction algorithms in order to determine optimal algorithm for precise geometrical inspection of PC elements. To do this, simulated scan points are first generated and used for algorithm performance analysis using a geometrical model and a measurement noise modeling that determine the coordinates of simulated scan points. For validation of the simulation approach, comparison tests with experimental data are performed and the results show that the simulation approach has a high similarity of more than 90% compared to experimental data in terms of the number of scan points, scan pattern, and scan density, proving the effectiveness of the simulation‐based evaluation method. In addition, it shows that a least square regression (LSR) algorithm provides the best performance with an edge extraction accuracy of 1.56 and 2.71 mm for simulated and experimental scan points, respectively. The contributions of this study are (1) development of the geometrical model and noise modeling based on actual scan data and (2) validation of simulated‐based evaluation method on the lab‐scale PC slabs.

Mobile augmented reality (MAR) enhances the real world through the superimposition of computer-generated information while not interfering with a users’ mobility, having great potential to support various construction tasks. However, such information may lead to cognitive overload and, thus, could lead to adverse effects on the performance of tasks. Also, the narrowing of a user’s field of view that comes with MAR use could limit his or her ability to notice events in their surroundings. Therefore, it is important to understand how MAR use affects cognitive behavior, as well as task and safety performance for better design and applications of MAR in construction. As a preliminary investigation, this study conducted laboratory simulations of rebar-inspection tasks and compared the cognitive load (CL), task performance (TP), and situational awareness (SA) of users of two types of MAR systems—i.e., head-mounted and handheld—against those of inspectors using traditional paper-based methods. In particular, participants’ CL was measured with the National Aeronautics and Space Administration’s Task Load Index (NASA-TLX), their TP by completion time and the number of rebars correctly detected, and their SA with Taylor’s Situation Awareness Rating Technique (SART). Based on the results, we discuss the impact of the MAR system on rebar-inspection tasks from both cognitive and safety perspectives.

In construction technology education (CTE), construction site tours play an essential role for undergraduate students to obtain familiarity with construction environments, combine content knowledge with practice, and develop their competencies to embrace construction innovations before entering the industry. Implementing real construction site visits for education purposes faces challenges in getting access to proper construction sites and ensuring the safety of visiting students. This study combined the application of Project-based learning (PBL), game-based learning (GBL), and deeper learning theories to develop TheProjectLive ePlatform for students to experience virtual site tours. In this platform, 360-degree panoramas were utilized to present the approximate complexity of construction sites and provide an immersive learning environment. The study evaluated the effects of the proposed virtual site tour approach through two years of implementation in a tertiary course: Introductory Construction Technology and Materials. The students’ knowledge acquisition and learning experience when applying the ePlatform were well measured through in-class quizzes and questionnaire surveys, respectively. Based on the descriptive and statistical sources of evidence, the developed ePlatform for conducting the virtual construction site tour demonstrated its potential to effectively improve students’ transferable knowledge acquisition. The results of two in-class quizzes designed to assess students’ comprehension of content knowledge and their competency to solve practical problems showed that the average scores of students who experienced the virtual site tour were higher than students who learned via lecture notes. Specifically, the average scores of the former were 13.3% and 17.8% higher than the latter in the two quizzes, respectively. According to students’ feedback, this case study research also provided suggestions to further improve the proposed virtual site tour approach in tertiary CTE, emphasizing the importance of clear content presentation as well as indicating the benefits of perceived helpfulness and well-designed game elements.

On 17-21 June 2019, the Conseil International du Bâtiment (CIB) World Building Congress 2019 (WBC 2019) on Constructing Smart Cities took place in The Hong Kong Polytechnic University with the host being the Department of Building and Real Estate. This triennial international congress facilitated the in-depth exchange of research ideas on the aspects of smart construction using information technologies, including “smart transportation and mobility”, and “smart planning, design, construction”. Besides, the CIB Working Commission Group WC78 emphasised the importance of using the up-to-date information technologies for smart city development. The fruitful discussions fostered the close collaboration between academia and practitioners. Built upon the research works presented in the CIB WBC 2019, outstanding conference papers were selected and invited for enriching the contents which were accepted for publication after rigorous peer review in this special issue of “Journal of Information Technology in Construction” which aims to promote the research interest of the information technologies in smart city development. Highlights of each paper is provided below for readers’ reference.

Augmented reality (AR) is capturing increasing attention as a way to provide cognitive assistance in many fields. Inspiring from the benefits of AR, architecture, engineering, and construction industries and researchers are interested to apply AR technologies for various construction tasks such as design review, assembly, inspection, or facility maintenance, etc. However, even though AR technologies are designed to support users’ cognitive capability by providing superimposed information on real-world scenes, this information from AR may lead to one’s cognitive overload, causing an adverse effect on task performance. As a result, it is important to understand how AR would affect one’s cognitive load, and in turn, task performance for better use of AR systems in construction. As a preliminary investigation, this research compared task performance and cognitive loads during traditional paper-based and AR-assisted rebar inspection tasks in the laboratory setting. Participants’ task performance was measured by task completion time and the number of rebars correctly detected, whereas cognitive load was measured by the NASA task load index (TLX). Based on the result, we discussed the impact of AR application on rebar inspection tasks from a cognitive perspective.