Computing in Civil Engineering 2023: Visualization, Information Modeling, and Simulation

The study shows the relationship between the AEC use case purposes, goals, and collaborative technologies in interactive workspaces (IWs). The new Human/Buildings Simulation, Integration, Visualization, and Automation Laboratory (H/B-SIVA Lab) at the University of Nebraska–Lincoln (UNL), which incorporates hardware, software, inputs, and outputs systems such as multimodal devices, wireless devices, and large displays, was used as an illustration. The study is still in progress, and local AEC researchers and professionals will be consulted on its validity in the future. It covers the attributes and benefits of IWs, the H/B-SIVA Lab, IWs use cases and task types, IWs emerging technologies, the proposed IWs framework, and the conclusion and future research. This study provides a standard language and structure for determining appropriate methods to enhance the adoption and successful adoption of IWs technologies and the use cases in collaborative project teams in the AEC industry for AEC researchers and professionals.

The metaverse concept as a science fiction concept has been around for a few decades, but new computing technologies have made it a reality in 2021 with Microsoft Mesh for Teams for Hololens, Meta Horizon Worlds and Workrooms for Oculus Quest, Nvidia Omniverse, HTC Viveverse, and many other apps for any type of head-mounted devices. While analysts estimate a market size as high as $13 trillion by 2030, there are challenges ahead. Despite growing interest in the metaverse across various industries, there is currently a lack of literature and research on the topic in the architecture, engineering, and construction (AEC) industry. The objective of this paper is to present the strengths, weaknesses, opportunities, and threats (SWOT) of this new mode of communication based on published articles in other industries. This study highlights the challenges for future efforts involving the implementation of metaverse in the AEC industry.

In this paper, a novel approach to deconstruction planning based on reality capture and gamified virtual reality (VR) is presented and demonstrated. In the approach, the in situ conditions of the asset are captured and stored in a 3D point cloud. Next, a mesh or BIM representation of the asset is created and imported into a 3D game engine. Finally, gamified VR software simulations are developed allowing an operator to conduct human-machine collaborative deconstruction planning experiments. As a result, deconstruction plans benefit from realistic, repeatable, risk-free iterative improvements. This approach builds upon prior work by contributing the new ability to import reality data into the deconstruction simulations. One essential disassembly workflow, cutting and packing, is fully implemented for demonstration. New, low-cost, reality-capture tools such as smartphone lidars and handheld scanners promise to diminish the cost of implementing the approach, provided that they meet the project’s needs.

Ensuring accessible and high-quality safety training is critical for preventing injuries and fatalities on construction job sites, especially considering the potential impact on the staggering number of over seven million construction workers in the United States. Construction workers accounted for approximately 20% of worker fatalities, equating to one in every five deaths annually. Although relatively new, virtual reality (VR) safety training has significant potential for improving safety training with immersive experiences and interactive environments. However, the effectiveness of VR safety training remains unknown, and limited studies are available. To investigate VR safety training efficacy, the authors compared pre- and post-training between a control and an experimental group to evaluate knowledge comprehension and retention. The control group participated in traditional school-based and physical simulation learning, while the experimental group completed both the VR safety training and the same training as the control group. The study focused on two safety topics: fire safety and confined space safety. The results demonstrate that VR safety training significantly improves learner comprehension and retention of safety knowledge, supporting its potential as an effective training tool for construction workers. The study also revealed that the immersive VR experience was user-friendly and contributed to increased self-confidence in understanding safety procedures, knowledge, and practices.

Collaborative motor tasks involving motion corporations among different human operators are commonly seen in many working scenarios, such as surgery operation, fabrication assembly, health care, and material handling. Although virtual training for these tasks has been discussed along with the advancement of communication technologies, few studies have examined the technical procedures and theoretical background of integrating embodied physics and haptic feedback with the virtual training of collaborative motor tasks. In this study, we choose collaborative material handling as an example to implement embodied physics in virtual training for collaborative motor tasks. Multi-player virtual reality (VR) environment is developed to establish a real-time training environment between geographically distributed operators. The virtual materials and environment are synchronized via a cloud server, creating a homogeneous context for the collaboration task. Geographically distributed operators can interact with the virtual environment by controlling a whole-body tracked virtual operator to report or move hazards and complete the material handling task as a team. In addition, the feeling of physical contact can be enhanced with haptic feedback. A pilot test shows that the collaborative training environment enhances safety awareness and degree of engagement. Meanwhile, simulated embodied physics can effectively bridge the gap between virtual and real training scenarios and enhance the task-learning experience.

Healthcare workers face a unique set of challenges during active shooter incidents. Due to job responsibilities and mobility issues, healthcare workers and patients are vulnerable in these types of scenarios. This study aims to develop a VR training platform to prepare healthcare workers for active shooter incidents. To achieve the goals of this study, we went through a collaborative process with stakeholders to identify the unique circumstances for healthcare workers and environments. To achieve the desired characteristics for the platform, we followed a four-component design framework consisting of the development of a representative virtual environment, a behavior-based storyline, interactive features, and an autonomous feedback system. In describing the detailed design of the four components, this paper presents a case study for researchers who are seeking to develop platforms that need user adaption and acceptance.

Teleoperated robots are increasingly being used in construction sites, but there is still a need for better human-robot interfaces. Auditory feedback using sonification has commonly been used to complement visual feedback in teleoperation applications. However, it is not yet well understood how operational and environmental sounds can support operators in complex tasks such as construction machine operations. In this paper, we describe the development of a virtual environment to assess the impacts of operational and environmental sounds on operators’ performances and cognitive loads during teleoperated demolition. Our goal is to examine whether different levels of operational and environmental sounds can increase the workers’ situation awareness, operational efficiency, and safety performance. Alternatively, we anticipate that some environmental noises may negatively affect the operators’ performances by increasing their mental workload and stress levels. Consequently, we plan to evaluate the effectiveness of including audio filters that minimize unwanted sounds while prioritizing desired sounds.

Experiential learning has been an effective educational tool and provides a learning experience to students via “learning by doing.” Different forms of experiential learning practices are available for students in existing curriculums such as internships, field works, gaming/simulations, volunteering, and hackathons. Datathons, a form of hackathons that focus on data, have been effective in the computer science community and have been successfully launched in recent years in the architectural, engineering, construction (AEC) community as well. ASCE Computing Division’s Visualization, Information Modeling, and Simulation (VIMS) Committee has successfully launched datathons for the past couple years. Our experience shows that datathons require a significant thought process during the planning phase and a sound outreach plan for execution of these datathons to bring diversity to the pool of participants. This paper reports on the lessons learned (LL) accumulated over the past years while launching these datathons and aims to help communities from academia and industry for hosting future datathons by leveraging these LL for improved student experience. The lessons learned will be discussed in relation to the planning, data preparation, and outreach phases of datathons.

Past research has proved that the provision of effective safety training is a primary course of action that minimizes construction accidents. Similarly, the incorporation of VR technology in safety training has gained a wide momentum to overcome the limitations of traditional safety training. In fact, VR has proved to significantly contribute to the learning outcomes of trainees in construction training. However, existing safety VR-based training programs are incomprehensive with a limited number of hazards; thus, there still exists a gap when it comes to the transition from confined to thorough and all-inclusive VR-based training programs that conclusively address a specific topic. Against this backdrop, this research develops a full VR-based safety training program that addresses the hazards in general and enabling works of construction projects. This is done to verify the feasibility and viability of VR technology when implemented and used on a larger scale. The module consists of five chapters that are taught in 10 main consecutive VR scenarios addressing a wide range of relevant hazards. The results revealed that the development of the module is feasible and viable.

Complex construction projects involve numerous interdependent stakeholders in close collaboration. Early detection of overloaded interfaces and unhealthy relationships between project stakeholders create the opportunity to address the potential overall project health problems. To identify unhealthy relationships and overloaded interfaces between project stakeholders in complex construction projects, new methods that also include perspectives of various project stakeholders are needed in addition to the existing conventional project management methods. In this paper, a new framework for assessment and visualization of interface health and workload conditions of stakeholder interactions in a group decision environment is introduced. Wide-ranging degrees of automation for implementing the framework are feasible and are discussed. The functionality of the proposed framework was demonstrated in an industrial rail line project located in North America. The contributions of this paper provide foundational material for further research in interface health and workload assessment in complex construction projects.

Integrated project delivery (IPD) method is associated with numerous benefits, including enhanced project performance, collaboration, and information sharing among project stakeholders. However, the lack of adequate incentive and reward mechanisms is still considered as the main reason for slowing down the adoption of IPD. As such, the goal of this paper is to identify a fair and efficient risk pool distribution among IPD project stakeholders. The adopted methodology included (1) assigning the risks associated with each stakeholder, (2) computing valuations for all possible subset coalitions among IPD project stakeholders that reflect their risk control capabilities as well as their coordination effects, and (3) utilizing cooperative game theory to generate fair and efficient distribution mechanisms given different a priori working and coalitional preferences. As such, a total of 22 risks were identified and quantified to calculate the risk control valuations of all subset coalitions using Monte-Carlo simulations. Afterward, these valuations were utilized to generate fair risk and reward distributions using the Shapley value and Owen value for games with a priori unions. The coalitional stability of the generated results was evaluated using propensity-to-disrupt ratios. Ultimately, the findings of this paper indicate that an IPD-multiparty agreement where all parties are engaged early on in establishing the contract results in the most balanced willingness to cooperate among stakeholders. Finally, the outcome of this paper equips industry practitioners with a distribution mechanism that corresponds to the adopted IPD relational configuration on one hand and the overall IPD project stability on the other.

Modular floating structures (MFS) offer an attractive solution for the expansion of coastal cities in adaptation to flooding and sea level rise driven by climate change. Yet, large-scale floating structures for human habitation are unprecedented with no guidelines to inform their practical design. For such projects to succeed, it is essential to investigate how prospective residents will experience life on a floating city from the perspective of comfort and habitability. In response, this paper leverages immersive virtual reality (VR) to establish a framework replicating the motions of a floating structure within any given sea state. The test bed successfully reproduced the motions of an MFS excited by waves corresponding to 1, 50, and 100-year storm events with 96.1%–98.2% accuracy. This validated the feasibility of exploring MFS user experience, decision making, and communication in a completely virtual environment. Ultimately, we establish VR as an invaluable tool for the exploration of immersive visual stimuli to response perception in the context of a floating city.

This paper considers the effect of redesigning an emergency department (ED) on improving its performance through changing its workflow, before and after COVID-19 surge. Before COVID-19, a discrete event simulation was developed with a focus on reducing the average length of stay (LOS) for all patients in the ED using different front-end processes alongside an expansion redesign. When SARS-CoV-2 and COVID-19 emerged, however, the implementation process was not completed. To understand the redesign impact on ED performance, a questionnaire was developed to gather information from its personnel. They were asked to present their ideas regarding the impact of redesign and its changes on improving ED operations, workflow efficiency, and lessons they learned during pandemic. Results show that respondents mostly agreed that pandemic has negatively affected ED operations; they also believed that most of the redesign changes need improvement.

The Industry Foundation Classes (IFC) and City Geography Markup Language (CityGML) are commonly used open data formats for representing and exchanging information within building information modeling (BIM) and geographic information system (GIS), respectively. Although the integration of BIM and GIS based on IFC and CityGML has a great potential to support urban road rehabilitation planning and management, the existing IFC and CityGML standards cannot comprehensively and explicitly describe the features required for urban road rehabilitation planning procedures. To this end, this study aims to develop a data model to sufficiently represent the required information, serving as a formal basis for the IFC and CityGML schema extensions. The proposed IFC and CityGML extensions could work as the foundation of urban road rehabilitation information sharing and simulation to facilitate decision-making related to comparing alternatives and optimizing plans by considering multiple objectives in the planning phase.

Digital twins (DT) have recently gained significant interest among architecture, engineering, construction, and operations (AECO) industry professionals and researchers. However, there is no consensus on the definition of digital twins to the point that some practitioners use building information models (BIM) and digital twins synonymously. This research focuses on developing a scope definition for the identification and classification of DT use cases. The results will help researchers and industry practitioners with planning the implementation of operational digital twins. A detailed review of the literature was conducted to find the existing definitions of operational digital twins. Afterward, an extensive review of use cases of operational digital twins was completed. Furthermore, these use cases were defined through a categorical content analysis, and they were placed within an existing widely used ontology. Examples of operational DT use cases include remote asset monitoring, remote asset control, and asset performance prediction. Use cases identified in this paper were reviewed by leading experts in the DT community. The findings of this paper will benefit researchers and industry practitioners in planning for digital twin implementations by providing a common language with attributes to define specific DT use cases.

Building information modeling (BIM) and virtual reality (VR) are technology tools used by architecture, engineering, and construction (AEC) professionals for team collaboration. A prior study suggests that visualization, voice, implicit communications like facial expression and body language, team members’ presence during technical knowledge exchange, and use of tools like pointer and markup are factors affecting multidisciplinary AEC team members’ mutual understanding of disciplinary knowledge, referred to as shared understanding, to collaborate, find solutions, and make decisions. This paper presents a comparative analysis of BIM and VR platforms for AEC team collaboration based on features that can affect team shared understanding. While VR has features that can address the gaps in BIM platforms to support team collaboration, the current commercially available VR tools lack some features like capturing facial expressions and full body language that make each platform of BIM and VR unique and complimentary for team collaboration.

Effective coordination among supply chain entities, particularly factory production, transportation, and onsite assembly, is critical in offsite construction as a means of mitigating the risk of schedule delays. Offsite construction companies thus tend to develop master schedules that consider not only production capacities and resources in the factory but also delivery logistics and onsite assembly processes. However, the current scheduling practice still lacks integration of the various components of the supply chain, instead relying on a manual and time-consuming approach. As a result, the master schedules generated do not fully take into consideration the dynamic relationships among the respective operational schedules of each supply chain entity. This, in turn, leads to unstable supply chain performance and underutilization of resources and, ultimately, cost overruns and project delays. In this context, the present study proposes an automated master scheduling system that employs the hybrid simulation paradigm to develop an integrated supply chain model. The developed method is implemented in a case study of a residential prefabricated panel producer, with the results demonstrating the effectiveness of the developed system in expediting master schedule generation while boosting supply chain resource utilization.

Virtual reality-based (VR-based) design reviews can help facility operators identify operability issues during preconstruction and prevent rework costs during construction. However, because VR benefits have not been documented in the construction industry, project managers have difficulty understanding them and typically do not implement VR-based design reviews. To quantify the benefits of VR use during preconstruction, we conducted a comparative case study through qualitative content analysis, interviews, and workflow modeling. We compared two buildings of a facility construction project: one where operability issues were identified through VR-based design reviews before construction and one where operability issues were not identified and had to be resolved during construction, leading to field rework, requests for information, and change orders totaling at least $100,000. Thus, this case study provides insights that may encourage project managers to consider using VR for detecting operability issues during preconstruction.

This paper studies a resource-constrained project scheduling problem with stochastic activity durations and multi-skilled resource constraints. Robust project scheduling is employed to tackle uncertainty. We name it the robust resource-constrained project scheduling problem with multi-skilled resources (RRCPSP-MR). The objective is to schedule the starting times of activities and allocate multi-skilled resources reasonably in order to maximize the robustness of the project schedule in the presence of activity duration variability. An optimization model is constructed to formulate this problem. Based on the NP-hardness attribute of the problem, a resource allocation heuristic algorithm is developed to obtain satisfactory solutions. In addition, a demonstration case is executed to show the problem clearly and verify the effectiveness of the proposed model and algorithm. It renders further proof that multi-skilled attributes of resources can improve the robustness of baseline schedules.

Design for manufacturing and assembly (DfMA) is an engineering methodology which aims to increase ease of manufacture and efficiency of assembly by considering manufacturing and assembly constraints in the design process. However, current DfMA approaches in the construction sector are not automated enough to identify the design features that may cause project delay in real time. This leads to longer design cycle. Also, current scheduling algorithms rely on human intervention to generate activity network from a design output. Addressing these inefficiencies, we propose an interpretative machining learning model to predict the construction duration given a design output. More importantly, the same model identifies the design features that may cause the most delay in the project. The model is trained on a residential design dataset with various features, such as layout, geometry, and element typology. The output of the model is the project duration and an importance map, indicating the influence each feature of the given design has on the total project duration. The results from this model can considerably reduce the design cycle by supporting architects to create fabrication and assembly aware design even when they have little knowledge of production and assembly processes. This model will contribute to a novel computational approach for DfMA.

Green infrastructure (GI) helps manage localized and riverine floods by reducing stormwater runoff and protecting floodplains. GI practices that reduce flooding risks and enhance infiltration include permeable pavements (PPs), rain gardens, and bioswales, among others. PPs are among the frequently used GIs for stormwater management and mitigation of flood risk because they allow more rainfall to soak into the ground and can be easily used in urban areas (i.e., in parking lots and roadway shoulders). While previous research on PPs focused on their benefits and engineering properties, little-to-no studies were conducted to optimize their maintenance practices. Hence, this paper aims at filling this knowledge gap. First, the maintenance, repair, and replacement process of PPs was modeled. Second, an agent-based simulation was developed to model the maintenance-related considerations of PPs. Third, an optimization module was integrated into the developed agent-based model to determine optimal maintenance strategies. The developed agent-based optimization model was applied to New York City’s network of PPs to help the city optimize the maintenance of its GI assets by minimizing the total incurred cost of maintenance operations. The findings indicated that the optimal strategy includes 13 service teams, a replacement policy, and 12 maintenance periods after which replacement is required. This study adds to the body of knowledge by proposing a dynamic agent-based model that could be used to improve the functionality and lifespan of PPs, which would ultimately assist in reducing flooding and help communities implement optimal GI strategies.

Various studies aimed to optimize the schedules of repetitive projects using line of balance (LOB) via different meta-heuristic optimization techniques. However, most studies considered constant productivity rates to complete activities’ units, disregarding the stochastic nature of the construction methods. This paper aims to minimize the uncertainties of the total project duration in non-serial repetitive projects using non-dominated sorting genetic algorithm II optimization (NSGA II). This is achieved through (1) developing a generic scheduling module for repetitive projects using best practices for LOB, (2) utilizing Monte Carlo simulation to assess the effect of uncertainties of crews’ productivity rates on the total project duration, and (3) implementing NSGA II to optimize the total project duration and minimize the overall standard deviation of the stochastic project schedule. The presented model would thus help planners and decision-makers to define the optimal schedules that decrease the uncertainties in meeting the scheduled project due date, thus decreasing the overall project risk.

Natural environments potentially have positive impacts on stress recovery by restoring depleted sources. Integrating natural objects into the built environments can create a restorative built environment. On the other hand, some factors, such as visual stimuli and their properties, can impede the design intentions of such restorative environments. Differences between visual properties of natural environments may change restorative effects by affecting human attention. This study aims to investigate the impact of the size of a green wall on restoration, stress, and attention in a virtual office environment. Twenty participants were recruited to experience two comparable environments with different green wall settings, a large and a small green wall. During the experiment, participants’ physiological responses, heart rate (HR), electrodermal activity (EDA), stress index (SI), and eye movements were measured to assess their stress and attention. The restorative state scale survey was administered after each environmental exposure. The results showed that there were no significant differences between responses recorded in two different settings. A small sample size may explain these results since higher restoration and stress reduction were expected in a virtual environment with a large green wall. In addition, comparing physiological responses during the stressor task and restoration in each session showed the restoration effect of exposing to both virtual environments with a green wall. The results are further explained using the green wall size selection, importance of including a non-green wall condition, and the impact of sample size.

Construction sites with high worker and equipment density tend to have elevated accident rates. One of the main fatalities is unexpected collisions during the execution of construction projects. These safety uncertainties increase the need for travel path planning, a component of construction site layout design used for obstacle and collision avoidance. The increasing scales of construction projects require a realistic simulation of collision and obstacle avoidance planning. This study aims to explore the feasibility of using an immersive visualization to project an automated path planning by introducing computer aided virtual environment for building information modeling (BIM CAVE). To achieve the current stage of using BIM CAVE in construction management, a systematic literature review was conducted. After evaluating the advantages of using this tool, this study verified the great potential of BIM CAVE on construction site path planning to improve safety and productivity by walking through the virtual construction.

This paper presents a simulation model for optimizing the allocation of resources in construction projects. The model was designed to help construction companies manage their resources, particularly heavy equipment, which accounts for a significant amount of the direct cost of any project. The model simulates the different projects considering various factors, including project schedules, equipment costs, and availability, to help program managers make informed decisions about allocating their owned resources across the other projects that are working concurrently. The simulation model provides a more flexible and dynamic plan for equipment management, reducing idle time and rental costs. The model was validated through a case study of a construction company with multiple projects of varying types, sizes, locations, and complexities. The results show that the simulation model achieved a 17.45% decrease in costs and a reduction in idle time, thus improving the operational efficiency of the construction company.

Construction firms face considerable risks that might lead to business bankruptcy. Failed construction companies leave behind unfinished projects, which leads to huge losses to project owners. While previous studies were conducted to understand the factors that contribute to the bankruptcy of construction organizations, little to no research was performed to quantitatively assess the risk of construction business bankruptcy. Hence, this paper addresses this knowledge gap by developing a fuzzy model for predicting the probability of business bankruptcy of construction companies. First, the following six failure warning signs were considered: financial management system, borrowed credit, estimating and job-cost reporting, project management, business plan, and communication. Second, 22 business-related attributes were identified and included in the proposed decision-support tool. Third, fuzzy membership functions and linguistic rules were developed based on expert consultation. Fourth, the Mamdani method was utilized for the inference and composition of the fuzzy linguistic terms. Finally, demonstrative case studies were presented to show the use of the developed fuzzy model and decision support tool. The results compared the risk of business bankruptcy for different scenarios as well as investigated the impacts of different combinations of business warning signs on the probability of bankruptcy. The findings also highlighted the importance of having early warning mechanisms for business management in the construction industry. This paper adds to the body of knowledge by developing a predictive model that helps construction companies forecast the risk of bankruptcy and take the needed corrective actions to avoid business bankruptcy.

Modularization is associated with various project benefits including cost savings, schedule reduction, improved quality, among others. However, successful implementation of modular projects requires early collaboration and proactive management of various associated risks. Both project communication structures and early engagement of all project stakeholders have a great impact on risk mitigation efficiency in modular construction. The goal of this paper is to study the stakeholders’ contribution in risk control of modular construction projects under different delivery methods. To this end, the authors followed a multistep methodology including (1) literature analysis to assign 17 modular risks among the various project stakeholders; (2) Monte-Carlo simulation to valuate risk control contribution associated with each stakeholder and their subset coalitions; and (3) cooperative game theory to compute the risk control contribution of each stakeholder under three different delivery methods including design-bid-build (DBB), design-build (DB), and integrated project delivery (IPD). The findings show that suppliers and contractors have the highest contribution in risk control when compared to owners and designers. Furthermore, the results indicated that IPD increases risk control capacity of contractors and subcontractors due to the ability for open communication between owner, designer, and contractor with the modular suppliers or subcontractors. Ultimately, this paper contributes to the body of knowledge by offering an unprecedented framework that captures the impact of delivery methods on risk control capabilities of stakeholders in modular construction projects.

This paper presents the development of a novel AR-based learning application named Social Presence-Enabled Augmented Reality (SPEAR) that presents opportunities for online peer learning through mobile devices. The app was developed using an AR Foundation framework in the Unity game engine. The learning module included in the app is structural beam-bending. The app allows users to place 3-dimensional (3D) virtual models of structural beams into the real-world environment. The users can then change the load and its position on the beam. A C# script for the finite element method was created to simulate the beam’s deformation based on the magnitude of load and load positions. In addition, the moment and shear diagrams based on the load and load position can be visualized in real time. Moreover, the voice chat feature was added to the application using a cloud-based server, Voice for Photon Unity Networking (PUN) 2, which delivers the feeling of social presence that is integral to online learning. This study demonstrates the technical feasibility of developing advanced visual and interactive learning materials for online engineering students in AR environments. As a prototype online-learning platform, the SPEAR app will allow researchers to test different learning theories and learning material designs generating new knowledge to improve online engineering learners’ motivation, self-confidence, and performance.

With the shortage of skilled labors in recent years, there is a pressing need for utilizing robots to perform repetitive and heavy construction tasks. Reinforcement learning (RL)-based robots become a promising solution because of their robustness and adaptability to unseen scenarios. However, long training time and complex reward design for these robots remain challenging. An effective solution is to collect expert demonstrations as inputs to better initialize policies of RL agents, or directly train inverse reinforcement learning (IRL) agents to recover reward functions. Therefore, this paper proposes a comprehensive virtual reality (VR)-based platform for expert demonstration collection. To show the effectiveness of our platform, a collaborative long-horizon construction task is implemented. We gathered 20 expert demonstrations as input to train a behavior cloning (BC) model. Results showed that the learned policy achieved reasonable success rates in completing the task, indicating the effectiveness of our demonstration collection platform.

Cognitive load is a metric that reflects construction workers’ mental effort during task performance for perceiving information and stimuli from the working environment. Potential cognitive impacts of human-system interaction must be evaluated carefully, specifically when proposing innovative display methods to improve traditional construction assembly patterns. However, identifying cognitive load during task performance is difficult because of the lack of directly observable features. This research proposed a deep learning classification of cognitive load and task conditions to address this problem based on an electroencephalogram (EEG)-centered physiological measurement. The study recruited 30 subjects to assemble medium-sized wood frame walls with an augmented reality (AR) conformal model. EEG was used as a neuroimaging technique to collect subjects’ brain rhythm signals. The task conditions (relax and observe, and assemble) were assigned to represent two different levels of cognitive load. The one-dimensional convolutional neural network-long short-term memory (1D CNN-LSTM) was deployed to classify the subtasks based on the EEG signal. Additionally, comparison tests for performance evaluation with other deep learning networks (1D CNN and LSTM) were conducted. The outcomes validated the usability of the proposed approach for identifying different task conditions with cognitive loads, which provides a prediction accuracy of 93.60%. Moreover, it suggested a promising application of workers’ activity recognition based on the EEG signal classification.

Augmented reality (AR) has been proven to be an effective tool for providing instructive information to users. This characteristic of AR could be used to alert construction workers to avoid potential safety issues such as struck-by accidents and near-misses. Therefore, this paper proposes a near-miss alerting framework for construction equipment that utilizes an AR interface driven by reality and BIM models. The framework includes the 3D virtual environment generation, AR real-time localization and object interaction, near-miss detection, and AR visualization. We developed struck-by incident scenarios with construction equipment and BIM models in a virtual environment that could be used with AR devices in the real world. The AR system includes a location-based near-miss detection method that detects moving objects around the user and alerts them through the AR interface. The system is tested in real-world settings, and the preliminary results show that AR could potentially enhance situational awareness for construction workers.

The construction industry often relies on subcontracting, where subcontractors bid for portions of a project before general contractors bid for the entire project in a process referred to as multi-stage bidding (MSG). MSG can be complex, and winning bidders may be burdened with underestimating their bids and encountering the winner’s curse. Despite various studies investigating this issue, further research is necessary to examine bidding strategies for subcontractors. This paper addresses this research need by exploring and comparing how bidding strategies based on reinforcement learning and game theory could aid subcontractors in mitigating the winner’s curse in MSG. The authors used a multi-step research methodology comprised of (1) formulating an MSG framework; (2) incorporating MSG game-theoretic bid function as the adopted game theory-based strategy, and modified Roth-Erev algorithm as the adopted reinforcement learning-based strategy; and (3) comparing the results of the two bidding strategies using an MSG simulation model. Results revealed that the reinforcement learning-based bidding strategy was more effective in mitigating the winner’s curse for the subcontractors in MSG compared to the game theory-based bidding strategy. Ultimately, this research may improve subcontractors’ pricing practices and support them in managing the complexities and uncertainties inherent in MSG decision-making.

Over the past years, the construction industry has been significantly impacted by the growing demand for efficient delivery of high-rise buildings in urban areas. Due to the magnitude of these projects and the multitude of crane-demanded tasks involved, the use of multiple tower cranes in such projects is common. However, the high congestion levels and logistic constraints in urban areas often encounter overlapping areas between tower cranes. Therefore, the planning of crane operations that considers overlapping areas is essential; however, past research has not explored this aspect sufficiently. This study aims to address this problem by investigating the influence of the number and size of overlapping areas on project completion time. To achieve this, we developed a simulation model to generate and simulate various scenarios associated with multi-crane operations with respect to the mentioned parameters. The study adopts a recently developed agent-based method for crane operations that minimizes the constraints imposed by overlapping areas (e.g., collision-related delays) and maximizes the benefits of these areas (e.g., accelerating material delivery to high-demand areas). Finally, the study simulates the construction of an actual high-rise project to evaluate various cases for positioning overlapping areas and explores the most time-saving strategy.

A core feature of digital twins (DTs) is the dynamic connection between a physical asset (or system) and its representative virtual model. Across the dimensions of various DT architecture types, the geometric dimension is foundational for use on AEC projects. While mechanisms for maintaining a dynamic connection between physical and digital geometry do exist, they tend to involve replacing existing information (e.g., progressive scan-to-BIM processes), rather than dynamically updating pre-existing geometric information. To support the latter vision, this paper presents an automated model updating architecture specifically for geometry by considering shape, pose, and topology parameters. Functional demonstrations are used to illustrate how this framework can be applied to different facets of building construction systems.

This study explores the potential of generative artificial intelligence (AI) models, specifically OpenAI’s generative pre-trained transformer (GPT) series, when integrated with building information modeling (BIM) tools as an interactive design assistant for architectural design. The research involves the development and implementation of three key components: (1) BIM2XML, a component that translates BIM data into extensible markup language (XML) format; (2) natural language-based architectural detailing through interaction with AI (NADIA), a component that refines the input design in XML by identifying designer intent, relevant objects, and their attributes, using pre-trained language models; and (3) XML2BIM, a component that converts AI-generated XML data back into a BIM tool. This study validated the proposed approach through a case study involving design detailing, using the GPT series and Revit. Our findings demonstrate the effectiveness of state-of-the-art language models in facilitating dynamic collaboration between architects and AI systems, highlighting the potential for further advancements.

Floor tiles are regarded as one of the most essential building materials in the construction industry. Nevertheless, inaccurate planning of the tiling layout of a building would lead to a significant increase in material wastage. Building information modeling (BIM) is one of the excellent design platforms that have enabled design improvement and concomitant reduction of material wastage in the construction industry. However, in tile installation, it is essential to prioritize, equally, both the architecture of tiling (by complying with industry standards) and waste-reduction measures. Therefore, this study developed a BIM-enabled dynamic algorithm with the aid of Autodesk Revit software to generate an optimal floor tile layout for a given user’s plan. The results of experimentation showed that the proposed method reduced wastage through efficient reuse of tiling. Additionally, a reduction in discarded tile area was observed, which ranged from 4% to 17% for selected tiles of different sizes in each tiling layout. Moreover, the algorithm was able to provide optimal tiling options through compliance with industry standards while ensuring the upkeep of aesthetic values.

Accidents caused by falling debris from buildings keep happening in densely populated cities in the US, even in cities with mandatory façade safety inspection programs (e.g., NYC, Boston, and Chicago). One of the major challenges in the current façade safety inspection program is the lack of systematic guidance for inspectors to comprehensively check façade conditions on-site. To address this challenge, the authors envisioned an approach to generate a list of applicable defect types for any given building façade. Building information modeling (BIM) has been leveraged to decompose facades into components and link them to applicable defects. The developed mechanism has been tested to generate checklists for 12 common façade components on real facades. The results of this work can be considered by inspection companies and city agencies for approving/rejecting inspection findings to improve their work processes for comprehensive inspections.

Digital twin, with captured as-is information, provides potential for condition monitoring and inspection of the built environment. However, the state-of-the-art digital twin lacks a systematic approach to observing the environment and communicating information to the facility manager due to the incomplete data description capabilities. In addition, capturing as-built geometric information would enhance the digital twin towards smart facility management, but the current employment of 2D computer vision provides limited support to reflect the building conditions for maintenance management. Therefore, this paper presents an AI-based digital twinning approach for automated joint 3D scene reconstruction and semantic enrichment to incorporate the as-is information of the built environment. Two works are researched sequentially: the first concerns integrating BIM data schema with Sensor Model Language (SensorML) to enhance sensor description capability for assorted information queries, and the second focuses on an automated 3D reconstruction and defect detection to enrich digital twin with the as-is condition of the built environment. It is envisaged that the research will contribute to a new method to enhance the digital twin for the built environment including a scientific approach for data mapping between the BIM domain and sensing domain and a new framework for capturing accurate as-built geometric information on the digital twin.

Using extended reality technology (XR; including virtual reality and augmented reality) to visualize 3D models can enhance collaboration in the construction industry. Despite its potential, there has been limited exploration into how XR can be effectively used as a collaboration tool for architecture/construction project. To address this gap, this paper investigates the use of XR technology for different types of BIM-based collaboration. Firstly, the types of collaboration in the construction industry were investigated and defined, including internal, external, and cross-disciplinary collaboration. This paper also provide framework, which covers XR technology attributes such as information, accessibility, and interoperability. Based on the investigation, it is possible to diagnose the current status of XR technology application, and it will contribute to propose a suitable XR system for various conditions of model-based collaboration.

Infrastructure, which encompasses highways, rails, ports, terminals, energy, and telecommunication systems, is critical to sustaining productivity expansion, living standards, and stability. These projects widely rely on different skills and sources of capital. There is also widespread consensus that infrastructure complexities are often difficult to predict. Managing and controlling all these inputs for balancing different project sides play critical roles in this context. These processes can, however, be automated, and their duration and costs are reduced with emerging technologies, specifically blockchain technology and digital twins for infrastructure projects. Using decentralization in the construction industry can be advantageous for applications that make subjective and transparent decisions on complex and large infrastructure projects. There are currently no systems that can process large amounts of data efficiently while simultaneously taking into account user information to facilitate the development of such technologies. This research focuses on identifying data-driven techniques for automating data extraction from decentralized autonomous organizations (DAO), using volunteers (voters) for assistance.

In this article, we present a novel approach for automating the process of laying roof insulation panels, which involves leveraging intelligent technologies to streamline the process. The proposed solution includes reading IFC content for material information from the design side, utilizing deep learning algorithms to identify roof insulation panel materials, and taking photos and verifying them with OpenCV after the roof insulation panels have been laid. By automating the process of identifying and verifying materials, the solution can improve the efficiency of the roof insulation panel laying process, reduce errors, and increase overall productivity. The article outlines the technical details of the approach, including the use of machine learning algorithms, and discusses the potential benefits and limitations of this approach. Ultimately, this research contributes to the ongoing efforts to automate construction processes, reduce labor costs, and improve the quality of construction projects.

Although extensive research has been conducted on BIM-based VR applications, the current approach has often been limited to specific software, resulting in a lack of information on other BIM and VR software programs. Therefore, the objective of this study is to provide an assessment of the multiple data conversion processes between different BIM and VR software programs through a compatibility test. The compatibility test was conducted for two sample BIM models: Duplex Apartment and Office; and the retention rate of model objects from BIM to VR was measured. Results showed that SketchUp to Unity process using FBX file format produced the highest retention rate (i.e., 99.59% for Duplex and 100% for Office). This study helps to inform appropriate technical pathways to convert BIM data to VR and aid in the decision-making processes for practitioners in given conditions.

With a focus on the automation of construction, this paper presents a literature review and overview of how digital twins can be used in construction and their potential applications. A digital twin is a digital, intelligent counterpart of a real-life object, human, process, or building, which is uniquely linked to its physical twin, establishing a one-to-one correspondence between them. Construction projects involve a huge amount of information creation and sharing among the project team. Hence, a large amount of data is generated in each project which needs to be created, analyzed, and made accessible to everyone working on the same building. A digital twin offers additional value over the use of building information models (BIM) to manage the construction process because of its potential to update using real-time progress and simulate forecasted conditions. Unlike digital twins in manufacturing, digital twins for construction are still poorly understood. The temporary nature of construction and the dynamic nature of the sites make monitoring of construction processes and resources difficult. To address this issue, this paper explores the use of digital twins in construction processes. It discusses the use cases of digital twins and their potential application in construction contexts. It is observed that sequencing tasks/processes, navigation, forecasting, and setting up data-enriched 3D models to simulate construction processes can all be potentially mirrored using digital twins with more innovations in existing technology in construction.

Structural simulation models using pre-defined assumptions and values of material properties usually produce results that differ from the real structures with varying degree of accuracy. This is commonly attributed to two broad types of uncertainties, namely aleatory (related to inherent randomness) and epistemic (related to lack of knowledge). Sources of such uncertainties include material properties, construction techniques, aging, and natural or man-made hazard-induced damage. Accurate computational models with on-time model updating capabilities are important goals in engineering research and practice for monitoring the structural health during the operation stage and for making rapid and well-informed decisions following extreme events, for example, major earthquakes. Moreover, the advances and recent adoption of artificial intelligence technologies bring effective and innovative solutions for the structural model updating endeavors. In this paper, a novel model updating method is proposed using two deep reinforcement learning algorithms, namely, Advantage Actor-Critic and Asynchronous Advantage Actor-Critic. In addition, transfer learning is adopted, which generalizes the trained model to various scenarios and enhances the computational efficiency. Through several computer experiments, the results demonstrate the high accuracy and computational efficiency of the proposed approach, which brings about its promising potential for practical engineering applications.

Change detection between as-planned building information modeling (BIM) and the as-is point cloud requires significant computational overhead, because it must deal with every geometric face in the BIM and every point in the point cloud one-to-one. To address this problem, our previous study presented an efficient data structure for change detection with a ray-trace algorithm. However, this approach is expected to be problematic when the BIM mesh is sufficiently large that there are special cases wherein its edges do not penetrate among the modifiable nested octree (MNO) nodes that need to be indexed. To make up for this limitation, the current study applied convex polyhedra intersection. The results of our experiments showed that the proposed method overcomes the previous study’s BIM mesh indexing problem. Furthermore, it presented a significant computation performance improvement in comparison with the previous approach: 13.6 and 1.1 times faster for two test datasets, respectively.

Building information modeling (BIM), a novel technology in the architectural engineering and construction (AEC) industry, contains various data and information, which is so practical and can be required by many stakeholders during the project’s life cycle. For non-technical users with limited or no skill in dealing with BIM software, access to this data can be time-consuming, and tedious. Automating the information extraction from BIM models can efficiently address this need. In this regard, this research proposes an artificial intelligence (AI)-based framework to facilitate information extraction from BIM models. Therefore, the user can ask questions and receive answers from the framework. Utilizing natural language processing (NLP), an ontology database (IfcOWL) and an NLP method [latent semantic analysis (LSA)], the purpose of the user is understood by the framework through syntactic analysis and semantic understanding of the question and answer to the user, based on functions. The results show that the speed of answering the questions in this framework is up to five times faster than the manual while maintaining high accuracy.

To achieve global climate goals, a greater focus needs to be on the energy-efficient conversion of the existing building stock in industrialized countries. To prioritize the retrofitting scenarios of large stocks of existing buildings, holistic life-cycle assessments (LCA) help to consider the environmental impacts in the decision-making. To enable the effortless creation of large building stock information, we propose a methodology to automatically create semantically rich 3D models for calculating the LCA of retrofitting variants. Robustness is achieved by providing flexibility toward input data, for example, geometric reconstruction based on different point clouds, such as laser scans, drone-based photogrammetry, or derived from Google Maps. Similarly, various image sources are used for the semantic enrichment of windows, such as from hand-held devices or Google Street View. Using a case study, we compare the performance of the geometric reconstruction, test window detection, and calculate first LCA results.

The construction industry has undergone a technological shift. Technology advancements have made robots a topic of discussion in construction. One challenge to overcome is how the robot receives information from designed BIM models. This study describes the methods employed for parametric modeling and generating model content of wall systems in Autodesk Revit added with a Dynamo script. Coordinates are determined for components based on model geometry and dimensions. Once generated, components are placed with the required material based on wall parameters. This research develops a method to add components based on wall materials from a traditionally modeled BIM extracting information such as location, object identifier (ID), type, and orientation which is formatted to transfer to the robot based on the needs of the robotic system as a list of tasks in a comma-separated values (.CSV) file. This study details the development process and early implementation of the Dynamo script.

Digital twin (DT) is designed to monitor a physical asset and improve operational efficiency by collecting real-time data, enabling predictive maintenance, and improving decision-making across the project life cycle. This research aims to deliver a basic understanding of DT and propose a framework that outlines the applications of DT in the construction industry. Ten academic publications about the DT topic within the construction industry were selected, identified, and organized. The research investigates three main objectives of the DT concept: (1) to define the general concept of DT, (2) to discuss the challenges found in the construction industry, and (3) to analyze the current research and propose future directions. In addition, this research is expected to find the gap in the research on DT in the construction sector. The study shows that by adopting DT, the industry can transform itself into a highly efficient, productive, quality-centered, and enable solutions to its challenges.

The utility sector has historically been challenged with poor information on subsurface utilities, leading to problems such as utility strikes, subsequent delays, and cost overruns. Emerging technologies such as a digital twin (DT) are being proposed to better capture subsurface utility data to minimize some of these problems. This study reviews the state of the practice of DT in the utility sector to pave the way for future research direction. The study involved selecting and critically reviewing relevant papers in two databases. The review’s outcome shows that DT adoption in the utility sector is still nascent, and more academic research is needed for significant advancement. It was also observed that the most advanced implementation of DT can be found in the water sector, while other utilities only implemented geometric DTs. Also, the problem of accurately locating existing subsurface facilities for easy maintenance or upgrade continues to linger.

The systems that support construction and maintenance planning for delivering the road digital transformation lack the up-to-date road data and digital processes to leverage them. Digital twins recently disrupted the infrastructure sector and can now serve as a fundamental building block to help address this problem. Digital twin differs significantly from a static design-stage BIM model. It can span across the road’s life cycle for reflecting the physical twin’s properties, updating data continuously, and improving connectivity. However, no implementation of such digital twin solutions exists on the horizon for infrastructure. The important items that have not been defined yet are workable digital twin data structures and cloud architecture. This study aims to develop a proof-of-concept digital twin data structure and an integrated cloud architecture that are able to support road products and processes. The outcomes of this research are the proposed data structures and developed road digital twin integrated cloud architecture. As reliable references, these data structures benefit people by applying digital twin technologies to facilitate road construction and O&M processes and improve the decision-making processes.

Current inspection and maintenance practices for bridges involve periodic manual visual surveys which are time consuming and cumbersome due to number of bridges in need of assessment. Unprecedented capabilities have become possible in recent years thanks to strides made in sensing technologies, computer vision, and machine learning. These technologies can be integrated into a digital twin framework for better insight into a bridge’s structural integrity, maintenance needs, and potential risks. A digital twin framework involves creating a virtual model that mimics the behavior and performance of a physical bridge. Data collection about a bridge’s physical condition is the first step in developing a framework. Physics simulation and graphical environment are next needed to host relevant models of the bridge. An illustrative example involving these steps and digital twin use for scenario simulation for different mechanisms is provided. The example focuses on modeling of a railway bridge in Lyndhurst, New Jersey.

This study aims to investigate critical factors that impact the performance of steel construction projects in Egypt when considering the use of building information modeling (BIM). A group of Egyptian practitioners and experts were selected to engage in a structured questionnaire survey, which helped define 22 factors that were categorized into three stages: pre-construction stage, construction stage, and general project performance. Relative importance index and dispersion analysis were conducted, and the findings indicated that “accurate BOQ and cost estimation” and “visualizing the construction process” are top-ranked factors. “Supporting construction and project management” comes second, whereas “planning of construction methods” and “facilitating understanding of the construction process” come in the third place. Therefore, in the context of adopting BIM, this study can inform strategies for performance improvement of steel construction projects in Egypt and potentially other developing countries.

Bridge textual reports capture technically detailed data/information about bridge conditions and maintenance actions, which offers opportunities to improve the prediction of future bridge conditions for further bridge maintenance decision-making support. To automatically analyze these reports, there is a need for relation extraction methods to extract relation information from the reports for linking recognized entities with predefined semantic categories (e.g., caused by) and representing the extracted semantic relations in a structured way. To address this need, this paper proposes a deep learning-based relation extraction model. The proposed model utilizes convolutional neural network (CNN) to encode sentence-level features, and bidirectional long short-term memory (BiLSTM) to build a relation extractor to capture the patterns of the predefined relation types. The proposed model was evaluated in extracting relations from multiple types of bridge-related textual reports for representing bridge defect information—including relations among bridge entities—in a semantically rich structured way.

Sustainability, particularly in the architecture, engineering, and construction (AEC) sector, is gaining worldwide importance as a result of the climate emergency. The AEC sector accounted for over a third of the global energy demand and approximately 37% of energy and process-related worldwide CO₂ emissions in 2021, factoring in projected emissions from the production of building materials. There has been a growing interest in the AEC sector toward digital twins due to their ability to monitor an asset’s greenhouse gas emissions in real time. However, the current emphasis of digital twins with respect to sustainability is mainly on energy consumption, with less focus on the embodied CO₂ emissions resulting from changes in building materials during operations and maintenance (O&M). This paper puts forth a framework to create digital twins for built assets, which would enable comprehensive carbon tracking during the O&M phase. This includes not only energy consumption but also the CO₂ emissions associated with changes in materials.

Despite the fast development of building information modeling (BIM) and its associated benefits, the adoption of BIM in stormwater drainage projects is still at its early stage. In this paper, the latest drainage design modeling standards and practices of 10 state departments of transportation in the US were reviewed. Furthermore, the interoperability between drainage models and industry foundation classes (IFC)—the International Organization for Standardization (ISO) standard for BIM was studied. It was found that although the state-of-the-art drainage modeling software can support interoperability with IFC, there are research gaps to be addressed to achieve seamless interoperability such as the lack of distinction in IFC entities for representing different drainage components (e.g., inlet, conduit, etc.). Solutions to fill the gaps were proposed such as consistent and comprehensive modeling standards/protocols and automated classification for drainage components leveraging invariant signatures, to support the life-cycle management of transportation infrastructure projects with BIM.

Due to dynamic organizations and unexpected conditions on project sites, the construction industry has suffered from schedule and cost overruns. Researchers have applied building information modeling (BIM) and supply chain management (SCM) concepts to integrate diverse stakeholders, and further, improve efficiency in construction projects. BIM can support supply chain integration (SCI) by providing reliable up-to-date information on a project, which reduces resource waste and completes the project as planned. Specifically, sharing updated material information, including the state of material fabrication, current location, each material’s due date on site, and site inventory status, is crucial for successful project execution because such data changes often. However, current information sharing via BIM is limited in order to achieve the desired level of supply chain integration. By capturing the state-of-practice and state-of-the-art, this study compiles the status of information sharing using BIM and the suggestions of BIM application against the desired level of information sharing to support supply chain integration. The results provide information sharing maturity in the construction industry and which areas need to be improved to achieve the desired level of information sharing. Based on the results, the study aims to suggest a direction for future research on material information sharing using BIM.

Road pavement condition is crucial information for maintaining infrastructure integrity, assuring road safety, and optimizing maintenance costs. However, historical condition data of urban pavements condition are not usually available because there is no technology that can evaluate pavement conditions in a low-cost and efficient way. On the one hand, this research proposes a system capable of obtaining and processing pavement images to evaluate urban pavements. On the other hand, a deep learning model is trained with over 50,000 images of 13.2 m × 2.6 m of asphalt pavement from different zones of Santiago, Chile. Following the processing of these images, the following distresses were manually labeled with two different levels of severities: patches; potholes; and transversal, longitudinal, and fatigue cracking. Finally, the distresses are measured using the dimensions of the artificial neural network’s bounding boxes. The artificial neural networks (ANNs) proposed for this research are YOLOv5 and YOLOv7.

Blockchain is a distributed ledger technology that verifies and records transactions simultaneously across a computer network, offering data dependability, traceability, and immutability. It has gained attention in the architecture, engineering, construction, and operations (AECO) industry. However, to justify its deployment costs, it is essential to identify where blockchain can generate the most value. This study proposes that the operations and maintenance (O&M) phase of a building’s life cycle, which has a significant environmental, social, and economic impact, can yield a higher return for blockchain. A literature review was conducted to investigate the implementation of blockchain in AECO, revealing a need for more attention to O&M. Inspired by the insights from the review and existing blockchain deployment frameworks, a high-level decision-making framework for blockchain adoption in O&M was developed. The paper also discusses various opportunities, challenges, and future research questions for a successful implementation of blockchain in buildings’ O&M.

Asset tracking is increasingly necessary for better management of offsite and onsite construction progress for modular construction projects. Delayed delivery of elements from prefabricated plants would postpone the construction progress, resulting in economic losses, disputes, and change orders. To certify these works transparently and precisely, a tamperproof digital asset tracking system is important. Blockchain can be the potential solution due to the immutability and trustworthiness of its record, while building information modeling (BIM)-based digital twins can provide rich semantic information on building assets. However, current studies have not achieved sufficient collaboration for automatic asset tracking and change visualization. To address the limitation, this paper proposes an integrated BIM-based blockchain framework based on smart contracts. First, assets and their semantic information, as well as construction schedule with the dependency among their relevant activities, are automatically transmitted from BIM to the blockchain, where corresponding QR codes are generated to attach physical assets. As their physical tracking data are updated in the blockchain, if any delay, the potential changes will be automatically propagated to all affected activities by executing compiled smart contracts. Once stakeholders certify these changes, the affected activities with corresponding assets are automatically visualized in the 4D environment for timely notification and collaboration. We also develop a prototype system to validate this framework’s feasibility in a trusted and traceable way.

This study investigates the synergies of integrated simulation approaches using building information modeling (BIM) and agent-based modeling (ABM) in construction. These modeling approaches in construction have been bridged by observing the movements of project participants (e.g., laborers, pedestrians), particularly in environments with spatial and temporal constraints. The key objectives of this study are to investigate (1) the issues integrated BIM-ABM modeling can address, (2) the functions each model performs, and (3) the benefits of such an integrated model. To this end, this study employed a systematic review of scholarly literature focusing on applications and synergies of BIM-ABM integration in the construction industry. Studies in this space primarily focused on the optimization of job site evacuation and project management. In the studies, simulation results highlighted benefits to construction projects through supporting safety at work, reduced construction costs, and enhanced productivity.

Construction waste has always been the primary source of solid waste. In the United States, more than 600 million tons of construction and demolition wastes (CD&W) are generated annually, and plenty of construction waste, including concrete, bricks, and wood, will be landfilled directly. In recent years, people gradually realized the importance of reducing construction waste and developed a variety of methods to address the problems. However, there are still millions of tons of recyclable and reusable materials thrown away during the building demolition process because there is a lack of systematic understanding of options with respect to material types, conditions, and the complex value chains of a circular materials system, which leads both the demand and supply sides to underestimate building materials’ salvaged value. The paper sets out to address the problem by proposing a general framework that focuses on constructing a knowledge graph to evaluate building materials’ potential salvage methods based on material type, usage duration, weather conditions, and local policy. Once the fundamental framework is established, the objective is to integrate the knowledge graph with BIM in order to automatically determine the condition of materials for salvage. This includes quantifying reusable and recyclable building materials and deducing their appropriate salvage methods.

With the COVID-19 pandemic accelerating the convergence of physical and digital, all aspects of real life are transformed into the infinite virtual world, the metaverse. As the metaverse takes shape and begins to mirror every piece of human experience, industries have started seeking transformational new opportunities beyond gaming. However, the utilization of metaverse in the construction industry is relatively low, while other sectors are already harvesting from the new unlimited world. To this end, this study first defines the noticeable features of the metaverse that are relevant to construction activities through systematic review and natural language process (NLP). Required technology milestones and critical challenges to realize the construction-metaverse (Con-Metaverse) are then identified through the NLP and review. The potential applications of the metaverse for construction are also discussed. This study is expected to expand the potentiality of metaverse to enhance its implementation in the construction industry.

A reasonable signage layout can reduce evacuees’ operational delays during emergencies. Building information modeling (BIM) with detailed signage information is essential for automatic checking and improving the signage layout. However, in current practice, exit signs of buildings are presented mostly in 2D drawing formats rather than in BIM. Manually adding these signages into BIM is time-consuming and labor-intensive, and reconstructing them with on-site data requires considerable device costs and workload. Hence, there is a need for a convenient, low-cost, and widely applicable approach to extract signage information from 2D drawings and add them into BIM. Related works on 2D drawings mainly focused on architectural and structural components, but those methods cannot directly apply to exit signs. This study proposes a deep learning method combined with pre-set rules to detect and locate exit signs from 2D drawings. The extracted information is expected to enrich existing building models.

New digital technologies instigated by Industry 4.0 are driving digital transformation across various industries. One of the most recent concepts attracting attention in the research and industrial community is digital twins (DT). Remarkable advancements as a result of DT adoption have been seen in manufacturing and automotive industries; however, much less adoption has been seen in the construction industry due to challenges such as industry key players’ technology-averse attitudes and a lack of evidence of the costs and benefits of DT adoption. This paper presents an exploratory investigation into the cost and benefits of DT implementation in the construction industry from the perspective of early adopters. Interviews with these adopters revealed that beyond the initial software and hardware cost, there are significant costs related to staff training, implementation time, and employer/employee adoption resistance. We propose a set of considerations and guidance for researchers and industry practitioners interested in DT implementation.

This research focuses on “3D building modeling” and “static and dynamic information integration environment” from the perspective of the digital twin. It demonstrates the effective use of the digital twin for visualizing information associated with a 3D environment, such as sunlight exposure and temperature, which are used as comfort indexes. Furthermore, the developed platform provides real-time display and analysis of the campus environment through the intuitive dashboard. Compared with the previous 3D information platforms, which are mainly based on static information display and pre-simulation, this research proposes a real-time information management environment through the combination of virtual 3D objects within the 3D WebGIS interface, the customized server, and the database, which can dynamically update the information of objects when events occur in reality. National Taiwan University is used as a study case to show how the digital twin helps make decisions from multiple scenarios and provides real-time suggestions.

With the rapid urbanization and increasing complexity of infrastructure systems, there is a growing need for innovative and efficient methods to monitor and maintain these assets. The advent of digital twin technology and advancements in computer vision have opened new avenues for utilizing crowdsourced data to improve infrastructure management, monitor conditions, and prioritize maintenance activities. This study presents a novel approach for estimating the camera pose of crowdsourced images, enabling their integration into digital twin models without requiring explicit location information. This method mitigates data privacy concerns, promotes cost-effective monitoring, and enhances stakeholder communication by aligning 2D image data with 3D digital twin models. A case study demonstrates the proposed methodology’s effectiveness and adaptability in real-world situations, showcasing its potential for fostering resilient and sustainable urban environments.

Recent developments in data modeling provide the means of aligning model information between competencies. However, due to different problem-solving approaches between disciplines, this is not sufficient to permit cross domain reasoning. A higher level of semantics is necessary for concept transfer between expertise domains. Our research defines a milieu for creating conceptual frameworks across architectural and structural design of cross laminated timber (CLT) and other mass engineered timber (MET) buildings through modeling explicit functional relationships between building components and design task tracking. MET products are a reliable and cost-effective alternative for mid-rise construction due to their resilience and suitability for prefabrication. Moreover, the maturing North American forestry stock ensures onshore resource availability for the US AEC industry. With this approach, graph-based internal conceptual models are explicitly represented to support decision making and design interaction tracking. Methods are demonstrated through flexible space allocation, structural design adaptable to global geometry at the component level, and an explicit informative layer where domain knowledge and decisions are declared. Moreover, the graph structure can be used to localize change tracking, aiding in version control. Finally, a case library prototype is demonstrated with the intent of disseminating best practice solutions in this new construction medium and facilitating their applications for learning practitioners.

Buildings create a huge amount of information throughout their life cycle. The major information loss occurs during the building handover from the construction team to the owner. Communication of vast amount of information generated through the building life cycle is complex, error prone, and is insufficient, especially during commissioning stage, leading to unavailability of necessary information to the building owner and occupants. This research reviewed strengths and weaknesses of the current approaches to information management through the building life cycle. The research found that limited research has been focused on information management at the commissioning stage of construction and beyond. In addition, the research explored the requirements for adequate commissioning and digital technologies which can be used as potential solutions for efficient commissioning. It was found that digital technologies such as BIM, DT, AR, smart interactive system, and tools can lead to better communication and visualization of real-time building information.

Water damage restoration is a complex and time-sensitive process that, if not addressed quickly, results in catastrophic results such as long-term structural damage, mold growth, and health hazards. Recent advancements in technology such as building information modeling (BIM) and infrared thermography (IRT) can facilitate water restoration projects by detecting and diagnosing problems. Current water damage restoration contractors rely on Xactimate for cost estimation, and this practice includes a manual process for sketching damaged areas and specifying materials. In this respect, this study proposes a technique for cost estimation in water loss restoration projects using a combination of BIM, IRT, and Xactimate. The proposed approach offers a faster and more accurate method for cost estimation, which can lead to improved project outcomes. Overall, the proposed approach presents a promising strategy to improve the efficiency and accuracy of water loss restoration cost estimation, ultimately leading to improved project outcomes and cost savings.

Nuclear power plants (NPPs) depend on precise procedures for safety and efficiency. These procedures contain work instructions detailing both sequential and conditional tasks. However, executing conditional tasks—tasks performed under specific conditions—often poses difficulties for operators. The hurdles lie in recalling crucial information, spotting key cues, and reacting appropriately to significant plant events linked to these tasks. Current computer-based procedures (CBPs) also fall short in autonomously generating operator reminders when conditional tasks are activated due to these tasks’ lack of computer interpretability. This paper presents an ontology: a computer-interpretable representation of conditional tasks. The ontology supports reason about potential events, suitable responses, task constraints, and potential hazards related to the procedure. A case study demonstrates the ontology’s effectiveness. Future research will focus on refining ontology and investigating automatic critical information extraction methods.

Digital twins are virtual counterparts of objects throughout their whole life cycle. This multi-industrial concept is gaining increasing interest, also in civil engineering, reflecting the interdisciplinary integration of industries. The virtual collaboration following the digital twinning idea will be based on multi-industrial standards, which forces a general paradigm not dedicated to an isolated industry. Therefore, also civil engineering community spotted the need for adopting comprehensive digital twinning. Nonetheless, the ongoing works still lack the principles driving the practical implementations. Therefore, this article proposes characteristics of digital twins of bridges. The proposed characteristics address the specificity of bridges and civil engineering practices but also follow general concepts of the digital twinning idea. The characteristics can be perceived as a part of a framework guiding the creation, utilization, and interpretation of digital twins of bridges.

The integration of 5D building information modelling (BIM) into mega rail projects has the potential to significantly enhance cost control and management. However, the implementation of 5D-BIM solutions has been a challenge due to technical, functional, and governance-related issues. This paper presents a conceptual framework that supports financial decision-making, enhances project management, and promotes efficient project delivery. The framework proposes a set of interrelated elements that include project governance, BIM policies and standards, digital platforms, BIM LOD, cost estimation classification, and continuous improvement. The proposed framework recognizes the importance of project governance in providing direction and structure for 5D-BIM implementation, while BIM policies and standards ensure that the BIM models produced meet the required standards of quality. Digital platforms provide a foundation for multiple users to create, access, share, or exchange project information. BIM LOD facilitates collaboration and coordination among all project stakeholders, while cost estimation classification aligns the estimating process with the development of project scope and financial decision-making processes. Continuous improvement is critical to optimizing processes and increasing efficiency, resulting in higher quality outcomes, greater stakeholders’ satisfaction, improved project performance, and an environment of innovation and learning.

Construction 4.0 (C4.0) technologies have the potential to revolutionize the architectural, engineering, and construction (AEC) industry by providing a safe and productive work environment for the workforce, which results in decreasing project costs and duration. However, the concern about the future of workforce careers has increased as the AEC industry is labor intensive and C4.0 technologies make their way into all projects’ phases. This study explores the critical challenges of C4.0 technologies for the workforce in the AEC industry through the existing literature. The results reveal that adopting C4.0 technologies reshapes projects’ dynamics and organizations’ structures and cultures, which is called routine-biased technological change. The results also demonstrate that demand changes in the job market and increases in the wage gap are the two main challenges of digitalization and automation for the workforce. The outcomes of this study help decision makers advance the uptake of C4.0 in the AEC industry.

Industry foundation classes (IFC) can facilitate quantity takeoff (QTO) from building information models (BIMs). In this paper, a Cartesian point-based computing method (named the automation extraction method, or AEM) was introduced to get the area of polygonal-shaped building components from IFC-based BIM. The AEM was implemented using Python programming language, tested on a sale area and a utility room of a commercial building, and adopted in an undergraduate construction management (CM) course project to help students gain experience with computing in CM tasks. The result using the AEM was compared to a manual extraction and calculation method. Results showed the difference from the manual QTO was within 1%, and it took stably less time in finishing the task with AEM. Post-project survey results showed about 49% students indicated the AEM method and exercise helped improve their understanding of computing concepts and applications in the architecture, engineering, and construction (AEC) domain.

Building information modeling has been widely adopted in the construction industry in the last decade. To better prepare students for the construction industry’s needs nationwide, many construction programs either have a BIM course in the curriculum or integrate BIM topics in various courses. Construction-related BIM topics include information modeling, design coordination, clash detection, process virtualization, virtual design and construction, and various integration with technologies such as virtual reality, augmented reality, drones, and laser scanners. Researchers have advanced BIM studies in recent years. However, the implementation of BIM courses still varies widely in construction management programs. These courses may be taught at different levels, and the content varies significantly among instructors. The authors investigated BIM course learning objectives, outcomes, and contents at various universities and concluded common topics that are essential in the course. Findings suggest that BIM can be taught in four approaches to help construction students understand the various applications of BIM in different project phases, including design, construction, and operation and maintenance. Furthermore, the findings provide valuable insights for educators to improve BIM courses to meet the needs of the construction industry. This paper emphasizes the importance of BIM education and provides recommendations for teaching BIM courses in construction management programs.

The need to prepare students for the workplace, shortage of skilled labor, and fast-paced changes in the industry necessitate improvements in the pedagogical frameworks of educational communities. Practitioners are required to provide practical insights, rigor, and realism to complement academia pedagogic efforts in construction education. However, this is being plagued by several complexities. Leveraging advances in computational techniques, this paper presents the considerations of practitioners and instructors in workforce development collaborations as inputs for a graphical user interface of a technology-driven matching platform for connecting professional and educational communities. Practitioners’ considerations are students and specific course-support related, while instructors’ considerations are related to practitioner suitability, project, and company characteristics. The study contributes to human factors principles in user interface design as well as user-centered design principles by highlighting information requirements of a collaborative network of instructors and practitioners. The findings of this study also provide insights to enhance industry-academia collaborations.

In order to teach technical skills, which are fundamental in construction and engineering education, educators rely heavily on practical and hands-on experiences. With limited available class time and resources, instructors face the difficult task of trying to provide real-world experiences to enhance student learning. In response to this need, virtual construction simulations have been widely explored across higher education as a method to enhance student learning and simulate practical experiences. Augmented reality (AR) and virtual reality (VR) experiences have grown significantly over recent years as technology continues to develop and provide additional teaching opportunities. This paper will conduct a thorough literature review and analysis of works that report on AR and VR construction education applications. Specific AR and VR trends emerged from the research which included the teaching focus of the simulation, type of device utilized, reasoning for implementation, as well as the benefits reported which will all be further summarized and analyzed in this study. The contribution of this work is in guiding future developers to leverage consistently reported benefits or to explore understudied applications of AR and VR in construction education to enhance student learning.

Construction engineering and management (CEM) domain covers multiple evolving sub-disciplines and directions. To understand those directions, numerous research efforts have conducted scientometric analysis of publications to explore their significance and impact. Despite their valuable insights, such research endeavors have been limited to exploratory analyses, whereas no previous attempt has been conducted to predict the future impact of research in CEM. This study fills this knowledge gap by performing a predictive analysis of citation metrics of publications in CEM using machine learning (ML). The developed model was trained on a dataset of 93,868 publications using an XGBoost algorithm. Testing showed that the model could predict high-impact research after 5 years from publication with an accuracy of 80.71%. Further analysis of the predicted model results identified “project planning and design,” “organizational issues,” and “information technologies, robotics, and automation” as the top forecasted CEM research subdisciplines that are anticipated to attract high citation counts. Ultimately, this research contributes to the CEM body of knowledge with a framework that can predict future citation trends, which can help guide researchers and stakeholders in academia identify research and funding opportunities.

The availability of 3D datasets is crucial for the development and testing of scan-vs-BIM and scan-to-BIM solutions, which are active fields of research in the architecture, engineering, and construction (AEC) research community. However, most of the publicly available datasets do not include building information models (BIM)—currently a common practice in the AEC industry—nor laser scanner-generated point cloud datasets. To address this gap, this research presents LivingBIM, a dataset of a recently constructed academic building that includes as-designed BIM models, as-built 3D point clouds, semantically segmented 3D point clouds, and panoramic images for a single facility. Moreover, this dataset includes mechanical and electrical rooms to represent some of the geometric complexities in AEC projects. The availability of this dataset can enhance the development and testing of ML models and other algorithms for the AEC industry.

Water treatment plants (WTPs) encompass complex processes, presenting challenges for both control algorithms and human operators. Traditional anomaly detection often requires human intervention, and both parties exhibit limitations when handling system anomalies. This study introduces a “digital twin” model of water systems, enhanced with an extended reality (XR) interface, designed to capture and replicate operators’ anomaly detection strategies. The objective is to overcome the difficulties associated with tracing and interpreting operators’ behaviors, which are often due to inadequate process pattern mining methods. The proposed approach is fourfold: (1) a water system digital twin equipped with simulation models and a virtual reality (VR) interface, (2) process capture for inspection and operation, (3) visual trajectory pattern mining for knowledge discovery, and (4) an augmented reality interface to guide workers. Experimental results indicate that for simulated anomaly inspection and detection, the computer’s recall was 0.712, whereas human operators achieved a recall of 0.851. A combination of both yielded a higher classification recall of 0.885. Knowledge transfer predicated on specific observations could address pressing WTP challenges, including a shortage of experienced operators and unreliable fault recovery systems.

Fall hazard is one of the leading causes of fatalities in the construction industry. To alleviate fall risks, the US Occupational Safety and Health Administration (OSHA) agency developed safety regulations for construction project team members. However, retrieving relevant information on fall protection from OSHA’s text-heavy standards is a challenge for personnel with limited safety knowledge and experience. With the rise of Industry 4.0, chatbots have become increasingly popular, offering a solution to the information overload in the architecture, engineering, construction, and operations (AECO) industry. This research aims to develop a dataset for building and validating intelligent construction safety chatbots (CSCs) to improve the efficiency of information retrieval from safety regulations (i.e., OSHA) using fall protection as an example. This research uses two state-of-the-art language models, Text-To-Text Transfer Transformer (T5) and Generative Pre-trained Transformer 3 (GPT-3), to generate natural language questions from US OSHA textual regulations about fall protection. The performance of the two models in question generation is compared and evaluated. The evaluation shows that T5 generates questions that are more relevant and diverse in structure and question type in comparison to GPT-3. Based on the evaluation results, the T5-generated questions are used to build a CSC dataset. The developed dataset can be used to train and evaluate a CSC, and the developed method can be extended to other fields, such as building codes and contracts. The contribution of this research is that it facilitates the adoption of transfer learning and chatbot technologies in the AECO industry.