Journal of Construction Engineering and Management

The architecture, engineering, and construction (AEC) industry invests significant resources in executing construction projects. However, contractual construction disagreements (CCDs), such as conflicts, claims, and disputes, frequently arise between contractual parties, leading to additional costs, prolongation costs, liquidated damages, or extension of time, to name a few examples. Although prior studies offer some insights, there still needs to be a more comprehensive and systematic identification of different digital technologies useful to prevent, mitigate, or resolve CCDs. This study fills this gap by exploring two primary research questions: (1) What digital technologies have been identified to manage contractual disagreements in the AEC industry? (2) How might artificial intelligence (AI) facilitate the digitalization of contractual disagreement management in the AEC industry? This study followed a rigorous systematic review protocol and used the Transparent Reporting of Systematic Reviews and Meta-Analysis (PRISMA) framework to identify 82 peer-reviewed articles published from 2000 to 2023. The findings demonstrated that AI, distributed ledger technologies, and building information modeling are the most dominant digital technologies in managing CCDs in the AEC industry. The study presents a conceptual framework that maps the benefits of AI and other digital solutions in facilitating conflict prevention, claim mitigation, and dispute resolution. The findings have valuable benefits for industry practitioners seeking to enhance CCD management. Moreover, the identified research avenues pave the way for future exploration and advancement of digital solutions in managing CCDs.

Abstract

The construction industry consists of various sectors that have different needs and functions. Those sector-specific differences create different risks that construction professionals empirically know. However, there is no documented and unbiased assessment to validate the empirical knowledge. Identifying the varying spectrum of risks present in different construction sectors in a systematic manner can facilitate more effective and efficient sharing, learning, and adoption of proven construction project management methods across these sectors. Ultimately, this can lead to significant improvements in construction productivity as a whole. This research analyzed risks in different construction sectors, including the commercial building, industrial, and civil infrastructure sectors in a comparative and quantitative manner. Project risk registers from the three construction sectors were analyzed using fuzzy set qualitative comparative analysis and coincidence analysis. The study identified various risk configurations in each sector, as well as their similarities and dissimilarities. Based on the findings, an ideal path to the utilization and dissemination of advanced construction management strategies and methods across the construction sectors was developed. These results are expected to assist project participants and stakeholders in adopting and implementing advanced project planning, delivery, and management strategies derived from other construction sectors while taking into account different risks.

Practical Applications

The construction industry possesses a wealth of effective and proven construction project management knowledge and know-how that holds the potential to enhance productivity. Despite these resources, the industry still faces productivity challenges. One contributing factor is the industry’s isolated nature, which makes it difficult to share and disseminate knowledge and know-how across construction sectors and the industry as a whole. Identifying similarities and differences across the construction sectors is one prerequisite for promoting seamless knowledge sharing and dissemination. These factors influence the level of modifications and adjustments for successful implementation in different construction sectors. In this background, this study identified similarities and dissimilarities in project risk spectrums across construction sectors in a comparative manner. Ideal pathways for sharing and disseminating knowledge and know-how were proposed based on the observed risk spectrums. The findings aim to streamline the sharing and dissemination of construction management expertise by offering direction for evaluating and selecting appropriate project planning, delivery, and management strategies. Such insights, which take into account different project risk spectrums in different construction sectors, will contribute significantly to improving productivity throughout the construction industry.

Blockchain, essentially a distributed and immutable database, has emerged as a potential solution to governance problems of accountability, transparency, and trust in the construction industry. In terms of construction quality management (CQM) applications, previous works mainly took a technical perspective, and little is known about the potential of blockchain-based governance for quality opportunism. Moreover, we have seen very few successful blockchain implementations in construction practices. Stakeholders meet the trade-off between potential benefits and risks in blockchain adoption decisions. Previous works mainly focused on barrier analysis, neglecting the dynamic interactions of stakeholders’ strategic behaviors on adopting blockchains. Against this backdrop, this research aims to systematically analyze blockchain impacts on CQM from a governance perspective and then investigate the owner and the main contractors’ strategic behaviors (e.g., adopting blockchains in CQM or not). The agency theory was used as the theoretical lens to examine how blockchain curbs contractors’ quality opportunistic behaviors as a governance mechanism. An evolutionary game theory model was developed to simulate adoption decision interactions between the owner and the main contractor. Finally, policy suggestions were highlighted for policymakers. This research could be one of the first studies examining blockchain potential to CQM from an opportunism governance perspective. Such discussions could inspire more discussions on blockchain-based governance and broaden researchers’ and practitioners’ understandings of blockchain impacts. The proposed policy suggestions from the equilibrium analysis could facilitate blockchain diffusion in the construction industry.

Climate change is increasingly exacerbating water shortages worldwide. Among the various repercussions of water scarcity, notably in developing countries, the most critical are the decline in social sustainability and the widening inequality within farming communities. In response, irrigation reforms aimed at establishing farmer-managed networks have been introduced to foster equitable water distribution and enhance the livelihood and food security of underprivileged farmers. However, these reforms have largely fallen short of achieving their social sustainability goals. A significant factor in this shortfall is the farmers’ limited capacity and reluctance to assume roles typically filled by bureaucracy under institutional reforms. This study explores farmers’ willingness to engage in a World Bank-assisted participatory irrigation infrastructure program. We utilized questionnaire surveys and hierarchical analysis to evaluate how various factors influence farmers’ willingness to participate. The findings indicate a multifaceted challenge that intensifies in communities fragmented by socioeconomic and political divides. Particularly, the predominance of large landowners in agricultural communities and the absence of sufficient bureaucratic support for participation are key impediments. Our research offers comprehensive insights into the regional sociopolitical obstacles obstructing farmer involvement in government-led participatory projects. It also guides policymakers in grasping the intricate interplay between program design, execution, and contextual elements, which is crucial for the sustainable development of resource-stressed areas.

The growth of the global construction market has attracted international companies to participate in overseas projects. Overseas projects are extremely dynamic with numerous uncertainties, raising the need to collect information about construction in host countries. Due to the vast amounts of text data in the construction industry, an automated method, specifically information retrieval, is required to find the necessary information. Previous studies have suggested automated methods to review various construction documents. However, these studies required substantial manual effort and mainly focused on only one language, resulting in loss of vital information because it is buried in documents written in the host country’s language. To address these limitations, this study proposes a cross-lingual information retrieval (CLIR) framework using pretrained Bidirectional Encoder Representations from Transformers (BERT) models to retrieve information from multilingual construction documents. The proposed framework employs language models (i.e., monolingual, multilingual, and cross-lingual) and trains these models on a construction data set to enhance their ability in construction-specific text. The framework achieved reliable performance of retrieval, even with minimal additional training using domain-specific data. The results indicate that training on the domain data set raises the level of retrieval, increasing the mean reciprocal rank of a specific task by up to 0.2128. With the employment of a monolingual model with machine translation, CLIR in a specific domain could be performed effectively without the need for a labeled data set. The suggested CLIR framework offers a practical alternative for dealing with construction documents in overseas projects, reducing time and cost while improving risk identification and mitigation.

Abstract

Carbon emission reduction (CER) in the construction industry can aid in achieving the international community’s carbon neutrality target. However, the low motivation of construction enterprises to reduce carbon emissions and the unsatisfactory effect of CER are still unresolved issues. This study aims to address these issues by constructing a building supply chain (BSC) consisting of a developer and a contractor using government subsidies and cost-sharing contracts. The optimal government subsidy and feedback equilibrium strategies of the BSC are examined using a combination of differential game theory and numerical simulations. The findings demonstrate that (1) cost-sharing contracts may enhance developer and contractor profits and building CER, goodwill, and demand without relying on government subsidies; (2) when subsidized by the government, each equilibrium strategy meets or exceeds the performance of the centralized model, with the cost-sharing contract having a negligible effect on the enhancement of each equilibrium strategy; and (3) both the game structure and the positioning of construction enterprises in the BSC are connected to the number of government subsidies. The city of Shenzhen, one of China’s first low-carbon pilot cities, provides a realistic environment for the simulation analysis, with the Block K residential building in Nanshan District serving as a case study. Furthermore, this work contributes to the body of knowledge by proposing a novel CER model for the BSC using differential game theory. The research provides new insights into the role of government subsidies in shaping profit distribution, game structure, and enterprise positioning. Findings demonstrate the value of cost-sharing contracts in improving CER, goodwill, demand, and profits when implemented collaboratively. This advances the theoretical understanding of incentives and strategies for promoting CER in construction.

Practical Applications

This research highlights the importance of collaborative efforts between the government and the building supply chain (BSC) to promote sustainable construction and carbon emission reduction (CER). The study found that government subsidies can be an effective tool to encourage developers and contractors to adopt CER practices. However, relying solely on subsidies is insufficient—collaboration through mechanisms such as cost-sharing contracts can further enhance sustainability outcomes when enterprises work together. To facilitate low-carbon construction, the government could provide subsidies for developers’ promotional and marketing activities as well as funding for contractors’ research and development of sustainable materials and technologies. Financial incentives such as tax breaks and preferential lending for potential homebuyers can also accelerate consumer demand. Ultimately, creating a supportive environment where enterprises proactively pursue CER creates a win–win situation where the BSC becomes more sustainable while firms improve their branding and profitability. The insights from this research highlight the need for a multipronged approach. Governments play a key role through policy and financial support. Realizing the full potential of sustainable construction also requires active participation from developers, contractors, and consumers. By outlining optimal strategies and incentives, this study provides valuable guidance to construction industry stakeholders seeking to implement CER collaboratively.

When projects suffer noncompletion, state highway agencies (SHAs) may trigger liquidated damage (LD) provisions, and at times, contractors may challenge their enforceability. Normally, to be compensated for the costs expected during the delay, states design the LD schedules by associating LD rates to specific contract sizes. A review of the literature found that states varied significantly in the LD schedule designs. However, no studies have explored the relationship between the LD rates and contract sizes (LDR-CS) across states. Exploring this relationship could lead to identifying the underlying model of the relationship, explaining how states vary the LD rates against contract sizes, running comparative analyses of the states’ LD schedules, and designing optimal LD schedules, among other potential benefits. To realize these benefits, the objectives of this work were to (1) statistically explore and characterize the LDR-CS relationship, and (2) develop a representative model of the relationship. To achieve these objectives, descriptive, box–whisker, and cluster analyses were performed to characterize the relationship, and regression analysis was utilized to search for the best-fit representation model. The relationship was found to be challenging; it had a unique L-shape, and was modeled successfully only using transformed nonlinear regression. The research results could facilitate performing LD comparative analysis among states, help SHAs assess and build confidence in their LD rates, and help update and optimize LD schedule designs. This work contributes to the body of knowledge with new statistical dimensions to comprehend the LDR-CS relationship, providing tables, charts, and transformed nonlinear models.

Prefabricated construction has proven sustainability and affordability through innovative solutions. Prefabricated housebuilding companies, as supply entities, play a vital role toward successful projects using prefabricated products. Many companies go into liquidation due to poor performance. Supply chain management performance is linked with organizational performance in the manufacturing domain. However, there is no performance framework to date for prefabricated housebuilding companies using supply chain management theory. The purpose of this study is to identify the supply chain management interventions in prefabricated housebuilding research and report relevant key performance indicators based on empirical evidence. These indicators were classified under performance dimensions and supply chain processes. These indicators were then checked for relevancy with subject matter by academic and industry experts engaged in prefabricated construction research and practice, respectively. Later an industry-wide Likert scale-based survey was conducted with experienced experts in practice, involved in the prefabricated construction business, for validation of the proposed framework. This study reports 40 key performance indicators, ranked under six principal component bodies of supply chain management, with low to high ranges from marketing to strategic management. The purposive selection is used for industry consultation with experts having practical experience. Survey results show all the indicators are highly significant except “Supplier driven strategy” which is still under a medium range of relative importance index. The top six key performance indicators are “Collaborative networking,” “Quality assurance,” “Entrepreneurial cognition,” “Geographical proximity,” “Intellectual property,” and “Relationship marketing.” The performance framework is suitable for vertically integrated companies involved in design, manufacturing, and construction. The qualitative nature of this framework is highly useful, with implementation ease, for companies to benchmark and gauge performance in a competitive market. This study explored the general supply chain management theoretical intervention for the development of an integrated performance framework as only specific elements were considered previously.

Cameras are one of the most valuable sensors for collecting high-quality visual data on construction sites for uses ranging from surveillance to automated information exaction. The dynamic nature of sites means the visual data from cameras can suffer from occlusions and lack of coverage due to progressing works, hindering the performance of automated visual analysis methods. Therefore, manual planning and adjustments by experienced practitioners are required for appropriate camera placement at the site, which is expensive and time-consuming. Past research has simulated cameras and used algorithms with an objective function to optimize installation parameters with planned site models ranging from two-dimensional (2D) to four-dimensional (4D). However, these models lack information from ongoing site conditions, hampering actual camera performance. This study proposes a camera placement framework incorporating 4D-building information model (BIM) and reality models. The framework first identifies the camera placement determinants through expert interviews. Next, the planned BIM and reality models are used to construct the simulation environment, and camera placement parameters are optimized. The proposed framework is implemented and evaluated on a construction site. 25% average camera coverage improvement from the benchmark solution is achieved. This study further contributes to the potential application of automated visual monitoring systems on construction sites.

Mediation has been promoted as a complementary alternative to traditional adjudicatory resolution methods for settling construction disputes. The use of mediation has been promoted for its time- and cost-saving advantages. The voluntary approach is also considered suitable to the spirit of disputing parties settling their own disputes by themselves and is thus considered a prerequisite design of mediation. Nevertheless, the power asymmetry between disputing parties may hinder bona fide mediation. This study examined the importance of voluntary participation in fostering collaborative mediating behaviors. The impact of power asymmetry on the use of voluntary construction dispute mediation was also explored. With data collected from mediation practitioners and the application of principal component factor analysis, constructs for voluntary participation (VP), collaborative mediating behaviors (CMB), and power asymmetry (PA) were developed. Partial least squares structural equation modeling analyses were then used to test the hypothesized relationships. It was found that (1) the practice of CMB would bring about positive mediation outcomes; (2) VP would engender collaborative mediating behaviors; and (3) PA between the disputing parties would have no significant negative impacts on voluntary attempts at mediation or the practice of CMB. These findings were validated by real mediation cases. This study contributes to construction mediation studies by affirming the importance of keeping mediation a voluntary process. With a flexible process, voluntary mediation can be a tenable option for resolving construction disputes notwithstanding the power differentials between the mediating parties.

Abstract

Over the years, the finance-based and resource-constrained project scheduling problem (FBRCPSP) has been aimed at scheduling activities and offsetting the capital gap without exceeding credit and renewable resource limits in capital-driven construction projects. However, the heuristics proposed for the FBRCPSP in previous studies neglected to focus on identifying efficient priority rules, which are understandable and intuitive for construction practitioners with different roles. Accordingly, this study explores efficient priority rules and evaluates their performance according to modified serial and parallel schedule generation scheme heuristics for the FBRCPSP. First, 11 priority rules that cover the project network, schedule, activity, and resource information are introduced, and three priority rules related to activity information are designed. Second, the two priority rule-based heuristics are applied in an example to generate multiple project schedules according to the different combinations of priority rules and heuristics. Furthermore, the performance of priority rules is tested on the metrics of project duration and profit through numerical experiments. The results show that the priority rules of the latest start time, latest finish time, and old great rank positional weight are the three best priority rules in general. Additionally, the priority rules evenly present more stable and superior results than those obtained by other priority rules for the different levels of weekly fixed overhead cost and the scenarios of contract terms. Based on the intuitive heuristics, the selected efficient priority rules assist contractors in deciding which priority rule should be applied in practice, and project managers can employ an effective priority rule to establish a baseline schedule in the initial project phase and quickly adjust the plan when it becomes infeasible for project execution.

Practical Applications

This study evaluates the performance of frequently used priority rules on finance-based and resource-constrained project scheduling heuristics in construction project management. The model and priority rule-based heuristics can be embedded into project management software or digitalized scheduling platforms in practice. Moreover, project managers can employ efficient priority rule-based heuristics to generate a desirable project schedule for mastering cash flow and resource-demand plans in the project planning stage. Intuitive priority rules are incorporated into the heuristics to quickly adjust or update schedules and financing alternatives for project management when a baseline schedule is disrupted during the project execution. In addition, practitioners can obtain more adaptive or efficient priority rules following the testing approach proposed in this work if they have rich similar project experience or big data in construction projects. In summary, this study offers construction project schedulers or managers practical scheduling strategies and approaches for addressing finance-based and resource-constrained construction projects.

Phase planning is one of the most important components of lean-based production planning that provides basic guidelines for the entire production process. In modular integrated construction (MiC) projects, the complicated and drawn-out features of the manufacturing or production process pose difficulties for informed phase planning decisions under uncertainties. However, owing to the nascent nature of MiC, traditional approaches have little prior knowledge of the uncertainties. This research aimed to address this problem by proposing a data-driven optimization method based on a set of valuable historical production data to hedge against uncertainties during production. A real-life case study was then conducted to validate this optimization approach. The planning solution, including the (1) critical production path, (2) detailed production schedules, and (3) simulated production process, balances production schedules and uncertainties to ensure feasible and robust phase planning. This optimization method can make full use of historical production data rather than approximations of the probability distributions to handle uncertainties in the phase planning process. This research provides an innovative and robust solution for MiC production managers to efficiently conduct phase planning under uncertainties. It enriches the literature on phase planning and contributes to lean MiC manufacturing. The biggest novelty of this research is to open up a window for researchers and practitioners to look into MiC production in factories, which are traditionally like a “black box” unknown to us.

Abstract

To ensure the safety of tunnel construction, it is necessary to accurately and timely measure the deformation of the shotcrete liner during the management of the construction process. The light detection and ranging (LiDAR) technique, known as the reality reproduction technology, provides a new solution for deformation measurement. However, the nonsmooth defects of shotcrete liner and the scattered noise points caused by the nearby dust, as well as a large number of nontunnel structures such as pipes, construction machinery, and vehicles in the obtained tunnel point cloud datasets, hinder the application of point clouds in deformation measurement of shotcrete liner. In this paper, a ring simulation sampling (RSS) method for automatic sampling and deformation measurement of shotcrete liner using the multiepoch LiDAR point clouds is proposed. This method constructs the virtual ring according to shape of the tunnel cross section and emits the rays from the ring to the center of each tunnel cross section. The length difference of the rays arriving at the outer wall of the multiepoch tunnel point clouds is calculated to achieve the analysis of overall and local deformations of the shotcrete liner. The shotcrete liner point clouds generated by the manual modeling and terrestrial laser scanning are tested to validate the effectiveness of the method in extracting the deformation of shotcrete liner. Compared with the conventional total station monitoring, the mean absolute deviation and root mean square error are 1.39 and 1.93 mm, respectively, which indicates that the RSS method could be effectively applied to the deformation measurement of tunnel shotcrete liner.

Practical Applications

Deformation measurement of tunnel shotcrete liner is crucial to safety of tunnel construction and implementation of dynamic parameter design. This study recommends the light detection and ranging (LiDAR) technique. The main work of this paper is to determine whether the tunnel shotcrete lining has been deformed as a whole or locally by comparing the obtained multiepoch high-precision 3D point clouds. Furthermore, the authors propose a method for automatic sampling and deformation measurement of shotcrete liner using the multiepoch LiDAR point clouds. Compared with conventional deformation measurement methods (i.e., the total station and fiber optics) that capture deformation information from a limited number of monitoring points, LiDAR technology enables the high-precision, omnidirectional, and noncontact acquisition of spatial data within tunnels. This serves as a complementary and enhanced tool to tunnel safety monitoring techniques and methodologies. In addition, the adoption of the method proposed in this paper facilitates the quality check of shotcrete liner, including thickness assessment and smoothness detection.

The prefabricated building has been widely promoted in recent years as it can effectively alleviate the conflict between economic growth and environmental resources. However, the development of the prefabricated building has fallen short of anticipated goals under the influence of the dynamic circumstances and behavioral strategies of multiple stakeholders. Understanding the relevant stakeholders’ behavioral strategies and collaborative evolution mechanisms is key to promoting prefabricated buildings’ orderly and efficient development. Therefore, this study combines the evolutionary game theory with system dynamics, introduces Gaussian white noise stochastic disturbance terms to model the complex characteristics of multiagent behavior toward prefabricated buildings, and establishes evolutionary game models and stochastic evolutionary game models for local governments, contractors, and consumers. Subsequently, the influences of strategy choice behavior with or without central government supervision were analyzed to study the collaborative driving mechanism of prefabricated buildings under the multiple effects of the government and market. The findings of this research underscore the necessity for government and market collaboration in championing the sustainable evolution of prefabricated buildings. While central government supervision spurs the growth of these structures, its static reward–punishment approach offers only fleeting collaborative momentum and fails to ensure market steadiness. In contrast, the improved dynamic incentive and disincentive mechanism can effectively control fluctuations in the evolutionary process, which is critical in achieving stable development and collaborative governance toward prefabricated buildings. This study contributes to the body of knowledge by broadening the horizons of evolutionary game theory applications and providing a perspective for understanding the behavioral strategies driving the development of prefabricated buildings by both government and market forces. Therefore, a series of driving mechanisms is proposed, providing theoretical guidance and practical insights to prompt the long-term development of prefabricated buildings more effectively.

Abstract

In order to solve the problem of lack of appropriate tools in the lean construction of construction projects, a framework of digital lean construction is proposed as a whole, and its management platform is implemented for construction phase by integrating lean construction with digital technologies. The concept of digital lean construction is proposed, its management model is constructed and refined, and the corresponding management platform is implemented for the construction phase. The framework is verified by holding an expert workshop and applying the management platform to typical construction projects. The research contributes not only to the establishment of the theoretical foundation to upgrade lean construction, but also to accelerating the transition from lean construction to smart lean construction. Two directions of future research are expected, i.e., to enhance the integration of the lean tools and digital technologies and clarify the transition to smart lean construction.

Practical Applications

Due to the complexity of lean construction and the lack of tool support, its widespread application have not been found significantly up to now. The development of digital technologies provides a potential solution to address this issue. Based on the integration of lean construction and digital technologies, a framework that includes management models and a management platform for digital lean construction was established in this paper. Then, a management platform was developed and applied to verify the management framework. It facilitates not only the efficient collaboration of the participants, but also the easy application of lean principles in the projects. The framework is expected to enhance quality, reduce management costs, and improve management capabilities in the projects. It provides a theoretical foundation for lean management and digital transformation upgrades of enterprises to drive changes in construction industry production methods and the corresponding management practices, promoting the high-quality development of the construction industry.

Abstract

Complex risk factors make metro construction safety accidents prone to occur, and there are various types of accidents. Accident reports record detailed information about different types of accidents in text form. However, effectively utilizing such unstructured data presents a significant challenge. Text mining (TM) provides a viable foundation for addressing this challenge, but related studies have limitations in risk feature extraction and lack of in-depth analysis capability. To address the deficiencies of existing studies and provide a feasible strategy for identifying key risk factors in the metro construction domain, this paper proposes an integrated model combining TM and machine learning–based Bayesian networks. Firstly, the term frequency-inverse document frequency (TF-IDF) algorithm in TM was used to separately extract the direct and indirect cause factors from the accident reports, with the missing factors supplemented using the TextRank algorithm. Then, depending on the assumption of whether to consider the conditional independence between factors, an improved naive Bayesian network (NBN) and a tree-augmented naive Bayesian network (TAN) were built based on the extracted factors and the corresponding accident types, respectively, for further in-depth analysis. Finally, the training set was divided to train the two network models, and sensitivity analysis was used to identify the key risk factors. Using 162 accident reports from China as an application example, the results showed that TAN exhibited a higher average accuracy (79.62%) in the test set compared with the improved NBN (71.75%), and the importance of risk factors for different accident types was successfully ranked from multiple perspectives using TAN. Meanwhile, some new insights into metro accidents in China were obtained, which can support decision-making for accident prevention and control. In conclusion, this paper effectively addresses the relevant limitations of accident text utilization and presents a novel approach for metro construction safety management.

Practical Applications

Analyzing accident texts can help gain insights from objective historical data to support safety management efforts. However, accident texts are often unstructured and contain a lot of irrelevant content. How to quickly extract valid information from accident text and use it to analyze accidents in depth is of continuous interest to safety managers. In particular, those models that have real-time decision support capabilities in addition to theoretical insights. This paper proposes an integrated model that combines text mining and machine-learning Bayesian networks. This model achieves comprehensive textual feature extraction, multifaceted accident causation analysis, and allows safety managers to input current accident information into the model to obtain real-time decision support for accident prevention and control. Although the proposed model is developed for metro construction, it can be slightly adapted by incorporating the characteristics of accident texts from similar domains to obtain an integrated model suitable for these domains, so as to effectively control the occurrence of safety accidents.

Collision accidents of construction vehicles frequently occur during the construction of building projects. It is difficult to warn of collision risk efficiently by using the safety control methods of on-site inspection and viewing surveillance video. Therefore, a novel collision risk warning model for construction vehicles is proposed in this paper. The model comprises a state awareness module and a collision risk assessment module. In the state awareness module, the YOLOv7 algorithm is used to identify and locate construction vehicles. The DeepSORT algorithm is used for the real-time tracking of construction vehicles. Finally, the state awareness module obtains a wealth of sensing information and provides it to the collision risk assessment module. In the collision risk assessment module, the speed assessment method and the minimum safety distance assessment method of construction vehicles are innovatively proposed and compiled. In the speed assessment method, the speed of construction vehicles is calculated and speeding warnings are performed using the transformation matrix between latitude and longitude coordinates and image pixel coordinates. In the minimum safety distance assessment method, the original surveillance picture is converted into a bird’s eye view (BEV) of the world coordinate system through inverse perspective mapping (IPM). Then the distance of all construction vehicles is traversed, and the visual warning of the minimum safe distance is provided. The effectiveness and robustness of this collision risk warning model were verified by taking three practical projects in different construction stages as examples. The research results show that the mean average precision ([email protected]:0.95) of the construction vehicles collision risk warning model can reach 89.10%, and it has a good tracking effect and an efficient collision risk warning strategy.

Construction operations, particularly concrete formwork, pose significant risks of musculoskeletal disorders (MSDs) to workers. Previous studies have examined the MSDs associated with conventional job-built formwork. In light of the growing popularity of modern ready-made formwork systems, and the claim that such systems reduce MSDs, it is imperative that researchers characterize the activities associated with the use of these systems and offer empirical insight into their relationship with MSDs. In response to this need, this study aims to assess and compare MSD risks related to different modern formwork systems. Specifically, the Rapid Entire Body Assessment (REBA), a method for full-body postural ergonomic risk assessment, was used to study the ergonomic hazards of form workers during the installation and removal of horizontal modular and prefabricated or engineered formwork systems. The findings indicate that most formwork tasks and activities subject workers to medium to high MSD risks, necessitating preventive actions or imminent preventive actions. Modular formwork systems may subject workers to fewer hazardous ergonomic working conditions compared with prefabricated or engineered formwork systems. The findings provide an improved understanding of formwork activities and the MSD risks associated with ready-made formwork system construction, and provide a valuable resource for formwork designers and constructors dedicated to improving worker health and safety in formwork construction.