Complex Construction Projects Research Articles

Automated Classification of Exchange Information Requirements for Construction Projects Using Word2Vec and SVM

This study addresses the challenge of automating the creation of Exchange Information Requirements (EIRs) for construction projects using Building Information Modelling (BIM) and Digital Twins, as specified in the ISO 19650 standard. This paper focuses on automating the classification of EIR paragraphs according to the ISO 19650 standard’s categories, aiming to improve information management in construction projects. It addresses a gap in applying AI to enhance BIM project management, where barriers often include technological limitations, a shortage of specialists, and limited understanding of the methodology. The proposed method uses Word2Vec for text vectorisation and Support Vector Machines (SVMs) with an RBF kernel for text classification, and it attempts to apply Word2Vec with cosine similarity for text generation. The model achieved an average F1 score of 0.7, with predicted categories for provided sentences and similar matches for selected phrases. While the text classification results were promising, further refinement is required for the text generation component. This study concludes that integrating AI tools such as Word2Vec and SVM offers a feasible solution for enhancing EIR creation. However, further development of text generation, particularly using advanced techniques such as GPT, is recommended. These findings contribute to improving managing complex construction projects and advancing digitalization in the AECO sector.

VEIDEA: A Comprehensive Framework for Implementing Building Information Modeling-Based Value Engineering Within a Common Data Environment in Construction Projects

The Architecture, Engineering, and Construction (AEC) industry faces significant global challenges, including frequent project delays, budget overruns, and inadequate stakeholder collaboration. To address these issues, Value Engineering (VE) and Building Information Modeling (BIM) have been increasingly used in large-scale, complex construction projects. Although many studies highlight the benefits of integrating VE with BIM, its full practical potential has not yet been realized. This study aims to investigate the integration of VE and BIM within a Common Data Environment (CDE) to improve decision making and project outcomes. A comprehensive framework was developed, consisting of four interconnected modules: (1) Creating the CDE, (2) Developing the BIM Model, (3) Implementing Value Engineering, and (4) Conducting a Value Engineering Study. Central to this framework is the introduction of the VEIDEA” data bank, a structured system based on the OmniClass classification, which stores and organizes VE ideas. Additionally, the framework incorporates the Analytical Hierarchy Process (AHP) to automate the evaluation phase, assisting designers and VE teams in making data-driven decisions on design alternatives. Empirical results from a case study of an office building show significant cost savings, with a 20% reduction in reinforced concrete (RC) slab costs and a 39% reduction in flooring material costs. These findings demonstrate the potential for integrating VE and BIM to enhance cost-effectiveness and overall project performance. This study offers a novel approach to optimizing project collaboration, decision making, and efficiency in the AEC industry.

PRODUCTIVITY IMPROVEMENT MODELS IN CONSTRUCTION PROJECT MANAGEMENT

The relevance of the research topic is due to the increasing complexity of construction projects, stricter requirements for deadlines, quality of work, as well as increased competition in the relevant industry. In the current conditions, traditional management methods often turn out to be ineffective, which leads to deadlines, budget overruns, and a significant decrease in the quality of construction. The purpose of the study is to analyze and systematize ideas about modern models of productivity improvement in construction project management, as well as to assess their potential impact on key performance indicators of projects. Special attention is paid to the formulation of the author's view of the advantages and limitations of specific models. The study revealed contradictions between the need to introduce innovative approaches to working with projects and the conservative practices that have developed in the industry. In addition, it is advisable to point out the discrepancy between the pace of development of digital technologies and the speed of their adaptation in the construction sector. It is concluded that integrated models combining elements of flexible methodologies, digital developments, and Lean approaches are the most effective. The role of digital twins, predictive analytics, and blockchain in improving productivity in this area is particularly emphasized.

Developing Standard BIM Execution Plans for Complex Construction Projects

This study addresses the critical need for standardizing building information modeling (BIM) execution plans (BEPs) in the architecture, engineering, construction, and operations (AECO) sector. Through the analysis of 36 BEP documents from international organizations, we have identified crucial components and put forth a comprehensive framework with the objective of improving digital transformation and collaboration in intricate construction projects. This study utilizes scientometric analysis to chart the development of BEP standards and incorporates empirical data from industry surveys to verify the suggested framework. The results of our research emphasize the advantages of using standardized building execution plans (BEPs) to decrease inefficiencies and enhance project outcomes. This makes a substantial contribution to the field of building information modeling (BIM) implementation.

Making logistics a central core in complex construction projects: a power-dependency analysis

In complex projects, such as hospital constructions, there are large interdependencies between the actors involved, especially relating to the flow of materials and resources. As new hospital buildings are often built on existing blocks and campuses, ongoing hospital operations may hinder logistics and construction operations and vice versa. To handle these issues, it has become increasingly common to implement construction logistics setups (CLSs). The purpose of the paper is to analyse how the centrality of the CLS in the project organization affects the coordination and conflict level in complex construction project management using a power dependency lens. The study is based on case studies of six hospital projects in the Nordic countries. Based on a cross-case analysis it is identified that: 1) from a logistics management perspective we identify three different foci of the CLS; i) security for hospital patients and staff, ii) on-site material flow coordination, and iii) flow coordination to and from site, and 2) from a project management perspective the main findings point towards the importance of centrality of the CLS in the project management organisation in order to ensure enough power to mandate enforcement of coordination.

Emergency logistics siting-path question for engineering construction projects based on quantum particle swarm algorithm

Emergency material security is the key to post-disaster emergency relief in complex environment engineering construction projects. Aiming at the emergency logistics center site path planning problem, the uncertain parameters of congestion time and maximum rescue time are described using trapezoidal fuzzy numbers, and the emergency logistics site path model of the two-phase engineering construction project is established. A quantum particle swarm optimization model is designed to avoid premature population convergence and maintain population diversity. The particle swarm algorithm uses the quantum spin gate’s rotation angle update to represent the particle velocity update. Taking the engineering construction project in the western mountainous area as an example, the validity and applicability of the model are verified through model comparison and sensitivity analysis. The results of the example show that in the complex environment, the quantum particle swarm algorithm takes 29.35 s in convergence time, and the particle swarm algorithm takes 40.12 s, which is 36.69% higher than the efficiency of PSO. In total cost, the quantum particle swarm algorithm has a total cost of 46,632.40 RMB, and the particle swarm algorithm has a total cost of 48,319.51 RMB, which is 3.62% lower than the cost of PSO. The quantum particle swarm algorithm’s total distance is 550.57 km, and the particle swarm algorithm’s total distance is 579.35 km, 5.23% lower than the total distance of PSO. The model established in this study can scientifically select the location of emergency facilities and formulate the emergency rescue path, reduce the response time of emergency rescue and storage costs, and provide decision support for the scheduling of emergency supplies for engineering construction projects in complex and dangerous areas.

Mitigating Co-Activity Conflicts and Resource Overallocation in Construction Projects: A Modular Heuristic Scheduling Approach with Primavera P6 EPPM Integration

This paper proposes a heuristic approach for managing complex construction projects. The tool incorporates Primavera P6 EPPM and Synchro 4D, enabling proactive clash detection and resolution of spatial conflicts during concurrent tasks. Additionally, it performs resource verification for sufficient allocation before task initiation. This integrated approach facilitates the generation of conflict-free and feasible construction schedules. By adhering to project constraints and seamlessly integrating with existing industry tools, the proposed solution offers a comprehensive and robust approach to construction project management. This constitutes, to our knowledge, the first dynamic digital twin for the delivery of a complex project.

Immersive engineering instruction: Using Virtual Reality to enhance students’ experience in the classroom

With the growing complexity of construction projects, the Architectural, Engineering, and Construction (AEC) sector increasingly requires a skilled workforce. This need is magnified by the challenge of less than ideal retention rates in engineering fields, prompting a search for methods to enhance the learning experience. Virtual Reality (VR) has emerged as an effective tool in this context, offering immersive and interactive learning environments that improve the grasp and retention of complex concepts in engineering. This research assesses the benefits of implementing a VR solution for building inspections in an undergraduate civil engineering program. It compares the use of a VR system against traditional desktop-based inspection techniques and considers cognitive load, user experience, and usability aspects of this implementation. Additionally, it examines how students’ spatial abilities affect their performance with both methods. Results demonstrate that VR does not increase cognitive load and is often perceived as requiring less effort by student users. While both the desktop and VR options produced similar usability scores, the VR implementation provided a much more engaging user experience. These results were replicated and echoed in a second study with actual engineering instructors, who likewise held a strong positive attitude towards the VR system, consistent with student attitudes. Taken together, these results highlight the potential for VR to revolutionize educational opportunities, suggesting that its further adoption and exploration should be prioritized as a useful and viable academic tool. Specifically, these results suggest that VR can enhance the learning process in civil engineering and make collaborative virtual building inspections more efficient and engaging.

Assesment of Quality Management Practice on High-Rise Building, the Case of Banking and Insurance Companies in Addis Ababa

This research focuses on the assessment of quality management practices within the context of constructing high-rise buildings, with a particular emphasis on buildings designated as headquarters for banking and insurance companies in Addis Ababa. The objective of this study is to gain a comprehensive understanding of the various factors that contribute to the successful execution of complex construction projects in this domain. Employing a hybrid research approach that combines both qualitative and quantitative methods, the investigation explores a range of aspects related to quality assurance, monitoring, evaluation, and regulatory oversight. The study explores the impact of inadequate quality management on the overall quality, structural integrity, and safety of high-rise buildings. It also identifies barriers and challenges in implementing quality management practices, as well as performance indicators and metrics for assessing the effectiveness of quality control measures. Additionally, the research delves into monitoring construction activities for compliance with quality control measures and ensuring quality standards for materials used in high-rise construction. Furthermore, it discusses quality benchmarks, standards, and the monitoring and evaluation of quality assurance measures implementation within organizations, including policies and procedures specific to high-rise building projects. Through interviews with various stakeholders, this study aims to provide valuable insights into enhancing the quality management processes in high-rise construction projects, ultimately contributing to the advancement of building safety and integrity in urban environments. Building upon these insights, the research concludes by presenting a series of strategic recommendations designed to enhance quality management practices in high-rise building construction projects. These recommendations span multiple dimensions, including strengthening regulatory oversight, implementing integrated quality assurance policies, establishing comprehensive monitoring and evaluation frameworks, defining quality benchmarks and performance metrics, ensuring robust materials quality control.

Relational contracting in Nordic construction – a comparative longitudinal account of institutional field developments

PurposeRelational contracting is increasingly being applied to complex and uncertain construction projects. However, it has proved hard to achieve stable performance and industry-level learning in this field. This paper employs an institutional perspective to analyze how legitimacy for relational contracting has been produced and challenged in Denmark, Finland, Norway and Sweden, including implications for dissemination and learning.Design/methodology/approachA collaborative case study design is used, where longitudinal accounts of the developments in relational contracting over more than 25 years in four Nordic countries were developed by scholars based in each country. The descriptions are underpinned by literature sources from research, practice and policy.FindingsThe countries share similar problem perceptions that have triggered the de-institutionalization of traditional contracting practices. Models and policies developed elsewhere are important sources of knowledge and legitimacy. Most countries have seen pendulum movements, where dissemination of relational contracting is followed by backlashes when projects fail to meet projected outcomes. Before long, however, relational contracting tends to re-emerge under new labels and in slightly new forms. Such a proliferation of concepts presents further obstacles to learning. Successful institutionalization is found to rely on realistic goals in combination with broad competence development at the organizational and industry levels.Practical implicationsIn seeking inspiration from other countries, policymakers should go beyond contract models to also consider strategies to manage industry-level learning.Originality/valueThe paper provides a unique longitudinal cross-country perspective on the field of relational contracting. As such, it contributes to the small stream of literature on long-term institutional change in the construction sector.

Dynamic Bayesian Network-Enabled Approach for Organizational Leadership Measurement of Complex Construction Projects

Dynamic Bayesian Network-Enabled Approach for Organizational Leadership Measurement of Complex Construction Projects

Building Engineering Cost Prediction Based On Deep Learning: Model Construction and Real - Time Optimization

Effective project planning, risk mitigation, and stakeholder satisfaction in the construction business are greatly impacted by accurate cost projection. Overspending, setbacks, and ruined projects are all possible results of imprecise cost estimates. For this reason, it is critical to guarantee the viability and success of a project by increasing the precision of cost predictions. Construction project complexity, a myriad of cost variables, and uncertainty are the obstacles that building engineering cost prediction must overcome. Predictions made using traditional approaches are commonly inaccurate because they fail to fully account for the complex interplay between project factors and expenses. Advanced modelling techniques that can handle complicated data and changeable project contexts are necessary to overcome these obstacles. An approach based on deep learning called Deep CostNet for Building Engineering Technique (DCN-BET) Cost Prediction is presented in this research. Its purpose is to solve the problems associated with building engineering cost prediction. The approach uses deep neural networks to extract intricate patterns from massive amounts of project data collected over time. Improved prediction accuracy and real-time optimisation during project execution are made possible by DCN-BET, which captures the nonlinear correlations between project characteristics and costs. Risk assessment and management, cost forecasting for resource allocation, and project budget estimation and planning are among the few of the many construction industry uses for DCN-BET. The effectiveness of DCN-BET is assessed by conducting thorough simulation analyses in contrast to more conventional cost prediction approaches. Training and testing the model with real-world building engineering datasets allows us to evaluate its accuracy and efficacy in project cost prediction. The results show that DCN-BET has the capacity to support real-time optimisation and significantly improved the accuracy of cost predictions, which improved the overall success and efficiency of the project.

Simulation of autonomous resource allocation through deep reinforcement learning-based portfolio-project integration

Resource allocation has always been a critical challenge for construction project planning, and it affects the cost, duration, and quality of the projects. However, current methods mainly focus on a single project and lack integrated planning and optimization across a construction company's multiple projects. This paper describes a simulation of an Autonomous Resource Allocation (ARA) model using Deep Reinforcement Learning (DRL) agents and methods like Double Deep Q-Networks and combined experience replay to develop and test ARA algorithms based on data harvesting from the Internet of Things (IoT) devices. The results show that DRL can successfully perform ARA by capturing the complex interactions among resource allocation features, without needing retraining when situations change. It shows promising future possibilities for construction companies to improve resource utilization and project performance for larger and more complex construction projects.

Applications of digital twin technology in construction safety risk management: a literature review

PurposeWith increasing complexity of construction projects and new construction processes and methods are adopted, more safety hazards are emerging at construction sites, requiring the application of the modern risk management methods. As an emerging technology, digital twin has already made valuable contributions to safety risk management in many fields. Therefore, exploring the application of digital twin technology in construction safety risk management is of great significance. The purpose of this study is to explore the current research status and application potential of digital twin technology in construction safety risk management.Design/methodology/approachThis study followed a four-stage literature processing approach as outlined in the systematic literature review procedure guidelines. It then combined the quantitative analysis tools and qualitative analysis methods to organize and summarize the current research status of digital twin technology in the field of construction safety risk management, analyze the application of digital twin technology in construction safety risk management and identify future research trends.FindingsThe research findings indicate that the application of digital twin technology in the field of construction safety risk management is still in its early stages. Based on the results of the literature analysis, this paper summarizes five aspects of digital twin technology's application in construction safety risk management: real-time monitoring and early warning, safety risk prediction and assessment, accident simulation and emergency response, safety risk management decision support and safety training and education. It also proposes future research trends based on the current research challenges.Originality/valueThis study provides valuable references for the extended application of digital twin technology and offers a new perspective and approach for modern construction safety risk management. It contributes to the enhancement of the theoretical framework for construction safety risk management and the improvement of on-site construction safety.

Study on the Ultimate Load-Bearing Capacity of Disc Buckle Tall Formwork Support Considering Uncertain Factors

Disc buckle steel pipe brackets are widely used in building construction due to the advantages of its simple structure, large-bearing capacity, rapid assembling and disassembling, and strong versatility. In complex construction projects, the uncertainties affecting the stability of disc buckle steel pipe support need to be considered to ensure the safety of disc buckle steel pipe supports. A surrogate model based on a deep neural network is built and trained to predict the ultimate load-carrying capacity of a stent. The results of the finite element model calculations are used to form the sample set of the surrogate model. Then, we combined the computationally efficient DNN surrogate model with the Monte Carlo method to consider the distribution of the ultimate load capacity of the disc buckle bracket under the uncertainties of the bracket node pin wedge tightness, the wall thickness of the steel pipe, and the connection of the connecting wall member. At the same time, based on the DNN model, the SHapley Additive exPlanations (SHAP) interpretability analysis method was used to study the degree of influence of various uncertainty factors on the ultimate bearing capacity of the stent. In practical engineering, the stability analysis of a disc buckle tall formwork support has shown that a surrogate model based on a deep neural network is efficient in predicting the buckling characteristic value of the support. The error rate of the prediction is less than 2%. The buckling characteristic values of the bracket vary in the range of 17–25. Among the various factors that influence the buckling characteristic value of the bracket, the joint wedge tightness has the greatest impact, followed by the bottom and top wall-connecting parts.

A REVIEW OF AGENT-BASED MODELING IN CONSTRUCTION MANAGEMENT: AN ANALYTICAL FRAMEWORK BASED ON MULTIPLE OBJECTIVES

The increased complexity of construction projects has caused various management challenges. To clarify the mechanism of construction system complexity and improve the ability to manage the complexity of construction projects, the Agent-based modeling (ABM) method has been introduced and used in the construction management field. Nevertheless, a systematic, holistic, and panoramic understanding of the use of the ABM model in the construction management field is still lacking. To address this research gap, this study reviewed 133 historical explorations retrieved from the database of Web of Science. By using the multiple objectives of construction management as the literature classification framework, the study described the research status of the agent-based modeling method in the field of construction management. On this basis, this paper suggested the improvement paths in the application of this method from three aspects. It is expected that this study will provide a theoretical basis for enhancing understanding of the use of the ABM method in construction management, and also provide insights for future explorations in the area.

Complexity in Construction Projects: A Literature Review

Improper understanding of complexity can be a leading factor in the failure of construction projects. This study aims to provide a better understanding of the complexity of construction projects. For this purpose, this study uses the systematic literature review (SLR) approach to review the related literature and propose a definition for complexity and the criteria that affect the degree of complexity in construction. The results of analyzing 49 studies from the literature showed that, generally, complexity is understood in three ways: the meaning of the word “complexity”, system and organizational complexity, and project complexity. Within these three types of definitions, it was found that “interdependency” and “multiple parts/parties” are the most frequently used keywords. The results also showed that another look at the current lingual definition of complexity is needed. Regarding the criteria, the results showed that the “number of stakeholders”, “scope and project objectives”, and “management structure” are the most important criteria to assess construction project complexity. Accordingly, this study provides a set of recommendations and strategies to help manage complexity in construction projects.

ANALISIS DAN MITIGASI RISIKO KESELAMATAN DAN KECELAKAAN KERJA PADA PROYEK PEMBANGUNAN BALI INTERCONTINENTAL GRAND BALLROOM

ANALISIS DAN MITIGASI RISIKO KESELAMATAN DAN KECELAKAAN KERJA PADA PROYEK PEMBANGUNAN BALI INTERCONTINENTAL GRAND BALLROOM

In-House Knowledge Management Using a Large Language Model: Focusing on Technical Specification Documents Review

In complex construction projects, technical specifications have to be reviewed in a short period of time. Even experienced engineers find it difficult to review every detail of technical specifications. In addition, it is not easy to transfer experienced knowledge to junior engineers. With the technological innovation of large language models such as ChatGPT, a fine-tuned language model is proposed as an effective solution for the automatic review of technical specification documents. Against this backdrop, this study examines the in-house technical specification documents that are not publicly available. Then, two fine-tuned large language models, GPT-3 and LLaMA2, are trained to answer questions related to technical specification documents. The results show that the fine-tuned LLaMA2 model generally outperforms the fine-tuned GPT-3 model in terms of accuracy, reliability, and conciseness of responses. In particular, the fine-tuned LLaMA2 model suppressed hallucinogenic effects better than the fine-tuned GPT-3 model. Based on the results, this study discussed the applicability and limitations of a fine-tuned large language model for in-house knowledge management. The results of this study are expected to assist practitioners in developing a domain-specific knowledge management solution by fine-tuning an open-source large language model with private datasets.

EXPLORING 4D AND 5D ANALYSIS IN BIM ENVIRONMENT FOR INFRASTRUCTURES: A CASE STUDY

Abstract. Building Information Modelling (BIM) has emerged as a focal point in the construction industry, garnering substantial attention due to its capacity to elevate product quality, facilitate accurate quantity determination, and enhance scheduling efficiency. The inherent complexity of construction projects necessitates the integration of BIM models endowed with automation functionalities for schedules and cost estimation. This integration ensures that updates seamlessly occur throughout the construction process, thereby mitigating project uncertainties and reducing overall costs. While the potential benefits of BIM are recognized, a substantial challenge persists in the Architecture, Engineering, and Construction (AEC) field defining workflows for the automated generation of optimized 4D/5D BIM simulation and analysis. The effective utilization of BIM as a transformative tool requires addressing this challenge to unlock its full potential in project management. BIM serves as a pivotal conduit for project data, providing a structured approach to elevate overall product quality, streamline processes, and minimize contingencies and costs associated with construction projects. Consequently, the successful implementation of BIM with automated 4D/5D simulation and analysis stands as a critical milestone in advancing the capabilities of the AEC industry, ensuring greater efficiency, accuracy, and cost-effectiveness in construction projects. According to these aspects, the time-cost analysis (4D/5D) of a project for the North-South railway station in Riyadh, designed by Architect Engineer Dia Hilal, was investigated.