Pub Date : 2024-11-16DOI: 10.1016/j.autcon.2024.105872
Anja Kunic, Davide Angeletti, Giuseppe Marrone, Roberto Naboni
Structural adaptivity and readiness for change are some of the key enablers of resilient and sustainable architecture. This paper presents an approach to the design and construction of reconfigurable timber slabs, termed ReconWood Slabs, which integrate a stress-driven design approach and cyber-physical construction processes to enhance data-informed circularity. Using advanced computational design tools, the research outlines a workflow for generating optimised slab configurations that balance structural performance with material reusability. The slabs, composed of modular beams connected via reversible steel fasteners, are designed for easy disassembly and reconfiguration, promoting material reuse across multiple building lifecycles. The paper demonstrates the system's potential through the construction of three slab structures employing Mixed Reality for material data tracking and assembly. The three structures store nearly a ton of CO2eq in reusable parts.
{"title":"Design and construction automation of reconfigurable timber slabs","authors":"Anja Kunic, Davide Angeletti, Giuseppe Marrone, Roberto Naboni","doi":"10.1016/j.autcon.2024.105872","DOIUrl":"10.1016/j.autcon.2024.105872","url":null,"abstract":"<div><div>Structural adaptivity and readiness for change are some of the key enablers of resilient and sustainable architecture. This paper presents an approach to the design and construction of reconfigurable timber slabs, termed ReconWood Slabs, which integrate a stress-driven design approach and cyber-physical construction processes to enhance data-informed circularity. Using advanced computational design tools, the research outlines a workflow for generating optimised slab configurations that balance structural performance with material reusability. The slabs, composed of modular beams connected via reversible steel fasteners, are designed for easy disassembly and reconfiguration, promoting material reuse across multiple building lifecycles. The paper demonstrates the system's potential through the construction of three slab structures employing Mixed Reality for material data tracking and assembly. The three structures store nearly a ton of CO2eq in reusable parts.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105872"},"PeriodicalIF":9.6,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-16DOI: 10.1016/j.autcon.2024.105873
Yun Chen , Gengyang Lu , Ke Wang , Shu Chen , Chenfei Duan
With the increasing demand for water conservancy engineering (WCE), the number of safety accidents during construction has continued to rise, requiring an urgent improvement in construction safety. The existing safety management regulations for water conservancy construction engineering (WCCE) comprise a considerable amount of text, with cross-references between different standards severely reducing their use efficiency. To address this issue, this paper proposes an ALBERT-BiLSTM-CRF model based on textual data from WCCE safety management standards. ALBERT, a lightweight pretrained language model, is integrated with the BiLSTM-CRF to construct an intelligent text entity recognition method. Association rules are used to extract entity relationships, and a knowledge graph representing the WCCE safety management standards is established. The results show that the ALBERT-BiLSTM-CRF algorithm improves the precision, with a recognition accuracy exceeding 85 %. Case studies validate that the constructed knowledge graph can quickly query safety standard knowledge, aiding in the generation of safety measures.
{"title":"Knowledge graph for safety management standards of water conservancy construction engineering","authors":"Yun Chen , Gengyang Lu , Ke Wang , Shu Chen , Chenfei Duan","doi":"10.1016/j.autcon.2024.105873","DOIUrl":"10.1016/j.autcon.2024.105873","url":null,"abstract":"<div><div>With the increasing demand for water conservancy engineering (WCE), the number of safety accidents during construction has continued to rise, requiring an urgent improvement in construction safety. The existing safety management regulations for water conservancy construction engineering (WCCE) comprise a considerable amount of text, with cross-references between different standards severely reducing their use efficiency. To address this issue, this paper proposes an ALBERT-BiLSTM-CRF model based on textual data from WCCE safety management standards. ALBERT, a lightweight pretrained language model, is integrated with the BiLSTM-CRF to construct an intelligent text entity recognition method. Association rules are used to extract entity relationships, and a knowledge graph representing the WCCE safety management standards is established. The results show that the ALBERT-BiLSTM-CRF algorithm improves the precision, with a recognition accuracy exceeding 85 %. Case studies validate that the constructed knowledge graph can quickly query safety standard knowledge, aiding in the generation of safety measures.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105873"},"PeriodicalIF":9.6,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-15DOI: 10.1016/j.autcon.2024.105854
Yaxian Dong , Yuqing Hu , Shuai Li , Jiannan Cai , Zhu Han
Asset tracking is crucial for managing prefabricated construction projects, as delayed deliveries might disrupt interdependent offsite and onsite activities, causing economic losses and disputes. To clarify liabilities, tamperproof asset tracking and delay propagation analysis are necessary. To achieve this, a BIM-blockchain integrated framework via smart contracts is proposed given rich information in BIM and blockchain's immutable records. First, asset information and interdependent activity schedule are automatically transmitted from BIM to blockchain. Then, QR codes are generated and attached to physical assets for tracking. If any delays, compiled smart contracts will automatically derive propagated impacts on offsite and onsite activities considering their interdependencies and proactively notify relevant parties. Affected activities with assets, certification time, and responsible parties are automatically visualized in 4D BIM for timely collaboration. The developed IFC-Ethereum prototype demonstrates the framework's feasibility and effectiveness, reducing coordination overhead costs and time. Traceable records help further calculate parties' penalties and compensation.
{"title":"BIM-blockchain integrated automatic asset tracking and delay propagation analysis for prefabricated construction projects","authors":"Yaxian Dong , Yuqing Hu , Shuai Li , Jiannan Cai , Zhu Han","doi":"10.1016/j.autcon.2024.105854","DOIUrl":"10.1016/j.autcon.2024.105854","url":null,"abstract":"<div><div>Asset tracking is crucial for managing prefabricated construction projects, as delayed deliveries might disrupt interdependent offsite and onsite activities, causing economic losses and disputes. To clarify liabilities, tamperproof asset tracking and delay propagation analysis are necessary. To achieve this, a BIM-blockchain integrated framework via smart contracts is proposed given rich information in BIM and blockchain's immutable records. First, asset information and interdependent activity schedule are automatically transmitted from BIM to blockchain. Then, QR codes are generated and attached to physical assets for tracking. If any delays, compiled smart contracts will automatically derive propagated impacts on offsite and onsite activities considering their interdependencies and proactively notify relevant parties. Affected activities with assets, certification time, and responsible parties are automatically visualized in 4D BIM for timely collaboration. The developed IFC-Ethereum prototype demonstrates the framework's feasibility and effectiveness, reducing coordination overhead costs and time. Traceable records help further calculate parties' penalties and compensation.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105854"},"PeriodicalIF":9.6,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-13DOI: 10.1016/j.autcon.2024.105865
Atena Karbalaei Mohammad Hossein, Amir Golroo, Medya Akhoundzadeh
The integration of smart technologies is set to revolutionize pavement data collection and analysis, leading to more efficient decision-making in Pavement Management Systems (PMS). Smart pavements, featuring embedded sensors, offer continuous streams of high-quality real-time data, enhancing the PMS data analysis process. This paper provides a detailed examination of these embedded smart systems, discussing their technologies, applications, and potential impacts on pavement management. The study highlights the role of smart materials in pavement engineering, offering self-sensing, self-healing, and energy-harvesting capabilities. It investigates sensor technologies for monitoring pavement conditions, focusing on both on-surface and below-surface sensors for comprehensive data collection. Future research directions emphasize advanced data management systems, sensor durability enhancement, economic modeling, standardization efforts, energy-efficient technologies, and pilot programs for real-world testing. This research provides insights into smart pavement advancements and challenges, paving the way for improved road infrastructure efficiency and sustainability.
{"title":"Smart embedded technologies and materials for enhanced pavement management","authors":"Atena Karbalaei Mohammad Hossein, Amir Golroo, Medya Akhoundzadeh","doi":"10.1016/j.autcon.2024.105865","DOIUrl":"10.1016/j.autcon.2024.105865","url":null,"abstract":"<div><div>The integration of smart technologies is set to revolutionize pavement data collection and analysis, leading to more efficient decision-making in Pavement Management Systems (PMS). Smart pavements, featuring embedded sensors, offer continuous streams of high-quality real-time data, enhancing the PMS data analysis process. This paper provides a detailed examination of these embedded smart systems, discussing their technologies, applications, and potential impacts on pavement management. The study highlights the role of smart materials in pavement engineering, offering self-sensing, self-healing, and energy-harvesting capabilities. It investigates sensor technologies for monitoring pavement conditions, focusing on both on-surface and below-surface sensors for comprehensive data collection. Future research directions emphasize advanced data management systems, sensor durability enhancement, economic modeling, standardization efforts, energy-efficient technologies, and pilot programs for real-world testing. This research provides insights into smart pavement advancements and challenges, paving the way for improved road infrastructure efficiency and sustainability.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105865"},"PeriodicalIF":9.6,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142637388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-13DOI: 10.1016/j.autcon.2024.105864
Tengchao Huang , Xuanwei Chen , Huosheng Hu , Shuang Song , Guifang Shao , Qingyuan Zhu
In this paper, a terrain-adaptive motion planner is developed specifically for articulated construction vehicles (ACVs) to address instability issues caused by elevation changes on unstructured construction sites—challenges that traditional 2D motion planners struggle to manage effectively. The proposed planner adopts a modular framework, incorporating a terrain elevation model, an articulated vehicle kinematic model, and a posture response model. These models collaboratively capture the dynamic interactions between the vehicle and the terrain. The planner utilizes a multi-objective evaluation function to enhance the vehicle's 3D motion stability, especially in challenging terrains. By considering real-time vehicle-terrain interactions, this function estimates and optimizes the vehicle's stability. The planner's effectiveness is validated through field tests with a scaled-down ACV prototype, demonstrating significant improvements in stability and confirming its potential for practical application on unstructured terrains.
{"title":"Terrain-adaptive motion planner for articulated construction vehicles in unstructured environments","authors":"Tengchao Huang , Xuanwei Chen , Huosheng Hu , Shuang Song , Guifang Shao , Qingyuan Zhu","doi":"10.1016/j.autcon.2024.105864","DOIUrl":"10.1016/j.autcon.2024.105864","url":null,"abstract":"<div><div>In this paper, a terrain-adaptive motion planner is developed specifically for articulated construction vehicles (ACVs) to address instability issues caused by elevation changes on unstructured construction sites—challenges that traditional 2D motion planners struggle to manage effectively. The proposed planner adopts a modular framework, incorporating a terrain elevation model, an articulated vehicle kinematic model, and a posture response model. These models collaboratively capture the dynamic interactions between the vehicle and the terrain. The planner utilizes a multi-objective evaluation function to enhance the vehicle's 3D motion stability, especially in challenging terrains. By considering real-time vehicle-terrain interactions, this function estimates and optimizes the vehicle's stability. The planner's effectiveness is validated through field tests with a scaled-down ACV prototype, demonstrating significant improvements in stability and confirming its potential for practical application on unstructured terrains.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105864"},"PeriodicalIF":9.6,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142637450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-13DOI: 10.1016/j.autcon.2024.105870
Raobo Li , Shu Gan , Xiping Yuan , Rui Bi , Weidong Luo , Cheng Chen , Zhifu Zhu
Point cloud registration plays a crucial role in processing large-scale building point cloud data. However, existing registration algorithms face challenges in effectively handling outliers in descriptor-based correspondence. This paper presents an automatic registration method for large-scale building point clouds that is capable of achieving swift and accurate registration without the need for initial guessing. The method employs a two-step matching optimization approach: coarse (two-point)-to-fine (three-point), selecting matches based on two-point reliability and three-point consistency. Spatial transformation parameters are broken down into rotations and translations. A progressively optimized kernel function is proposed for estimating rotation, while a clustering confidence algorithm computes translation. Comprehensive experiments were conducted using real-world data. The results indicate that the approach swiftly and accurately estimates optimal outcomes when processing large-scale building point clouds with outlier rates up to 99%. Compared to six existing registration methods, the proposed approach reduces rotation error by 6.15% and translation error by 12.83%, while improving efficiency by 2.57%.
{"title":"Automatic registration of large-scale building point clouds with high outlier rates","authors":"Raobo Li , Shu Gan , Xiping Yuan , Rui Bi , Weidong Luo , Cheng Chen , Zhifu Zhu","doi":"10.1016/j.autcon.2024.105870","DOIUrl":"10.1016/j.autcon.2024.105870","url":null,"abstract":"<div><div>Point cloud registration plays a crucial role in processing large-scale building point cloud data. However, existing registration algorithms face challenges in effectively handling outliers in descriptor-based correspondence. This paper presents an automatic registration method for large-scale building point clouds that is capable of achieving swift and accurate registration without the need for initial guessing. The method employs a two-step matching optimization approach: coarse (two-point)-to-fine (three-point), selecting matches based on two-point reliability and three-point consistency. Spatial transformation parameters are broken down into rotations and translations. A progressively optimized kernel function is proposed for estimating rotation, while a clustering confidence algorithm computes translation. Comprehensive experiments were conducted using real-world data. The results indicate that the approach swiftly and accurately estimates optimal outcomes when processing large-scale building point clouds with outlier rates up to 99%. Compared to six existing registration methods, the proposed approach reduces rotation error by 6.15% and translation error by 12.83%, while improving efficiency by 2.57%.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105870"},"PeriodicalIF":9.6,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142637386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-12DOI: 10.1016/j.autcon.2024.105862
Feng Xu, Yexin Zou, Yangwenzhao Li
The inherent complexity of historic buildings, particularly their internal structures, presents significant challenges to the efficiency of digital model creation. This paper aims to enhance modeling efficiency by automating the creation of timber frames using a procedural modeling method. It translates the architectural rules used by local carpenters into modeling rules for procedural modeling, allowing for the automatic generation of a digital model that closely resembles the actual timber frame with a few simple constraints. While some manual identification and correction are still necessary, the workload is significantly reduced compared to traditional methods, and the precision meets the requirements of HBIM. The results show that this approach greatly improves the efficiency of modeling large-scale historic buildings and serves as a valuable complement to traditional HBIM methods. Future research will focus on enhancing the integrity and diversity of the models, such as expanding the range of supported traditional building types.
{"title":"Procedural modeling of historic buildings' timber frames for HBIM based on carpenters' architectural rules","authors":"Feng Xu, Yexin Zou, Yangwenzhao Li","doi":"10.1016/j.autcon.2024.105862","DOIUrl":"10.1016/j.autcon.2024.105862","url":null,"abstract":"<div><div>The inherent complexity of historic buildings, particularly their internal structures, presents significant challenges to the efficiency of digital model creation. This paper aims to enhance modeling efficiency by automating the creation of timber frames using a procedural modeling method. It translates the architectural rules used by local carpenters into modeling rules for procedural modeling, allowing for the automatic generation of a digital model that closely resembles the actual timber frame with a few simple constraints. While some manual identification and correction are still necessary, the workload is significantly reduced compared to traditional methods, and the precision meets the requirements of HBIM. The results show that this approach greatly improves the efficiency of modeling large-scale historic buildings and serves as a valuable complement to traditional HBIM methods. Future research will focus on enhancing the integrity and diversity of the models, such as expanding the range of supported traditional building types.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105862"},"PeriodicalIF":9.6,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142637406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-12DOI: 10.1016/j.autcon.2024.105871
Miran Seo , Samraat Gupta , Youngjib Ham
Building sustainable habitats on the moon has been planned for decades. However, applying fully automated construction systems is still challenging in altered environments. Teleoperation, which is the remote control of the machine, can serve as an intermediate phase before achieving fully autonomous systems. Since the teleoperation between operators on the earth-ground and robots on the lunar surface introduces inevitable communication time delays under a deep space network system, it is important to understand its impact on task performance and operator behaviors in teleoperated construction tasks. This paper develops a simulated lunar environment for excavator teleoperation systems in virtual reality to examine task performance and operator behaviors in time delay conditions. The outcomes indicate that time delays significantly degrade task performance, and the operators modify their control strategies to cope with the time delay conditions. The findings will contribute to understanding human behaviors in time-delayed teleoperation of lunar construction tasks.
{"title":"Exploratory study on time-delayed excavator teleoperation in virtual lunar construction simulation: Task performance and operator behavior","authors":"Miran Seo , Samraat Gupta , Youngjib Ham","doi":"10.1016/j.autcon.2024.105871","DOIUrl":"10.1016/j.autcon.2024.105871","url":null,"abstract":"<div><div>Building sustainable habitats on the moon has been planned for decades. However, applying fully automated construction systems is still challenging in altered environments. Teleoperation, which is the remote control of the machine, can serve as an intermediate phase before achieving fully autonomous systems. Since the teleoperation between operators on the earth-ground and robots on the lunar surface introduces inevitable communication time delays under a deep space network system, it is important to understand its impact on task performance and operator behaviors in teleoperated construction tasks. This paper develops a simulated lunar environment for excavator teleoperation systems in virtual reality to examine task performance and operator behaviors in time delay conditions. The outcomes indicate that time delays significantly degrade task performance, and the operators modify their control strategies to cope with the time delay conditions. The findings will contribute to understanding human behaviors in time-delayed teleoperation of lunar construction tasks.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105871"},"PeriodicalIF":9.6,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142637448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-12DOI: 10.1016/j.autcon.2024.105846
Jungwon Lee , Seungjun Ahn , Daeho Kim , Dongkyun Kim
Construction safety standards are in unstructured formats like text and images, complicating their effective use in daily tasks. This paper compares the performance of Retrieval-Augmented Generation (RAG) and fine-tuned Large Language Model (LLM) for the construction safety knowledge retrieval. The RAG model was created by integrating GPT-4 with a knowledge graph derived from construction safety guidelines, while the fine-tuned LLM was fine-tuned using a question-answering dataset derived from the same guidelines. These models' performance is tested through case studies, using accident synopses as a query to generate preventive measurements. The responses were assessed using metrics, including cosine similarity, Euclidean distance, BLEU, and ROUGE scores. It was found that both models outperformed GPT-4, with the RAG model improving by 21.5 % and the fine-tuned LLM by 26 %. The findings highlight the relative strengths and weaknesses of the RAG and fine-tuned LLM approaches in terms of applicability and reliability for safety management.
{"title":"Performance comparison of retrieval-augmented generation and fine-tuned large language models for construction safety management knowledge retrieval","authors":"Jungwon Lee , Seungjun Ahn , Daeho Kim , Dongkyun Kim","doi":"10.1016/j.autcon.2024.105846","DOIUrl":"10.1016/j.autcon.2024.105846","url":null,"abstract":"<div><div>Construction safety standards are in unstructured formats like text and images, complicating their effective use in daily tasks. This paper compares the performance of Retrieval-Augmented Generation (RAG) and fine-tuned Large Language Model (LLM) for the construction safety knowledge retrieval. The RAG model was created by integrating GPT-4 with a knowledge graph derived from construction safety guidelines, while the fine-tuned LLM was fine-tuned using a question-answering dataset derived from the same guidelines. These models' performance is tested through case studies, using accident synopses as a query to generate preventive measurements. The responses were assessed using metrics, including cosine similarity, Euclidean distance, BLEU, and ROUGE scores. It was found that both models outperformed GPT-4, with the RAG model improving by 21.5 % and the fine-tuned LLM by 26 %. The findings highlight the relative strengths and weaknesses of the RAG and fine-tuned LLM approaches in terms of applicability and reliability for safety management.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105846"},"PeriodicalIF":9.6,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142637389","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-10DOI: 10.1016/j.autcon.2024.105836
Ahmed Moussa , Mohamed Ezzeldin , Wael El-Dakhakhni
Infrastructure projects often encounter performance challenges, such as cost overruns and safety issues, due to complex risk interactions and systemic risks. Existing literature treats risk interactions and systemic risks separately and relies on models that struggle with nonlinearities, adaptability, and practical applications, leading to suboptimal risk management. To address this gap, this paper uses machine learning (ML) algorithms to analyze historical project data and predict the impacts of risk interactions and systemic risks on future projects. The results show that ML-based models provide accurate and practical data-driven predictions of project performance under risk interactions and systemic risks. These findings are valuable for infrastructure project managers seeking to improve risk mitigation strategies and project outcomes. The paper lays also the foundation for future research on leveraging advanced predictive analytics in managing complex project risks more effectively.
由于复杂的风险相互作用和系统性风险,基础设施项目经常会遇到绩效挑战,如成本超支和安全问题。现有文献将风险相互作用和系统性风险分开处理,并依赖于难以解决非线性、适应性和实际应用问题的模型,从而导致了次优的风险管理。为了弥补这一不足,本文使用机器学习(ML)算法分析历史项目数据,预测风险相互作用和系统性风险对未来项目的影响。研究结果表明,基于 ML 的模型可以对风险相互作用和系统性风险下的项目绩效进行准确、实用的数据驱动预测。这些发现对于寻求改善风险缓解策略和项目成果的基础设施项目经理来说非常有价值。本文还为今后研究如何利用先进的预测分析技术更有效地管理复杂的项目风险奠定了基础。
{"title":"Predicting and managing risk interactions and systemic risks in infrastructure projects using machine learning","authors":"Ahmed Moussa , Mohamed Ezzeldin , Wael El-Dakhakhni","doi":"10.1016/j.autcon.2024.105836","DOIUrl":"10.1016/j.autcon.2024.105836","url":null,"abstract":"<div><div>Infrastructure projects often encounter performance challenges, such as cost overruns and safety issues, due to complex risk interactions and systemic risks. Existing literature treats risk interactions and systemic risks separately and relies on models that struggle with nonlinearities, adaptability, and practical applications, leading to suboptimal risk management. To address this gap, this paper uses machine learning (ML) algorithms to analyze historical project data and predict the impacts of risk interactions and systemic risks on future projects. The results show that ML-based models provide accurate and practical data-driven predictions of project performance under risk interactions and systemic risks. These findings are valuable for infrastructure project managers seeking to improve risk mitigation strategies and project outcomes. The paper lays also the foundation for future research on leveraging advanced predictive analytics in managing complex project risks more effectively.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"168 ","pages":"Article 105836"},"PeriodicalIF":9.6,"publicationDate":"2024-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142637404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}