Automation in Construction最新文献

英文中文

A data-driven and knowledge-based decision support system for optimized construction planning and control

IF 9.6 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-02-24 DOI: 10.1016/j.autcon.2025.106066

Moslem Sheikhkhoshkar , Hind Bril El-Haouzi , Alexis Aubry , Farook Hamzeh , Farzad Rahimian

Despite the use of various construction planning and control systems, no prior data-driven and knowledge-based system provides optimized solutions based on specific project team needs and applications. This paper presents a data-driven and knowledge-based decision support system that utilizes a knowledge database constructed from experts' experience and proposes multi-level and integrated systems for planning and control of construction projects. A mixed-method approach gathers data from industry professionals, develops a knowledge repository based on Rough Set Theory (RST), launches an inference engine using the Pyke package, and integrates these insights into a decision support system optimized by a multi-objective mathematical model. The developed system considers the functional requirements of the project team and suggests an optimized and fit-for-purpose planning and control system. To demonstrate its practicality, it applies to a real-world renovation project. This paper contributes to enhancing systematic and data-driven decision-making for planning and control systems based on expert knowledge and the specific needs of the project team.

{"title":"A data-driven and knowledge-based decision support system for optimized construction planning and control","authors":"Moslem Sheikhkhoshkar , Hind Bril El-Haouzi , Alexis Aubry , Farook Hamzeh , Farzad Rahimian","doi":"10.1016/j.autcon.2025.106066","DOIUrl":"10.1016/j.autcon.2025.106066","url":null,"abstract":"<div><div>Despite the use of various construction planning and control systems, no prior data-driven and knowledge-based system provides optimized solutions based on specific project team needs and applications. This paper presents a data-driven and knowledge-based decision support system that utilizes a knowledge database constructed from experts' experience and proposes multi-level and integrated systems for planning and control of construction projects. A mixed-method approach gathers data from industry professionals, develops a knowledge repository based on Rough Set Theory (RST), launches an inference engine using the Pyke package, and integrates these insights into a decision support system optimized by a multi-objective mathematical model. The developed system considers the functional requirements of the project team and suggests an optimized and fit-for-purpose planning and control system. To demonstrate its practicality, it applies to a real-world renovation project. This paper contributes to enhancing systematic and data-driven decision-making for planning and control systems based on expert knowledge and the specific needs of the project team.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"173 ","pages":"Article 106066"},"PeriodicalIF":9.6,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143474781","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}

引用次数: 0

Deep learning-based pipe segmentation and geometric reconstruction from poorly scanned point clouds using BIM-driven data alignment

IF 9.6 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-02-24 DOI: 10.1016/j.autcon.2025.106071

Wanchen Yu , Jiangpeng Shu , Zihan Yang , Hongliang Ding , Wuhua Zeng , Yong Bai

Pipe reconstruction is an important prerequisite for pipe maintenance. However, scanned point clouds often contain defects, presenting a significant challenge for automated segmentation and geometric reconstruction. To address this challenge, this paper proposes a learning-based segmentation method, PipeSegNet, along with a geometric reconstruction process. In the segmentation stage, a method is developed to generate datasets with controlled density from BIM. Meanwhile, alignment strategies are introduced to address feature and label inconsistencies between BIM-generated and real datasets. PipeSegNet enhances global and local perceptual capability, achieving pipe segmentation accuracy of 96.37 % and IoU of 91.45 %, ensuring high-quality reconstruction. Comparative and module evaluation experiments demonstrate the effectiveness of PipeSegNet combined with the alignment strategies. The total average relative error of the reconstructed pipes is 2.73 %. This paper provides valuable insights into the pipe segmentation and reconstruction from point clouds, particularly in scenes with poor scanning quality, contributing to efficient infrastructure maintenance.

{"title":"Deep learning-based pipe segmentation and geometric reconstruction from poorly scanned point clouds using BIM-driven data alignment","authors":"Wanchen Yu , Jiangpeng Shu , Zihan Yang , Hongliang Ding , Wuhua Zeng , Yong Bai","doi":"10.1016/j.autcon.2025.106071","DOIUrl":"10.1016/j.autcon.2025.106071","url":null,"abstract":"<div><div>Pipe reconstruction is an important prerequisite for pipe maintenance. However, scanned point clouds often contain defects, presenting a significant challenge for automated segmentation and geometric reconstruction. To address this challenge, this paper proposes a learning-based segmentation method, PipeSegNet, along with a geometric reconstruction process. In the segmentation stage, a method is developed to generate datasets with controlled density from BIM. Meanwhile, alignment strategies are introduced to address feature and label inconsistencies between BIM-generated and real datasets. PipeSegNet enhances global and local perceptual capability, achieving pipe segmentation accuracy of 96.37 % and IoU of 91.45 %, ensuring high-quality reconstruction. Comparative and module evaluation experiments demonstrate the effectiveness of PipeSegNet combined with the alignment strategies. The total average relative error of the reconstructed pipes is 2.73 %. This paper provides valuable insights into the pipe segmentation and reconstruction from point clouds, particularly in scenes with poor scanning quality, contributing to efficient infrastructure maintenance.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"173 ","pages":"Article 106071"},"PeriodicalIF":9.6,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143474733","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}

引用次数: 0

Statistical characterization and attenuation of vibration effect for continuous asphalt pavement survey using ground-penetrating radar

IF 9.6 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-02-22 DOI: 10.1016/j.autcon.2025.106057

Siqi Wang, Tao Ma, Weiguang Zhang

The vibrations from the antenna during ground-penetrating radar (GPR) surveys may introduce unwanted frequency components in the radar data, thus producing noise in the predicted dielectric constant values along the survey distance. Existing statistical methods for vibration effect attenuation require multiple inputs, which is not feasible for real-time processing. This paper characterized the vibration effect and proposed a real-time statistical method for vibration effect attenuation during continuous GPR surveys. Time and frequency domain features were investigated on the dielectric constant values along the survey distance. Results show that the vibration noise is Gaussian-distributed. Window-based-smoothing methods were proposed to remove the vibration effect. The mean prediction error at the highest operating speed (40 km/h) drops from 11.8 % to 2.4 %. The recommended Gaussian fitting window does not require customized input parameters. The processing time is within seconds, which allows real-time and automatic attenuation of the vibration effect.

{"title":"Statistical characterization and attenuation of vibration effect for continuous asphalt pavement survey using ground-penetrating radar","authors":"Siqi Wang, Tao Ma, Weiguang Zhang","doi":"10.1016/j.autcon.2025.106057","DOIUrl":"10.1016/j.autcon.2025.106057","url":null,"abstract":"<div><div>The vibrations from the antenna during ground-penetrating radar (GPR) surveys may introduce unwanted frequency components in the radar data, thus producing noise in the predicted dielectric constant values along the survey distance. Existing statistical methods for vibration effect attenuation require multiple inputs, which is not feasible for real-time processing. This paper characterized the vibration effect and proposed a real-time statistical method for vibration effect attenuation during continuous GPR surveys. Time and frequency domain features were investigated on the dielectric constant values along the survey distance. Results show that the vibration noise is Gaussian-distributed. Window-based-smoothing methods were proposed to remove the vibration effect. The mean prediction error at the highest operating speed (40 km/h) drops from 11.8 % to 2.4 %. The recommended Gaussian fitting window does not require customized input parameters. The processing time is within seconds, which allows real-time and automatic attenuation of the vibration effect.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"173 ","pages":"Article 106057"},"PeriodicalIF":9.6,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464826","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}

引用次数: 0

Digital twin model for analyzing deformation and seepage in high earth-rock dams

IF 9.6 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-02-21 DOI: 10.1016/j.autcon.2025.106079

Jichen Tian , Ruijie Yu , Jiankang Chen , Chen Chen , Yanling Li , Xinjian Sun , Huibao Huang

Digital twin technology is vital in hydraulic engineering for real-time visualization, performance analysis, and risk management of water infrastructure systems. This paper proposes a digital twin model for deformation and seepage analysis of high earth-rock dams, integrating deep learning with the Finite Element Method (FEM). Key contributions include a sensor-based monitoring point model with time-variant update and extrapolation capabilities and a point-to-domain model that achieves full-domain monitoring predictions from point-level monitoring by learning the node relationships generated by FEM using neural networks and dynamic monitoring loss functions. Applied to a 186-m dam, the model achieves an average error of 3.17 %, improving deformation prediction accuracy by 19.44 % and simulation accuracy by 64.42 %. This approach facilitates real-time monitoring, predictive analysis, and early warnings, making it a powerful tool for hydraulic engineering safety. Future work will focus on exploring three-dimensional high-precision modeling and advancing data fusion techniques.

{"title":"Digital twin model for analyzing deformation and seepage in high earth-rock dams","authors":"Jichen Tian , Ruijie Yu , Jiankang Chen , Chen Chen , Yanling Li , Xinjian Sun , Huibao Huang","doi":"10.1016/j.autcon.2025.106079","DOIUrl":"10.1016/j.autcon.2025.106079","url":null,"abstract":"<div><div>Digital twin technology is vital in hydraulic engineering for real-time visualization, performance analysis, and risk management of water infrastructure systems. This paper proposes a digital twin model for deformation and seepage analysis of high earth-rock dams, integrating deep learning with the Finite Element Method (FEM). Key contributions include a sensor-based monitoring point model with time-variant update and extrapolation capabilities and a point-to-domain model that achieves full-domain monitoring predictions from point-level monitoring by learning the node relationships generated by FEM using neural networks and dynamic monitoring loss functions. Applied to a 186-m dam, the model achieves an average error of 3.17 %, improving deformation prediction accuracy by 19.44 % and simulation accuracy by 64.42 %. This approach facilitates real-time monitoring, predictive analysis, and early warnings, making it a powerful tool for hydraulic engineering safety. Future work will focus on exploring three-dimensional high-precision modeling and advancing data fusion techniques.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"173 ","pages":"Article 106079"},"PeriodicalIF":9.6,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464968","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}

引用次数: 0

Deep learning for crack segmentation: Redundant-to-effective feature transformation

IF 9.6 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-02-21 DOI: 10.1016/j.autcon.2025.106069

Xuehui Zhang , Xiaohang Li , Zixuan Li , Xuezhao Tian , Junhai An , Zhanhai Yu

Deep learning techniques have demonstrated remarkable performance in crack segmentation, particularly in convolutional neural networks like U-Net. However, the problem of feature redundancy in the network limits the network's ability to discover effective features. To address this problem, a feature correlation loss function (FC-Loss) was proposed. FC-Loss directly supervises the average correlation of the features of the first few layers through deep supervision to encourage the model to capture more independent features, and combines the Dropout technology to screen effective features. In order to verify this method, a dataset Crack2181 containing 2181 crack images was constructed. A series of experiments were carried out on it, and the results showed that combining FC-Loss with Dropout technology can effectively alleviate the problem of feature redundancy, improve the accuracy of crack segmentation and the generalization ability of the model.

引用次数: 0

Parametric archetype: An incremental learning model based on a similarity measure for building material stock aggregation 参数原型：基于相似性测量的增量学习模型，用于建筑材料存量汇总

IF 9.6 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-02-20 DOI: 10.1016/j.autcon.2025.106064

Wanyu Pei , Rudi Stouffs

To reduce reliance on virgin resources, the building material stock (BMS) serves as a source for material recycling and reuse. However, quantifying BMS in urban areas with scarce material data remains challenging. This paper addresses this challenge by proposing a “parametric archetype” method, which integrates similarity measures in BMS modelling. The similarity in material content between buildings is quantified using an Euclidean distance measure based on multidimensional building feature parameters. By mapping material data to similar buildings, a cohesive dataset can be formed and further enriched, enabling incremental larger-scale BMS aggregation. This model is trained using a dataset with 52 Singapore buildings, achieving a 20.24% error rate in material predictions for all urban buildings. The finding highlights the feasibility of conducting BMS aggregation with quantifiable accuracy even with limited material data points. The proposed model can be integrated with environmental impact analysis of material circularity and support sustainable urban resource management.

{"title":"Parametric archetype: An incremental learning model based on a similarity measure for building material stock aggregation","authors":"Wanyu Pei , Rudi Stouffs","doi":"10.1016/j.autcon.2025.106064","DOIUrl":"10.1016/j.autcon.2025.106064","url":null,"abstract":"<div><div>To reduce reliance on virgin resources, the building material stock (BMS) serves as a source for material recycling and reuse. However, quantifying BMS in urban areas with scarce material data remains challenging. This paper addresses this challenge by proposing a “parametric archetype” method, which integrates similarity measures in BMS modelling. The similarity in material content between buildings is quantified using an Euclidean distance measure based on multidimensional building feature parameters. By mapping material data to similar buildings, a cohesive dataset can be formed and further enriched, enabling incremental larger-scale BMS aggregation. This model is trained using a dataset with 52 Singapore buildings, achieving a 20.24% error rate in material predictions for all urban buildings. The finding highlights the feasibility of conducting BMS aggregation with quantifiable accuracy even with limited material data points. The proposed model can be integrated with environmental impact analysis of material circularity and support sustainable urban resource management.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"172 ","pages":"Article 106064"},"PeriodicalIF":9.6,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143445456","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}

引用次数: 0

Instance segmentation of reinforced concrete bridge point clouds with transformers trained exclusively on synthetic data

IF 9.6 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-02-20 DOI: 10.1016/j.autcon.2025.106067

Asad Ur Rahman , Vedhus Hoskere

Bridges in the United States require element-level inspections every 24 months, typically relying on laborious manual assessments. Three-dimensional (3D) point clouds from LiDAR or photogrammetry can facilitate these inspections, but are difficult to leverage without automatically identifying individual structural elements. Existing research focuses on semantic segmentation, which classifies points into broader categories rather than identifying each element instance. A major bottleneck is the difficulty of producing instance-level annotations. To address this gap, the paper proposes and evaluates three synthetic data generation approaches to produce automatically labeled point clouds of bridges with element instance-level annotations. An occlusion technique is introduced to increase realism. The synthetic data is then evaluated for training Mask3D transformer model for instance segmentation of field-collected point clouds, achieving mean Average Precision (mAP) scores of 91.7 % on LiDAR data and 63.8 % on photogrammetry. These results demonstrate the potential to enhance element-level bridge inspections and improve overall infrastructure management.

{"title":"Instance segmentation of reinforced concrete bridge point clouds with transformers trained exclusively on synthetic data","authors":"Asad Ur Rahman , Vedhus Hoskere","doi":"10.1016/j.autcon.2025.106067","DOIUrl":"10.1016/j.autcon.2025.106067","url":null,"abstract":"<div><div>Bridges in the United States require element-level inspections every 24 months, typically relying on laborious manual assessments. Three-dimensional (3D) point clouds from LiDAR or photogrammetry can facilitate these inspections, but are difficult to leverage without automatically identifying individual structural elements. Existing research focuses on semantic segmentation, which classifies points into broader categories rather than identifying each element instance. A major bottleneck is the difficulty of producing instance-level annotations. To address this gap, the paper proposes and evaluates three synthetic data generation approaches to produce automatically labeled point clouds of bridges with element instance-level annotations. An occlusion technique is introduced to increase realism. The synthetic data is then evaluated for training Mask3D transformer model for instance segmentation of field-collected point clouds, achieving mean Average Precision (mAP) scores of 91.7 % on LiDAR data and 63.8 % on photogrammetry. These results demonstrate the potential to enhance element-level bridge inspections and improve overall infrastructure management.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"173 ","pages":"Article 106067"},"PeriodicalIF":9.6,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143452970","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}

引用次数: 0

Environmental sensing in autonomous construction robots: Applicable technologies and systems

IF 9.6 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-02-19 DOI: 10.1016/j.autcon.2025.106075

Chinedu Okonkwo, Ibukun Awolusi

Environmental sensing is crucial for the effective operation of mobile robots, particularly on construction sites where conditions can change rapidly. While some studies have implemented different sensing technologies independently for autonomous mobile robot navigation, comprehensive studies on applicable sensors and technologies for dynamic construction environments, particularly for enhancing productivity and safety, are lacking. To fill this gap, this paper provides a comprehensive review of environmental sensing technologies for mobile construction robots, assessing their strengths, weaknesses, and applicability in the dynamic construction environment. Utilizing a combination of scientometric analysis and a critical review, three themes—vision-based sensing, localization and mapping, and autonomous navigation and path planning, which form the main sensing systems for the operation of autonomous mobile robots—were identified and analyzed. The review also identified and evaluated the different sensor technologies that facilitate environmental sensing. This paper also highlights significant research gaps and provides recommendations for future research studies.

{"title":"Environmental sensing in autonomous construction robots: Applicable technologies and systems","authors":"Chinedu Okonkwo, Ibukun Awolusi","doi":"10.1016/j.autcon.2025.106075","DOIUrl":"10.1016/j.autcon.2025.106075","url":null,"abstract":"<div><div>Environmental sensing is crucial for the effective operation of mobile robots, particularly on construction sites where conditions can change rapidly. While some studies have implemented different sensing technologies independently for autonomous mobile robot navigation, comprehensive studies on applicable sensors and technologies for dynamic construction environments, particularly for enhancing productivity and safety, are lacking. To fill this gap, this paper provides a comprehensive review of environmental sensing technologies for mobile construction robots, assessing their strengths, weaknesses, and applicability in the dynamic construction environment. Utilizing a combination of scientometric analysis and a critical review, three themes—vision-based sensing, localization and mapping, and autonomous navigation and path planning, which form the main sensing systems for the operation of autonomous mobile robots—were identified and analyzed. The review also identified and evaluated the different sensor technologies that facilitate environmental sensing. This paper also highlights significant research gaps and provides recommendations for future research studies.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"172 ","pages":"Article 106075"},"PeriodicalIF":9.6,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143437589","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}

引用次数: 0

Automated fall risk classification for construction workers using wearable devices, BIM, and optimized hybrid deep learning

IF 9.6 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-02-19 DOI: 10.1016/j.autcon.2025.106072

Min-Yuan Cheng, Deyla V.N. Soegiono, Akhmad F.K. Khitam

With the highest rate of workplace fatalities, construction is one of the world's most hazardous industries. Current risk mitigation approaches, which still rely heavily on traditional methods, do not allow decision-makers to respond quickly and accurately to the dynamic changes that typify modern construction environments. To address this issue, this paper develops an automated worker fall risk monitoring system for dynamic construction sites, by integrating real-time data from wearable devices and BIM with optimized hybrid deep learning model. The model utilizes Neural Network (NN) for time-independent variables and Graph Neural Network (GNN) for time-dependent variables. Optimization is achieved through the Symbiotic Organisms Search (SOS), enhancing the model's architecture and output weights. The classification performance of SOS-NN-GNN consistently outperformed other models, which resulted in 90.98 % accuracy. This highlights the model's reliability in automatically detecting fall risk levels, significantly reducing fall-related accidents, and improving safety, efficiency, and project outcomes in construction engineering.

{"title":"Automated fall risk classification for construction workers using wearable devices, BIM, and optimized hybrid deep learning","authors":"Min-Yuan Cheng, Deyla V.N. Soegiono, Akhmad F.K. Khitam","doi":"10.1016/j.autcon.2025.106072","DOIUrl":"10.1016/j.autcon.2025.106072","url":null,"abstract":"<div><div>With the highest rate of workplace fatalities, construction is one of the world's most hazardous industries. Current risk mitigation approaches, which still rely heavily on traditional methods, do not allow decision-makers to respond quickly and accurately to the dynamic changes that typify modern construction environments. To address this issue, this paper develops an automated worker fall risk monitoring system for dynamic construction sites, by integrating real-time data from wearable devices and BIM with optimized hybrid deep learning model. The model utilizes Neural Network (NN) for time-independent variables and Graph Neural Network (GNN) for time-dependent variables. Optimization is achieved through the Symbiotic Organisms Search (SOS), enhancing the model's architecture and output weights. The classification performance of SOS-NN-GNN consistently outperformed other models, which resulted in 90.98 % accuracy. This highlights the model's reliability in automatically detecting fall risk levels, significantly reducing fall-related accidents, and improving safety, efficiency, and project outcomes in construction engineering.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"172 ","pages":"Article 106072"},"PeriodicalIF":9.6,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143445572","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}

引用次数: 0

Binocular vision-based guidance for robotic assembly of prefabricated components

IF 9.6 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-02-18 DOI: 10.1016/j.autcon.2025.106065

Chenyu Liu , Jing Wu , Yunfan Gu , Luqi Xie , Gang Wu

A robot-assisted installation method, which uses a crane to bear the component's weight and two robots to control the lifted component for precise horizontal positioning, was proposed in a previous study. To enhance the capability to operate large prefabricated components, this paper designs a binocular vision-based technique for real-time localization of the end-tool during the component-pushing process. Each robot is continuously commanded to rotate and translate the end tool based on the measured difference between its current and target poses, until this difference is within an acceptable threshold. The principles and implementation details of the visual method are described in this paper. Even if the robot deforms or slips, accurate measurement and adjustment of the end tool's pose allow effective pushing of the component to the target area. Test results demonstrate that the binocular vision guidance technology is feasible and effective, improving the flexibility and practicability of the installation-assisted robot.

引用次数: 0

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Automation in Construction

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀