Automation in Construction最新文献_第2页

Self-adaptive seam detection framework for unmanned structural steel welding robots in unstructured environments

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-04-23 DOI: 10.1016/j.autcon.2025.106221

Yuzhen He , Zhaoqi Huang , Haotian Liu , Jingang Ye , Yujie Lu , Xianzhong Zhao

{"title":"Self-adaptive seam detection framework for unmanned structural steel welding robots in unstructured environments","authors":"Yuzhen He , Zhaoqi Huang , Haotian Liu , Jingang Ye , Yujie Lu , Xianzhong Zhao","doi":"10.1016/j.autcon.2025.106221","DOIUrl":"10.1016/j.autcon.2025.106221","url":null,"abstract":"<div><div>Existing vision-based seam detection frameworks for structural steel welding robots perform well in static, predefined workspaces but struggle in dynamic, unstructured real production environments. Therefore, a self-adaptive seam detection framework is proposed that enables welding robots to interpret the actual welding environment through an estimation of the target workpiece pose. An enhanced pose estimation algorithm is developed to generate a reliable workpiece pose estimation based on solely one RGB image. Based on this real-time workpiece pose, the system autonomously determined the necessary robot movements toward an optimal position and orientation for subsequent high-precision structured light sensor measurements. The seam extraction and welding trajectory planning were then completed through an automated process. Experimental results demonstrate that the proposed framework not only enables cost-effective, fully automated weld seam detection in dynamic unstructured environments, but also achieves 72 % higher efficiency than conventional methods while eliminating human intervention.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"175 ","pages":"Article 106221"},"PeriodicalIF":9.6,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143859003","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

Efficient instance segmentation framework for UAV-based pavement distress detection

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-04-22 DOI: 10.1016/j.autcon.2025.106195

Jiakai Zhou , Yang Wang , Wanlin Zhou

{"title":"Efficient instance segmentation framework for UAV-based pavement distress detection","authors":"Jiakai Zhou , Yang Wang , Wanlin Zhou","doi":"10.1016/j.autcon.2025.106195","DOIUrl":"10.1016/j.autcon.2025.106195","url":null,"abstract":"<div><div>Pavement distress detection is critical for ensuring road safety. Recently, Unmanned Aerial Vehicles (UAVs) become an efficient means of capturing large-scale pavement images. However, traditional pavement distress detection methods face challenges with UAV images: object detection lacks pixel-level information, while semantic segmentation fails to differentiate between individual instances. This paper introduces PDIS-Net, an instance segmentation framework specifically designed for UAV-based pavement distress detection. PDIS-Net first employs a fully dynamic convolution kernel generation strategy, predicting both kernel positions and weights. These kernels are then optimized via metric learning and kernel fusion. Finally, these high-quality kernels are convolved with feature maps to produce accurate instance masks. Experimental results on the UAPD-Instance dataset reveal that PDIS-Net achieves a mean average precision (mAP) of 78.1% at 30.8 FPS, outperforming other methods by 15.4%. Furthermore, real-world tests validate the robustness and effectiveness of PDIS-Net in highway pavement distress detection, highlighting its potential for practical deployment.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"175 ","pages":"Article 106195"},"PeriodicalIF":9.6,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143854968","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

Parallel simulation and prediction techniques for digital twins in urban underground spaces

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-04-21 DOI: 10.1016/j.autcon.2025.106212

Haofeng Gong , Dong Su , Shiqi Zeng , Xiangsheng Chen

{"title":"Parallel simulation and prediction techniques for digital twins in urban underground spaces","authors":"Haofeng Gong , Dong Su , Shiqi Zeng , Xiangsheng Chen","doi":"10.1016/j.autcon.2025.106212","DOIUrl":"10.1016/j.autcon.2025.106212","url":null,"abstract":"<div><div>With the advancement of intelligent systems and the increasing utilization of underground spaces, digital twin technology has become pivotal in enhancing the efficiency and safety of subterranean operations and maintenance. The concept of parallel simulation and prediction (PSP) technology, a critical component in the realization of digital twins, along with its associated research challenges, requires further elucidation. This paper offers a comprehensive overview of current research on PSP within the context of digital twins for urban underground spaces. The 62 papers meeting the inclusion and exclusion criteria are categorized into two key areas: model updating and future evolution prediction. Key challenges identified include the need for regular updates in geometric models, the demand for real-time predictive analytics, and data-related issues in information modeling. Finally, future research directions are outlined, focusing on the automatic interpretation of detection data, self-updating digital twin models, and multi-source heterogeneous data integration technologies.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"175 ","pages":"Article 106212"},"PeriodicalIF":9.6,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851690","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

Integrating domain-specific knowledge and fine-tuned general-purpose large language models for question-answering in construction engineering management

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-04-21 DOI: 10.1016/j.autcon.2025.106206

Shenghua Zhou , Xuefan Liu , Dezhi Li , Tiantian Gu , Keyan Liu , Yifan Yang , Mun On Wong

{"title":"Integrating domain-specific knowledge and fine-tuned general-purpose large language models for question-answering in construction engineering management","authors":"Shenghua Zhou , Xuefan Liu , Dezhi Li , Tiantian Gu , Keyan Liu , Yifan Yang , Mun On Wong","doi":"10.1016/j.autcon.2025.106206","DOIUrl":"10.1016/j.autcon.2025.106206","url":null,"abstract":"<div><div>General-purpose Large Language Models (GLLMs) for Question-Answering (QA) of Construction Engineering Management (CEM) usually lack CEM knowledge and fine-tuning datasets, leading to unsatisfactory performance. Hence, this paper integrates the CEM External Knowledge Base (CEM-EKB) with out-of-domain fine-tuned GLLMs for CEM-QA. It encompasses (i) devising a process to develop the CEM-EKB with 235 documents, (ii) conducting out-of-domain fine-tuning to enhance GLLMs' abilities, (iii) integrating CEM-EKB with fine-tuned GLLMs, (iv) building CEM-QA test datasets with 5050 Multiple-Choice Questions (MCQs) and 100 Case-Based Questions (CBQs), and (v) comparing GLLMs' performance. The results indicate that CEM knowledge-incorporated fine-tuned GLLMs surpass original GLLMs by an average of 27.1 % in professional examinations, with an average improvement of 27.5 % across 7 CEM subdomains and 22.05 % for CBQs. This paper contributes to devising an effective, reusable, and updatable CEM-EKB; revealing the feasibility of out-of-domain datasets for fine-tuning; and sharing a large-scale CEM-QA test dataset.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"175 ","pages":"Article 106206"},"PeriodicalIF":9.6,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851689","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

Robust crack detection in complex slab track scenarios using STC-YOLO and synthetic data with highly simulated modeling

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-04-21 DOI: 10.1016/j.autcon.2025.106219

Wenbo Hu , Xianhua Liu , Zhizhang Zhou , Weidong Wang , Zheng Wu , Zhengwei Chen

引用次数: 0

Integration of BIM and ontologies for pumped storage hydropower design change management in EPC projects

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-04-21 DOI: 10.1016/j.autcon.2025.106189

Shihang Zhang , Sherong Zhang , Han Liu , Xiaohua Wang , Zhiyong Zhao , Chao Wang , Lei Yan

引用次数: 0

Deep learning-based point cloud completion for MEP components

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-04-19 DOI: 10.1016/j.autcon.2025.106218

Hongzhe Yue , Qian Wang , Yangzhi Yan , Guanying Huang

引用次数: 0

Robust skeleton-based AI for automatic multi-person fall detection on construction sites with occlusions

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-04-18 DOI: 10.1016/j.autcon.2025.106216

Doil Kim , Xiaoqun Yu , Shuping Xiong

{"title":"Robust skeleton-based AI for automatic multi-person fall detection on construction sites with occlusions","authors":"Doil Kim , Xiaoqun Yu , Shuping Xiong","doi":"10.1016/j.autcon.2025.106216","DOIUrl":"10.1016/j.autcon.2025.106216","url":null,"abstract":"<div><div>Rapid and accurate automatic fall detection is essential for improving worker safety and reducing the severity of fall-related incidents on construction sites. To address the challenges of real-time detection in complex and obstructed construction environments, this paper develops a specialized dataset for fall scenarios and introduces a skeleton-based AI model called YOSAP-LSTM. This model integrates YOLOv8 for human detection, SORT and AlphaPose for precise tracking of human keypoints, and a 1D CNN-LSTM for classifying falls versus non-falls. This approach achieves an impressive accuracy of 98.66 % (sensitivity: 97.32 %; specificity: 99.10 %), outperforming current fall detection algorithms while maintaining high accuracy under occlusions. Deployed on an edge device (NVIDIA Jetson Xavier NX), the system runs at 6.44 fps, meeting real-time requirements for portable applications. The YOSAP-LSTM model is both robust and practical, offering significant potential for real-world use in construction by enhancing worker safety through timely fall detection in challenging environments.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"175 ","pages":"Article 106216"},"PeriodicalIF":9.6,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143843847","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

Augmented Reality-based construction site management using optimized BIM and project schedule integration 利用优化的 BIM 和项目进度表集成，实现基于增强现实技术的施工现场管理

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-04-18 DOI: 10.1016/j.autcon.2025.106204

Sanyukta Arvikar , Pa Pa Win Aung , Gichun Cha , Seunghee Park

{"title":"Augmented Reality-based construction site management using optimized BIM and project schedule integration","authors":"Sanyukta Arvikar , Pa Pa Win Aung , Gichun Cha , Seunghee Park","doi":"10.1016/j.autcon.2025.106204","DOIUrl":"10.1016/j.autcon.2025.106204","url":null,"abstract":"<div><div>The construction industry has experienced significant transformation with the adoption of Building Information Modeling (BIM) technology, which provides a virtual representation of both the physical and functional components of construction projects. In this context, project scheduling becomes a vital tool for site managers to assess construction progress. This paper introduces an augmented reality (AR) system for construction site management that integrates optimized BIM models with project schedules to enhance real-time progress tracking. Optimized models are crucial for accurate overlaying at full scale in the real world, allowing for real-time monitoring of site progress based on evolving project timelines. This is achieved through a method of splitting the BIM model according to user-selected timeframes within the AR application. The system was tested on five bridge construction sites, and its effectiveness was evaluated through a structured survey of 30 on-site professionals, including engineers and project managers. The findings offer valuable insights for the construction industry, enabling efficient management and tracking of project progress by comparing planned schedules with actual performance. Additionally, this paper addresses a gap in the limited research on the integration of BIM and AR for site progress monitoring, while minimizing the loss of Revit metadata.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"175 ","pages":"Article 106204"},"PeriodicalIF":9.6,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143847510","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

Transformer-based time-series GAN for data augmentation in bridge digital twins

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-04-18 DOI: 10.1016/j.autcon.2025.106208

Vahid Mousavi , Maria Rashidi , Shayan Ghazimoghadam , Masoud Mohammadi , Bijan Samali , Joshua Devitt

{"title":"Transformer-based time-series GAN for data augmentation in bridge digital twins","authors":"Vahid Mousavi , Maria Rashidi , Shayan Ghazimoghadam , Masoud Mohammadi , Bijan Samali , Joshua Devitt","doi":"10.1016/j.autcon.2025.106208","DOIUrl":"10.1016/j.autcon.2025.106208","url":null,"abstract":"<div><div>Recent advancements in AI-based Digital Twins (DTs) have substantially influenced bridge monitoring and maintenance, especially through Deep Learning (DL) for sensor-based damage detection. However, the effectiveness of DL models is constrained by the extensive training data they require, which is often costly and time-consuming to collect in bridge infrastructure contexts. To address this data scarcity, this paper proposes a data augmentation strategy employing a transformer-based time-series Wasserstein generative adversarial network with gradient penalty (TTS-WGAN-GP) to generate synthetic acceleration data. The synthetic data's fidelity is validated through similarity metrics and frequency domain analysis, showing close alignment with real acceleration signals for damage detection. Results demonstrate that this method achieves high-quality synthetic data with superior computational efficiency compared to existing approaches, improving dataset balancing and potentially enhancing the performance of data-driven models in DTs. This approach reduces dependence on extensive data collection, supporting reliable bridge health monitoring applications.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"175 ","pages":"Article 106208"},"PeriodicalIF":9.6,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143843842","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