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}
{"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}
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}
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}
Wenbo Hu , Xianhua Liu , Zhizhang Zhou , Weidong Wang , Zheng Wu , Zhengwei Chen
{"title":"Robust crack detection in complex slab track scenarios using STC-YOLO and synthetic data with highly simulated modeling","authors":"Wenbo Hu , Xianhua Liu , Zhizhang Zhou , Weidong Wang , Zheng Wu , Zhengwei Chen","doi":"10.1016/j.autcon.2025.106219","DOIUrl":"10.1016/j.autcon.2025.106219","url":null,"abstract":"<div><div>Crack detection in slab tracks plays a crucial role in accident prevention. Existing algorithms primarily operate on monotonous concrete backgrounds and often struggle with data scarcity and complex scenes. This paper proposes a parametric slab track model replicating real-world inspection conditions through high-fidelity virtual simulation, enabling realistic synthetic crack data generation. The subsequently developed STC-YOLO network utilizes these synthetic images to enhance fine crack detection in complex slab track scenes. Results show that STC-YOLO trained on synthetic data (4:1 virtual-to-real ratio) achieves over 20 % improvements in both mAP and recall compared to using no virtual images, outperforming traditional augmentation methods like horizontal flipping and color dithering. Moreover, STC-YOLO exhibits over 6 % higher mAP than the baseline algorithm and surpasses five state-of-the-art object detection networks. The proposed algorithm greatly reduces the cost of data acquisition.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"175 ","pages":"Article 106219"},"PeriodicalIF":9.6,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851691","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}
Shihang Zhang , Sherong Zhang , Han Liu , Xiaohua Wang , Zhiyong Zhao , Chao Wang , Lei Yan
{"title":"Integration of BIM and ontologies for pumped storage hydropower design change management in EPC projects","authors":"Shihang Zhang , Sherong Zhang , Han Liu , Xiaohua Wang , Zhiyong Zhao , Chao Wang , Lei Yan","doi":"10.1016/j.autcon.2025.106189","DOIUrl":"10.1016/j.autcon.2025.106189","url":null,"abstract":"<div><div>Design changes are an inevitable multidisciplinary issue in the Engineering, Procurement, and Construction (EPC) projects for pumped storage hydropower systems. However, semantic heterogeneity poses significant challenges making Building Information Modeling (BIM) workflows for design change management time-consuming and error-prone. To address this issue, this paper proposes an ontology integration approach that unifies decentralized knowledge of Industry Foundation Classes (IFC) and the BIM Collaboration Format (BCF). A Semantic Design Change Management System (SDCMS) is developed for EPC contractors and validated through a case study. The results indicate that the proposed approach achieves significant improvements in system efficiency and data standardization. This paper highlights the potential for knowledge reuse to automate BIM workflows and provides practical insights into renewable energy construction management in the context of energy transition and carbon neutrality.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"175 ","pages":"Article 106189"},"PeriodicalIF":9.6,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143854967","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}
Hongzhe Yue , Qian Wang , Yangzhi Yan , Guanying Huang
{"title":"Deep learning-based point cloud completion for MEP components","authors":"Hongzhe Yue , Qian Wang , Yangzhi Yan , Guanying Huang","doi":"10.1016/j.autcon.2025.106218","DOIUrl":"10.1016/j.autcon.2025.106218","url":null,"abstract":"<div><div>Point clouds are increasingly leveraged for as-built model reconstruction of facilities. However, point clouds of Mechanical, Electrical, and Plumbing (MEP) systems often experience extensive occlusions, which heavily affect the performance of model reconstruction. To address this challenge, this paper explores deep learning (DL)-based point cloud completion algorithms to complete occluded MEP point clouds. Due to the limited availability of datasets, parametric BIM modeling and occlusion simulation are used to generate synthetic point cloud datasets of MEP components. Based on generated datasets, the effectiveness of five different DL algorithms and five distinct training strategies for point cloud completion are investigated. The results indicate that: (1) The PoinTr model with a pre-training strategy achieved the best Chamfer Distance (CD) and F-score, demonstrating effective completion even with 75 % missing point clouds. 2) Applying the proposed point cloud completion method to three practical tasks further demonstrates the algorithm's applicability.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"175 ","pages":"Article 106218"},"PeriodicalIF":9.6,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143850770","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}
{"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}
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}
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}