{"title":"Multi-stage recognition scheme for urban road construction intrusion using fiber-optic distributed acoustic sensing","authors":"Peng Wu , Jing Wu , Yixuan Dong , Shuya Zhang , Lan Wu , Dong Wu","doi":"10.1016/j.autcon.2025.106554","DOIUrl":"10.1016/j.autcon.2025.106554","url":null,"abstract":"<div><div>Urban road construction threatens buried utility networks, causing significant economic and safety risks. Traditional monitoring scheme faces high costs, limited coverage, and slow response times. This paper introduces an urban-scale multi-stage recognition scheme using fiber-optic distributed acoustic sensing (DAS) for real-time road construction intrusion monitoring across existing urban telecom networks. The multi-stage approach includes: prejudgment, efficiently filtering potential intrusion regions; recognition, using a hybrid deep learning model for event classification; and review, enhancing reliability through a spatial-temporal continuity mechanism. A comprehensive urban intrusion dataset was created featuring distinct vibration patterns from seven interference and eight construction events. A challenging 14-day field test across 60 km of urban environment validated the approach, achieving 99.25 % localization accuracy, 98.80 % classification accuracy, and a response time of 0.99 s. This scalable, cost-effective solution for infrastructure protection integrates with existing telecom networks and offers potential applications in urban security and emergency response.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"180 ","pages":"Article 106554"},"PeriodicalIF":11.5,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145118970","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}
Chao Lin , Yu Chen , Kenta Itakura , Shreejan Maharjan , Pang-jo Chun
{"title":"Bridge inspection using image–point cloud fusion with image filtering, damage detection and 3D registration","authors":"Chao Lin , Yu Chen , Kenta Itakura , Shreejan Maharjan , Pang-jo Chun","doi":"10.1016/j.autcon.2025.106538","DOIUrl":"10.1016/j.autcon.2025.106538","url":null,"abstract":"<div><div>Complex image backgrounds often compromise the reliability of damage detection. In bridge inspection, a further challenge lies in accurately recording and localizing the detected damage onto a 3D model. Based on image and point cloud data (PCD) fusion, this paper proposes a five-step methodology for detecting bridge damage and registering it on a 3D model. High-quality images and PCD files are simultaneously collected using a LiDAR 3D camera with their relationships clearly recorded. The complete bridge PCD is segmented and subsequently utilized to select images containing needed components and filter out the background via 3D-to-2D projection. Damage is detected from background-filtered images and then registered on the bridge PCD through 2D-to-3D projection. An experiment conducted on an actual bridge validated the feasibility of the proposed framework, confirming that the methodology not only produces clear and intuitive 3D visualizations of damage but also effectively supports detailed inspection and maintenance tasks.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"180 ","pages":"Article 106538"},"PeriodicalIF":11.5,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145118966","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}
Boyu Wang , Fangzhou Lin , Mingkai Li , Zhenyu Liang , Hongzhe Yue , Qian Wang , Jack C.P. Cheng
{"title":"Aligning as-built and as-designed: Local point cloud to BIM registration via hybrid visibility map encoding for construction digital twins","authors":"Boyu Wang , Fangzhou Lin , Mingkai Li , Zhenyu Liang , Hongzhe Yue , Qian Wang , Jack C.P. Cheng","doi":"10.1016/j.autcon.2025.106551","DOIUrl":"10.1016/j.autcon.2025.106551","url":null,"abstract":"<div><div>Aligning local as-built data including point clouds and images with as-designed BIMs is critical for enabling construction digital twins. However, automated registration of local scan data to BIMs remains challenging due to modality gaps, large search spaces, structural self-similarity, and geometric inconsistencies. This paper leverages visibility maps for their inherent robustness to modality differences and strong discriminative capability in self-similar environments, proposing a hybrid visibility map encoding approach that integrates traditional geometric descriptors with deep features extracted from vision foundation models for local point cloud to BIM registration. Experiments on real construction sites showed over 92 % registration success, outperforming traditional local and global feature-based methods. The results enable more effective quality control, progress tracking, and model updating for stakeholders concerned with construction projects. This work paves the way for future research on applying foundation models to cross-domain data alignment and broader applications in the built environment sector.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"180 ","pages":"Article 106551"},"PeriodicalIF":11.5,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145118969","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}
Hao Feng , Yi Zhong , Chenxi Zhou , Shengliang Ji , Chenbo Yin , Donghui Cao
{"title":"Collaborative high-precision trajectory control for heavy excavators based on an improved particle swarm optimization algorithm","authors":"Hao Feng , Yi Zhong , Chenxi Zhou , Shengliang Ji , Chenbo Yin , Donghui Cao","doi":"10.1016/j.autcon.2025.106546","DOIUrl":"10.1016/j.autcon.2025.106546","url":null,"abstract":"<div><div>Heavy excavators suffer from low trajectory accuracy due to nonlinear dynamics, inter-joint coupling, and synchronization errors among electro-hydraulic systems. Conventional methods inadequately address these issues during high-speed operation. To overcome these limitations, this research proposes a cooperative control framework that integrates a collaborative evaluation method and an improved particle swarm optimization. A dual error metric is designed based on the tracking error of the single servo system and mean-coupled collaborative error. The inertia weight adaptive method, asynchronous learning coefficient adjustment method, and elite mutation method are introduced to improve the algorithm's performance. Experimental results demonstrate that under 400 mm/s high-speed condition, the proposed controller achieves a root mean square error of 10.90 mm, representing reductions of 61.65 % and 72.26 % compared to master-slave collaborative trajectory controller and traditional independent parallel controller respectively. The proposed collaborative high-precision trajectory controller enables precise and robust control of excavators across different speed scenarios.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"180 ","pages":"Article 106546"},"PeriodicalIF":11.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145093961","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}
Zihan Liu , Tianxiang Liu , Hanbin Luo , Yongping Di , Han Gao , Wenli Liu
{"title":"Bilevel programming approach for large-scale urban flood control measures of drainage system","authors":"Zihan Liu , Tianxiang Liu , Hanbin Luo , Yongping Di , Han Gao , Wenli Liu","doi":"10.1016/j.autcon.2025.106533","DOIUrl":"10.1016/j.autcon.2025.106533","url":null,"abstract":"<div><div>Despite the increasing attention on urban flood control measures (UFCM) for urban drainage systems (UDS), current approaches often overlook the spatial variation in urban flood resilience (UFR) and trade-offs across multiple decision-making levels. To address these challenges, this paper develops a bilevel multi-objective optimization (BMOO) model for large-scale UFCM, aiming at an optimal trade-off of public safety, sustainability, and efficiency. The results show that the model can effectively address the diverse objectives of two decision-making levels. The bilevel model can reduce the risk of surface overflows risk and improve the resilience of the UDS compared to the initial scheme while saving 39.8 % of the travel distance. In general, this paper presents a bilevel approach to solve simultaneously a multi-objective and multi-level decision-making problem in large-scale UFCM, providing an optimized solution for regional-level spatial prioritization, component-level critical segments identification, and route planning in UDS maintenance activity.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"180 ","pages":"Article 106533"},"PeriodicalIF":11.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145093963","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}
Joseph M. Gattas , Lisa-Mareike Ottenhaus , Hongjia Liu , Yi Min Xie
{"title":"Design and optimisation of timber-framed structures using a stock of reclaimed elements","authors":"Joseph M. Gattas , Lisa-Mareike Ottenhaus , Hongjia Liu , Yi Min Xie","doi":"10.1016/j.autcon.2025.106527","DOIUrl":"10.1016/j.autcon.2025.106527","url":null,"abstract":"<div><div>The reuse of reclaimed timber in structural applications is limited by irregular geometries and mixed material properties, posing complex optimisation challenges. This paper presents a computational framework for designing timber-framed modular buildings from mixed reclaimed material stock. It combines a set-based stock allocation method with an integer linear programming optimisation, where cutting and jointing patterns are decision variables. Two case studies demonstrate the framework, including the construction of multiple modular houses using nearly two kilometres of recycled timber. A globally optimal solution for six houses was found in under 1.5 s, using 760 parts with 77.6% stock utilisation and 83.7% cutting efficiency. Compared to existing stock-constrained structural design tools, the framework expands capability by handling mixed grades, stock allocation across structural subsystems, and enabling cutting and jointing into shorter, longer, or laminated members. It further allows near-real-time optimisation of materially efficient part arrangements within framed structural systems.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"180 ","pages":"Article 106527"},"PeriodicalIF":11.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145093964","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":"Automated BIM generation for MEP systems from CAD data using multi-drawing graph integration","authors":"Qian Zhao , Hao Shi , Liangchen Zhou , Guonian Lv","doi":"10.1016/j.autcon.2025.106542","DOIUrl":"10.1016/j.autcon.2025.106542","url":null,"abstract":"<div><div>Building information modeling (BIM) of mechanical, electrical, and plumbing (MEP) systems is essential for building facility management. Computer-aided-design (CAD) data are detailed sources for MEP BIM modeling. However, existing methods for MEP BIM are complex, leading to heavy reliance on manual intervention. This paper addresses this challenge by proposing an approach for generating MEP BIM models from CAD data. Graph structures are introduced to represent MEP systems, and multiple graph structures converted from CAD drawings are utilized to match pipeline components and aggregate dispersed information across various drawings. Based on the integrated pipeline graph, missing information is inferred and completed considering the relationships between components, ensuring detailed and accurate modeling results. Experiments on an actual factory case demonstrate the reliability and efficiency of this approach. This paper contributes to the MEP BIM theory by providing a perspective on interpreting MEP CAD data and a robust technical route of CAD-to-BIM conversion for MEP systems.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"180 ","pages":"Article 106542"},"PeriodicalIF":11.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145093962","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}
Hanmo Wang , Zhuyin Lu , Shawn Owyong , Huan Ting Chen , Cai Wu , Tam H. Nguyen , Alexander Lin
{"title":"Advancing graph-supported machine learning in generative design for architectural engineering","authors":"Hanmo Wang , Zhuyin Lu , Shawn Owyong , Huan Ting Chen , Cai Wu , Tam H. Nguyen , Alexander Lin","doi":"10.1016/j.autcon.2025.106530","DOIUrl":"10.1016/j.autcon.2025.106530","url":null,"abstract":"<div><div>Graph-Supported Machine Learning (GML), including Graph Neural Networks (GNNs) and Probabilistic Graphical Models (PGMs), shows promise for tackling Generative Design (GD) challenges in architectural engineering. However, a systematic review of its use, limitations, and future potential is still lacking. This paper addresses that gap by analyzing 70 peer-reviewed papers, mapping their applications, data sources, and model types. A two-tier analysis identifies key limitations, including small datasets, narrow generalization, and limited integration of physical laws or expert feedback. To overcome these challenges, five strategic directions are proposed: co-evolving data and algorithms, hybrid modeling with Bayesian Networks and GNNs, graph sparsification, human-in-the-loop design refinement, and physics-informed learning. These directions guide the development of more versatile and practical GML models, able to adapt across scales, reduce computational cost, and align with design intent and engineering principles. The findings are intended to foster innovative design practices and advance automation in construction through enhanced computer-aided design.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"180 ","pages":"Article 106530"},"PeriodicalIF":11.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145094179","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}
Weili Fang , Guanghui Geng , Gan Zhang , Peter E.D. Love
{"title":"Autonomous launching gantry: Improved monocular vision approach for real-time pose estimation of precast concrete girders","authors":"Weili Fang , Guanghui Geng , Gan Zhang , Peter E.D. Love","doi":"10.1016/j.autcon.2025.106534","DOIUrl":"10.1016/j.autcon.2025.106534","url":null,"abstract":"<div><div>The absence of accurate and real-time 6-DoF pose data for precast concrete girders renders launching gantry operations predominantly manual, thereby impeding further automation. Such limitations pose a critical question: <em>How can we accurately and robustly estimate the pose of precast concrete girders in real-time during launching gantry operations?</em> To address that question, our paper proposes a monocular vision-based approach to estimate the 6-DoF pose of the precast concrete girder in launching gantry operations. The approach detects the ChArUco board regions using the YOLOv11n model, applies GAN-based image deblurring. The 6-DoF pose is then estimated using a Perspective-n-Point solver and transformed to the gantry coordinate system. Field tests demonstrate robust performance, achieving a mean reprojection error of 0.113 pixels and a processing latency of 60 ms per frame. The results validate the approach's robustness and real-time performance, highlighting monocular vision as a cost-effective alternative to LiDAR–IMU fusion for large-scale automation in construction.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"180 ","pages":"Article 106534"},"PeriodicalIF":11.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145094163","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}
Zijin Qiu , Jiepeng Liu , Yantao Wu , Pengkun Liu , Hongtuo Qi , Haobo Liang , Yi Xia
{"title":"LLM-based framework for automated and customized floor plan design","authors":"Zijin Qiu , Jiepeng Liu , Yantao Wu , Pengkun Liu , Hongtuo Qi , Haobo Liang , Yi Xia","doi":"10.1016/j.autcon.2025.106512","DOIUrl":"10.1016/j.autcon.2025.106512","url":null,"abstract":"<div><div>Interpreting diverse and ambiguous natural language (NL) user requirements into precise floor plans poses significant challenges for design automation. This paper presents a large language model (LLM)-based framework to automate and customize vectorized floor plan design. This framework utilizes a syntax tree for NL parsing and automated dataset enrichment. A dual LLM approach involves using a recognition model for automated dataset augmentation, while a generation model interprets user inputs to create diverse, geometrically precise vectorized floor plans that align with complex semantic preferences. Experimental results demonstrate the proposed LLM-based models' effectiveness, achieving high accuracy in interpreting user requirements and high quality in generating corresponding vectorized floor plans. Additionally, a large-scale NL-based dataset is generated through the automatic recognition of existing floor plans. The proposed method can advance automated and user-centric floor plan design by enabling direct NL interaction and generating readily usable vectorized outputs.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"180 ","pages":"Article 106512"},"PeriodicalIF":11.5,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145094176","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}