Computer-Aided Civil and Infrastructure Engineering最新文献

{"title":"Pretrained graph neural network for embedding semantic, spatial, and topological data in building information models","authors":"Jin Han, Xin‐Zheng Lu, Jia‐Rui Lin","doi":"10.1111/mice.70073","DOIUrl":"https://doi.org/10.1111/mice.70073","url":null,"abstract":"Large foundation models have demonstrated significant advantages in civil engineering, but they primarily focus on textual and visual data, overlooking the rich semantic, spatial, and topological features in building information modeling (BIM) models. Therefore, this study develops the first large‐scale graph neural network, BIGNet, to learn and reuse multidimensional design features embedded in BIM models. First, a scalable graph representation is introduced to encode the “semantic‐spatial‐topological” features of BIM components, and a dataset with nearly 1 million nodes and 3.5 million edges is created. Subsequently, BIGNet is proposed by introducing a new message‐passing mechanism to GraphMAE2 and further pretrained with a node masking strategy. Finally, BIGNet is evaluated in various transfer learning tasks for BIM‐based design checking. Results show that: (1) homogeneous graph representation outperforms heterogeneous graph in learning design features, (2) considering local spatial relationships in a 30 cm radius enhances performance, and (3) BIGNet with graph attention network‐based feature extraction achieves the best transfer learning results. This innovation leads to a 72.7% improvement in average F1‐score over non‐pretrained models, demonstrating its effectiveness in learning and transferring BIM design features and facilitating their automated application in future design and lifecycle management.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"62 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145035378","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":"Cover Image, Volume 40, Issue 23","authors":"","doi":"10.1111/mice.70069","DOIUrl":"10.1111/mice.70069","url":null,"abstract":"<p><b>The cover image</b> is based on the article <i>Rapid regional assessment of post-hazard structures and transportation infrastructure using aerial images</i> by Sen Yang et al., https://doi.org/10.1111/mice.70015.\u0000\u0000 <figure>\u0000 <div><picture>\u0000 <source></source></picture><p></p>\u0000 </div>\u0000 </figure></p>","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"40 23","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/mice.70069","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145035379","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}

{"title":"Cover Image, Volume 40, Issue 23","authors":"","doi":"10.1111/mice.70068","DOIUrl":"10.1111/mice.70068","url":null,"abstract":"<p><b>The cover image</b> is based on the article <i>A computational method for real-time roof defect segmentation in robotic inspection</i> by Xiayu Zhao et al., https://doi.org/10.1111/mice.13471.\u0000\u0000 <figure>\u0000 <div><picture>\u0000 <source></source></picture><p></p>\u0000 </div>\u0000 </figure></p>","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"40 23","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/mice.70068","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145035380","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}

{"title":"Muck volume measurement of earth pressure balance shield using 3D point cloud based on deep learning","authors":"Shaojie Qin,&nbsp;Yong Fang,&nbsp;Xiao Wang,&nbsp;Junfeng Zhou,&nbsp;Song Luo","doi":"10.1111/mice.70067","DOIUrl":"10.1111/mice.70067","url":null,"abstract":"<p>Earth pressure balance shield over-excavation leads to ground loss, causing ground collapse and posing a serious threat to infrastructure and transportation. Existing shield muck volume control techniques, which are based on weighing or observing the muck box, are unreliable, time-consuming and have large errors. In this paper, a muck volume measurement algorithm and a 3D point cloud segmentation model are proposed to measure the muck volume and control the shield excavation with high accuracy and automation. The model constructs a point-serialized attentional interaction approach that addresses the limitations of the disordered and sparse properties of the point cloud on the local attentional receptive field. In order to segment the dynamic boundary between muck and box, the model designs normal conditional positional encoding to enhance the spatial characteristic representation of the point clouds. The model was trained and tested based on a real shield muck point cloud. The mean accuracy, mean intersection over union, and overall accuracy of the model are 0.987, 0.971, and 0.983, respectively. The maximum calculation error of the muck volume is 3.65% and the average error is 2.71%, which are less than the errors of existing construction technology. The average processing time of the segmentation model for a single sample is 32.5 s, which is about 60 times faster than manual segmentation. These findings have significant engineering value for shield construction control. The code and muck point cloud samples can be obtained from https://github.com/posuifeng/Muck-point-cloud-segmentation.git, password: 3jpi.</p>","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"40 25","pages":"4296-4320"},"PeriodicalIF":9.1,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145035381","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 detection system of metro tunnel lining crack using dynamic snake convolution","authors":"Zhutian Pan, Xuepeng Zhang, Bo Li, Yujing Jiang, Ningbo Li, Chengwei Mei, Hang Su, Yue Cai","doi":"10.1111/mice.70065","DOIUrl":"https://doi.org/10.1111/mice.70065","url":null,"abstract":"Inspecting defects in tunnel linings is a crucial part of tunnel maintenance work. Traditional tunnel inspection methods are generally inefficient, making it difficult to complete intensive inspection tasks and provide detailed characteristic data of cracks within the limited maintenance time. In this research, a deep learning–driven automatic inspection method was developed to evaluate the structural health of metro tunnel linings and deliver quantitative data on lining cracks. The proposed framework encompasses (1) addressing the balance between detection speed and imaging accuracy, developing a front‐end inspection vehicle—the metro tunnel defect detection system—which efficiently and rapidly captures high‐resolution images of the lining surface, alongside establishing a CNN‐based classifier for fast classification of crack images. (2) Considering the slender morphological characteristics of cracks, the DSC_CrackU model was developed for crack segmentation. This model introduces dynamic snake convolution (DSConv) and achieves fine segmentation of cracks by adaptively adjusting the shape of convolution kernels. Meanwhile, it integrates multidimensional feature information by means of the feature fusion module and utilizes the self‐efficient channel module to enhance sensitivity to crack regions. Results show that the algorithm uses fewer computational parameters while maintaining excellent performance in other metrics. (3) We propose a quantitative characterization algorithm based on DSC_CrackU recognition outcomes, which maps pixel‐dimensional features of cracks to the physical dimension, thereby forging a connection between the theoretical framework and engineering standards. Field application tests across multiple tunnels validated the technical feasibility of the proposed framework for engineering applications.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"72 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145035454","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":"Low‐complexity real‐time detection Transformer for identifying bridge vehicle loads","authors":"Longfei Chang, Qizhi Tang, Jingzhou Xin, Yan Jiang, Hong Zhang, Zhenyuan Li, Yin Zhou, Jianting Zhou","doi":"10.1111/mice.70061","DOIUrl":"https://doi.org/10.1111/mice.70061","url":null,"abstract":"Vehicle load identification (VLI) is pivotal for bridge health monitoring, safety assessment, and intelligent maintenance. However, computer vision‐based VLI is confronted by two critical challenges, that is, compromised identification accuracy under dynamic scene and computational constraints imposed by edge monitoring devices. To this end, a low‐complexity real‐time detection Transformer (LC‐RTDETR) is developed to establish a framework for bridge VLI. The proposed LC‐RTDETR provides foundational perception for VLI and features three advantages: (1) lightweight feature extraction via the star network backbone, (2) robust feature representation enabled by the dynamic‐range histogram self‐attention module for single‐scale fusion, and (3) enhanced multi‐scale processing efficiency through the proposed context‐guided spatial feature reconstruction pyramid network. This architecture augments accuracy in complex scenes while reducing computational demands. For continuous trajectory acquisition, detections from the proposed LC‐RTDETR are utilized by BoT‐SORT tracking, which incorporates bridge‐specific camera motion estimation and two‐stage identity association. Precise vehicle positioning is achieved through dual‐bounding‐box localization, in which body‐suspension error minimization and orientation vector updating are implemented. Experimentally, LC‐RTDETR outperforms RTDETR with a 9.8% higher frames per second, 48.2% fewer parameters, and 65.4% lower floating‐point operations. Practical validation confirms robustness to illumination changes, occlusion, motion blur, and adverse weather while accurately capturing stable trajectory during lane‐changing maneuvers and speed fluctuations to enable vehicle localization. Finally, effective weight‐position matching is fully integrated within the framework.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"18 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145035383","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 defect segmentation and quantification in concrete structures via unmanned aerial vehicle‐based lightweight deep learning","authors":"Yangtao Li, Haitao Zhao, Hao Gu, Yang Wei, Zhenyang Xiang, Yiming Wang, Yang Yu, Tengfei Bao","doi":"10.1111/mice.70062","DOIUrl":"https://doi.org/10.1111/mice.70062","url":null,"abstract":"Large‐scale water‐related concrete structures, such as dams, inevitably develop defects over time. Traditional manual inspections are inefficient, hazardous, and prone to high false detection rates. Unmanned aerial vehicles (UAVs) equipped with high‐resolution cameras provide a safer and more efficient alternative. Although deep learning (DL) has advanced defect detection from UAV imagery, many existing approaches are not specifically designed for UAV‐based inspection scenarios, where both inference efficiency and deployment constraints must be carefully considered. In addition, relatively few methods incorporate three‐dimensional (3D) reconstruction for spatial localization and dimensional quantification of concrete defects, limiting the applicability in scenarios requiring precise structural assessment. To overcome current limitations, this study presents an automated framework for defect detection and quantitative assessment in large‐scale concrete structures by integrating UAV photogrammetry, multi‐view 3D reconstruction, and DL techniques. A lightweight defect segmentation method is developed by embedding an enhanced shifted window multi‐head self‐attention module into a streamlined U‐Net architecture, effectively capturing both fine‐grained local details and broader contextual cues. The improved attention mechanism enables efficient inter‐window communication with minimal computational overhead, enhancing the network's ability to detect small and fragmented defects. To further reduce model complexity and improve deployment efficiency, knowledge distillation is applied during training, allowing the student model to maintain high segmentation accuracy with reduced computational cost. In parallel, a multi‐view stereo reconstruction approach is employed to generate accurate 3D point clouds of the inspected structures. Defect locations and dimensions are then quantitatively evaluated through reverse mapping and photogrammetric analysis. The proposed framework is validated through case studies on concrete beams and high‐arch dams. Experimental results demonstrate that the enhanced lightweight U‐Net achieves accurate segmentation, while the 3D reconstruction enables defect‐precise spatial localization and millimeter‐level measurement. These findings highlight the potential of combining UAV imaging, DL, and 3D reconstruction for efficient and reliable inspection of large concrete structures.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"66 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145035382","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":"Data-driven optimization of wind pressure sensor placement on low-rise buildings using computational fluid dynamics and multi-resolution dynamic mode decomposition","authors":"R. Al-Chalabi,&nbsp;M. Alanani,&nbsp;A. Elshaer,&nbsp;A. El Damatty","doi":"10.1111/mice.70025","DOIUrl":"10.1111/mice.70025","url":null,"abstract":"<p>This study presents a novel hybrid framework for optimal sensor placement to evaluate wind loads on low-rise buildings. Recognizing the challenges of deploying dense sensor arrays in turbulent atmospheric boundary layer wind tunnel tests, the proposed method integrates large eddy simulation with multi-resolution dynamic mode decomposition (mrDMD) to isolate spatiotemporally dominant flow features. Unlike traditional DMD-based approaches that capture global modes, the use of mrDMD enables scale-separated modal analysis, enhancing sensitivity to transient and localized flow dynamics. These modes guide a QR pivoting algorithm, which efficiently selects sensor locations that maximize information content. The framework demonstrates a sensor count reduction of over 80%, from 1426 candidates to just 182 sensors, while preserving high reconstruction accuracy (<i>R</i> &gt; 90%) for both mean and fluctuating pressure fields. This distinction enables robust and cost-effective wind load assessment without compromising fidelity. The methodology is validated using wind tunnel experiments and is shown to be applicable for generalized wind scenarios through an angle-of-attack-unified sensor configuration. By combining modal decomposition with informed optimization, this framework advances state-of-the-art techniques in structural monitoring, offering practical utility in experimental and real-world applications.</p>","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"40 23","pages":"3652-3673"},"PeriodicalIF":9.1,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/mice.70025","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145002954","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}

{"title":"Data-driven distributionally robust optimization of railway alignments in earthquake-prone regions considering active fault zone risks","authors":"Taoran Song,&nbsp;Hao Pu,&nbsp;T. Y. Yang,&nbsp;Paul Schonfeld,&nbsp;Wei Guo,&nbsp;Xiao Pan,&nbsp;Jianping Hu","doi":"10.1111/mice.70054","DOIUrl":"10.1111/mice.70054","url":null,"abstract":"<p>Railway alignment design in earthquake-prone regions faces many challenges, among which an active fault zone threat is a dominant factor. However, slight attention has been devoted in this field to the complex fault zone risks affecting alignment optimization (AO). To this end, the first-known AO model that estimates active fault zone risks is proposed according to the distributionally robust optimization (DRO) theory. In this model, a data-driven minimax DRO function is formulated to compute the uncertain fault zone risks while optimizing railway alignments. In addition, a degree-of-regret (DoR) chance constraint is developed to trade off solution quality and search conservatism during optimization. To solve this DRO model, a particle swarm algorithm is improved in two ways. First, a Monte Carlo simulation is customized based on several alignment refinement analyses to assess possible railway losses due to uncertain fault zone damages. Afterward, a solution selection operator is devised to determine the best alignment alternatives while tackling the DoR constraint. Ultimately, the proposed DRO model and algorithm are applied to a real-world railway example. Their effectiveness is verified through two sensitivity analyses and by being compared with the best solution found by human designers.</p>","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"40 25","pages":"4321-4341"},"PeriodicalIF":9.1,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/mice.70054","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144924117","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}

{"title":"Exact Dirichlet boundary multi-resolution hash encoding solver for structures","authors":"Xiaoge Tian,&nbsp;Jiaji Wang,&nbsp;Xinzheng Lu","doi":"10.1111/mice.70045","DOIUrl":"10.1111/mice.70045","url":null,"abstract":"<p>Designed to address computationally expensive scientific problems, physics-informed neural networks (PINNs) have primarily focused on solving issues involving relatively simple geometric shapes. Drawing inspiration from exact Dirichlet boundary PINN and neural representation field, this study first develops a multi-resolution hash encoding solver (MHS) as another pure physics-driven alternative. Compared to vanilla PINN, MHS achieves a 1000-time increase in computational speed for the 2D plane stress case. When compared to finite element method (FEM) software with graphic processing unit (GPU) acceleration, MHS can achieve a five-time speedup for the plane case and a two-time speedup for the 3D two-span three-story frame case. The general performance of optimized hyperparameters in automated machine learning MHS (AMHS) is evaluated by transferring AMHS to solve another hyper-elasticity rubber cube problem. For a hyper-elasticity cube, the AMHS model can approach solutions with comparable accuracy to FEM results, while the developed parallel MHS delivers at least 100 times in acceleration parametric analysis, compared to FEM commercial software (GPU-accelerated).</p>","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"40 25","pages":"4172-4192"},"PeriodicalIF":9.1,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/mice.70045","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144924118","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}