Automation in Construction最新文献

英文中文

Associative reasoning for engineering drawings using an interactive attention mechanism 基于交互注意机制的工程图关联推理

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

Automation in Construction

Pub Date : 2025-02-01 DOI: 10.1016/j.autcon.2024.105942

Xu Xuesong , Xiao Gang , Sun Li , Zhang Xia , Wu Peixi , Zhang Yuanming , Cheng Zhenbo

In infrastructure construction, engineering drawings combine graphic and textual information, with text playing a critical role in retrieving and measuring the similarity of these drawings in practical applications. However, existing research primarily focuses on graphics, neglecting the extraction and semantic representation of text. Existing Optical Character Recognition (OCR)-based methods face challenges in clustering text into coherent semantic modules, frequently dispersing related text across different regions. Therefore, this paper proposes a deep learning framework for the semantic extraction of text from engineering drawings. By integrating textual, positional, and image features, this framework enables semantic extraction and represents engineering drawings as knowledge graphs. An interactive attention-based approach is employed for associative retrieval of engineering drawings via subgraph matching. Evaluation on datasets from a transportation design institute and public sources demonstrates the framework's effectiveness in both semantic extraction and relational reasoning.

在基础设施建设中，工程图纸是图文信息的结合，在实际应用中，文本在检索和测量工程图纸的相似度方面起着至关重要的作用。然而，现有的研究主要集中在图形上，忽略了文本的提取和语义表示。现有的基于光学字符识别（OCR）的方法在将文本聚类到连贯的语义模块中，导致相关文本经常分散在不同的区域。因此，本文提出了一种用于工程图纸文本语义提取的深度学习框架。通过集成文本、位置和图像特征，该框架支持语义提取，并将工程图纸表示为知识图。采用基于交互注意的子图匹配方法对工程图进行关联检索。对来自交通设计院和公共资源的数据集的评估表明，该框架在语义提取和关系推理方面都是有效的。

{"title":"Associative reasoning for engineering drawings using an interactive attention mechanism","authors":"Xu Xuesong , Xiao Gang , Sun Li , Zhang Xia , Wu Peixi , Zhang Yuanming , Cheng Zhenbo","doi":"10.1016/j.autcon.2024.105942","DOIUrl":"10.1016/j.autcon.2024.105942","url":null,"abstract":"<div><div>In infrastructure construction, engineering drawings combine graphic and textual information, with text playing a critical role in retrieving and measuring the similarity of these drawings in practical applications. However, existing research primarily focuses on graphics, neglecting the extraction and semantic representation of text. Existing Optical Character Recognition (OCR)-based methods face challenges in clustering text into coherent semantic modules, frequently dispersing related text across different regions. Therefore, this paper proposes a deep learning framework for the semantic extraction of text from engineering drawings. By integrating textual, positional, and image features, this framework enables semantic extraction and represents engineering drawings as knowledge graphs. An interactive attention-based approach is employed for associative retrieval of engineering drawings via subgraph matching. Evaluation on datasets from a transportation design institute and public sources demonstrates the framework's effectiveness in both semantic extraction and relational reasoning.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"170 ","pages":"Article 105942"},"PeriodicalIF":9.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918043","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

AI-driven computer vision-based automated repair activity identification for seismically damaged RC columns 基于ai驱动计算机视觉的地震损伤RC柱自动修复活动识别

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

Automation in Construction

Pub Date : 2025-02-01 DOI: 10.1016/j.autcon.2024.105959

Samira Azhari, Sara Jamshidian, Mohammadjavad Hamidia

Manual visual inspection is the conventional method for post-earthquake damage assessment, which is unsafe, subjective, and prone to human error. This paper presents an automated rapid and non-contact seismic damage state prediction methodology for reinforced concrete columns using crack image analysis. For surface damage quantification, three features of crack texture complexity including percolation, heterogeneity, and Renyi entropy-based dimensions are measured. Various shallow- and deep-learning-rooted algorithms are trained using a large collected experimental database to develop FEMA P-58-compliant repair activity predictive models. Based on the structural parameters, geometric features, and image-extracted indices, 10 groups of input features are defined. For the overfitting assessment and generalizability evaluation of models, five-fold cross-validations are conducted. Among shallow learning-based algorithms, CatBoost algorithm performs best for the scenarios that rely on vision-derived intricacy indices. Using the deep learning-based multilayer perceptron model as a feedforward artificial neural network, 92 % accuracy is achieved for the testing dataset.

人工目视检查是传统的震后震害评估方法，具有不安全、主观、易出现人为误差等特点。提出了一种基于裂缝图像分析的钢筋混凝土柱地震损伤状态自动快速非接触预测方法。为了量化表面损伤，测量了裂纹织构复杂性的三个特征，包括渗透性、非均质性和基于Renyi熵的维度。使用收集的大型实验数据库训练各种浅层和深度学习算法，以开发符合FEMA p- 58的修复活动预测模型。基于结构参数、几何特征和图像提取指标，定义了10组输入特征。对于模型的过拟合评价和泛化性评价，进行了五重交叉验证。在基于浅学习的算法中，CatBoost算法在依赖于视觉衍生的复杂性指标的场景中表现最好。使用基于深度学习的多层感知器模型作为前馈人工神经网络，测试数据集的准确率达到92%。

{"title":"AI-driven computer vision-based automated repair activity identification for seismically damaged RC columns","authors":"Samira Azhari, Sara Jamshidian, Mohammadjavad Hamidia","doi":"10.1016/j.autcon.2024.105959","DOIUrl":"10.1016/j.autcon.2024.105959","url":null,"abstract":"<div><div>Manual visual inspection is the conventional method for post-earthquake damage assessment, which is unsafe, subjective, and prone to human error. This paper presents an automated rapid and non-contact seismic damage state prediction methodology for reinforced concrete columns using crack image analysis. For surface damage quantification, three features of crack texture complexity including percolation, heterogeneity, and Renyi entropy-based dimensions are measured. Various shallow- and deep-learning-rooted algorithms are trained using a large collected experimental database to develop FEMA P-58-compliant repair activity predictive models. Based on the structural parameters, geometric features, and image-extracted indices, 10 groups of input features are defined. For the overfitting assessment and generalizability evaluation of models, five-fold cross-validations are conducted. Among shallow learning-based algorithms, CatBoost algorithm performs best for the scenarios that rely on vision-derived intricacy indices. Using the deep learning-based multilayer perceptron model as a feedforward artificial neural network, 92 % accuracy is achieved for the testing dataset.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"170 ","pages":"Article 105959"},"PeriodicalIF":9.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142939667","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

Loss function inversion for improved crack segmentation in steel bridges using a CNN framework

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

Automation in Construction

Pub Date : 2025-02-01 DOI: 10.1016/j.autcon.2024.105896

Andrii Kompanets , Remco Duits , Gautam Pai , Davide Leonetti , H.H. (Bert) Snijder

Automating bridge visual inspection using deep learning algorithms for crack detection in images is a prominent way to make these inspections more effective. This paper addresses several challenges associated with crack detection: (1) data imbalance, caused by a small crack area as compared to the background, and (2) a high false positive rate, due to a large amount of crack-like features in the background. First, a new benchmark dataset is presented, containing images of cracks in steel bridges along with pixel-wise annotations. Secondly, the importance of incorporating background patches is examined to assess their impact on network performance when applied to high resolution images of cracks in steel bridges. Finally, a loss function is introduced that enables the use of a relatively large number of background patches in neural network training. The proposed approaches yield a significant reduction in false positive rates, thereby improving the overall performance of crack segmentation.

引用次数: 0

Ensemble learning framework for forecasting construction costs 预测建筑成本的集成学习框架

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

Automation in Construction

Pub Date : 2025-02-01 DOI: 10.1016/j.autcon.2024.105903

Omar Habib , Mona Abouhamad , AbdElMoniem Bayoumi

Construction cost forecasting is vital for tendering processes, enabling the evaluation of bidding offers to maximize revenues and avoid losses. In recent years, the automation of this forecasting process has gained attention due to the limitations of traditional approaches that rely on human experts, which can lead to subjective judgments. This paper introduces an ensemble learning decision-support framework that combines regression random forests and gradient-boosting regression trees through regression voting to automate cost estimation for residential and commercial projects. Evaluation of this approach using the dataset from San Francisco’s building inspection department in the United States demonstrated significant performance improvements over support vector regression. This paper highlights the importance of automating construction cost forecasting with artificial intelligence techniques for construction companies and is expected to encourage companies and building inspection departments worldwide to publish more datasets for the application of advanced deep learning models.

建筑成本预测对于投标过程至关重要，它可以评估投标报价，从而最大限度地提高收益并避免损失。近年来，由于传统方法依赖于人类专家，会导致主观判断，因此这种预测过程的自动化受到了关注。本文介绍了一种集合学习决策支持框架，该框架通过回归投票将回归随机森林和梯度提升回归树结合起来，实现了住宅和商业项目成本估算的自动化。利用美国旧金山建筑检查部门的数据集对该方法进行的评估表明，与支持向量回归相比，该方法的性能有了显著提高。本文强调了利用人工智能技术实现建筑成本预测自动化对建筑公司的重要性，并有望鼓励世界各地的公司和建筑检测部门发布更多数据集，以应用先进的深度学习模型。

引用次数: 0

Structural performance evaluation via digital-physical twin and multi-parameter identification 基于数字物理孪生和多参数识别的结构性能评价

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

Automation in Construction

Pub Date : 2025-02-01 DOI: 10.1016/j.autcon.2024.105907

Yixuan Chen , Sicong Xie , Jian Zhang

The performance of existing structures is often compromised by damage and condition changes, challenging current evaluation methods in accurately assessing their service status. This paper introduces a structural performance evaluation method via digital-physical twin and multi-parameter identification. Key features include: (1) a digital twin framework that integrates non-contact sensing data with finite element models. (2) a technique for local stiffness reduction using intelligent crack inspection data, where deep learning extracts crack information and a mechanical model calculates stiffness reduction coefficients. (3) a multi-parameter identification approach combining non-contact monitoring data with twin substructure models, employing substructure interaction technology and an enhanced unscented Kalman filter algorithm to identify critical parameters like support stiffness. The method's feasibility is demonstrated through a case study involving a frame structure, offering a new paradigm for the safety assessment of existing structures.

现有结构的性能经常受到损伤和状态变化的影响，这对现有的评估方法在准确评估其使用状态方面提出了挑战。介绍了一种基于数字物理孪生和多参数识别的结构性能评价方法。主要特征包括：(1)将非接触式传感数据与有限元模型集成在一起的数字孪生框架。(2)基于智能裂纹检测数据的局部刚度折减技术，其中深度学习提取裂纹信息，力学模型计算刚度折减系数。(3)将非接触监测数据与双子结构模型相结合，采用子结构相互作用技术和增强的无气味卡尔曼滤波算法识别支护刚度等关键参数的多参数识别方法。通过对某框架结构的实例分析，验证了该方法的可行性，为既有结构的安全评估提供了一种新的范式。

引用次数: 0

From surveys to simulations: Integrating Notre-Dame de Paris' buttressing system diagnosis with knowledge graphs 从调查到模拟：整合巴黎圣母院的支撑系统诊断与知识图谱

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

Automation in Construction

Pub Date : 2025-02-01 DOI: 10.1016/j.autcon.2024.105927

Antoine Gros , Livio De Luca , Frédéric Dubois , Philippe Véron , Kévin Jacquot

The assessment of structural safety and a thorough understanding of buildings' structural behavior are critical to enhancing the resilience of the built environment. Cultural Heritage (CH) buildings present unique diagnosis challenges due to their diverse designs and construction techniques, often requiring attention during maintenance or disaster relief efforts. However, collaboration across CH and Architecture, Engineering, and Construction (AEC) fields is hindered by increasing information complexity and prolonged feedback loops. This paper introduces a methodological approach utilizing Knowledge Graph technologies to integrate structural diagnosis information and processes. The approach is applied to the diagnosis of the Notre-Dame de Paris buttressing system, demonstrated through a proof-of-concept knowledge system. By leveraging Knowledge Graph functionalities, insights are derived from the spatialization and provenance of mechanical phenomena, including observed or simulation-predicted cracks in mortar-bound masonry.

结构安全评估和对建筑物结构行为的透彻理解对于增强建筑环境的弹性至关重要。文化遗产（CH）建筑由于其多样化的设计和建造技术而面临着独特的诊断挑战，在维护或救灾工作中往往需要关注。然而，CH和建筑、工程和施工（AEC）领域的合作受到信息复杂性增加和反馈循环延长的阻碍。本文介绍了一种利用知识图谱技术集成结构诊断信息和过程的方法。该方法被应用于巴黎圣母院支撑系统的诊断，并通过概念验证知识系统进行了演示。通过利用知识图谱功能，可以从机械现象的空间化和起源中获得见解，包括在砂浆砌体中观察到的或模拟预测的裂缝。

{"title":"From surveys to simulations: Integrating Notre-Dame de Paris' buttressing system diagnosis with knowledge graphs","authors":"Antoine Gros , Livio De Luca , Frédéric Dubois , Philippe Véron , Kévin Jacquot","doi":"10.1016/j.autcon.2024.105927","DOIUrl":"10.1016/j.autcon.2024.105927","url":null,"abstract":"<div><div>The assessment of structural safety and a thorough understanding of buildings' structural behavior are critical to enhancing the resilience of the built environment. Cultural Heritage (CH) buildings present unique diagnosis challenges due to their diverse designs and construction techniques, often requiring attention during maintenance or disaster relief efforts. However, collaboration across CH and Architecture, Engineering, and Construction (AEC) fields is hindered by increasing information complexity and prolonged feedback loops. This paper introduces a methodological approach utilizing Knowledge Graph technologies to integrate structural diagnosis information and processes. The approach is applied to the diagnosis of the Notre-Dame de Paris buttressing system, demonstrated through a proof-of-concept knowledge system. By leveraging Knowledge Graph functionalities, insights are derived from the spatialization and provenance of mechanical phenomena, including observed or simulation-predicted cracks in mortar-bound masonry.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"170 ","pages":"Article 105927"},"PeriodicalIF":9.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142816508","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

Entropy-centric framework for understanding and managing project dynamics in construction 以熵为中心的框架，用于理解和管理建设中的项目动态

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

Automation in Construction

Pub Date : 2025-02-01 DOI: 10.1016/j.autcon.2024.105928

Elyar Pourrahimian , Diana Salhab , Farook Hamzeh , Simaan AbouRizk

Traditional construction management methodologies often fail to address unforeseen challenges and uncertainties. This paper highlights that projects can exist in different states, often unidentified by project managers. These varying states necessitate different approaches, indicating that one-size-fits-all methods are insufficient. Using project data, entropy calculations, and simulations within a Design Science Research methodology, this paper offers indicators for evaluating project states and improving decision-making. The application of ChaosCompass to eight real-world projects showed higher entropy in projects exceeding budgets and schedules, indicating greater disorder and unpredictability. Conversely, projects on budget and schedule displayed more controlled progress. The findings reveal a significant correlation between high entropy and low forecast accuracy, underscoring entropy's critical role in project dynamics. This paper advocates an entropy-based approach to construction management, promising a more resilient and adaptable framework to address modern project complexities.

传统的施工管理方法往往不能解决不可预见的挑战和不确定性。本文强调了项目可以存在于不同的状态中，而这些状态通常不被项目经理所识别。这些不同的状态需要不同的方法，这表明一刀切的方法是不够的。利用设计科学研究方法中的项目数据、熵计算和模拟，本文提供了评估项目状态和改进决策的指标。ChaosCompass对八个现实世界项目的应用表明，在超出预算和进度的项目中，熵值更高，表明更大的无序性和不可预测性。相反，在预算和时间表上的项目显示出更多的控制进度。研究结果揭示了高熵与低预测精度之间的显著相关性，强调了熵在项目动态中的关键作用。本文提倡一种基于熵的施工管理方法，承诺一个更有弹性和适应性的框架来解决现代项目的复杂性。

{"title":"Entropy-centric framework for understanding and managing project dynamics in construction","authors":"Elyar Pourrahimian , Diana Salhab , Farook Hamzeh , Simaan AbouRizk","doi":"10.1016/j.autcon.2024.105928","DOIUrl":"10.1016/j.autcon.2024.105928","url":null,"abstract":"<div><div>Traditional construction management methodologies often fail to address unforeseen challenges and uncertainties. This paper highlights that projects can exist in different states, often unidentified by project managers. These varying states necessitate different approaches, indicating that one-size-fits-all methods are insufficient. Using project data, entropy calculations, and simulations within a Design Science Research methodology, this paper offers indicators for evaluating project states and improving decision-making. The application of ChaosCompass to eight real-world projects showed higher entropy in projects exceeding budgets and schedules, indicating greater disorder and unpredictability. Conversely, projects on budget and schedule displayed more controlled progress. The findings reveal a significant correlation between high entropy and low forecast accuracy, underscoring entropy's critical role in project dynamics. This paper advocates an entropy-based approach to construction management, promising a more resilient and adaptable framework to address modern project complexities.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"170 ","pages":"Article 105928"},"PeriodicalIF":9.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142816515","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

Intelligent enhancement and identification of pipeline hyperbolic signal in 3D ground penetrating radar data 三维探地雷达数据中管道双曲线信号的智能增强与识别

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

Automation in Construction

Pub Date : 2025-02-01 DOI: 10.1016/j.autcon.2024.105902

Yonggang Shen , Guoxuan Ye , Tuqiao Zhang , Tingchao Yu , Yiping Zhang , Zhenwei Yu

Concealed pipeline maintenance in aging residential areas faces a key challenge of discrepancies between existing data and reality. Ground-penetrating radar with dense, high-speed 3D monitoring capabilities can provide massive data, but effective analysis is difficult due to the presence of irrelevant information. To accurately extract target information, this paper first proposes a 3D data array block concept, which enhances the feature relevance of target data blocks while expanding the data volume. An energy density window method is also proposed to enhance horizontal cross-sectional pipeline signals. Furthermore, a model named PR3DCNN for pipeline recognition is developed based on 3D convolutional neural networks and residual modules. Experimental results demonstrate that PR3DCNN has a classification accuracy of 0.871 for pipelines. After strengthening with 3D data array blocks and the energy density window, the PR-EDW-B model achieves an accuracy of 0.900, and can also classify the pipeline material and calculate its orientation.

老化小区隐蔽管道维修面临着数据与现实不一致的关键挑战。具有密集、高速3D监测能力的探地雷达可以提供大量数据，但由于存在无关信息，难以进行有效分析。为了准确提取目标信息，本文首先提出了三维数据阵列块的概念，在扩大数据量的同时增强了目标数据块的特征相关性。提出了一种能量密度窗法来增强水平截面管道信号。在此基础上，建立了基于三维卷积神经网络和残差模块的管道识别模型PR3DCNN。实验结果表明，PR3DCNN对管道的分类准确率为0.871。PR-EDW-B模型经过三维数据阵列块和能量密度窗口增强后，精度达到0.900，还可以对管道材料进行分类并计算其方向。

{"title":"Intelligent enhancement and identification of pipeline hyperbolic signal in 3D ground penetrating radar data","authors":"Yonggang Shen , Guoxuan Ye , Tuqiao Zhang , Tingchao Yu , Yiping Zhang , Zhenwei Yu","doi":"10.1016/j.autcon.2024.105902","DOIUrl":"10.1016/j.autcon.2024.105902","url":null,"abstract":"<div><div>Concealed pipeline maintenance in aging residential areas faces a key challenge of discrepancies between existing data and reality. Ground-penetrating radar with dense, high-speed 3D monitoring capabilities can provide massive data, but effective analysis is difficult due to the presence of irrelevant information. To accurately extract target information, this paper first proposes a 3D data array block concept, which enhances the feature relevance of target data blocks while expanding the data volume. An energy density window method is also proposed to enhance horizontal cross-sectional pipeline signals. Furthermore, a model named PR3DCNN for pipeline recognition is developed based on 3D convolutional neural networks and residual modules. Experimental results demonstrate that PR3DCNN has a classification accuracy of 0.871 for pipelines. After strengthening with 3D data array blocks and the energy density window, the PR-EDW-B model achieves an accuracy of 0.900, and can also classify the pipeline material and calculate its orientation.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"170 ","pages":"Article 105902"},"PeriodicalIF":9.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142816517","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

Automatic crack defect detection via multiscale feature aggregation and adaptive fusion 基于多尺度特征聚合和自适应融合的裂纹缺陷自动检测

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

Automation in Construction

Pub Date : 2025-02-01 DOI: 10.1016/j.autcon.2024.105934

Hanyun Huang , Mingyang Ma , Suli Bai, Lei Yang, Yanhong Liu

In this paper, a multi-scale feature aggregation and adaptive fusion network, is proposed for automatic and accurate pavement crack defect segmentation. Specifically, faced with the linear characteristic of pavement crack defects, a multiple-dimension attention (MDA) module is proposed to effectively capture long-range correlation from three directions, including space, width and height, and help identify the pavement crack defect boundaries. On this basis, a multi-scale skip connection (MSK) module is proposed, which can effectively utilize the feature information from multiple receptive fields to support accurate feature reconstruction in the decoding stage. Furthermore, a multi-scale attention fusion (MSAF) module is proposed to realize effective multi-scale feature representation and aggregation. Finally, an adaptive weight fusion (AWL) module is proposed to dynamically fuse the output features across different network layers for accurate multi-scale crack defect segmentation. Experiments indicate that proposed network is superior to other mainstream segmentation networks on pixelwise crack defect detection task.

本文提出了一种多尺度特征聚合自适应融合网络，用于路面裂缝缺陷自动准确分割。具体而言，针对路面裂缝缺陷的线性特征，提出了多维关注（MDA）模块，从空间、宽度和高度三个方向有效捕获路面裂缝缺陷的远程相关性，帮助识别路面裂缝缺陷边界。在此基础上，提出了一种多尺度跳跃连接（MSK）模块，该模块可以有效地利用来自多个接收场的特征信息，支持解码阶段准确的特征重建。在此基础上，提出了多尺度注意力融合（MSAF）模块，实现了有效的多尺度特征表示和聚合。最后，提出一种自适应权值融合（AWL）模块，动态融合不同网络层的输出特征，实现多尺度裂纹缺陷的精确分割。实验表明，该网络在像素裂纹缺陷检测任务上优于其他主流分割网络。

{"title":"Automatic crack defect detection via multiscale feature aggregation and adaptive fusion","authors":"Hanyun Huang , Mingyang Ma , Suli Bai, Lei Yang, Yanhong Liu","doi":"10.1016/j.autcon.2024.105934","DOIUrl":"10.1016/j.autcon.2024.105934","url":null,"abstract":"<div><div>In this paper, a multi-scale feature aggregation and adaptive fusion network, is proposed for automatic and accurate pavement crack defect segmentation. Specifically, faced with the linear characteristic of pavement crack defects, a multiple-dimension attention (MDA) module is proposed to effectively capture long-range correlation from three directions, including space, width and height, and help identify the pavement crack defect boundaries. On this basis, a multi-scale skip connection (MSK) module is proposed, which can effectively utilize the feature information from multiple receptive fields to support accurate feature reconstruction in the decoding stage. Furthermore, a multi-scale attention fusion (MSAF) module is proposed to realize effective multi-scale feature representation and aggregation. Finally, an adaptive weight fusion (AWL) module is proposed to dynamically fuse the output features across different network layers for accurate multi-scale crack defect segmentation. Experiments indicate that proposed network is superior to other mainstream segmentation networks on pixelwise crack defect detection task.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"170 ","pages":"Article 105934"},"PeriodicalIF":9.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142887890","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

Graph neural networks for classification and error detection in 2D architectural detail drawings 基于图神经网络的二维建筑详图分类与错误检测

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

Automation in Construction

Pub Date : 2025-02-01 DOI: 10.1016/j.autcon.2024.105936

Jaechang Ko , Donghyuk Lee

The assessment and classification of architectural sectional drawings is critical in the architecture, engineering, and construction (AEC) field, where the accurate representation of complex structures and the extraction of meaningful patterns are key challenges. This paper established a framework for standardizing different forms of architectural drawings into a consistent graph format, and evaluated different Graph Neural Networks (GNNs) architectures, pooling methods, node features, and masking techniques. This paper demonstrates that GNNs can be practically applied in the design and review process, particularly for categorizing details and detecting errors in architectural drawings. The potential for visual explanations of model decisions using Explainable AI (XAI) is also explored to enhance the reliability and user understanding of AI models in architecture. This paper highlights the potential of GNNs in architectural data analysis and outlines the challenges and future directions for broader application in the AEC field.

建筑剖面图的评估和分类在建筑、工程和施工（AEC）领域至关重要，其中复杂结构的准确表示和有意义模式的提取是关键挑战。本文建立了将不同形式的建筑图纸标准化为一致的图格式的框架，并评估了不同的图神经网络（gnn）架构、池化方法、节点特征和掩蔽技术。本文证明了gnn可以实际应用于设计和审查过程，特别是在建筑图纸的细节分类和错误检测方面。还探讨了使用可解释AI （XAI）对模型决策进行可视化解释的潜力，以提高架构中AI模型的可靠性和用户理解。本文强调了gnn在建筑数据分析中的潜力，并概述了在AEC领域更广泛应用的挑战和未来方向。

引用次数: 0

首页上一页

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.

﹀