Automation in Construction最新文献_第5页

Self-supervised learning for multi-label sewer defect classification 多标签下水道缺陷分类的自监督学习

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2026-01-02 DOI: 10.1016/j.autcon.2025.106751

Tugba Yildizli , Tianlong Jia , Jeroen Langeveld , Riccardo Taormina

Automated sewer defect detection has advanced through deep learning, particularly supervised methods using CCTV images, but based on large annotated datasets. This paper proposes a semi-supervised learning (SSL) approach to reduce labeling demands. The method comprises self-supervised pre-training on unlabeled images using SwAV (Swapping Assignments between multiple Views) followed by fine-tuning for multi-label classification. Experiments on the Sewer-ML dataset demonstrate that the SSL approach, trained on only 35k labeled images, achieves an F1-score of 69.11%, and F2_CIW of 54.22%, surpassing the fully supervised baseline trained from scratch on 1.04 million images. Increasing the unlabeled pre-training data further enhances performance, while ImageNet initialization consistently outperforms training from scratch. Self-supervised learning also helps mitigate the effects of mislabeled data, which is observed to be present even in the Sewer-ML ground truth. Overall, self-supervised learning provides an accurate, scalable, and cost-effective alternative to fully supervised approaches, particularly in data-scarce or imperfectly labeled scenarios.

自动化下水道缺陷检测通过深度学习取得了进展，特别是使用闭路电视图像的监督方法，但基于大型注释数据集。本文提出了一种半监督学习（SSL）方法来减少标注需求。该方法包括使用SwAV（在多个视图之间交换分配）对未标记图像进行自监督预训练，然后对多标签分类进行微调。在seur - ml数据集上的实验表明，SSL方法仅在35k标记图像上进行训练，f1得分为69.11%，F2CIW为54.22%，超过了在104万张图像上从头开始训练的完全监督基线。增加未标记的预训练数据进一步提高性能，而ImageNet初始化始终优于从头开始训练。自我监督学习还有助于减轻错误标记数据的影响，即使在下水道- ml的基础事实中也观察到这种情况。总的来说，自监督学习提供了一种准确的、可扩展的、具有成本效益的替代完全监督方法，特别是在数据稀缺或不完美标记的场景中。

{"title":"Self-supervised learning for multi-label sewer defect classification","authors":"Tugba Yildizli , Tianlong Jia , Jeroen Langeveld , Riccardo Taormina","doi":"10.1016/j.autcon.2025.106751","DOIUrl":"10.1016/j.autcon.2025.106751","url":null,"abstract":"<div><div>Automated sewer defect detection has advanced through deep learning, particularly supervised methods using CCTV images, but based on large annotated datasets. This paper proposes a semi-supervised learning (SSL) approach to reduce labeling demands. The method comprises self-supervised pre-training on unlabeled images using SwAV (Swapping Assignments between multiple Views) followed by fine-tuning for multi-label classification. Experiments on the Sewer-ML dataset demonstrate that the SSL approach, trained on only 35k labeled images, achieves an F1-score of 69.11%, and F2<sub>CIW</sub> of 54.22%, surpassing the fully supervised baseline trained from scratch on 1.04 million images. Increasing the unlabeled pre-training data further enhances performance, while ImageNet initialization consistently outperforms training from scratch. Self-supervised learning also helps mitigate the effects of mislabeled data, which is observed to be present even in the Sewer-ML ground truth. Overall, self-supervised learning provides an accurate, scalable, and cost-effective alternative to fully supervised approaches, particularly in data-scarce or imperfectly labeled scenarios.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106751"},"PeriodicalIF":11.5,"publicationDate":"2026-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145880902","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

Collaborative learning architecture for autonomous excavator planning and execution 自主挖掘机规划与执行的协同学习体系结构

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-12-30 DOI: 10.1016/j.autcon.2025.106742

Junhyung Cho , Mingyu Shin , Joongheon Kim , Soyi Jung

Autonomous excavation systems face fundamental challenges balancing computational tractability with operational sophistication. This paper presents the collaborative learning for excavation framework (CLEF), resolving this trade-off through strategic decomposition: separating high-level planning from low-level execution while maintaining collaborative optimization. The framework’s key contributions include a bidirectional information flow between specialized modules consisting of reinforcement learning for strategic planning using polar coordinates, and attention-enhanced generative adversarial imitation learning (A-GAIL) with multi-head attention capturing phase-specific temporal dependencies. Unlike monolithic approaches suffering computational intractability, CLEF enables module specialization while coordinating through shared representations. Planning decisions condition trajectory generation while execution outcomes update environmental models, creating adaptive behavior without manual tuning. Validation demonstrates 90.8% success rate compared to 71.1% for monolithic approaches, with trajectory generation achieving 91.3% completion confirming superior performance essential for construction automation.

自主挖掘系统面临着平衡计算可追溯性和操作复杂性的根本挑战。本文提出了挖掘框架的协作学习（CLEF），通过战略分解解决了这种权衡：在保持协作优化的同时，将高级规划与低级执行分离开来。该框架的主要贡献包括专门模块之间的双向信息流，包括使用极坐标进行战略规划的强化学习，以及具有多头注意力捕获特定阶段时间依赖性的注意力增强生成对抗模仿学习（a - gail）。与遭受计算困难的整体方法不同，CLEF在通过共享表示进行协调时支持模块专门化。规划决策条件轨迹生成，而执行结果更新环境模型，无需手动调优即可创建自适应行为。验证的成功率为90.8%，而单片方法的成功率为71.1%，轨迹生成的完成率为91.3%，这证实了施工自动化所必需的卓越性能。

{"title":"Collaborative learning architecture for autonomous excavator planning and execution","authors":"Junhyung Cho , Mingyu Shin , Joongheon Kim , Soyi Jung","doi":"10.1016/j.autcon.2025.106742","DOIUrl":"10.1016/j.autcon.2025.106742","url":null,"abstract":"<div><div>Autonomous excavation systems face fundamental challenges balancing computational tractability with operational sophistication. This paper presents the collaborative learning for excavation framework (CLEF), resolving this trade-off through strategic decomposition: separating high-level planning from low-level execution while maintaining collaborative optimization. The framework’s key contributions include a bidirectional information flow between specialized modules consisting of reinforcement learning for strategic planning using polar coordinates, and attention-enhanced generative adversarial imitation learning (A-GAIL) with multi-head attention capturing phase-specific temporal dependencies. Unlike monolithic approaches suffering computational intractability, CLEF enables module specialization while coordinating through shared representations. Planning decisions condition trajectory generation while execution outcomes update environmental models, creating adaptive behavior without manual tuning. Validation demonstrates 90.8% success rate compared to 71.1% for monolithic approaches, with trajectory generation achieving 91.3% completion confirming superior performance essential for construction automation.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106742"},"PeriodicalIF":11.5,"publicationDate":"2025-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145880900","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

Unified data synthesis for automated 3D Visual Inspection and digital twinning of bridges 统一数据合成，实现桥梁自动三维视觉检测和数字孪生

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-12-29 DOI: 10.1016/j.autcon.2025.106741

Wang Wang , Mingjing Xu , Zhen Cao , Jingzi Guo , Chong Liu , Haowei Zhang , Xiaoling Zhang

The automation of 3D bridge inspection is critically limited by scarce annotated data and a fundamental lack of understanding regarding which intrinsic point cloud features drive Sim-to-Real (S2R) success. The paper proposes a unified procedural synthesis framework to overcome this data bottleneck. The core contributions are twofold: (1) Dual-output generation, which yields segmented ground truth and the first bridge component-level point cloud completion dataset via physical simulation. (2) Systematic feature ablation, establishing a definitive S2R importance hierarchy: Surface Normals

≫

Geometry

>

RGB. This finding offers critical guidance for efficient sensor deployment and data synthesis. A model trained exclusively on synthetic data achieved a satisfactory 84.2% mIoU on a real-world benchmark, validating direct S2R transfer and proving synthetic data can substitute manual annotation. The validated methodology provides the foundation to seamlessly integrate procedural damage models, extending automation from component identification to defect detection for analysis-ready digital twins.

3D桥梁检测的自动化受到缺乏注释数据和根本缺乏对内在点云特征驱动模拟到真实（S2R）成功的理解的严重限制。本文提出了一个统一的程序综合框架来克服这一数据瓶颈。核心贡献有两个方面：(1)双输出生成，通过物理模拟产生分段的地面真值和第一个桥梁组件级点云补全数据集。(2)系统的特征消融，建立了明确的S2R重要性层次：表面法线（Surface法线）>几何（Geometry） & RGB。这一发现为有效的传感器部署和数据合成提供了关键指导。在真实基准测试中，仅使用合成数据训练的模型获得了令人满意的84.2% mIoU，验证了直接S2R传输，并证明合成数据可以替代人工注释。经过验证的方法为无缝集成程序损坏模型提供了基础，将自动化从组件识别扩展到可用于分析的数字孪生的缺陷检测。

{"title":"Unified data synthesis for automated 3D Visual Inspection and digital twinning of bridges","authors":"Wang Wang , Mingjing Xu , Zhen Cao , Jingzi Guo , Chong Liu , Haowei Zhang , Xiaoling Zhang","doi":"10.1016/j.autcon.2025.106741","DOIUrl":"10.1016/j.autcon.2025.106741","url":null,"abstract":"<div><div>The automation of 3D bridge inspection is critically limited by scarce annotated data and a fundamental lack of understanding regarding which intrinsic point cloud features drive Sim-to-Real (S2R) success. The paper proposes a unified procedural synthesis framework to overcome this data bottleneck. The core contributions are twofold: (1) Dual-output generation, which yields segmented ground truth and the first bridge component-level point cloud completion dataset via physical simulation. (2) Systematic feature ablation, establishing a definitive S2R importance hierarchy: Surface Normals <span><math><mo>≫</mo></math></span> Geometry <span><math><mo>></mo></math></span> RGB. This finding offers critical guidance for efficient sensor deployment and data synthesis. A model trained exclusively on synthetic data achieved a satisfactory 84.2% mIoU on a real-world benchmark, validating direct S2R transfer and proving synthetic data can substitute manual annotation. The validated methodology provides the foundation to seamlessly integrate procedural damage models, extending automation from component identification to defect detection for analysis-ready digital twins.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106741"},"PeriodicalIF":11.5,"publicationDate":"2025-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145880899","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

Real-time stereo reconstruction and geometric quantification of pavement distress with a variable-baseline platform 基于变基线平台的路面损伤实时立体重建与几何量化

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-12-27 DOI: 10.1016/j.autcon.2025.106743

Guang-Zhu Zhang, Qingliang Xu, Hong-Feng Li, Chun-Peng Han, Qiushi Li

Accurate maintenance planning requires not only detecting pavement distress but also reconstructing its 3D geometry and reporting metrics. This paper develops Iterative Geometry Encoding Volume-Lite (IGEV-Lite), a compact derivative of IGEV-Stereo, and couples it with a variable-baseline stereo platform. IGEV-Lite adopts a GhostNetV2 backbone with feature transfer–re-encoding context network and a compact iterative updater, plus deployment accelerations; instance-level region of interest (ROI) cropping focuses computation, and plane-referenced, gridded integration yields maximum depth and integrated volume. Under a unified protocol, accuracy improves from an end-point error (EPE) of 0.608 to 0.584 px (pixels) and a disparity outlier rate (D1) of 3.24 % to 2.97 %, while latency drops from 135 ms to 97 ms. Quantification tests conducted at a perpendicular angle to the ground achieve 2.7 % depth and 0.9 % volume error at B = 240 mm. Combining a lightweight stereo backbone with plane-referenced integration provides deployment-ready, geometry-faithful quantification of distress.

准确的维护计划不仅需要检测路面破损情况，还需要重建其三维几何形状并报告指标。本文开发了IGEV-Lite (Iterative Geometry Encoding Volume-Lite, IGEV-Lite)，这是IGEV-Stereo的紧凑导数，并将其与可变基线立体平台耦合在一起。IGEV-Lite采用GhostNetV2骨干网，具有特征传输-重新编码上下文网络和紧凑的迭代更新器，以及部署加速；实例级感兴趣区域（ROI）裁剪侧重于计算，平面参考的网格集成产生最大深度和集成体积。在统一协议下，准确率从0.608提高到0.584像素，视差异常率（D1）从3.24%提高到2.97%，延迟从135 ms下降到97 ms。在与地面垂直的角度下进行的量化试验，在B = 240 mm处深度误差为2.7%，体积误差为0.9%。将轻型立体主干与平面参考集成相结合，可提供部署就绪、几何可靠的遇险量化。

{"title":"Real-time stereo reconstruction and geometric quantification of pavement distress with a variable-baseline platform","authors":"Guang-Zhu Zhang, Qingliang Xu, Hong-Feng Li, Chun-Peng Han, Qiushi Li","doi":"10.1016/j.autcon.2025.106743","DOIUrl":"10.1016/j.autcon.2025.106743","url":null,"abstract":"<div><div>Accurate maintenance planning requires not only detecting pavement distress but also reconstructing its 3D geometry and reporting metrics. This paper develops Iterative Geometry Encoding Volume-Lite (IGEV-Lite), a compact derivative of IGEV-Stereo, and couples it with a variable-baseline stereo platform. IGEV-Lite adopts a GhostNetV2 backbone with feature transfer–re-encoding context network and a compact iterative updater, plus deployment accelerations; instance-level region of interest (ROI) cropping focuses computation, and plane-referenced, gridded integration yields maximum depth and integrated volume. Under a unified protocol, accuracy improves from an end-point error (EPE) of 0.608 to 0.584 px (pixels) and a disparity outlier rate (D1) of 3.24 % to 2.97 %, while latency drops from 135 ms to 97 ms. Quantification tests conducted at a perpendicular angle to the ground achieve 2.7 % depth and 0.9 % volume error at B = 240 mm. Combining a lightweight stereo backbone with plane-referenced integration provides deployment-ready, geometry-faithful quantification of distress.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106743"},"PeriodicalIF":11.5,"publicationDate":"2025-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145844991","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

Implicit neural representations for surrogate modeling in the built environment 建筑环境中代理建模的隐式神经表征

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-12-27 DOI: 10.1016/j.autcon.2025.106744

Sarah Mokhtar, Caitlin Mueller

Physical phenomena, including aerodynamics and heat transfer, exhibit complex shape-dependent relationships with building geometry, shaping microclimates that directly affect urban livability and comfort. In design and engineering practice, surrogate models reduce the computational burden of simulations, providing faster and more iterative performance feedback within design workflows. This paper introduces Per-FORM, a framework that leverages implicit neural representations (INRs) for predictive modeling in the built environment. The approach accommodates variations in geometric complexity, scale, and topology while representing continuous physical fields through decoupled modules encoding both geometry and building influence. Its ability to infer full-field and near-surface predictions is evaluated across multiple metrics, demonstrating state-of-the-art accuracy for complex geometries. Beyond predictive accuracy, Per-FORM brings simulation-in-the-loop feedback into digital workflows, supporting performance-informed exploration, ideation, and conceptualization, and enriching informed creative processes in design and engineering practice.

物理现象，包括空气动力学和热传递，与建筑几何形状表现出复杂的形状依赖关系，形成直接影响城市宜居性和舒适度的小气候。在设计和工程实践中，代理模型减少了模拟的计算负担，在设计工作流中提供更快、更迭代的性能反馈。本文介绍了Per-FORM，这是一个利用隐式神经表征（INRs）在建筑环境中进行预测建模的框架。该方法适应几何复杂性、规模和拓扑结构的变化，同时通过编码几何和建筑影响的解耦模块表示连续的物理场。通过多种指标评估其推断全场和近地表预测的能力，展示了复杂几何形状的最先进精度。除了预测准确性之外，Per-FORM还将循环仿真反馈带入数字工作流程，支持性能知情的探索、构思和概念化，并丰富设计和工程实践中的知情创意过程。

{"title":"Implicit neural representations for surrogate modeling in the built environment","authors":"Sarah Mokhtar, Caitlin Mueller","doi":"10.1016/j.autcon.2025.106744","DOIUrl":"10.1016/j.autcon.2025.106744","url":null,"abstract":"<div><div>Physical phenomena, including aerodynamics and heat transfer, exhibit complex shape-dependent relationships with building geometry, shaping microclimates that directly affect urban livability and comfort. In design and engineering practice, surrogate models reduce the computational burden of simulations, providing faster and more iterative performance feedback within design workflows. This paper introduces Per-FORM, a framework that leverages implicit neural representations (INRs) for predictive modeling in the built environment. The approach accommodates variations in geometric complexity, scale, and topology while representing continuous physical fields through decoupled modules encoding both geometry and building influence. Its ability to infer full-field and near-surface predictions is evaluated across multiple metrics, demonstrating state-of-the-art accuracy for complex geometries. Beyond predictive accuracy, Per-FORM brings simulation-in-the-loop feedback into digital workflows, supporting performance-informed exploration, ideation, and conceptualization, and enriching informed creative processes in design and engineering practice.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106744"},"PeriodicalIF":11.5,"publicationDate":"2025-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837256","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

Intelligent UAV-based deep learning system for multi-class concrete dam damage detection 基于无人机的多等级混凝土坝损伤检测深度学习系统

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-12-26 DOI: 10.1016/j.autcon.2025.106730

Ben Huang , Fei Kang , Xi Liu

Accurate damage detection is critical for ensuring the safety and long-term stability of dams. However, conventional inspection methods often suffer from low automation, high labor intensity, and high costs. To address these limitations, this paper proposes an intelligent detection system based on an enhanced YOLOX framework, designed for real-time identification of multiple damage types in concrete dams using unmanned aerial vehicles (UAVs). The improved model is lightweight, containing only 8.94 million parameters, yet achieves a mAP₅₀ of 0.821 and an F₁-score of 0.781. Based on this model, detection software was implemented with the PyQt5 framework, and an integrated UAV-based system was constructed to support high-precision, real-time analysis of both image and video data. This approach provides an automated and intelligent solution for the visual inspection of concrete dam damage, offering significant potential for practical engineering applications and future intelligent monitoring systems.

准确的损伤检测是保证大坝安全和长期稳定的关键。然而，传统的检测方法往往存在自动化程度低、劳动强度大、成本高等问题。为了解决这些限制，本文提出了一种基于增强型YOLOX框架的智能检测系统，用于使用无人机实时识别混凝土大坝中的多种损伤类型。改进后的模型是轻量级的，仅包含894万个参数，但mAP50为0.821，f1得分为0.781。基于该模型，采用PyQt5框架实现了检测软件，构建了基于无人机的集成系统，支持图像和视频数据的高精度、实时分析。该方法为混凝土大坝损伤目视检测提供了一种自动化、智能化的解决方案，为实际工程应用和未来的智能监测系统提供了巨大的潜力。

引用次数: 0

Enhancing LLM-based building data query with chain-of-thought, retrieval-augmented generation, and fine-tuning 使用思维链、检索增强生成和微调增强基于llm的构建数据查询

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-12-26 DOI: 10.1016/j.autcon.2025.106738

Mingchen Li , Ziqi Hu , Parastoo Mohebi , Shuhao Li , Zhe Wang

To enhance energy efficiency and occupant satisfaction, modern buildings have collected rich streams of operational and sensor data. Semantic models for buildings, such as the Brick schema expressed in the Resource Description Framework (RDF) and Web Ontology Language (OWL), have standardized the representation of devices, points, and systems. However, non-expert users still faced barriers to accessing such data, because effective use required proficiency in the SPARQL Protocol and RDF Query Language (SPARQL) and navigation of thousands of interconnected nodes and relations. This paper presents BuildingGPT2, a framework that combined large language model fine-tuning, vector-graph retrieval-augmented generation, and chain-of-thought prompting to enable natural-language querying of Brick-based models. The framework was trained on semantic models from 40 real buildings and evaluated in a zero-shot setting on 5 held-out buildings. Using LLaMA 3.1–70B, SPARQL query generation accuracy improved from 49.25 % to 97.11 %, substantially lowering the barrier to interacting with building semantic models.

为了提高能源效率和居住者满意度，现代建筑收集了丰富的操作和传感器数据流。建筑物的语义模型，例如在资源描述框架（RDF）和Web本体语言（OWL）中表达的Brick模式，已经标准化了设备、点和系统的表示。然而，非专业用户在访问这些数据时仍然面临障碍，因为有效地使用这些数据需要熟练掌握SPARQL协议和RDF查询语言（SPARQL），以及在数千个相互连接的节点和关系中导航。本文介绍了BuildingGPT2，这是一个框架，它结合了大型语言模型微调、向量图检索增强生成和思维链提示，以实现基于砖块的模型的自然语言查询。该框架在40个真实建筑的语义模型上进行了训练，并在5个废弃建筑的零射击设置中进行了评估。使用LLaMA 3.1-70B， SPARQL查询生成准确率从49.25%提高到97.11%，大大降低了与构建语义模型交互的障碍。

{"title":"Enhancing LLM-based building data query with chain-of-thought, retrieval-augmented generation, and fine-tuning","authors":"Mingchen Li , Ziqi Hu , Parastoo Mohebi , Shuhao Li , Zhe Wang","doi":"10.1016/j.autcon.2025.106738","DOIUrl":"10.1016/j.autcon.2025.106738","url":null,"abstract":"<div><div>To enhance energy efficiency and occupant satisfaction, modern buildings have collected rich streams of operational and sensor data. Semantic models for buildings, such as the Brick schema expressed in the Resource Description Framework (RDF) and Web Ontology Language (OWL), have standardized the representation of devices, points, and systems. However, non-expert users still faced barriers to accessing such data, because effective use required proficiency in the SPARQL Protocol and RDF Query Language (SPARQL) and navigation of thousands of interconnected nodes and relations. This paper presents BuildingGPT2, a framework that combined large language model fine-tuning, vector-graph retrieval-augmented generation, and chain-of-thought prompting to enable natural-language querying of Brick-based models. The framework was trained on semantic models from 40 real buildings and evaluated in a zero-shot setting on 5 held-out buildings. Using LLaMA 3.1–70B, SPARQL query generation accuracy improved from 49.25 % to 97.11 %, substantially lowering the barrier to interacting with building semantic models.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106738"},"PeriodicalIF":11.5,"publicationDate":"2025-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837318","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

Intelligent prediction and control of deformation induced by a servo-strutted deep excavation adjacent to existing tunnels 与既有隧道相邻的伺服支撑深基坑变形智能预测与控制

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-12-24 DOI: 10.1016/j.autcon.2025.106735

Mingpeng Liu , Dechun Lu , Franz Tschuchnigg , Fengwen Lai , Xin Zhou , Feng Chen

To enable intelligent prediction and control of excavation-induced deformations, including wall deflection, ground surface settlement, and nearby tunnel displacements, this paper proposes an integrated approach combining in-situ test-based numerical modelling, Bayesian-optimised deep neural networks (BO-DNNs), and a DNN-based Newton-Raphson (DNN-NR) algorithm. The proposed framework serves as a decision-support tool for pre-construction planning of a deep excavation adjacent to existing tunnels. Specifically, the verified numerical models generate the training dataset for the BO-DNN model, which achieves high predictive accuracy for maximum deformations under varying servo-force combinations and excavation geometries. The BO-DNN analysis reveals that servo forces significantly influence deformation patterns and can even alter the direction of wall deflection and ground settlement. Leveraging this surrogate model, the DNN-NR algorithm efficiently identifies optimal servo forces to minimise deformations. The applications demonstrate that the DNN-NR-derived forces effectively restrict deformations within allowable limits. Furthermore, the algorithm quantifies the relative importance of each servo strut in deformation control and provides allowable axial force thresholds, facilitating adaptive force adjustments during the excavation.

为了智能预测和控制开挖引起的变形，包括墙体挠度、地表沉降和隧道附近位移，本文提出了一种综合方法，将基于原位试验的数值模拟、贝叶斯优化深度神经网络（bo - dnn）和基于dnn的牛顿-拉斐尔（DNN-NR）算法相结合。该框架可作为邻近现有隧道的深基坑施工前规划的决策支持工具。具体来说，经过验证的数值模型生成了BO-DNN模型的训练数据集，该模型对不同伺服力组合和开挖几何形状下的最大变形达到了很高的预测精度。BO-DNN分析表明，随动力对变形模式有显著影响，甚至可以改变墙体挠度和地面沉降方向。利用该替代模型，DNN-NR算法有效地识别最佳伺服力以最小化变形。应用表明，dnn - nn推导的力有效地将变形限制在允许的范围内。此外，该算法量化了各伺服支柱在变形控制中的相对重要性，并提供了允许的轴向力阈值，便于开挖过程中的自适应力调整。

{"title":"Intelligent prediction and control of deformation induced by a servo-strutted deep excavation adjacent to existing tunnels","authors":"Mingpeng Liu , Dechun Lu , Franz Tschuchnigg , Fengwen Lai , Xin Zhou , Feng Chen","doi":"10.1016/j.autcon.2025.106735","DOIUrl":"10.1016/j.autcon.2025.106735","url":null,"abstract":"<div><div>To enable intelligent prediction and control of excavation-induced deformations, including wall deflection, ground surface settlement, and nearby tunnel displacements, this paper proposes an integrated approach combining in-situ test-based numerical modelling, Bayesian-optimised deep neural networks (BO-DNNs), and a DNN-based Newton-Raphson (DNN-NR) algorithm. The proposed framework serves as a decision-support tool for pre-construction planning of a deep excavation adjacent to existing tunnels. Specifically, the verified numerical models generate the training dataset for the BO-DNN model, which achieves high predictive accuracy for maximum deformations under varying servo-force combinations and excavation geometries. The BO-DNN analysis reveals that servo forces significantly influence deformation patterns and can even alter the direction of wall deflection and ground settlement. Leveraging this surrogate model, the DNN-NR algorithm efficiently identifies optimal servo forces to minimise deformations. The applications demonstrate that the DNN-NR-derived forces effectively restrict deformations within allowable limits. Furthermore, the algorithm quantifies the relative importance of each servo strut in deformation control and provides allowable axial force thresholds, facilitating adaptive force adjustments during the excavation.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106735"},"PeriodicalIF":11.5,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145823223","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

Vision-language model-based intelligent assistant for onsite construction safety inspection 基于视觉语言模型的施工现场安全检查智能助手

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-12-24 DOI: 10.1016/j.autcon.2025.106728

Rahat Hussain , Doyeop Lee , Muhammad Sibtain Abbas , Syed Farhan Alam Zaidi , Akeem Pedro , Chansik Park

Construction site inspection demands a contextual understanding of dynamic job-site conditions, traditionally relying on inspectors' expertise combined with adherence to predefined safety regulations and industry standards to identify hazards. While vision-language models can detect and describe hazards, they struggle to correlate observations with regulations due to limitations in geometric reasoning. Recent studies show progress in compliance checking, but these models are still challenged by dynamic scenarios. This paper introduces a hybrid framework that combines geometric reasoning with LLM-powered interpretation to improve regulation-aware hazard detection. The system achieved high detection accuracy: 97 % for ladder use, 94.6 % for mobile scaffolding, and 99 % for fire-related work. Captioning performance evaluated through BLEU, ROUGE, METEOR, and BERT Score showed strong semantic alignment. User feedback confirmed its efficiency and ease of use, even under dynamic conditions. By integrating visual data with regulatory reasoning, the proposed system offers a practical, domain-adapted solution for enhancing construction safety inspections.

建筑工地检查需要对动态工作现场条件的上下文理解，传统上依赖检查员的专业知识，并遵守预定义的安全法规和行业标准来识别危险。虽然视觉语言模型可以检测和描述危险，但由于几何推理的限制，它们很难将观察结果与规则联系起来。近年来的研究表明，依从性检查取得了进展，但这些模型仍然受到动态情景的挑战。本文介绍了一种混合框架，将几何推理与llm驱动的解释相结合，以改进法规感知的危害检测。该系统达到了很高的检测精度：对梯子使用的检测准确率为97%，对移动脚手架的检测准确率为94.6%，对火灾相关工作的检测准确率为99%。通过BLEU， ROUGE， METEOR和BERT Score评估字幕性能显示出较强的语义一致性。用户反馈证实了它的效率和易用性，即使在动态条件下也是如此。通过将可视化数据与监管推理相结合，所提出的系统为加强建筑安全检查提供了一个实用的、适合领域的解决方案。

{"title":"Vision-language model-based intelligent assistant for onsite construction safety inspection","authors":"Rahat Hussain , Doyeop Lee , Muhammad Sibtain Abbas , Syed Farhan Alam Zaidi , Akeem Pedro , Chansik Park","doi":"10.1016/j.autcon.2025.106728","DOIUrl":"10.1016/j.autcon.2025.106728","url":null,"abstract":"<div><div>Construction site inspection demands a contextual understanding of dynamic job-site conditions, traditionally relying on inspectors' expertise combined with adherence to predefined safety regulations and industry standards to identify hazards. While vision-language models can detect and describe hazards, they struggle to correlate observations with regulations due to limitations in geometric reasoning. Recent studies show progress in compliance checking, but these models are still challenged by dynamic scenarios. This paper introduces a hybrid framework that combines geometric reasoning with LLM-powered interpretation to improve regulation-aware hazard detection. The system achieved high detection accuracy: 97 % for ladder use, 94.6 % for mobile scaffolding, and 99 % for fire-related work. Captioning performance evaluated through BLEU, ROUGE, METEOR, and BERT Score showed strong semantic alignment. User feedback confirmed its efficiency and ease of use, even under dynamic conditions. By integrating visual data with regulatory reasoning, the proposed system offers a practical, domain-adapted solution for enhancing construction safety inspections.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106728"},"PeriodicalIF":11.5,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145823225","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

Automated crack detection in axially loaded grouted connections of offshore wind turbines using embedded Fibre Bragg Grating sensor data 利用嵌入式光纤光栅传感器数据自动检测海上风力涡轮机轴向加载注浆连接中的裂纹

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2025-12-24 DOI: 10.1016/j.autcon.2025.106734

Jakob Borgelt , Joshua Possekel , Peter Schaumann , Elyas Ghafoori

Grouted connections are critical components in offshore wind turbine foundations subjected to cyclic axial loading. Understanding their fatigue degradation is essential for structural integrity. This paper presents an application of a frequency-based method for automated crack detection and evaluation in grouted connections using embedded Fibre Bragg Grating (FBG) sensors. The method identifies mechanical response reversal, from grout compression to elongation at load peaks, linked to crack initiation, using short-time Fourier transform (STFT) analysis of FBG signals. Validated through fatigue testing, it enables robust, automated, and spatially resolved crack detection throughout the fatigue life. Statistical evaluation revealed typical crack progression from outer regions towards central shear key levels. A correlation was found between crack formation and displacement behaviour, segmented into stable, incremental, and progressive degradation phases. Rapid displacement increases in the progressive phase occurred only after cracks formed across all shear key levels, offering insights for damage detection and monitoring strategies.

注浆连接是海上风力发电机基础中承受轴向循环荷载的关键部件。了解它们的疲劳退化对结构完整性至关重要。本文介绍了一种基于频率的方法，用于嵌入式光纤布拉格光栅（FBG）传感器在注浆连接中的自动裂纹检测和评估。该方法利用FBG信号的短时傅里叶变换（STFT）分析，识别与裂纹萌生有关的机械响应反转，从浆液压缩到荷载峰值时的伸长。通过疲劳测试验证，它可以在整个疲劳寿命期间实现可靠、自动化和空间分辨的裂纹检测。统计评价显示，典型的裂缝由外区向中心剪切关键水平扩展。裂缝形成和位移行为之间存在相关性，可分为稳定、增量和渐进退化阶段。在推进阶段，位移的快速增加只发生在所有剪切关键水平上形成裂缝之后，这为损伤检测和监测策略提供了见解。

{"title":"Automated crack detection in axially loaded grouted connections of offshore wind turbines using embedded Fibre Bragg Grating sensor data","authors":"Jakob Borgelt , Joshua Possekel , Peter Schaumann , Elyas Ghafoori","doi":"10.1016/j.autcon.2025.106734","DOIUrl":"10.1016/j.autcon.2025.106734","url":null,"abstract":"<div><div>Grouted connections are critical components in offshore wind turbine foundations subjected to cyclic axial loading. Understanding their fatigue degradation is essential for structural integrity. This paper presents an application of a frequency-based method for automated crack detection and evaluation in grouted connections using embedded Fibre Bragg Grating (FBG) sensors. The method identifies mechanical response reversal, from grout compression to elongation at load peaks, linked to crack initiation, using short-time Fourier transform (STFT) analysis of FBG signals. Validated through fatigue testing, it enables robust, automated, and spatially resolved crack detection throughout the fatigue life. Statistical evaluation revealed typical crack progression from outer regions towards central shear key levels. A correlation was found between crack formation and displacement behaviour, segmented into stable, incremental, and progressive degradation phases. Rapid displacement increases in the progressive phase occurred only after cracks formed across all shear key levels, offering insights for damage detection and monitoring strategies.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106734"},"PeriodicalIF":11.5,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145823224","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