Automation in Construction最新文献_第5页

Real-time knowledge management for construction value engineering: Live capture and BERT-aided case-based retrieval 建筑价值工程的实时知识管理：实时捕获和bert辅助的基于案例的检索

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

Automation in Construction

Pub Date : 2026-01-17 DOI: 10.1016/j.autcon.2026.106782

Fuhao Zu , Xueqing Zhang

Effective reuse of creative ideas from value engineering (VE) workshops is crucial for cost-effective, innovative design. Conventional methods like post-project reviews and keyword searches often lack context, real-time availability, and semantic relevance, limiting the practical reuse of past insights. This paper addresses the fundamental question of how knowledge generated during VE workshops can be effectively captured and reused to support future idea generations. To solve this, it proposes an integrated methodology combining BIM-based live capture with a hybrid retrieval system. This system uses structured attributes and Bidirectional Encoder Representations from Transformers (BERT) based semantic similarity to ensure context-aware reuse. A prototype Revit plug-in was developed for structured capture and semantic search. Evaluation demonstrated strong performance, superiority over baseline methods, and high user acceptance. This paper provides a practical framework and tool for structured documentation and intelligent knowledge reuse, thereby enhancing creativity support for construction VE practices.

有效地重用来自价值工程（VE）车间的创意对于具有成本效益的创新设计至关重要。传统的方法，如项目后审查和关键字搜索，通常缺乏上下文、实时可用性和语义相关性，限制了对过去见解的实际重用。本文解决了如何有效地捕获和重用在VE研讨会期间生成的知识以支持未来的想法生成的基本问题。为了解决这一问题，本文提出了一种基于bim的实时捕获与混合检索系统相结合的集成方法。该系统使用结构化属性和基于语义相似度的双向编码器表示（BERT）来确保上下文感知重用。开发了用于结构化捕获和语义搜索的原型Revit插件。评估显示了强大的性能，优于基线方法，并且用户接受度高。本文为结构化文档和智能知识重用提供了一个实用的框架和工具，从而增强了对构建VE实践的创造性支持。

{"title":"Real-time knowledge management for construction value engineering: Live capture and BERT-aided case-based retrieval","authors":"Fuhao Zu , Xueqing Zhang","doi":"10.1016/j.autcon.2026.106782","DOIUrl":"10.1016/j.autcon.2026.106782","url":null,"abstract":"<div><div>Effective reuse of creative ideas from value engineering (VE) workshops is crucial for cost-effective, innovative design. Conventional methods like post-project reviews and keyword searches often lack context, real-time availability, and semantic relevance, limiting the practical reuse of past insights. This paper addresses the fundamental question of how knowledge generated during VE workshops can be effectively captured and reused to support future idea generations. To solve this, it proposes an integrated methodology combining BIM-based live capture with a hybrid retrieval system. This system uses structured attributes and Bidirectional Encoder Representations from Transformers (BERT) based semantic similarity to ensure context-aware reuse. A prototype Revit plug-in was developed for structured capture and semantic search. Evaluation demonstrated strong performance, superiority over baseline methods, and high user acceptance. This paper provides a practical framework and tool for structured documentation and intelligent knowledge reuse, thereby enhancing creativity support for construction VE practices.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106782"},"PeriodicalIF":11.5,"publicationDate":"2026-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145995537","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

Stakeholder-centric whole-lifecycle framework for guiding the development and implementation of construction digital twins 以利益相关者为中心的全生命周期框架，用于指导建筑数字孪生的开发和实施

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

Automation in Construction

Pub Date : 2026-01-17 DOI: 10.1016/j.autcon.2026.106773

Wahib Saif , Omar Doukari , Mohamad Kassem

Construction Digital Twins (CDTs) are increasingly recognised for their potential to improve construction project management. However, successful implementation requires more than just deploying technology; it demands a stakeholder-centric, whole-system lifecycle approach. Existing frameworks are largely technocentric, focusing on technical demonstrations in isolated use cases and offering limited guidance on stakeholders' roles, interactions, and system lifecycle considerations. To address these gaps, this paper introduces a socio-technical CDT framework spanning five lifecycle stages: Define, Design, Deploy, Refine, and Decommission. Grounded in an eight-month longitudinal industrial case study and informed by a CDT triad taxonomy (applications, data, technologies), the framework guides CDT development and maps stakeholder engagement throughout its lifecycle. Stakeholders are categorised into four actor groups: Strategic, Advisory, Technical, and Operational, whose interdependencies are conceptualised through an actor role model. The framework extends CDT applicability beyond controlled demonstrations to real project contexts, while emphasising the need for validation across diverse organisational settings.

建筑数字孪生（CDTs）因其改善建筑项目管理的潜力而日益受到认可。然而，成功的实施需要的不仅仅是部署技术；它需要一个以涉众为中心的全系统生命周期方法。现有框架在很大程度上是以技术为中心的，关注于孤立用例中的技术演示，并提供有关涉众角色、交互和系统生命周期考虑的有限指导。为了解决这些差距，本文介绍了一个跨越五个生命周期阶段的社会技术CDT框架：定义、设计、部署、改进和退役。该框架以为期8个月的纵向工业案例研究为基础，并以CDT三元分类（应用程序、数据、技术）为依据，指导CDT开发，并在其整个生命周期中绘制涉众参与的地图。涉众被分为四个行动者组：战略、咨询、技术和运营，其相互依赖关系通过行动者角色模型概念化。该框架将CDT的适用性从受控的演示扩展到实际的项目环境，同时强调了跨不同组织设置进行验证的必要性。

{"title":"Stakeholder-centric whole-lifecycle framework for guiding the development and implementation of construction digital twins","authors":"Wahib Saif , Omar Doukari , Mohamad Kassem","doi":"10.1016/j.autcon.2026.106773","DOIUrl":"10.1016/j.autcon.2026.106773","url":null,"abstract":"<div><div>Construction Digital Twins (CDTs) are increasingly recognised for their potential to improve construction project management. However, successful implementation requires more than just deploying technology; it demands a stakeholder-centric, whole-system lifecycle approach. Existing frameworks are largely technocentric, focusing on technical demonstrations in isolated use cases and offering limited guidance on stakeholders' roles, interactions, and system lifecycle considerations. To address these gaps, this paper introduces a socio-technical CDT framework spanning five lifecycle stages: Define, Design, Deploy, Refine, and Decommission. Grounded in an eight-month longitudinal industrial case study and informed by a CDT triad taxonomy (applications, data, technologies), the framework guides CDT development and maps stakeholder engagement throughout its lifecycle. Stakeholders are categorised into four actor groups: Strategic, Advisory, Technical, and Operational, whose interdependencies are conceptualised through an actor role model. The framework extends CDT applicability beyond controlled demonstrations to real project contexts, while emphasising the need for validation across diverse organisational settings.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106773"},"PeriodicalIF":11.5,"publicationDate":"2026-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145995539","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

Lightweight semantic segmentation for construction progress monitoring using 3D point clouds 基于三维点云的施工进度监测轻量级语义分割

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

Automation in Construction

Pub Date : 2026-01-17 DOI: 10.1016/j.autcon.2026.106765

Jinting Huang , Zhonghua Xiao , Ankang Ji , Limao Zhang

This paper proposes a lightweight semantic segmentation framework utilizing 3D point cloud data to enable automatic and rapid construction progress monitoring in high-rise building projects. This study centers on developing an efficient L-PointNet++ model that integrates self-attention mechanisms and MobileNetV3 modules, significantly reducing computational complexity and achieving a 95.63 % reduction in total training time compared to traditional PointNet++. A dual-stage training strategy is adopted to effectively address class imbalance, resulting in high segmentation accuracy with mean Intersection over Union (mIoU) values of 0.9308 for edge points and 0.9300 for corner points. Experimental results indicate that the developed framework can significantly enhance the speed and adaptability of as-built BIM model reconstruction and provide substantial improvements in decision-making efficiency and project management through the implementation of a visualization-based progress monitoring and early-warning system. Overall, the proposed approach demonstrates notable advantages in 3D reconstruction accuracy, speed, and project control, providing a robust solution for real-time construction progress monitoring applications.

本文提出了一种利用三维点云数据的轻量级语义分割框架，实现高层建筑项目施工进度的自动快速监测。本研究的重点是开发一个高效的l - pointnet++模型，该模型集成了自注意机制和MobileNetV3模块，显著降低了计算复杂度，与传统的pointnet++相比，总训练时间减少了95.63%。采用双阶段训练策略，有效解决了类不平衡问题，分割精度较高，边缘点的平均mIoU值为0.9308，角点的平均mIoU值为0.9300。实验结果表明，所开发的框架可以通过实施基于可视化的进度监测预警系统，显著提高BIM模型重建的速度和适应性，显著提高决策效率和项目管理水平。总体而言，该方法在三维重建精度、速度和项目控制方面具有显着优势，为实时施工进度监控应用提供了强大的解决方案。

{"title":"Lightweight semantic segmentation for construction progress monitoring using 3D point clouds","authors":"Jinting Huang , Zhonghua Xiao , Ankang Ji , Limao Zhang","doi":"10.1016/j.autcon.2026.106765","DOIUrl":"10.1016/j.autcon.2026.106765","url":null,"abstract":"<div><div>This paper proposes a lightweight semantic segmentation framework utilizing 3D point cloud data to enable automatic and rapid construction progress monitoring in high-rise building projects. This study centers on developing an efficient L-PointNet++ model that integrates self-attention mechanisms and MobileNetV3 modules, significantly reducing computational complexity and achieving a 95.63 % reduction in total training time compared to traditional PointNet++. A dual-stage training strategy is adopted to effectively address class imbalance, resulting in high segmentation accuracy with mean Intersection over Union (mIoU) values of 0.9308 for edge points and 0.9300 for corner points. Experimental results indicate that the developed framework can significantly enhance the speed and adaptability of as-built BIM model reconstruction and provide substantial improvements in decision-making efficiency and project management through the implementation of a visualization-based progress monitoring and early-warning system. Overall, the proposed approach demonstrates notable advantages in 3D reconstruction accuracy, speed, and project control, providing a robust solution for real-time construction progress monitoring applications.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106765"},"PeriodicalIF":11.5,"publicationDate":"2026-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145995538","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

Distributed acoustic sensing for monitoring engineering infrastructure: Mechanisms, signal analytics, and applications 分布式声学传感监测工程基础设施：机制，信号分析和应用

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

Automation in Construction

Pub Date : 2026-01-17 DOI: 10.1016/j.autcon.2026.106784

Yuanyuan Li , Runze Zhao , Yin Liu , Hongnan Li , Qingrui Yue , Hongbing Chen

Vibration monitoring of engineering infrastructures is indispensable for structural safety and scientific maintenance. Distributed acoustic sensing (DAS) has been increasingly adopted in engineering field, owing to its attractive characteristics over conventional point-based transducers, including high spatial resolution, spatial continuity, non-invasiveness and superior stability. These advantages align well with instrumentation requirements for long-term and widely-distributed vibration monitoring in large-scale infrastructures. Accordingly, this paper provides a systematic review of DAS technique with respect to sensing mechanisms, deployment strategies, signal analysis, and typical applications. This review is structured around a complete operational workflow that explicates what the technology is, how it works, and what it enables in practice. Furthermore, current challenges and promising directions are discussed to envisage the widespread implementation of DAS systems, with the ultimate goal of automated monitoring for infrastructures. This review also aims to provide an exhaustive reference for researchers, professionals or engineering inspectors seeking state-of-the-art in DAS research.

工程基础设施的振动监测是保证结构安全、科学维护的重要手段。分布式声传感技术（DAS）以其高空间分辨率、空间连续性、非侵入性和优越的稳定性等优点，在工程领域得到了越来越多的应用。这些优点很好地满足了大型基础设施中长期和广泛分布的振动监测的仪器要求。因此，本文从传感机制、部署策略、信号分析和典型应用等方面对DAS技术进行了系统的综述。这个审查是围绕一个完整的操作工作流构建的，它解释了技术是什么，它是如何工作的，以及它在实践中支持什么。此外，讨论了当前的挑战和有希望的方向，以设想DAS系统的广泛实施，最终目标是基础设施的自动监测。本综述还旨在为研究人员、专业人员或工程检查员提供详尽的参考，以寻求最新的DAS研究。

{"title":"Distributed acoustic sensing for monitoring engineering infrastructure: Mechanisms, signal analytics, and applications","authors":"Yuanyuan Li , Runze Zhao , Yin Liu , Hongnan Li , Qingrui Yue , Hongbing Chen","doi":"10.1016/j.autcon.2026.106784","DOIUrl":"10.1016/j.autcon.2026.106784","url":null,"abstract":"<div><div>Vibration monitoring of engineering infrastructures is indispensable for structural safety and scientific maintenance. Distributed acoustic sensing (DAS) has been increasingly adopted in engineering field, owing to its attractive characteristics over conventional point-based transducers, including high spatial resolution, spatial continuity, non-invasiveness and superior stability. These advantages align well with instrumentation requirements for long-term and widely-distributed vibration monitoring in large-scale infrastructures. Accordingly, this paper provides a systematic review of DAS technique with respect to sensing mechanisms, deployment strategies, signal analysis, and typical applications. This review is structured around a complete operational workflow that explicates what the technology is, how it works, and what it enables in practice. Furthermore, current challenges and promising directions are discussed to envisage the widespread implementation of DAS systems, with the ultimate goal of automated monitoring for infrastructures. This review also aims to provide an exhaustive reference for researchers, professionals or engineering inspectors seeking state-of-the-art in DAS research.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106784"},"PeriodicalIF":11.5,"publicationDate":"2026-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145976064","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

Artifact-driven LLM integration for mouseless design workflows 无鼠标设计工作流的工件驱动LLM集成

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

Automation in Construction

Pub Date : 2026-01-16 DOI: 10.1016/j.autcon.2026.106766

Ghang Lee , Sejin Park , Soo-in Yang

This paper investigates “mouseless design” feasibility, replacing traditional mouse-based interfaces with natural language interaction, in professional design practice. A three-month experiment tested LLMs for developing a sports complex project for competition. Through triangulation analysis of 2162 conversation turns, 1281 messages, and an 84-page design journal, this study established a quantitative baseline for LLM performance across professional design workflows. It revealed 86.9% unsuccessful individual interactions despite successful project completion and identified inconsistent spatial reasoning and geometry handling as the main weaknesses. Two methodological breakthroughs using conversational programming overcame these limitations: the “artifact-driven” approach repositioning LLMs as custom digital tool creators rather than direct design generators, and self-learning approaches extending complex BIM functionality. A statistical analysis (χ²(90) = 156, Cramer's V = 0.120) shows that terminology alignment serves as a success multiplier when combined with other strategies. These contributions provide empirical evidence for natural language-driven design while identifying critical requirements for successful AI integration.

本文在专业设计实践中探讨“无鼠标设计”的可行性，用自然语言交互取代传统的基于鼠标的界面。一项为期三个月的实验测试了llm为比赛开发体育综合体项目的能力。通过对2162个会话回合、1281条消息和84页的设计期刊进行三角分析，本研究为LLM在专业设计工作流程中的表现建立了定量基线。它揭示了86.9%不成功的个人互动，尽管成功完成了项目，并确定了不一致的空间推理和几何处理是主要弱点。对话式编程的两个方法论突破克服了这些限制：“工件驱动”方法将llm重新定位为定制的数字工具创建者，而不是直接的设计生成器，以及扩展复杂BIM功能的自我学习方法。统计分析（χ2(90) = 156, Cramer's V = 0.120）表明，术语对齐与其他策略结合使用时，可以起到成功乘数的作用。这些贡献为自然语言驱动的设计提供了经验证据，同时确定了成功的人工智能集成的关键需求。

{"title":"Artifact-driven LLM integration for mouseless design workflows","authors":"Ghang Lee , Sejin Park , Soo-in Yang","doi":"10.1016/j.autcon.2026.106766","DOIUrl":"10.1016/j.autcon.2026.106766","url":null,"abstract":"<div><div>This paper investigates “mouseless design” feasibility, replacing traditional mouse-based interfaces with natural language interaction, in professional design practice. A three-month experiment tested LLMs for developing a sports complex project for competition. Through triangulation analysis of 2162 conversation turns, 1281 messages, and an 84-page design journal, this study established a quantitative baseline for LLM performance across professional design workflows. It revealed 86.9% unsuccessful individual interactions despite successful project completion and identified inconsistent spatial reasoning and geometry handling as the main weaknesses. Two methodological breakthroughs using conversational programming overcame these limitations: the “artifact-driven” approach repositioning LLMs as custom digital tool creators rather than direct design generators, and self-learning approaches extending complex BIM functionality. A statistical analysis (χ<sup>2</sup>(90) = 156, Cramer's V = 0.120) shows that terminology alignment serves as a success multiplier when combined with other strategies. These contributions provide empirical evidence for natural language-driven design while identifying critical requirements for successful AI integration.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106766"},"PeriodicalIF":11.5,"publicationDate":"2026-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145976063","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

Virtual reality-based experimental analysis of personality and cognitive traits on task performance and safety in novice tower crane operators 基于虚拟现实的塔机新手任务绩效与安全的人格与认知特征实验分析

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

Automation in Construction

Pub Date : 2026-01-14 DOI: 10.1016/j.autcon.2026.106776

Seungkeun Yeom , Juui Kim , Seungwon Seo , Seongkyun Ahn , Choongwan Koo , Taehoon Hong

This paper investigates how personality traits and psychological-cognitive states influence task performance, safety, and physiological responses of novice tower crane operators through a virtual reality (VR) simulation integrated with continuous biometric monitoring. Fifty participants completed object lifting, obstacle navigation, and precision placement tasks while personality profiles and biosignals (ECG, EDA) were collected and analyzed using principal component analysis,cluster-based classification, and additional statistical methods. High extraversion and situational awareness enhanced speed and accuracy, whereas high openness, stress sensitivity, and acrophobia led to longer durations and reduced accuracy. High conscientiousness shortened task times by 19.12% but increased collisions by approximately threefold, revealing a trade-off between efficiency and safety. By integrating behavioral, cognitive, and physiological data, this work advances technology-enabled, data-driven safety management. The proposed approach enables automated operator risk profiling, intelligent task allocation, and proactive safety interventions for high-rise construction projects involving crane operations.

本文通过结合连续生物特征监测的虚拟现实（VR）模拟，研究了人格特征和心理认知状态如何影响塔式起重机新手的任务绩效、安全性和生理反应。50名参与者完成了物体举起、障碍物导航和精确放置任务，同时收集了性格特征和生物信号（ECG、EDA），并使用主成分分析、基于聚类的分类和其他统计方法进行了分析。高外向性和情境意识提高了速度和准确性，而高开放性、压力敏感性和恐高症导致持续时间更长和准确性降低。高度的责任心将任务时间缩短了19.12%，但将碰撞增加了大约三倍，揭示了效率和安全之间的权衡。通过整合行为、认知和生理数据，这项工作推进了技术驱动、数据驱动的安全管理。所提出的方法为涉及起重机操作的高层建筑项目实现了自动操作员风险分析、智能任务分配和主动安全干预。

{"title":"Virtual reality-based experimental analysis of personality and cognitive traits on task performance and safety in novice tower crane operators","authors":"Seungkeun Yeom , Juui Kim , Seungwon Seo , Seongkyun Ahn , Choongwan Koo , Taehoon Hong","doi":"10.1016/j.autcon.2026.106776","DOIUrl":"10.1016/j.autcon.2026.106776","url":null,"abstract":"<div><div>This paper investigates how personality traits and psychological-cognitive states influence task performance, safety, and physiological responses of novice tower crane operators through a virtual reality (VR) simulation integrated with continuous biometric monitoring. Fifty participants completed object lifting, obstacle navigation, and precision placement tasks while personality profiles and biosignals (ECG, EDA) were collected and analyzed using principal component analysis,cluster-based classification, and additional statistical methods. High extraversion and situational awareness enhanced speed and accuracy, whereas high openness, stress sensitivity, and acrophobia led to longer durations and reduced accuracy. High conscientiousness shortened task times by 19.12% but increased collisions by approximately threefold, revealing a trade-off between efficiency and safety. By integrating behavioral, cognitive, and physiological data, this work advances technology-enabled, data-driven safety management. The proposed approach enables automated operator risk profiling, intelligent task allocation, and proactive safety interventions for high-rise construction projects involving crane operations.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106776"},"PeriodicalIF":11.5,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145957799","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

Efficient UAV trajectory optimization for fine-detailed 3D building reconstruction 面向精细三维建筑重建的高效无人机轨迹优化

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

Automation in Construction

Pub Date : 2026-01-14 DOI: 10.1016/j.autcon.2026.106775

Tianrui Shen, Lai Kang, Yingmei Wei, Shanshan Wan, Haixuan Wang, Chao Zuo

Using images captured by UAVs for high-fidelity 3D building reconstruction in architectural engineering is popular and effective nowadays; however, planning a flight trajectory that maximizes reconstruction quality with minimal flight time remains a critical challenge. This paper proposes a universal co-optimization framework that bridges reconstruction objectives with flight dynamics through an integrated planning paradigm. The proposed approach performs initial flight planning by solving a Traveling Salesman Problem over candidate viewpoints and updating them according to the unit-length contribution criterion. The adaptive radius is determined, and subsequently, the sphere-based corridor is constructed to enforce the trajectory passing all updated viewpoints within the corresponding spatial tolerances. Next, an optimal control problem is formulated and solved using a nonlinear solver to obtain the final flight trajectory satisfying both dynamic and safety constraints. Experimental comparisons with state-of-the-art methods on three public scenes and two real scenes captured by ourselves demonstrate that the proposed approach significantly improves flight efficiency, reducing travel distance and flight duration by approximately 10% to 40% with comparable or superior reconstruction quality.

利用无人机捕获的图像进行高保真的三维建筑重建是目前建筑工程中较为流行和有效的方法。然而，规划一个飞行轨迹，以最小的飞行时间最大限度地提高重建质量仍然是一个关键的挑战。本文提出了一个通用的协同优化框架，通过综合规划范式将重建目标与飞行动力学联系起来。该方法通过求解候选视点上的旅行推销员问题，并根据单位长度贡献准则对候选视点进行更新，从而实现初始飞行计划。确定自适应半径，然后构建基于球体的廊道，使轨迹在相应的空间容差范围内通过所有更新的视点。其次，建立了最优控制问题，并利用非线性求解器求解，得到了同时满足动力和安全约束的最终飞行轨迹。在三个公共场景和我们自己捕获的两个真实场景上与最先进的方法进行的实验比较表明，所提出的方法显着提高了飞行效率，将飞行距离和飞行时间减少了约10%至40%，并且具有相当或更好的重建质量。

{"title":"Efficient UAV trajectory optimization for fine-detailed 3D building reconstruction","authors":"Tianrui Shen, Lai Kang, Yingmei Wei, Shanshan Wan, Haixuan Wang, Chao Zuo","doi":"10.1016/j.autcon.2026.106775","DOIUrl":"10.1016/j.autcon.2026.106775","url":null,"abstract":"<div><div>Using images captured by UAVs for high-fidelity 3D building reconstruction in architectural engineering is popular and effective nowadays; however, planning a flight trajectory that maximizes reconstruction quality with minimal flight time remains a critical challenge. This paper proposes a universal co-optimization framework that bridges reconstruction objectives with flight dynamics through an integrated planning paradigm. The proposed approach performs initial flight planning by solving a Traveling Salesman Problem over candidate viewpoints and updating them according to the unit-length contribution criterion. The adaptive radius is determined, and subsequently, the sphere-based corridor is constructed to enforce the trajectory passing all updated viewpoints within the corresponding spatial tolerances. Next, an optimal control problem is formulated and solved using a nonlinear solver to obtain the final flight trajectory satisfying both dynamic and safety constraints. Experimental comparisons with state-of-the-art methods on three public scenes and two real scenes captured by ourselves demonstrate that the proposed approach significantly improves flight efficiency, reducing travel distance and flight duration by approximately 10% to 40% with comparable or superior reconstruction quality.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106775"},"PeriodicalIF":11.5,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145976062","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

Condition-aware AI framework for automated structural health monitoring 用于自动结构健康监测的状态感知AI框架

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

Automation in Construction

Pub Date : 2026-01-14 DOI: 10.1016/j.autcon.2025.106748

Hamed Hasani, Francesco Freddi

This study presents an AI-powered framework for automated structural health monitoring that integrates modal identification, anomaly detection, and damage localization under varying environmental and operational conditions. The approach combines stochastic subspace identification with frequency–spatial domain decomposition for automated modal extraction and a condition-aware anomaly detector based on a conditional variational autoencoder. A secondary SSA–OC-SVM module verifies and localizes damage. The methodology is validated on a laboratory-scale structure through 500 one-hour tests under temperature variations up to 35 °C and diverse loading conditions. The identified modes exhibit MAC = 0.99–1.00, confirming reliable automated identification. The CVAE reconstructs healthy-state modal frequencies with MAPE = 0.23%, RMSE = 0.027 Hz, and

R^{2}

= 0.836, effectively distinguishing environmental effects (

\leq 0.27

pp) from genuine structural changes. The integrated framework further accurately localizes all induced damage scenarios across nine structural zones, demonstrating high accuracy, robustness, and scalability for next-generation SHM automation.

本研究提出了一个人工智能驱动的自动化结构健康监测框架，该框架集成了模态识别、异常检测和不同环境和操作条件下的损伤定位。该方法结合了随机子空间识别与频率-空间域分解的自动模态提取，以及基于条件变分自编码器的状态感知异常检测器。辅助SSA-OC-SVM模块对损坏进行验证和定位。该方法在实验室规模的结构上进行了500次一小时的测试，在温度变化高达35°C和各种负载条件下进行了验证。识别模式的MAC值为0.99-1.00，表明自动识别是可靠的。CVAE重构健康态模态频率，MAPE = 0.23%, RMSE = 0.027 Hz, R2 = 0.836，有效区分了环境影响（≤0.27 pp）和真实结构变化。集成框架进一步准确地定位了9个结构区域的所有诱发损伤场景，为下一代SHM自动化展示了高精度、鲁棒性和可扩展性。

{"title":"Condition-aware AI framework for automated structural health monitoring","authors":"Hamed Hasani, Francesco Freddi","doi":"10.1016/j.autcon.2025.106748","DOIUrl":"10.1016/j.autcon.2025.106748","url":null,"abstract":"<div><div>This study presents an AI-powered framework for automated structural health monitoring that integrates modal identification, anomaly detection, and damage localization under varying environmental and operational conditions. The approach combines stochastic subspace identification with frequency–spatial domain decomposition for automated modal extraction and a condition-aware anomaly detector based on a conditional variational autoencoder. A secondary SSA–OC-SVM module verifies and localizes damage. The methodology is validated on a laboratory-scale structure through 500 one-hour tests under temperature variations up to 35 °C and diverse loading conditions. The identified modes exhibit MAC = 0.99–1.00, confirming reliable automated identification. The CVAE reconstructs healthy-state modal frequencies with MAPE = 0.23%, RMSE = 0.027 Hz, and <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> = 0.836, effectively distinguishing environmental effects (<span><math><mrow><mo>≤</mo><mn>0</mn><mo>.</mo><mn>27</mn></mrow></math></span> pp) from genuine structural changes. The integrated framework further accurately localizes all induced damage scenarios across nine structural zones, demonstrating high accuracy, robustness, and scalability for next-generation SHM automation.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106748"},"PeriodicalIF":11.5,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145976055","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

Domain-adaptive instance segmentation for far-field object monitoring using SAM-based weak supervision and noisy student self-training 基于sam的弱监督和噪声学生自训练的远场目标监测领域自适应实例分割

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

Automation in Construction

Pub Date : 2026-01-13 DOI: 10.1016/j.autcon.2026.106772

Minkyu Koo , Taegeon Kim , Minhyun Lee , Kinam Kim , Hongjo Kim

Automating construction site monitoring through deep learning–based segmentation presents challenges due to the high cost of pixel-wise annotations. This paper introduces a weakly and self-supervised learning framework that enhances segmentation accuracy while reducing annotation burden. Human-annotated bounding-box ground truth is used as prompts for the Segment Anything Model (SAM) to generate high-quality polygon mask labels, which are further refined through self-training. Compared to fully supervised learning models, the framework integrates Transfer Learning, Pseudo-Label Refinement, and the Noisy Student technique, improving mask mean Average Precision (Mask mAP) by 3–63% across seven target domains and achieving a Mask mAP of 72.27%. The approach also outperforms existing weakly supervised techniques, including BoxSnake and BoxTeacher, by 18% and 25.95%, respectively, and exceeds the performance of point-based methods such as PointWSSIS by 48.78%.

由于像素级标注的高成本，通过基于深度学习的分割自动化施工现场监控提出了挑战。本文引入了一种弱自监督学习框架，在降低标注负担的同时提高了分割精度。将人类标注的边界框地面真值作为SAM （Segment Anything Model）的提示符，生成高质量的多边形掩码标签，并通过自我训练进一步细化。与完全监督学习模型相比，该框架集成了迁移学习、伪标签细化和噪声学生技术，在7个目标域将mask mean Average Precision （mask mAP）提高了3-63%，实现了72.27%的mask mAP。该方法也比现有的弱监督技术（包括BoxSnake和BoxTeacher）分别高出18%和25.95%，并且比基于点的方法（如PointWSSIS）的性能高出48.78%。

引用次数: 0

Controllable reference-based semantic crack-image generation using diffusion model for intelligent infrastructure inspection 基于扩散模型的可控制参考语义裂缝图像生成，用于基础设施智能检测

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

Automation in Construction

Pub Date : 2026-01-13 DOI: 10.1016/j.autcon.2025.106759

Wenshang Yan , Hongnan Li

Improving the accuracy and robustness of deep-learning-based crack-segmentation models remains a significant challenge, primarily because of the insufficient quantity and diversity of the available pixel-level annotated data. To address this issue, this paper proposes a controllable Crack Reference-based Diffusion Model (CRDM). The proposed model can accurately synthesize realistic cracks on crack-free background images by leveraging predefined masks and reference images. Notably, it effectively transfers crack features from reference images to generated images, while maintaining high semantic accuracy. Extensive experiments are performed to demonstrate the advantages of CRDM in producing high-quality, diverse, crack images with precise controllability. The dataset augmented with the CRDM-generated images improves the performance of crack-segmentation models by ∼1 % IoU, across various scenarios. Further performance gains are achieved through our refined label-filtering strategy. The proposed CRDM exhibits strong potential for crack-segmentation tasks, effectively reducing the time and cost of data annotation and acquisition.

提高基于深度学习的裂缝分割模型的准确性和鲁棒性仍然是一个重大挑战，主要是因为可用的像素级注释数据的数量和多样性不足。针对这一问题，本文提出了一种基于裂纹参考的可控扩散模型（CRDM）。该模型可以利用预定义的蒙版和参考图像，在无裂纹背景图像上准确合成真实的裂纹。值得注意的是，它有效地将裂缝特征从参考图像转移到生成图像，同时保持了较高的语义准确性。大量的实验证明了CRDM在产生高质量、多样化、具有精确可控性的裂纹图像方面的优势。使用crdm生成的图像增强的数据集在各种场景下将裂缝分割模型的性能提高了约1% IoU。通过我们改进的标签过滤策略，进一步提高了性能。所提出的CRDM在裂缝分割任务中表现出强大的潜力，有效地减少了数据标注和获取的时间和成本。

{"title":"Controllable reference-based semantic crack-image generation using diffusion model for intelligent infrastructure inspection","authors":"Wenshang Yan , Hongnan Li","doi":"10.1016/j.autcon.2025.106759","DOIUrl":"10.1016/j.autcon.2025.106759","url":null,"abstract":"<div><div>Improving the accuracy and robustness of deep-learning-based crack-segmentation models remains a significant challenge, primarily because of the insufficient quantity and diversity of the available pixel-level annotated data. To address this issue, this paper proposes a controllable Crack Reference-based Diffusion Model (CRDM). The proposed model can accurately synthesize realistic cracks on crack-free background images by leveraging predefined masks and reference images. Notably, it effectively transfers crack features from reference images to generated images, while maintaining high semantic accuracy. Extensive experiments are performed to demonstrate the advantages of CRDM in producing high-quality, diverse, crack images with precise controllability. The dataset augmented with the CRDM-generated images improves the performance of crack-segmentation models by ∼1 % IoU, across various scenarios. Further performance gains are achieved through our refined label-filtering strategy. The proposed CRDM exhibits strong potential for crack-segmentation tasks, effectively reducing the time and cost of data annotation and acquisition.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106759"},"PeriodicalIF":11.5,"publicationDate":"2026-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145962001","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