Automation in Construction最新文献_第9页

Generalizing fatigue prediction models for construction workers: Cross-experiment evaluation with transfer learning across thermal and load conditions 建筑工人疲劳预测模型的推广：热负荷条件下迁移学习的交叉实验评估

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

Automation in Construction

Pub Date : 2025-11-25 DOI: 10.1016/j.autcon.2025.106680

Sharjeel Anjum , Muhammad Khan , Chukwuma Nnaji , Ashrant Aryal , Amanda S. Koh

Physical fatigue among construction workers is a major safety concern, impacting both health and productivity. Machine learning (ML) models for fatigue monitoring often struggle with generalizing across varying work conditions and populations. This paper advances fatigue monitoring automation by (1) developing ML models trained under diverse temperature and load conditions (Dataset 1), (2) evaluating generalizability on unseen construction-related data (Dataset 2), and (3) proposing transfer learning-based fine-tuning to enhance models' adaptability while reducing the need for large datasets. Initial accuracies on Dataset 1 were 87.5 % (RFC), 89.7 % (XGBoost), and 92 % (FatigueNet); however, these dropped sharply to 40 % (RFC, XGBoost) and 29 % (FatigueNet) under the generalizability test. When trained from scratch on combined datasets, RFC and FatigueNet achieved 47 % and 60 % accuracy, highlighting challenges with generalization. Transfer learning improved FatigueNet's accuracy to 82 % and RFC's to 87 %. These results demonstrate transfer learning's potential for real-time fatigue monitoring and construction site safety.

建筑工人的身体疲劳是一个主要的安全问题，影响健康和生产力。用于疲劳监测的机器学习（ML）模型通常难以在不同的工作条件和人群中进行泛化。本文通过(1)开发在不同温度和负载条件下训练的ML模型（数据集1），(2)评估未见建筑相关数据（数据集2）的泛化性，以及(3)提出基于迁移学习的微调以增强模型的适应性，同时减少对大型数据集的需求来推进疲劳监测自动化。数据集1的初始准确度为87.5% (RFC), 89.7% （XGBoost）和92% (FatigueNet)；然而，在通用性测试中，这些数据急剧下降到40% （RFC, XGBoost）和29% （FatigueNet）。当在组合数据集上从零开始训练时，RFC和FatigueNet的准确率分别达到47%和60%，这凸显了泛化的挑战。迁移学习将FatigueNet的准确率提高到82%，RFC的准确率提高到87%。这些结果证明了迁移学习在实时疲劳监测和施工现场安全方面的潜力。

{"title":"Generalizing fatigue prediction models for construction workers: Cross-experiment evaluation with transfer learning across thermal and load conditions","authors":"Sharjeel Anjum , Muhammad Khan , Chukwuma Nnaji , Ashrant Aryal , Amanda S. Koh","doi":"10.1016/j.autcon.2025.106680","DOIUrl":"10.1016/j.autcon.2025.106680","url":null,"abstract":"<div><div>Physical fatigue among construction workers is a major safety concern, impacting both health and productivity. Machine learning (ML) models for fatigue monitoring often struggle with generalizing across varying work conditions and populations. This paper advances fatigue monitoring automation by (1) developing ML models trained under diverse temperature and load conditions (Dataset 1), (2) evaluating generalizability on unseen construction-related data (Dataset 2), and (3) proposing transfer learning-based fine-tuning to enhance models' adaptability while reducing the need for large datasets. Initial accuracies on Dataset 1 were 87.5 % (RFC), 89.7 % (XGBoost), and 92 % (FatigueNet); however, these dropped sharply to 40 % (RFC, XGBoost) and 29 % (FatigueNet) under the generalizability test. When trained from scratch on combined datasets, RFC and FatigueNet achieved 47 % and 60 % accuracy, highlighting challenges with generalization. Transfer learning improved FatigueNet's accuracy to 82 % and RFC's to 87 %. These results demonstrate transfer learning's potential for real-time fatigue monitoring and construction site safety.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"181 ","pages":"Article 106680"},"PeriodicalIF":11.5,"publicationDate":"2025-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145593092","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

Machine learning-based automatic detection and prediction of cracks and corrosion using spatiotemporal measurements from distributed fiber optic sensors 基于机器学习的裂缝和腐蚀的自动检测和预测，利用分布式光纤传感器的时空测量

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

Automation in Construction

Pub Date : 2025-11-24 DOI: 10.1016/j.autcon.2025.106679

Sina Poorghasem, Yiming Liu, Zhan Jiang, Jinxin Chen, Yi Bao

Monitoring and predicting damages of civil infrastructure are essential for safe and efficient operation and maintenance. This paper presents a digital twin-based approach for automatic detection and prediction of cracks and corrosion utilizing spatiotemporal measurements of strains from distributed fiber optic sensors. Generative machine learning techniques are used to improve the quantity and quality of datasets used to develop damage detection and prediction models. The performance of the approach was evaluated using laboratory experiments through case studies on reinforced concrete beams and steel pipes. Results demonstrated that cracks and corrosion were detected accurately (accuracy>0.98) and efficiently (latency = 0.17 ms). Predictions of strain distributions were performed 7 min ahead for cracks and 21 h ahead for corrosion. The effects of sensing parameters on performance were investigated, enabling sensor configuration optimization. The presented approach advances the ability to monitor and predict damages based on advanced machine learning and distributed fiber optic sensing techniques.

监测和预测民用基础设施的损害是保证民用基础设施安全、高效运行和维护的必要条件。本文提出了一种基于数字孪生的方法，利用分布式光纤传感器的应变时空测量来自动检测和预测裂缝和腐蚀。生成式机器学习技术用于提高用于开发损伤检测和预测模型的数据集的数量和质量。通过钢筋混凝土梁和钢管的实例试验，对该方法的性能进行了评价。结果表明，裂纹和腐蚀检测准确（精度>；0.98），有效（延迟= 0.17 ms）。裂纹和腐蚀分别提前7分钟和21小时预测应变分布。研究了传感参数对性能的影响，实现了传感器配置的优化。该方法基于先进的机器学习和分布式光纤传感技术，提高了监测和预测损伤的能力。

{"title":"Machine learning-based automatic detection and prediction of cracks and corrosion using spatiotemporal measurements from distributed fiber optic sensors","authors":"Sina Poorghasem, Yiming Liu, Zhan Jiang, Jinxin Chen, Yi Bao","doi":"10.1016/j.autcon.2025.106679","DOIUrl":"10.1016/j.autcon.2025.106679","url":null,"abstract":"<div><div>Monitoring and predicting damages of civil infrastructure are essential for safe and efficient operation and maintenance. This paper presents a digital twin-based approach for automatic detection and prediction of cracks and corrosion utilizing spatiotemporal measurements of strains from distributed fiber optic sensors. Generative machine learning techniques are used to improve the quantity and quality of datasets used to develop damage detection and prediction models. The performance of the approach was evaluated using laboratory experiments through case studies on reinforced concrete beams and steel pipes. Results demonstrated that cracks and corrosion were detected accurately (accuracy>0.98) and efficiently (latency = 0.17 ms). Predictions of strain distributions were performed 7 min ahead for cracks and 21 h ahead for corrosion. The effects of sensing parameters on performance were investigated, enabling sensor configuration optimization. The presented approach advances the ability to monitor and predict damages based on advanced machine learning and distributed fiber optic sensing techniques.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"181 ","pages":"Article 106679"},"PeriodicalIF":11.5,"publicationDate":"2025-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145593113","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

Mobile robotic rebar cage assembly via imitation learning 基于模仿学习的移动机器人钢筋笼组装

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

Automation in Construction

Pub Date : 2025-11-24 DOI: 10.1016/j.autcon.2025.106671

Tao Sun , Beining Han , Jimmy Wu , Szymon Rusinkiewicz , Yi Shao

Manipulation remains a key bottleneck in achieving fully autonomous rebar cage assembly. Existing solutions based on rail-guided systems are expensive, poorly scalable, and limited in capability. This paper introduces a framework that leverages a mobile manipulator and uses visual servoing together with imitation learning (IL) to address complex rebar manipulation tasks. The framework enables autonomous execution of two challenging manipulation tasks: (a) tight-fit rebar slot insertion and (b) rebar tying at complex intersection nodes within cages. Using only low-cost RGB cameras, the proposed approach achieves over 90% success rate for over 20 rollouts on both tasks. A highlight is the integration of a segmentation module and a reinsertion strategy that improves tight-fit insertion performance by 41.7% over the baseline and significantly improves robustness to background changes. Notably, the system requires neither depth sensors nor explicit geometric modeling, and supports rapid deployment in novel environments. This paper establishes a foundation for extending autonomy to broader rebar manipulation scenarios. Qualitative results are available on the project website¹.

操作仍然是实现全自动钢筋笼组装的关键瓶颈。现有的基于轨道制导系统的解决方案价格昂贵，可扩展性差，而且能力有限。本文介绍了一种利用移动机械手，结合视觉伺服和模仿学习（IL）来解决复杂钢筋操纵任务的框架。该框架能够自动执行两项具有挑战性的操作任务：(a)紧密配合的螺纹钢槽插入和(b)在笼内复杂的交叉节点绑扎螺纹钢。仅使用低成本的RGB相机，所提出的方法在两个任务上进行超过20次的推出，成功率超过90%。一个亮点是分割模块和插入策略的集成，在基线基础上提高了41.7%的紧密配合插入性能，并显着提高了对背景变化的鲁棒性。值得注意的是，该系统既不需要深度传感器，也不需要明确的几何建模，并且支持在新环境中快速部署。本文为将自治扩展到更广泛的螺纹钢操作场景奠定了基础。定性结果可在项目网站上查阅。

{"title":"Mobile robotic rebar cage assembly via imitation learning","authors":"Tao Sun , Beining Han , Jimmy Wu , Szymon Rusinkiewicz , Yi Shao","doi":"10.1016/j.autcon.2025.106671","DOIUrl":"10.1016/j.autcon.2025.106671","url":null,"abstract":"<div><div>Manipulation remains a key bottleneck in achieving fully autonomous rebar cage assembly. Existing solutions based on rail-guided systems are expensive, poorly scalable, and limited in capability. This paper introduces a framework that leverages a mobile manipulator and uses visual servoing together with imitation learning (IL) to address complex rebar manipulation tasks. The framework enables autonomous execution of two challenging manipulation tasks: (a) tight-fit rebar slot insertion and (b) rebar tying at complex intersection nodes within cages. Using only low-cost RGB cameras, the proposed approach achieves over 90% success rate for over 20 rollouts on both tasks. A highlight is the integration of a segmentation module and a reinsertion strategy that improves tight-fit insertion performance by 41.7% over the baseline and significantly improves robustness to background changes. Notably, the system requires neither depth sensors nor explicit geometric modeling, and supports rapid deployment in novel environments. This paper establishes a foundation for extending autonomy to broader rebar manipulation scenarios. Qualitative results are available on the project website<span><span><sup>1</sup></span></span>.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"181 ","pages":"Article 106671"},"PeriodicalIF":11.5,"publicationDate":"2025-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145593116","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

Computationally assisted design and fabrication of curved bamboo composite shell structures 弯曲竹复合材料壳结构的计算辅助设计与制造

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

Automation in Construction

Pub Date : 2025-11-24 DOI: 10.1016/j.autcon.2025.106684

Shih-Yuan Wang , Yu-Ting Sheng , Wei-Che Lo , Sze-Teng Liong , Y.S. Gan , Jun-Hui Liang

The natural heterogeneity and geometric irregularity of bamboo limit its structural reliability in construction. This paper presents a Computationally Assisted Fabrication Process (CAFP) that integrates material-informed design, structural simulation, and digital fabrication within an automation-oriented workflow. Ultra-thin laminated bamboo sheets are exploited for their conditional bending capacity, enabling actively bent structures and complex curved shells. To overcome instability observed in prior assemblies, fiberglass reinforcement is incorporated, with mechanical testing confirming substantial improvements in flexural strength. Simulation-driven optimization further reduces stress utilization from 36.4% to 5.5% and maximum displacement from 24.4 cm to 1.43 cm, demonstrating significant gains in stability and efficiency. The workflow systematically links geometry generation, structural evaluation, strip-based mesh segmentation, and parametric joinery design, providing an end-to-end pathway from design to digital construction. By embedding material properties into computational processes, the paper contributes an automation-ready method for reliable and efficient bamboo construction, expanding its potential in architectural practice.

竹材本身的非均质性和几何不规则性限制了其结构的可靠性。本文提出了一种计算辅助制造工艺（CAFP），它将材料信息设计、结构模拟和数字化制造集成在一个自动化的工作流程中。超薄层压竹片利用其条件弯曲能力，实现主动弯曲结构和复杂的弯曲外壳。为了克服先前组件中观察到的不稳定性，加入了玻璃纤维增强，机械测试证实了弯曲强度的显著提高。模拟驱动的优化进一步将应力利用率从36.4%降低到5.5%，最大位移从24.4 cm降低到1.43 cm，证明了稳定性和效率的显著提高。工作流系统地将几何图形生成、结构评估、基于条带的网格分割和参数化细木工设计联系起来，提供了从设计到数字施工的端到端路径。通过将材料特性嵌入到计算过程中，本文为可靠和高效的竹结构提供了一种自动化的方法，扩大了其在建筑实践中的潜力。

{"title":"Computationally assisted design and fabrication of curved bamboo composite shell structures","authors":"Shih-Yuan Wang , Yu-Ting Sheng , Wei-Che Lo , Sze-Teng Liong , Y.S. Gan , Jun-Hui Liang","doi":"10.1016/j.autcon.2025.106684","DOIUrl":"10.1016/j.autcon.2025.106684","url":null,"abstract":"<div><div>The natural heterogeneity and geometric irregularity of bamboo limit its structural reliability in construction. This paper presents a Computationally Assisted Fabrication Process (CAFP) that integrates material-informed design, structural simulation, and digital fabrication within an automation-oriented workflow. Ultra-thin laminated bamboo sheets are exploited for their conditional bending capacity, enabling actively bent structures and complex curved shells. To overcome instability observed in prior assemblies, fiberglass reinforcement is incorporated, with mechanical testing confirming substantial improvements in flexural strength. Simulation-driven optimization further reduces stress utilization from 36.4% to 5.5% and maximum displacement from 24.4 cm to 1.43 cm, demonstrating significant gains in stability and efficiency. The workflow systematically links geometry generation, structural evaluation, strip-based mesh segmentation, and parametric joinery design, providing an end-to-end pathway from design to digital construction. By embedding material properties into computational processes, the paper contributes an automation-ready method for reliable and efficient bamboo construction, expanding its potential in architectural practice.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"181 ","pages":"Article 106684"},"PeriodicalIF":11.5,"publicationDate":"2025-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145593112","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

BIM-enabled lifecycle carbon emission management integrating multi-physical field steady-state methods during operation bim支持的生命周期碳排放管理，集成了运行期间的多物理场稳态方法

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

Automation in Construction

Pub Date : 2025-11-24 DOI: 10.1016/j.autcon.2025.106683

Hao Yuan , Bo Huang , Manqiu Wang , Yao Tang , Jin Mao , Lun Xiong

With growing global focus on climate change, carbon emission control in the construction industry has become a key to sustainable development. Current full-life-cycle carbon calculation faces two challenges: large errors and low efficiency due to reliance on single factors and lightweight models; and over-reliance on standardized data, poor adaptability to complex scenarios, and lagging energy consumption data updates in existing life cycle assessment tools. This paper proposes a multi-physics coupling algorithm for operational phase emissions and develops a BIM-based collaborative framework. Verified results show operational phase calculation accuracy within ±7 %. An apartment case study in Chongqing, China, reveals operational emissions account for 71.55 % of total life-cycle emissions, driven mainly by heating, ventilation and air conditioning systems. The method proposed and the application developed in the research can improve the efficiency of building carbon emission calculation and promote the low-carbon development of the construction industry.

随着全球对气候变化的日益关注，建筑行业的碳排放控制已成为可持续发展的关键。目前全生命周期碳计算面临两大挑战：由于依赖单一因素和轻量化模型，误差大、效率低；现有生命周期评估工具过度依赖标准化数据，对复杂场景适应性差，能耗数据更新滞后。提出了一种多物理场耦合的运行相位发射算法，并开发了基于bim的协同框架。验证结果表明，运行相位计算精度在±7%以内。中国重庆的一项公寓案例研究显示，运营排放占全生命周期排放总量的71.55%，主要由供暖、通风和空调系统驱动。本研究提出的方法和开发的应用可以提高建筑碳排放计算的效率，促进建筑行业的低碳发展。

{"title":"BIM-enabled lifecycle carbon emission management integrating multi-physical field steady-state methods during operation","authors":"Hao Yuan , Bo Huang , Manqiu Wang , Yao Tang , Jin Mao , Lun Xiong","doi":"10.1016/j.autcon.2025.106683","DOIUrl":"10.1016/j.autcon.2025.106683","url":null,"abstract":"<div><div>With growing global focus on climate change, carbon emission control in the construction industry has become a key to sustainable development. Current full-life-cycle carbon calculation faces two challenges: large errors and low efficiency due to reliance on single factors and lightweight models; and over-reliance on standardized data, poor adaptability to complex scenarios, and lagging energy consumption data updates in existing life cycle assessment tools. This paper proposes a multi-physics coupling algorithm for operational phase emissions and develops a BIM-based collaborative framework. Verified results show operational phase calculation accuracy within ±7 %. An apartment case study in Chongqing, China, reveals operational emissions account for 71.55 % of total life-cycle emissions, driven mainly by heating, ventilation and air conditioning systems. The method proposed and the application developed in the research can improve the efficiency of building carbon emission calculation and promote the low-carbon development of the construction industry.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"181 ","pages":"Article 106683"},"PeriodicalIF":11.5,"publicationDate":"2025-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145593115","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

Assembly sequence planning method for robotic timber wall prefabrication 机器人木墙预制装配顺序规划方法

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

Automation in Construction

Pub Date : 2025-11-21 DOI: 10.1016/j.autcon.2025.106669

Cheng-Hsuan Yang, Liang-Ting Tsai, Yuxiang Chen, Shih-Chung Kang

The adoption of industrial robots in construction has increased over the past decade, especially in prefabricated building processes. A key challenge in robotic prefabrication is determining a feasible and efficient assembly sequence. Existing assembly sequence planning (ASP) methods mainly address component placement but lack consideration for material characteristics, fastening operations, and execution constraints in timber wall framing. To address this gap, this paper developed an automated ASP method that integrates stud placement and fastening motions, ensuring tool-collision-free and feasible sequences. The method includes three modules: data preprocessing, stud placement sequencing, and assembly sequence refining. A parameterized geometric representation (PGR) model combined with an eight-parameter stud relation matrix automatically generates missing fastening data, reducing manual input. A scenario-based sequencing approach prevents tucking motions, and a modified A-star algorithm generates near-optimal sequences. Feasibility and performance tests confirmed that the method reduces robotic travel time and ensures tool-collision-free execution.

在过去的十年中，工业机器人在建筑中的应用有所增加，特别是在预制建筑过程中。机器人预制的一个关键挑战是确定一个可行和高效的装配顺序。现有的装配顺序规划（ASP）方法主要解决组件放置问题，但缺乏对材料特性、紧固操作和木墙框架执行约束的考虑。为了解决这一问题，本文开发了一种自动化ASP方法，该方法集成了螺柱放置和紧固运动，确保了工具无碰撞和可行的顺序。该方法包括三个模块：数据预处理、螺柱放置排序和装配序列精炼。参数化几何表示（PGR）模型结合八参数螺柱关系矩阵自动生成缺失的紧固数据，减少人工输入。基于场景的排序方法可以防止折叠运动，改进的A-star算法可以生成接近最优的序列。可行性和性能测试证实，该方法减少了机器人的移动时间，并确保了工具的无碰撞执行。

{"title":"Assembly sequence planning method for robotic timber wall prefabrication","authors":"Cheng-Hsuan Yang, Liang-Ting Tsai, Yuxiang Chen, Shih-Chung Kang","doi":"10.1016/j.autcon.2025.106669","DOIUrl":"10.1016/j.autcon.2025.106669","url":null,"abstract":"<div><div>The adoption of industrial robots in construction has increased over the past decade, especially in prefabricated building processes. A key challenge in robotic prefabrication is determining a feasible and efficient assembly sequence. Existing assembly sequence planning (ASP) methods mainly address component placement but lack consideration for material characteristics, fastening operations, and execution constraints in timber wall framing. To address this gap, this paper developed an automated ASP method that integrates stud placement and fastening motions, ensuring tool-collision-free and feasible sequences. The method includes three modules: data preprocessing, stud placement sequencing, and assembly sequence refining. A parameterized geometric representation (PGR) model combined with an eight-parameter stud relation matrix automatically generates missing fastening data, reducing manual input. A scenario-based sequencing approach prevents tucking motions, and a modified A-star algorithm generates near-optimal sequences. Feasibility and performance tests confirmed that the method reduces robotic travel time and ensures tool-collision-free execution.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"181 ","pages":"Article 106669"},"PeriodicalIF":11.5,"publicationDate":"2025-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145567522","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

Inchworm-inspired climbing robot for steel structures with three bionic operating modes 受尺蠖启发的钢结构攀爬机器人，具有三种仿生操作模式

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

Automation in Construction

Pub Date : 2025-11-21 DOI: 10.1016/j.autcon.2025.106665

Yidong Tang , Changyong Liu , Xuefeng Ma , Limao Zhang , Jiaqi Wang

Steel climbing robots have been utilized to assist manual inspection in recent years for ensuring the reliability of steel structures. However, existing steel climbing robots face significant challenges in efficiently navigating and inspecting complex and confined steel structures. In response, this paper proposes a steel structure climbing robot inspired by the inchworm with three working modes, enabling fast crawling in open spaces, slow creeping in confined spaces, perpendicular surface switching, crossing obstacles, and manipulation capabilities. Climbing and manipulation capabilities of Tribot are analyzed and evaluated by experiments. Tribot achieves step distances of 270 mm and 60 mm in fast crawling mode and slow creeping mode. In manipulation mode, Tribot shows a good 4-DOF manipulation capacity with a carrying load of 1 kg. Obstacle crossing experiments demonstrate that the Tribot can traverse the U-ribs with a height of 260 mm and shows a climbing surface switching capacity between 0° and 180°.

近年来，为了保证钢结构的可靠性，钢爬机器人被用于辅助人工检测。然而，现有的爬钢机器人在高效导航和检测复杂约束钢结构方面面临着重大挑战。为此，本文提出了一种以尺蠖为灵感的钢结构爬行机器人，该机器人具有开放空间快速爬行、密闭空间缓慢爬行、垂直表面切换、跨越障碍物和操作能力三种工作模式。通过实验对Tribot的攀爬能力和操纵能力进行了分析和评价。在快速爬行模式和缓慢爬行模式下，Tribot的步距分别为270毫米和60毫米。在操作模式下，Tribot表现出良好的四自由度操作能力，承载重量为1公斤。实验结果表明，Tribot可以通过高度为260 mm的u型肋，并具有0°~ 180°的爬坡面切换能力。

引用次数: 0

Automated construction of knowledge graphs for accelerated design and understanding of ultra-high-performance concrete 知识图谱的自动构建，加速了超高性能混凝土的设计和理解

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

Automation in Construction

Pub Date : 2025-11-20 DOI: 10.1016/j.autcon.2025.106667

Zhan Jiang , Yide Ran , Zhaozhuo Xu , Shaoyi Huang , Weina Meng , Yi Bao

Knowledge graphs have enabled incorporation of concrete domain knowledge into machine learning-accelerated material design via representing knowledge using digital, operable graphs, toward a knowledge-guided data-driven paradigm with essential interpretability, transparency, and trustworthiness. However, manual construction of knowledge graphs is time-consuming and labor-intensive. This paper presents a framework for the automated construction of material knowledge graphs that leverage the one-shot capability of large language models to address this challenge. The approach reduces the time required to build a comprehensive knowledge graph for ultra-high-performance concrete from 52 h to 1 h. The applications are demonstrated through three use cases, and its generalizability is validated via an application to the accelerated design of ultra-high-performance geopolymer. The framework reveals the complex physicochemical pathways between material components and performance properties, accelerating both the speed of material design and the depth of understanding in the process, pushing the boundaries of knowledge-guided data-driven design.

通过使用数字化、可操作的图形表示知识，知识图能够将具体领域知识整合到机器学习加速的材料设计中，朝着具有基本可解释性、透明度和可信赖性的知识引导数据驱动范式发展。然而，手工构建知识图是费时费力的。本文提出了一个框架，用于自动构建材料知识图，利用大型语言模型的一次性能力来解决这一挑战。该方法将构建高性能混凝土综合知识图谱所需的时间从52小时减少到1小时。通过三个用例演示了该方法的应用，并通过在高性能地聚合物加速设计中的应用验证了其通用性。该框架揭示了材料成分和性能属性之间复杂的物理化学途径，加快了材料设计的速度和对过程的理解深度，推动了知识引导数据驱动设计的边界。

{"title":"Automated construction of knowledge graphs for accelerated design and understanding of ultra-high-performance concrete","authors":"Zhan Jiang , Yide Ran , Zhaozhuo Xu , Shaoyi Huang , Weina Meng , Yi Bao","doi":"10.1016/j.autcon.2025.106667","DOIUrl":"10.1016/j.autcon.2025.106667","url":null,"abstract":"<div><div>Knowledge graphs have enabled incorporation of concrete domain knowledge into machine learning-accelerated material design via representing knowledge using digital, operable graphs, toward a knowledge-guided data-driven paradigm with essential interpretability, transparency, and trustworthiness. However, manual construction of knowledge graphs is time-consuming and labor-intensive. This paper presents a framework for the automated construction of material knowledge graphs that leverage the one-shot capability of large language models to address this challenge. The approach reduces the time required to build a comprehensive knowledge graph for ultra-high-performance concrete from 52 h to 1 h. The applications are demonstrated through three use cases, and its generalizability is validated via an application to the accelerated design of ultra-high-performance geopolymer. The framework reveals the complex physicochemical pathways between material components and performance properties, accelerating both the speed of material design and the depth of understanding in the process, pushing the boundaries of knowledge-guided data-driven design.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"181 ","pages":"Article 106667"},"PeriodicalIF":11.5,"publicationDate":"2025-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145560072","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

Text-mining framework for domain-specific dictionaries in hospital building maintenance requests 用于医院建筑维护请求的特定领域词典的文本挖掘框架

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

Automation in Construction

Pub Date : 2025-11-20 DOI: 10.1016/j.autcon.2025.106668

Ismael Weber , Eduardo Luis Isatto

Hospitals face significant challenges in managing corrective building maintenance due to the high volume and complexity of requests. This paper proposes a framework for developing domain-specific term dictionaries to support the automated categorization of maintenance requests. Using 24,466 work orders (WOs) from a Brazilian university hospital (2017–2022), the research identifies and categorizes key terms across six service areas: building maintenance, carpentry, electricity, HVAC, painting, and plumbing. The methodology applies text mining techniques, including preprocessing, term grouping, and statistical validation using the Chi-Square test. The resulting dictionaries capture linguistic patterns used by end-users and achieved a weighted average detection rate of 88 % in the initial dataset. Validation with 7739 WOs from 2023 showed a 71 % detection rate, confirming the framework's adaptability to evolving vocabulary. These findings demonstrate the potential of domain-specific dictionaries as foundational tools for semantic classification, paving the way for future automated systems in facility management.

由于请求的数量和复杂性，医院在管理正确的建筑物维护方面面临重大挑战。本文提出了一个用于开发特定领域术语字典的框架，以支持维护请求的自动分类。该研究使用了巴西一所大学医院（2017-2022）的24,466份工作订单（WOs），确定并分类了六个服务领域的关键术语：建筑维护、木工、电力、暖通空调、油漆和管道。该方法应用文本挖掘技术，包括预处理、术语分组和使用卡方检验的统计验证。生成的字典捕获了最终用户使用的语言模式，并在初始数据集中实现了88%的加权平均检测率。使用2023年的7739个wo进行验证，检测率为71%，证实了该框架对不断变化的词汇的适应性。这些发现证明了领域特定词典作为语义分类基础工具的潜力，为未来设施管理中的自动化系统铺平了道路。

{"title":"Text-mining framework for domain-specific dictionaries in hospital building maintenance requests","authors":"Ismael Weber , Eduardo Luis Isatto","doi":"10.1016/j.autcon.2025.106668","DOIUrl":"10.1016/j.autcon.2025.106668","url":null,"abstract":"<div><div>Hospitals face significant challenges in managing corrective building maintenance due to the high volume and complexity of requests. This paper proposes a framework for developing domain-specific term dictionaries to support the automated categorization of maintenance requests. Using 24,466 work orders (WOs) from a Brazilian university hospital (2017–2022), the research identifies and categorizes key terms across six service areas: building maintenance, carpentry, electricity, HVAC, painting, and plumbing. The methodology applies text mining techniques, including preprocessing, term grouping, and statistical validation using the Chi-Square test. The resulting dictionaries capture linguistic patterns used by end-users and achieved a weighted average detection rate of 88 % in the initial dataset. Validation with 7739 WOs from 2023 showed a 71 % detection rate, confirming the framework's adaptability to evolving vocabulary. These findings demonstrate the potential of domain-specific dictionaries as foundational tools for semantic classification, paving the way for future automated systems in facility management.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"181 ","pages":"Article 106668"},"PeriodicalIF":11.5,"publicationDate":"2025-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145560092","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

Integrated decision-making for cable crane group dispatch in high arch dams using multi-scale simulation 基于多尺度模拟的高拱坝缆索吊车群调度综合决策

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

Automation in Construction

Pub Date : 2025-11-19 DOI: 10.1016/j.autcon.2025.106643

Chunju Zhao , Jun He , Fang Wang , Junjie Xiong , Xiang Zheng , Yihong Zhou

In high arch dam construction, multiple cable cranes are often deployed to pour multiple blocks simultaneously to accelerate progress. In such scenarios, traditional dispatching methods often overlook the integrated decision-making required between the Match of Blocks and Cranes (MBC) and Pouring Operation Planning (POP), impairing the balance of progress, safety, and quality. This paper proposes a multi-scale simulation framework that integrates Discrete Event Simulation (DES) and Agent-Based Simulation (ABS) to model pouring processes at block and crane scales, enabling unified decision-making of MBC and POP. Agent-based mechanism generated POPs for each MBC by accurately predicting crane efficiency, rationally allocating unloading zones, and coordinating parallel operations under safety and quality constraints. An arch dam construction case demonstrated that the proposed framework reduced the construction period by approximately one month and improved average monthly pouring intensity by 5.56% compared to single-scale simulation, while enhancing task balance over the manual dispatching method.

在高拱坝施工中，经常采用多台吊车同时浇筑多个块体，以加快进度。在这种情况下，传统的调度方法往往忽视了砌块与起重机匹配（MBC）和浇筑作业计划（POP）之间的综合决策，破坏了进度、安全和质量的平衡。本文提出了一种多尺度仿真框架，将离散事件仿真（DES）和基于agent的仿真（ABS）相结合，在块体和起重机尺度上对浇注过程进行建模，实现了MBC和POP的统一决策。基于agent的机制，在安全和质量约束下，通过准确预测起重机效率、合理分配卸车区域、协调并行作业，为每个MBC生成pop。一个拱坝施工实例表明，与单尺度模拟相比，该框架可缩短工期约1个月，提高月平均浇筑强度5.56%，同时比人工调度方法增强任务平衡性。

{"title":"Integrated decision-making for cable crane group dispatch in high arch dams using multi-scale simulation","authors":"Chunju Zhao , Jun He , Fang Wang , Junjie Xiong , Xiang Zheng , Yihong Zhou","doi":"10.1016/j.autcon.2025.106643","DOIUrl":"10.1016/j.autcon.2025.106643","url":null,"abstract":"<div><div>In high arch dam construction, multiple cable cranes are often deployed to pour multiple blocks simultaneously to accelerate progress. In such scenarios, traditional dispatching methods often overlook the integrated decision-making required between the Match of Blocks and Cranes (MBC) and Pouring Operation Planning (POP), impairing the balance of progress, safety, and quality. This paper proposes a multi-scale simulation framework that integrates Discrete Event Simulation (DES) and Agent-Based Simulation (ABS) to model pouring processes at block and crane scales, enabling unified decision-making of MBC and POP. Agent-based mechanism generated POPs for each MBC by accurately predicting crane efficiency, rationally allocating unloading zones, and coordinating parallel operations under safety and quality constraints. An arch dam construction case demonstrated that the proposed framework reduced the construction period by approximately one month and improved average monthly pouring intensity by 5.56% compared to single-scale simulation, while enhancing task balance over the manual dispatching method.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"181 ","pages":"Article 106643"},"PeriodicalIF":11.5,"publicationDate":"2025-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145560094","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