Automation in Construction最新文献

英文中文

Indoor scan-to-BIM automation: From mobile perception to 3D building modelling 室内扫描到bim自动化：从移动感知到3D建筑建模

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

Automation in Construction

Pub Date : 2025-12-18 DOI: 10.1016/j.autcon.2025.106731

Junqi Luo , Zexin Yang , Pengcheng Shi , Qin Ye

Scan-to-BIM is a crucial yet challenging task in intelligent construction, bridging real-world perception and virtual reconstruction. With growing demands for high-fidelity digital twins, its importance is increasingly evident. Unlike prior surveys focusing on isolated components, this review offers an updated and cross-disciplinary overview of the complete indoor Scan-to-BIM workflow, incorporating recent AI-driven advances and available benchmark datasets. First, the relationship between Scan-to-BIM and key AEC modules is clarified. Next, the problem formulation is defined, followed by a discussion of current challenges. Then, commonly used devices and core technologies are reviewed, including mobile LiDAR-based indoor point cloud map generation, point cloud-based architectural semantic segmentation, and indoor architectural element modelling, along with emerging research directions. Finally, existing benchmarking datasets and evaluation metrics for indoor Scan-to-BIM applications are summarized. This review serves as a comprehensive resource for researchers and practitioners in civil engineering, geomatics, and robotics, advancing the understanding and application of Scan-to-BIM.

在智能建筑中，扫描到bim是一项至关重要但具有挑战性的任务，它连接了现实世界的感知和虚拟重建。随着对高保真数字孪生的需求不断增长，其重要性日益明显。不同于之前的调查侧重于孤立的组件，本综述提供了完整的室内扫描到bim工作流的更新和跨学科概述，结合了最新的人工智能驱动的进展和可用的基准数据集。首先，明确了Scan-to-BIM与关键AEC模块之间的关系。接下来，定义问题的表述，然后讨论当前的挑战。然后，对基于移动激光雷达的室内点云地图生成、基于点云的建筑语义分割、室内建筑元素建模等常用设备和核心技术进行了综述，并提出了新兴的研究方向。最后，总结了现有的室内扫描到bim应用的基准数据集和评估指标。这篇综述为土木工程、地理信息学和机器人领域的研究人员和实践者提供了全面的资源，促进了对扫描到bim的理解和应用。

{"title":"Indoor scan-to-BIM automation: From mobile perception to 3D building modelling","authors":"Junqi Luo , Zexin Yang , Pengcheng Shi , Qin Ye","doi":"10.1016/j.autcon.2025.106731","DOIUrl":"10.1016/j.autcon.2025.106731","url":null,"abstract":"<div><div>Scan-to-BIM is a crucial yet challenging task in intelligent construction, bridging real-world perception and virtual reconstruction. With growing demands for high-fidelity digital twins, its importance is increasingly evident. Unlike prior surveys focusing on isolated components, this review offers an updated and cross-disciplinary overview of the complete indoor Scan-to-BIM workflow, incorporating recent AI-driven advances and available benchmark datasets. First, the relationship between Scan-to-BIM and key AEC modules is clarified. Next, the problem formulation is defined, followed by a discussion of current challenges. Then, commonly used devices and core technologies are reviewed, including mobile LiDAR-based indoor point cloud map generation, point cloud-based architectural semantic segmentation, and indoor architectural element modelling, along with emerging research directions. Finally, existing benchmarking datasets and evaluation metrics for indoor Scan-to-BIM applications are summarized. This review serves as a comprehensive resource for researchers and practitioners in civil engineering, geomatics, and robotics, advancing the understanding and application of Scan-to-BIM.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106731"},"PeriodicalIF":11.5,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145785133","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

No-reference image quality assessment via degraded-content inference for sewer inspection images 基于退化内容推理的无参考图像质量评价

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

Automation in Construction

Pub Date : 2025-12-17 DOI: 10.1016/j.autcon.2025.106727

Xingyu Chen, Zegen Wang, Jianghai He, Yaowen Ran, Mi Chen, Jiayi Hu, Chaoyue Li

Sewer inspection images captured via CCTV often experience significant quality degradation due to complex pipeline environments and the motion of inspection robots. To address the challenges in quality assessment and support subsequent enhancement or detection tasks, this paper proposes DI-IQA, a no-reference image quality assessment model tailored for sewer inspection scenarios. DI-IQA introduces a degraded content inference (DCI) module based on GANs, guided by dark channel prior and luminance consistency losses, and an image quality regression (IQR) module that integrates features from the generator, discriminator, degraded images, and discrepancy images. Besides, two datasets were constructed for training: the Degraded Sewer Inspection Image Dataset (5350 image pairs) for DCI module, and the Sewer Inspection IQA Dataset (1000 images) for IQR module. Experiments show DI-IQA achieves PLCC 0.934 and SROCC 0.931 on the Sewer Inspection IQA Dataset, demonstrating outstanding performance, and up to PLCC 0.976 and SROCC 0.973 on natural image benchmarks.

由于复杂的管道环境和检测机器人的运动，通过闭路电视捕获的下水道检查图像通常会出现严重的质量下降。为了解决质量评估中的挑战并支持后续的增强或检测任务，本文提出了针对下水道检测场景量身定制的无参考图像质量评估模型DI-IQA。DI-IQA引入了一个基于gan的退化内容推理（DCI）模块，该模块以暗通道先验和亮度一致性损失为指导，以及一个图像质量回归（IQR）模块，该模块集成了生成器、鉴别器、退化图像和差异图像的特征。此外，构建了两个数据集用于训练：DCI模块的退化下水道检查图像数据集（5350对图像）和IQR模块的下水道检查IQA数据集（1000张图像）。实验表明，DI-IQA在下水道检查IQA数据集上达到PLCC 0.934和SROCC 0.931，表现出优异的性能，在自然图像基准上达到PLCC 0.976和SROCC 0.973。

{"title":"No-reference image quality assessment via degraded-content inference for sewer inspection images","authors":"Xingyu Chen, Zegen Wang, Jianghai He, Yaowen Ran, Mi Chen, Jiayi Hu, Chaoyue Li","doi":"10.1016/j.autcon.2025.106727","DOIUrl":"10.1016/j.autcon.2025.106727","url":null,"abstract":"<div><div>Sewer inspection images captured via CCTV often experience significant quality degradation due to complex pipeline environments and the motion of inspection robots. To address the challenges in quality assessment and support subsequent enhancement or detection tasks, this paper proposes DI-IQA, a no-reference image quality assessment model tailored for sewer inspection scenarios. DI-IQA introduces a degraded content inference (DCI) module based on GANs, guided by dark channel prior and luminance consistency losses, and an image quality regression (IQR) module that integrates features from the generator, discriminator, degraded images, and discrepancy images. Besides, two datasets were constructed for training: the Degraded Sewer Inspection Image Dataset (5350 image pairs) for DCI module, and the Sewer Inspection IQA Dataset (1000 images) for IQR module. Experiments show DI-IQA achieves PLCC 0.934 and SROCC 0.931 on the Sewer Inspection IQA Dataset, demonstrating outstanding performance, and up to PLCC 0.976 and SROCC 0.973 on natural image benchmarks.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106727"},"PeriodicalIF":11.5,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145784695","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

Automating concrete production control with computer vision-based aggregate characterisation 基于计算机视觉的骨料表征的混凝土生产自动化控制

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

Automation in Construction

Pub Date : 2025-12-17 DOI: 10.1016/j.autcon.2025.106716

Max Coenen , Dries Beyer , Sahar Mohammadi , Max Meyer , Christian Heipke , Michael Haist

Concrete production is increasingly affected by fluctuations in the properties of natural and especially recycled aggregates. This paper investigates whether particle size distribution and material composition can be automatically determined from conveyor-belt image data during production. A backbone-agnostic deep-learning framework based on CNNs and Vision Transformers is applied to predict these properties and is extended with an additional branch that estimates aleatoric uncertainty directly from data via an uncertainty-aware loss formulation. The approach is evaluated on more than 80,000 real-world images collected using a camera-based sensor system installed on an operational concrete mixing plant. The results show accurate prediction of both grading curves and recycled material composition, providing a reliable basis for improved quality control for concrete producers and aggregate suppliers. The publicly available dataset enables further research and supports future progress towards fully automated, real-time quality assessment in concrete production.

混凝土生产日益受到天然骨料，特别是再生骨料性能波动的影响。本文研究了在生产过程中能否从输送带图像数据中自动确定物料粒度分布和成分。基于cnn和Vision transformer的骨干不可知深度学习框架被用于预测这些属性，并扩展了一个额外的分支，该分支通过不确定性感知损失公式直接从数据中估计任意不确定性。该方法通过安装在运行中的混凝土搅拌站上的基于摄像头的传感器系统收集的80,000多张真实图像进行了评估。结果表明，对级配曲线和再生料组成的预测均较为准确，为混凝土生产企业和骨料供应商提高质量控制水平提供了可靠依据。公开可用的数据集可以进一步研究，并支持未来在混凝土生产中实现全自动、实时质量评估的进展。

{"title":"Automating concrete production control with computer vision-based aggregate characterisation","authors":"Max Coenen , Dries Beyer , Sahar Mohammadi , Max Meyer , Christian Heipke , Michael Haist","doi":"10.1016/j.autcon.2025.106716","DOIUrl":"10.1016/j.autcon.2025.106716","url":null,"abstract":"<div><div>Concrete production is increasingly affected by fluctuations in the properties of natural and especially recycled aggregates. This paper investigates whether particle size distribution and material composition can be automatically determined from conveyor-belt image data during production. A backbone-agnostic deep-learning framework based on CNNs and Vision Transformers is applied to predict these properties and is extended with an additional branch that estimates aleatoric uncertainty directly from data via an uncertainty-aware loss formulation. The approach is evaluated on more than 80,000 real-world images collected using a camera-based sensor system installed on an operational concrete mixing plant. The results show accurate prediction of both grading curves and recycled material composition, providing a reliable basis for improved quality control for concrete producers and aggregate suppliers. The publicly available dataset enables further research and supports future progress towards fully automated, real-time quality assessment in concrete production.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106716"},"PeriodicalIF":11.5,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145787899","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

Small target worker detection based on improved YOLOv12 for large construction scenes 基于改进YOLOv12的大型施工场景小目标工人检测

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

Automation in Construction

Pub Date : 2025-12-16 DOI: 10.1016/j.autcon.2025.106722

Yufeng Yin , Xiaoyan Liu

Object detection technology has been widely used to improve the efficiency of industrial production in recent years. However, worker detection is a challenging task due to the small size of workers in large construction scenes and background interference that obscures worker features. To address such issues, a specialized small target worker dataset is constructed in large construction scenes to provide precise data support for model training and testing. In addition, a small target worker detection method is proposed: by introducing a strong attention strategy into the backbone network to enhance key feature extraction capabilities, improving the neck network structure to fuse multi-scale shallow features and prevent the loss of worker features, and focusing on the residuals of small target bounding boxes to improve localization precision and convergence speed. The results achieve state-of-the-art performance on three small target datasets, indicating the superiority and generalization of the proposed method for small target detection. This paper advances the perception of small workers at long distances in large construction scenes, providing professional data and theoretical support for safety early warnings.

近年来，目标检测技术被广泛应用于提高工业生产效率。然而，由于大型施工场景中工人的体积较小，背景干扰会模糊工人特征，因此工人检测是一项具有挑战性的任务。为了解决这些问题，在大型施工场景中构建专门的小目标工人数据集，为模型训练和测试提供精确的数据支持。此外，提出了一种小目标worker检测方法：通过在骨干网络中引入强关注策略，增强关键特征提取能力；改进颈部网络结构，融合多尺度浅层特征，防止worker特征丢失；关注小目标边界盒残差，提高定位精度和收敛速度。结果表明，该方法在三个小目标数据集上的检测性能达到了最先进的水平，表明了该方法在小目标检测中的优越性和泛化性。提出了大型施工场景中远距离小工的感知，为安全预警提供了专业数据和理论支持。

{"title":"Small target worker detection based on improved YOLOv12 for large construction scenes","authors":"Yufeng Yin , Xiaoyan Liu","doi":"10.1016/j.autcon.2025.106722","DOIUrl":"10.1016/j.autcon.2025.106722","url":null,"abstract":"<div><div>Object detection technology has been widely used to improve the efficiency of industrial production in recent years. However, worker detection is a challenging task due to the small size of workers in large construction scenes and background interference that obscures worker features. To address such issues, a specialized small target worker dataset is constructed in large construction scenes to provide precise data support for model training and testing. In addition, a small target worker detection method is proposed: by introducing a strong attention strategy into the backbone network to enhance key feature extraction capabilities, improving the neck network structure to fuse multi-scale shallow features and prevent the loss of worker features, and focusing on the residuals of small target bounding boxes to improve localization precision and convergence speed. The results achieve state-of-the-art performance on three small target datasets, indicating the superiority and generalization of the proposed method for small target detection. This paper advances the perception of small workers at long distances in large construction scenes, providing professional data and theoretical support for safety early warnings.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106722"},"PeriodicalIF":11.5,"publicationDate":"2025-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145787864","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

Frequency-aware crack segmentation network (FACS-net) and crack topology loss (CT-loss) for thin cracks 薄裂纹的频率感知裂纹分割网络（FACS-net）和裂纹拓扑损失（CT-loss）

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

Automation in Construction

Pub Date : 2025-12-15 DOI: 10.1016/j.autcon.2025.106719

Siheon Joo, Seokhwan Kim, Hongjo Kim

Structural crack analysis is vital for infrastructure safety, but existing segmentation models often miss fine cracks due to spectral bias in deep networks. This especially affects thin cracks, which are frequently underrepresented. This paper presents FACS-Net, a Frequency-Aware Crack Segmentation Network with Crack Topology Loss (CT-Loss), to mitigate spectral bias and enhance crack-specific representations. FACS-Net employs frequency-aware attention for decoding, while CT-Loss explicitly incorporates boundary accuracy and structural continuity into the learning objective. Given the high edge-to-area ratio of thin cracks, the proposed approach ensures accurate localization without sacrificing topological coherence. Evaluation on CrackVision12K shows that FACS-Net significantly improves detection of thin cracks (width

\leq

2 px), outperforming Hybrid-Segmentor by 0.306 IoU and 0.360 CTS. Overall, FACS-Net achieves state-of-the-art performance with 0.663 IoU and 0.651 CTS, demonstrating precise segmentation and robust structural preservation.

结构裂缝分析对基础设施安全至关重要，但现有的分割模型由于深度网络中的频谱偏差，往往会遗漏细微裂缝。这尤其影响到薄裂缝，而薄裂缝经常被低估。本文提出了FACS-Net，一种带有裂纹拓扑损失（CT-Loss）的频率感知裂纹分割网络，以减轻频谱偏差并增强裂纹特定表示。FACS-Net采用频率感知注意力进行解码，而CT-Loss明确地将边界精度和结构连续性纳入学习目标。考虑到薄裂纹的高边面积比，该方法在不牺牲拓扑相干性的情况下保证了精确的定位。在CrackVision12K上的评估表明，FACS-Net显著提高了薄裂纹（宽度≤2 px）的检测，比Hybrid-Segmentor高出0.306 IoU和0.360 CTS。总体而言，FACS-Net以0.663 IoU和0.651 CTS实现了最先进的性能，展示了精确的分割和强大的结构保存。

引用次数: 0

Data-informed Digital Twin for large-scale 3D printing in construction 数据为基础的数字孪生，用于建筑中的大规模3D打印

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

Automation in Construction

Pub Date : 2025-12-15 DOI: 10.1016/j.autcon.2025.106706

Lior Skoury , Ofer Asaf , Aaron Sprecher , Achim Menges , Thomas Wortmann

Large-scale 3D printing promises major benefits for the architecture, engineering and construction (AEC) industry but faces challenges including variable material behaviour, multi-machine coordination and dynamic process control. This paper presents a data-driven digital twin that couples real-time monitoring, predictive modelling and adaptive feedback. Machine parameters are continuously linked to material rheology and print outcomes, forming a virtual representation of the process. A clustering-based analysis classifies material mixtures and drives feedback control of printing parameters, improving stability, accuracy and efficiency. The digital twin is demonstrated on a large-scale setup with two machines operating in parallel and five services forming a closed feedback loop. Experiments show reduced material consumption by 7.5% and more consistent, higher-quality prints when using the predictive digital twin. These results indicate that integrating digital twins into large-scale 3D printing can support more robust, adaptive and scalable production.

大规模3D打印有望为建筑、工程和施工（AEC）行业带来重大好处，但也面临着包括可变材料性能、多机器协调和动态过程控制在内的挑战。本文提出了一种数据驱动的数字孪生模型，它结合了实时监测、预测建模和自适应反馈。机器参数不断与材料流变学和打印结果联系在一起，形成过程的虚拟表示。基于聚类的分析对材料混合物进行分类，并驱动打印参数的反馈控制，从而提高稳定性、准确性和效率。数字孪生在大型设置上进行了演示，两台机器并行运行，五个服务形成一个封闭的反馈回路。实验表明，当使用预测性数字孪生时，材料消耗减少了7.5%，打印效果更加一致，质量更高。这些结果表明，将数字孪生集成到大规模3D打印中可以支持更健壮、自适应和可扩展的生产。

引用次数: 0

Pixel-level image localization for updating 3D digital twins of dams using frequency convolutional networks 基于频率卷积网络的大坝三维数字孪生体的像素级图像定位

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

Automation in Construction

Pub Date : 2025-12-14 DOI: 10.1016/j.autcon.2025.106715

Hang Zhao , Vahidreza Gharehbaghi , Caroline Bennett , Rémy D. Lequesne , Jian Li

This paper presents PIL3D, an automated pixel-level image localization framework for maintaining up-to-date 3D digital twins of large-scale civil infrastructure, with a focus on dam structures. Unlike conventional 3D model updating approaches that require extensive manual data acquisition and labor-intensive processing, PIL3D automatically predicts the 3D coordinates of every pixel in an input image relative to an existing model, enabling fully automated dense pixel-to-point correspondences. Experimental validation on a real-world dam case demonstrates centimeter-level localization accuracy, significantly reducing manual intervention, data collection requirements, and computational demand. By integrating PIL3D into digital twin workflows, infrastructure inspection, monitoring, and maintenance can be streamlined into a continuous, automated process, advancing the state of automation in construction and asset management.

本文介绍了PIL3D，这是一个用于维护大型民用基础设施的最新3D数字孪生的自动化像素级图像定位框架，重点是大坝结构。传统的3D模型更新方法需要大量的人工数据采集和劳动密集型处理，与之不同的是，PIL3D可以自动预测输入图像中每个像素相对于现有模型的3D坐标，实现完全自动化的密集像素对点对应。在实际大坝案例上的实验验证证明了厘米级的定位精度，大大减少了人工干预、数据收集要求和计算需求。通过将PIL3D集成到数字孪生工作流程中，基础设施检查、监控和维护可以简化为一个连续的自动化过程，从而提高了建筑和资产管理的自动化水平。

引用次数: 0

Adaptive reinforcement learning algorithm for real-time energy optimization in building digital twins with heterogeneous IoT sensor networks 基于异构物联网传感器网络的数字孪生建筑实时能量优化自适应强化学习算法

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

Automation in Construction

Pub Date : 2025-12-13 DOI: 10.1016/j.autcon.2025.106714

Manea Almatared , Maher Abuhussain , Zahra Andleeb , Faizah Mohammed Bashir

Building operations contribute significantly to global carbon emissions, yet existing digital twins rely on static strategies that fail to adapt to dynamic conditions. This paper investigates whether an adaptive reinforcement learning framework with hierarchical transfer learning can optimize real-time energy use and comfort across heterogeneous buildings without extensive retraining. The paper develops and validates a proximal policy optimization controller integrated with a digital twin and 348 IoT sensors across three commercial buildings in a 14-month randomized crossover trial. The approach achieves 23.7 % and 14.9 % energy reductions compared to rule-based control and model predictive control, respectively, while maintaining 94.7 % comfort satisfaction and demonstrating 78 % transfer learning efficiency. These findings provide facility managers and grid operators with a scalable, hardware-validated approach that reduces operational costs and stabilizes demand response without compromising occupant comfort. Future work extends this hierarchical transfer framework to mixed-mode ventilation and district-level energy coordination to further enhance grid interactivity.

建筑运营对全球碳排放的贡献很大，但现有的数字孪生依赖于静态策略，无法适应动态条件。本文研究了具有分层迁移学习的自适应强化学习框架是否可以在不进行大量再培训的情况下优化异构建筑的实时能源使用和舒适度。本文在为期14个月的随机交叉试验中，在三座商业建筑中开发并验证了集成了数字孪生和348个物联网传感器的近端策略优化控制器。与基于规则的控制和模型预测控制相比，该方法分别降低了23.7%和14.9%的能量，同时保持了94.7%的舒适性满意度和78%的迁移学习效率。这些发现为设施管理人员和电网运营商提供了一种可扩展的、经过硬件验证的方法，可以降低运营成本，稳定需求响应，同时不影响居住者的舒适度。未来的工作将这种分层转移框架扩展到混合模式通风和区域一级的能源协调，以进一步增强电网的交互性。

{"title":"Adaptive reinforcement learning algorithm for real-time energy optimization in building digital twins with heterogeneous IoT sensor networks","authors":"Manea Almatared , Maher Abuhussain , Zahra Andleeb , Faizah Mohammed Bashir","doi":"10.1016/j.autcon.2025.106714","DOIUrl":"10.1016/j.autcon.2025.106714","url":null,"abstract":"<div><div>Building operations contribute significantly to global carbon emissions, yet existing digital twins rely on static strategies that fail to adapt to dynamic conditions. This paper investigates whether an adaptive reinforcement learning framework with hierarchical transfer learning can optimize real-time energy use and comfort across heterogeneous buildings without extensive retraining. The paper develops and validates a proximal policy optimization controller integrated with a digital twin and 348 IoT sensors across three commercial buildings in a 14-month randomized crossover trial. The approach achieves 23.7 % and 14.9 % energy reductions compared to rule-based control and model predictive control, respectively, while maintaining 94.7 % comfort satisfaction and demonstrating 78 % transfer learning efficiency. These findings provide facility managers and grid operators with a scalable, hardware-validated approach that reduces operational costs and stabilizes demand response without compromising occupant comfort. Future work extends this hierarchical transfer framework to mixed-mode ventilation and district-level energy coordination to further enhance grid interactivity.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106714"},"PeriodicalIF":11.5,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145759499","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 fiber optic sensors for monitoring cracks in civil infrastructure 用于监测民用基础设施裂缝的分布式光纤传感器

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

Automation in Construction

Pub Date : 2025-12-13 DOI: 10.1016/j.autcon.2025.106717

Shengju Xie , Yiming Liu , Farhad Ansari , Yi Bao

Distributed Fiber Optic Sensors (DFOS) have exhibited unique strengths in monitoring cracks, providing real-time, spatially-distributed data that indicate structural integrity and support automation in the construction, operation, maintenance, management, and recycling of structures or structural components. This paper systematically reviews the scientific principles, influencing factors, technical methods, and applications of DFOS, aiming to enhance understanding and promote the applications of DFOS in automated monitoring of infrastructure. Fiber optic cables, installation methods, and sensing technologies are reviewed to promote construction practices. The reviewed contents extend to advancements in machine learning and digital twinning technologies for real-time, automated data processing, analysis, and visualization of the presence, location, and severity of cracks. Major challenges and emerging opportunities of utilizing DFOS are discussed to facilitate future research. This paper advances the understanding, development, and engineering applications of DFOS for monitoring cracks toward intelligent digitalization and automation of civil infrastructure.

分布式光纤传感器（DFOS）在监测裂缝方面表现出独特的优势，提供实时、空间分布的数据，表明结构完整性，并支持结构或结构部件的施工、操作、维护、管理和回收的自动化。本文系统综述了DFOS的科学原理、影响因素、技术方法及其应用，旨在加深对DFOS在基础设施自动化监测中的认识，促进其应用。光纤电缆，安装方法和传感技术进行审查，以促进施工实践。回顾的内容扩展到机器学习和数字孪生技术的进展，用于实时，自动化数据处理，分析和可视化裂缝的存在，位置和严重程度。讨论了利用DFOS的主要挑战和新机遇，以促进未来的研究。本文对DFOS裂缝监测技术在民用基础设施智能化、数字化和自动化方面的应用进行了展望。

{"title":"Distributed fiber optic sensors for monitoring cracks in civil infrastructure","authors":"Shengju Xie , Yiming Liu , Farhad Ansari , Yi Bao","doi":"10.1016/j.autcon.2025.106717","DOIUrl":"10.1016/j.autcon.2025.106717","url":null,"abstract":"<div><div>Distributed Fiber Optic Sensors (DFOS) have exhibited unique strengths in monitoring cracks, providing real-time, spatially-distributed data that indicate structural integrity and support automation in the construction, operation, maintenance, management, and recycling of structures or structural components. This paper systematically reviews the scientific principles, influencing factors, technical methods, and applications of DFOS, aiming to enhance understanding and promote the applications of DFOS in automated monitoring of infrastructure. Fiber optic cables, installation methods, and sensing technologies are reviewed to promote construction practices. The reviewed contents extend to advancements in machine learning and digital twinning technologies for real-time, automated data processing, analysis, and visualization of the presence, location, and severity of cracks. Major challenges and emerging opportunities of utilizing DFOS are discussed to facilitate future research. This paper advances the understanding, development, and engineering applications of DFOS for monitoring cracks toward intelligent digitalization and automation of civil infrastructure.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106717"},"PeriodicalIF":11.5,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145759751","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

Low-cost pavement roughness evaluation using Inertial Measurement Unit (IMU)-Pulsed Coherent Radar (PCR) sensor fusion 基于惯性测量单元(IMU)-脉冲相干雷达（PCR）传感器融合的低成本路面粗糙度评估

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

Automation in Construction

Pub Date : 2025-12-12 DOI: 10.1016/j.autcon.2025.106713

Yazan Ibrahim Alatoom , Omar Smadi

Pavement roughness monitoring is critical for infrastructure management, but conventional automated profiling systems require substantial capital investments, making them inaccessible to limited-budget transportation agencies. This paper introduces a low-cost system combining Inertial Measurement Unit (IMU) and Pulsed Coherent Radar (PCR) technologies through sensor fusion. The approach captures vehicle dynamics via the IMU and pavement surface profiles via the PCR, using frequency-domain processing to isolate true pavement roughness from vehicle-induced motion. Comprehensive validation across twelve road segments and 216 test configurations demonstrates strong performance: MAPE below 9 % and R² exceeding 0.96 compared to reference measurements. A multi-stage optimization framework integrating Sequential Model-Based Optimization algorithm achieves 80–88 % accuracy improvements through systematic parameter calibration. The complete system costs $214 USD, providing a cost-effective solution for IRI estimation. A user-friendly graphical interface enables practical deployment by non-technical personnel. This approach enables broader adoption of automated pavement monitoring by agencies with limited budgets.

路面粗糙度监测对基础设施管理至关重要，但传统的自动分析系统需要大量的资本投资，这使得预算有限的运输机构无法使用。本文介绍了一种结合惯性测量单元（IMU）和脉冲相干雷达（PCR）技术的低成本传感器融合系统。该方法通过IMU捕获车辆动态，通过PCR捕获路面表面轮廓，并使用频域处理从车辆引起的运动中分离出真实的路面粗糙度。对12个路段和216种测试配置的综合验证显示出强大的性能：与参考测量值相比，MAPE低于9%，R2超过0.96。结合序列模型优化算法的多阶段优化框架，通过系统参数标定，精度提高80 ~ 88%。整套系统的成本为214美元，为IRI估计提供了一个经济有效的解决方案。用户友好的图形界面使非技术人员也能进行实际部署。这种方法使预算有限的机构能够更广泛地采用自动路面监测。

{"title":"Low-cost pavement roughness evaluation using Inertial Measurement Unit (IMU)-Pulsed Coherent Radar (PCR) sensor fusion","authors":"Yazan Ibrahim Alatoom , Omar Smadi","doi":"10.1016/j.autcon.2025.106713","DOIUrl":"10.1016/j.autcon.2025.106713","url":null,"abstract":"<div><div>Pavement roughness monitoring is critical for infrastructure management, but conventional automated profiling systems require substantial capital investments, making them inaccessible to limited-budget transportation agencies. This paper introduces a low-cost system combining Inertial Measurement Unit (IMU) and Pulsed Coherent Radar (PCR) technologies through sensor fusion. The approach captures vehicle dynamics via the IMU and pavement surface profiles via the PCR, using frequency-domain processing to isolate true pavement roughness from vehicle-induced motion. Comprehensive validation across twelve road segments and 216 test configurations demonstrates strong performance: MAPE below 9 % and R<sup>2</sup> exceeding 0.96 compared to reference measurements. A multi-stage optimization framework integrating Sequential Model-Based Optimization algorithm achieves 80–88 % accuracy improvements through systematic parameter calibration. The complete system costs $214 USD, providing a cost-effective solution for IRI estimation. A user-friendly graphical interface enables practical deployment by non-technical personnel. This approach enables broader adoption of automated pavement monitoring by agencies with limited budgets.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106713"},"PeriodicalIF":11.5,"publicationDate":"2025-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145732318","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

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Automation in Construction

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀