Automation in Construction最新文献_第5页

Automatic prediction of railway ballast layer thickness using graph neural network based on GPR reflection signals 基于探地雷达反射信号的图神经网络铁路道砟层厚度自动预测

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-06-16 DOI: 10.1016/j.autcon.2025.106318

Zhan Yang , Rongshan Yang , Xiaolong Liang , Shiqiang Liang , Melese Tibebu Tegegne , Qiang Zhang , Yong Liu

{"title":"Automatic prediction of railway ballast layer thickness using graph neural network based on GPR reflection signals","authors":"Zhan Yang , Rongshan Yang , Xiaolong Liang , Shiqiang Liang , Melese Tibebu Tegegne , Qiang Zhang , Yong Liu","doi":"10.1016/j.autcon.2025.106318","DOIUrl":"10.1016/j.autcon.2025.106318","url":null,"abstract":"<div><div>Ground-Penetrating Radar (GPR) is widely employed for detecting the thickness of railway ballast layer. However, the complexity of the GPR data often requires manual interpretation by experts, which limits the efficiency of large-scale inspections. To address this challenge, this paper proposes a graph neural network-based method for automatic ballast layer thickness prediction. This method leverages Temporal Convolutional Networks (TCNs) to extract temporal patterns from the GPR A-scans and employs Graph Convolutional Networks (GCNs) with a self-adaptive adjacency matrix to dynamically learn and refine the spatial correlations across multiple A-scans. The proposed method was validated using a combined dataset of simulated and field data, and further tested through on-site applications. Experimental results show that the method outperforms four baseline models in prediction accuracy while maintaining high inference efficiency. In on-site tests, the average absolute prediction errors of Two-Way Travel Time (TWTT) and thickness were 0.25 % and 3.06 %, respectively. These findings demonstrate the effectiveness, efficiency, and potential scalability of the proposed method for railway ballast layer thickness detection.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"177 ","pages":"Article 106318"},"PeriodicalIF":9.6,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144290718","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

Multi-domain transfer generation of cavity defect data in asphalt pavements using 3D GPR and 3D forward modeling 基于三维探地雷达和三维正演建模的沥青路面空腔缺陷多域传输生成

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-06-16 DOI: 10.1016/j.autcon.2025.106345

Peng Wang , Lei Zhang , Yiqiu Tan , Zhen Leng

{"title":"Multi-domain transfer generation of cavity defect data in asphalt pavements using 3D GPR and 3D forward modeling","authors":"Peng Wang , Lei Zhang , Yiqiu Tan , Zhen Leng","doi":"10.1016/j.autcon.2025.106345","DOIUrl":"10.1016/j.autcon.2025.106345","url":null,"abstract":"<div><div>The paucity of GPR data pertaining to cavity defects significantly impedes the advancement of intelligent nondestructive testing methods in pavement engineering. This paper illustrates that heterogeneous forward models of cavity defects, constructed using pseudo-random generation algorithms, exhibit remarkable accuracy in mimicking the electromagnetic responses within asphalt pavement structures. A unified multi-domain transfer learning framework, employing StarGAN, facilitates the cross-domain generation of data representing cavity defects in asphalt pavements. The model effectively suppresses clutter interference, thereby preserving cavity defect characteristics in heterogeneous forward images, while adeptly synthesizing signals conforming to heterogeneous structural properties in homogeneous forward images. Quantitative assessments reveal an exceptionally high degree of similarity between the synthetically generated data and actual samples (LPIPS≈0). The measured cavity defect features generated by StarGAN exhibit high physical regularity and morphological diversity compared to real samples (LPIPS<0.1). This paper introduces a novel approach to data augmentation for GPR applications in asphalt roads.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"177 ","pages":"Article 106345"},"PeriodicalIF":9.6,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144290720","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

Unsupervised anomaly segmentation model for rail damage based on image-inpainting and cold diffusion 基于图像预处理和冷扩散的钢轨损伤无监督异常分割模型

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-06-16 DOI: 10.1016/j.autcon.2025.106342

Chengjia Han, Yiqing Dong, Maggie Y. Gao, Liwei Dong, Yaowen Yang

{"title":"Unsupervised anomaly segmentation model for rail damage based on image-inpainting and cold diffusion","authors":"Chengjia Han, Yiqing Dong, Maggie Y. Gao, Liwei Dong, Yaowen Yang","doi":"10.1016/j.autcon.2025.106342","DOIUrl":"10.1016/j.autcon.2025.106342","url":null,"abstract":"<div><div>Ensuring structural health of rail tracks is critical for safe train operations. While deep learning-based vision models are widely used for rail damage detection, supervised methods suffer from limited generalization due to scarce and diverse annotated data. Unsupervised models often experience missed detections and false positives when handling complex and variable rail background textures, as well as rail damage with significant intra-class variability. To address these limitations, this paper proposes an unsupervised pixel-level rail damage segmentation model based on a cold diffusion framework, called InpRailDiffusion. It introduces inpainting-based noise and uses a Mamba-enhanced, time-conditioned U-Net for progressive noise removal. Damage segmentation is achieved by analyzing pixel-wise differences between generated and original images with adaptive thresholding. A multi-scale masking strategy fuses reconstruction features at various spatial resolutions, reducing false positives and missed detections. Evaluated on RSDDs-I and RSDDs-II, InpRailDiffusion outperformed state-of-the-art baselines with MIoU/F1-Scores of 0.864/0.844 and 0.845/0.814, respectively.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"177 ","pages":"Article 106342"},"PeriodicalIF":9.6,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144290719","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

Cost-effective optimization system for automated asphalt pavement maintenance 高性价比的自动化沥青路面养护优化系统

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-06-16 DOI: 10.1016/j.autcon.2025.106333

Zhou Zidong, Yu Xin, Gao Yuchao, Liu Weizheng

引用次数: 0

2D–3D fusion approach for improved point cloud segmentation 改进点云分割的2D-3D融合方法

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-06-15 DOI: 10.1016/j.autcon.2025.106336

Hongzhe Yue , Qian Wang , Mingyu Zhang , Yutong Xue , Liang Lu

引用次数: 0

Model-based planning of complex 3D laser scanning campaigns for bridge digitisation 基于模型的桥梁数字化复杂三维激光扫描运动规划

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-06-14 DOI: 10.1016/j.autcon.2025.106289

Kwasi Nyarko Poku-Agyemang, Alexander Reiterer

{"title":"Model-based planning of complex 3D laser scanning campaigns for bridge digitisation","authors":"Kwasi Nyarko Poku-Agyemang, Alexander Reiterer","doi":"10.1016/j.autcon.2025.106289","DOIUrl":"10.1016/j.autcon.2025.106289","url":null,"abstract":"<div><div>Large, complex structures like bridges are essential infrastructure, expensive to design, construct, monitor, and maintain. The digitisation of bridges has advanced in areas such as structural health monitoring, maintenance, load simulation, and bridge information modelling. 3D laser scanning captures these structures in digital space, and recent advancements have improved the creation of realistic digital twins. These technological improvements necessitate an optimised planning process for scanning campaigns, aiming to maximise coverage efficiently and reduce reliance on subjective human expertise. This paper introduces a model-based approach for planning-for-scanning (P4S), which devises efficient bridge scanning strategies using single or multiple laser scanners. Utilising existing bridge information, such as architectural plans and scanner properties, the algorithm estimates positions and trajectories to capture high-quality point clouds. Tested on the Gaskugel Bridge over the Dreisam River in Freiburg, Germany, the approach demonstrated enhanced data quality and efficiency compared to traditional methods relying on human expertise.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"177 ","pages":"Article 106289"},"PeriodicalIF":9.6,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144280212","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

Semantic interoperability on IoT: Aligning IFC and Smart Application Reference (SAREF) sensor data models 物联网的语义互操作性：调整IFC和智能应用参考（SAREF）传感器数据模型

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-06-14 DOI: 10.1016/j.autcon.2025.106328

Ebere Donatus Okonta , Farzad Rahimian , Vladimir Vukovic , Sergio Rodriguez

{"title":"Semantic interoperability on IoT: Aligning IFC and Smart Application Reference (SAREF) sensor data models","authors":"Ebere Donatus Okonta , Farzad Rahimian , Vladimir Vukovic , Sergio Rodriguez","doi":"10.1016/j.autcon.2025.106328","DOIUrl":"10.1016/j.autcon.2025.106328","url":null,"abstract":"<div><div>This paper proposes extending the Smart Application Reference (SAREF) ontology to enable sensor modelling based on the Industry Foundation Classes (IFC) standard, enhancing semantic interoperability between IoT (Internet of Things) and Building Information Modelling (BIM). The paper introduces the Information Assigned to Device Based Ontology Matching approach (IADOM) to align saref:Sensor and IfcSensor data models. Leveraging RDF (Resource Definition Framework) Semantic Web technology, the research modelled and visualised sensor data models in the Protégé software environment, exploring basic information that defined the sensor, including class, properties, relations, attributes, geometry, and interaction. Ontology results indicate property and interaction similarities and differences in saref:Sensor and IfcSensor. The extended ontology provides a standardised and interoperable representation of sensor data and their relationships within BIM and proves that SAREF ontology extension can enhance semantic interoperability between IoT devices and BIM systems, facilitating efficient data exchange, enabling advanced analytics and decision-making processes in smart buildings.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"177 ","pages":"Article 106328"},"PeriodicalIF":9.6,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144280213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Automated inference of context-specific hazards in construction using BIM and Ontology 使用BIM和本体对建筑中特定环境的危险进行自动推断

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-06-14 DOI: 10.1016/j.autcon.2025.106338

Seongyeon Hwang , Seoyoung Jung , Seulki Lee

引用次数: 0

Multi-LOD generative approach for multi-objective sustainability optimization from the early stages of building design 建筑设计早期多目标可持续性优化的多lod生成方法

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-06-13 DOI: 10.1016/j.autcon.2025.106326

Catherine Bouillon , Benjamin Cohen Boulakia , Karim Beddiar , Yves Jaboin , Fabrice Duval

{"title":"Multi-LOD generative approach for multi-objective sustainability optimization from the early stages of building design","authors":"Catherine Bouillon , Benjamin Cohen Boulakia , Karim Beddiar , Yves Jaboin , Fabrice Duval","doi":"10.1016/j.autcon.2025.106326","DOIUrl":"10.1016/j.autcon.2025.106326","url":null,"abstract":"<div><div>Given the urgency of reducing the buildings' environmental impact, this article focuses on optimizing sustainability from the earliest design phases, when decisions have the greatest influence. To address the challenges posed by the coarse granularity of digital models during the sketching phase and the often-conflicting nature of sustainability criteria, a generative workflow is proposed. This workflow, based on a multi-Level of Detail (LOD) framework, enables the evaluation and tracking of multiple sustainability criteria throughout the design iterations. This systemic methodology integrates automated functional spatial-planning, hierarchical segmentation of construction solutions, and systematic exploration of Pareto-optimal alternatives for bi-objective optimization. The framework is validated during the sketch phase using life-cycle cost and global warming potential, across eight real-world office-building case studies. Feedback from ten construction experts confirms the Proof-of-Concept's effectiveness in supporting both retrospective and prospective decision-making, underscoring its potential to advance sustainable design practices in the Architecture, Engineering, and Construction sector.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"177 ","pages":"Article 106326"},"PeriodicalIF":9.6,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144271684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Automated detection of complex construction scenes using a lightweight transformer-based method 基于轻量级变压器的复杂施工场景自动检测方法

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-06-13 DOI: 10.1016/j.autcon.2025.106330

Hongru Xiao , Bin Yang , Yujie Lu , Wenshuo Chen , Songning Lai , Biaoli Gao

{"title":"Automated detection of complex construction scenes using a lightweight transformer-based method","authors":"Hongru Xiao , Bin Yang , Yujie Lu , Wenshuo Chen , Songning Lai , Biaoli Gao","doi":"10.1016/j.autcon.2025.106330","DOIUrl":"10.1016/j.autcon.2025.106330","url":null,"abstract":"<div><div>Accurate and real-time object detection in complex construction scenes from multiple viewpoints plays a crucial role in effective project management. However, this task remains limited by boundary information sharing and scene sensitivity inherent in deep features. To investigate the deep features in construction scenes and analyze method performance, SODA and VisDrone datasets, mean Average Precision (mAP) series metrics, visual inspection, Grad-CAM, and ablation studies are utilized. This paper proposes a lightweight Transformer-based detection framework named Complex Construction Scenes Transformer (CCS-TR), which integrates with a Scale-Isolate Fusion Attention (SIFA) mechanism and an Instructive Contrastive Learning (ICL) strategy. Evaluation results demonstrate that CCS-TR achieves a 5.1 %–8.8 % improvement in detection accuracy while maintaining lower computational costs, making it suitable for real-time on-site detection. Future work will address detection in interacting complex scenes and develop multi-modal collaboration strategies for extreme lighting.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"177 ","pages":"Article 106330"},"PeriodicalIF":9.6,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272280","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