Automation in Construction最新文献_第9页

Weighted adaptive active transfer learning for imbalanced multi-object classification in construction site imagery 基于加权自适应主动迁移学习的建筑工地图像不平衡多目标分类

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-05-26 DOI: 10.1016/j.autcon.2025.106297

Karunakar Reddy Mannem , Samuel A. Prieto , Borja García de Soto , Fernando Bacao

{"title":"Weighted adaptive active transfer learning for imbalanced multi-object classification in construction site imagery","authors":"Karunakar Reddy Mannem , Samuel A. Prieto , Borja García de Soto , Fernando Bacao","doi":"10.1016/j.autcon.2025.106297","DOIUrl":"10.1016/j.autcon.2025.106297","url":null,"abstract":"<div><div>Construction site monitoring relies on robust image classification to enhance safety, track progress, and optimize resource management. However, the amount of clutter and the high cost of manual labeling pose significant challenges. This paper presents an approach to multi-object classification in construction sites using Adaptive Active Transfer Learning. The Weighted Active Transfer Learning with Adaptive Sampling (WATLAS) framework is introduced, where Transfer Learning is combined with weighted Active Learning to efficiently classify diverse objects. A pre-trained InceptionV3 architecture integrated with bidirectional long short-term memory (BiLSTM) layers is utilized, and superior performance is achieved through adaptive sampling techniques compared to traditional methods. WATLAS achieves 97 % accuracy on a comprehensive dataset of 9344 construction site images spanning 15 object categories and maintaining 90 % accuracy with only 5 % labeled data. By optimizing performance metrics, the framework demonstrates significant improvements over traditional methods, making it a scalable solution for construction site monitoring.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"176 ","pages":"Article 106297"},"PeriodicalIF":9.6,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144134788","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

Integrative AI and UAV-based visual recognition with metaheuristics for automated repair cost analysis of bridge structural deterioration 基于人工智能和无人机视觉识别的桥梁结构退化维修成本分析

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-05-24 DOI: 10.1016/j.autcon.2025.106273

Jui-Sheng Chou , Jhe-Shian Lien , Chi-Yun Liu

{"title":"Integrative AI and UAV-based visual recognition with metaheuristics for automated repair cost analysis of bridge structural deterioration","authors":"Jui-Sheng Chou , Jhe-Shian Lien , Chi-Yun Liu","doi":"10.1016/j.autcon.2025.106273","DOIUrl":"10.1016/j.autcon.2025.106273","url":null,"abstract":"<div><div>Aging bridges urgently need maintenance, as many exceed their lifespans. Traditional inspections are manual, time-consuming, costly, and error-prone. This has prompted a shift toward integrating advanced technologies to automate inspection processes and provide more efficient and accurate maintenance solutions. This paper introduces a multi-stage automated inspection system for bridge maintenance designed to classify bridge components and accurately assess the type and extent of deterioration. Unmanned aerial vehicles (UAVs) capture high-resolution images of bridge components, enabling comprehensive visual data collection without requiring manual access to challenging or hazardous areas. The inspection process employs the Vision Transformer (ViT) model for precise image classification, while You Only Look Once (YOLO) is used for instance segmentation. To further enhance the system's effectiveness, the Pilgrimage Walk Optimization (PWO)-Lite algorithm is applied to optimize the detection of deteriorated areas and estimate repair costs. This integration improves structural assessments, extends bridge longevity, and benefits bridge management agencies.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"176 ","pages":"Article 106273"},"PeriodicalIF":9.6,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144125010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Intelligent design of steel-concrete composite box girder bridge cross-sections based on generative models 基于生成模型的钢-混凝土组合箱梁桥截面智能设计

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-05-23 DOI: 10.1016/j.autcon.2025.106292

Yingjie Zhu , Liying Chen , Guorui Huang , Jiaji Wang , Si Fu , Yan Bai

{"title":"Intelligent design of steel-concrete composite box girder bridge cross-sections based on generative models","authors":"Yingjie Zhu , Liying Chen , Guorui Huang , Jiaji Wang , Si Fu , Yan Bai","doi":"10.1016/j.autcon.2025.106292","DOIUrl":"10.1016/j.autcon.2025.106292","url":null,"abstract":"<div><div>To enhance the efficiency and accuracy of composite box girder bridge design and achieve rapid and high-precision cross-section design, an effective intelligent algorithm is imperative. However, the development of intelligent design for steel-concrete composite box girder bridges is constrained by data scarcity and the performance of existing generative models. This paper introduces a pre-trained Vision Transformer as an Image Encoder (<em>E</em><sub>I</sub>) to enhance generative models for bridge design. Firstly, a dataset of 350 bridge designs is constructed for training and evaluation. Then, enhanced Condition-Feature models are developed and compared with fundamental generative models. The results show that the Condition-Feature Variational Autoencoder Generative Adversarial Network performs best, demonstrating the effectiveness of <em>E</em><sub>I</sub> in intelligent bridge design. This paper fills the gap in intelligent bridge design, offers valuable insights for future engineering research, and showcase the potential and application prospects of deep learning in bridge design.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"176 ","pages":"Article 106292"},"PeriodicalIF":9.6,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144116190","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

Design science research (DSR) in construction: Theoretical conceptualization of practice and practical realization of theory 建设中的设计科学研究：实践的理论概念化与理论的实践实现

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-05-23 DOI: 10.1016/j.autcon.2025.106298

Ningshuang Zeng , Luxuan Han , Yan Liu , Jingfeng Yuan , Qiming Li

引用次数: 0

Deep learning for automated crack quantification with distributed fiber optic sensing: Addressing strain overlap and interface nonlinearity 基于分布式光纤传感的深度学习自动裂纹量化：处理应变重叠和界面非线性

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-05-22 DOI: 10.1016/j.autcon.2025.106280

Lu Xuanyi, He Sudao, Zhang Shenghan

{"title":"Deep learning for automated crack quantification with distributed fiber optic sensing: Addressing strain overlap and interface nonlinearity","authors":"Lu Xuanyi, He Sudao, Zhang Shenghan","doi":"10.1016/j.autcon.2025.106280","DOIUrl":"10.1016/j.autcon.2025.106280","url":null,"abstract":"<div><div>Distributed fiber optic sensors (DFOS) hold significant potential for automation in construction, particularly in identifying and quantifying cracks through strain distributions. However, interpreting these distributions is challenging, especially when strain peaks overlap and there is nonlinearity in the cable-structure interface. To address this problem, this paper develops a deep learning model, termed Physical-Constrained FiberNet (PC-FiberNet), to intelligently interpret strain distributions under multiple crack scenarios. PC-FiberNet accurately identifies the location and width of each crack while simultaneously estimating the material and interfacial parameters of the cable. These parameters facilitate the development of numerical models. To enhance the robustness and generalizability of the proposed model, a transfer learning approach is employed. The performance of PC-FiberNet is validated through extensive tests and simulations. This paper enhances the application of DFOS to structural health monitoring, offering an effective approach to crack quantification in a multi-cracking scenario.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"176 ","pages":"Article 106280"},"PeriodicalIF":9.6,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144116487","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

Vehicle intrusion detection in highway work zones using inertial sensors and lightweight deep learning 基于惯性传感器和轻量级深度学习的高速公路工作区域车辆入侵检测

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-05-22 DOI: 10.1016/j.autcon.2025.106291

Moein Younesi Heravi , Ayenew Yihune Demeke , Israt Sharmin Dola , Youjin Jang , Inbae Jeong , Chau Le

{"title":"Vehicle intrusion detection in highway work zones using inertial sensors and lightweight deep learning","authors":"Moein Younesi Heravi , Ayenew Yihune Demeke , Israt Sharmin Dola , Youjin Jang , Inbae Jeong , Chau Le","doi":"10.1016/j.autcon.2025.106291","DOIUrl":"10.1016/j.autcon.2025.106291","url":null,"abstract":"<div><div>Highway work zones are prone to intrusion events that threaten workers' safety and disrupt operations. Existing intrusion detection systems often produce high false alarms, causing alarm fatigue and reduced responsiveness. To address this, a data-driven intrusion detection method is proposed to distinguish real vehicle intrusions from non-hazardous events using inertial measurement unit (IMU) sensors attached to traffic cones. Acceleration and angular velocity data were collected through field experiments involving vehicle collisions, manual handling, and wind displacement. After preprocessing and data augmentation, a lightweight Long Short-Term Memory (LSTM) model was trained and optimized for real-time performance on edge devices. Evaluation yielded a 96 % accuracy and a 97 % recall for actual intrusions. Resultant acceleration and angular velocity are recognized as key features. This cost-effective, scalable solution enhances safety by effectively identifying actual hazards, minimizing false alarms, and mitigating the negative impact of alarm fatigue in highway work zones.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"176 ","pages":"Article 106291"},"PeriodicalIF":9.6,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144116188","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

Optimizing asphalt compaction: Vibratory roller amplitude and predictive modeling 优化沥青压实：振动压路机振幅和预测模型

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-05-20 DOI: 10.1016/j.autcon.2025.106278

Kamal Nasir Ahmad , Xianhua Chen , Adnan Khan , Qing Lu

{"title":"Optimizing asphalt compaction: Vibratory roller amplitude and predictive modeling","authors":"Kamal Nasir Ahmad , Xianhua Chen , Adnan Khan , Qing Lu","doi":"10.1016/j.autcon.2025.106278","DOIUrl":"10.1016/j.autcon.2025.106278","url":null,"abstract":"<div><div>Effective compaction quality significantly impacts pavement durability and performance, with uneven compaction often resulting from traditional empirical approaches that adjust vibration modes and rolling periods. This paper investigates the effects of vibratory roller amplitude optimization on asphalt pavement compaction and develops predictive models for intelligent compaction (IC) parameters and in-place density using machine learning (ML) methods. Results indicate that higher-amplitude vibration passes yielded higher average intelligent compaction measurement values (ICMVs) and in-place density. Predictive models were developed using XGBoost and CatBoost, optimized through the Bayesian Optimization Algorithm (BOA). Among them, the XGBoost models achieved the best performance in predicting ICMVs and non-nuclear density (NND) values, demonstrating high accuracy (R<sup>2</sup> = 0.9362, 0.9916) and low error (RMSE = 4.5678, 1.1934) during validation. These findings have significant implications for compaction quality control and provide a foundation for future research to enhance predictive models for ICMVs and NND under diverse construction conditions.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"176 ","pages":"Article 106278"},"PeriodicalIF":9.6,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144099101","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

Augmented reality and ultrasonic sensor-based tool for rebar inspection on construction sites 基于增强现实和超声传感器的建筑工地钢筋检测工具

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-05-20 DOI: 10.1016/j.autcon.2025.106288

Alexis Toledo Bórquez , Felipe Muñoz La Rivera , Rodrigo F. Herrera , Javier Mora Serrano

{"title":"Augmented reality and ultrasonic sensor-based tool for rebar inspection on construction sites","authors":"Alexis Toledo Bórquez , Felipe Muñoz La Rivera , Rodrigo F. Herrera , Javier Mora Serrano","doi":"10.1016/j.autcon.2025.106288","DOIUrl":"10.1016/j.autcon.2025.106288","url":null,"abstract":"<div><div>The traditional inspection of reinforcing steel bars (rebar) in construction often suffers from inaccuracies, inefficiencies, and challenges posed by environmental factors, leading to project delays and increased costs. This paper presents a method for improving rebar inspection by integrating Augmented Reality (AR), Internet of Things (IoT) technologies, and Building Information Modeling (BIM). The paper introduces an AR-based tool equipped with low-cost ultrasonic sensors, which automates the rebar counting process and provides real-time data visualization. The tool addresses key limitations in traditional inspection workflows by reducing human error and enhancing data reliability. Experimental results from conceptual on-site tests demonstrate significant improvements in inspection accuracy, workflow efficiency, and user engagement. This approach offers a cost-effective, scalable solution adaptable to various project sizes, contributing to the advancement of digital technologies in the construction industry and accelerating the adoption of Construction 4.0.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"176 ","pages":"Article 106288"},"PeriodicalIF":9.6,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144088884","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

Optimizing best-fit algorithms for complex cross-vault geometries in HBIM generation using point cloud data 使用点云数据在HBIM生成中优化复杂交叉拱顶几何的最佳拟合算法

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-05-19 DOI: 10.1016/j.autcon.2025.106274

Juan Moyano , Luigi Barazzetti , Mattia Previtali , Juan E. Nieto-Julián

{"title":"Optimizing best-fit algorithms for complex cross-vault geometries in HBIM generation using point cloud data","authors":"Juan Moyano , Luigi Barazzetti , Mattia Previtali , Juan E. Nieto-Julián","doi":"10.1016/j.autcon.2025.106274","DOIUrl":"10.1016/j.autcon.2025.106274","url":null,"abstract":"<div><div>Builders of the past naturally adjusted geometries to fit existing surfaces. Today, replicating these forms during the 3D digitization of historical elements poses a significant challenge for BIM operators. Achieving a precise fit for the geometry of a cross-vault facilitates the implementation of the Scan-to-BIM approach for repetitive objects with significant variations in their geometry. This paper introduces a descriptive mathematical model that provides BIM experts with a foundation for creating multiple geometric replicas. The approach employs clustering algorithms, optimization techniques, frequency analysis via Fourier transform, and ordinary Kriging interpolation. Two parametric BIM models are developed: one simple model defined by five variables and another more complex model defined by nine geometric variables. Both models are validated against the segmented point cloud. The results indicate interpolated standard deviations of ±0.0085 m for the simple vault and ± 0.0066 m for the complex vault. The difference between using the simple and complex vault models is ±0.0082 m, representing a variation of 0.01 % in the values of the five optimized parameters.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"176 ","pages":"Article 106274"},"PeriodicalIF":9.6,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084525","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

Hybrid data generation and deep learning for GPR-based reconstruction of robotic-built underground structures 基于gpr的机器人地下结构重建的混合数据生成和深度学习

IF 9.6 1区工程技术

Automation in Construction Pub Date : 2025-05-16 DOI: 10.1016/j.autcon.2025.106275

Haibing Wu , Brian Sheil

{"title":"Hybrid data generation and deep learning for GPR-based reconstruction of robotic-built underground structures","authors":"Haibing Wu , Brian Sheil","doi":"10.1016/j.autcon.2025.106275","DOIUrl":"10.1016/j.autcon.2025.106275","url":null,"abstract":"<div><div>There is substantial potential for future underground construction operations to be performed by autonomous robots. This paper proposes a 360-degree digital reconstruction framework for robotic-built underground structures using in-pipe rotating ground penetrating radar (GPR). Unlike conventional ground-level applications, placing GPR inside pipes significantly reduces signal attenuation by shortening the distance to the target, enhancing imaging accuracy. To overcome limited data, this paper proposes a high-fidelity in-pipe GPR generator that combines calibrated synthetic data with real-world pipe reflections, clutter, and random noises. Besides, a ‘stochastic-ellipse-union’ method models robot-constructed structures mathematically, ensuring dataset diversity. Moreover, a optimized 2D digital antenna model, calibrated to 97 % accuracy using a genetic algorithm, reduces radargram generation time by 99.2 % compared to traditional 3D methods. Benchmark tests among seven DL models identified ResNet101-enhanced U-Net as optimal, achieving an intersection-over-union score of 0.937, proving the effectiveness of the framework in reconstructing robotic-built underground structures.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"176 ","pages":"Article 106275"},"PeriodicalIF":9.6,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144066116","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