Automation in Construction最新文献

英文中文

Depth-aware detection of hanging objects for state reasoning in construction sites 建筑工地悬吊物状态推理的深度感知检测

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

Automation in Construction

Pub Date : 2026-01-06 DOI: 10.1016/j.autcon.2025.106757

Gilsu Jeong , Joonseok Lee , Moonseo Park , Changbum R. Ahn

Hanging objects, referring to materials or components lifted and transported by tower cranes, require continuous monitoring, as undetected suspended loads can cause severe accidents and disrupt construction workflows. However, conventional vision-based detection models struggle to recognize the hanging state due to visual ambiguity and reliance on appearance without spatial reasoning. To address this challenge, this paper proposes a framework that leverages monocular depth information to infer the hanging state more effectively. The approach incorporates a depth-aware feature module, which captures depth differences and spatial context, and a segmentation-guided depth preprocessing that refines object boundaries. Integrated into baseline detectors, the proposed method significantly improves detection accuracy and reduces false positives in complex scenes. Experimental results demonstrate the value of depth-aware modeling and establish a foundation for reliable, state-aware detection of hanging objects, enabling automated monitoring and supporting more efficient management of lifting operations and site workflows in construction environments.

悬吊物是指由塔吊吊起和运输的材料或部件，需要持续监控，因为未被发现的悬吊载荷可能导致严重事故并扰乱施工流程。然而，传统的基于视觉的检测模型由于视觉模糊和依赖于外观而没有空间推理而难以识别悬挂状态。为了解决这一挑战，本文提出了一个利用单目深度信息更有效地推断悬挂状态的框架。该方法结合了一个深度感知特征模块，用于捕获深度差异和空间背景，以及一个分割引导的深度预处理，用于细化对象边界。该方法与基线检测器相结合，显著提高了复杂场景下的检测精度，减少了误报。实验结果证明了深度感知建模的价值，并为可靠的、状态感知的悬挂物体检测奠定了基础，实现了自动化监控，并支持了建筑环境中起重作业和现场工作流的更有效管理。

{"title":"Depth-aware detection of hanging objects for state reasoning in construction sites","authors":"Gilsu Jeong , Joonseok Lee , Moonseo Park , Changbum R. Ahn","doi":"10.1016/j.autcon.2025.106757","DOIUrl":"10.1016/j.autcon.2025.106757","url":null,"abstract":"<div><div>Hanging objects, referring to materials or components lifted and transported by tower cranes, require continuous monitoring, as undetected suspended loads can cause severe accidents and disrupt construction workflows. However, conventional vision-based detection models struggle to recognize the hanging state due to visual ambiguity and reliance on appearance without spatial reasoning. To address this challenge, this paper proposes a framework that leverages monocular depth information to infer the hanging state more effectively. The approach incorporates a depth-aware feature module, which captures depth differences and spatial context, and a segmentation-guided depth preprocessing that refines object boundaries. Integrated into baseline detectors, the proposed method significantly improves detection accuracy and reduces false positives in complex scenes. Experimental results demonstrate the value of depth-aware modeling and establish a foundation for reliable, state-aware detection of hanging objects, enabling automated monitoring and supporting more efficient management of lifting operations and site workflows in construction environments.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106757"},"PeriodicalIF":11.5,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145921014","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

Retrieval optimization for construction documents in low-resource languages using contrastive sentence generation and matryoshka representation learning 基于对比句生成和套娃表示学习的低资源语言建筑文档检索优化

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

Automation in Construction

Pub Date : 2026-01-06 DOI: 10.1016/j.autcon.2025.106749

Kichang Choi , Minwoo Jeong , Younga Shin , Jong won Ma , Kinam Kim , Hongjo Kim

The Retrieval-Augmented Generation (RAG) framework struggles in low resource languages like Korean, particularly in specialized domains such as construction. This paper proposes RAGO-CONSTRUCT, a retrieval optimization methodology for existing RAG systems that integrate Contrastive Sentence Generation (CSG) and Sentence Block Embedding (SBE) with Matryoshka Representation Learning (MRL) to improve retrieval accuracy in Korean construction documents. CSG enables automated dataset generation using local LLMs, while SBE optimizes document chunking strategies to align with embedding model strengths. An 8986-pair training dataset was generated using local LLMs without requiring manual annotation, enabling fine-tuning with Multiple Negative Ranking Loss and Matryoshka Representation Learning. RAGO-CONSTRUCT demonstrated model-agnostic effectiveness across different embedding architectures, with multilingual-e5-large achieving 53.7 % overall accuracy, outperforming OpenAI's text-embedding-3-large by 12.35 % point. The methodology showed consistent performance improvements regardless of the base embedding model used. This approach addresses critical challenges in domain-specific RAG applications for low-resource languages.

检索-增强生成（RAG）框架在韩语等资源匮乏的语言中举步维艰，尤其是在建筑等专门领域。本文提出了一种针对现有RAG系统的检索优化方法——RAGO-CONSTRUCT，该方法将对比句生成（CSG）、句子块嵌入（SBE）和套表表示学习（MRL）相结合，以提高韩语建筑文档的检索精度。CSG支持使用本地llm自动生成数据集，而SBE则优化文档分块策略，以配合嵌入模型的优势。使用本地llm生成8986对训练数据集，无需手动注释，可以使用多重负排名损失和套表表示学习进行微调。RAGO-CONSTRUCT在不同的嵌入架构中展示了模型无关的有效性，multilingual-e5-large的总体准确率达到53.7%，比OpenAI的文本嵌入-3-large高出12.35个百分点。无论使用何种基本嵌入模型，该方法都显示出一致的性能改进。这种方法解决了针对低资源语言的特定领域的RAG应用程序中的关键挑战。

{"title":"Retrieval optimization for construction documents in low-resource languages using contrastive sentence generation and matryoshka representation learning","authors":"Kichang Choi , Minwoo Jeong , Younga Shin , Jong won Ma , Kinam Kim , Hongjo Kim","doi":"10.1016/j.autcon.2025.106749","DOIUrl":"10.1016/j.autcon.2025.106749","url":null,"abstract":"<div><div>The Retrieval-Augmented Generation (RAG) framework struggles in low resource languages like Korean, particularly in specialized domains such as construction. This paper proposes RAGO-CONSTRUCT, a retrieval optimization methodology for existing RAG systems that integrate Contrastive Sentence Generation (CSG) and Sentence Block Embedding (SBE) with Matryoshka Representation Learning (MRL) to improve retrieval accuracy in Korean construction documents. CSG enables automated dataset generation using local LLMs, while SBE optimizes document chunking strategies to align with embedding model strengths. An 8986-pair training dataset was generated using local LLMs without requiring manual annotation, enabling fine-tuning with Multiple Negative Ranking Loss and Matryoshka Representation Learning. RAGO-CONSTRUCT demonstrated model-agnostic effectiveness across different embedding architectures, with multilingual-e5-large achieving 53.7 % overall accuracy, outperforming OpenAI's text-embedding-3-large by 12.35 % point. The methodology showed consistent performance improvements regardless of the base embedding model used. This approach addresses critical challenges in domain-specific RAG applications for low-resource languages.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106749"},"PeriodicalIF":11.5,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145920967","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 scan-to-BIM for construction digital transformation: Conceptual framework, processing methods and best-practice guidelines 用于建筑数字化转型的自动扫描到bim：概念框架、处理方法和最佳实践指南

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

Automation in Construction

Pub Date : 2026-01-06 DOI: 10.1016/j.autcon.2025.106755

Ke You , Ke Chen , Fan Xue

The global Architecture, Engineering, and Construction (AEC) industry has witnessed surging demand for Construction Digital Transformation (CDT) over the past decade. Scan-to-BIM delivers accurate as-is conditions and reconstructs detailed BIM for diverse CDT applications. Researchers have proposed automated scan-to-BIM using algorithms and AI to minimize labor demands, but a comprehensive review with systematic guidelines is lacking. This paper presents a conceptual model of scan-to-BIM processes and reviews development patterns and trends based on 58 cases. Based on the model, this paper offers a four-step guideline for AEC practitioners to adopt automated scan-to-BIM effectively. The contribution of this paper is three-fold. First, the conceptual model offers a comprehensive and simplified overview of scan-to-BIM processes for beginners. Secondly, trends emerge, e.g., transformation from rigid rules to AI methods. Thirdly, the best-practice guidelines empower AEC practitioners to maximize scan-to-BIM advantages tailored to their needs.

在过去的十年中，全球建筑、工程和建筑（AEC）行业见证了对建筑数字化转型（CDT）的需求激增。Scan-to-BIM可提供准确的原状条件，并为各种CDT应用程序重建详细的BIM。研究人员提出了使用算法和人工智能自动扫描到bim的方案，以最大限度地减少劳动力需求，但缺乏具有系统指导方针的全面审查。本文提出了扫描到bim流程的概念模型，并基于58个案例回顾了其发展模式和趋势。基于该模型，本文提供了AEC从业者有效采用自动扫描到bim的四步指南。本文的贡献有三方面。首先，概念模型为初学者提供了扫描到bim过程的全面和简化的概述。其次，出现了一些趋势，例如从严格的规则到人工智能方法的转变。第三，最佳实践指南使AEC从业者能够根据他们的需求最大限度地发挥扫描到bim的优势。

引用次数: 0

Comprehensive review of robotic wire arc additive manufacturing for steel structures: Process, material behaviour, structural applications and pathways to automated construction 钢结构机器人电弧增材制造的综合综述：工艺，材料行为，结构应用和自动化施工途径

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

Automation in Construction

Pub Date : 2026-01-05 DOI: 10.1016/j.autcon.2025.106758

Zhao Zhang , Fengyang He , Zhonghao Chen , Lei Yuan , Hong Guan , Zengxi Pan , Huijun Li

As civil engineering advances toward next-generation construction, the integration of robotics, automation, and sustainable manufacturing is becoming increasingly critical. Robotic Wire Arc Additive Manufacturing (WAAM) provides a promising pathway through flexible deposition control and efficient material utilisation in steel structures. This review focuses on WAAM-fabricated steels and synthesises current developments in process, material behaviour, structural applications and future research directions. Relationships between WAAM parameters and deposition strategies are examined to clarify their influence on the performance of WAAM-fabricated steels. Reported material behaviours, including tensile, fatigue, corrosion, and high temperature behaviour, are systematically assessed. Structural applications relevant to direct fabrication, hybrid construction, and repair-related interventions are evaluated to illustrate practical pathways for WAAM in civil engineering. By linking WAAM process with both material and structural performance, this review establishes knowledge and guidance for advancing WAAM toward reliable and efficient adoption in both academic research and industrial practice within civil engineering.

随着土木工程向下一代建筑发展，机器人、自动化和可持续制造的集成变得越来越重要。机器人电弧增材制造（WAAM）通过灵活的沉积控制和高效的材料利用，为钢结构提供了一条有前途的途径。本文综述了waam型钢及其合成材料在工艺、材料性能、结构应用和未来研究方向等方面的最新进展。研究了WAAM参数与沉积策略之间的关系，以阐明它们对WAAM装配钢性能的影响。报告的材料行为，包括拉伸，疲劳，腐蚀和高温行为，系统地评估。本文评估了与直接制造、混合施工和维修相关干预措施相关的结构应用，以说明WAAM在土木工程中的实际应用途径。通过将WAAM工艺与材料和结构性能联系起来，本综述为推进WAAM在土木工程的学术研究和工业实践中可靠和有效地采用建立了知识和指导。

{"title":"Comprehensive review of robotic wire arc additive manufacturing for steel structures: Process, material behaviour, structural applications and pathways to automated construction","authors":"Zhao Zhang , Fengyang He , Zhonghao Chen , Lei Yuan , Hong Guan , Zengxi Pan , Huijun Li","doi":"10.1016/j.autcon.2025.106758","DOIUrl":"10.1016/j.autcon.2025.106758","url":null,"abstract":"<div><div>As civil engineering advances toward next-generation construction, the integration of robotics, automation, and sustainable manufacturing is becoming increasingly critical. Robotic Wire Arc Additive Manufacturing (WAAM) provides a promising pathway through flexible deposition control and efficient material utilisation in steel structures. This review focuses on WAAM-fabricated steels and synthesises current developments in process, material behaviour, structural applications and future research directions. Relationships between WAAM parameters and deposition strategies are examined to clarify their influence on the performance of WAAM-fabricated steels. Reported material behaviours, including tensile, fatigue, corrosion, and high temperature behaviour, are systematically assessed. Structural applications relevant to direct fabrication, hybrid construction, and repair-related interventions are evaluated to illustrate practical pathways for WAAM in civil engineering. By linking WAAM process with both material and structural performance, this review establishes knowledge and guidance for advancing WAAM toward reliable and efficient adoption in both academic research and industrial practice within civil engineering.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106758"},"PeriodicalIF":11.5,"publicationDate":"2026-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145903173","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

Path planning for UAV-based construction safety inspection under spatiotemporal interference from tower cranes 塔吊时空干扰下基于无人机的建筑安全检测路径规划

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

Automation in Construction

Pub Date : 2026-01-05 DOI: 10.1016/j.autcon.2026.106762

Pinsheng Duan , Xuehai Fu , Jinxin Hu , Jianliang Zhou , Ping Guo

Construction sites are dynamic, complex, high-risk environments, where Unmanned Aerial Vehicles (UAVs) are vital for enhancing safety inspection efficiency. As large-scale dynamic obstacles, tower cranes can interfere with effective UAV inspection paths. This paper proposes a safety inspection path planning method under the spatiotemporal interference of multiple tower cranes. First, a 3D model of the construction site is reconstructed, and inspection viewpoints for UAV flights are generated by optimizing safety inspection strategies. Then, a hierarchical path planning framework is established: the lower-level planner strictly enforces real-time safety obstacle avoidance strategies, while the higher-level planner focuses on global planning to meet inspection requirements. Finally, both simulation and real project studies are conducted to verify the feasibility of the method. Results from the real project show that the effective coverage area is increased by 39.01 % compared with traditional methods. This paper provides theoretical and practical support for UAV-assisted safety inspections in construction.

建筑工地是动态、复杂、高风险的环境，无人机对于提高安全检查效率至关重要。塔吊作为大型动态障碍物，会干扰无人机有效的巡检路径。提出了一种多塔机时空干扰下的安全检测路径规划方法。首先，重建施工现场三维模型，通过优化安全检查策略生成无人机飞行检查视点；然后，建立分层路径规划框架：低层规划器严格执行实时安全避障策略，高层规划器注重全局规划以满足巡检需求。最后，通过仿真和实际工程研究验证了该方法的可行性。实际工程结果表明，与传统方法相比，有效覆盖面积增加了39.01%。为无人机辅助施工安全检测提供理论和实践支持。

{"title":"Path planning for UAV-based construction safety inspection under spatiotemporal interference from tower cranes","authors":"Pinsheng Duan , Xuehai Fu , Jinxin Hu , Jianliang Zhou , Ping Guo","doi":"10.1016/j.autcon.2026.106762","DOIUrl":"10.1016/j.autcon.2026.106762","url":null,"abstract":"<div><div>Construction sites are dynamic, complex, high-risk environments, where Unmanned Aerial Vehicles (UAVs) are vital for enhancing safety inspection efficiency. As large-scale dynamic obstacles, tower cranes can interfere with effective UAV inspection paths. This paper proposes a safety inspection path planning method under the spatiotemporal interference of multiple tower cranes. First, a 3D model of the construction site is reconstructed, and inspection viewpoints for UAV flights are generated by optimizing safety inspection strategies. Then, a hierarchical path planning framework is established: the lower-level planner strictly enforces real-time safety obstacle avoidance strategies, while the higher-level planner focuses on global planning to meet inspection requirements. Finally, both simulation and real project studies are conducted to verify the feasibility of the method. Results from the real project show that the effective coverage area is increased by 39.01 % compared with traditional methods. This paper provides theoretical and practical support for UAV-assisted safety inspections in construction.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106762"},"PeriodicalIF":11.5,"publicationDate":"2026-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145903172","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

Accurate concrete spalling segmentation from bounding box supervision using Segment Anything 使用分段任何从边界盒监督混凝土剥落准确分割

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

Automation in Construction

Pub Date : 2026-01-03 DOI: 10.1016/j.autcon.2025.106752

Chen Zhang , Dhanada K. Mishra , Matthew M.F. Yuen , Yantao Yu , Jize Zhang

Accurate pixel-level segmentation of concrete spalling has been severely hampered by the prohibitive cost of manual annotation. This paper investigates how accurate pixel-level defect segmentation can be achieved using only low-cost weakly supervised bounding box annotations. A three-stage framework is proposed to generate and refine pseudo-masks from bounding boxes using the Segment Anything Model (SAM), dynamic self-correction, and inference-time fusion. The proposed method outperformed existing techniques by over 10% in F1 score on a large-scale spalling dataset. These findings establish the economic viability of deploying scalable automated inspection systems by drastically reducing data annotation costs, providing a practical and scalable pathway for spalling assessment.

人工标注的高昂成本严重阻碍了混凝土剥落的精确像素级分割。本文研究了如何使用低成本的弱监督边界框注释实现精确的像素级缺陷分割。提出了一种基于分段任意模型（SAM）、动态自校正和推理时间融合的三阶段框架，从边界框生成和细化伪掩码。该方法在大规模剥落数据集上的F1分数比现有技术高出10%以上。这些发现通过大幅降低数据注释成本，确立了部署可扩展自动检测系统的经济可行性，为剥落评估提供了实用且可扩展的途径。

引用次数: 0

Intelligent prediction of TBM tunneling loads based on modal reconstruction and collaborative modeling 基于模态重构和协同建模的TBM隧道荷载智能预测

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

Automation in Construction

Pub Date : 2026-01-03 DOI: 10.1016/j.autcon.2025.106737

Kang Fu , Yiguo Xue , Daohong Qiu , Jingkai Qu , Huimin Gong

Accurate prediction of TBM tunneling loads is essential for enabling intelligent control. This paper proposes an intelligent prediction framework that integrates modal reconstruction with collaborative modeling. An improved Multivariate Variational Mode Decomposition (IMVMD) combined with Refined Composite Multiscale Diversity Entropy (RCMDE) is employed to extract the trend, seasonal, cyclic, and residual components of tunneling load signals. For each component, specialized predictive models, including Transformer, Bidirectional Gated Recurrent Unit (BiGRU), Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM), and Extreme Gradient Boosting (XGBoost), are developed to construct a collaborative hybrid learning architecture. A CNN-LSTM-based error correction strategy is further introduced, resulting in a corrected hybrid learning (CHL) model that achieved an R² of 0.9972, a MAPE of 0.66 %, and an MAE of 11.73, exceeding traditional models by more than 60 % on average. The proposed method provides reliable technical support for intelligent perception and automated control in TBM tunneling.

隧道掘进机掘进荷载的准确预测是实现智能控制的关键。提出了一种将模态重构与协同建模相结合的智能预测框架。采用改进的多元变分模态分解（IMVMD）和改进的复合多尺度多样性熵（RCMDE）方法提取隧道荷载信号的趋势分量、季节分量、循环分量和残差分量。对于每个组件，开发了专门的预测模型，包括变压器，双向门通循环单元（BiGRU），卷积神经网络长短期记忆（CNN-LSTM）和极端梯度增强（XGBoost），以构建协作混合学习架构。进一步引入了基于cnn - lstm的纠错策略，得到了修正后的混合学习（CHL）模型，其R2为0.9972，MAPE为0.66%，MAE为11.73，比传统模型平均提高了60%以上。该方法为隧道掘进机的智能感知和自动控制提供了可靠的技术支持。

{"title":"Intelligent prediction of TBM tunneling loads based on modal reconstruction and collaborative modeling","authors":"Kang Fu , Yiguo Xue , Daohong Qiu , Jingkai Qu , Huimin Gong","doi":"10.1016/j.autcon.2025.106737","DOIUrl":"10.1016/j.autcon.2025.106737","url":null,"abstract":"<div><div>Accurate prediction of TBM tunneling loads is essential for enabling intelligent control. This paper proposes an intelligent prediction framework that integrates modal reconstruction with collaborative modeling. An improved Multivariate Variational Mode Decomposition (IMVMD) combined with Refined Composite Multiscale Diversity Entropy (RCMDE) is employed to extract the trend, seasonal, cyclic, and residual components of tunneling load signals. For each component, specialized predictive models, including Transformer, Bidirectional Gated Recurrent Unit (BiGRU), Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM), and Extreme Gradient Boosting (XGBoost), are developed to construct a collaborative hybrid learning architecture. A CNN-LSTM-based error correction strategy is further introduced, resulting in a corrected hybrid learning (CHL) model that achieved an <em>R</em><sup>2</sup> of 0.9972, a <em>MAPE</em> of 0.66 %, and an <em>MAE</em> of 11.73, exceeding traditional models by more than 60 % on average. The proposed method provides reliable technical support for intelligent perception and automated control in TBM tunneling.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106737"},"PeriodicalIF":11.5,"publicationDate":"2026-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145880897","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

Digital twin–driven temperature field optimization in tunnel freezing restoration using particle swarm optimization 基于粒子群算法的隧道冻结修复温度场数字双驱动优化

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

Automation in Construction

Pub Date : 2026-01-02 DOI: 10.1016/j.autcon.2025.106747

Jie Zhou , Chao Ban , Chengjun Liu , Zeyao Li , Huade Zhou , Hsinming Shang

The distribution and evolution of temperature field are key concerns in freezing restoration projects, while traditional methods face limitations due to sparse sensor placement and simplified simulation inputs. More effective and accurate methods are needed to determine the temperature field. A PSO-based digital twin model was developed and validated with a tunnel freezing restoration project in Bangkok, Thailand. By integrating real-time field temperature data, the model enables dynamic optimization of parameters, enhancing the accuracy. Single-parameter optimization achieves fast convergence, ideal for early-stage calibration, while multi-parameter optimization improves performance under complex conditions. In these cases, PSO demonstrates better performance compared with GA and DE. When using multiple measurement points, the model may encounter local optima. The hybrid optimization strategy (GA-PSO) provides an effective pathway to mitigate the issue of local optima. This paper demonstrates the model feasibility and effectiveness, offering a practical approach for dynamic temperature management in complex freezing environments.

温度场的分布和演变是冻结恢复工程的关键问题，而传统的方法由于传感器布置的稀疏和模拟输入的简化而面临局限性。需要更有效和准确的方法来确定温度场。建立了基于pso的数字孪生模型，并通过泰国曼谷的隧道冻结修复项目进行了验证。该模型通过集成实时现场温度数据，实现了参数的动态优化，提高了精度。单参数优化实现了快速收敛，非常适合早期校准，而多参数优化提高了复杂条件下的性能。在这些情况下，粒子群算法比遗传算法和遗传算法表现出更好的性能。当使用多个测量点时，模型可能会遇到局部最优。混合优化策略（GA-PSO）为解决局部最优问题提供了有效途径。本文论证了该模型的可行性和有效性，为复杂冰冻环境下的动态温度管理提供了一种实用的方法。

{"title":"Digital twin–driven temperature field optimization in tunnel freezing restoration using particle swarm optimization","authors":"Jie Zhou , Chao Ban , Chengjun Liu , Zeyao Li , Huade Zhou , Hsinming Shang","doi":"10.1016/j.autcon.2025.106747","DOIUrl":"10.1016/j.autcon.2025.106747","url":null,"abstract":"<div><div>The distribution and evolution of temperature field are key concerns in freezing restoration projects, while traditional methods face limitations due to sparse sensor placement and simplified simulation inputs. More effective and accurate methods are needed to determine the temperature field. A PSO-based digital twin model was developed and validated with a tunnel freezing restoration project in Bangkok, Thailand. By integrating real-time field temperature data, the model enables dynamic optimization of parameters, enhancing the accuracy. Single-parameter optimization achieves fast convergence, ideal for early-stage calibration, while multi-parameter optimization improves performance under complex conditions. In these cases, PSO demonstrates better performance compared with GA and DE. When using multiple measurement points, the model may encounter local optima. The hybrid optimization strategy (GA-PSO) provides an effective pathway to mitigate the issue of local optima. This paper demonstrates the model feasibility and effectiveness, offering a practical approach for dynamic temperature management in complex freezing environments.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106747"},"PeriodicalIF":11.5,"publicationDate":"2026-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145880898","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

Self-supervised learning for multi-label sewer defect classification 多标签下水道缺陷分类的自监督学习

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

Automation in Construction

Pub Date : 2026-01-02 DOI: 10.1016/j.autcon.2025.106751

Tugba Yildizli , Tianlong Jia , Jeroen Langeveld , Riccardo Taormina

Automated sewer defect detection has advanced through deep learning, particularly supervised methods using CCTV images, but based on large annotated datasets. This paper proposes a semi-supervised learning (SSL) approach to reduce labeling demands. The method comprises self-supervised pre-training on unlabeled images using SwAV (Swapping Assignments between multiple Views) followed by fine-tuning for multi-label classification. Experiments on the Sewer-ML dataset demonstrate that the SSL approach, trained on only 35k labeled images, achieves an F1-score of 69.11%, and F2_CIW of 54.22%, surpassing the fully supervised baseline trained from scratch on 1.04 million images. Increasing the unlabeled pre-training data further enhances performance, while ImageNet initialization consistently outperforms training from scratch. Self-supervised learning also helps mitigate the effects of mislabeled data, which is observed to be present even in the Sewer-ML ground truth. Overall, self-supervised learning provides an accurate, scalable, and cost-effective alternative to fully supervised approaches, particularly in data-scarce or imperfectly labeled scenarios.

自动化下水道缺陷检测通过深度学习取得了进展，特别是使用闭路电视图像的监督方法，但基于大型注释数据集。本文提出了一种半监督学习（SSL）方法来减少标注需求。该方法包括使用SwAV（在多个视图之间交换分配）对未标记图像进行自监督预训练，然后对多标签分类进行微调。在seur - ml数据集上的实验表明，SSL方法仅在35k标记图像上进行训练，f1得分为69.11%，F2CIW为54.22%，超过了在104万张图像上从头开始训练的完全监督基线。增加未标记的预训练数据进一步提高性能，而ImageNet初始化始终优于从头开始训练。自我监督学习还有助于减轻错误标记数据的影响，即使在下水道- ml的基础事实中也观察到这种情况。总的来说，自监督学习提供了一种准确的、可扩展的、具有成本效益的替代完全监督方法，特别是在数据稀缺或不完美标记的场景中。

{"title":"Self-supervised learning for multi-label sewer defect classification","authors":"Tugba Yildizli , Tianlong Jia , Jeroen Langeveld , Riccardo Taormina","doi":"10.1016/j.autcon.2025.106751","DOIUrl":"10.1016/j.autcon.2025.106751","url":null,"abstract":"<div><div>Automated sewer defect detection has advanced through deep learning, particularly supervised methods using CCTV images, but based on large annotated datasets. This paper proposes a semi-supervised learning (SSL) approach to reduce labeling demands. The method comprises self-supervised pre-training on unlabeled images using SwAV (Swapping Assignments between multiple Views) followed by fine-tuning for multi-label classification. Experiments on the Sewer-ML dataset demonstrate that the SSL approach, trained on only 35k labeled images, achieves an F1-score of 69.11%, and F2<sub>CIW</sub> of 54.22%, surpassing the fully supervised baseline trained from scratch on 1.04 million images. Increasing the unlabeled pre-training data further enhances performance, while ImageNet initialization consistently outperforms training from scratch. Self-supervised learning also helps mitigate the effects of mislabeled data, which is observed to be present even in the Sewer-ML ground truth. Overall, self-supervised learning provides an accurate, scalable, and cost-effective alternative to fully supervised approaches, particularly in data-scarce or imperfectly labeled scenarios.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106751"},"PeriodicalIF":11.5,"publicationDate":"2026-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145880902","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

Collaborative learning architecture for autonomous excavator planning and execution 自主挖掘机规划与执行的协同学习体系结构

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

Automation in Construction

Pub Date : 2025-12-30 DOI: 10.1016/j.autcon.2025.106742

Junhyung Cho , Mingyu Shin , Joongheon Kim , Soyi Jung

Autonomous excavation systems face fundamental challenges balancing computational tractability with operational sophistication. This paper presents the collaborative learning for excavation framework (CLEF), resolving this trade-off through strategic decomposition: separating high-level planning from low-level execution while maintaining collaborative optimization. The framework’s key contributions include a bidirectional information flow between specialized modules consisting of reinforcement learning for strategic planning using polar coordinates, and attention-enhanced generative adversarial imitation learning (A-GAIL) with multi-head attention capturing phase-specific temporal dependencies. Unlike monolithic approaches suffering computational intractability, CLEF enables module specialization while coordinating through shared representations. Planning decisions condition trajectory generation while execution outcomes update environmental models, creating adaptive behavior without manual tuning. Validation demonstrates 90.8% success rate compared to 71.1% for monolithic approaches, with trajectory generation achieving 91.3% completion confirming superior performance essential for construction automation.

自主挖掘系统面临着平衡计算可追溯性和操作复杂性的根本挑战。本文提出了挖掘框架的协作学习（CLEF），通过战略分解解决了这种权衡：在保持协作优化的同时，将高级规划与低级执行分离开来。该框架的主要贡献包括专门模块之间的双向信息流，包括使用极坐标进行战略规划的强化学习，以及具有多头注意力捕获特定阶段时间依赖性的注意力增强生成对抗模仿学习（a - gail）。与遭受计算困难的整体方法不同，CLEF在通过共享表示进行协调时支持模块专门化。规划决策条件轨迹生成，而执行结果更新环境模型，无需手动调优即可创建自适应行为。验证的成功率为90.8%，而单片方法的成功率为71.1%，轨迹生成的完成率为91.3%，这证实了施工自动化所必需的卓越性能。

{"title":"Collaborative learning architecture for autonomous excavator planning and execution","authors":"Junhyung Cho , Mingyu Shin , Joongheon Kim , Soyi Jung","doi":"10.1016/j.autcon.2025.106742","DOIUrl":"10.1016/j.autcon.2025.106742","url":null,"abstract":"<div><div>Autonomous excavation systems face fundamental challenges balancing computational tractability with operational sophistication. This paper presents the collaborative learning for excavation framework (CLEF), resolving this trade-off through strategic decomposition: separating high-level planning from low-level execution while maintaining collaborative optimization. The framework’s key contributions include a bidirectional information flow between specialized modules consisting of reinforcement learning for strategic planning using polar coordinates, and attention-enhanced generative adversarial imitation learning (A-GAIL) with multi-head attention capturing phase-specific temporal dependencies. Unlike monolithic approaches suffering computational intractability, CLEF enables module specialization while coordinating through shared representations. Planning decisions condition trajectory generation while execution outcomes update environmental models, creating adaptive behavior without manual tuning. Validation demonstrates 90.8% success rate compared to 71.1% for monolithic approaches, with trajectory generation achieving 91.3% completion confirming superior performance essential for construction automation.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106742"},"PeriodicalIF":11.5,"publicationDate":"2025-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145880900","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.

﹀