Advanced Engineering Informatics最新文献_第4页

Auto-summarization of the texts of construction dispute precedents 工程纠纷判例文本的自动摘要

IF 8 1区工程技术

Advanced Engineering Informatics Pub Date : 2025-04-22 DOI: 10.1016/j.aei.2025.103381

Wonkyoung Seo , Youngcheol Kang

{"title":"Auto-summarization of the texts of construction dispute precedents","authors":"Wonkyoung Seo , Youngcheol Kang","doi":"10.1016/j.aei.2025.103381","DOIUrl":"10.1016/j.aei.2025.103381","url":null,"abstract":"<div><div>Advancements in text analysis are driving the adoption of document automation in the construction industry. Despite significant financial losses from construction disputes, efforts to automate document processes in this domain remain limited. Effective dispute management requires the rapid identification of relevant precedent cases to help practitioners respond appropriately. However, the complexity and length of such texts pose challenges to quick comprehension. This study presents a natural language processing (NLP) model for automatically summarizing construction dispute case texts. The model was tested on 300 U.S. construction dispute cases sourced from the Westlaw database. Various NLP models, including large language models (LLMs) such as OpenAI’s models and BERT, were evaluated, achieving an F-score of approximately 0.39 based on the ROUGE-L metric. To accomplish the domain-specific objective of summarizing construction precedent cases, this study explored multiple approaches, including data preprocessing, fine-tuning, and model engineering using LangChain. Furthermore, this study aims to develop models for summarizing legal precedent texts and investigates methods to capture the distinctive characteristics of construction dispute data compared to general legal texts. The models were validated through domain experts who recognize the unique nature of construction disputes, enhancing the reliability of the evaluation process. The findings contribute significantly to the automation of construction dispute document summarization, enabling practitioners to manage such cases more efficiently.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103381"},"PeriodicalIF":8.0,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143860025","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

A degradation modeling method based on artificial neural network supported Tweedie exponential dispersion process 基于人工神经网络支持特威迪指数分散过程的降解建模方法

IF 8 1区工程技术

Advanced Engineering Informatics Pub Date : 2025-04-22 DOI: 10.1016/j.aei.2025.103376

Zhongze He , Shaoping Wang , Di Liu

{"title":"A degradation modeling method based on artificial neural network supported Tweedie exponential dispersion process","authors":"Zhongze He , Shaoping Wang , Di Liu","doi":"10.1016/j.aei.2025.103376","DOIUrl":"10.1016/j.aei.2025.103376","url":null,"abstract":"<div><div>Degradation modeling is crucial for predicting product performance and reliability. Stochastic process-based methods are widely used due to their ability to incorporate uncertainties. These methods typically involve three main components: stochastic process models, degradation paths, and model parameters. However, traditional approaches often overlook the inherent uncertainties in both the model and degradation path, leading to potential modeling errors. This paper proposes a novel approach that combines artificial neural networks with the Tweedie exponential dispersion process framework to adaptively fit the stochastic process model that best reflects the actual degradation trend. The hybrid model is parameterized by process parameters and network parameters, and offline-trained using gradient-based algorithms. For predicting degradation in new individuals with incomplete data, the process parameters are regarded as random variables to account for individual heterogeneity and time-varying uncertainties. Bayesian inference is used to estimate process parameters based on the trained model, with real-time data used to update the parameters for improved accuracy. A simulation dataset based on a non-standard process validate the method’s effectiveness. Furthermore, a real degradation dataset is used to demonstrate its application in engineering scenario. Results show that the proposed approach better captures true degradation trends, offering higher prediction accuracy compared to conventional models.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103376"},"PeriodicalIF":8.0,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143855886","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

Cloud-fog-edge based computing architechture and a hierarchical decision approach for distributed synchronized manufacturing systems 基于云雾边缘的计算架构和分布式同步制造系统的分层决策方法

IF 8 1区工程技术

Advanced Engineering Informatics Pub Date : 2025-04-22 DOI: 10.1016/j.aei.2025.103386

Zhicong Hong , Ting Qu , Yongheng Zhang , Zhongfei Zhang , George Q. Huang

{"title":"Cloud-fog-edge based computing architechture and a hierarchical decision approach for distributed synchronized manufacturing systems","authors":"Zhicong Hong , Ting Qu , Yongheng Zhang , Zhongfei Zhang , George Q. Huang","doi":"10.1016/j.aei.2025.103386","DOIUrl":"10.1016/j.aei.2025.103386","url":null,"abstract":"<div><div>The demand for personalized products and rapid delivery has driven manufacturers to outsource a significant portion of their production and logistics tasks to collaborators, resulting in a gradual decentralization of manufacturing systems and the emergence of distributed manufacturing networks. This shift introduces three key challenges: (1) Security concerns prevent full transparency in resource and information sharing across enterprises; (2) Decentralized decision-making structures create conflicts of interest in multi-party collaborations; (3) Strong interdependence between production and logistics processes leads to mutual constraints in order allocation, production, and transportation. To address these, this paper analyzes the collaborative relationships between manufacturers and multiple collaborators and constructs a hierarchical control network of synchronized actions. A cloud-fog-edge-based hierarchical computing architechture is proposed to support distributed synchronized manufacturing scenarios, focusing on the core control modules. Finally, an Analytical Target Cascading (ATC) based production–distribution synchronization model is developed. In the experimental section, two strategies are examined: Hierarchical Synchronous Control (HSC) and Conventional Synchronous Control (CSC). Experimental results demonstrate that the HSC strategy effectively improves the collaborative efficiency of production and logistics, enhances order fulfillment rates, strengthens the system’s resilience to disturbances, and significantly reduces the overall operational costs of distributed synchronized manufacturing system.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103386"},"PeriodicalIF":8.0,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143855829","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

An edge-cloud IIoT framework for predictive maintenance in manufacturing systems 用于制造系统预测性维护的边缘云IIoT框架

IF 8 1区工程技术

Advanced Engineering Informatics Pub Date : 2025-04-22 DOI: 10.1016/j.aei.2025.103388

Nivethitha Somu, Nirupam Sannagowdara Dasappa

{"title":"An edge-cloud IIoT framework for predictive maintenance in manufacturing systems","authors":"Nivethitha Somu, Nirupam Sannagowdara Dasappa","doi":"10.1016/j.aei.2025.103388","DOIUrl":"10.1016/j.aei.2025.103388","url":null,"abstract":"<div><div>Despite significant research efforts on Industrial Internet of Things (IIoT) based Predictive Maintenance (PdM) systems, challenges related to the availability of real-time machine operational data, reliable computing-deployment architecture, and implementation in real-time manufacturing environments continue to be major concerns. Hence, this work presents Intelligent PdM (IntelliPdM), an end-to-end IIoT predictive maintenance framework implemented on an edge-cloud platform that processes the real-time heterogeneous data streams (IoT sensors and cameras) and provides intelligent decisions on faults, failures, and maintenance schedules via. endpoints and interactive web user interface (dashboards, alerts/recommendations, and analytics. SmartHome, a synthetic data generation framework was properly configured to generate synthetic data based on limited real-time operational data or open-source benchmark machine health datasets covering all possible industrial fault scenarios. Experimental validations using synthetic data, generated from real-time machine health data collected from a testbed setup at a research center in Western Europe, along with on-site implementation in a large manufacturing unit in Singapore, effectively demonstrate the efficiency of IntelliPdM in delivering accurate and reliable fault diagnostics. Over a 12-months real-time implementation, IntelliPdM demonstrated (i) an accuracy of 93–95%, (ii) 25–30% reduction in maintenance costs, (iii) 70–75% decrease in equipment breakdowns, (iv) 35–45% reduction in downtime, (v) 20–25% increase in production, and (vi) 10x return on investment.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103388"},"PeriodicalIF":8.0,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143860026","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

Deep reinforcement learning-based air traffic flow coordination in flow-centric airspace 以流量为中心的空域中基于深度强化学习的空中交通流协调

IF 8 1区工程技术

Advanced Engineering Informatics Pub Date : 2025-04-21 DOI: 10.1016/j.aei.2025.103342

Chunyao Ma , Yash Guleria , Sameer Alam , Max Z. Li

{"title":"Deep reinforcement learning-based air traffic flow coordination in flow-centric airspace","authors":"Chunyao Ma , Yash Guleria , Sameer Alam , Max Z. Li","doi":"10.1016/j.aei.2025.103342","DOIUrl":"10.1016/j.aei.2025.103342","url":null,"abstract":"<div><div>Air traffic flow coordination to avoid congestion at major flow intersections is a key enabler for the flow-centric airspace concept. This paper addresses the problem of air traffic flow coordination at major flow intersections by presenting a comprehensive solution encompassing flow identification, prediction, and re-routing at the Nominal Flow Intersections (NFIs). To identify the NFIs, a graph-based flow-pattern consistency approach is proposed to model and analyze daily air traffic flow patterns. With the identified NFIs, a transformer encoder-based neural network is adopted to learn the relations among the flow of flights at the NFIs to predict future demand. Finally, to avoid the foreseen demand exceeding the flow limit and reduce the congestion at NFIs, a reinforcement learning-based flow re-routing agent is designed and trained to dynamically assign alternative routes to air traffic flows based on the evolving flow states. The agent’s performance is quantified by the congestion reduction in the flows, quantified by the flight travel time. The proposed model is trained and tested using ADS-B data for December 2019 for two major en-route flows in the French airspace. The average travel time in each major flow is 30 min. Results show that, compared with the originally planned flows which have exceeded the flow limit, the per-flight travel time in the two flows is reduced by 3.34 min (11.1%) and 1.96 min (6.5%) through flow re-routing. Moreover, the overall travel time for flights around the two major flows (due to re-routing) is reduced by 1.45 min and 1.04 min respectively.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103342"},"PeriodicalIF":8.0,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851782","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

Reliable recommendations for CCTV sewer inspections through multi-label image classification 通过多标签图像分类为闭路电视下水道检查提供可靠建议

IF 8 1区工程技术

Advanced Engineering Informatics Pub Date : 2025-04-21 DOI: 10.1016/j.aei.2025.103317

Remi Cuingnet, Marine Bernard, Phillipe R. Sampaio, Ines Sakhri, Keryan Chelouche, Jérôme Jossent, Islam Doumi, Emmanuelle Gaudichet, Damien Chenu, Aude Maitrot, Marie Lachaize

{"title":"Reliable recommendations for CCTV sewer inspections through multi-label image classification","authors":"Remi Cuingnet, Marine Bernard, Phillipe R. Sampaio, Ines Sakhri, Keryan Chelouche, Jérôme Jossent, Islam Doumi, Emmanuelle Gaudichet, Damien Chenu, Aude Maitrot, Marie Lachaize","doi":"10.1016/j.aei.2025.103317","DOIUrl":"10.1016/j.aei.2025.103317","url":null,"abstract":"<div><div>Sewer infrastructure is crucial for public health and environmental protection. The maintenance of these sewerage networks, with millions of kilometers of pipe, heavily relies on efficient Closed-Circuit Television (CCTV) inspections for identifying and addressing these issues promptly. This paper investigates the potential of hierarchical multi-label image classification to provide reliable recommendations for sewer pipe defects to assist CCTV inspectors. It focuses on both primary defect types and their specific subcategories, as defined by the European standard EN 13508-2. Experiments were conducted on a dataset of 1.2 million annotated sewer inspection images. Surprisingly, the simplest approach of directly predicting the final defect categories outperformed more complex hierarchical methods. When compared against expert human annotators, the multi-label classification methods provided substantially more reliable recommendations. While opportunities remain to further improve performance, these results underscore the promising potential of these methods to assist human inspectors in the maintenance of wastewater infrastructures.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103317"},"PeriodicalIF":8.0,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851783","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

An efficient 2D-3D fusion method for bridge damage detection under complex backgrounds with imbalanced training data 一种高效的二维三维融合方法，用于复杂背景下不平衡训练数据的桥梁损伤检测

IF 8 1区工程技术

Advanced Engineering Informatics Pub Date : 2025-04-21 DOI: 10.1016/j.aei.2025.103373

Wen-Jie Zhang , Hua-Ping Wan , Michael D. Todd

{"title":"An efficient 2D-3D fusion method for bridge damage detection under complex backgrounds with imbalanced training data","authors":"Wen-Jie Zhang , Hua-Ping Wan , Michael D. Todd","doi":"10.1016/j.aei.2025.103373","DOIUrl":"10.1016/j.aei.2025.103373","url":null,"abstract":"<div><div>Existing bridge structures are inevitably affected by various adverse environments and loads during routine operations, which accelerates structural damage and highlights the necessity of conducting bridge inspections. Because of their cost-effectiveness and non-contact capabilities, computer vision methods applied to images from unmanned aerial vehicle (UAV) survey campaigns are promising ways to conduct bridge inspections. Bridge images captured by UAVs often contain numerous complex background pixels due to the small size of damage. Additionally, the existing damage datasets used for training suffer from a severe inter-class imbalance, which significantly affects the accuracy of damage recognition. This study proposes a 2D-3D fusion method for bridge damage segmentation and localization, effectively identifying damage under complex backgrounds with imbalanced data. First, a 3D reconstruction method is introduced to reconstruct bridge point clouds and generate depth maps from different viewpoints. Second, an RGB-D segmentation model is presented to extract the region of interest from images by integrating 2D and 3D information. Third, an improved DeepLabv3 + model is developed to segment damage and integrate it with point clouds for three-dimensional visualization. Field experiments are conducted on a multi-span simply supported girder bridge to validate the effectiveness of the proposed method. The ROI extraction model achieves an F-measure of 98.85%, and the damage segmentation model attains a mAP of 82.21%. Additionally, the 3D visualization result indicates areas of interest (e.g., wet spot, cavities, and spalling) on the cover girder, providing valuable guidance for bridge maintenance. These findings demonstrate the effectiveness and practicality of the proposed method in bridge inspection.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103373"},"PeriodicalIF":8.0,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143855885","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

ELA-YOLO: An efficient method with linear attention for steel surface defect detection during manufacturing ELA-YOLO：一种基于线性关注的钢材表面缺陷检测方法

IF 8 1区工程技术

Advanced Engineering Informatics Pub Date : 2025-04-19 DOI: 10.1016/j.aei.2025.103377

Ruichen Ma , Jinglong Chen , Yong Feng , Zitong Zhou , Jingsong Xie

{"title":"ELA-YOLO: An efficient method with linear attention for steel surface defect detection during manufacturing","authors":"Ruichen Ma , Jinglong Chen , Yong Feng , Zitong Zhou , Jingsong Xie","doi":"10.1016/j.aei.2025.103377","DOIUrl":"10.1016/j.aei.2025.103377","url":null,"abstract":"<div><div>Research on deep learning methods for steel surface defect detection significantly enhances product quality and manufacturing efficiency. However, practical industrial scenarios pose challenges, including variations in color, lighting, reflective conditions, and other environmental factors that affect defect visibility. Additionally, defects vary in size and shape, with some being so small or concealed that accurate detection is difficult. Complex textures of detected images further increase computational cost, often compromising efficiency for high precision. In this paper, we propose a novel method called ELA-YOLO for defect detection, using YOLOv8 as the underlying framework. First, we introduce linear attention to the network to improve the model’s representation capability while managing computational complexity. Second, we propose a selective feature pyramid network to enhance feature fusion across different levels. Third, we design a lightweight detection head to output detection results efficiently. Experimental results demonstrate that ELA-YOLO achieves the highest accuracy: 81.7 mAP on the NEU-DET dataset, 99.3 mAP on the DAGM2007 dataset and 74.3 mAP on the GC10-DET dataset. Additionally, it achieves the lowest parameters (5.4 M), computational complexity (16.5 GFLOPs), and relatively low latency (101.3 FPS). Our method strikes an optimal balance between efficiency and accuracy, demonstrating comprehensive performance in industrial steel surface defect detection.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103377"},"PeriodicalIF":8.0,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143850298","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

A multi-task engineering design intention recognition approach based on Vision Transformer and EEG data 基于视觉变换和脑电数据的多任务工程设计意图识别方法

IF 8 1区工程技术

Advanced Engineering Informatics Pub Date : 2025-04-18 DOI: 10.1016/j.aei.2025.103353

Mingrui Li , Zuoxu Wang , Fan Li , Jihong Liu

{"title":"A multi-task engineering design intention recognition approach based on Vision Transformer and EEG data","authors":"Mingrui Li , Zuoxu Wang , Fan Li , Jihong Liu","doi":"10.1016/j.aei.2025.103353","DOIUrl":"10.1016/j.aei.2025.103353","url":null,"abstract":"<div><div>Engineering product design involves a variety of tasks and scenarios, including design modeling, design calculation, process planning, etc. When performing these design tasks, designers generate constantly shifting design intentions. Accurately recognizing these design intentions allows for a more thorough exploration of design processes from the perspective of cognition, facilitating the advancement of intelligent engineering design. Electroencephalogram (EEG) technology has emerged as an effective tool in recent years, which can provide direct insight into designers’ cognitive processes and intentions. However, the current application of EEG technology in engineering design faces difficulties in adapting to multi-task scenarios and rarely targets the design process directly. This study proposed a design intention recognition approach based on Vision Transformer (ViT) and EEG data applicable to multiple engineering design tasks. An image-like representation matrix is introduced to organize designers’ EEG data with the retention of its spatial and frequency features. Then, standard EEG data under different design intentions as well as the EEG data from real design processes is utilized to train and fine-tune a ViT-based design intention recognition model. An experiment workflow for collecting the two types of EEG data is also presented, along with detailed examples of three design tasks. The comparative experiment results and the case study demonstrates the feasibility of the proposed design intention recognition approach.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103353"},"PeriodicalIF":8.0,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143842647","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

Optimized UAV view planning for high-quality 3D reconstruction of buildings using a modified sparrow search algorithm 基于改进麻雀搜索算法的高质量建筑物三维重建优化无人机视角规划

IF 8 1区工程技术

Advanced Engineering Informatics Pub Date : 2025-04-18 DOI: 10.1016/j.aei.2025.103344

Zhenyu Liang , Liu Yang , Zhaolun Liang , Jeff Chak Fu Chan , Zhaojie Zhang , Mingzhu Wang , Jack C.P. Cheng

{"title":"Optimized UAV view planning for high-quality 3D reconstruction of buildings using a modified sparrow search algorithm","authors":"Zhenyu Liang , Liu Yang , Zhaolun Liang , Jeff Chak Fu Chan , Zhaojie Zhang , Mingzhu Wang , Jack C.P. Cheng","doi":"10.1016/j.aei.2025.103344","DOIUrl":"10.1016/j.aei.2025.103344","url":null,"abstract":"<div><div>High-quality 3D reconstruction of existing buildings is essential for their maintenance, restoration, and management. Effective view planning for image collection significantly impacts the quality of photogrammetry-based 3D reconstruction. Intricate building structures, such as the overhangs, protrusions, and concave regions, can lead to under-sampled regions with traditional view planning methods, while excessively increasing the number of views require substantial computational resources and data collection efforts. To address these issues, this paper proposes a novel exploration-then-exploitation view planning strategy to achieve high-quality building reconstruction with minimal views. Firstly, the UAV no-fly regions and building attention regions are identified through semantic and geometric analysis of the images and coarse model during the exploration stage. Then, a novel optimization fitness function is mathematically formulated, considering building attention regions and reconstruction influential factors, including distance, incidence angle, parallax angle, and overlap. Furthermore, a modified sparrow search algorithm is proposed with the improved optimization mechanism and the integration of view planning physical model, enabling effective generation of optimal viewpoint set. Finally, the collision-free shortest trajectory is designed, allowing the UAV to collect images and reconstruct a high-quality model during exploitation stage. Experiments in virtual and real-world scenarios validate the effectiveness of our proposed modified SSA mechanism and the view planning strategy. Results demonstrate that the modified SSA achieves higher convergence accuracy and speed compared to the original SSA, PSO and GA. Our strategy can generate more accurate and complete 3D reconstruction models with the same or fewer captured images compared to commonly used and state-of-the-art strategies.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103344"},"PeriodicalIF":8.0,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143842568","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