检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Carrara, Andrea Nousias, Stavros Borrmann, André Technical University of Munich School of Engineering and Design Chair of Computational Modelling and Simulation Germany

This paper introduces a new approach to extract and analyze vector data from technical drawings in PDF format. Our method involves converting PDF files into SVG format and creating a feature-rich graph representation, which captures the relationships between vector entities using geometrical information. We then apply a graph attention transformer with hierarchical label definition to achieve accurate line-level segmentation. Our approach is evaluated on two datasets, including the public FloorplanCAD dataset, which achieves state-of-the-art results on weighted F1 score, surpassing existing methods. The proposed vector-based method offers a more scalable solution for large-scale technical drawing analysis compared to vision-based approaches, while also requiring significantly less GPU power than current state-of-the-art vector-based techniques. Moreover, it demonstrates improved performance in terms of the weighted F1 (wF1) score on the semantic segmentation task. Our results demonstrate the effectiveness of our approach in extracting meaningful information from technical drawings, enabling new applications, and improving existing workflows in the AEC industry. Potential applications of our approach include automated building information modeling (BIM) and construction planning, which could significantly impact the efficiency and productivity of the industry. © 2024, CC BY-NC-SA.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Formal analysis and validation of levels of geometry (LOG) in building information models 27

Formal analysis and validation of levels of geometry (LOG) i...

引用

27th EG-ICE International Workshop on Intelligent Computing in Engineering 2020

作者： Abualdenien, Jimmy Borrmann, André Computational Modelling and Simulation Technical University of Munich Germany

ISBN: (纸本)9783798331556

Construction projects are multidisciplinary and contractual. The collaboration among the project participants and the quality of the exchanged building information throughout the project lifecycle are prescribed in legal agreements. The Level of Development (LOD) concept is widely used for describing the building elements' maturity. Detailing models to a certain LOD is crucial for integrating the partial models as well as consumes additional time and costs. Every LOD comprises requirements for both Level of Geometry (LOG) and Level of Information (LOI). Thus far, the validation of LOD is limited to the LOI, whereas, checking the quality of the LOG is a complex and unsolved task. This paper proposes a framework for validating the LOG of building elements. In more detail, a LOG dataset is modelled, and then a formal metric is defined based on an extracted set of geometric features. Finally, a random forest model is developed for predicting the LOG. © EG-ICE 2020 Workshop on Intelligent Computing in Engineering, Proceedings. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Retracing positions of terrestrial laser scanners to reinstate legacy point clouds 27

Retracing positions of terrestrial laser scanners to reinsta...

引用

27th EG-ICE International Workshop on Intelligent Computing in Engineering 2020

作者： Eickeler, Felix Borrmann, André Computational Modelling and Simulation Technical University of Munich Germany

ISBN: (纸本)9783798331556

Laser scanners provide a mostly geometric representation, but further details can be collected by analysing the recording setup. While the recording configuration is needed in post-processing, it is generally not passed on to the engineers as most scans are created by surveyors and handled by subcontractors. This disconnection between the consumer and the creator can be observed by the fact, that most laser scanned point clouds include intensity information. In day to day use, the intensity information serves as a substitute for colour as it provides contrasts between different objects in the recording. However, from the technical perspective the intensity is the result of the recording device interacting with the surface. This interaction should not be used for automation as different recording setups may result in different interactions and outcomes. Facing this problem, we propose a mechanism to enrich terrestrial laser scans by recreating original scan parameters and further converting the intensity to reflectivity - a sole property of the recorded surface. © EG-ICE 2020 Workshop on Intelligent Computing in Engineering, Proceedings. All rights reserved.

关键词： Scanning

来源：评论

学校读者我要写书评

暂无评论

From point cloud to IFC: A masonry arch bridge case study 27

From point cloud to IFC: A masonry arch bridge case study

引用

27th EG-ICE International Workshop on Intelligent Computing in Engineering 2020

作者： Sánchez-Rodríguez, Ana Esser, Sebastian Abualdenien, Jimmy Borrmann, André Riveiro, Belén Department of Materials Engineering Applied Mechanics and Construction School of Industrial Engineering University of Vigo Spain Chair of Computational Modelling and Simulation Technical University of Munich Germany

ISBN: (纸本)9783798331556

For the last several years, laser scanning has become one of the reference technologies when talking about the monitoring of assets. Nowadays, the trend is to use these data for creating semantically rich three-dimensional (3D) models, broadly known as digital twins. The bottleneck appears when processing the large amount of data acquired with the laser scanner. This paper tackles the creation of IFC data models using classified point cloud data. The point labelling methodology is based on one in the state-of-the-art, whose results have been improved. Then, each group of points is converted to a triangulated mesh, and the resultant geometrical objects are placed in an IFC-based model in a low and high level of detail. Moreover, the resultant IFC model allows the enrichment of the captured geometry with additional information. © EG-ICE 2020 Workshop on Intelligent Computing in Engineering, Proceedings. All rights reserved.

关键词： Arch bridges

来源：评论

学校读者我要写书评

暂无评论

Georeferencing within IFC: A Novel Approach for Infrastructure Objects

Georeferencing within IFC: A Novel Approach for Infrastructu...

引用

ASCE International Conference on Computing in Civil Engineering 2019: Visualization, Information Modeling, and simulation, i3CE 2019

作者： Jaud, Štefan Donaubauer, Andreas Borrmann, André Department of Computational Modelling and Simulation Dept. of Civil Geo and Environmental Engineering Technical Univ. of Munich Munich80333 Germany Dept. of Civil Geo and Environmental Engineering Technical Univ. of Munich Munich80333 Germany

ISBN: (数字)9780784482421

ISBN: (纸本)9780784482421

The transfer of design data into nature is a necessary task during the construction process. For this, the geodetic coordinate reference system (gCRS) used during the design process needs to be accounted for and the distortions included need to be handled appropriately. In the context of building information modelling (BIM) and the vendor-neutral data format industry foundation classes (IFC), the gCRS represents an important metadata item of the model which is included and maintained throughout the project's lifetime. Although the IFC4 supports gCRSs by providing the option to refer to an identifier of the European Petroleum Survey Group (EPSG) database, it is not able to handle custom gCRSs, which can be defined for large infrastructure projects, such as the Brenner Base Tunnel (BBT). We highlight these deficiencies of the schema and propose a novel approach by expanding the IFC schema with the well-known text (WKT) notation. © 2019 American Society of Civil Engineers.

关键词： Architectural design

来源：评论

学校读者我要写书评

暂无评论

BIM-integrated LCA - model analysis and implementation for practice

引用

IOP Conference Series: Earth and Environmental Science 2019年第1期323卷

作者： K Forth A Braun A Borrmann Chair of Computational Modelling and Simulation Technical University of Munich Arcisstr. 21 80333 Munich Germany

Ecological impacts of buildings can be quantified using the method of Lifecycle Assessment (LCA). With the help of digital methods and semantic building models (BIM), those impacts can be reduced by investigation of variants and their LCA comparison. However, there is a large deviation in the results due to inaccuracies in the modeling and the calculation tools. This paper proposes an improved workflow of BIM-integrated LCA avoiding those inaccuracies. As a first step, various sources of error are identified using a model analysis, which is examined with 25 models focusing on geometry and materiality. Thereby different workflows are investigated, modeling recommendations are derived based on the error analysis, and the findings are implemented in a prototype. Through an optimized calculation process, the semi-automatic calculation of life cycle assessments becomes faster, more consistent and more accurate due to the improved integration in BIM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nonlinear sensor fault diagnosis in wireless sensor networks using structural response data 23

Nonlinear sensor fault diagnosis in wireless sensor networks...

引用

23rd International Workshop of the European Group for Intelligent Computing in Engineering, EG-ICE 2016

作者： Dragos, Kosmas Smarsly, Kay Jahr, Katrin Department of Computing in Civil Engineering Bauhaus University Weimar Germany Department of Computational Modelling and Simulation Technical University Munich Germany

This paper introduces a novel approach towards sensor fault diagnosis in wireless structural health monitoring systems. As compared to traditional fault diagnosis approaches, a number of innovations are reported in this paper. First, by embedding fault models and algorithms directly into wireless sensor nodes, sensor faults can be self-detected by the nodes in a distributedcooperative fashion. Second, no redundant sensor installations are required for fault diagnosis, because the wireless sensor nodes exploit the redundant information of correlated sensors already installed in the monitored structure ("analytical redundancy"). Third, instead of using raw time series of sensor data for analytical redundancy, the sensor data is first transformed from the time domain into the frequency domain on-board the sensor nodes, entailing significantly reduced data traffic. Fourth, nonlinearities in the data sets (e.g. due to measurement factors) are handled by implementing the analytical redundancy approach in terms of feedforward backpropagation neural networks embedded into the wireless sensor nodes. Fifth, due to the adaptation abilities of the embedded neural networks, sensor fault diagnosis remains efficient and accurate even if the monitored structure is subject to structural changes (or damage) as reflected in the sensor data. Sixth, no a priori knowledge about the structure or about the sensor instrumentation is required because the neural networks, representing a purely data-driven approach, take previously collected sensor data as the sole basis for fault diagnosis. This paper presents the fault diagnosis methodology, followed by the implementation into a fault-tolerant wireless structural health monitoring system prototype. Validation experiments on a laboratory test structure demonstrate the efficiency and accuracy of the proposed approach.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Verification benchmarks for single-phase flow in three-dimensional fractured porous media

arXiv

引用

arXiv 2020年

作者： Berre, Inga Boon, Wietse M. Flemisch, Bernd Fumagalli, Alessio Gläser, Dennis Keilegavlen, Eirik Scotti, Anna Stefansson, Ivar Tatomir, Alexandru Brenner, Konstantin Burbulla, Samuel Devloo, Philippe Duran, Omar Favino, Marco Hennicker, Julian Lee, I-Hsien Lipnikov, Konstantin Masson, Roland Mosthaf, Klaus Chiara Nestola, Maria Giuseppina Ni, Chuen-Fa Nikitin, Kirill Schädle, Philipp Svyatskiy, Daniil Yanbarisov, Ruslan Zulianp, Patrick Department of Mathematics University of Bergen Allégaten 41 Bergen5007 Norway Department of Mathematics KTH Royal Institute of Technology Lindstedtsvägen 25 Stockholm11428 Sweden Department of Hydromechanics and Modelling of Hydrosystems University of Stuttgart Pfaffenwaldring 61 Stuttgart70569 Germany Laboratory for Modeling and Scientific Computing MOX Politecnico di Milano p.za Leonardo da Vinci 32 Milano20133 Italy Department of Applied Geology Geosciences Center University of Göttingen Goldschmidtstrasse 3 Göttingen37077 Germany Department of Earth Sciences Uppsala University Villavägen 16 UppsalaS-75236 Sweden University of Côte d’Azur CNRS INRIA LJAD Nice France Institute of Applied Analysis and Numerical Simulation University of Stuttgart Pfaffenwaldring 57 Stuttgart70569 Germany FEC Universidade Estadual de Campinas Cidade Universitária R. Josiah Willard Gibbs 85 Campinas-SPCEP 13083-839 Brazil Institute of Earth Sciences University of Lausanne Building Geopolis UNIL-Mouline Lausanne1015 Switzerland Section de Mathématiques Université de Genève 2-4 rue du Lièvre CP 64 Genève1211 Switzerland Graduate Institute of Applied Geology National Central University Taiwan Center for Environmental Studies National Central University Taiwan Los Alamos National Laboratory New Mexico United States Department of Environmental Engineering Technical University of Denmark Bygningstorvet Building 115 Kgs. Lyngby2800 Denmark Numerical Simulation in Science Medicine and Engineering Group Institute of Computational Science Università della Svizzera italiana. Via G. Buffi 13 Lugano Ticino6900 Switzerland Marchuk Institute of Numerical Mathematics of Russian Academy of Sciences Moscow Russia ETH Zürich Geothermal Energy and Geofluids Group Institute of Geophysics Zürich8092 Switzerland

Flow in fractured porous media occurs in the earth’s subsurface, in biological tissues, and in man-made materials. Fractures have a dominating influence on flow processes, and the last decade has seen an extensive development of models and numerical methods that explicitly account for their presence. To support these developments, we present a portfolio of four benchmark cases for single-phase flow in three-dimensional fractured porous media. The cases are specifically designed to test the methods’ capabilities in handling various complexities common to the geometrical structures of fracture networks. Based on an open call for participation, results obtained with 17 numerical methods were collected. This paper presents the underlying mathematical model, an overview of the features of the participating numerical methods, and their performance in solving the benchmark cases. Copyright © 2020, The Authors. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

26th Annual computational Neuroscience Meeting (CNS*2017): Part 3 Antwerp, Belgium. 15-20 July 2017 Abstracts

引用

BMC NEUROSCIENCE 2017年第SUPPL 1期18卷 95-176页

作者： [Anonymous] Department of Neuroscience Yale University New Haven CT 06520 USA Department Physiology & Pharmacology SUNY Downstate Brooklyn NY 11203 USA NYU School of Engineering 6 MetroTech Center Brooklyn NY 11201 USA Departament de Matemàtica Aplicada Universitat Politècnica de Catalunya Barcelona 08028 Spain Institut de Neurobiologie de la Méditerrannée (INMED) INSERM UMR901 Aix-Marseille Univ Marseille France Center of Neural Science New York University New York NY USA Aix-Marseille Univ INSERM INS Inst Neurosci Syst Marseille France Laboratoire de Physique Théorique et Modélisation CNRS UMR 8089 Université de Cergy-Pontoise 95300 Cergy-Pontoise Cedex France Department of Mathematics and Computer Science ENSAT Abdelmalek Essaadi’s University Tangier Morocco Laboratory of Natural Computation Department of Information and Electrical Engineering and Applied Mathematics University of Salerno 84084 Fisciano SA Italy Department of Medicine University of Salerno 84083 Lancusi SA Italy Dipartimento di Fisica Università degli Studi Aldo Moro Bari and INFN Sezione Di Bari Italy Data Analysis Department Ghent University Ghent Belgium Coma Science Group University of Liège Liège Belgium Cruces Hospital and Ikerbasque Research Center Bilbao Spain BIOtech Department of Industrial Engineering University of Trento and IRCS-PAT FBK 38010 Trento Italy Department of Data Analysis Ghent University Ghent 9000 Belgium The Wellcome Trust Centre for Neuroimaging University College London London WC1N 3BG UK Department of Electronic Engineering NED University of Engineering and Technology Karachi Pakistan Blue Brain Project École Polytechnique Fédérale de Lausanne Lausanne Switzerland Departement of Mathematics Swansea University Swansea Wales UK Laboratory for Topology and Neuroscience at the Brain Mind Institute École polytechnique fédérale de Lausanne Lausanne Switzerland Institute of Mathematics University of Aberdeen Aberdeen Scotland UK Department of Integrativ

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “Anomalous Consistency in Mild Cognitive Impairment: A complex networks approach” [Chaos Solitons Fract. J. 70 (2014) 144–155]

引用

Chaos, Solitons & Fractals 2015年 73卷 202-202页

作者： J.H. Martínez P. Ariza M. Zanin D. Papo F. Maestú J.M. Pastor R. Bajo Stefano Boccaletti J.M. Buldú Complex Systems Group Technical University of Madrid Madrid Spain Modelling and Simulation Laboratory Universidad del Rosario de Colombia Bogotá Colombia Laboratory of Biological Networks Centre for Biomedical Technology (UPM-URJC) Madrid Spain Faculdade de Ciências e Tecnologia Departamento de Engenharia Electrotécnica Universidade Nova de Lisboa Lisboa Portugal The INNAXIS foundation and Research Institute Madrid Spain Laboratory of Cognitive and Computational Neuroscience Centre for Biomedical Technology (UPM-UCM) Madrid Spain CNR-Istituto dei Sistemi Complessi Via Madonna del Piano 10 50019 Sesto Fiorentino Italy Complex Systems Group Universidad Rey Juan Carlos Madrid Spain

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：