Filters

Settings

Now showing1 - 10 of 65
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: with files ,
    How can development plans promote the sustainability of construction projects?
    (Technische Universität Hamburg, Institut für Digitales und Autonomes Bauen, 2024-09-18)
    Luther, Jan
    ;
    Maibaum, Jonas
    The increasing demands on sustainability require a reorientation in neighborhood and building planning that takes into account various criteria from different areas. Early planning decisions in particular have a significant influence on the later sustainability performance of construction projects. Development plans are a suitable instrument for considering and ultimately defining tangible sustainability requirements for future neighborhood quarters and buildings at municipal level. A multi-layered model-based approach was developed for this purpose, which can be seen as a link between municipal neighborhood development and the subsequent building planning. Based on identified development plan parameters, a two-stage semi-automated process is used to perform a multi-criteria (ecological, economic and social) sustainability assessment. Initially, the parametric building envelope is generated based on the assumed development plans boundary conditions. In the second step, this is linked with component assemblies, materials, social, cost and environmental parameters. This process is repeated for various compliant scenarios and the results are then compared to determine the Pareto optimum for various criteria. In this way, the potential of the sustainability requirements defined in development plans can be clarified and the influence of early consideration and comparison of different scenarios for municipal urban and neighborhood development can be demonstrated. Advancing standardization (system, management and technical standards) and digitalization (data availability) in the field of neighbourhood planning and development will allow the potential to be further exploited in the future.
    Publicationtype: Conference Paper
      8  49
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: with files ,
    Geometric rule check with Answer Set Programming for barrier-free navigation
    (Technische Universität Hamburg, Institut für Digitales und Autonomes Bauen, 2024-09-18)
    Kurzawa, Marian
    The topic of rule-based navigation within buildings is an area of current research. The objective to make a public building accessible for all user groups requires the implementation of complex geometric rule checks. This paper defines exemplary rules based on the German building code DIN 18040-1 and implements rule checks using a declarative programming approach (Answer Set Programming). The results indicate that the declarative implementation has some significant limitations in terms of complexity (linear solver). However, it also offers a promising approach to constraint-based geometric rule checking, which could be a valuable contribution to future research.
    Publicationtype: Conference Paper
      9  70
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: with files ,
    Automated Inspection of Obstructed Fire Extinguishers Using Amodal Instance Segmentation
    (Technische Universität Hamburg, Institut für Digitales und Autonomes Bauen, 2024-09-18)
    Heinbach, Jan Hendrik
    ;
    Aziz, Angelina
    Fire safety inspections are essential to ensure the safety of occupants during a fire outbreak. These inspections involve checking various items, such as fire safety equipment (FSE), to ensure they are unobstructed and fully functional. Recent research has highlighted the potential of machine learning and computer vision in automating and enhancing fire safety inspection processes using image analysis. However, identifying obstacles or potential obstructions in front of fire extinguishers effectively remains a challenge. The research focuses on reviewing documented images to identify instances where extinguishers are obstructed, either partially or fully. This study proposes a novel approach to address this challenge by combining modal and amodal instance segmentation models to evaluate the level of obstruction. One conducts classical (modal) instance segmentation of visible fire extinguisher parts, while the other performs amodal segmentation. Additionally, the annotation and dataset creation for amodal segmentation tasks is addressed. The study generates obstacles on images from both open-source and self-created datasets containing (unblocked) fire extinguishers. This approach requires only one modal annotation iteration to generate modal and amodal annotation data. Results demonstrate the effectiveness of the proposed approach in detecting covered or partially blocked extinguishers. Future research aims to refine amodal mask results and extend the approach to other FSE components, further enhancing fire safety inspection processes.
    Publicationtype: Conference Paper
      19  87
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: with files ,
    Tagungsband des 35. Forum Bauinformatik 2024
    (Technische Universität Hamburg, Institut für Digitales und Autonomes Bauen, 2024-09-18)
    Publicationtype: Conference Proceedings
      385  283
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: with files ,
    Enabling Circular Construction: Evaluating ICDD for Effective Deconstruction Processes
    (Technische Universität Hamburg, Institut für Digitales und Autonomes Bauen, 2024-09-18)
    Jung, Victoria
    The construction industry faces significant challenges related to information loss, from preproduction, assembly and operation through to eventual deconstruction. Furthermore, the urgent need to decarbonise the construction sector demands the reuse of building materials. The use of existing building materials as secondary resources can make a significant contribution to sustainability goals. However, many deconstruction and material reuse initiatives are hindered by insufficient information available from the planning, manufacturing, and operational phases. In response to these challenges and aiming to maximise material reusability, this paper evaluates the Information Container for Linked Document Delivery (ICDD) as a long-term data storage solution for supporting circular construction practices. The study investigates how ICDD can mitigate information loss during transitions from pre-production, on-site assembly, and operation to deconstruction by archiving relevant deconstruction information. It identifies key deconstruction data requirements and information preservation standards. The application of the ICDD framework is demonstrated through a case study on the deconstruction of an assembled steel girder.
    Publicationtype: Conference Paper
      28  64
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: with files ,
    DiggiTwin : End-to-end use of digital twins to realize a climate-neutral building stock
    (Technische Universität Hamburg, Institut für Digitales und Autonomes Bauen, 2024-09-18)
    Badri, Sriram
    ;
    Mohan, Nijanthan
    ;
    Oyen, Marc
    ;
    Schnittcher, Lukas
    The construction sector is one of the most resource-intensive sectors and responsible for a considerable share of energy consumption and greenhouse gas emissions. In order to achieve the sector targets of the German government's climate protection plan, the planning, construction, operation, maintenance and dismantling of buildings must be completely rethought and reassessed. This paper proposes an end-to-end digital method which captures the entire life cycle of a building. An interdisciplinary work that combines expertise from the fields of computer science, electrical, civil and energy engineering and tests the method on existing buildings at Aachen University of Applied Science with a main focus on optimising the building's energy consumption. The digital twin is created using methods from the field of Building Information Modelling and linked with sensor technology, data analysis and artificial intelligence in order to identify anomalies in energy consumption. With the availability of geometric, functional and real-time data from the sensors, one can identify key performance indicators relevant to the respective use cases and simulate "what if" scenarios by making predictions to achieve optimum results in terms of sustainability.
    Publicationtype: Conference Paper
      12  52
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: with files ,
    Distance-based Loss Function for Machine Learning in Image Segmentation of Concrete Cracks
    (Technische Universität Hamburg, Institut für Digitales und Autonomes Bauen, 2024-09-18)
    Özcan, Baris
    ;
    Schmiedecke, Fabian Alexander
    Crack detection is essential for maintaining the integrity and safety of infrastructure such as bridges, roads, and buildings. Traditional manual inspection methods are labor-intensive and error-prone, which underscores the need for automated solutions. Advances in machine learning have shown promise in automating this task, but further improvements are necessary to address specific challenges, such as the thin and elongated nature of cracks, varying lighting conditions, and background noise. This paper presents a refined loss function designed to enhance the performance of machine learning models in detecting fine-structured concrete cracks. This loss function considers the spatial distances between predicted and actual crack locations, penalizing false positives that are far from true crack positions. In this way, our approach emphasizes the thin nature and continuity of cracks, ensuring that even the smallest features are accurately detected. Our initial experiments demonstrate that this strategy offers a more accurate and reliable solution to crack detection.
    Publicationtype: Conference Paper
      34  51
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: with files ,
    Implementing information container to link multi-models for semantic digital twins
    (Technische Universität Hamburg, Institut für Digitales und Autonomes Bauen, 2024-09-18)
    Zhang, Yingying
    Infrastructure Digital Twins (DTs) are commonly understood as up-to-date virtual representations of the physical infrastructure assets. The Digital Twins data pattern contains not only geometric and spatial aspects of the physical entities but also incorporates heterogeneous information including specifications, sensor data, performance metrics, maintenance records, and operational reports. At the same time, the continued expansion of the Digital Twin system without proper modeling, decoupling, and optimization of control workflows will further reduce its manageability and reliability. This paper presents a data archiving method using an Information Container for linked Document Delivery (ICDD), which is primarily based on ISO 21597, to containerize heterogeneous Digital Twins payload in arbitrary formats and provide validation services. The proposed container uses a standardized structure to implement services such as data linking, version control, and access control, thus making the Digital Twin data archiving more efficient and reliable.
    Publicationtype: Conference Paper
      78  86
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: with files ,
    Deriving Fabrication Information from BIM for Automated Robotic Task Planning
    (Technische Universität Hamburg, Institut für Digitales und Autonomes Bauen, 2024-09-18)
    Brinkhoff, Maikel Jean Silvo
    ;
    Kolani, Mohammad Reza
    Construction robotics enables the integration of multiple technologies (e.g., Building Information Modelling, Artificial Intelligence and Additive Manufacturing), thus presenting an opportunity for further productivity gains for the construction industry. However, a key obstacle lies in generating fine-grained information required for robots to plan autonomous tasks. To achieve reliable robot-based construction automation, information about the product design to be built and the status of construction progress must be available to the robot systems in real time. Building Information Modeling (BIM) holds promise in converting high-level building information into the requisite level of detail for robotic operations. One approach is to enrich the data from Industry Foundation Classes (IFC) models with construction data and convert it into a robotic format for robot task planning. We propose leveraging and extending the data extracted from BIM models to integrate with Robotic Operating Systems (ROS), a prevalent framework for robot control. The framework is evaluated through robotised bricklaying realised by MoveIt, and visualised using Rviz.
    Publicationtype: Conference Paper
      40  94
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: with files ,
    Nachhaltigkeitsbewertungen durch IoT-gestützte Auswertung von Nutzerverhalten im Rahmen des As-Used BIM
    (Technische Universität Hamburg, Institut für Digitales und Autonomes Bauen, 2024-09-18)
    Gehring, Maximilian
    ;
    Luo, Yunqing
    Gebäude stellen einen wesentlichen Teil des weltweiten Energieverbrauchs und der CO2-Emissionen dar, insbesondere während ihres Betriebs. Zur Beurteilung ihrer Nachhaltigkeit und Energieeffizienz werden verschiedene Verfahren wie das ESG-Rating angewendet, vor allem im Kontext des Asset Managements großer Gebäudeportfolios. Während der Planung wird der Energiebedarf eines Gebäudes geschätzt. Da viele Gebäude ineffizient betrieben werden, ist es von großem Interesse anhand des tatsächlichen Nutzerverhaltens eine genauere Bewertung der Nachhaltigkeit zu ermöglichen. Diese Forschung wird durch den vermehrten Einsatz von IoT-Technologie unterstützt, die eine Echtzeitdatenerfassung ermöglicht. Die Integration des Building Information Model (BIM) und IoT birgt jedoch technische und datenschutzrechtliche Herausforderungen. Besonders während der Betriebsphase bleiben Daten oft isoliert und können nicht nahtlos zwischen verschiedenen Systemen ausgetauscht werden. In diesem Kontext wird ein Konzept entwickelt, das darauf abzielt die Gebäudenachhaltigkeit basierend auf dem Nutzerverhalten innerhalb von BIM unter Verwendung von IoT-Sensordaten zu bewerten. Durch eine praktische Anwendung wird dieses Konzept veranschaulicht und trägt zur weiteren Optimierung der Energieeffizienz von Gebäuden bei.
    Publicationtype: Conference Paper
      23  89