The transition to a circular economy in the Architecture, Engineering, and Construction (AEC) industry requires coordinated supply chain transitions. Digital tools, such as data-sharing platforms and BIM-based circular design tools, offer potential but remain underutilized, particularly among material suppliers. To bridge this adoption gap, we developed a serious game that connects digital solution developers with AEC professionals, fostering collaboration in circular construction. Tested in a national Growth Fund project, the game simulates real-world challenges, emphasizing needs for data sharing and intermediation. Future integration into lifelong learning programs will equip professionals with the skills to drive circular innovations.
HVAC systems significantly impact building energy use and operational faults can significantly reduce their efficiency. While data-driven fault detection and diagnosis techniques have become well-established, the ability to emulate faults is critical, given the lack of available fault data for algorithm training. This study develops a condensing heat exchanger emulator using thermodynamics and fault simulation. A hybrid gray-box approach with Bayesian optimization estimates heat transfer coefficients under varying conditions. Testing shows the model accurately matches nominal data and reliably simulates faults like fouling, scaling, and excess air. This tool enhances fault analysis, improving HVAC optimization and reliability.
The construction industry is increasingly adopting sustainable, resource-efficient practices requiring data-driven decisions. However, manual data preparation and lack of standardisation impede this transition. Certification systems like DGNB, quality seals like QNG and classification systems like the EU Taxonomy incorporate measurable sustainability criteria, highlighting the need for reliable data. This study utilises LLMs to extract data from product data sheets and Environmental Product Declarations, converting it to standardised JSON schema. By integrating Python and knowledge graphs, the structured data can be matched against sustainability criteria, serving as foundation for planners, contractors, and clients to make AI-based decisions for sustainable building products.
Trust is a crucial factor in construction projects, despite the industry relies heavily on teams working separately and collaborating in a temporary or informal way. This paper attempts to clearly define trust by reviewing existing research and adapting ideas from other fields to the particular challenges of construction. As the construction industry adopts more and more technology, building and maintaining this digital trust is critical to overcoming challenges such as miscommunication, delays and resistance to change. This paper provides a roadmap for understanding trust not just as a 'soft' value, but as a practical requirement for successful, modern construction projects.
This study examines integrating Digital Twin (DT) technology into Facility Management (FM) via Autodesk Tandem, focusing on connecting physical assets to digital models. By leveraging IoT data and real-time insights, the research demonstrates enhanced FM capabilities, including real-time monitoring, data visualization, and asset management. Using the Digital Built Environment Maturity Model (dbEMM), Autodesk Tandem achieves the Standard Operation maturity level, addressing the limitations of traditional FM systems. This work highlights DT’s transformative potential to bridge physical-digital gaps, improving operational efficiency and providing a strong foundation for advancing DT-driven FM practices and innovations.
Graph Neural Networks have shown promising results to make predictions for time-series data collected by IoT sensors in buildings. While the process of collecting and structuring data is mostly automated, correctly capturing the physical causalities in the models still requires domain knowledge and manual labor. In this paper, we evaluate the capabilities and challenges of Foundation Models like ChatGPT to configure the GNNs. We conduct experiments prompting two different Foundation Models to construct graphs on small and large scale and compare the resulting graphs and the performance of GNNs based on these graphs for a simulated small scale data set.
This study investigates the factors driving the adoption of 3D printing technology in construction industry, focusing on Türkiye and developing EU countries. A comprehensive literature review identified 27 key drivers, which were evaluated through a survey of 106 professionals using Relative Importance Index (RII). Results reveal that faster construction, lower rate of site accidents and fatalities, and reduction in material waste are the most significant drivers, while freedom in design due to less strict standards was found to be the least important. The research emphasizes the need for targeted initiatives to enhance the integration of 3D printing in construction projects.
Circular building practice involves creation, maintenance, repair, and reuse of components. This positioning paper highlights the lack of digital models for such practices and proposes the History Stack framework for sustainable bio-based building economy. It advocates avoiding monolithic data models in favor of flexible structures reflecting dynamic changes. Key elements include access to foundational data like material sources, fabrication methods, and design logics, ensuring adaptability throughout a building's lifecycle. The History Stack links diverse digital models, supporting the evolution of practices and heterogeneous data types aligned with EU intentions for the Building Logbook and next-generation BIM-like systems.
Previous expert systems for excavation support system (ESS) recommendations often overlooked lateral supports and water-barrier methods, limiting their applicability to small projects with a single retaining wall type. These methods were unsuitable for large-scale projects, where varying site conditions require different ESS configurations for each excavation side. This study proposes an ESS design assistant tailored for large construction projects. While LLMs like GPT-4.0 and DeepSeek show promise, they struggle with practical ESS recommendations. To address this, we developed a multi-step machine learning-based ESS recommendation system, achieving weighted F1 scores of 0.951 (retaining walls), 0.981 (water-barrier applications), and 0.831 (lateral supports).
