This paper outlines the development of a Existing Building Digital Twin system for social housing in Scotland. The project focuses on enhancing retrofit planning and execution. Research methodology involved stakeholder workshops, surveys, and case-based reasoning methods. Key findings highlight the need for a decentralised, secure digital system integrating diverse data sources. The paper proposes ten components addressing various aspects of DT development, aiming to create a robust, user-friendly tool for decision-making in retrofit projects, supporting the country's transition to net-zero carbon emissions. The system is expected to offer benefits including improved energy efficiency, cost savings, and enhanced living conditions.
In the built asset industry, data-enriched models are typicallyexchanged at the file level, often via memorandumsas wrappers listing multiple files or converting to 2D PDFsfor signing. These methods pose challenges for authenticationand data integrity, even at the file level. This paperexplores integrating digital signatures into Industry FoundationClasses (IFC)-based data exchanges by identifyinga structure within the existing IFC data schema as a digitalsignature container and applying it to assign signatures toeach object. Consequently, unauthorized changes becomedetectable, fostering trust, traceability, and transparency.
Cognitive Digital Twins (CDTs) emerge as an evolution of the Digital Twin (DT) concept, incorporating cognitive capabilities to enhance data-driven decision-making in complex and dynamic systems such as healthcare. The integration of machine learning (ML) promises transformative approach to healthcare facility management (FM). This study explores key data types and application areas relevant to CDT development, derived from a review of ML implementations in healthcare. The findings categorize data types, including health records, and appointment data, alongside application areas such as decision support and waiting time prediction. These insights provide a novel foundation for CDT-driven healthcare solutions, enabling proactive management.
Road infrastructure is a complex system with interconnected subsystems, making the assessment of condition correlation crucial for predictive maintenance. However, the substantial heterogeneity of these subsystems complicates the correlation of existing data sets. To address this challenge, we propose a conceptual framework representing data sets and their spatial and temporal relationships through graphs by enhancing existing approaches with considerations of temporal dependencies. Hence, large-scale correlation analyses between heterogeneous subsystems and their related data are enabled. Validation is performed using real-world data from German infrastructure management, specifically associating traffic count data with bridge conditions based on their spatial and temporal relations.
Traditional push-based workflows in Building Information Modeling (BIM) often suffer from inefficiencies that hinder precise and effective data exchange. The following study introduces a pull-based approach designed to address challenges, induced by inefficient push-based workflows, by focusing on targeted information requests and automating validation processes. The proposed method improves data quality, ensures compliance, and streamlines workflows by minimizing redundancies, reducing coordination cycles, and prioritizing relevant data. The pull-based approach enhances digital data processes and improves stakeholder communication, providing a practical and efficient alternative to the currently dominant push-based workflows while unlocking new opportunities for BIM adoption.
Building Information Modeling (BIM) and Virtual Reality (VR) integration offers significant potential to enhance collaboration throughout the AECO project lifecycle. However, practical implementation faces challenges, including equipment constraints, technical limitations, user experience issues, and policy gaps. This study systematically reviews 36 articles, classifying these barriers and identifying key challenges and future directions in this area. The findings highlight interaction and interoperability as critical challenges, with future research needed in real-time multi-user collaboration, automated BIM-VR data synchronization, and user-friendly systems. Addressing these gaps will maximize the potential of BIM-based VR, fostering effective multidisciplinary collaboration and innovation in the AECO industry.
The construction industry struggles with data integration due to semantic heterogeneity across stakeholders and lifecycle phases. Users must handle complex formats, inconsistent naming conventions, and diverse standards, detracting from core tasks. This work presents a hybrid matching system combining lexical similarity with domain-specific pattern recognition to align terms across terminologies. Automated enrichment from standardized sources and semantic fingerprinting enable property mapping between stakeholders, domains, and formats. A Human-in-the-Loop component ensures continuous refinement via expert feedback. Real-world evaluation in facility management scenarios achieved 86.6% initial accuracy in attribute matching and significant query processing time reductions over manual approaches.
Reliance on digital technologies has revolutionized building management, but data quality remains a key challenge. This study presents a two-step approach to enhance data quality: calculating metrics like accuracy, completeness, and consistency, and applying machine-learning models to correct gaps and inconsistencies. Tested with pilot data across Europe, completeness improved from 55% to 100%, while accuracy and consistency reached 100% and 72.14%. Using a centralized data lake, the system ensures real-time synchronization for digital twins and services. This approach aligns with the Energy Performance of Buildings Directive (EPBD), advancing energy efficiency and providing scalable solutions for smart building data management.
With the Corporate Sustainability Reporting Directive (CSRD), the EU requests companies to report their greenhouse gas emissions related to energy consumption. Particularly, in verticals with complex technical environments like construction or manufacturing the tracking of individual devices and equipment is challenging. To approach this challenge a versatile and easy-to-use monitoring solution is necessary. Therefore, we propose a plug-and-play energy metering device, Meter-X, with 5G-enabled edge-cloud connectivity for live monitoring that can be installed by non-professionals. The paper describes the hardware and software stack, analyses the measurement accuracy and demonstrates the potential of the device in two field tests.
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.
