Search

This study explores the potential of Blockchain (BC)-enabled Digital Twins (DT) using qualitative semi-structured interviews to investigate the perception of stakeholders in the Architectural, Engineering, Construction and Facility Management (AEC-FM) industry on the relevance of BC-enabled DTs in augmenting stakeholder collaboration. The findings revealed that most interviewees perceived the potential of a BC-enabled DT in fostering stakeholder collaboration, leading to enhanced project delivery. Some participants viewed affordability drivers, whilst some highlighted the desire to fulfil client demands as influencing drivers for BC-enabled DT implementation in the AEC-FM industry. The study’s empirical findings align with evidence from other industrial sectors, proving that BC can ensure data integrity in a decentralised peer-to-peer framework, whilst DTs can leverage that data for effective and reliable decision-making. In the AEC-FM industry, these technologies are nascent; however, their potential integration could tackle critical issues regarding stakeholder collaboration and information fragmentation, leading to value generation in a decentralised and immutable manner. This study offers insights into implementation strategies for a BC-enabled DT collaborative environment and contributes to accelerating the industry’s approach to digital transformation

As mixed-reality (XR) technology becomes more available, virtually simulated training scenarios have shown great potential in enhancing training effectiveness. Realistic virtual representation plays a crucial role in creating immersive experiences that closely mimic real-world scenarios. With reference to previous methodological developments in the creation of information-rich digital reconstructions, this paper proposes a framework encompassing key components of the 3D scanning pipeline. While 3D scanning techniques have advanced significantly, several challenges persist in the field. These challenges include data acquisition, noise reduction, mesh and texture optimisation, and separation of components for independent interaction. These complexities necessitate the search for an optimised framework that addresses these challenges and provides practical solutions for creating realistic virtual representations in immersive training environments. The following exploration acknowledges and addresses challenges presented by the photogrammetry and laser-scanning pipeline, seeking to prepare scanned assets for real-time virtual simulation in a games-engine. This methodology employs both a camera and handheld laser-scanner for accurate data acquisition. Reality Capture is used to combine the geometric data and surface detail of the equipment. To clean the scanned asset, Blender is used for mesh retopology and reprojection of scanned textures, and attention given to correct lighting details and normal mapping, thus preparing the equipment to be interacted with by Virtual Reality (VR) users within Unreal Engine. By combining these elements, the proposed framework enables realistic representation of industrial equipment for the creation of training scenarios that closely resemble real-world contexts

Efficient optimization of business processes required a profound understanding of expertise provided by domain specialists. However, extracting such insights can indeed be a laborious and time-consuming endeavour. This paper introduces the Multi-Aspectual Knowledge Elicitation framework (MAKE4ML) — a novel approach designed to effortlessly and effectively extract valuable information from domain experts. This framework inherently facilitates the development of machine-learning models capable of optimizing business processes, thereby diminishing reliance on experts. The framework's application within a food warehouse company is showcased, specifically targeting the enhancement of the procurement process. The employed methodology revolves around conducting comprehensive interviews with procurement experts, thereby enabling a meticulous exploration of diverse facets inherent to a business process. Subsequently, the gathered insights are employed to conceive and calibrate a machine learning model (time series forecasting). This model effectively emulates the domain experts' proficiency, offering invaluable decision-oriented insights. The outcomes of this study show that our framework allows efficient knowledge elicitation, which is a pivotal factor in formulating and deploying a bespoke machine-learning model. The proposed approach can be extended into various other business processes, thereby paving the way for operational refinement, cost reduction, and amplified efficiency

Within the overarching theme of “Managing the Digital Transformation of Construction Industry” the 23rd International Conference on Construction Applications of Virtual Reality (CONVR 2023) presented 123 high-quality contributions on the topics of: Virtual and Augmented Reality (VR/AR), Building Information Modeling (BIM), Simulation and Automation, Computer Vision, Data Science, Artificial Intelligence, Linked Data, Semantic Web, Blockchain, Digital Twins, Health & Safety and Construction site management, Green buildings, Occupant-centric design and operation, Internet of Everything. The editors trust that this publication can stimulate and inspire academics, scholars and industry experts in the field, driving innovation, growth and global collaboration among researchers and stakeholders.