Shen, Xiaohan (2025) Vision-based information management using digital construction knowledge graphs to integrate data in digital twins for prefabricated construction. PhD thesis, University of New South Wales, Australia.
Abstract
Amid increasing demands for efficiency, safety, and digitalisation in the construction industry, vision based technologies such as site cameras and object detection algorithms are being widely adopted. However, current approaches lack a robust framework for integrating this unstructured visual data with Building Information Modelling (BIM), limiting their utility in Digital Twin (DT) systems. This research addresses this gap by proposing a novel Semantic-driven Prefabricated Digital Twin (SPCDT) tailored for prefabricated construction. The novelty of this work lies in the development of a Vision-based Ontology for Construction (VOC) and a Comprehensive Construction Knowledge Graph (Con-KG), which enable the transformation of visual data into machine-readable, queryable, and semantically enriched representations. Machine Learning (ML) models (Mask R-CNN, You Only Look Once, version 8 (YOLOv8)) are used to detect and track prefabricated components on construction sites, and their outputs are semantically integrated with BIM data using Resource Description Framework (RDF) and SPARQL Protocol and RDF Query Language (SPARQL) technologies. The value of this research is demonstrated through a real-world case study, where the system enables automated progress monitoring, and data dimension transformation. The proposed approach advances construction informatics by improving data coherence, usability, and interoperability in DT. It offers a scalable foundation for future integration of Virtual Reality (VR) / Augmented Reality (AR) interfaces, Artificial Intelligence (AI)-driven reasoning, and real-time feedback mechanisms, contributing to smarter and more adaptive construction workflows.
| Item Type: | Thesis (Doctoral) |
|---|---|
| Thesis advisor: | Sepasgozar, Mohammad Ebrahimzade; Ostwald, Michael and Wang, Changxin |
| Uncontrolled Keywords: | construction knowledge graph; ontology; digital twin; construction management; information management; prefabricated construction |
| Index terms: | efficiency, building information modelling, digital construction, case study, transformation, virtual reality, construction industry, dimension, interoperability, artificial intelligence, prefabricated component, reasoning, digitalization, usability, construction site, informatic, ontology, integration, progress monitoring, coherence, augmented reality, machine learning, workflow, digital twin, object detection |
| Subjects: | computer vision, cognitive psychology, digital engineering, human factors and perception, visualization, digital technology, performance management, education and knowledge transfer, management, project controls, organizational analysis, information systems, information science, systems and processes, industry analysis, virtual reality, user-centered design, business, data collection methods, design methods, work location, health monitoring assessment and metrics, artificial intelligence |
| Topics: | Health and Safety, Quality Management, Research Practice, Business Strategy, Digital Applications, Design Practice, Organizational Design, Site Management, Time Control |
| Descriptive scope: | 4 PCTE |
N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here