Wang, Liannian (2025) Advancing construction requirements management through 4D BIM and generative AI. PhD thesis, North Carolina State University, USA.
Abstract
Effective management of construction requirements is critical for successful project delivery. However, current management practices involve project-specific, document-based workflows with high information intensity and manual effort, leading to challenges such as limited standardisation, inefficiency, errors, and omissions. Industry solutions rely on manual inputs and static building information modelling (BIM) support, while research efforts including machine learning applications remain narrow, costly, and inaccessible. To bridge this gap, this dissertation presents a framework integrating 4D BIM and generative artificial intelligence (GenAI) to enhance automation and decision support in construction requirements management. The dissertation is organised into four studies. The first develops a comprehensive digital workflow for requirements management using 4D BIM, linking requirements to construction elements and schedules to enable real-time tracking, visual verification, and improved coordination among stakeholders. The second focuses on design change management by developing a 4D BIM-integrated Design Change Management Model (DCMM) that supports visualising sequential design revisions, ensuring data interoperability, and enhancing traceability of design impacts. The third addresses the challenge of extracting and interpreting unstructured requirement documents by developing a construction requirements-specific ontology and integrating it with a fine-tuned large language model (LLM), improving classification accuracy, scalability, and accessibility of advanced AI tools for construction professionals. The fourth presents a GenAI-assisted compliance checking system that combines ontology-informed prompting, Industry Foundation Classes (IFC) metadata grounding, and a two-step relevance ranking strategy to retrieve relevant clauses, generate structured reasoning outputs, and evaluate performance using a benchmark dataset. Together, these studies address critical gaps in current requirements management practices by combining GenAI with 4D BIM and structured domain knowledge to enhance automation, reduce manual workload, and improve the clarity and consistency of requirements processes.
| Item Type: | Thesis (Doctoral) |
|---|---|
| Thesis advisor: | Han, Kevin; Gupta, Abhinav; Jaselskis, Edward and Singh, Munindar |
| Index terms: | accessibility, management practice, automation, strategy, dataset, reasoning, standardization, workload, building information modelling, traceability, accuracy, coordination, compliance, artificial intelligence, workflow, project delivery, requirements management, documents, machine learning application, ontology, industry foundation classes, construction professional, real-time tracking, design change, data interoperability, decision support, dissertation, large language model |
| Subjects: | professional development, performance measurement, information systems, contractual arrangements, cognitive psychology, supplier oversight, research dissemination and communication, data science, artificial intelligence, education and knowledge transfer, health safety and environment, project delivery, management, data management, computational design, decision analysis, data exchange, automation and robotics, inclusive design |
| Topics: | Quality Management, Human Resources, Procurement, Supply Chain Management, Health and Safety, Engineering Principles, Information Management, Organizational Design, Design Practice, Risk Management, Digital Applications, Business Strategy, Research Practice |
| Descriptive scope: | 3 PCT |
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