Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Knowledge representation, storage and retrieval for BIM supported building evacuation design

Boje, Calin Petrut 2018. Knowledge representation, storage and retrieval for BIM supported building evacuation design. PhD Thesis, Cardiff University.
Item availability restricted.

[thumbnail of Final thesis_corrections_12062018.pdf]
PDF - Accepted Post-Print Version
Download (13MB) | Preview
[thumbnail of Electronic Thesis and Dissertation Publication Form] PDF (Electronic Thesis and Dissertation Publication Form) - Supplemental Material
Restricted to Repository staff only

Download (139kB)


Safe evacuation design is a complex process, which relies on crowd simulation models when assessing the performance of large or complicated building layouts. Current simulation methods and tools lack automation and are limited to geometry when relying on BIM interoperability. The use of semantic web linked data is seen as a step towards integrating and leveraging current digital resources to facilitate intelligent and automatic design capable of knowledge processing. An intelligent software system has been developed which is capable of integrating multiple information sources and which can facilitate fast automatic construction and analysis of crowd simulation models for design decision support. The system includes several developed OWL ontologies and SWRL rules which represent design knowledge from the fire evacuation field, thus being able to process and store data about a multi-disciplinary design field. The work conducted towards the development of the system involved investigation into crowd analysis tools, evacuation and digital building models. The ontology and knowledge operators are presented and discussed, providing insight into future exploration of such methods with the aim of outlining their benefits and limitations. The system and knowledge engineered have been tested using a case study, proving they are capable of fast processing and correct interpretation of model data.

Item Type: Thesis (PhD)
Date Type: Completion
Status: Unpublished
Schools: Engineering
Uncontrolled Keywords: Evacuation, Design, Crowd Simulation, Building Information Modelling, Ontology, Industry Foundation Classes
Date of First Compliant Deposit: 4 July 2018
Last Modified: 30 Mar 2021 12:56

Actions (repository staff only)

Edit Item Edit Item


Downloads per month over past year

View more statistics