Introducing an ontology based framework for dynamic hazard identification

Aziz, Abdul (2017) Introducing an ontology based framework for dynamic hazard identification. Masters thesis, Memorial University of Newfoundland.

[img] [English] PDF - Accepted Version
Available under License - The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission.

Download (11MB)


An automated hazard identification technique can substantially contribute to risk assessment efficiency. This work presents an effort to introduce a dynamic hazard identification technique, which can translate the event propagation scenario into a graphical representation with probabilistic interpretation of hazards. Expert knowledge based database structure and probabilistic data driven dynamics were implemented on an ontology-based intelligent platform. A simple demonstration utilizing semantic webbased Web Ontology Language (OWL) was transformed into the Probabilistic-OWL (PR-OWL) based Multi Entity Bayesian Network (MEBN), which was incorporated with prior probabilities, to produce Situation Specific Bayesian Networks (SSBN) referring to hazard probabilities. A generalized and detailed dynamic hazard scenario model was then developed based on this same framework following the proposed methodology. Two open-source software, Protégé and UnBBayes, were used to develop the models. Case studies with different operational and environmental scenarios were presented to demonstrate the applicability of the generic model. To verify the application, the ontology based hazard scenario model was implemented on 45 individual accidents (from the CSB Database) with different operational aspects. This model was further used for causality studies and hazard mitigation measures.

Item Type: Thesis (Masters)
Item ID: 12936
Additional Information: Includes bibliographical references (pages 87-96).
Keywords: Dynamic Hazard Identification, Ontology, Bayesian Network, Probabilistic Hazard, Safety & Risk Engineering, Ontology based Hazard Identification
Department(s): Engineering and Applied Science, Faculty of
Date: October 2017
Date Type: Submission
Library of Congress Subject Heading: Hazard mitigation; Hazard signs -- Automation

Actions (login required)

View Item View Item


Downloads per month over the past year

View more statistics