University of Birmingham
Derailment risk analysis, monitoring and management at railway turnouts
Abstract
dc:description.abstractThe general objective of the thesis is to develop a number of novel Bayesian- based mathematical models that are applicable for the railway sector. Hence, it is assumed that the thesis will be an element of, or facilitate future AI (Artificial Intelligence) Risk Management and Safety Standards, which will inevitably be developed for the sector. The thesis primarily concentrates on applications that support decision-making processes, related to derailments at railway turnout sys- tem. The first objective is to determine, evaluate and prioritise the risk factors that cause derailments; secondly, it will identify and demonstrate the relationship among these driving factors; and finally, it will show the prospective usage of Bayesian networks as an intuitive modelling instrument that makes the process of modelling risk more transparent and consistent. In order to achieve the aforementioned objectives, this thesis is established on various novel methodological approaches using either qualitative or quantitative methods, or a combination of the two. A comprehensive review is conducted in order to interpret and acquire an in-depth understanding of suitable methods of analysing risk in addition to five original studies on the subjects of component failures, human errors and the environmental impact to measure, rank, categorise, and identify the factors that cause derailment in the railway sector. The proposed novel methodologies in addition to their MATLAB and R codes are introduced for utilisation in a developed framework for analysing, monitoring and managing risk for railway turnout.
Degree
thesis:*- Name dc:type.qualificationname
- d_ph
- Level dc:type.qualificationlevel
- d_ph
- Grantor dc:publisher.institution
- University of Birmingham
- Year dc:date.issued
- 2019
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Dindar, Serdar
- ORCID person:identifier.orcid
Subjects
dc:subject × 1Rights
- Language dc:language.dcterms_iso639_2
- eng
Identifiers
dc:identifier.*- Dc Identifier Grantnumber
- H2020-RISE Project No. 691135