• DocumentCode
    484815
  • Title

    Development of an Intelligent System for Railway Risk Analysis

  • Author

    An, Min ; Chen, Yao ; Baker, Chris

  • Author_Institution
    Sch. of Civil Eng., Univ. of Birmingham, Birmingham
  • fYear
    2008
  • fDate
    20-22 Oct. 2008
  • Firstpage
    1
  • Lastpage
    6
  • Abstract
    This article describes the development of an intelligent system for railway risk analysis using fuzzy reasoning approach (FRA) and fuzzy analytical hierarchy decision making process (Fuzzy-AHP), which is specially designed and developed for the railways. In the system, FRA is employed to estimate the risk level (RL) of each failure event in terms of failure probability (FP) and consequent severity (CS). This allows imprecision or approximate information in risk analysis process. Fuzzy-AHP technique is incorporated into the risk model to use its advantage in determining the relative importance of the risk contributors, i.e. weight factor (WF) so that the risk assessment can be progressed from component level to the subsystem level and finally to system level. This risk assessment system can evaluate both qualitative and quantitative risk data and information associated with a railway system efficiently and effectively, which will provide railway risk analysts, managers and engineers with a method and tool to improve their safety management of railway systems and set safety standards. A case study on rolling stock asset risk analysis is used to illustrate the application of the intelligent system.
  • Keywords
    fuzzy reasoning; railway safety; risk analysis; consequent severity; failure probability; fuzzy analytical hierarchy decision making process; fuzzy reasoning approach; intelligent system; railway risk analysis; risk assessment; Risk assessment; fuzzy analytical hierarchy process; fuzzy reasoning approach; rolling stock asset;
  • fLanguage
    English
  • Publisher
    iet
  • Conference_Titel
    System Safety, 2008 3rd IET International Conference on
  • Conference_Location
    Birmingham
  • ISSN
    0537-9989
  • Print_ISBN
    978-0-86341-970-6
  • Type

    conf

  • Filename
    4781244