pyBNBowTie: Python library for Bow-Tie Analysis based on Bayesian Networks

Research output: Contribution to journalConference articlepeer-review

Abstract

In addition to more conventional but often less precise methods, the risk assessment as part of the risk management process can be performed with the bow-tie analysis method. A bow-tie analysis describes the effects of causes on a top event and the resulting consequences. Bayesian networks, on the other hand, offer a mathematically concise way of describing dependencies between events under uncertainty. The mapping of bow-tie analysis into Bayesian networks is intended to make their superior calculation options available. While the mapping algorithm of a bow-tie method into a Bayesian network is described in the literature, no computer program carrying out this mapping has been found so far. In this text, a Python library, that is validated using published examples, is presented and made publicly available for mapping bow-tie methods into Bayesian networks.

Original languageEnglish
Pages (from-to)344-351
Number of pages8
JournalProcedia Computer Science
Volume180
Issue number180
DOIs
Publication statusPublished - 2021
EventInternational Conference on Industry 4.0 and Smart Manufacturing - online, Austria
Duration: 23 Nov 202025 Nov 2020
Conference number: 2

Keywords

  • Bayesian network
  • bow-tie analysis
  • risk analysis
  • risk assessment

Fingerprint

Dive into the research topics of 'pyBNBowTie: Python library for Bow-Tie Analysis based on Bayesian Networks'. Together they form a unique fingerprint.

Cite this