Non-stationary Dynamic Bayesian Networks in Modeling of Troubleshooting Process
2009 (English)In: International Journal of Approximate Reasoning, ISSN 0888-613X, E-ISSN 1873-4731Article in journal (Other academic) Submitted
In research and industry, decision theoretic troubleshooting of complex automotive systems has recently gained increased interest. With suitable troubleshooting, uptime can be increased and repair times shortened. To perform decision theoretic troubleshooting, probability computations are needed. In this work we consider computation of these probabilities under external interventions, which changes dependency relations. We apply a non-stationary dynamic Bayesian network (nsDBN), where the interventions so called events. The events change dependency relations, and drive the nsDBN forward. In the paper, we present how to build models using event driven nsDBN, how to perform inference, and how to use the method in troubleshooting. Event driven nsDBN can be used to model any process subject to interventions, and in particular it opens for solving more general troubleshooting problems than previously presented in literature.
Place, publisher, year, edition, pages
Engineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-51927OAI: oai:DiVA.org:liu-51927DiVA: diva2:278133