Gabriela Medina-Oliva

Overview on Bayesian networks applications for dependability, risk analysis and maintenance areas

In this paper, a bibliographical review over the last decade is presented on the application of Bayesian networks to dependability, risk analysis and maintenance. It is shown an increasing trend of the literature related to these domains. This trend is due to the benefits that Bayesian networks provide in contrast with other classical methods of dependability analysis such as Markov Chains, Fault Trees and Petri Nets. Some of these benefits are the capability to model complex systems, to make predictions as well as diagnostics, to compute exactly the occurrence probability of an event, to update the calculations according to evidences, to represent multi-modal variables and to help modeling user-friendly by a graphical and compact approach. This review is based on an extraction of 200 specific references in dependability, risk analysis and maintenance applications among a database with 7000 Bayesian network references. The most representatives are presented, then discussed and some perspectives of work are provided.

Fault Diagnosis System Based on Ontology for Fleet Case Reused

Maintenance plays a key role by improving system availability, performance efficiency, and product quality. Condition based maintenance plus (CBM+) and Prognostics and Health Management (PHM) maintenance strategies propose new maintenance approaches in a “predict and prevent” view. In these anticipative approaches, early diagnosis plays a key role. Such a diagnosis is hard since only partial information is available. We propose to use the benefit of past event occurred on similar systems to help diagnosis. The originality of the approach lies in the consideration of systems that are not identical to the one under study. Indeed, similar systems are considered in order to gather more relevant and wider information to handle current diagnosis case. The level of similarity is controlled using an ontology in order to broaden or narrow the search.