Bayesian networks have been proposed by many authors as the modeling technique of choice for the development of diagnostic systems. This paper describes a procedure for efficient creation of Bayesian networks for diagnostics. We have applied this procedure in diagnostic systems for diesel locomotives, satellite communication systems, and satellite testing equipment. We divide the process into several phases: problem decomposition, sub-problem definition, design and testing of a Bayesian networks for subsystems, and finally integration into a complete Bayesian network, We describe all of the steps of the network design process, especially details of knowledge acquisition and the integration of information from different sources. We develop the networks starting with the simplest forms of Bayesian networks, increasing their complexity as needed while carefully balancing model accuracy and knowledge acquisition cost.
Construction of Bayesian networks for diagnostics
2000 IEEE Aerospace Conference. Proceedings (Cat. No.00TH8484) ; 5 ; 193-200 vol.5
2000-01-01
808867 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Construction of Bayesian Networks for Diagnostics
British Library Conference Proceedings | 2000
|Evaluation of Bayesian networks used for diagnostics
IEEE | 2003
|11.0402 Evaluation of Bayesian Networks Used for Diagnostics
British Library Conference Proceedings | 2003
|Sparse Bayesian Learning for Gas Path Diagnostics
Online Contents | 2013
|Web Deployment of Bayesian Network Based Vehicle Diagnostics
SAE Technical Papers | 2001
|