NASA NTRS · 20110014231
Diagnosing Intermittent and Persistent Faults using Static Bayesian Networks
Abstract
Both intermittent and persistent faults may occur in a wide range of systems. We present in this paper the introduction of intermittent fault handling techniques into ProDiagnose, an algorithm that previously only handled persistent faults. We discuss novel algorithmic techniques as well as how our static Bayesian networks help diagnose, in an integrated manner, a range of intermittent and persistent faults. Through experiments with data from the ADAPT electrical power system test bed, generated as part of the Second International Diagnostic Competition (DXC-10), we show that this novel variant of ProDiagnose diagnoses intermittent faults accurately and quickly, while maintaining strong performance on persistent faults.
Keep this discovery
Explore connections, maps & timelines
Megshoel, Ole Jakob. 2010-10-13. Diagnosing Intermittent and Persistent Faults using Static Bayesian Networks. https://searchnasa.com/record/nasa%3A20110014231/diagnosing-intermittent-and-persistent-faults-using-static-bayesian-networks
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.