Automated Prognostics and Health Management (PHM) is a requirement for the advanced military aircraft. PHM is the key to achieving true condition-based maintenance. PHM processing strategies include modules for the detection, diagnosis and prognosis of known fault conditions. However in real operations there will also occur faults and other off-nominal operations that were never anticipated nor ever encountered before. We call these events anomalies. Missing the presence of an anomaly could potentially be catastrophic with the loss of the pilot and aircraft. We have developed a neural net approach for performing anomaly detection. The neural net anomaly detector 'learns' to recognize consistent sets of multiple input sensor signal patterns from known nominal data. It is generic and has been applied to a variety of aircraft subsystems and for fusion with other detectors with excellent results. Presented are a description of the neural net anomaly detector and the application to advanced military aircraft.
Anomaly detection for advanced military aircraft using neural networks
2001 IEEE Aerospace Conference Proceedings (Cat. No.01TH8542) ; 6 ; 3113-3123 vol.6
01.01.2001
1863423 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch