Before a helicopter leaves the plant, it needs to be tuned so that its vibrations meet the required specifications helicopter track and balance is currently performed based on sensitivity coefficients' which have been statistically developed after years of production experience. The fundamental problem with using these sensitivity coefficients, however, is that they do not account for both he non-linear coupling between modifications and the non-linear effect of modifications on high amplitude vibrations. Therefore, in order to ensure the reliabiilty of the linear coefficients, only a limited number of modifications are simultaneously applied. This implies that a number of flights are performed before the aircraft is tuned, resulting in increased production and maintenance cost. In this project, we demonstrate the application of artificial neural nets in learning the nonlinear effect of modifications, so as to be able to select the appropriate set of modifications in fewer iterations (flights). The effectiveness of neural nets for track and balance is currently being tested at the Sikorsky production line.
Helicopter track and balance with artifical neural nets
Abstimmung der Richtungsstabilität und der Balance von Hubschraubern mit Hilfe neuronaler Netze
1992
8 Seiten, 11 Bilder, 6 Tabellen, 10 Quellen
Aufsatz (Konferenz)
Englisch
Investigation on Helicopter Rotor Track and Balance
British Library Conference Proceedings | 1997
|HELICOPTER TRACK AND BALANCE BY INTERVAL MODELING
British Library Conference Proceedings | 2001
|A PROBABILITY-BASED APPROACH TO HELICOPTER TRACK AND BALANCE
British Library Conference Proceedings | 2003
|Plant Growth Model Using Artifical Neural Networks
SAE Technical Papers | 1997
|NTRS | 1961
|