Abstract: Traditional methods for performance prediction of a turbomachinery are usually based on certain computations from a
set of data obtained in limited experiment measurements of the
machine, or the machinemodels. Since the
computational (mathematical) models used in such performance
prediction are often crude, most of the predicted results are
only correct in very small ranges around the known data
points. Beyond the limited ranges, the accuracy of the resultant
predictions decrease abruptly. Therefore, an alternative
approach, neural network technique, is studied for performance
prediction of turbomachinery. The new approach has been applied
to two typical performance prediction cases to verify its
feasibility and reliability.
Key words: BP
neural networks Turbomachine Performance prediction
Manuscript received on
May 25, 1999; revised manuscript June 22, 1999
|