SSME parameter estimation using radial basis function neural networks

Author

Wheeler, Kevin R. ; Dhawan, Atam P.

Author_Institution

Dept. of Electr. & Comput. Eng., Cincinnati Univ., OH, USA

Volume

5

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

3352

Abstract

Radial basis function neural networks (RBFNN) were used to estimate Space Shuttle main engine (SSME) sensor values for sensor validation. The high pressure oxidizer turbine (HPOT) discharge temperature, a redlined parameter, was estimated during the startup transient of nominal engine operation and during simulated input sensor failures. The K-Means clustering algorithm was used on the data for placement of the basis function centers. The performance of the RBFNN is compared with that of a feedforward neural network trained with the Quickprop learning algorithm

Keywords

aerospace computing; aerospace engines; feedforward neural nets; parameter estimation; sensors; space vehicles; K-means clustering; Quickprop learning algorithm; Space Shuttle main engine; discharge temperature; feedforward neural network; high pressure oxidizer turbine; input sensor failures; parameter estimation; radial basis function neural networks; redlined parameter; sensor validation; startup transient; Artificial neural networks; Clustering algorithms; Engines; Feedforward neural networks; Neural networks; Parameter estimation; Radial basis function networks; Space shuttles; Temperature sensors; Turbines;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374774

Filename

374774