Gain scheduling for fly-by-throttle flight control using neural networks

Author

Chu, Chung-Kuang ; Yu, Gwo-Ruey ; Jonckheere, Edmond A. ; Youssef, Hussein M.

Author_Institution

Dept. of Electr. Eng. Syst., Univ. of Southern California, Los Angeles, CA, USA

Volume

2

fYear

1996

fDate

11-13 Dec 1996

Firstpage

1557

Abstract

A neural network approach to gain scheduling linear dynamic controllers for propulsion controlled aircraft (PCA) system is introduced. The linear controllers are synthesized by an H_∞ method to solve the “model matching problem” for the flown-by-throttle crippled aircraft to match the nominal aircraft response at distinct flight conditions. The radial basis network is then applied to train the gain scheduling controller. A simulation on the pitch control design of an L-1011 under emergency fly-by-throttle control demonstrates the concept

Keywords

H^∞ control; aircraft control; control system synthesis; feedforward neural nets; model reference adaptive control systems; neurocontrollers; H_∞ method; L-1011; PCA system; crippled aircraft; emergency fly-by-throttle control; fly-by-throttle flight control; gain scheduling; gain scheduling linear dynamic controllers; linear controller synthesis; model matching problem; neural networks; pitch control design; propulsion controlled aircraft system; radial basis network; Aerospace control; Aircraft propulsion; Control design; Control system synthesis; Control systems; Dynamic scheduling; Gain; Network synthesis; Neural networks; Principal component analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Decision and Control, 1996., Proceedings of the 35th IEEE Conference on

Conference_Location

Kobe

ISSN

0191-2216

Print_ISBN

0-7803-3590-2

Type

conf

DOI

10.1109/CDC.1996.572744

Filename

572744