HELICOPTER STATION-KEEPING - COMPARING LQR, FUZZY-LOGIC AND NEURAL-NET CONTROLLERS

Citation
D. Mclean et H. Matsuda, HELICOPTER STATION-KEEPING - COMPARING LQR, FUZZY-LOGIC AND NEURAL-NET CONTROLLERS, Engineering applications of artificial intelligence, 11(3), 1998, pp. 411-418
Citations number
11
Categorie Soggetti
Computer Science Artificial Intelligence","Robotics & Automatic Control","Computer Science Artificial Intelligence",Engineering,"Robotics & Automatic Control","Engineering, Eletrical & Electronic
ISSN journal
09521976
Volume
11
Issue
3
Year of publication
1998
Pages
411 - 418
Database
ISI
SICI code
0952-1976(1998)11:3<411:HS-CLF>2.0.ZU;2-6
Abstract
Station-keeping is a difficult flight control mode for helicopters sin ce they have little forward speed and are dynamically unstable in that mode. In this paper the designs for a fuzzy-logic controller and neur al-network (NN) controllers which are used to provide acceptable stati on-keeping performance for a single main rotor helicopter are presente d. The effectiveness of the proposed designs is established from an ex amination of a number of results obtained from a simulation of the con trolled helicopter. The required training and recall data needed for t he NN were obtained from the responses of the same helicopter type bei ng controlled in a station-keeping mode by a continuous, linear, optim al feedback control law, obtained by solving a linear quadratic regula tor problem. (C) 1998 Elsevier Science Ltd. All rights reserved.