DocumentCode :
3149220
Title :
Optimal controller approximation using neural and fuzzy-neural networks
Author :
Niestroy, Michael
Author_Institution :
Dept. of Aerosp. Eng. & Eng. Mech., Texas Univ., Austin, TX, USA
Volume :
1
fYear :
1996
fDate :
8-11 Sep 1996
Firstpage :
486
Abstract :
A feedforward neural network has been shown to possess the ability of approximating an optimal controller over a subspace of initial conditions. In addition to a feedforward neural network the fuzzy logic/neural network hybrid ANFIS (adaptive network based fuzzy inference system) structure has been shown to be a universal approximator. This paper discusses briefly the use of ANFIS to approximate an optimal feedback controller for the nontrivial problem of guiding a high-speed vehicle (glider) to a ground target and compares results to a three layer feedforward neural network controller. The controllers are trained using optimal open loop state and control data generated by VF02AD. Simulation results show that both controller types guide the vehicle to within 1000 ft of the target with practically no degradation in the optimal impact velocity over a range of initial conditions. The advantages and disadvantages of both controllers are discussed together with some practical limitations of the ANFIS optimal feedback controller
Keywords :
aircraft control; attitude control; feedback; feedforward neural nets; fuzzy control; fuzzy neural nets; neurocontrollers; nonlinear dynamical systems; optimal control; adaptive network based fuzzy inference system; feedback; feedforward neural network; fuzzy-neural networks; glider altitude control; nonlinear dynamical systems; optimal control; universal approximator; Adaptive control; Adaptive systems; Feedforward neural networks; Fuzzy logic; Fuzzy neural networks; Fuzzy systems; Land vehicles; Neural networks; Open loop systems; Optimal control;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Fuzzy Systems, 1996., Proceedings of the Fifth IEEE International Conference on
Conference_Location :
New Orleans, LA
Print_ISBN :
0-7803-3645-3
Type :
conf
DOI :
10.1109/FUZZY.1996.551789
Filename :
551789
Link To Document :
بازگشت