DocumentCode :
8318
Title :
Reinforcement learning based controller synthesis for flexible aircraft wings
Author :
Kumar, Manoj ; Rajagopal, Karthikeyan ; Balakrishnan, Sivasubramanya N. ; Nguyen, Nhan T.
Author_Institution :
Missouri Univ. of Sci. & Technol., Rolla, MO, USA
Volume :
1
Issue :
4
fYear :
2014
fDate :
Oct. 2014
Firstpage :
435
Lastpage :
448
Abstract :
Aeroelastic study of flight vehicles has been a subject of great interest and research in the last several years. Aileron reversal and flutter related problems are due in part to the elasticity of a typical airplane. Structural dynamics of an aircraft wing due to its aeroelastic nature are characterized by partial differential equations. Controller design for these systems is very complex as compared to lumped parameter systems defined by ordinary differential equations. In this paper, a stabilizing statefeedback controller design approach is presented for the heave dynamics of a wing-fuselage model. In this study, a continuous actuator in the spatial domain is assumed. A control methodology is developed by combining the technique of “proper orthogonal decomposition” and approximate dynamic programming. The proper orthogonal decomposition technique is used to obtain a low-order nonlinear lumped parameter model of the infinite dimensional system. Then a near optimal controller is designed using the single-network-adaptive-critic technique. Furthermore, to add robustness to the nominal single-network-adaptive-critic controller against matched uncertainties, an identifier based adaptive controller is proposed. Simulation results demonstrate the effectiveness of the single-network-adaptive-critic controller augmented with adaptive controller for infinite dimensional systems.
Keywords :
actuators; adaptive control; aerospace components; aircraft control; control system synthesis; dynamic programming; learning (artificial intelligence); optimal control; partial differential equations; stability; state feedback; vehicle dynamics; aeroelastic study; aileron; aircraft wing structural dynamics; approximate dynamic programming technique; continuous actuator; control methodology; controller synthesis; flexible aircraft wings; flight vehicles; identifier based adaptive controller; infinite dimensional system; low-order nonlinear lumped parameter model; near optimal controller; ordinary differential equation; partial differential equation; proper orthogonal decomposition technique; reinforcement learning; single-network-adaptive-critic technique; stabilizing state feedback controller design approach; wing-fuselage model; Adaptation models; Adaptive control; Aircraft; Atmospheric modeling; Cost function; Learning (artificial intelligence); Method of moments; Optimal control; Single-network-adaptive-critic; adaptive control; adaptive critic; flexible wing; partial differential equation; proper orthogonal decomposition; uncertainty;
fLanguage :
English
Journal_Title :
Automatica Sinica, IEEE/CAA Journal of
Publisher :
ieee
ISSN :
2329-9266
Type :
jour
DOI :
10.1109/JAS.2014.7004670
Filename :
7004670
Link To Document :
بازگشت