Attenuation of vibratory response is an important design consideration in many aeroelastic systems, and active methods of vibration reduction have been studied extensively in this context. Synthesis of active controllers requires a good analytical model of the system to be available. In those problems in which the aeroelastic system is inherently nonlinear, a robust control scheme is difficult to implement, particularly in the presence of large uncertainties in the model. The use of artificial neural networks, with on-line learning capabilities, is explored as an approach for developing robust control strategies for such problems. In particular, the use of neural networks to mimic the behavior of a linear quadratic Gaussian controller that is applicable to nonlinear systems is presented. The helicopter rotor blade is a classic example of an aeroelastic system in which vibration reduction is an overriding concern, and in which the plant is both nonlinear and contains uncertainties. A simplified two-dimensional representation of this aeroelastic system, consisting of an airfoil with a trailing-edge control flap, is considered as a test case in the present work; both structural and aerodynamic nonlinearities are included in the problem.
Neural-network-based controller for nonlinear aeroelastic system
Unterdrückung nichtlinearer aeroelastischer Schwingungen mit Regelungssystemen auf Basis neuronaler Netze
AIAA Journal ; 36 , 2 ; 249-255
1998
7 Seiten, 13 Bilder, 1 Tabelle, 16 Quellen
Aufsatz (Zeitschrift)
Englisch
neuronales Netz , Steuerungs- und Regelungssystem , Schwingungsdämpfung , Aerodynamik , elastische Schwingung , Selbstoptimierung , Regelungsmodell , Hubschrauber , Rotor (Drehflügel) , Tragfläche (Aerodynamik) , Landeklappe , Nichtlinearität , lineare Regelung , Regelabweichung , Lernprogrammierung
Neural-Network-Based Controller for Nonlinear Aeroelastic System
Online Contents | 1998
|Suppression of nonlinear aeroelastic vibrations by learned neural network controller
Emerald Group Publishing | 2018
|