Single Network Adaptive Critic (SNAC) Architecture for Optimal Tracking Control of a Morphing Aircraft during a Pull-up Maneuver

Abstract

In this paper, we discuss the application of a Single Network Adaptive Critic (SNAC) tracking controller on a morphing fighter aircraft modeled as a time-varying system. The performance of the aircraft is investigated from a flight dynamics perspective during a pull-up maneuver; and the time scale over which the morphing occurs is of the same order as the flight dynamics, due to which the influence of time-varying effects is significant. The time varying dynamical equations are adopted for a fighter aircraft which is assumed to be equipped with a variable-sweep wing. The SNAC controller is implemented on the longitudinal dynamic model of this aircraft. The neural network is trained to provide optimal tracking control over the aircraft flight envelope state space as the wing is swept along a specific morphing trajectory during the maneuver. Nomenclaturek = discrete time index j = sweep angle trajectory index = state input = co-state = control = lift-curve slope = static longitudinal stability derivative coefficient = sweep angle = time = System matrix = Control matrix = longitudinal velocity = normal velocity = pitch rate = pitch angle S = solution of Joseph stabilized version of Riccati equation Q = State weighting matrix R = Control weighting matrix = sampling time tol = training tolerance

Attitude-Tracking Control for Over-Actuated Tailless UAVs at Cruise Using Adaptive Dynamic Programming

“…With the development of the aviation industry, modern flight control is no longer satisfied with just ensuring flight stability. Many researchers [30][31][32][33][34] began to consider how to track the command signal optimally.…”

Adaptive Critic Control For Aircraft Lateral-Directional Dynamics

“…Until now several RL Flight Controllers have been proposed with different ACD frameworks. [12][13][14][15][16][17][18][19][20][21] One limitation of these controllers is that they have an exorbitant computational requirement. This requirement comes from learning two different functions with separate function approximation structures.…”

Adaptive Neural Control Based on High Order Integral Chained Differentiator for Morphing Aircraft

“…For a linear morphing aircraft dynamic model, an indirect adaptive control method is designed in [6], which comprises the receding horizon optimal control law coupled with the modified sequential least squares parameter identification. In [20], a single network adaptive critic tracking controller design for a morphing aircraft is studied, wherein the set of initial weights of the neural network is determined by using a linear system model, which requires offline pretraining. Based on the concepts of feedback linearization, in [21], a combination of dynamic inversion and structured model reference adaptive control is used for the control of a morphing air vehicle.…”