DL-Based Reduced-Order Modeling and Fuzzy Output Tracking Control Design With Vibration Suppression for a Flexible...

This article addresses the issue of reduced-order modeling and finite-dimensional guaranteed cost output tracking (GCOT) control design with the fuselage's elastic vibration suppression for a flexiblevariable wingspan aircraft (FVWA). The rigid-flexible coupled system dynamics of the FVWA are represented by ordinary differential equations (ODEs) and the beam equation. Via an integration of deep learning (DL) and sparse identification of nonlinear dynamics (SINDy), a reduced-order modeling framework that employs DL for dimensionality reduction and utilizes SINDy for governing dynamics identification is proposed to surmount the difficulty caused by the rigid-flexible complex dynamics. Then, a finite-dimensional fuzzy flight control algorithm is developed via the Takagi-Sugeno (T-S) fuzzy control technique and the integral control to achieve the goal of flight command tracking and the fuselage's elastic vibration suppression for the FVWA. Meanwhile, an upper bound of the quadratic flight performance index is also provided. Finally, numerical simulation results are presented to illustrate the effectiveness and superiority of the theoretical method.