Attitude Control of a Variant Flying Wing UAV Based on L1 Adaptive and Fuzzy Clustering

This study presents a full-envelope attitude-stabilisation and trajectory-tracking strategy for morphing flying-wing UAVs operating in highly nonlinear and strongly coupled conditions. The approach integrates fuzzy C-means (FCM) envelope partitioning with L1 adaptive control. Small-disturbance linear models are first generated at multiple altitude–Mach trim points; the FCM algorithm then performs unsupervised clustering in the state space, yielding representative subintervals that capture local flight-dynamic characteristics. The optimal cluster number and fuzziness exponent are selected using the partition coefficient, partition index, partition entropy, and Xie–Beni indices. For each sub-interval, an LQR baseline controller is designed and augmented by an L1 adaptive compensator, where a low-pass filter decouples adaptation from robustness to guarantee specified transient-performance bounds under matched/unmatched uncertainties, actuator saturation, and external disturbances. A feed-forward pre-filter realises online decoupling of the multi-input multi-output channels, thereby enhancing adaptability to variable sweep angles and large aerodynamic variations. Simulations covering low-speed/small-sweep and high-speed/large-sweep scenarios demonstrate that the proposed method sustains robust stability across the clustered envelope, outperforming conventional control schemes and confirming its engineering applicability.