A HYBRID AUTOPILOT FOR BTT STEERING USING RBF NEURAL NETS

摘要

A hybrid neural adaptive control scheme is proposed to alleviate the tracking problems associated with a BTT autopilot. This employs a Gaussian Radial Basis Function neural network in parallel with an independently regulated, fixed-gain lateral autopilot to adaptively compensate for roll-induced cross-coupling, time-varying aerodynamic derivatives and control surface constraints to achieve consistent tracking performance over the flight envelope. The hybrid scheme is evaluated against realistic pitch acceleration and roll rate profiles generated from a typical guidance scenario and its performance compared with constant parameter and gain scheduled autopilots.