HYBRID NEURAL ADAPTIVE-CONTROL FOR BANK-TO-TURN MISSILES

A novel hybrid neural adaptive bank-to-turn (BTT) lateral autopilot is described for a short-range command-to-line-of-sight (CLOS) surface-t o-air missile. This employs a multiinput-multioutput Gaussian radial b asis function (RBF) network in parallel with a constant parameter, ind ependently regulated lateral autopilot, to adaptively compensate for r oll-induced cross-coupling time-varying aerodynamic derivatives and co ntrol surface constraints, in order to achieve consistent tracking per formance over the flight envelope, The hybrid neural autopilot is eval uated in three dimensional (six-degree of freedom) simulation studies against realistic pitch acceleration and roll rate profiles generated from a typical CLOS guidance scenario, and its performance compared wi th a carefully designed gain scheduled autopilot, The results are foun d to be encouraging and clearly demonstrate the potential advantages o f the neurocontrol scheme.