ADAPTIVE ROBUST BANK-TO-TURN MISSILE AUTOPILOT DESIGN USING NEURAL NETWORKS

An adaptive robust neural-network-based control approach is proposed f or bank-to-turn missile autopilot design. Feedforward neural networks with sigmoid hidden units are analyzed in detail for controller design . Without prior knowledge of the so-called optimal neural networks, we design a controller that exploits the advantages of both neural netwo rks and robust adaptive control theory. For this scheme, a stable adap tive law is determined by using the Lyapunov theory, and the boundedne ss of all signals in the closed-loop system is guaranteed. No prior of fline training phase is necessary, and only a single neural network is employed. It is shown that the tracking errors converge to a neighbor hood of zero. Performance of the controller is demonstrated by means o f simulations.