Neuro-controller design for nonlinear fighter aircraft maneuver using fully tuned RBF networks

In this paper, an on-line learning neuro-control scheme that incorporates a growing radial basis function network (GRBFN) is proposed for a nonlinear aircraft controller design. The scheme iu based on Feedback-error-learning strategy in which the neuroflight-controller (NFC) augments a conventional controller in the loop. Bq using the: Lyapunov synthesis approach, the tuni ng rule for updating all the parameters of the RBFN weights. widths and cen ters of the Gaussian functions) is derived which ensures the stability of t he overall system with improved tracking accuracy. The theoretical results are validated using simulation studies based on a nonlinear 6-DOF high perf ormance fighter aircraft undergoing a high alpha stability-axis roll maneuv er. Compared with a traditional RBFN where only the weights are tuned, a GR BFN with tuning of all the parameters can implement a more compact network structure with smaller tracking error. (C) 2001 Elsevier Science Ltd. All r ights reserved.