ONLINE LEARNING NONLINEAR DIRECT NEUROCONTROLLERS FOR RESTRUCTURABLE CONTROL-SYSTEMS

This paper describes an innovative approach to the problem of the on-l ine determination of a control law in order to achieve a dynamic recon figuration of an aircraft that has sustained extensive damage to a vit al control surface, The approach consists of the use of on-line learni ng neural network controllers that have the capability of bringing an aircraft, whose dynamics can become unstable after a substantial damag e, back to an equilibrium condition. This goal has been achieved throu gh the use of a specific training algorithm, the extended back-propaga tion algorithm (EBPA), and proper selection of the architectures for t he neural network controllers. The EBPA has recently shown remarkable improvements over the back-propagation algorithm in terms of convergen ce time and local minimum problems. The methodology is illustrated thr ough a nonlinear dynamic simulation of a typical combat maneuver for a high-performance aircraft.