Neuro-flight controllers for aircraft using Minimal Resource Allocating Networks (MRAN)

This paper presents the application of the recently developed Minimal Resou rce Allocating Network (MRAN) for aircraft flight control, with special emp hasis on its robustness and fault tolerance properties. MRAN is a dynamic R adial Basis Function network (RBFN) incorporating a growing and pruning str ategy resulting in a compact network structure. For the aircraft control ap plication presented here, a simple scheme in which MRAN aids a conventional controller using a feedback error learning mechanism is presented. The rob ustness and the fault tolerant nature of the neuro controller is illustrate d using a F8 fighter aircraft model in an autopilot mode. The objective of the controller is to follow the velocity and pitch rate pilot commands unde r large parameter variations and sudden changes in actuator time constants. Simulation results demonstrate the satisfactory performance of the MRAN ne uro-flight controller even under these faulty conditions.