Neural Flight Control System Research Articles

Elaboration of simulation complex for realization of adaptive neural flight control system to be used on commercial aircraft in compliance with EASA-FAA standards

Elaboration of simulation complex for realization of adaptive neural flight control system to be used on commercial aircraft in compliance with EASA-FAA standards

Direct adaptive neural flight control system for an unstable unmanned aircraft

A direct adaptive controller design using neural network is proposed for an unstable unmanned research aircraft similar in configuration to combat aircraft. The control law to track the pitch rate command is developed based on system theory. Neural network with linear filters and back propagation through time learning algorithm is used to approximate the control law. The bounded signal requirement to develop the neural controller is circumvented using an off-line finite time training scheme, which provides the necessary stability and tracking performances. On-line learning scheme is implemented to compensate for uncertainties due to variation in aerodynamic coefficients, control surface failures and also variations in center of gravity position. The performance of the proposed control scheme is validated at different flight conditions. The disturbance rejection capability of the neural controller is analyzed in the presence of the realistic gust and sensor noises. Hardware-in-loop simulation is also carried out to study the behavior of control surface deflections in real-time.

FLIGHT CONTROL SYSTEM DESIGN FOR COMMERCIAL AIRCRAFT USING NEURAL NETWORKS

This paper describes a neural network based approach for flight control design of commercial aircraft. A neural flight control system is used to actuate the gains of a linear controller for gain scheduling purposes without any explicit system identification. The neural network system uses reference models to specify desired handling qualities. Simulation results demonstrate the good tracking performance of the proposed control approach and the learning capability of the proposed neural network controller by showing rapid convergence of the network weights.