In this paper, adaptive critic based neural networks have been used to design a controller for a benchmark problem in aircraft autolanding. The adaptive critic control methodology comprises successive adaptations of two neural networks, namely action and critic network (which approximate the Hamiltonian equations associated with optimal control theory) until closed loop optimal control is achieved. The autolanding problem deals with longitudinal dynamics of an aircraft which is to be landed in a specified touchdown region (within acceptable ranges of speed, pitch angle and sink rate) in the presence of wind disturbances and gusts using elevator deflection as the control for glideslope and flare modes. The performance of the neurocontroller is compared to that of a conventional proportional-integral-differential (PID) controller. The results show that the neurocontrollers have good potential for aircraft applications
S. N. Balakrishnan and G. Saini, "Adaptive Critic Based Neurocontroller for Autolanding of Aircrafts," Proceedings of the 1997 American Control Conference, 1997, Institute of Electrical and Electronics Engineers (IEEE), Jan 1997.
The definitive version is available at http://dx.doi.org/10.1109/ACC.1997.609699
1997 American Control Conference, 1997
Mechanical and Aerospace Engineering
Keywords and Phrases
Hamiltonian Equations; PID Controller; Adaptive Control; Adaptive Critic Based Neural Networks; Aircraft Autolanding; Aircraft Landing Guidance; Autopilot; Closed Loop Optimal Control; Control System Synthesis; Elevator Deflection; Flare Mode; Glideslope Mode; Longitudinal Dynamics; Neurocontroller; Neurocontrollers; Wind Disturbances; Wind Gusts
Article - Conference proceedings
© 1997 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.