Title :
A neural network based, real-time algorithm for detection and mitigation of pilot induced oscillations
Author :
Cox, Chad ; Lewis, Carl ; Suchomel, Charles
Author_Institution :
Accurate Autom. Corp., Chattanooga, TN, USA
Abstract :
A neural network-based pilot-induced oscillations (PIO) detection algorithm and a PIO compensation method were shown to be highly effective during a series of piloted simulations. During PIO, the aircraft oscillates in a manner that is out of phase with the pilot´s control inputs. The pilot is not aware when PIO are driven by pilot-aircraft coupling, so he may continue driving the oscillations in an ineffective attempt to stop them. PIO have caused a significant number of aircraft accidents
Keywords :
aerospace computing; aerospace simulation; aircraft control; motion compensation; neurocontrollers; oscillations; real-time systems; aircraft accidents; aircraft oscillation; neural network-based real-time algorithm; oscillation compensation method; oscillation mitigation; pilot control inputs; pilot-aircraft coupling; pilot-induced oscillations detection algorithm; piloted simulations; Accidents; Aerodynamics; Aerospace control; Automatic control; Control systems; Laboratories; Military aircraft; Neural networks; Testing; User interfaces;
Conference_Titel :
Systems, Man, and Cybernetics, 2000 IEEE International Conference on
Conference_Location :
Nashville, TN
Print_ISBN :
0-7803-6583-6
DOI :
10.1109/ICSMC.2000.885042