Title :
A neural network based receding horizon optimal (RHO) controller
Author :
Long, Theresa W. ; Hanzevack, Emil L. ; Midwood, Brent R.
Author_Institution :
NeuroDyne Inc., Cambridge, MA, USA
Abstract :
A neural network based RHO controller is developed for jet aircraft engines. It takes advantage of the learning ability of the neural network to obtain the mapping function between system input and output, and does not predicate upon a priori knowledge of the system model. The controller was tested using OREOX, a jet engine simulator provided by Pratt and Whitney. The controller recovers from system changes in seconds. Due to the smoothing and stability measures undertaken, the control trajectories are smooth and stable even when the target thrust is changed abruptly
Keywords :
aerospace engines; aircraft control; learning (artificial intelligence); neurocontrollers; optimal control; OREOX simulator; aircraft control; jet aircraft engines; learning; neural network; receding horizon optimal control; Aircraft propulsion; Control systems; Cost function; Jet engines; Neural networks; Optimal control; Smoothing methods; Stability; Testing; Weight control;
Conference_Titel :
American Control Conference, 1997. Proceedings of the 1997
Conference_Location :
Albuquerque, NM
Print_ISBN :
0-7803-3832-4
DOI :
10.1109/ACC.1997.611037
