Abstract
In this paper a neural network model-based predictive control strategy for aircraft systems with unknown parametersis presented.The objective of the paper is to stabilize dynamical systems by an adaptive control law through an optimization procedure in which a cost function representingth e deviation error betweend esired set-points and the predicted outputs obtained from a neural network is minimized. Due to its capability of characterizing dynamic functional relationships and its feedback processing structure, a recurrent neural network is employed as an adaptive estimator for future state values. The neural network training is performed by the dynamic sequential recursive back propagation learning algorithm, which allows the neural network to be trained on-line. It is shown that the proposed neural network learning algorithm has potential for designing flight control systemsw hich can compensatefo r unpredictable changes in an aircraft dynamics over a wide range of flight conditions and other uncertainties.
Original language | English |
---|---|
State | Published - 2000 |
Event | 38th Aerospace Sciences Meeting and Exhibit 2000 - Reno, NV, United States Duration: Jan 10 2000 → Jan 13 2000 |
Conference
Conference | 38th Aerospace Sciences Meeting and Exhibit 2000 |
---|---|
Country/Territory | United States |
City | Reno, NV |
Period | 01/10/00 → 01/13/00 |