Methods for estimating the aerospace system parameters and controlling them through two neural networks are presented in this study. We equate the energy function of Hopfield neural network to integral square of errors in the system dynamics and extract the parameters of a system. Parameter convergence is proved. For control, we equate the equilibrium status of a "modified" Hopfield neural network to the steady state Riccati solution with the system parameters as inputs. Through these two networks, we present the online identification and control of an aircraft using its nonlinear dynamics.
Z. Hu and S. N. Balakrishnan, "Online Identification and Control of Aerospace Vehicles Using Recurrent Networks," Proceedings of the 1999 IEEE International Conference on Control Applications, 1999, Institute of Electrical and Electronics Engineers (IEEE), Jan 1999.
The definitive version is available at https://doi.org/10.1109/CCA.1999.806180
1999 IEEE International Conference on Control Applications, 1999
Mechanical and Aerospace Engineering
Keywords and Phrases
Hopfield Neural Nets; Hopfield Neural Network; Riccati Equations; Aerospace Control; Aerospace Vehicle Control; Energy Function; Integral Square of Errors; Neural Networks; Neurocontrollers; Nonlinear Dynamical Systems; Nonlinear Dynamics; Online Control; Online Identification; Parameter Convergence; Recurrent Networks; Recurrent Neural Nets; Steady State Riccati Solution; System Dynamics; System Parameters
Article - Conference proceedings
© 1999 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
01 Jan 1999