Online Identification and Control of Aerospace Vehicles Using Recurrent Networks
This document has been relocated to http://scholarsmine.mst.edu/mec_aereng_facwork/3450
There were 10 downloads as of 28 Jun 2016.
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.