Title :
Model predictive neural control with applications to a 6 DOF helicopter model
Author :
Wan, Eric A. ; Bogdanov, Alexander A.
Author_Institution :
Oregon Graduate Inst., Beaverton, OR, USA
Abstract :
We present a method for optimal control of MIMO non-linear systems based on a combination of a neural network (NN) feedback controller and a state-dependent Riccati equation (SDRE) controller. Optimization of the NN is performed within a receding horizon model predictive control (MPC) framework, subject to dynamic and kinematic constraints. The SDRE controller augments the NN controller by providing an initial feasible solution and improving stability. The resulting technique is applied to a 6 degree of freedom (DOF) model of an autonomous helicopter
Keywords :
MIMO systems; Riccati equations; aircraft control; dynamics; feedback; helicopters; kinematics; neurocontrollers; nonlinear control systems; optimisation; predictive control; 6 DOF helicopter model; MIMO nonlinear systems; autonomous helicopter; dynamic constraints; kinematic constraints; model predictive neural control; neural network feedback controller; optimal control; receding horizon model predictive control framework; state-dependent Riccati equation controller; Adaptive control; Constraint optimization; Control systems; MIMO; Neural networks; Nonlinear control systems; Nonlinear equations; Optimal control; Predictive models; Riccati equations;
Conference_Titel :
American Control Conference, 2001. Proceedings of the 2001
Conference_Location :
Arlington, VA
Print_ISBN :
0-7803-6495-3
DOI :
10.1109/ACC.2001.945592
