Title :
Upper bounds for approximation of continuous-time dynamics using delayed outputs and feedforward neural networks
Author :
Lavretsky, Eugene ; Hovakimyan, Naira ; Calise, Anthony J.
Author_Institution :
Phantom Works, Boeing Co., Huntington Beach, CA, USA
Abstract :
The problem of approximation of unknown dynamics of a continuous-time observable nonlinear system is considered using a feedforward neural network, operating over delayed sampled outputs of the system. Error bounds are derived that explicitly depend upon the sampling time interval and network architecture. The main result of this note broadens the class of nonlinear dynamical systems for which adaptive output feedback control and state estimation problems are solvable.
Keywords :
adaptive control; adaptive estimation; continuous time systems; feedback; feedforward neural nets; neurocontrollers; nonlinear dynamical systems; observability; state estimation; adaptive estimation; adaptive output feedback control; continuous-time dynamics; continuous-time observable nonlinear system; delayed outputs; error bounds; feedforward neural networks; network architecture; nonlinear dynamical systems; observability; sampling time interval; state estimation problems; upper bounds for approximation; Adaptive control; Adaptive systems; Feedforward neural networks; Neural networks; Nonlinear dynamical systems; Nonlinear systems; Output feedback; Programmable control; Sampling methods; Upper bound;
Journal_Title :
Automatic Control, IEEE Transactions on
DOI :
10.1109/TAC.2003.816987
