Model-free control of nonlinear stochastic systems with discrete-time measurements
- 1 September 1998
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 43 (9), 1198-1210
- https://doi.org/10.1109/9.718605
Abstract
Consider the problem of developing a controller for general (nonlinear and stochastic) systems where the equations governing the system are unknown. Using discrete-time measurement, this paper presents an approach for estimating a controller without building or assuming a model for the system. Such an approach has potential advantages in accommodating complex systems with possibly time-varying dynamics. The controller is constructed through use of a function approximator, such as a neural network or polynomial. This paper considers the use of the simultaneous perturbation stochastic approximation algorithm which requires only system measurements. A convergence result for stochastic approximation algorithms with time-varying objective functions and feedback is established. It is shown that this algorithm can greatly enhance the efficiency over more standard stochastic approximation algorithms based on finite-difference gradient approximations.Keywords
This publication has 49 references indexed in Scilit:
- A neural network controller for systems with unmodeled dynamics with applications to wastewater treatmentIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1997
- Optimization of discrete event systems via simultaneous perturbation stochastic approximationIIE Transactions, 1997
- Neural-net-based direct self-tuning control of nonlinear plantsInternational Journal of Control, 1997
- Dynamic structure neural networks for stable adaptive control of nonlinear systemsIEEE Transactions on Neural Networks, 1996
- Discrete-time model reference adaptive control of nonlinear dynamical systems using neural networksInternational Journal of Control, 1996
- Control of nonlinear dynamical systems using neural networks. II. Observability, identification, and controlIEEE Transactions on Neural Networks, 1996
- A more efficient global optimization algorithm based on Styblinski and TangNeural Networks, 1994
- Uniqueness of the weights for minimal feedforward nets with a given input-output mapNeural Networks, 1992
- On the almost sure convergence of a general stochastic approximation procedureBulletin of the Australian Mathematical Society, 1986
- A Newton-Raphson Version of the Multivariate Robbins-Monro ProcedureThe Annals of Statistics, 1985