Neural networks and genetic algorithms for robust predictive controller

Authors:
Bouzouita Badreddine;Bouani Faouzi;Ksouri Mekki
Affiliations:
Laboratory of Analysis and Control of Systems, ENIT, Tunisia;Laboratory of Analysis and Control of Systems, ENIT, Tunisia and National Institute of Applied Sciences and Technology, Tunisia;Laboratory of Analysis and Control of Systems, ENIT, Tunisia
Venue:
ACMOS'06 Proceedings of the 8th WSEAS international conference on Automatic control, modeling & simulation
Year:
2006

Citing 5
Cited 0

On linear programming and robust modelpredictive control using impulse-responses

Systems & Control Letters
On the convergence of interior-reflective Newton methods for nonlinear minimization subject to bounds

Mathematical Programming: Series A and B
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
Global Optimization with Polynomials and the Problem of Moments

SIAM Journal on Optimization
Brief Constrained robust predictive controller for uncertain processes modeled by orthonormal series functions

Automatica (Journal of IFAC)

Quantified Score

Hi-index	0.00

Visualization

Abstract

The present work focuses on robust predictive control (RPC) of uncertain processes modeled by Controlled Auto Regressive Integrated Moving Average (CARIMA) model. The RPC is based on worst case strategy, e.g., the control law is obtained by the resolution of a min-max optimization problem. In fact, the presence of uncertainty on the AR part of the CARIMA model leads to the resolution of a non convex optimization problem. In this work, non conventional methods such as Hopfield neural networks (HNN) and genetic algorithms (GA) are used for the resolution of the non convex optimization problem. The efficiency of the HNN and GA optimizers are tested on benchmark functions. Simulation results are also presented to illustrate the performance of the RPC based on HNN and GA.