Approximate neural economic set-point optimisation for control systems

Authors:
Maciej Ławryńczuk;Piotr Tatjewski
Affiliations:
Institute of Control and Computation Engineering, Warsaw University of Technology, Warsaw, Poland;Institute of Control and Computation Engineering, Warsaw University of Technology, Warsaw, Poland
Venue:
ICAISC'10 Proceedings of the 10th international conference on Artifical intelligence and soft computing: Part II
Year:
2010

Citing 2
Cited 0

Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Neural models in computationally efficient predictive control cooperating with economic optimisation

ICANN'07 Proceedings of the 17th international conference on Artificial neural networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper describes a neural approach to economic set-point optimisation which cooperates with Model Predictive Control (MPC) algorithms. Because of high computational complexity, nonlinear economic optimisation cannot be repeated frequently on-line. Alternatively, an additional steady-state target optimisation based on a linear or a linearised model and repeated as often as MPC is usually used. Unfortunately, in some cases such an approach results in constraint violation and numerical problems. The approximate neural set-point optimiser replaces the whole nonlinear economic set-point optimisation layer.