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
Hi-index | 0.01 |
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.