Emotional Learning to Control Large-Scale Systems
| Authors: | Bakhtiari Reyhaneh, Tehran University, Iran (Islamic Republic of)
Labibi Batool, K. N. Toosi University of Technology, Iran (Islamic Republic of) |
|---|
| Topic: | 3.2 Cognition and Control ( AI, Fuzzy, Neuro, Evolut.Comp.) |
|---|
| Session: | Soft Computing for Control |
|---|
| Keywords: | Neuro-Fuzzy Controller, Large-Scale Systems, Emotional Learning, Intelligent Systems, Large-Scale Systems, Hierarchical Control, Multi-Agent Systems |
|---|
Abstract
In this paper, with a new look at emotional controller and modifying its structure; a novel approach to hierarchical control of large-scale systems is introduced. Design of controller is founded on emotional learning and the control system consists of neuro-fuzzy controller, whose weights are updated according to emotional signals. This signal is produced in a block called critic, whose job is to evaluate system behaviour. Simulation results demonstrate that the proposed learning scheme, which is applied to a nonlinear three-tank system, provides better control reliability and robustness than classic robust schemes.
