Article ID Journal Published Year Pages File Type
1729905 Annals of Nuclear Energy 2008 8 Pages PDF
Abstract

The design and evaluation of a novel approach to reactor core power control based on emotional learning is described. The controller includes a neuro-fuzzy system with power error and its derivative as inputs. A fuzzy critic evaluates the present situation, and provides the emotional signal (stress). The controller modifies its characteristics so that the critic’s stress is reduced. Simulation results show that the controller has good convergence and performance robustness characteristics over a wide range of operational parameters.

Related Topics
Physical Sciences and Engineering Energy Energy Engineering and Power Technology
Authors
, , ,