IDENTIFYING NUCLEAR POWER PLANT TRANSIENTS USING THE DISCRETE BINARY ARTIFICIAL BEE COLONY (DBABC) ALGORITHM

The identification of possible transients in a nucl ear power plant is a highly relevant problem. This is mainly due to the fact that the operation of a n uclear power plant involves a large number of state variables whose behaviors are extremely dynamic. In risk situations, besides the huge cognitive overload that operators are submitted to, there is also the problem related with the considerable decrease in the effective time for cor rect decision making. To minimize these problems and help operators to make the corrective actions in due time, this paper presents a new contribution in this area and introduces an experim ental transient identification system based exclusively on the abilities of the Discrete Binary Artificial Bee Colony (DBABC) algorithm to find the best centroid positions that correctly ide ntifies a transient in a nuclear power plant. The DBABC is a reworking of the Artificial Bee Colony (ABC) algorithm which presents the advantage of operating in both continuous and discr ete search spaces. Through the analysis of experimental results, the effective performance of the proposed DBABC algorithm is shown against some well known best performing algorithms from the literature.