FUELGEN - EFFECTIVE EVOLUTIONARY DESIGN OF REFUELLINGS FOR PRESSURIZED-WATER REACTORS

The paper describes the design of an efficient and robust genetic algo rithm for the nuclear fuel loading problem (i.e. refuellings: the in-c ore fuel management problem) - a complex combinatorial, multimodal opt imisation. Evolutionary computation as performed by FUELGEN replaces h euristic search of the kind performed by the FUELCON expert system (CA I 12/4), to solve the same problem. In contrast to the traditional gen etic algorithm which makes strong requirements on the representation u sed and its parameter settings in order to be efficient, the results o f recent research on new, robust genetic algorithms show that represen tations unsuitable for the traditional genetic algorithm carl still be used to good effect with little parameter adjustment.The representati on presented here is a simple symbolic one with no linkage attributes, making the genetic algorithm particularly easy to apply to fuel loadi ng problems with differing core structures and assembly inventories. A nonlinear fitness function has been constructed to direct the search efficiently in the presence of the many local optima that result from the constraint on solutions.