Comparative study of meta-heuristic algorithms for reactor fuel reloading optimization based on the developed BP-ANN calculation method

Abstract

In order to obtain optimal core configurations, the problems of fuel reloading optimization must be solved in nuclear engineering field. This problem is a combinational optimization problem with an enormous solution space. In the traditional calculation method, the meta-heuristic algorithms (MHAs) are used to search and update optimization solutions continuously, while the core physics calculation programs are used to calculate the optimization parameters. In this research, we developed a new BP-ANN calculation method to solve the problems of fuel reloading optimization for thorium-based block-type high temperature gas-cooled reactors (HTGRs). In this method, the function of core physics calculation programs are replaced by BP-ANNs in order to reduce calculation time. Besides, five different MHAs, which are genetic algorithm (GA), particle swarm optimization (PSO), Teaching-learning based optimization algorithm (TLBO), harmony search (HS) and Rank-based ant system (RAS), are used under this new method to solve the problems of fuel reloading optimization, respectively. The results shows that PSO is the best MHA with a real feasible solution ratio of 0.30 and the best fitness function value of 0.455904. Compared to the traditional calculation method, the calculation time of BP-ANN calculation method is reduced to 0.7% of the former.