Particle swarm evolutionary computation-based framework for optimizing the risk and cost of low-demand systems of nuclear power plants

ABSTRACTIn this paper, an adapted multi-objective multi-swarm co-evolutionary particle swarm optimization (PSO) framework is developed to simultaneously optimize the risk and cost of low-demand systems of nuclear power plants (NPPs). In the built framework, multi-swarm co-evolutionary strategy is introduced to handle the fitness assignment puzzle of multi-objective optimization problems. Besides, to deal with the mixed-integer problem of the decision variables vector, a sub-interval covering-based nearest boundary method is also adopted. To illustrate the effectiveness and efficiencies of the proposed method, a typical high-pressurized injection system (HPIS) is analyzed. The results indicate that, compared with the classic non-dominated sorting genetic algorithm (NSGA)-II approach, the proposed method is more simple and easier to be convergent, besides, of which the Pareto front is better distributed.