摘要：A genetic algorithm that aims at achieving genetic population diversity in order to avoid the premature convergence of the optimisation problems to undesirable local maxima is presented in this work. The method employs fundamental concepts of diffuse numbers. Each individual is represented by a diffuse number and the crossover and mutation operations are redefined in accordance with the new genetic pattern. The scope of the new proposal was assessed by comparing its performance with the conesponding traditional genetic algorithm. The results show that the variant based on diffuse sets succeeds in achieving better population diversity without losing much selective pressure in the search for the optimal solution.
其他摘要：A genetic algorithm that aims at achieving genetic population diversity in order to avoid the premature convergence of the optimisation problems to undesirable local maxima is presented in this work. The method employs fundamental concepts of diffuse numbers. Each individual is represented by a diffuse number and the crossover and mutation operations are redefined in accordance with the new genetic pattern. The scope of the new proposal was assessed by comparing its performance with the conesponding traditional genetic algorithm. The results show that the variant based on diffuse sets succeeds in achieving better population diversity without losing much selective pressure in the search for the optimal solution.
