Self-adaptation procedures in genetic algorithms applied to the optimal design of composite structures

摘要: It is recognized that the efficiency of Genetic Algorithms improves if some adaptive rules are included. In this work, properties in applied to structural optimization studied. The work by using additional information related behavior state and design variables problem. At each generation, self-adaptation genetic parameters evolutionary conditions attempts improve search. introduction occurs at three levels: (i) when defining search domain generation; (ii) considering a crossover operator based on commonality local improvements; (iii) controlling mutation, including behavioral data. Self-adaptation has proved be highly beneficial automatically dynamically adjusting parameters. Numerical examples showing these benefits presented.