抄録
In this paper, Genetic Algorithms (GAs) are applied to structural optimization problems. These problems are one of the complex and constrained optimization problems. Therefore, to solve the problems, the GAs with strong searching capability and the mechanisms which handle the constraints efficiently must be prepared. So this paper applies penalty method and pulling back method to Distributed Probabilistic Model-Building Genetic Algorithm (DPMBGA). DPMBGA is the extended algorithm of Probabilistic Model-Building GA (PMBGA) and it has high searching capability. DPMBGA with the penalty method and pulling back method are applied to truss structural optimization problems. Through the simulation, the searching capability and efficiency of penalty method and the pulling back method are discussed. From the discussion, it is concluded that the pulling back method can derive good solution even when the problem is difficult. Compared to the penalty method, the number of the individuals that violate the constraints is smaller in the pulling back method.
