Study on shape creation of building's roof by evaluating aesthetic sensibility

The purpose of this study is to develop an optimum design method for roof shapes satisfying both aesthetic sensibility (beauty) and economic evaluation by using the genetic algorithm (GA). The object is the roof of a gymnasium, and the target roof shape is asymmetrical. The roof shapes were evaluated on the basis of the satisfaction degrees of both economic evaluation and beauty. The economic evaluation used stress evaluation values that were obtained by the finite element method analysis. The KANSEI (equal to aesthetic sensibility) evaluation values were calculated from the learned results of the questionnaire by a neural network. Each satisfaction degree is calculated by membership functions. The synthetic satisfaction degree is calculated by fuzzy theory by using both the stress satisfaction degree and the KANSEI satisfaction degree. The roof shape, which has the highest synthetic degree of satisfaction, is created by the GA. A beautiful shape, which was not created only by the stress evaluation, was created by also considering the beauty evaluation.