|
چکیده
|
Metal sheets play an important role in mechanical design, particularly in aerospace structures. Rivet connections are frequently used to connect these sheets. The riveting quality greatly influences the rupture of rivet and sheet. Various parameters affect the quality of this operation. In this paper, optimization of the parameters contributing to the riveting quality in order to minimize the value of maximum tangential stress in sheets is addressed. To this end, tolerance of the upper sheet’s hole diameter, tolerance of the lower sheet’s hole diameter, friction coefficient, tolerance of the rivet diameter and rivet length were considered as the parameters influencing the riveting quality. A total of 64 models were obtained by the permutations of the parameters two at a time. The output of the models comprised the height of the riveted part, the maximum diameter of the riveted part, and the maximum tangential stress in the sheets, which is the cause of cracks in the sheets. These outputs were determined using finite element method. The objective function for minimization is maximum tangential stress for which there is no analytical relation. Thus, three methods including multivariable linear regression (MLR), artificial neural network model of radial basis function (RBF) type, and a hybrid model of artificial neural network and genetic algorithm (ANN-GA) were employed to model this function. Further, the performance of the three models MLR, RBF, and ANN-GA were compared and the most suitable one was selected to model the objective function. The upper and lower limits for the problem variables as well as the upper and lower limits for the values of height and diameter after riveting were considered as constraints. There exists no analytical relation also for these values. The regression model was used to model the values of height and diameter after riveting. The imperialist competitive algorithm is utilized to solve this optimization problem.
|