Predicting the buckling Capacity of Steel Cylindrical Shells with Rectangular Stringers under Axial Loading by using Artificial Neural Networks

Abstract

A parametric study was carried out in order to investigate the buckling capacity of the vertically stiffened cylindrical shells. To this end ANSYS software was used. Cylindrical steel shells with different yield stresses, diameter-to-thickness ratios (D/t) and number of stiffeners were modeled and their buckling capacities were calculated by displacement control nonlinear static analysis. Radial basis function (RBF) neural networks were used to predict the buckling capacity of shells. Herein 70 percent of the results of numerical analyses were used to train the neural network and the remainders were used to test and validate the results of neural networks. Results of this study showed that RBF neural networks are useful tools to predict the buckling capacity of vertically stiffened cylindrical shells. It was also shown that buckling capacities of stiffened shells exponentially vary by distance of adjacent stiffeners (unstiffened length).