Document Type : Research Article
Authors
educational group
Abstract
Failure and buckling in shell structures, including silos, can be created for various reasons such as distortion, defects created during construction, defects created during operation, or environmental factors, etc. Silos can be subjected to a variety of lateral and axial loads, but since they are in fact affected by the combination of these loads, silos behave under the influence of composite loads. The silos in this research are hot-rolled and located on the ground. The variables of this research are type and scope of defect. Silos are also evaluated in semi-filled and semi-solid state. The model silos were analyzed in ANSYS software. The radial radial neural network RBF was used to predict the buckling capacity of the cylindrical shells. The results of this study indicate that artificial neural networks are a good tool for predicting buckling capacity of silos with defects.
Keywords
)