Prediction of compression buckling load and buckling mode of hat-stiffened panels using artificial neural network

摘要

The composite hat-stiffened panel is a typical structure that embodies the concepts of high strength and light weight. It has many design parameters and multiple buckling failure modes. The prediction accuracy of the traditional simplified method of engineering calculation is not high. Although the finite element method can achieve high-precision prediction, it is time-consuming for engineering designers. In this study, two kinds of artificial neural networks are established to predict the compression buckling behavior of composite hat-stiffened panels. First, the buckling behavior of the composite hat-stiffened panel is studied using the combination of finite element simulation and experimental verification. Then, considering the variations of four mechanical properties of the stiffened panels, the finite element model group is used to generate the training dataset and test dataset of the neural network in batches. Two kinds of neural networks are comparatively selected to predict the buckling load and buckling failure mode. Based on the testing dataset and the new dataset, the performance and generalization ability of the artificial neural networks are examined. The results show that the trained artificial neural networks can accurately and efficiently predict the buckling behavior of composite hat-stiffened panels under axial compression.