Artificial Neural Network for the prediction of fatigue life of a flexible foldable origami antenna with Kresling pattern

Abstract

In this paper, we present a comprehensive fatigue analysis of a foldable origami helical antenna with Finite Element Method (FEM) and Artificial Neural Network (ANN). We study the effect of design parameters such as total height, length ratio (b/a), height of story, thickness, length and thickness ratios of creases, and radius of the circumscribed circle of polygonal on the fatigue life. We employ ANN method to reduce the computational cost of the conventional methods for predicting the fatigue life of the origami antenna. Although ANN is trained with a limited set of data, our results reveal that the proposed approach predicts the fatigue failure of the antenna with high accuracy. This trained ANN determines the life cycle of the origami structure with less than 1% error on the training set and less than 2% error on the test set. The ANN results illustrate that the fatigue life of the structure is improved by increasing the radius of the circumscribed circle and decreasing the thickness of the structure. We discover that some values of the length ratio (b/a) magnify the effect of total height on the life cycle. In addition, we show how the creases parameters of the structure play an important role in the fatigue life of the antenna.