Artificial neural networks solution to display residual hoop stress field encircling a split-sleeve cold expanded aircraft fastener hole

Cold expansion of holes is a technique, generating intricate three-dimensional residual stresses around fastener holes essentially vital for airplane fatigue resistance. In this work, attention was given to Artificial Neural Networks (ANN) modeling to build up and train simulations of stress topography surrounding a 4% expanded hole. For this, experimental data of recently abridged step drilling-Fourier method was employed. At input layer of ANN; information available for steps through thickness and radial directions, angular variation around the hole, and at output layer, residual hoop stresses were exercised to train and test multilayered, hierarchically connected and directed networks with varying number of hidden layers. It was shown that Levenberg–Marquardt (LM) model with 9 neurons in hidden layer yielded the best of the results, as error percentages were remarkably small both in training and testing sequences. Several results of step drilling-Fourier solution (ATÖzdemir method), diffraction methods and current ANN predictions were overlaid and similarities in residual stress distributions perceived to valid only at regions where strain gradient was not changing precipitously. Nevertheless, best fit to strain data at confusing zones was achieved after ANN modeling.