A data-driven model for predicting the fatigue life of 7075–2 T651 aluminum alloy considering the effects of the size of pits

Abstract

Aluminum alloy 7075-T651 exposed to the marine environment is often affected by chloride-induce, which leads to stress concentration. a sharp stress concentration will accelerate the derivative rate of crack and the fatigue life of the Aluminum alloy 7075-T651 decreases. In order to investigate the SCF affected by pitting corrosion, which is used to evaluate its fatigue life. This paper established some numerical models with different sizes of pits to explore the SCF, considering their coupling effects. Based on the back propagation (BP) Neural Network model, a prediction model was proposed to investigate the SCF. A study on sensitivity analysis indicated that the depth of pits is the most important factor to influence the SCF. Additionally, the fatigue performance of the aluminum alloy 7075-T651 was explored, based on the fracture mechanics theory. The results show that the SCF increases, as the length and the width of the pits increase, and decreases, as the pit depth increases.The predicted results of this model were verified by the numerical results and the experimental results.