Abstract: Corrosion and fatigue tests were conducted on 7050 aluminum alloy successively,and the fatigue life of the corroded alloy was obtained. Response surface method and BP neural network were used to obtain the mapping relationship between corrosion time, NaCl solution concentration, loading frequency, maximum stress and corrosion fatigue life. The corrosion fatigue life of the alloy was predicted, and the prediction errors of the two models were compared. The results show that the reliability of the two models was good under different load conditions. The root mean square errors of the predicted values by response surface model and BP neural network model and test values of the logarithmic fatigue life of the corroded alloy were 0.071 0 and 0.068 3, and the coefficients of determination were 0.951 9 and 0.998 0, respectively. The prediction accuracy of BP neural network model was better than that of response surface model.