Currently in the industry, the is a lack of designated corrosion assessment method for the failure pressure prediction of pipe elbows. In this study, empirical equations based on artificial neural network and finite element analysis for the failure pressure prediction of API 5L X52 corroded pipe elbow with longitudinally aligned interacting corrosion defects subjected to internal pressure is proposed. Artificial neural networks trained using failure pressure obtained from finite element analysis for varied defect spacings, depths, and lengths were used to develop the equations. The new equations predicted failure pressures for these pipe grades with a coefficient of determination value of 0.99 and an error range of-9.81 to 4.58 for normalized defect spacings of 0.00 to 2.00, normalized defect lengths of 0.00 to 1.00, and normalized defect depths of 0.00 to 0.80. © 2022 IEEE.