A study of pipe interacting corrosion defects using the FEM and neural networks

Abstract

In this paper we present an application of the neural network technology for the assessment of pipes with interacting defects. Finite element simulations are carried out on a pipe containing two aligned and equally shaped defects of 80 × 32 mm and various defect spacing, providing a database containing the relation between the failure pressures of pipes with multiple and single defects. Neural networks are conceived by using this database, establishing interaction rules and a pipe assessment of interacting defects in the longitudinal and circumferential directions. The neural networks results are compared with those derived from the Det Norske Veritas code (DNV RP-F101).