Currently, fatigue-sensitive components in oil and gas industry that suffer localised corrosion have to be replaced. The production is initially shut down for the risk assessment and may, or may not, be re-started whilst awaiting replacement components. Replacement of in-service components has a high cost, mainly due to the associated lost production, and it can take up to two years in terms of planning and procurement of replacement components. Gaining assurance that existing components are safe for temporary use until replacement components are available would avoid the costly interruption of production without impairing the safety & reliability of operations. This project, using experimental tests, Finite Element (FE) analysis and artificial neural network (ANN) approaches, aims to develop a tool able to predict the remaining time to failure of components from localised corrosion (pitting). This would enable optimisation of inspection programs and prioritisation of replacement plans for critical components. In addition, the improvements made to the prediction of corrosion-fatigue in design will assist in optimising the design of pipelines.