Corrosion resistant alloys (CRA) are often used for well–head equipment and the first length of flowlines until the application of corrosion inhibited carbon steel becomes a viable choice. CRAs possess excellent general corrosion resistance owing to the presence of passive film. However susceptibility of CRAs to pitting corrosion is a major concern. The chosen material should be able to maintain its integrity at the targeted operating conditions and still being cost-effective. This research aims to provide a new insight on the pitting behaviour of one of the low grade CRA materials namely AISI 316L at severely corrosive conditions. The objective of this research is to develop a cost effective and reliable material pre-selection model based on experimental data along with the help of an artificial neural network (ANN).Experiments were carried out in a jet impingement cell based on the Taguchi’s orthogonal array (OA). Each steel specimen was subjected to specific conditions involving a pH range of 3 – 5 chloride concentrations between 1 wt% and 12 wt% acetic acid range 50-600 ppm temperatures in the range 100? C – 175? C and partial pressure of CO2 was 10bar. Pitting potentials (Epit) were extracted from cyclic polarization tests. The ANN was used to process the experimental results and to predict pitting potentials for various operational conditions. A good correlation between the experimental results and predicted data was found. Additional experiments were conducted to validate the predicted values. The developed ANN was used to simulate pitting potential of 316L as a function of pH chloride concentration acetic acid concentration temperature and the resulting corrosion domain diagrams are presented.