The objective of this study is to enhance the longevity of damaged or defective components through necessary repairs. In corrosive environments, stainless steels, such as 304 and 316NG austenitic stainless steel (SS), are preferred due to their chemical composition. Notably, 316SS contains a higher molybdenum content, resulting in improved resistance to pitting and crevice corrosion. The simulation of intergranular stress corrosion cracking (IGSCC) in SS piping relies on factors like applied and residual stresses, environmental conditions, and sensitization degree. To understand crack growth rates and times-to-initiation for each material, "damage parameters (DPs)" are utilized. These DPs consolidate the individual influences of various parameters. To estimate the DPs an artificial neuronal network (ANN) is proposed in this work. The ANN serves as a tool for predicting the DPs based on the given inputs. The obtained results are then utilized in numerical simulations to assess crack growth rates, times-to-initiation, and reliability for damaged 304SS and 316SS. Finally, this paper investigates the impact of replacing old 304 material with new 316NG material on piping reliability. By examining the effects of this replacement, the study aims to provide insights into how the reliability of the piping can be improved through material upgrades.