Predictions of corrosion current density and potential by using chemical composition and corrosion cell characteristics in microalloyed pipeline steels

Artificial neural networks with feed forward topology and back propagation algorithm were employed to predict the effects of chemical composition and corrosion cell characteristics on both corrosion current density and potential of microalloyed pipeline steels. Doing this, the chemical compositions comprising of “carbon”, “magnesium”, “niobium”, “titanium”, “nitrogen”, “molybdenum”, “nickel”, “aluminum”, “copper”, “chromium”, “vanadium” and “carbon equivalent” (all in weight percentage) along with corrosion cell characteristics of “reference electrode”, “scan rate”, “temperature”, “relative pressure of oxygen”, “pressure of purged CO2”, “chloride ion”, as well as, “bicarbonate concentration” were considered together as the input parameters of the network while the “corrosion current density” and “corrosion potential” were considered as the outputs. For purpose of constructing the models, 87 different data were gathered from literatures wherein different examinations were performed. Then data were randomly divided into training, testing and validating sets. Scatter plots and statistical criteria of “absolute fraction of variance (R2)”, and “mean relative error (MRE)” were used to evaluate the prediction performance and universality of the developed models. Based on the analyses, the proposed models could be further used in practical applications and corrosion monitoring of the microalloyed steels.