Predicting Aluminum Corrosion Inhibition with Schiff Base Compounds Using Support Vector Machines (SVMs)

Corrosion is a chemical reaction that happens when a metal comes into contact with certain chemicals or environmental conditions. The aforementioned contact has the potential to occur by chemical or electrochemical mechanisms, resulting in significant deformation or severe metal damage. In this study, the performance of the multiple linear regression approach and the support vector machine algorithm method for predicting aluminum corrosion inhibition by Schiff bases was evaluated. To this end, corrosion inhibitor efficiency of Schiff base compounds was collected and extracted from scientific sources. 70% of the data was allocated for training, while the remaining 30% was used for validating the models. The results of the models were evaluated using various criteria, including the coefficient of determination (R), root mean square error (RMSE), mean percentage error (MPE), and relative square error (RSE). The findings revealed that the support vector machine algorithm, with a correlation coefficient of R2 = 0.9, exhibited superior performance and greater accuracy in predicting Schiff base corrosion inhibitor efficiency for aluminum compared to modeling with multiple linear regression.