Quantitative structure activity relationship and artificial neural network as vital tools in predicting coordination capabilities of organic compounds with metal surface: A review

Abstract

It has been well-established that organic corrosion inhibitors often form protective film through coordinate bonding with the metal. Different computational and experimental methods are used to describe the nature and effectiveness of such metal-inhibitor bonds. Quantitative structure activity relationship (QSAR) is one of the most recent and reliable computational methods used to describe metal-inhibitor coordination, leading to corrosion inhibition. The quest for the design of new, high-performance environmentally benign compounds that can effectively impede corrosion without excessive large-scale experimental trials has heightened research interest in molecular structure-corrosion inhibition relationship. Correlation between corrosion inhibition potentials and molecular descriptors of organic compounds is becoming increasingly advanced. This is also as new techniques such as machine learning, artificial neural network (ANN), support vector machine (SVM) and genetic function approximation (GFA) are becoming more famous with advancement in computer technology. This review article presents a summary of previous works on the use of QSAR and ANN as predictive tools for metal-organic compound coordination towards corrosion inhibition.