A predictive model for corrosion inhibition of mild steel by thiophene and its derivatives using artificial neural network

Abstract

Corrosion inhibition performance of thiophene and its derivatives were studied using potentiodynamic polarization. The study used the artificial neural network analysis effectively generalized correct responses that broadly resemble the data in the training set. The neural network can now be put to use with the actual data, this involves feeding the neural network values for Hammett constants, dipole moment, HOMO energy, LUMO energy and energy gap. The analysis produced instantaneous results of corrosion inhibitor efficiency. The predictions were reliable, provided the input values are within the range used in the training set. © 2012 by ESG.