Nyquist Plots Prediction Using Neural Networks in Corrosion Inhibition of Steel by Schiff Base

The corrosion inhibition effect of N,N′-bis(n-Hydroxybenzaldehyde)-1,3-Propandiimine on mild steel has been investigated in 1 M HCl using electrochemical impedance spectroscopy. A predictive model was presented for Nyquist plots using an artificial neural network. The proposed model predicted the imaginary impedance based on the real part of the impedance as a function of time. The model took into account the variations of the real impedance and immersion time of steel in a corrosive environment, considering constant corrosion inhibitor concentrations. The best-fit training data set was obtained with eleven neurons in the hidden layer for Schiff base inhibitor, which made it possible to predict the efficiency. On the validation data set, simulations and experimental data test were in good agreement. The developed model can be used for the prediction of the real and imaginary parts of the impedance as a function of time.