Impact of Environmental Parameters on the Corrosion Inhibition of 7- Hydroxyphenoxazone: an Experimental and Artificial Neural Network Study

Artificial neural network model is a high precision predictive tool for unknown values without performing the related experiments. It can be developed and utilized for prediction of nonlinear corrosion processes. In this way, owning a numer of input values, the output can predicted, exactely. In present work, first, the effect of holding time, hydrodynamic conditions and temperature were investigated on the inhibiting efficiency of 7-Hydroxyphenoxazone on steel corrosion in 1.0M HCl solution by electrochemical impedance spectroscopy (EIS). Then, the experimental variables such as concentration, immersion time, and hydrodynamic condition were taken as the input values and the corrosion inhibiting efficiency as the output value of artificial neural network model. Results showed that by increasing immersion time up to 8 hours, with 100ppm of 7-Hydroxyphenoxazone, the polarization resitance increases from 1660 to 2260 Ωcm2 and inhibition efficiency reaches to 91%. Also, by increasing rotational speed up to 500 rpm and temperature up to 550C, the inhibition efficiency decreases from 86.6% to 24% and 60%, respectively. The prediction results of artificial neural network indicated the good agreement with experimental data and the trained values of artificial neural network predicted the inhibiting efficiency values with average error less than 1%.