Browsing by Author "Boucherit, M. N."
Now showing 1 - 2 of 2
- Results Per Page
- Sort Options
Item Artificial Intelligence To Predict Inhibition Performance Of Pitting Corrosion(University of Eloued جامعة الوادي, 2017-01-01) Boukhari, Y.; Boucherit, M. N.; Zaabat, M.; Amzert, S.; Brahimi, K.This work aims to compare several algorithms for predicting the inhibition performance of localized corrosion. For this more than 400 electrochemical experiments were carried out in a corrosive solution containing an inorganic inhibitor. Pitting potential is used to indicate the performance of the inhibitor/oxidant mixture to prevent pitting corrosion. At the end of the electrochemical program a file containing all the experimental results has been prepared and submitted to several algorithms. Through a training phase each algorithm uses a set of experimental results to adjust its parameters and another set to predict the pitting potential starting from the properties and the chemical composition of the solution. The prediction performance of an algorithm is estimated by the difference between experimental pitting potential and the calculated one. The order of performance of the algorithms is: GA-ANN > LS-SVM > PSO-ANN > ANN >ANFIS > KNN > RT > KBP > LDA.Item CORROSION OF A CARBON STEEL COVERED BY TREATED BENTONITES IN AQUEOUS SOLUTION(University of Eloued جامعة الوادي, 2017-09-01) Arbaoui, F.; Amzert, S. A.; Boucherit, M. N.In the present work we realised an electrochemical system for steel/clay/aqueous solutions study. Two Algerian bentonites have been considered. The obtained results show that both clays are corrosive even in the absence of chloride ions. We show that this corrosiveness is related to the cationic exchange capacity (CEC). The chemical treatment of clays by tungstate reduces significantly their CEC and corrosiveness. Electrochemical impedance spectroscopy results prove that tungstate reduce iron and chlorides ions transport through the clay. This deduction is supported also by microscopic observations.