Neural networks prediction of different frequencies’ effects on calcareous deposits formation under pulse cathodic protection

Abstract

This paper deals with the calcareous deposition by using pulse cathodic protection on steel structures submerged in the synthetic sea water. In order to fully characterize the complex underlying mechanism of this process and evaluate the effects of a thorough range of frequencies, a prediction model is developed using a hybrid of Neural Networks and Genetic Algorithms (GA). Process variables, i.e. time, frequency and final required current, have been experimentally studied with the aid of chronoamperometric technique. A portion of this dataset is used to train the prediction model, while the rest is set aside to test its predictive performance. This hybrid Neural Networks model uses GA to achieve its optimal architecture for prediction. Finally, it is concluded that the proposed model has an excellent prediction capability of final current density in the various range of frequencies by comparing the results with the experimental data.