Identification of Impressed Current Cathodic Protection System (ICCP) By Artificial Neural Network.

Abstract

The corrosion of metallic structures buried in soil or submerged in water which became a problem of worldwide significance and cause most of the corrosion in petroleum industry can be controlled by cathodic protection. Cathodic protection (CP) is a popular technique used to minimize the corrosion of metals in a variety of large structures . In this study the identification of impressed current cathodic protection system was presented and the results were simulated by artificial neural networks for system identification which was implemented using MATLAB R 2010 A programming. The best network architecture was chosen for protection system. The multilayer feed forward network for neural network was used. The four environment variables (conductivity C, temperature T, aeration factor A, and potential reading V) were used as the input to the network to identify the minimum current density as output in a feed forward network structure with one hidden layer using the practical results data for the learning process which was concluded.