An Improved PID Controller Based on Artificial Neural Networks for Cathodic Protection of Steel in Chlorinated Media

In this study, artificial neural networks (ANNs) were implemented to determine design parameters for an impressed current cathodic protection (ICCP) prototype. An ASTM A36 steel plate was tested in 3.5% NaCl solution, seawater, and NS4 using electrochemical impedance spectroscopy (EIS) to monitor the evolution of the substrate surface, which affects the current required to reach the protection potential ( ${\text{E}}_{prot}$). Experimental data were collected as training datasets and analyzed using statistical methods, including box plots and correlation matrices. Subsequently, ANNs were applied to predict the current demand at different exposure times, enabling the estimation of electrochemical parameters (limiting voltage values) that can be used to optimize a self-regulating ICCP system. The obtained electrochemical parameters were then used, through Particle Swarm Optimization (PSO), to fine-tune an ANN-based proportional-integral-derivative (PID) controller for the ICCP system.