An Artificial Neural Network Modeling to Study Unpredictable Degradation of Carbon Steel Marine Structure with Environmental Variables: Chloride, Sulphate, Bicarbonates, pH

摘要

Corrosion mechanisms of the submersed structures in offshore and onshore installations are complex with high degrees of interaction between the corrosion species, products and metallurgies. For better understanding of the mechanisms of the effects of co-existences of these parameters and to predict the unpredictable life of the structures, an ANN model was developed, using a series of experimental data, varying the corrosion influencing parameters viz. SO_4~(2-), Cl~-, HCO_3~-, pH and temperature. Experimental data revealed that, while Cl~-, HCO_3~-, ions and temperature strongly influence in increasing the corrosion rate, SO_4~(2-) ions decrease the rate. The effect of pH is different depending on its range between 4-12. Corrosion rates predicted by the ANN model in 3D graphics computed by Matlab programming, showed the interesting phenomenon of conjoint effects of multiple variables which throw new ideas of mitigation of corrosion by simply modifying the chemistry of the constituents. The morphology of the least and most degraded surfaces was studied by SEM.