Predicting the Corrosion Rates of Steels in Sea Water Using Artificial Neural Network
Wei You, Yaxiu Liu · 2008
Back-propagation artificial neural network was developed to predict the corrosion rates of steels in sea water. Leave-one out method was used to train the ANN model. Test results showed that the prediction performance of the ANN model is satisfactory: the scatter dots distribute along the 0__45deg diagonal line in the scatter diagram, the values of statistical criteria are 1.3498 muAldrcm-2 (MSE), 10.85%(MSRE), and 1.8668(VOF) respectively. Moreover, the ANN model was used to analyse the quantitative effects of parameters of environment in sea water on the corrosion rate, results showed that the corrosion rate decreases with the increase of temperature and pH value, increase with the increase of oxygen content and oxidation-reduce potent, and change little with the increase of salt content.