Predicting the Corrosion Rates of Steels in Sea Water Using Artificial Neural Network

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.

[1]  D. J. C. Mackay,et al.  Estimation of Hot Torsion Stress Strain Curves in Iron Alloys Using a Neural Network Analysis , 1999 .

[2]  Walter Bogaerts,et al.  SCC Analysis of Austenitic Stainless Steels in Chloride-Bearing Water by Neural Network Techniques , 1992 .

[3]  K. V. Sudhakar,et al.  Prediction of corrosion-fatigue behavior of DP steel through artificial neural network , 2001 .

[4]  M Karplus,et al.  Evolutionary optimization in quantitative structure-activity relationship: an application of genetic neural networks. , 1996, Journal of medicinal chemistry.

[5]  Robert A. Cottis,et al.  Phenomenological modelling of atmospheric corrosion using an artificial neural network , 1999 .

[6]  M. Urquidi-Macdonald,et al.  Prediction of IGSCC in Type 304 SS using an artificial neural network , 1994 .

[7]  Walter Bogaerts,et al.  Neural network prediction of stress corrosion cracking , 1992 .

[8]  Sybrand van der Zwaag,et al.  Effects of Carbon Concentration and Cooling Rate on Continuous Cooling Transformations Predicted by Artificial Neural Network , 1999 .

[9]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[10]  J. I. Mickalonis,et al.  Predictive Models for Determination of Pitting Corrosion Versus Inhibitor Concentrations and Temperature for Radioactive Sludge in Carbon Steel Waste Tanks , 1998 .

[11]  F. Haynie,et al.  EFFECTS OF ATMOSPHERIC POLLUTANTS ON CORROSION BEHAVIOR OF STEELS , 1971 .

[12]  J. I. Mickalonis,et al.  Prediction of Aluminum Pitting in Natural Waters via Artificial Neural Network Analysis , 1999 .

[13]  Mathematics of Control, Signals, and Systems , 1994 .

[14]  Salvador Pintos,et al.  Artificial neural network modeling of atmospheric corrosion in the MICAT project , 2000 .

[15]  Ah Chung Tsoi,et al.  Universal Approximation Using Feedforward Neural Networks: A Survey of Some Existing Methods, and Some New Results , 1998, Neural Networks.

[16]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[17]  Y. Cheng,et al.  Artificial neural network technology for the data processing of on-line corrosion fatigue crack growth monitoring , 1999 .

[18]  Hong Chen,et al.  Approximation capability in C(R¯n) by multilayer feedforward networks and related problems , 1995, IEEE Trans. Neural Networks.