Pitting potential modeling using Bayesian neural networks

Abstract Polarization tests have become a common technique to study pitting corrosion behavior of stainless steel. Based on these experimental tests, the pitting potential value may be determined at the potential at which current density reaches the value of 100 μA/cm 2 . The potential at this value of current density, associated to the breakdown potential, provides useful information about the likelihood of suffering pitting corrosion in the material under study: a more positive pitting potential means that the material can be expected to be more resistant to pitting corrosion. In this paper, a model based on Bayesian neural networks is presented in order to predict this potential value in different environmental conditions. In this way, it is possible to make comparison of corrosion resistance of the material under study in different environmental conditions. The results based on correlation coefficient and root mean square show the utility of this tool to predict potential values without requiring the use of polarization tests.

[1]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[2]  نوال محمد داود الكروي.  Corrosion of stainless steel , 2011 .

[3]  M. Moayed,et al.  A comparative study of critical pitting temperature (CPT) of stainless steels by electrochemical impedance spectroscopy (EIS), potentiodynamic and potentiostatic techniques , 2012 .

[4]  Richard J. Chater,et al.  Why stainless steel corrodes , 2002, Nature.

[5]  Martin T. Hagan,et al.  Neural network design , 1995 .

[6]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[7]  J. Vereecken.  The 8th International Symposium Electrochemical Methods in Corrosion Research , 2004 .

[8]  M. Moayed,et al.  An investigation on the effect of bleaching environment on pitting corrosion and transpassive dissolution of 316 stainless steel , 2005 .

[9]  Á. Horváth,et al.  Comparative electrochemical study of 08H18N10T, AISI 304 and AISI 316L stainless steels , 2007 .

[10]  K. V. D. Bergh,et al.  Electrochemistry: a powerful analytical tool in steel research , 2004 .

[11]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[12]  Alexander M. Korsunsky,et al.  Direct evidence of initial pitting corrosion , 2008 .

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

[14]  Li Xiaogang,et al.  Cellular automata modeling on pitting current transients , 2009 .

[15]  M. Kamrunnahar,et al.  Prediction of corrosion behavior using neural network as a data mining tool , 2010 .

[16]  C. García,et al.  Pitting corrosion of welded joints of austenitic stainless steels studied by using an electrochemical minicell , 2008 .

[17]  Z. Ahmad.  Principles of Corrosion Engineering and Corrosion Control , 2006 .