Identification of Corrosive Substances and Types of Corrosion Through Electrochemical Noise Using Signal Processing and Machine Learning

  • Lorraine Marques Alves
  • Romulo Almeida Cotta
  • Patrick Marques CiarelliEmail author
  • Evandro O. T. Salles
  • Klaus F. Côco
  • Jorge L. A. Samatelo


Several systems in industries are subject to the effects of corrosion, such as machines, structures, and a lot of equipment. As consequence, the corrosion can damage structures and equipment, causing financial losses and accidents. Among the most common types is the localized corrosion, and it is present in most industrial processes and is the most difficult to detect. Such consequences can be reduced considerably with the use of methods of detection, analysis and monitoring of corrosion in hazardous areas, which can provide useful information to maintenance planning and accident prevention. In this work, we analyze some features extracted from electrochemical noise for the classification of different types of localized corrosion. Furthermore, we use some techniques to identify corrosive substances that may cause corrosion in materials. For both tasks, we apply signal processing and machine learning techniques. Experimental results show that the features obtained using wavelet transform and recurrence quantification analysis are effective to solve both tasks: the corrosion identification and the classification of substances. Almost all evaluated machine learning techniques achieved an average accuracy above 90%.


Corrosion Electrochemical noise Machine learning Wavelet transforms Recurrence quantification analysis 



Evandro O. T. Salles would like to thank FAPES - Fundação de Amparo à Pesquisa e Inovação do Espírito Santo by the partial support under grant 244/2016. Patrick Marques Ciarelli thanks the partial funding of his research work provided by CNPq (Grant 312032/ 2015-3).


  1. Aballe, A., Bethencourt, M., Botana, F., & Marcos, M. (1999). Using wavelets transform in the analysis of electrochemical noise data. Electrochimica Acta, 44(26), 4805–4816.CrossRefGoogle Scholar
  2. Ahmad, S., Jibran, M. A. A., Azad, A. K., & Maslehuddin, M. (2014). A simple and reliable setup for monitoring corrosion rate of steel rebars in concrete. The Scientific World Journal, 2014, 10.Google Scholar
  3. Alves, L.M., Cotta, R.A., & Ciarelli, P.M. (2017). Identification of types of corrosion through electrochemical noise using machine learning techniques. In Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods (ICPRAM), (pp. 332–340).Google Scholar
  4. Alves, L.M., Cotta, R.A., Prado, A.R., & Ciarelli, P.M. (2017). Identification of corrosive substances through electrochemical noise using wavelet and recurrence quantification analysis. In Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods (ICPRAM), (pp. 718–723).Google Scholar
  5. Amaya, J., Cottis, R. A., & Botana, F. (2005). Shot noise and statistical parameters for the estimation of corrosion mechanisms. Corrosion Science, 47(12), 3280–3299.CrossRefGoogle Scholar
  6. Barr, E., Pierrerd, L., & Greenfield, A. (2001). Application of electrochemical noise monitoring to inhibitor evaluation and optimization in the field: Results from the kaybob south sour gas field. In Corrosion. NACE International.
  7. Bergelson, V. (2000). The multifarious poincaré recurrence theorem. Descriptive Set Theory and Dynamical Systems, 1, 31–57.CrossRefzbMATHGoogle Scholar
  8. Cottis, R. (2001). Interpretation of electrochemical noise data. Corrosion, 57(3), 265–285.CrossRefGoogle Scholar
  9. Cottis, R., & Turgoose, S. (1999). Corrosion testing made easy: Impedance and noise analysis (1st ed.). Houston: NACE International.Google Scholar
  10. Cottis, R. A., Homborg, A., & Mol, J. (2015). The relationship between spectral and wavelet techniques for noise analysis. Electrochimica Acta, 202, 277–287.CrossRefGoogle Scholar
  11. Cox, W. M. (2014). A strategic approach to corrosion monitoring and corrosion management. Procedia Engineering, 86, 567–575.CrossRefGoogle Scholar
  12. Duda, R., Hart, D. G., & Stork, P. (2000). Pattern recognition (1st ed.). Hoboken: Wiley Interscience.Google Scholar
  13. Fadel, S. G., Fatore, M., Duarte, S., & Paulovich, V. (2015). Loch: A neighborhood-based multidimensional projection technique for high-dimensional sparse spaces. Neurocomputing, 150, 546–556.CrossRefGoogle Scholar
  14. Gentil, V. (2003). Corrosão. 4a ed. Rio de Janeiro: Livros Técnicos e Científicos.Google Scholar
  15. Garcia-Ochoa, E., & Corvo, F. (2015). Using recurrence plot to study the dynamics of reinforcement steel corrosion. Protection of Metals and Physical Chemistry of Surfaces, 51(4), 716–724.CrossRefGoogle Scholar
  16. Haykin, S. (1998). Neural networks: A comprehensive foundation (2nd ed.). Upper Saddle River: Prentice Hall.zbMATHGoogle Scholar
  17. Hou, Y., Aldrich, C., Lepkova, K., Suarez, L., & Kinsella, B. (2016). Monitoring of carbon steel corrosion by use of electrochemical noise and recurrence quantification analysis. Corrosion Science, 112, 63–72.CrossRefGoogle Scholar
  18. Jian, L., Weikang, K., Jiangbo, S., Ke, W., Weikui, W., Weipu, Z., et al. (2013). Determination of corrosion types from electrochemical noise by artificial neural networks. International Journal of Electrochemical Science, 8, 2365–2377.Google Scholar
  19. Koch, G., Varney, J., Thompson, N., Moghissi, O., Gould, M., & Payer, J. (2016). International measures of prevention, application and economics of corrosion technologies study (impact). Technical Report, NACE International.Google Scholar
  20. Mallat, S. (2009). A wavelet tour of signal processing: The sparse way (3rd ed.). Burlington: Academic Press Elsevier.zbMATHGoogle Scholar
  21. Marquardt, D. W. (1963). An algorithm for least-squares estimation of nonlinear parameters. Journal of the Society for Industrial and Applied Mathematics, 11(2), 431–441.MathSciNetCrossRefzbMATHGoogle Scholar
  22. Marwan, N., Romano, M., Thiel, M., & Kurths, J. (2007). Recurrence plots for the analysis of complex systems. Physics Reports, 438, 237–329.MathSciNetCrossRefGoogle Scholar
  23. Montalban, L., Henttu, P., & Piche, R. (2007). Recurrence quantification analysis of electrochemical noise data during pit development. International Journal of Bifurcation and Chaos, 17, 3725–3728.CrossRefzbMATHGoogle Scholar
  24. Moshrefi, R., Mahjani, M., & Jafarian, M. (2014). Application of wavelet entropy in analysis of electrochemical noise for corrosion type identification. Electrochemistry Communications, 48, 49–51.CrossRefGoogle Scholar
  25. Planinsic, P., & Petek, A. (2008). Characterization of corrosion process by current noise-based fractal and correlation analysis. Electrochimica Acta, 53(16), 5206–5214.CrossRefGoogle Scholar
  26. Poursaee, A. (2010). Potentiostatic transient technique, a simple approach to estimate the corrosion current density and Stern–Geary constant of reinforcing steel in concrete. Cement and Concrete Research, 40(9), 1451–1458.CrossRefGoogle Scholar
  27. Quinlan, J. (1988). Decision trees and multivalued attributes (11th ed.). Oxford: Oxford University Press.zbMATHGoogle Scholar
  28. Research, E.P.A. (1980). Basics of corrosion measurements—application note corr-1. Technical Report, Princeton.Google Scholar
  29. Theodoridis, S., & Koutroumbas, K. (2008). Pattern recognition (4th ed.). Amsterdam: Elsevier.zbMATHGoogle Scholar

Copyright information

© Brazilian Society for Automatics--SBA 2018

Authors and Affiliations

  1. 1.Federal University of Espírito SantoVitória-ESBrazil

Personalised recommendations