Application of the Random Forest Algorithm of Corrosion Losses of Aluminum for the First Year of Exposure in Various Regions of the World

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription Access

Abstract

Using the random forest algorithm (RF), two models are obtained for predicting first-year corrosion losses K1 of aluminum in an open atmosphere in various regions of the world. The RF1 model was obtained using the combined databases of the international programs ISO CORRAG and MICAT and tests in Russia and is intended for evaluation of K1 in different types of atmosphere in different regions of the world. The model makes it possible to predict K1 only in the continental regions of the world. For all types of atmospheres, a comparison was made of the accuracy of the prediction of K1 according to the RF1 model and the dose-response function (DRF) presented in the ISO 9223 standard. For continental sites, a comparison of the reliability of the prediction is given by the RF2 model and the dose-response functions presented in ISO 9223 and the new DRF. It is shown that the reliability of predictions for both RF models is significantly better than using dose-response functions.

About the authors

M. A. Gavryushina

Frumkin Institute of Physical Chemistry and Electrochemistry, Russian Academy of Sciences, 119071, Moscow, Russia

Email: maleeva.marina@gmail.com
Россия, 119071, Москва

A. I. Marshakov

Frumkin Institute of Physical Chemistry and Electrochemistry, Russian Academy of Sciences, 119071, Moscow, Russia

Email: maleeva.marina@gmail.com
Россия, 119071, Москва

Yu. M. Panchenko

Frumkin Institute of Physical Chemistry and Electrochemistry, Russian Academy of Sciences, 119071, Moscow, Russia

Author for correspondence.
Email: maleeva.marina@gmail.com
Россия, 119071, Москва

References

  1. ISO 9223:2012(E). Corrosion of metals and alloys. Corrosivity of atmospheres. Classification, determination and estimation, International Standards Organization, Geneve, 2012.
  2. ISO 9224:2012(E) Corrosion of metals and alloys. Corrosivity of atmospheres. Guiding values for the corrosivity categories, 2012.
  3. Panchenko Yu.M., Marshakov A.I. // Corr. Sci. 2016. V. 109. P. 217.
  4. Abramova M.G., Panchenko Y.M., Vetrova E.Y. et al. // Prot. Met. Phys. Chem. Surf. 2021. V. 57. № 7. P. 1272–1282.
  5. Panchenko Yu.M., Marshakov A.I., Nikolaeva L.A., Igonin T.N. // Civil Eng. J. 2020. V. 6. № 8. P. 1503.
  6. Knotkova D., Boschek P., Kreislova K. In Atmospheric Corrosion, Kirk W.W. and Lawson H.H., Eds., Philadelphia, PA, USA: American Soc. Test. Mater., 1995. P. 38.
  7. Morcillo M., In Atmospheric Corrosion, Kirk W.W. and Lawson H.H., Eds., Philadelphia, PA, USA: American Soc. Test. Mater. 1995. P. 257.
  8. Tidblad J., Kucera V., Mikhailov A.A., Henriksen J., Kreislova K., Yaites T., Stöckle B., Schreiner M. // Water, Air, and Soil Pollution. 2001. V. 130. P. 1457.
  9. Панченко Ю.М., Шувахина Л.А., Михайловский Ю.Н. // Защита металлов. 1982. Т. 18. С. 575.
  10. Panchenko Yu.M., Marshakov A.I., Nikolaeva L.A., Igonin T.N. // Corr. Eng. Sci. Tech. 2020. V. 55. № 8. P. 655.
  11. Breiman L. // Machine Learning. 2001. V. 45. P. 5.
  12. Zhi Y., Fu D., Zhang D., Yang T., Li X. // Metals. 2019. V. 9. № 3. P. 383.
  13. Yan L., Diao Y., Gao K. // Materials. 2020. V. 13. № 15. P. 3266.
  14. Zhi Y., Jin Z., Lu L., Yang T., Zhou D., Pei Z., Wu D., Fu D., Zhang D., Li X. // Corrosion Science. 2021. V. 178. № 109084.
  15. Panchenko Yu.M., Marshakov A.I., Bardin I.V., Shklyaev A.V. // Prot. Metals Phys. Chem. Surf. 2019. V. 55. №. 4. P. 753.
  16. Mikhailov A.A., Tidblad J., Kucera V. // Prot. Metals. 2004. V. 40. № 6. P. 541.
  17. Tidblad J., Kucera V., Mikhailov A.A., Knotkova D. In Outdoor Atmospheric Corrosion, Townsend H.E., Eds., West Conshohocken, PA, USA: American Soc. Test. Mater., 2002, p. 73.
  18. Panchenko Yu.M., Marshakov A.I., Nikolaeva L.A., Kovtanyuk V.V. // AIMS Materials Sci. 2018. V. 5. № 4. P. 624.
  19. Scikit-learn. Machine Learning in Python // https://scikit-learn.org/stable/index.html
  20. https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html

Supplementary files

Supplementary Files
Action
1. JATS XML
2.

Download (237KB)
3.

Download (268KB)
4.

Download (254KB)
5.

Download (372KB)
6.

Download (343KB)

Copyright (c) 2023 М.А. Гаврюшина, А.И. Маршаков, Ю.М. Панченко