Atmospheric corrosion: statistical validation of models

Authors

  • V. Díaz Facultad de ingeniería. Universidad de la República Oriental del Uruguay
  • V. Martínez-Luaces Facultad de Química. Universidad de la República Oriental del Uruguay
  • G. Guineo-Cobs Facultad de Química. Universidad de la República Oriental del Uruguay

DOI:

https://doi.org/10.3989/revmetalm.2003.v39.i4.335

Keywords:

Atmospheric corrosion, Bilogarithmic law, Correlation coefficient, Lack of fit, Statistical analysis

Abstract


In this paper we discuss two different methods for validation of regression models, applied to corrosion data. One of them is based on the correlation coefficient and the other one is the statistical test of lack of fit. Both methods are used here to analyse fitting of bilogarithmic model in order to predict corrosion for very low carbon steel substrates in rural and urban-industrial atmospheres in Uruguay. Results for parameters A and n of the bilogarithmic model are reported here. For this porpose, all repeated values were used instead of using average values as usual. Modelling is carried out using experimental data corresponding to steel substrates under the same initial meteorological conditions (in fact, they are put in the rack at the same time). Results of correlation coefficient are compared with the lack of it tested at two different signification levels (a= 0.01 and a= 0.05). Unexpected differences between them are explained and finally, it is possible to conclude, at least in the studied atmospheres, that the bilogarithmic model does not fit properly the experimental data.

Downloads

Download data is not yet available.

Downloads

Published

2003-08-30

How to Cite

Díaz, V., Martínez-Luaces, V., & Guineo-Cobs, G. (2003). Atmospheric corrosion: statistical validation of models. Revista De Metalurgia, 39(4), 243–251. https://doi.org/10.3989/revmetalm.2003.v39.i4.335

Issue

Section

Articles