A comprehensive approach based on SVM to model pitting corrosion behaviour of EN 1.4404 stainless steel

Abstract

Potentiodynamic polarisation tests have been widely used to evaluate pitting corrosion behaviour of stainless steels. This technique involves two principal steps: the interpretation of the polarisation curve and the microscopic analysis of the material surface. Therefore, analysing the influence of all possible environmental conditions on pitting corrosion behaviour can be complex. To deal with this problem, automatic models based on Bayes classifier (BC) and support vector machines (SVMs) techniques are presented in this work. The principal environmental variables involved in pitting corrosion: chloride ion concentration, pH and temperature are considered. Based on the obtained results related to precision and accuracy terms, SVMs models using linear or radial basis function kernels outperform models based on Bayes theory. In addition, ROC analysis reveals that SVMs models using linear kernel is the best option providing maximum values of sensitivity and specificity. These results reflect the validity of the presented model to be applied in the automatic determination of the corrosion state of austenitic stainless steel as function of environmental conditions, not requiring the use of polarisation tests.

Prediction of pitting corrosion status of EN 1.4404 stainless steel by using a 2‐stage procedure based on support vector machines

“…Based on our previous studies, when only environmental conditions (chloride ion concentration, pH, and temperature) were considered to model pitting corrosion behaviour, the maximum value of accuracy reached by the proposed model was 0.87. Thus, comparing this value with the result obtained by the model proposed in this work (accuracy = 0.952), it can be concluded that breakdown potential is a relevant parameter to be considered in the analysis of pitting corrosion susceptibility of stainless steel.…”

“…With the aim to develop a model capable to predict pitting corrosion status of stainless steel without resorting to electrochemical tests, authors presented a different study . In this case, the model was developed considering the most critical environmental factors involved in pitting corrosion (chloride ion concentration, pH, and temperature), not considering the breakdown potential values.…”

A support vector machine‐based ensemble algorithm for pitting corrosion modeling of EN 1.4404 stainless steel in sodium chloride solutions

“…In this work, according to the studies presented previously, a novel ensemble model based on SVM is presented. The model consists of three phases: in the first one, the breakdown potential value was estimated according to the environmental conditions.…”

Characterization of pitting corrosion of stainless steel using artificial neural networks

“…Based on our previous studies about modelling behavior of stainless steels , and referring to the works presented in the literature review, the models based on artificial intelligence techniques have become a useful tool to be applied in the corrosion studies. In this sense, this work presents different models based on artificial neural networks, including the analysis about the influence of the Bayesian regularization in order to predict pitting status of 316 L stainless steel (1 when the material suffers pitting attack and 0 for no pitting attack).…”