Corrosion Behaviour Modelling Using Artificial Neural Networks: A Case Study in Biogas Environment

Abstract

The main objective established in this work was to develop a model based on artificial neural networks (ANNs) to predict the corrosion status of stainless steel involved in biogas production, analyzing the influence of the material composition and the breakdown potential value. To achieve this objective, an ANN model capable of predicting the corrosion status of the material without the need to perform microscopic analysis on the material surface was proposed. The applicability of the corrosion models was verified via the experimental data considering different factors such as stainless steel composition, biogas environments simulated by artificial solution, temperature, surface finish, and the breakdown potential of the passive layer of stainless steel obtained from electrochemical tests. The optimal prediction performance shown by the model in terms of specificity and sensitivity values were 0.969 and 0.971, respectively, obtaining an accuracy of 0.966. Furthermore, analyzing the influence of the breakdown potential on corrosion modelling, an alternative model was presented capable of predicting the corrosion status automatically, without the need to resort to electrochemical tests for new conditions. The results demonstrated the utility of this technique to be considered in design and maintenance planning tasks for stainless steel structures subjected to localized corrosion in biogas production.