Modelling input data interactions for the optimization of artificial neural networks used in the prediction of pitting corrosion

Abstract

Purpose This paper aims to predict the localized corrosion resistance by the application of artificial neural networks. It emphasizes the importance to take into account the relationships between the physical parameters before presenting them to the network. Design/methodology/approach The work was conducted in two phases. At the beginning, the authors executed an experimental program to measure pitting corrosion resistance of carbon steel in an aqueous environment. More than 900 electrochemical experiments were conducted in chemical solutions containing different concentrations of pitting agents, corrosion inhibitors and oxidant reagents. The obtained results were collected in a table where for a combination of the experimental parameters corresponds a pitting potential Epit obtained from the corresponding electrochemical experiment. In the second step, the authors used the experimental data to train different artificial neuron networks for predicting pitting potentials. Findings In this step, the authors considered the relationships that the chemical parameters are likely to have between them. Two types of relationships were taken into account: chemical equilibria which are controlled by the pH and the synergistic relationships that some corrosion inhibitors may have when they are in the presence of a chemical oxidant. Originality/value This comparative study shows that adjusting the input data by considering the physical relationships between them allows a better prediction of the pitting potential. The quality of the prediction, quantified by a regression factor, is qualitatively confirmed by a statistical distribution of the gap between experimental and calculated pitting potentials.

Pitting corrosion prediction from cathodic data: application of machine learning

“…The properties of the chemical solutions are close to that of the cooling fluid used in the circuit. Design/methodology/approach -In a previous study, this paper demonstrated the effectiveness of machine learning in predicting the localized corrosion resistance of a material by considering as input data the physicochemical properties of its environment (Boucherit et al, 2019). With the present study, the authors improve the results by considering as input data, cathodic currents.…”

“…The cathodic current values are the input data. The present work differs from that carried out previously where we considered as input data the physicochemical properties of the solution (Boucherit et al, 2019). In the present work, we limit observations only to the current response of the material following a cathodic potential scan and then speculate on its resistance to pitting corrosion.…”

“…By exploiting these data, we build mathematical models based on different algorithms and we adjust them so that they can predict the performance of steel against localized corrosion in a given environment (Boukhari et al, 2017). In a recently published study (Boucherit et al, 2019), we used different multilayer neural networks to predict pitting potential. We considered as input data the measured physicochemical properties of the solution.…”

Using Intelligent Models to Predict Weight Loss of Raw Materials During Cement Clinker Production

“…In contrary, it is difficult or even impossible to predict outcome with conventional statistical models [7]. The major advantages of using artificial intelligence is that it does not need the explicit knowledge behavior of phenomena and any kind of mathematical equation in advance [8]. The intelligent models need only to be trained by sufficient data under optimal parameters [9] to predict the target with high performance [10].…”

Application and Comparison of Machine Learning Algorithms for Predicting Mass Loss of Cement Raw Materials due to Decarbonation Process

“…In the present study, various models such as Deep Networks using Auto-Encoder (DN-AE), Artificial Neural Network (ANN), Artificial Neural Network combined with Particle Swarm Optimization algorithm (PSO-ANN) and Ant Colony Optimization (ACO) combined with Artificial Neural Network (ACO-ANN) are used to predict the mass loss of cement raw materials due to decarbonation process. These algorithms are intelligent methodologies that have shown successful and promising results in the domains of modelling and prediction [8] and can be useful and powerful alternative [9]. DN-AE has achieved a good prediction performance on limited protein phosphorylation [10].…”