Data Mining Model for Prediction Effect of Corrosion Inhibition

(2018) Data Mining Model for Prediction Effect of Corrosion Inhibition. Journal of Bio- and Tribo-Corrosion. ISSN 21984220 (ISSN)

Full text not available from this repository.

Abstract

Electrochemical impedance Nyquist tests have become a common technique to study corrosion inhibition behavior of steel. Methionine has been investigated as corrosion inhibitor for carbon steel (C-steel) in 1 M HCl solution using electrochemical impedance spectroscopy (EIS). Based on these experimental tests, the efficiency of the inhibitor increases with increase in the inhibitor concentration and decreases with increase in temperature. In this paper, a model based on neural networks is presented in order to obtain predictions of imaginary impedance based on the real part of the impedance as a function of inhibitor concentration and temperature. For the network, the learning algorithm, the hyperbolic tangent sigmoid transfer function, and the linear transfer function were used. The results based on correlation coefficient and root-mean-square show the utility of this tool to predict impedance values without requiring the use of EIS tests. © 2018, Springer International Publishing AG, part of Springer Nature.

Item Type: Article
Keywords: Corrosion inhibitor Electrochemical test Neural network
Divisions: Other
Journal or Publication Title: Journal of Bio- and Tribo-Corrosion
Journal Index: Scopus
Volume: 4
Number: 2
Identification Number: https://doi.org/10.1007/s40735-018-0139-y
ISSN: 21984220 (ISSN)
Depositing User: Zahra Otroj
URI: http://eprints.mui.ac.ir/id/eprint/8178

Actions (login required)

View Item View Item