A Artificial Neural-Based Prediction of Corrosion Rates in Structural Steel

DOI

No DOI

Published In

Volume 2, Issue 3 (2022)

Published Online

May-June 2022

Pages

05-07

Article Type

Research Article

Check for updates

No DOI available for cross-reference

A phenomenaloutcome for theprediction of disintegration in steelwas proposedwith the capacity to learn ofartificialneural network using MATLAB programming. The assumption for disintegration rate has transformed into a huge test for the Indiansteel business too concerning the planning neighborhood. This paper presents the assessments finished towards the assumption ofcorrosion rates by using fake cerebrum associations (ANN), in which getting ready of 406 courses of action of data using Levenberg-Marquardtalgorithm gained from preliminary data. The readiness sets have been created for three levels of utilization, for instance, mild,moderate and outrageous through ANN and achieved an example of a consistent informative twist. The data limits consideredwereequivalenttosimulatecorrosionofstructuralsteelexposedtoatmospheric,marineorchemicalenvironment.Thecorrelation estimations (R) in ANN has turned out to be 90%. The trial results have been endorsed to certify the ampleness of developedANNmodelforpredictionofcorrosionrate. Keywords: Corrosion,Artificialneuralnetworks(ANN),Levenberg-Marquardt estimation.