Quantitative and Qualitative Analysis of Atmospheric Effects on Carbon Steel Corrosion Using an ANN Model

This study develops an artificial neural network (ANN) model to predict the corrosion rate of carbon steel under a wide range of atmospheric conditions. The model incorporates input variables, including temperature (−3.1–28.2 °C), relative humidity (33.3–91.1%), time of wetness (0.003–0.976), precip...

Full description

Saved in:
Bibliographic Details
Main Authors: Pasupuleti L. Narayana, Saurabh Tiwari, Anoop K. Maurya, Muhammad Ishtiaq, Nokeun Park, Nagireddy Gari Subba Reddy
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Metals
Subjects:
Online Access:https://www.mdpi.com/2075-4701/15/6/607
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850168031786827776
author Pasupuleti L. Narayana
Saurabh Tiwari
Anoop K. Maurya
Muhammad Ishtiaq
Nokeun Park
Nagireddy Gari Subba Reddy
author_facet Pasupuleti L. Narayana
Saurabh Tiwari
Anoop K. Maurya
Muhammad Ishtiaq
Nokeun Park
Nagireddy Gari Subba Reddy
author_sort Pasupuleti L. Narayana
collection DOAJ
description This study develops an artificial neural network (ANN) model to predict the corrosion rate of carbon steel under a wide range of atmospheric conditions. The model incorporates input variables, including temperature (−3.1–28.2 °C), relative humidity (33.3–91.1%), time of wetness (0.003–0.976), precipitation (13–4656 mm), sulfur dioxide (0–68.2 mg/m<sup>2</sup>·d), and chloride concentrations (0 to 359.8 mg/m<sup>2</sup>·d). The model demonstrated excellent predictive capability and reliability, with R<sup>2</sup> values of 97.2% and 77.6% for the training and testing datasets, respectively. The model demonstrated a strong predictive performance, with an R<sup>2</sup> of 97.2% for the training set and 77.6% for the test set. It achieved a mean absolute error (MAE) of 5.633 μm/year for training and 18.86 μm/year for testing, along with a root mean square error (RMSE) of 0.000055, indicating reliable generalization despite the limited dataset size. The analysis showed that the relative humidity had the most significant impact on the corrosion rate. The practical applications of the model extend to optimizing material selection and devising effective maintenance strategies.
format Article
id doaj-art-80a05faa3fb74a009c899f8a74e2b65f
institution OA Journals
issn 2075-4701
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Metals
spelling doaj-art-80a05faa3fb74a009c899f8a74e2b65f2025-08-20T02:21:04ZengMDPI AGMetals2075-47012025-05-0115660710.3390/met15060607Quantitative and Qualitative Analysis of Atmospheric Effects on Carbon Steel Corrosion Using an ANN ModelPasupuleti L. Narayana0Saurabh Tiwari1Anoop K. Maurya2Muhammad Ishtiaq3Nokeun Park4Nagireddy Gari Subba Reddy5Titanium Department, Advanced Metal Division, Korea Institute of Materials Science, Changwon 51508, Republic of KoreaSchool of Materials Science and Engineering, Yeungnam University, Gyeongsan 38541, Republic of KoreaTitanium Department, Advanced Metal Division, Korea Institute of Materials Science, Changwon 51508, Republic of KoreaVirtual Materials Laboratory, School of Materials Science and Engineering, Engineering Research Institute, Gyeongsang National University, Jinju 52828, Republic of KoreaSchool of Materials Science and Engineering, Yeungnam University, Gyeongsan 38541, Republic of KoreaVirtual Materials Laboratory, School of Materials Science and Engineering, Engineering Research Institute, Gyeongsang National University, Jinju 52828, Republic of KoreaThis study develops an artificial neural network (ANN) model to predict the corrosion rate of carbon steel under a wide range of atmospheric conditions. The model incorporates input variables, including temperature (−3.1–28.2 °C), relative humidity (33.3–91.1%), time of wetness (0.003–0.976), precipitation (13–4656 mm), sulfur dioxide (0–68.2 mg/m<sup>2</sup>·d), and chloride concentrations (0 to 359.8 mg/m<sup>2</sup>·d). The model demonstrated excellent predictive capability and reliability, with R<sup>2</sup> values of 97.2% and 77.6% for the training and testing datasets, respectively. The model demonstrated a strong predictive performance, with an R<sup>2</sup> of 97.2% for the training set and 77.6% for the test set. It achieved a mean absolute error (MAE) of 5.633 μm/year for training and 18.86 μm/year for testing, along with a root mean square error (RMSE) of 0.000055, indicating reliable generalization despite the limited dataset size. The analysis showed that the relative humidity had the most significant impact on the corrosion rate. The practical applications of the model extend to optimizing material selection and devising effective maintenance strategies.https://www.mdpi.com/2075-4701/15/6/607atmospheric conditionscorrosion ratecarbon steelartificial neural networkquantitative estimation
spellingShingle Pasupuleti L. Narayana
Saurabh Tiwari
Anoop K. Maurya
Muhammad Ishtiaq
Nokeun Park
Nagireddy Gari Subba Reddy
Quantitative and Qualitative Analysis of Atmospheric Effects on Carbon Steel Corrosion Using an ANN Model
Metals
atmospheric conditions
corrosion rate
carbon steel
artificial neural network
quantitative estimation
title Quantitative and Qualitative Analysis of Atmospheric Effects on Carbon Steel Corrosion Using an ANN Model
title_full Quantitative and Qualitative Analysis of Atmospheric Effects on Carbon Steel Corrosion Using an ANN Model
title_fullStr Quantitative and Qualitative Analysis of Atmospheric Effects on Carbon Steel Corrosion Using an ANN Model
title_full_unstemmed Quantitative and Qualitative Analysis of Atmospheric Effects on Carbon Steel Corrosion Using an ANN Model
title_short Quantitative and Qualitative Analysis of Atmospheric Effects on Carbon Steel Corrosion Using an ANN Model
title_sort quantitative and qualitative analysis of atmospheric effects on carbon steel corrosion using an ann model
topic atmospheric conditions
corrosion rate
carbon steel
artificial neural network
quantitative estimation
url https://www.mdpi.com/2075-4701/15/6/607
work_keys_str_mv AT pasupuletilnarayana quantitativeandqualitativeanalysisofatmosphericeffectsoncarbonsteelcorrosionusinganannmodel
AT saurabhtiwari quantitativeandqualitativeanalysisofatmosphericeffectsoncarbonsteelcorrosionusinganannmodel
AT anoopkmaurya quantitativeandqualitativeanalysisofatmosphericeffectsoncarbonsteelcorrosionusinganannmodel
AT muhammadishtiaq quantitativeandqualitativeanalysisofatmosphericeffectsoncarbonsteelcorrosionusinganannmodel
AT nokeunpark quantitativeandqualitativeanalysisofatmosphericeffectsoncarbonsteelcorrosionusinganannmodel
AT nagireddygarisubbareddy quantitativeandqualitativeanalysisofatmosphericeffectsoncarbonsteelcorrosionusinganannmodel