Skip to content
DraconiticResearch
Search Sources API
197,785 studies31 sourcesUpdated 2 min ago
Peer-reviewedCC BY 4.0ACS Omega

Corrosion Prediction of AZ31 Mg Alloy Using Machine Learning and Digital Smartphone Images

  • Héctor Hernán Hernández Zarta1
  • Vitória Helena de Azevedo2
  • André Maia Guedes2
  • Habdias de Araujo Silva-Neto2
  • Thiago Ferreira da Conceição2
  • Diego Galvan2
  1. 1Universidad Nacional de Córdoba , , Haya de la Torre y Medina Allende , ,
  2. 2Universidade Federal de Santa Catarina, Campus Universitário Trindade , , , ,
Open at sourcePDFDOICite

Abstract

This work presents a machine learning approach for analyzing the corrosion behavior of AZ31 magnesium alloy using digital images acquired with a smartphone camera assembled to a homemade studio. A controlled imaging system combined with automated feature extraction enabled the quantification of surface color and texture changes associated with corrosion progression. After removing multicollinearity through correlation-based feature selection, the resulting descriptors were used to develop supervised models for two different complementary tasks. First, classification models were trained to categorize samples according to corrosion exposure time (in days) based solely on image-derived features. The Linear Support Vector Classifier (LinearSVC) achieved the best performance, reaching a test accuracy of 0.906. Second, regression models were developed to quantitatively predict hydrogen evolution during corrosion from the same image descriptors. The optimized k-Nearest Neighbors (KNN) regressor provided the most accurate prediction of hydrogen volume (R2 = 0.914), along with low RMSE (1.76 mL) and MAE (0.94 mL) values, indicating strong agreement between predicted and experimental hydrogen volumes. These results demonstrate that macroscopic image features encode relevant physicochemical information related to corrosion processes, enabling both the classification of corrosion stages and the quantitative prediction of hydrogen generation using a rapid, low-cost, and nondestructive approach.

Related

  1. Computational Fluid Dynamics-Informed Machine Learning-Enabled Digital Twin for Vapor Maldistribution Prediction in Structured Packed Distillation Columns
    Alek Nino, Hang Yi, Tony Cai +2
    ChemRxivPreprintCC BYFull textGeneral chemistryChemRxiv
  2. Artificial Intelligence-Assisted Engineering of Nanocomposite Corrosion Protection Materials: A Critical Review of Machine Learning, Molecular Simulation, and Experimental Verification
    Kufre Essien, Akanimo N. Ekanem, Aniedi E. Nyong +4
    Materials and DevicesPeer-reviewedCC BY-NC-NDFull textPhysical chemistryDOAJ
  3. Municipal wastewater sludge/laser-induced graphene nanozyme for machine-learning-assisted smartphone colorimetric tetracycline sensing
    Nguyen Ngoc Nghia, Phung Thanh An, Nguyen Huu Hieu
    RSC advancesPeer-reviewedCC BY-NCFull textMaterials & polymersEurope PMCEurope PMCPMC
  4. A Machine Learning Approach to logBB Prediction Combining Molecular Docking and Quantum-Chemical Descriptors
    Lilian Rouille
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv
  5. Accelerating Proton Affinity Prediction with Multi-Fidelity Machine Learning
    Debjyoti Bhattacharya, Yifan Liu, Valentino R. Cooper +1
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv

Cite

BibTeXRIS
BibTeX
@article{zarta2026corrosion,
  title = {{Corrosion Prediction of AZ31 Mg Alloy Using Machine Learning and Digital Smartphone Images}},
  author = {Héctor Hernán Hernández Zarta and Vitória Helena de Azevedo and André Maia Guedes and Habdias de Araujo Silva-Neto and Thiago Ferreira da Conceição and Diego Galvan},
  journal = {ACS Omega},
  year = {2026},
  month = oct,
  doi = {10.1021/acsomega.6c06905},
  url = {https://pubs.acs.org/acsodf/article/doi/10.1021/acsomega.6c06905/5446778/Corrosion-Prediction-of-AZ31-Mg-Alloy-Using},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Corrosion Prediction of AZ31 Mg Alloy Using Machine Learning and Digital Smartphone Images
AU  - Héctor Hernán Hernández Zarta
AU  - Vitória Helena de Azevedo
AU  - André Maia Guedes
AU  - Habdias de Araujo Silva-Neto
AU  - Thiago Ferreira da Conceição
AU  - Diego Galvan
PY  - 2026
DA  - 2026/10/08
JO  - ACS Omega
DO  - 10.1021/acsomega.6c06905
UR  - https://pubs.acs.org/acsodf/article/doi/10.1021/acsomega.6c06905/5446778/Corrosion-Prediction-of-AZ31-Mg-Alloy-Using
AB  - This work presents a machine learning approach for analyzing the corrosion behavior of AZ31 magnesium alloy using digital images acquired with a smartphone camera assembled to a homemade studio. A controlled imaging system combined with automated feature extraction enabled the quantification of surface color and texture changes associated with corrosion progression. After removing multicollinearity through correlation-based feature selection, the resulting descriptors were used to develop supervised models for two different complementary tasks. First, classification models were trained to categorize samples according to corrosion exposure time (in days) based solely on image-derived features. The Linear Support Vector Classifier (LinearSVC) achieved the best performance, reaching a test accuracy of 0.906. Second, regression models were developed to quantitatively predict hydrogen evolution during corrosion from the same image descriptors. The optimized k-Nearest Neighbors (KNN) regressor provided the most accurate prediction of hydrogen volume (R2 = 0.914), along with low RMSE (1.76 mL) and MAE (0.94 mL) values, indicating strong agreement between predicted and experimental hydrogen volumes. These results demonstrate that macroscopic image features encode relevant physicochemical information related to corrosion processes, enabling both the classification of corrosion stages and the quantitative prediction of hydrogen generation using a rapid, low-cost, and nondestructive approach.
SN  - 2470-1343
ER  -