Machines. Technologies. Materials.
Vol. 20 (2026), Issue 5, pg(s) 195-198

TECHNOLOGIES

Artificial intelligence-assisted framework for predicting electrochemical deterioration of reinforced concrete structures under combined chloride and stray current exposure

  • 1 State University of Novi Pazar, Department of Technical and Technological Sciences, Faculty of Civil Engineering, Novi Pazar, Serbia
  • 2 University of Pristina, Faculty of Technical Sciences, Architecture, Kosovska Mitrovica

Abstract

Reinforcement corrosion remains a major cause of premature deterioration of reinforced concrete infrastructure, especially when chloride ingress and stray direct currents act simultaneously. This paper develops and computationally demonstrates an artificial intelligence-assisted framework for predicting a relative electrochemical deterioration score from seven measurable inputs: corrosion potential, concrete electrical resistivity, corrosion current density, chloride content, moisture, temperature and stray-current intensity. A reproducible synthetic parametric database of 1,200 scenarios was generated within physically plausible engineering ranges. Four supervised learning models—an artificial neural network, Random Forest, support vector regression and Gradient Boosting—were trained using a 75/25 stratified train-test split. Prediction accuracy was assessed by R², mean absolute error and root mean square error, while permutation importance was used to interpret the dominant predictors. The ensemble models achieved the strongest performance, and the importance analysis confirmed that corrosion current density, chloride content and electrical resistivity exerted the largest influence on the predicted condition. The results are a methodological demonstration rather than validation against laboratory or field measurements. The proposed workflow is intended to complement conventional electrochemical inspection, support maintenance prioritisation and provide a transparent basis for future calibration using monitored reinforced concrete structures.

References

  1. U.M. Angst, B. Elsener, C.K. Larsen, Ø. Vennesland, Critical chloride content in reinforced concrete – A review, Cement and Concrete Research 39 (2009) 1122–1138. https://doi.org/10.1016/j.cemconres.2009.08.006.
  2. C. Andrade, C. Alonso, Corrosion rate monitoring in the laboratory and on-site, Construction and Building Materials 10 (1996) 315–328. https://doi.org/10.1016/0950-0618(95)00044-5.
  3. B. Elsener (Ed.), Corrosion of Steel in Concrete: Prevention, Diagnosis, Repair, 2nd ed., Wiley-VCH, Weinheim, 2013.
  4. C. Alonso, C. Andrade, M. Castellote, P. Castro, Chloride threshold values to depassivate reinforcing bars embedded in a standardized OPC mortar, Cement and Concrete Research 30 (2000) 1047–1055. https://doi.org/10.1016/S0008-8846(00)00265-9.
  5. Z. Chen, L. Gao, D.A. Koleva, Evaluating the stray current corrosion of steel rebar in different layouts, Measurement 196 (2022) 111217. https://doi.org/10.1016/j.measurement.2022.111217.
  6. M. Chen, R.P. Chen, Y. Chen, X. Ma, Stray current induced chloride ion transport and corrosion characteristics of cracked ultra-high performance concrete, Construction and Building Materials 398 (2023) 132536. https://doi.org/10.1016/j.conbuildmat.2023.132536.
  7. Y.-Q. Chen, M.-Y. Chen, R.-P. Chen, X. Kang, Stray current induced ITZ effect on chloride transport in concrete, Construction and Building Materials 409 (2023) 133759. https://doi.org/10.1016/j.conbuildmat.2023.133759.
  8. Q. Chen, Q. Zhang, T. Zhu, et al., Coupling effect of concrete cracks and stray current on chloride-induced corrosion of rebar, Construction and Building Materials 449 (2024) 138403. https://doi.org/10.1016/j.conbuildmat.2024.138403.
  9. ASTM International, ASTM C876-22b: Standard Test Method for Corrosion Potentials of Uncoated Reinforcing Steel in Concrete, West Conshohocken, PA, 2022.
  10. RILEM TC 154-EMC, Test methods for on-site corrosion rate measurement of steel reinforcement in concrete by means of the polarization resistance method, Materials and Structures 37 (2004) 623–643.
  11. W.Z. Taffese, L. Espinosa-Leal, Prediction of chloride resistance level of concrete using machine learning for durability and service-life assessment, Journal of Building Engineering 60 (2022) 105146. https://doi.org/10.1016/j.jobe.2022.105146.
  12. V.Q. Tran, Machine learning approach for investigating chloride diffusion coefficient of concrete containing supplementary cementitious materials, Construction and Building Materials 328 (2022) 127103. https://doi.org/10.1016/j.conbuildmat.2022.127103.
  13. K.H. Liu, J.K. Zheng, F. Pacheco-Torgal, X.Y. Zhao, Innovative modelling framework of chloride resistance of recycled aggregate concrete using ensemble machine-learning methods, Construction and Building Materials 337 (2022) 127613. https://doi.org/10.1016/j.conbuildmat.2022.127613.
  14. W.Z. Taffese, L. Espinosa-Leal, A machine learning method for predicting the chloride migration coefficient of concrete, Construction and Building Materials 348 (2022) 128566. https://doi.org/10.1016/j.conbuildmat.2022.128566.
  15. W.Z. Taffese, B. Hilloulin, Y. Villagran Zaccardi, et al., Machine learning in concrete durability: challenges and pathways identified by RILEM TC 315-DCS towards enhanced predictive models, Materials and Structures 58 (2025) 145.
  16. L. Breiman, Random forests, Machine Learning 45 (2001) 5–32. https://doi.org/10.1023/A:1010933404324.
  17. C. Cortes, V. Vapnik, Support-vector networks, Machine Learning 20 (1995) 273–297. https://doi.org/10.1007/BF00994018.
  18. J.H. Friedman, Greedy function approximation: a gradient boosting machine, Annals of Statistics 29 (2001) 1189–1232. https://doi.org/10.1214/aos/1013203451.
  19. C.M. Bishop, Pattern Recognition and Machine Learning, Springer, New York, 2006.
  20. ISO 12696:2022, Cathodic protection of steel in concrete, International Organization for Standardization, Geneva, 2022.

Article full text

Download PDF