International Journal of Engineering and Manufacturing (IJEM)
IJEM Vol. 16, No. 3, 8 Jun. 2026
Cover page and Table of Contents: PDF (size: 1954KB)
Physics-Informed Hybrid Machine Learning Framework for Adsorption-Consistent Prediction of Corrosion Inhibition Efficiency
PDF (1954KB), PP.42-66
Views: 0 Downloads: 0
Author(s)
Index Terms
Physics-informed neural networks, corrosion inhibition efficiency, adsorption thermodynamics, hybrid machine learning, surrogate modeling, Langmuir isotherm, materials informatics, data-driven corrosion modeling
Abstract
Accurately predicting corrosion inhibition efficiency (IE) remains a significant challenge in electrochemical systems because inhibitor performance depends on a complex interaction between molecular electronic structure, solution chemistry, and adsorption thermodynamics at the metal–electrolyte interface. Although machine learning (ML) models have shown strong predictive potential in corrosion studies, most existing approaches function as purely data-driven regressors and do not explicitly incorporate adsorption-based electrochemical principles. As a result, they may generate thermodynamically inconsistent predictions, particularly when applied beyond the range of the training data. In this work, a physics-informed hybrid machine learning framework is developed for adsorption-controlled corrosion systems. A Physics-Informed Neural Network (PINN) is used to incorporate the Langmuir adsorption relationship directly into the training process, ensuring monotonic consistency between surface coverage (θ), adsorption equilibrium constant (K_ads), and inhibition efficiency. To capture nonlinear interactions and multivariate effects beyond the analytical adsorption model, a Gradient Boosting Regressor (GBR) is introduced as a complementary data-driven component. The predictions from both models are then integrated using Ridge-based stacking, allowing a balanced combination of physical interpretability and statistical flexibility. The framework is trained using a composite dataset consisting of 100 experimentally reported corrosion inhibitors and 1000 physics-consistent synthetic samples generated within experimentally observed parameter ranges. Across five-fold cross-validation, the hybrid model achieves stable predictive performance with a mean test-set coefficient of determination of R² ≈ 0.90 while preserving adsorption-consistent behavior. The standalone GBR provides the highest numerical accuracy, while the PINN improves physical consistency and interpretability; the stacked model combines these advantages effectively. Overall, the results show that embedding adsorption thermodynamics within machine learning models improves predictive reliability, physical consistency, and model transparency in corrosion inhibition studies. Rather than introducing a fundamentally new algorithm, this work demonstrates a corrosion-specific integration of physics-informed learning and hybrid regression for more reliable inhibitor screening. The proposed framework provides a structured and reproducible approach for early-stage corrosion inhibitor design and can be extended to other adsorption-governed systems, including catalysis, surface protection, and electrochemical materials engineering.
Cite This Paper
Aswin Karkadakattil, "Physics-Informed Hybrid Machine Learning Framework for Adsorption-Consistent Prediction of Corrosion Inhibition Efficiency", International Journal of Engineering and Manufacturing (IJEM), Vol.16, No.3, pp.42-66, 2026. DOI:10.5815/ijem.2026.03.04
Reference
[1]Saviour, A.; Umoren, S.A.; Solomon, M.M.; Saji, V.S. Fundamentals of corrosion inhibition. In Polymeric Materials in Corrosion Inhibition, 1st ed.; Elsevier: Amsterdam, The Netherlands, 2020; pp. 103-127.
[2]Sastri, V.S. Green Corrosion Inhibitors: Theory and Practice, 1st ed.; John Wiley & Sons: Hoboken, NJ, USA, 2012; 304p. https://doi.org/10.1002/9781118015438
[3]Mazumder, M.A.J. Global impact of corrosion: Occurrence, cost and mitigation. Glob. J. Eng. Sci. 2020, 5, 1-4. https://doi.org/10.33552/GJES.2020.05.000618
[4]Chaubey, N.; Savita; Qurashi, A.; Chauhan, D.S.; Quraishi, M.A. Frontiers and advances in green and sustainable inhibitors for corrosion applications: A critical review. J. Mol. Liq. 2021, 321, 1-13. https://doi.org/10.1016/j.molliq.2020.114385
[5]Wei, H.; Heidarshenas, B.; Zhou, L.; Hussain, G.; Li, Q.; Ostrikov, K.K. Green inhibitors for steel corrosion in acidic environment: State of art. Mater. Today Sustain. 2020, 10, 100044. https://doi.org/10.1016/j.mtsust.2020.100044
[6]Sherif, E.M. The role of corrosion inhibitors in protecting metallic structures against corrosion in harsh environments. In Role of Colloidal Systems in Environmental Protection; Fanun, M., Ed.; Elsevier: Amsterdam, The Netherlands, 2014; pp. 509-526. https://doi.org/10.1016/B978-0-444-63283-8.00020-X
[7]Fink, J.K. Corrosion Inhibitors. In Petroleum Engineer's Guide to Oil Field Chemicals and Fluids, 1st ed.; Gulf Professional Publishing: Houston, TX, USA, 2021; pp. 217-252. https://doi.org/10.1016/B978-0-12-383844-5.00006-4
[8]Agarwal, P.; Landolt, D. Effect of anions on the efficiency of aromatic carboxylic acid corrosion inhibitors in near neutral media: Experimental investigation and theoretical modeling. Corros. Sci. 1998, 40, 673-691. https://doi.org/10.1016/S0010-938X(97)00170-4
[9]Popov, B.N. Corrosion inhibitors. In Corrosion Engineering, 1st ed.; Elsevier: Amsterdam, The Netherlands, 2015; pp. 581-597.https://doi.org/10.1016/B978-0-444-62722-3.00014-8
[10]Dariva, C.G.; Galio, A.F. Corrosion Inhibitors-Principles, Mechanisms and Applications. In Developments in Corrosion Protection; Aliofkhazraei, M., Ed.; Intech.: London, UK, 2016; pp. 365-379.
[11]Umoren, S.A.; Solomon, M.M. Effect of halide ions on the corrosion inhibition efficiency of different organic species-A review. J. Ind. Eng. Chem. 2015, 21, 81-100. https://doi.org/10.1016/j.jiec.2014.09.033
[12]Singh, P.; Srivastava, V.; Quraishi, M.A. Novel quinoline derivatives as green corrosion inhibitors for mild steel in acidic medium: Electrochemical, SEM, AFM, and XPS studies. J. Mol. Liq. 2016, 216, 164-173. https://doi.org/10.1016/j.molliq.2015.12.086
[13]Rani, B.E.; Basu, B.B.J. Green inhibitors for corrosion protection of metals and alloys: An overview. Int. J. Corros. 2012, 2012, 1-15. https://doi.org/10.1155/2012/380217
[14]Hou, B.; Li, X.; Ma, X.; DU, C.; Zang, D.; Zheng, M.; Xu, W.; Lu, D.; Ma, F. The cost of corrosion in China. NPJ Mater. Degrad. 2017, 1, 1-10. https://doi.org/10.1038/s41529-017-0005-2
[15]Perez, T.E. Corrosion in the oil and gas industry: An increasing challenge for materials. Jom 2013, 65, 1033-1042. https://doi.org/10.1007/s11837-013-0675-3
[16]Alrefaee, S.H.; Rhee, K.Y.; Verma, C.; Quraishi, M.A.; Ebenso, E.E. Challenges and advantages of using plant extract as inhibitors in modern corrosion inhibition systems: Recent advancements. J. Mol. Liq. 2021, 321, 114666. https://doi.org/10.1016/j.molliq.2020.114666
[17]Feng, L.; Yang, H.; Wang, F. Experimental and theoretical studies for corrosion inhibition of carbon steel by imidazoline derivative in 5% NaCl saturated Ca(OH)2 solution. Electrochim. Acta 2011, 58, 427-436. https://doi.org/10.1016/j.electacta.2011.09.063
[18]Wang, Q.; Tan, B.; Bao, H.; Xie, Y.; Mou, Y.; Li, P.; Chen, D.; Shi, Y.; Li, X.; Yang, W. Evaluation of Ficus tikoua leaves extract as an eco-friendly corrosion inhibitor for carbon steel in HCl media. Bioelectrochemistry 2019, 128, 49-55. https://doi.org/10.1016/j.bioelechem.2019.03.001
[19]Shahmoradi, A.R.; Ranjbarghanei, M.; Javidparvar, A.A.; Guo, L.; Berdimurodov, E.; Ramezanzadeh, B. Theoretical and surface/electrochemical investigations of walnut fruit green husk extract as effective inhibitor for mild-steel corrosion in 1M HCl electrolyte. J. Mol. Liq. 2021, 338, 13. https://doi.org/10.1016/j.molliq.2021.116550
[20]Machnikova, E.; Whitmire, K.H.; Hackerman, N. Corrosion inhibition of carbon steel in hydrochloric acid by furan derivatives. Electrochim. Acta 2008, 53, 6024-6032. https://doi.org/10.1016/j.electacta.2008.03.021
[21]Abd El-Lateef, H.M.; Alnajjar, A.O. Enhanced the protection capacity of poly (o-toluidine) by synergism with zinc or lanthanum additives at C-steel/HCl interface: A combined DFT, molecular dynamic simulations and experimental methods. J. Mol. Liq. 2020, 303, 112641. https://doi.org/10.1016/j.molliq.2020.112641
[22]Mahdavian, M.; Tehrani-Bagha, A.R.; Alibakhshi, E.; Ashhari, S.; Palimi, M.J.; Farashi, S.; Javadian, S.; Ektefa, F. Corrosion of mild steel in hydrochloric acid solution in the presence of two cationic gemini surfactants with and without hydroxyl substituted spacers. Corros. Sci. 2018, 137, 62-75. https://doi.org/10.1016/j.corsci.2018.03.034
[23]Jawich, M.W.; Oweimreen, G.A.; Ali, S.A. Heptadecyl-tailed mono-and bis-imidazolines: A study of the newly synthesized compounds on the inhibition of mild steel corrosion in a carbon dioxide-saturated saline medium. Corros. Sci. 2012, 65, 104-112. https://doi.org/10.1016/j.corsci.2012.08.001
[24]Ong, G.; Kasi, R.; Subramaniam, R. A review on plant extracts as natural additives in coating applications. Prog. Org. Coat. 2021, 151, 106091. https://doi.org/10.1016/j.porgcoat.2020.106091
[25]Quites, D.; Leiza, J.R.; Mantione, D.; Somers, A.; Forsyth, M.; Paulis, M. Incorporation of a Coumarate Based Corrosion Inhibitor in Waterborne Polymeric Binders for Corrosion Protection Applications. Macromol. Mater. Eng. 2021, 307, 2100772. https://doi.org/10.1002/mame.202100772
[26]Zhao, Z., Guo, L., Feng, L., Lu, H., Xu, Y., Wang, J., ... & Zou, X. (2019). Polydopamine functionalized graphene oxide nanocomposites reinforced the corrosion protection and adhesion properties of waterborne polyurethane coatings. European Polymer Journal, 120, 109249. https://doi.org/10.1016/j.eurpolymj.2019.109249
[27]Møller, V. B., Dam-Johansen, K., Frankær, S. M., & Kiil, S. (2017). Acid-resistant organic coatings for the chemical industry: a review. Journal of Coatings Technology and Research, 14(2), 279-306. https://doi.org/10.1007/s11998-016-9905-2
[28]Wilcox, G. D., & Gabe, D. R. (1993). Electrodeposited zinc alloy coatings. Corrosion science, 35(5-8), 1251-1258. https://doi.org/10.1016/0010-938X(93)90345-H
[29]Yan, W., Ong, W. K., Wu, L. Y., & Wijesinghe, S. L. (2019). Investigation of using sol-gel technology for corrosion protection coating systems incorporating colours and inhibitors. Coatings, 9(1), 52. https://doi.org/10.3390/coatings9010052
[30]Li, L., Nie, S., Li, C., Chen, X., Qiao, Y., Ma, R., ... & Cui, J. (2024). Study on cavitation erosion-corrosion behavior of CoCrFeNiMoCu0.1 high entropy alloy in 3.5 wt% NaCl solution. Ultrasonics Sonochemistry, 110, 107021. https://doi.org/10.1016/j.ultsonch.2024.107021
[31]Reclaru, L., Brooks, R. A., Zuberbühler, M., Eschler, P. Y., Constantin, F., & Tomoaia, G. (2014). Evaluation of taper joints with combined fatigue and crevice corrosion testing: Comparison to human explanted modular prostheses. Materials Science and Engineering: C, 34, 69-77. https://doi.org/10.1016/j.msec.2013.10.005
[32]Royhman, D., Pourzal, R., Hall, D., Lundberg, H. J., Wimmer, M. A., Jacobs, J., ... & Mathew, M. T. (2021). Fretting-corrosion in hip taper modular junctions: The influence of topography and pH levels-An in-vitro study. Journal of the mechanical behavior of biomedical materials, 118, 104443. https://doi.org/10.1016/j.jmbbm.2021.104443
[33]Lekbach, Y., Liu, T., Li, Y., Moradi, M., Dou, W., Xu, D., ... & Lovley, D. R. (2021). Microbial corrosion of metals: The corrosion microbiome. In Advances in microbial physiology (Vol. 78, pp. 317-390). Academic Press. https://doi.org/10.1016/bs.ampbs.2021.01.002
[34]Răuță, D. I., Matei, E., & Avramescu, S. M. (2025). Recent development of corrosion inhibitors: types, mechanisms, electrochemical behavior, efficiency, and environmental impact. Technologies, 13(3), 103. https://doi.org/10.3390/technologies13030103
[35]Olajire, A. A. (2018). Recent advances on organic coating system technologies for corrosion protection of offshore metallic structures. Journal of molecular liquids, 269, 572-606. https://doi.org/10.1016/j.molliq.2018.08.053
[36]Hayatdavoudi, H., & Rahsepar, M. (2017). A mechanistic study of the enhanced cathodic protection performance of graphene-reinforced zinc rich nanocomposite coating for corrosion protection of carbon steel substrate. Journal of Alloys and Compounds, 727, 1148-1156. https://doi.org/10.1016/j.jallcom.2017.08.250
[37]Xie, J., Zhang, J., You, Z., Liu, S., Guan, K., Wu, R., ... & Feng, J. (2021). Towards developing Mg alloys with simultaneously improved strength and corrosion resistance via RE alloying. Journal of Magnesium and Alloys, 9(1), 41-56. https://doi.org/10.1016/j.jma.2020.08.016
[38]Kadhim, A., Betti, N., Al-Adili, A., Shaker, L. M., & Al-Amiery, A. A. (2022). Limits and developments in organic inhibitors for corrosion of mild steel: a critical review (Part two: 4-aminoantipyrine). International Journal of Corrosion and Scale Inhibition, 11(1), 43-63. https://doi.org/10.17675/2305-6894-2022-11-1-2
[39]Cowley, W. E., Robinson, F. P. A., & Kerrich, J. E. (1968). Anodic Protection for the Control of Corrosion Fatigue. British Corrosion Journal, 3(5), 223-237. https://doi.org/10.1179/000705968798326028
[40]Cuomo, S., Di Cola, V. S., Giampaolo, F., Rozza, G., Raissi, M., & Piccialli, F. (2022). Scientific machine learning through physics-informed neural networks: Where we are and what's next. Journal of Scientific Computing, 92(3), 88. https://doi.org/10.1007/s10915-022-01939-z
[41]Feng, Z., Jiang, Z., & Yan, C. (2025). Prediction of corrosion lifetime of marine environment steel pipe piles based on physics-informed neural network. Discover Applied Sciences. https://doi.org/10.1007/s42452-025-08143-2
[42]Hu, Q., Zhang, Z., Wang, F., Su, Z., Zhang, Q., & Zhou, J. (2026). A Physics-Informed Neural Network Method for Predicting Maximum Pitting Corrosion Depth in Pipelines. Process Safety and Environmental Protection, 108520. https://doi.org/10.1016/j.psep.2026.108520
[43]Taotao, Z. H. O. U., Yingzheng, L. I. U., Wenpei, Z. H. E. N. G., Hengliang, J. I. A. N. G., Haipeng, L. I. U., & Gang, X. I. A. (2025). Pipeline Corrosion Prediction Method Based on Physics-informed Neural Networks. Journal of Chinese Society for Corrosion and Protection, 45(5), 1320-1330.
[44]Riyaz, N. U. S., Khaled, M., Alshami, A., & Hussein, I. A. (2025). Machine learning-driven prediction of corrosion inhibitor efficiency: Emerging algorithms, challenges, and future outlooks. Arabian Journal for +. https://doi.org/10.1007/s13369-025-10386-5
[45]Alrabghi, A. (2025). A modelling approach for asset degradation: Advancing digital twin in maintenance. Int. J. Simul. Model, 24(1), 76-86. https://doi.org/10.2507/IJSIMM24-1-715
[46]Tang, Y., Dehaghani, M. R., & Wang, G. G. (2025). Capturing Lifecycle System Degradation in Digital Twin Model Updating. arXiv preprint arXiv:2503.08953.
[47]Michopoulos, J. G., Apetre, N. A., Iliopoulos, A. P., & Steuben, J. C. (2025). On a Multiphysics Digital Twin for Aging Prediction of Adhesive Step Lap Joints. Journal of Computing and Information Science in Engineering, 25(7), 071001. https://doi.org/10.1115/1.4067988
[48]Zeng, Z. C., Xu, Y. L., Zhang, K. W., Cai, L. H., Ding, Y. H., & Tian, Y. D. (2025). A sequenced digital twin framework for performance assessment of cracked RC beams with rebar corrosion. Construction and Building Materials, 494, 143250. https://doi.org/10.1016/j.conbuildmat.2025.143250
[49]Elizabeth, I., & Barshilia, H. C. (2025). A comprehensive review on corrosion detection methods for aircraft: Moving from offline methodologies to real-time monitoring combined with digital twin technology. Engineering Science & Technology, 69-98. https://doi.org/10.37256/est.6120255638
[50]Peratta, A., Adey, R., Butchers, R., & Curtin, T. (2025, April). Digital twin and corrosion modeling techniques for atmospheric corrosion in aircraft structures. In CONFERENCE 2025 (pp. 1-14). Association for Materials Protection and Performance. https://doi.org/10.5006/C2025-00568
[51]Samimi, A. (2026). Corrosion Analysis and Mitigation Strategies: A Data-Driven Approach. Journal of Chemical Engineering and Energy Materials, 2(1), 1-14.
[52]Ohimor, E. O., Effi, M. E., Akakabota, A. O., Friday, M., Anetokhe, M. A., Gundat, J., & Umukoro, J. Combined Application of Corrosion Prediction Tools-A Review.
[53]Kohan, A., Xu, J., Xiao, L., Wu, X., Kukkar, A., Hussain, S., ... & Acharya, U. R. (2026). Human-Centered Pathways to Trustworthy AI in Healthcare: A Comparative Analysis of Explainable AI, Human-in-the-Loop, Hybrid AI, and Uncertainty Quantification Techniques. https://doi.org/10.21203/rs.3.rs-8976235/v1
[54]Chiaburu, T. C. (2026). Uncertainty in Explainable Artificial Intelligence (Doctoral dissertation, Dissertation, Berlin, Technische Universität Berlin, 2026).
[55]Löfström, H., Löfström, T., Hjort, A., & Yapicioglu, F. R. (2026). Concerning Uncertainty--A Systematic Survey of Uncertainty-Aware XAI. arXiv preprint arXiv:2603.26838.
[56]He, W., Jiang, Z., Xiao, T., Xu, Z., & Li, Y. (2026). A survey on uncertainty quantification methods for deep learning. ACM Computing Surveys, 58(7), 1-35.
[57]Yapicioglu, F. R. (2025). Uncertainty Considerations of Explainable AI in Data-Driven Systems.
[58]Schauer, A., & Schnurr, D. (2025). Fostering Trustworthy Human-AI Collaboration through Explainable AI and Uncertainty Quantification. https://doi.org/10.1257/rct.15730