A machine learning approach for corrosion small datasets
Source abstract
Abstract
Abstract In this work, we developed a QSAR model using the K-Nearest Neighbor (KNN) algorithm to predict the corrosion inhibition performance of the inhibitor compound. To overcome the small dataset problems, virtual samples are generated and added to the training set using a Virtual Sample Generation (VSG) method. The generalizability of the proposed KNN + VSG model is verified by using six small datasets from references and comparing their prediction performances. The research shows that for the six datasets, the proposed model is able to make predictions with the best accuracy. Adding virtual samples to the training data helps the algorithm recognize feature-target relationship patterns, and therefore increases the number of chemical quantum parameters correlated with corrosion inhibition efficiency. This proposed method strengthens the prospect of ML for developing material designs, especially in the case of small datasets.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Corrosion Behavior and Inhibition · Hydrogen embrittlement and corrosion behaviors in metals · Concrete Corrosion and Durability
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (54)
Show source-provided references
1. Finšgar, M. & Jackson, J. Application of corrosion inhibitors for steels in acidic media for the oil and gas industry: a review. Corros. Sci. 86, 17–41 (2014).10.1016/j.corsci.2014.04.044 ↗
2. Tiu, B. D. B. & Advincula, R. C. Polymeric corrosion inhibitors for the oil and gas industry: design principles and mechanism. React. Funct. Polym. 95, 25–45 (2015).10.1016/j.reactfunctpolym.2015.08.006 ↗
3. Kadhim, A. et al. Corrosion inhibitors. A review. Int. J. Corros. Scale Inhib. 10, 54–67 (2021).
4. Miralrio, A. & Vázquez, A. E. Plant extracts as green corrosion inhibitors for different metal surfaces and corrosive media: a review. Processes 8, 8 (2020).10.3390/pr8080942 ↗
5. Keshavarz, M. H. et al. Simple approach to predict corrosion inhibition efficiency of imidazole and benzimidazole derivatives as well as linear organic compounds containing several polar functional groups. Zeitschrift fur Anorg. und Allg. Chemie 642, 906–913 (2016).10.1002/zaac.201600230 ↗
6. Majd, M. T. et al. Probing molecular adsorption/interactions and anti-corrosion performance of poppy extract in acidic environments. J. Mol. Liq. 304, 112750 (2020).10.1016/j.molliq.2020.112750 ↗
7. Alrefaee, S. H. et al. Challenges and advantages of using plant extract as inhibitors in modern corrosion inhibition systems: Recent advancements. J. Mol. Liq. 321, 114666 (2021).10.1016/j.molliq.2020.114666 ↗
8. Salleh, S. Z. et al. Plant extracts as green corrosion inhibitor for ferrous metal alloys: a review. J. Clean. Prod. 304, 127030 (2021).10.1016/j.jclepro.2021.127030 ↗
9. El-Haddad, M. N. & Fouda, A. E. A. S. Evaluation of Curam drug as an ecofriendly corrosion inhibitor for protection of stainless steel-304 in hydrochloric acid solution: chemical, electrochemical, and surface morphology studies. J. Chinese Chem. Soc. 68, 826–836 (2021).10.1002/jccs.202000409 ↗
10. Farahati, R. et al. Experimental and computational study of penicillamine drug and cysteine as water-soluble green corrosion inhibitors of mild steel. Prog. Org. Coatings. 142, 105567 (2020).10.1016/j.porgcoat.2020.105567 ↗
11. Neves, B. J. et al. QSAR-based virtual screening: advances and applications in drug discovery. Front. Pharmacol. 9, 1–7 (2018).10.3389/fphar.2018.01275 ↗
12. Toropov, A. A. & Toropova, A. P. QSPR/QSAR: state-of-art, weirdness, the future. Molecules 25, 1292 (2020).10.3390/molecules25061292 ↗
13. Belghiti, M. E. et al. Computational simulation and statistical analysis on the relationship between corrosion inhibition efficiency and molecular structure of some hydrazine derivatives in phosphoric acid on mild steel surface. Appl. Surf. Sci. 491, 707–722 (2019).10.1016/j.apsusc.2019.04.125 ↗
14. Winkler, D. A. Predicting the performance of organic corrosion inhibitors. Metals 7, 1–8 (2017).10.3390/met7120553 ↗
15. Mendoza, R. L. C. et al. Density functional theory and electrochemical studies: structure-efficiency relationship on corrosion inhibition. J. Chem. Inf. Model. 55, 2391–2402 (2015).10.1021/acs.jcim.5b00385 ↗
16. Li, L. et al. The discussion of descriptors for the QSAR model and molecular dynamics simulation of benzimidazole derivatives as corrosion inhibitors. Corros. Sci. 99, 76–88 (2015).10.1016/j.corsci.2015.06.003 ↗
17. Khaled, K. F. & Al-Mobarak, N. A. A predictive model for corrosion inhibition of mild steel by thiophene and its derivatives using artificial neural network. Int. J. Electrochem. Sci. 7, 1045–1059 (2012).10.1016/S1452-3981(23)13393-1 ↗
18. Khaled, K. F. & Sherik, A. Using neural networks for corrosion inhibition efficiency prediction during corrosion of steel in chloride solutions. Int. J. Electrochem. Sci. 8, 9918–9935 (2013).10.1016/S1452-3981(23)13022-7 ↗
19. Quadri, T. W. et al. Development of QSAR-based (MLR/ANN) predictive models for effective design of pyridazine corrosion inhibitors. Mater. Today Commun. 30, 103163 (2022).10.1016/j.mtcomm.2022.103163 ↗
20. Ser, C. T. et al. Prediction of corrosion inhibition efficiency of pyridines and quinolines on an iron surface using machine learning-powered quantitative structure-property relationships. Appl. Surf. Sci. 512, 145612 (2020).10.1016/j.apsusc.2020.145612 ↗
21. Liu, Y. et al. A machine learning‑based QSAR model for benzimidazole derivatives as corrosion inhibitors by incorporating comprehensive feature selection. Interdiscip. Sci. Comput. Life Sci. 11, 738–747 (2019).10.1007/s12539-019-00346-7 ↗
22. Zhi, Y. et al. Long-term prediction on atmospheric corrosion data series of carbon steel in China based on NGBM(1,1) model and genetic algorithm. Anti-Corrosion Methods Mater 66, 403–411 (2019).10.1108/ACMM-11-2017-1858 ↗
23. De Masi, G. et al. Machine learning approach to corrosion assessment in subsea pipelines. MTS/IEEE Ocean. 2015 - Genova Discovering Sustainable Ocean Energy for a New World 8–13 (2015).10.1109/OCEANS-Genova.2015.7271592 ↗
24. Beltran-Perez, C. et al. A general use QSAR-ARX model to predict the corrosion inhibition efficiency of drugs in terms of quantum mechanical descriptors and experimental comparison for lidocaine. Int. J. Mol. Sci. 23, 5086 (2022).10.3390/ijms23095086 ↗
25. Chen, Z. S. et al. A PSO based virtual sample generation method for small sample sets: applications to regression datasets. Eng. Appl. Artif. Intell. 59, 236–243 (2017).10.1016/j.engappai.2016.12.024 ↗
26. Roy, M. A. et al. Machine-learning-guided descriptor selection for predicting corrosion resistance in multi-principal element alloys. npj Mater. Degrad. 6, 9 (2022).10.1038/s41529-021-00208-y ↗
27. Coelho, L. B. et al. Reviewing machine learning of corrosion prediction in a data-oriented perspective. npj Mater. Degrad. 6, 8 (2022).10.1038/s41529-022-00218-4 ↗
28. Chen, Z. S. et al. Integrating virtual sample generation with input-training neural network for solving small sample size problems: application to purified terephthalic acid solvent system. Soft Comput. 25, 6489–6504 (2021).10.1007/s00500-021-05641-4 ↗
29. Li, D. C. et al. A new approach for manufacturing forecast problems with insufficient data: the case of TFT-LCDs. J. Intell. Manuf. 24, 225–233 (2013).10.1007/s10845-011-0577-6 ↗
30. Luo, H. & Paal, S. G. Reducing the effect of sample bias for small data sets with double-weighted support vector transfer regression. Comput. Civ. Infrastruct. Eng. 36, 248–263 (2021).10.1111/mice.12617 ↗
31. Asanya, K. C. et al. Robust Bayesian approach to logistic regression modeling in small sample size utilizing a weakly informative student’s t prior distribution. Commun. Stat. Theory Methods. 52, 1–11 (2021).
32. Wang, X. & Yao, J. Linear regression estimation methods for inferring standard values of snow load in small sample situations. Math. Probl. Eng. 2020, 1–10 (2020).
33. Liu, Q. et al. A new support vector regression model for equipment health diagnosis with small sample data missing and its application. Shock Vib. 2021 (2021). https://doi.org/10.1155/2021/6675078.10.1155/2021/6675078 ↗
34. Liu, B. et al. Small dataset modeling and application of plant medicine extraction. Commun. Comput. Inform. Sci. 1006, 381–392 (2019).10.1007/978-981-13-7986-4_34 ↗
35. Li, D. C. et al. Using virtual samples to improve learning performance for small datasets with multimodal distributions. Soft Comput. 23, 11883–11900 (2019).10.1007/s00500-018-03744-z ↗
36. Raikwal, J. S. & Saxena, K. Performance evaluation of SVM and K-nearest neighbor algorithm over medical data set. Int. J. Comput. Appl. 50, 35–39 (2012).
37. Kumar, S. & Chong, I. Correlation analysis to identify the effective data in machine learning: Prediction of depressive disorder and emotion states. Int. J. Environ. Res. Public Health. 15, 2907 (2018).10.3390/ijerph15122907 ↗
38. Vettoretti, M. & Di Camillo, B. A variable ranking method for machine learning models with correlated features: In-silico validation and application for diabetes prediction. Appl. Sci. 11, 7740 (2021).10.3390/app11167740 ↗
39. Moedjahedy, J. et al. CCrFS: combine correlation features selection for detecting phishing websites using machine learning. Futur. Internet. 14, 229 (2022).10.3390/fi14080229 ↗
40. Ying, X. An overview of overfitting and its solutions. J. Phys. Conf. Ser. 1168, 022022 (2019).10.1088/1742-6596/1168/2/022022 ↗
41. Yan, L. et al. Corrosion rate prediction and influencing factors evaluation of low-alloy steels in marine atmosphere using machine learning approach. Sci. Technol. Adv. Mater. 21, 359–370 (2020).10.1080/14686996.2020.1746196 ↗
42. Giola, C. et al. Learning curves: a novel approach for robustness improvement of load forecasting. Eng. Proc. 5, 38 (2021).
43. Brumen, B. et al. Overview of machine learning process modelling. Entropy 23, 1123 (2021).10.3390/e23091123 ↗
44. Hassan, A. H. M. et al. Visualization & prediction of COVID-19 future outbreak by using machine learning. Int. J. Inf. Technol. Comput. Sci. 13, 16–32 (2021).
45. Song-Qing, H. et al. 3D-QSAR study and molecular design of benzimidazole derivatives as corrosion inhibitors. Chem. J. Chinese Univ. 32, 2402 (2011).
46. Kozlica, D. K. et al. Synergistic effect of 2-mercaptobenzimidazole and octylphosphonic acid as corrosion inhibitors for copper and aluminium – An electrochemical, XPS, FTIR and DFT study. Corros. Sci. 182, 109082 (2021).10.1016/j.corsci.2020.109082 ↗
47. Kokalj, A. Corrosion inhibitors: physisorbed or chemisorbed? Corros. Sci. 196, 109939 (2022).10.1016/j.corsci.2021.109939 ↗
48. Imandoust, S. B. & Bolandraftar, M. Application of K-nearest neighbor (KNN) approach for predicting economic events: theoretical background. Int. J. Eng. Res. Appl. 3, 605–610 (2013).
49. Sutojo, T. et al. Investigating the impact of synthetic data distribution on the performance of regression models to overcome small dataset problems. Proc. 2020 International Seminar on Application for Technology of Information and Communication (iSemantic). 125–130 (IEEE, 2020).10.1109/iSemantic50169.2020.9234265 ↗
50. Xu, Q. S. & Liang, Y. Z. Monte Carlo cross validation. Chemom. Intell. Lab. Syst. 56, 1–11 (2001).10.1016/S0169-7439(00)00122-2 ↗
51. Jun Lv, Y. et al. Steel corrosion prediction based on support vector machines. Chaos Solitons Fractals. 136, 109807 (2020).10.1016/j.chaos.2020.109807 ↗
52. Zhou, C. et al. A novel stacking heterogeneous ensemble model with hybrid wrapper-based feature selection for reservoir productivity predictions. Complexity 2021, 1–12 (2021).
53. Zhang, Y. et al. Data augmentation strategy for small sample short‐term load forecasting of distribution transformer. Int. Trans. Electr. Energy Syst. 30, e12209 (2019).10.1002/2050-7038.12209 ↗
54. Scikit-learn. Scikit-learn user guide - Release 0.23.2. (2020).