Investigasi Model Machine Learning Berbasis QSPR pada Inhibitor Korosi Pirimidin

Muhamad Akrom, Totok Sutojo

Sari


Karena korosi menyebabkan kerugian yang cukup besar di banyak bidang, termasuk ekonomi, lingkungan, masyarakat, industri, keamanan, dan keselamatan, hal itu menjadi perhatian utama bagi sektor industri dan akademik. Pengendalian kerusakan material berbasis senyawa organik saat ini menjadi bidang yang banyak diminati. Karena tidak beracun, terjangkau, dan efektif dalam berbagai situasi korosif, pirimidin berpotensi sebagai penghambat korosi. Dibutuhkan banyak waktu dan sumber daya untuk melakukan investigasi eksperimental dalam eksplorasi kandidat penghambat korosi potensial. Dalam studi ini, kami mengevaluasi algoritma gradient boosting regressor (GBR), support vector regression (SVR), dan k-nearest neighbor (KNN) sebagai model prediktif efisiensi inhibisi korosi menggunakan pendekatan machine learning (ML) berbasis model quantitative structure-property relationship (QSPR). Berdasarkan metrik coefficient of determination (R2) dan root mean square error (RMSE), kami menemukan bahwa model GBR memiliki performa prediksi terbaik dibandingkan model SVR dan KNN maupun model dari literatur untuk dataset senyawa pirimidin. Secara keseluruhan, penelitian kami menawarkan perspektif baru tentang kemampuan model ML untuk meramalkan penghambatan korosi pada permukaan besi.

Kata Kunci


machine learning; QSPR; corrosion; inhibition efficiency; pyrimidine

Teks Lengkap:

PDF

Referensi


Akrom, M. (2022). Investigation Of Natural Extracts As Green Corrosion Inhibitors In Steel Using Density Functional Theory. In Jurnal Teori dan Aplikasi Fisika (Vol. 10, Issue 01).

Akrom, M., Saputro, A. G., Maulana, A. L., Ramelan, A., Nuruddin, A., Rustad, S., & Dipojono, H. K. (2023). DFT and microkinetic investigation of oxygen reduction reaction on corrosion inhibition mechanism of iron surface by Syzygium Aromaticum extract. Applied Surface Science, 615. https://doi.org/10.1016/j.apsusc.2022.156319

Alamri, A. H., & Alhazmi, N. (2022). Development of data driven machine learning models for the prediction and design of pyrimidine corrosion inhibitors. Journal of Saudi Chemical Society, 26(6). https://doi.org/10.1016/j.jscs.2022.101536

Anadebe, V. C., Nnaji, P. C., Onukwuli, O. D., Okafor, N. A., Abeng, F. E., Chukwuike, V. I., Okoye, C. C., Udoh, I. I., Chidiebere, M. A., Guo, L., & Barik, R. C. (2022). Multidimensional insight into the corrosion inhibition of salbutamol drug molecule on mild steel in oilfield acidizing fluid: Experimental and computer aided modeling approach. Journal of Molecular Liquids, 349. https://doi.org/10.1016/j.molliq.2022.118482

Belghiti, M. E., Echihi, S., Dafali, A., Karzazi, Y., Bakasse, M., Elalaoui-Elabdallaoui, H., Olasunkanmi, L. O., Ebenso, E. E., & Tabyaoui, M. (2019). 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. Applied Surface Science, 491, 707–722. https://doi.org/10.1016/J.APSUSC.2019.04.125

Beltran-Perez, C., Serrano, A. A. A., Solís-Rosas, G., Martínez-Jiménez, A., Orozco-Cruz, R., Espinoza-Vázquez, A., & Miralrio, A. (2022). 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. International Journal of Molecular Sciences, 23(9). https://doi.org/10.3390/ijms23095086

Camacho-Mendoza, R. L., Feria, L., Zárate-Hernández, L. Á., Alvarado-Rodríguez, J. G., & Cruz-Borbolla, J. (2022). New QSPR model for prediction of corrosion inhibition using conceptual density functional theory. Journal of Molecular Modeling, 28(8). https://doi.org/10.1007/s00894-022-05240-6

El Assiri, E. H., Driouch, M., Lazrak, J., Bensouda, Z., Elhaloui, A., Sfaira, M., Saffaj, T., & Taleb, M. (2020). Development and validation of QSPR models for corrosion inhibition of carbon steel by some pyridazine derivatives in acidic medium. Heliyon, 6(10). https://doi.org/10.1016/j.heliyon.2020.e05067

Haladu, S. A., Dalhat Mu’azu, N., Ali, S. A., Elsharif, A. M., Odewunmi, N. A., & Abd El-Lateef, H. M. (2022). Inhibition of mild steel corrosion in 1 M H2SO4 by a gemini surfactant 1,6-hexyldiyl-bis-(dimethyldodecylammonium bromide): ANN, RSM predictive modeling, quantum chemical and MD simulation studies. Journal of Molecular Liquids, 350, 118533. https://doi.org/10.1016/J.MOLLIQ.2022.118533

Kokalj, A. (2022). Corrosion inhibitors: physisorbed or chemisorbed? Corrosion Science, 196, 109939. https://doi.org/10.1016/J.CORSCI.2021.109939

Kozlica, D. K., Kokalj, A., & Milošev, I. (2021). Synergistic effect of 2-mercaptobenzimidazole and octylphosphonic acid as corrosion inhibitors for copper and aluminium – An electrochemical, XPS, FTIR and DFT study. Corrosion Science, 182, 109082. https://doi.org/10.1016/J.CORSCI.2020.109082

Kumar, D., Jain, V., & Rai, B. (2022). Capturing the synergistic effects between corrosion inhibitor molecules using density functional theory and ReaxFF simulations - A case for benzyl azide and butyn-1-ol on Cu surface. Corrosion Science, 195. https://doi.org/10.1016/j.corsci.2021.109960

Li, L., Zhang, X., Gong, S., Zhao, H., Bai, Y., Li, Q., & Ji, L. (2015). The discussion of descriptors for the QSAR model and molecular dynamics simulation of benzimidazole derivatives as corrosion inhibitors. Corrosion Science, 99, 76–88. https://doi.org/10.1016/j.corsci.2015.06.003

Quadri, T. W., Olasunkanmi, L. O., Akpan, E. D., Fayemi, O. E., Lee, H. S., Lgaz, H., Verma, C., Guo, L., Kaya, S., & Ebenso, E. E. (2022). Development of QSAR-based (MLR/ANN) predictive models for effective design of pyridazine corrosion inhibitors. Materials Today Communications, 30. https://doi.org/10.1016/j.mtcomm.2022.103163

Quadri, T. W., Olasunkanmi, L. O., Fayemi, O. E., Akpan, E. D., Lee, H. S., Lgaz, H., Verma, C., Guo, L., Kaya, S., & Ebenso, E. E. (2022). Multilayer perceptron neural network-based QSAR models for the assessment and prediction of corrosion inhibition performances of ionic liquids. Computational Materials Science, 214. https://doi.org/10.1016/j.commatsci.2022.111753

Quadri, T. W., Olasunkanmi, L. O., Fayemi, O. E., Lgaz, H., Dagdag, O., Sherif, E. S. M., Akpan, E. D., Lee, H. S., & Ebenso, E. E. (2022). Predicting protection capacities of pyrimidine-based corrosion inhibitors for mild steel/HCl interface using linear and nonlinear QSPR models. Journal of Molecular Modeling, 28(9). https://doi.org/10.1007/s00894-022-05245-1

Quadri, T. W., Olasunkanmi, L. O., Fayemi, O. E., Lgaz, H., Dagdag, O., Sherif, E. S. M., Alrashdi, A. A., Akpan, E. D., Lee, H. S., & Ebenso, E. E. (2022). Computational insights into quinoxaline-based corrosion inhibitors of steel in HCl: Quantum chemical analysis and QSPR-ANN studies. Arabian Journal of Chemistry, 15(7). https://doi.org/10.1016/j.arabjc.2022.103870

Ser, C. T., Žuvela, P., & Wong, M. W. (2020). Prediction of corrosion inhibition efficiency of pyridines and quinolines on an iron surface using machine learning-powered quantitative structure-property relationships. Applied Surface Science, 512, 145612. https://doi.org/10.1016/J.APSUSC.2020.145612

Sutojo, T., Rustad, S., Akrom, M., Syukur, A., Shidik, G. F., & Dipojono, H. K. (2023). A machine learning approach for corrosion small datasets. Npj Materials Degradation, 7(1). https://doi.org/10.1038/s41529-023-00336-7

Thakur, A., Kaya, S., Abousalem, A. S., & Kumar, A. (2022). Experimental, DFT and MC simulation analysis of Vicia Sativa weed aerial extract as sustainable and eco-benign corrosion inhibitor for mild steel in acidic environment. Sustainable Chemistry and Pharmacy, 29. https://doi.org/10.1016/j.scp.2022.100785




DOI: https://doi.org/10.31315/e.v20i2.9864

Refbacks

  • Saat ini tidak ada refbacks.

##plugins.generic.alm.title##

##plugins.generic.alm.loading##

Metrics powered by PLOS ALM


Eksergi ISSN-p  1410-394X, ISSN-e 2460-8203 diterbitkan oleh Prodi Teknik Kimia Universitas Pembangunan Nasional "Veteran" Yogyakarta.

Sekretariat: Prodi Teknik Kimia UPN "Veteran" Yogyakarta Jl. SWK 104 (Lingkar Utara) Condong catur Sleman Yogyakarta 55283

Creative Commons License


Eksergi by http://jurnal.upnyk.ac.id/index.php/eksergi/index/ is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Jumlah Pengunjung:

  web stats

View My Stats