Predicting the Corrosion Rate of Al and Mg Alloys Coated by Plasma Spraying Method with Machine Learning

Year 2024, , 130 - 142, 26.06.2024

Hüseyin Özkavak , Recai Fatih Tunay

https://doi.org/10.55546/jmm.1459329

Abstract

Developing technology has increased the need for materials that are more economical in terms of cost and more reliable in terms of strength, chemical and physical properties in all industrial areas. This has necessitated the development of new materials or the improvement of existing material properties. Surface coating methods are used to improve existing material properties. In this study, Al and Mg alloys, which are considered as an alternative to steel material in terms of being lightweight materials, were coated with Al2O3 and TiO2 at different rates by plasma spraying method, and the corrosion behaviors of the coatings in different environments were predicted using machine learning methods. AA7075 and AZ91 non-metal materials were chosen as the substrate for the study. Different ratios of Al2O3 and TiO2 ceramic materials were coated on the substrates. To determine the corrosion resistance of the coated samples, corrosion experiments were carried out in 3.5% NaCl and 0.3M H2SO4 environments. Using the experimental results, corrosion rate values were estimated using machine learning algorithms such as XGBoost, Random Forest (RF) and artificial neural networks (ANN) methods, depending on the substrate material, corrosive environment and coating rates. At the end of the study, corrosion rate values were estimated with low error rates and the best estimate was obtained with the XGBoost method (0.9968 R2 value).

Keywords

Coating, AZ91, AA7075, seramic materials, machine learning

Project Number

FDK-2019-7386.

Thanks

This study was supported by Süleyman Demirel University Scientific Research Projects Coordination Unit with Project number of FDK-2019-7386. The authors thank Prof. Dr. Yusuf Kayalı for their contributions to this work. This study was produced from Hüseyin Özkavak's PhD thesis.

Plazma Püskürtme Yöntemiyle Kaplanan Al ve Mg Alaşımlarının Korozyon Oranının Makine Öğrenmesi ile Tahmin Edilmesi

Abstract

Gelişen teknoloji, tüm endüstriyel alanlarda maliyet açısından daha ekonomik, mukavemet, kimyasal ve fiziksel özellikler açısından daha güvenilir malzemelere olan ihtiyacı artırmıştır. Bu durum yeni malzemelerin geliştirilmesini veya mevcut malzeme özelliklerinin iyileştirilmesini zorunlu kılmıştır. Mevcut malzeme özelliklerinin iyileştirilmesi için yüzey kaplama yöntemleri kullanılmaktadır. Bu çalışmada, hafif malzeme olması açısından çelik malzemeye alternatif olarak değerlendirilen Al ve Mg alaşımları, plazma püskürtme yöntemiyle farklı oranlarda Al2O3 ve TiO2 ile kaplanmış ve kaplamaların farklı ortamlardaki korozyon davranışları ortaya çıkarılmıştır. makine öğrenimi yöntemleri kullanılarak tahmin edilmiştir. Çalışma için alt tabaka olarak AA7075 ve AZ91 metal olmayan malzemeler seçildi. Altlık üzerine farklı oranlarda Al2O3 ve TiO2 seramik malzemeleri kaplandı. Kaplanan numunelerin korozyon direncini belirlemek için %3,5 NaCl ve 0,3M H2SO4 ortamında korozyon deneyleri yapıldı. Deneysel sonuçlar kullanılarak altlık malzemesi, korozif ortam ve kaplama oranlarına bağlı olarak XGBoost, Random Forest (RF) gibi makine öğrenme algoritmaları ve yapay sinir ağları (ANN) yöntemleri kullanılarak korozyon hızı değerleri tahmin edilmeye çalışılmıştır. Çalışma sonunda korozyon hızı değerleri düşük hata oranlarıyla tahmin edilmiş ve en iyi tahmin XGBoost yöntemiyle elde edilmiştir (0,9968 R2 değeri).

Keywords

Kaplama, AZ91, AA7075, seramik malzemeler, makine öğrenmesi

Supporting Institution

This study was supported by Süleyman Demirel University Scientific Research Projects Coordination Unit with Project number of FDK-2019-7386.

Project Number

FDK-2019-7386.

Thanks

The authors thank Prof. Dr. Yusuf Kayalı for their contributions to this work

References

• Al-Fakih, A.M., Algamal, Z.Y., Lee, M.H., Abdallah, H.H., Maarof, H., Aziz, M, Quantitative structure–activity relationship model for prediction study of corrosion inhibition efficiency using two-stage sparse multiple linear regression. Journal of Chemometrics 30, 361–368,2016.
• Altinkok, N., Koker, R., Neural network approach to prediction of bending strength and hardening behaviour of particulate rein forced (Al–Si–Mg)-aluminium matrix composites. Materials & Design 25(7), 595–602,2004.
• Aslan, A. (ICSAR’22) Akciğer Kanserinin Derin Öğrenme Yaklaşımları Kullanılarak Tespit Edilmesi. 1076-1082, 2022.
• Ashby, M.F., Bréchet, Y.J.M., Cebon, D., Salvo, L., Selection strategies for materials and processes. Material&Design 25,51-67,2004.
• Basha, M. T., Srikantha, A., Venkateshwarlua, B., A Critical Review on Nano structured Coatings for Alumina-Titania (Al2O3-TiO2) Deposited by Air Plasma Spraying Process (APS). Materials Today: Proceedings 22, 1554–1562, 2020.
• Bakhsheshi-Rad, H.R., Daroonparvar, M., Yajid, M.A.M., Kumar, P., Razzaghi, M., Ismail, A.F., Sharif, S., Berto, F., Characterization and Corrosion Behavior Evaluation of Nanostructured TiO2 and Al2O3-13 wt.% TiO2 Coatings on Aluminum Alloy Prepared via High-Velocity Oxy-Fuel Spray. Journal of Materials Engineering and Performance, 30, 1356–1370, 2021.
• Behara, S., Poonawala, T., Thomas, T., Crystal structure classification in ABO3 perovskites via machine learning. Comp. Mater. Sci., 188, 2021.
• Bilgin, M. Makine Öğrenmesi. Papatya Yayincilik, Istanbul,2018.
• Bolelli, G., Lusvarghi, L., Barletta, M., HVOF-Sprayed WC-CoCr coatings on Al alloy: Effect of the coating thickness on the tribological properties. 17th International Conference on Wear of Materials 267, 944-953,2009.
• Cameron, A.C.and Windmeijer, F. A., An R-squared measure of goodness of fit for some common nonlinear regression models. Journal of Econometrics 77, no. 2,329-342, 1997.
• Chai, T. and Draxler, R. R., Root mean square error (RMSE) or mean absolute error (MAE) ?–Arguments against avoiding RMSE in the literature. Geoscientific Model Development 7 (3), 1247-1250,2014.
• Cheng, W., Changxin, W., Yan, Z., Stoichko, A., Dezhen, X., Turab, L., Yanjing, S., Modeling solid solution strengthening in high entropy alloys using machine learning. Acta Materialia, 212, 116917,2021.
• Chern-Tong, H. and. Aziz, I. B. A., A corrosion prediction model for oil and gas pipeline using CMARPGA. 2016 3rd International Conference on Computer and Information Sciences (ICCOINS), Kuala Lumpur, Malaysia, 403-407,2016.
• Dey, S., Sultana, N., Kaiser, M.S., Dey, P., Datta, S., Computational intelligence based design of age-hardenable aluminium alloys for different temperature regimes. Materials Design 92, 522–534, 2016.
• El-Rehim, A.; Alaa, F.; Zahran, H.Y.; Habashy, D.M.; Al-Masoud, H.M., Simulation and prediction of the Vickers hardness of AZ91 magnesium alloy using artificial neural network model. Crystals 10(4), 290,2020.
• Ernst, P., Fletcher, K., SUMEBore – thermally sprayed protective coatings for cylinder liner surfaces,1–12,2011.
• Fan, J., Wang, X., Wu, L., Zhou, H., Zhang, F., Yu, X., Lu, X., Xiang, Y., Comparison of support vector machine and extreme gradient boosting for predicting daily global solar radiation using temperature and precipitation in humid subtropical climates: A case study in China. Energy Convers. Manag. 164,102–111,2018.
• Giard, B., Karlsson, S., Machine learning for the prediction of duplex stainless steel mechanical properties: hardness evolu tion under low temperature aging. Examensarbete Inom Teknik, Grundnıvå, 15 Hp Stockholm, Sverige,2021.
• Gibbons, G.J., Hansell, R.G., Down-selection and optimization of thermal-sprayed coatings for aluminum mould tool protection and upgrade. J. Thermal Spray Technology 15, 340-347,2006.
• He, S.M., Zeng X., Peng, L.M., Gao, X., Nie, J.F., Ding, W.J., Microstructure and strengthening mechanism of high strength Mg-10Gd-2Y-0.5 Zr alloy. Journal of. Alloy Compounds 427(1), 316-323, 2007.
• Han, K., Öztürk, G., Aslan, A., Yapay Sinir Ağları Kullanarak Yüzey Pürüzlülüğü Tespiti. 1st International Conference on Pioneer and Innovative Studies, Konya, Turkey June 5-7, 2023.
• Harju, M., Halme, J., Jarn, M., Rosenholm, J.B., Mantyla, T., Influence of Aqueous Aging on Surface Properties of Plasma Sprayed Oxide Coatings. Journal of Colloid Interface Science, 313(1), 194-201, 2007.
• Hou, Y., Aldrich, C., Lepkova, K., Kinsella, B., Identifying corrosion of carbon steel buried in iron ore and coal cargoes based on recurrence quantification analysis of electrochemical noise. Electrochim. Acta, 283, 212–220,2018.
• Hongyu, M., Pengfei, Q.,Yu, C., Rui, L., Peiling, K.,Fuhui, W., Li, L., Prediction of multilayer Cr/GLC coatings degradation in deep-sea environments based on integrated mechanistic and machine learning models.Corrosion Science, 224, 111513,2023.
• Islak, S., Buytoz, S. Plazma Püskürtme Yöntemiyle AISI 304 Paslanmaz Çelik Yüzeyinde Elde Edilen ZrO2/Al2O3-%13 TiO2 Kompozit Kaplamasının Mikroyapı Özellikleri. 6th International Advanced Technologies Symposium, 16-18 May, Elazığ, 6-12, 2011.
• Jia, S., Zou, Y., Xu, J., Wang, J., Yu, L., Effect of TiO2 Content on Properties of Al2O3 Thermal Barrier Coatings by Plasma Spraying. Transactions of Nonferrous Metals Society of China, 25, 175-183, 2015.
• Jian, F., Xiao, C., Huilong, G., Sidney, L., Helen, L., Development of machine learning algorithms for predicting internal corrosion of crude oil and natural gas pipelines. Computers & Chemical Engineering 177, 108358,2023.
• Kilic, A., Odabası, Ç., Yildirim, R., Eroglu, D., Assessment of critical materials and cell design factors for high performance lithium-sulfur batteries using machine learning. Chemical Engineering Journal,390,2020.
• Kojima, Y., Project of platform science and technology for advanced magnesium alloys. Materials Transactions 42,1154–1159,2001.
• Kumari, S., Tiyyagura, H.R., Douglas, T.E.L., Mohammed, E.A.A., Adriaens, A., Fuchs-Godec, R., Mohan, M.K., Skirtach, A.G., ANN prediction of corrosion behaviour of uncoated and biopolymers coated cp-Titanium substrates. Materials Design 157, 35–51, 2018.
• Kurt, A., Buldu, B., Cedimoğlu, İ.H., XGBOOST ve Rastgele Orman Algorıtmalarının Ağ Tabanlı Saldırı Tespıtıne Yönelık Performanslarının Karşılaştırılması. International Marmara Sciences Congress (Spring) Proceedings Book3,2020.
• Lei, J., Changsheng, W., Huadong, F., Jie, S., Zhihao, Z., Jianxin. X., Discovery of aluminum alloys with ultra-strength and high-toughness via a property-oriented design strategy. Journal of Materials Science & Technology 98,33-43,2022.
• Liu, J., Wang, H., Yuan, Z., Forecast model for inner corrosion rate of oil pipeline based on PSO-SVM. International Journal of Simulation Process Modelling 7, 74–80, 2012.
• Liu, R., Wang, M., Wang, H., Chi, J., Meng, F., Liu, L., Wang, F., Recognition of NiCrAlY coating based on convolutional neural network, Material. Degradation 6, 2022.
• Michalak, M., Toma, F.-L., Latka, L., Sokolowski, P., Barbosa, M.; Ambroziak, A, A Study on the Microstructural Characterization and Phase Compositions of Thermally Sprayed Al2O3-TiO2 Coatings Obtained from Powders and Water-Based Suspensions. Materials 13, 2638,2020.
• Mordike, B.L., Ebert, T., Magnesium properties-application-potential. Materials Science Engineering A, 30237–30245,2001.
• Morks, M., Akimoto, K., The Role of Nozzle Diameter on the Microstructure and Abrasion Wear Resistance of Plasma Sprayed Al2O3/TiO2 Composite Coatings. Journal of Manufacturing Processers 10, 1-5, 2008.
• Ossai, C.I., A data-driven machine learning approach for corrosion risk assessment—a comparative study. Big Data Cognitive Computer 3, 1–22,2019.
• Pei, Z., Zhang, D., Zhi, Y., Yang, T., Jin, L.Fu, D., Cheng, X.,Terryn, H.A., Mol, J.M. C., Li, X., Towards understanding and prediction of atmospheric corrosion of an Fe/Cu corrosion sensor via machine learning. Corros. Sci.,170,2020.
• Picas, J.A., Forn, T.A., Rilla, R., Martín, E., HVOF thermal sprayed coatings on aluminium alloys and aluminium matrix composites. Surface and Coating Technology 200, 1178–1181,2005.
• Ren, C.-Y., Qiao, W., Tian, X., Natural gas pipeline corrosion rate prediction model based on BP neural network, In Proceedings of the Fuzzy Engineering and Operations Research. Babolsar, Iran, 25–26 October 2012; Springer: Berlin/Heidelberg, Germany, 449–455,2012.
• Rotshtein, V.P., Yu, F.I., Proskurovsky, D.I., et al., Microstructure of the near-surface layers of austenitic stainless steels irradiated with a low-energy, high-current electron beam. Surface Coating Technology 180 ,382–386,2004.
• Shi, Z., Song, G., Atrens, A., Influence of the b phase on the corrosion performance of anodised coatings on magnesium–aluminium alloys. Corrosion Science 47,2760–2777,2005.
• Shi, Y., Fu, D., Zhou, X., Yang, T., Zhi, Y., Pei, Z., Zhang, D., Shao, L., Data mining to online galvanic current of zinc/copper Internet atmospheric corrosion monitor. Corros. Sci. ,133, 2018.
• Schmidt, J., Shi, J., Borlido, P., Chen, L., Botti, S., Marques, M.A.L., Predicting the thermodynamic stability of solids combining density functional theory and machine learning. Chem. Mater. 29, 5090–5103, 2017.
• Song, G., StJohn, D., Corrosion behaviour of magnesium in ethylene glycol, Corrosion Science 46,381–1399,2004.
• Šuopys, A., Marcinauskas, L., Kėželis, R., Aikas, M., Uscila, R., Thermal And Chemical Resistance of Plasma Sprayed Al2O3, Al2O3-TiO2 Coatings. Research Square preprint.
• Toma, F., Et, A., Corrosion Resistance of Aps and Hvof Sprayed Coatings in The Al2O3-TiO2 System. Journal of Thermal Spray Technology 19,137-147,2009.
• Toma, F., Et, A., Corrosion Resistance of Aps and Hvof Sprayed Coatings in The Al2O3-TiO2 System. Journal of Thermal Spray Technology 19, 137-147,2010.
• Tian, W., Meng, F., Liu, L., Li, Y., Wang, F., Lifetime prediction for organic coating under alternating hydrostatic pressure by artificial neural network, Sci. Rep. 7, 40827, 2017.
• URL: Morde, V., XGBoost Algorithm: Long May She Reign!, Medium , https://towardsdatascience.com/https-medium-com-vishalmorde-xgboost-algorithm-long-she-may-rein edd9f99be63d adresinden alındı.
• URL: Brownlee, J., A Gentle Introduction to XGBoost for Applied Machine Learning, 10 Haziran 2020 tarihinde https://machinelearningmastery.com/gentle-introduction-xgboost-applied-machine-learning/
• URL: Breiman, L., Cutler, A., Random Forests, 10 Haziran 2020 tarihinde Berkeley Üniversitesi: https://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm.
• Verma, P., Anwar, S., Khan, S., & Mane, S. B, Network intrusion detection using clustering and gradient boosting, In 2018 9th International Conference on Computing. Communication and Networking Technologies (ICCCNT) ,1-7,2018.
• Vel´azquez, J.C., Caleyo, F., Valor, A., Hallen, J.M., Predictive model for pitting corrosion in buried oil and gas pipelines. Corrosion 65, 332–342, 2009.
• Xinming, F., Zhilei, W., Lei, J., Fan, Z., Zhihao, Z., Simultaneous enhancement in mechanical and corrosion properties of Al-Mg-Si alloys using machine learning. Journal of Materials Science & Technology 167, 1–13,2023.
• Yan, Y., Mattisson, T., Moldenhauer, P., Anthony, E.J., Clough, P.T., Applying machine learning algorithms in estimating the perforamance of heterogeneous, multi-component materials as oxygen carriers for chemical-looping processes. Chemical Engineering Journal, 387,2020.
• Yang, B., Cao, J.-M., Jiang, D.-P., Lv, J.-D. Facial expression recognition based on dual-feature fusion and improved random forest classifier. Multimed. Tools Appl. 77, 20477–20499, 2017.
• Ya-li G., Cun-shan, W., Man, Y., Hong-bin, L., The Resistance to Wear and Corrosion of Laser-Cladding Al2O3 Ceramic Coating on Mg Alloy.Applied Surface Science 253, 5306-5311,2007.