Makine Öğrenmesi Kullanarak Krom Kaplama Örtme Gücünün Tahmin Edilmesi

Yıl 2021, Cilt: 33 Sayı: 2, 709 - 719, 15.09.2021

Ramazan Katırcı , Hidayet Takcı

https://doi.org/10.35234/fumbd.950667

Cited By: 1

Öz

Krom kaplama, malzemelerin fiziksel özelliklerini ve korozyon dayanımını iyileştirmek için tüm dünyada yaygın olarak kullanılmaktadır. Bu çalışmada krom kaplamanın örtme gücünü tahmin etmek ve örtme gücüne etki eden öznitelikleri belirlemek için makine öğrenmesi algoritmaları kullanılmıştır. Bu amaçla GP (Gaussian Process), KNN (K-Nearest Neighbors), RF (Random Forest), SVR (Support Vector Regressor) ve XGB (eXtreme Gradient Boosting) algoritmaları seçilmiş ve bu algoritmaların hiper-parametreleri optimize edilmiştir. En yüksek R2 ve en düşük MSE değerlerini veren şartlar belirlenmiştir. Çapraz doğrulama için LOO (Leave One Out) metodu kullanılmıştır. En iyi sonuç SVR metodu ile elde edilmiştir. R2, MSE ve MAPE değeri sırasıyla 0,80, 0,26 ve 18.29 dur. Kaplamanın örtme gücüne etki eden en önemli iki öznitelik borik asit ve A kimyasalıdır. Bu kimyasalların yüksek seviyeleri kaplamanın örtme gücünü artırmıştır. Tüm algoritmaların hiper-parametreleri ızgara tarama yöntemi ile 2 veya daha fazla seviyede optimize edilmiştir. SVR metodunda en etkin iki hiper-parametre kernel ve C parametresidir. Kernel ve C hiper-parametreleri sırasıyla “rbf” ve 1 olduğu durumda en yüksek R2 değeri elde edilmiştir. Bu çalışma makine öğrenmesi algoritmalarını elektrokaplama sahasına uygulayan ilk çalışmalardandır. Bu yönüyle öncü olma niteliği taşımaktadır.

Anahtar Kelimeler

Makine öğrenmesi, Cr(III) Elektrokaplama, Destek Vektör Regresyonu (SVR), Rassal Orman (RF), K-En Yakın Komşu Algoritması (KNN)

Kaynakça

• Chen, T., & Guestrin, C. (2016). XGBoost. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785
• Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297. https://doi.org/10.1007/BF00994018
• Feng, Z., Liu, A., Ren, L., Zhang, J., Yang, P., & An, M. (2016). Computational Chemistry and Electrochemical Mechanism Studies of Auxiliary Complexing Agents Used for Zn-Ni Electroplating in the 5-5’-Diethylhydantoin Electrolyte. Journal of The Electrochemical Society, 163(14), D764–D773. https://doi.org/10.1149/2.0591614jes
• Handy, S. L., Oduoza, C. F., & Pearson, T. (2006). Theoretical aspects of electrodeposition of decorative chromium from trivalent electrolytes and corrosion rate study of different nickel/chromium coatings. Transactions of the Institute of Metal Finishing, 84(6), 300–308. https://doi.org/10.1179/174591906X162946
• He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016-Decem, 770–778. https://doi.org/10.1109/CVPR.2016.90
• Holland, C. W., & Cravens, D. W. (1973). Fractional Factorial Experimental Designs in Marketing Research. Journal of Marketing Research, 10(3), 270. https://doi.org/10.2307/3149694
• Katirci, R., Aktas, H., & Zontul, M. (2021). The prediction of the ZnNi thickness and Ni % of ZnNi alloy electroplating using a machine learning method. Transactions of the Institute of Metal Finishing, 99(3), 162–168. https://doi.org/10.1080/00202967.2021.1898183
• Katırcı, R. (2016). A chrome coating from a trivalent chromium bath containing extremely low concentration of Cr<SUP align="right">3+</SUP> ions. International Journal of Surface Science and Engineering, 10(1), 73. https://doi.org/10.1504/IJSURFSE.2016.075318
• Katırcı, R., Sezer, E., & Ustamehmetoğlu, B. (2015). Statistical optimisation of organic additives for maximum brightness and brightener analysis in a nickel electroplating bath. Transactions of the IMF, 93(2), 89–96. https://doi.org/10.1179/0020296714Z.000000000219
• Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84–90. https://doi.org/10.1145/3065386
• Lee, J.-Y., Kim, M., & Kwon, S.-C. (2009). Effect of polyethylene glycol on electrochemically deposited trivalent chromium layers. Transactions of Nonferrous Metals Society of China, 19(4), 819–823. https://doi.org/10.1016/S1003-6326(08)60357-X
• Lenz, B., Hasselbruch, H., Großmann, H., & Mehner, A. (2020). Application of CNN networks for an automatic determination of critical loads in scratch tests on a-C:H:W coatings. Surface and Coatings Technology, 393(February), 125764. https://doi.org/10.1016/j.surfcoat.2020.125764
• Muralidhara, H. B., & Arthoba Naik, Y. (2008). Electrochemical deposition of nanocrystalline zinc on steel substrate from acid zincate bath. Surface and Coatings Technology, 202(14), 3403–3412. https://doi.org/10.1016/j.surfcoat.2007.12.012
• Pavlov, Y. L. (2019). Random forests. Random Forests, 1–122. https://doi.org/10.1201/9780429469275-8
• Peterson, L. (2009). K-nearest neighbor. Scholarpedia, 4(2), 1883. https://doi.org/10.4249/scholarpedia.1883
• Rasmussen, C. E., & Williams, C. K. I. (2005). Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning). The MIT Press.
• Ren, X., Song, Y., Liu, A., Zhang, J., Yuan, G., Yang, P., Zhang, J., An, M., Matera, D., & Wu, G. (2015). Computational Chemistry and Electrochemical Studies of Adsorption Behavior of Organic Additives during Gold Deposition in Cyanide-free Electrolytes. Electrochimica Acta, 176, 10–17. https://doi.org/10.1016/j.electacta.2015.06.147
• Sasaki, K., Kabushiki, G. C., Abstracts, C., & Waddell, P. E. E. (1976). United States Patent [ 191. 1985, 575–585.
• Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, 1–14.
• Surviliene, S., Nivinskiene, O., Češuniene, A., & Selskis, A. (2006). Effect of Cr(III) solution chemistry on electrodeposition of chromium. Journal of Applied Electrochemistry, 36(6), 649–654. https://doi.org/10.1007/s10800-005-9105-8
• Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the Inception Architecture for Computer Vision. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016-Decem, 2818–2826. https://doi.org/10.1109/CVPR.2016.308
• Webb, G. I., Sammut, C., Perlich, C., Horváth, T., Wrobel, S., Korb, K. B., Noble, W. S., Leslie, C., Lagoudakis, M. G., Quadrianto, N., Buntine, W. L., Quadrianto, N., Buntine, W. L., Getoor, L., Namata, G., Getoor, L., Han, Xin Jin, J., Ting, J.-A., Vijayakumar, S., … Raedt, L. De. (2011). Leave-One-Out Cross-Validation. In Encyclopedia of Machine Learning (pp. 600–601). Springer US. https://doi.org/10.1007/978-0-387-30164-8_469
• Zeng, Z., Sun, Y., & Zhang, J. (2009). The electrochemical reduction mechanism of trivalent chromium in the presence of formic acid. Electrochemistry Communications, 11(2), 331–334. https://doi.org/10.1016/J.ELECOM.2008.11.055
• Zhu, J., Wang, X., Kou, L., Zheng, L., & Zhang, H. (2020). Prediction of control parameters corresponding to in-flight particles in atmospheric plasma spray employing convolutional neural networks. Surface and Coatings Technology, 394(May), 125862. https://doi.org/10.1016/j.surfcoat.2020.125862