Prediction of Wear Properties of Experimental Produced Porcelain Ceramics Using Artificial Neural Networks (ANN)

Yıl 2023, Cilt: 1 Sayı: 2, 66 - 74, 31.12.2023

Ahmet Gürkan Yüksek , Tahsin Boyraz , Ahmet Akkuş

Öz

In this study, the production and wear properties of porcelain ceramics produced by powder metallurgy method were examined and modelling with artificial neural networks was studied using the experimental data obtained. Porcelain ceramics were prepared by the powder metallurgy route. Mixtures prepared by mechanical alloying method in alumina ball mills were produced by sintering under normal atmospheric conditions after being shaped in a dry press. After drying, the powders were compressed by uniaxial pressing at 200 MPa. The green compacts were sintered at 1100-1200 oC for 1-5 h in air. Then, characterization studies of the sintered samples were carried out and the wear experimental results obtained were converted into data suitable for modelling with artificial neural networks. In the continuation of the study, experimental wear results using artificial neural networks were analysed and modelled. Wear load, wear time, sintering temperature and sintering time were used as artificial neural networks input variables. Wear values were taken as output variables of artificial neural networks. An artificial neural network was established for the prediction of wear properties of porcelain ceramic composites. As a result, the training results and test results were compared with the actual values to control the network performance. A good agreement was observed between the experimental and artificial neural networks model results. After the artificial neural networks estimation, confirmation tests were performed to confirm the experimental results.

Anahtar Kelimeler

Ceramic, Porselen, Wear, Artificial Neural Networks

Deneysel Olarak Üretilen Porselen Seramiklerin Aşınma Özelliklerinin Yapay Sinir Ağları (YSA) Kullanılarak Tahmin Edilmesi

Öz

Bu çalışmada toz metalurjisi yöntemi ile üretilen porselen seramiklerin üretim ve aşınma özellikleri incelenmiş ve elde edilen deneysel veriler kullanılarak yapay sinir ağları ile modelleme çalışması yapılmıştır. Porselen seramikler toz metalurjisi yöntemi ile hazırlanmıştır. Alümina bilyalı değirmenlerde mekanik alaşımlama yöntemi ile hazırlanan karışımlar kuru preste şekillendirildikten sonra normal atmosferik koşullarda sinterlenerek üretilmiştir. Kurutulduktan sonra tozlar 200 MPa'da tek eksenli presleme ile sıkıştırılmıştır. Yeşil kompaktlar 1100-1200 oC'de 1-5 saat süreyle havada sinterlenmiştir. Ardından sinterlenen numunelerin karakterizasyon çalışmaları gerçekleştirilmiş ve elde edilen aşınma deneysel sonuçları yapay sinir ağları ile modellemeye uygun verilere dönüştürülmüştür. Çalışmanın devamında yapay sinir ağları kullanılarak deneysel aşınma sonuçları analiz edilmiş ve modellenmiştir. Yapay sinir ağları giriş değişkenleri olarak aşınma yükü, aşınma süresi, sinterleme sıcaklığı ve sinterleme süresi kullanılmıştır. Aşınma değerleri yapay sinir ağlarının çıkış değişkenleri olarak alınmıştır. Porselen seramik kompozitlerin aşınma özelliklerinin tahmini için bir yapay sinir ağı kurulmuştur. Sonuç olarak, ağ performansını kontrol etmek için eğitim sonuçları ve test sonuçları gerçek değerlerle karşılaştırılmıştır. Deneysel ve yapay sinir ağları model sonuçları arasında iyi bir uyum gözlenmiştir. Yapay sinir ağları tahmininden sonra, deneysel sonuçları doğrulamak için doğrulama testleri yapılmıştır.

Anahtar Kelimeler

Porselen, Aşınma, Yapay Sinir Ağları, seramik

Kaynakça

• [1] T. Boyraz and A. Akkuş, Investigation of wear properties of mullite and aluminium titanate added porcelain ceramics, Journal of Ceramic Processing Research, 2021, 22(2), 226-231.
• [2] Ahmet Akkuş and Tahsin Boyraz, ‘Fabrication and characterization of aluminium titanate and mullite added Porcelain ceramics’, J. Ceram. Proc. Res., 20[1] (2019) 54~58.
• [3] O. Turkmen, A. Kucuk, S. Akpinar, ‘’Effect of wollastonite addition on sintering of hard porcelain’’, Ceram. Inter. 41[4] (2015) 5505–5512.
• [4] M.Saclı, U. Onen, T. Boyraz, ‘’Microstructural Characterization and Thermal Properties of Aluminium Titanate / Porcelain Ceramic Matrix Composites’’, Acta Physica Polonica A, 127[4] (2015) 1133-1135.
• [5] S. Kitouni, A. Harabi, ‘’ Sintering and mechanical properties of porcelains prepared from algerian raw materials’’, Cerâmica, 57 (2011) 453-460.
• [6] S.Y.R. Lopez, J.S. Rodriguez, S.S. Sueyoshi, ‘’Determination of the activation energy for densification of porcelain stoneware’’, J. Ceram. Process. Res. 12 [3] (2011) 228–232.
• [7] J. Martin-Marquez, J.M.a. Rincon, M. Romero, ‘’Effect of firing temperature on sintering of porcelain stoneware tiles’’, Ceram. Int., 34 (2008) 1867–1873.
• [8] J. Martin-Marquez, A.G. De la Torre, M.A.G. Aranda, J.M.a. Rincon, M. Romero, ‘’Evolution with temperature of crystalline and amorphous phases in porcelain stoneware’’, J. Am. Ceram. Soc. 92 (2009) 229–234.
• [9] Y. Iqbal, E.J. Lee, ‘’Microstructural evolution in triaxial porcelain’’, J. Am. Ceram. Soc. 83 (2000) 3121–3127.
• [10] Ahmet Akkuş and Tahsin Boyraz, ‘’Investigation of wear properties of CaO, MgO added stabilized zirconia ceramics produced by different pressing methods’’, J. Ceram. Proc. Res., 19[3] (2018) 249~252.
• [11] D. H.Buckley, K.Miyoshi, ‘’Friction and wear of ceramics’’ , Wear, 100[1–3](1984)333-353.
• [12] Y. Kong, Z. Yang, G. Zhang, Q. Yuan, ‘’Friction and wear characteristics of mullite, ZTM and TZP ceramics’’, Wear 218 (1998)159-166.
• [13] C. Baudín, AA. Tricoteaux, H. Joire, ‘’Improved resistance of alumina to mild wear by aluminium titanate additions’’, J. Eur. Ceram. Soc., 34 (2014) 69–80.
• [14] H.Y. Yu, Z.B. Cai, P.D. Ren, M.H. Zhu, Z.R. Zhou, ‘’Friction and wear behavior of dental feldspathic porcelain’’, Wear, 261 (2006) 611–621.
• [15] S. Bueno, L. Micele, C. Melandri, C. Baudin, G. De Portu, ‘’Improved wear behaviour of alumina–aluminium titanate laminates with low residual stresses and large grained interfaces’’, J. Eur. Ceram. Soc., 31 (2011) 475–483.
• [16] S. Taktak, M.S. Baspinar, ‘’Wear and friction behaviour of alumina/mullite composite by sol–gel infiltration technique’’, Materials and Design, 26 (2005) 459–464.
• [17] H.H. Luo, F.C. Zhang, S.G. Roberts, ‘’Wear resistance of reaction sintered alumina/mullite composites’’, Materials Science and Engineering A, 478 (2008) 270–275.
• [18] Öztürk, Ç., Akpınar, S. & Tığ, M. Effect of calcined colemanite addition on properties of porcelain tile. J Aust Ceram Soc 58, 321–331 (2022).
• [19] Serragdj, I., Harabi, A., Kasrani, S. et al. Effect of ZrO2 additions on densification and mechanical properties of modified resistant porcelains using economic raw materials. J Aust Ceram Soc 55, 489–499 (2019).
• [20] Aydin, T., Bican, O. & Gümrük, R. Investigation of wear resistance of the porcelain tile bodies by solid particle impingement using alumina particles. J Aust Ceram Soc 56, 525–531 (2020).
• [21] M. Madhiarasan and M. Louzazni, Analysis of Artificial Neural Network: Architecture, Types, and Forecasting Applications, Journal of Electrical and Computer Engineering, 2022, V.2022, ID 5416722.
• [22] Shekhawat, P. Agarwal, A. Singh, A. Patnaik, Prediction of thermal and thermo-mechanical behavior of nano-zirconia reinforced aluminium matrix composites, Materialwissenschaft und Werkstofftechnik (Materials Science and Engineering Technology), 53 (2022) 1216–1228.
• [23] Haykin, S. (1994) Neural Networks: A Comprehensive Foundation. Macmillan Publishing, New York.
• [24] M. Hassan, A. Alrashdan, M. T. Hayajneh, A. T. Mayyas, Prediction of density, porosity and hardness in aluminium–copper-based composite materials using ANN, Journal of Materials Processing Technology, 209/2 (2009) 894–899.
• [25] L. V. Fausett, Fundamentals of neural networks: architectures, algorithms and applications, Englewood Cliffs, NJ: Prentice-Hall, 1994.
• [26] J. D. Kelleher, B. Mac Namee, ve A. D’Arcy, Fundamentals of machine learning for predictive data analytics: algorithms, worked examples, and case studies. Cambridge, Massachusetts: The MIT Press, 2015.
• [27] E. Guresen ve G. Kayakutlu, Definition of artificial neural networks with comparison to other networks, Procedia Comput. Sci., 3 (2011) 426-433.
• [28] L. Breiman, Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author), Stat. Sci., 16/3 (2001).
• [29] A. Ramanathan, L. L. Pullum, F. Hussain, D. Chakrabarty, ve S. Kumar Jha, “Integrating Symbolic and Statistical Methods for Testing Intelligent Systems Applications to Machine Learning and Computer Vision”, içinde Proceedings of the 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE), Research Publishing Services, (2016) 786-791.
• [30] A. G. Yuksek, E. T., Senadim S. Elagoz, Modeling of reflectance properties of ZnO film using artificial neural networks, Journal of optoelectronics and advanced materials, 17/11-12(2015) 1615-1628.
• [31] R. Pramod, G. B. V. Kumar, P. S. S. Gouda, A.T. Mathew, A Study on the Al2O3 reinforced Al7075 Metal Matrix Composites Wear behavior using Artificial Neural Networks, Materials Today: Proceedings. 5 (2018) 11376–11385.
• [32] C.Z. Huang, L. Zhang, L. He, J. Sun, B. Fang, B.Zou, Z.Q.Li, X. Ai, A study on the prediction of the mechanical properties of a ceramic tool based on an artificial neural network, Journal of Materials Processing Technology, 2002, V.129/1–3(2002) 399-402.
• [33] M. Kubat, Neural networks: a comprehensive foundation by Simon Haykin, Macmillan, 1994, ISBN 0-02-352781-7., Knowl. Eng. Rev., 13 (1999) 409-412.
• [34] F. B. Fitch, Warren S. McCulloch and Walter Pitts. A logical calculus of the ideas immanent in nervous activity. Bulletin of mathematical biophysics, 5 (1943)115–133.”, J. Symb. Log., 9/ 2, 49-50, 1944.
• [35] L. V. Fausett, Fundamentals of neural networks: architectures, algorithms, and applications. Englewood Cliffs, NJ: Prentice-Hall, 1994.
• [36] K. Gurney, An Introduction to Neural Networks, CRC Press, 2018.
• [37] D. E. Rumelhart, G. E. Hinton, ve R. J. Williams, Learning representations by back-propagating errors, Nature, 323/6088, 533-536, 1986.
• [38] D. Graupe, Principles of Artificial Neural Networks, 2. bs, c. 6. içinde Advanced Series in Circuits and Systems, vol. 6. WORLD SCIENTIFIC, 2007.
• [39] X. Hu, DB-HReduction: A data preprocessing algorithm for data mining applications, Appl. Math. Lett., c. 16, sy 6, ss. 889-895, Ağu. 2003,
• [40] J. M. González-Sopeña, V. Pakrashi, ve B. Ghosh, An overview of performance evaluation metrics for short-term statistical wind power forecasting, Renew. Sustain. Energy Rev., 138, 110515, 2021,