ANFİS Model ile Mg Alaşımlarının Sıkıştırılabilirliğinin Tahminleme Performasının İncelenmesi

Yıl 2022, , 1469 - 1482, 28.12.2022

Demet Zalaoğlu , Pinar Karakus

https://doi.org/10.35414/akufemubid.1099381

Öz

Bu çalışmada, farklı Zn (ağırlıkça %5 ve 10 Zn) oranlarına sahip Mg alaşımlarına ait toz karışımları hazırlanmış ve farklı sıkıştırma basınçlarında sıkıştırılarak hesaplanan ham yoğunluklar ile ANFİS model için test ve eğitim verileri elde edilmiştir. Elde edilen test ve eğitim verileri, Matlab programında ANFİS ile eğitilmiş ve sonuçlar incelenmiştir. Yapılan eğitimlerde, ANFİS model de giriş üyelik fonksiyon tipi olarak trimf, üyelik fonksiyonu sayıları olarak ise 2 2, 3 3, 4 4, 5 5 kullanılmış, çıkış üyelik fonksiyonu constant olarak seçilmiştir. MAPE, MSE, RMSE göre seçilen üyelik fonksiyonlarının tahminleme performansları karşılaştırılmıştır. Elde edilene sonuçlar, ANFİS modelinin Mg-Zn toz karışımlarının sıkıştırılabilirliğinde kullanılabilirliğini göstermiştir.

Anahtar Kelimeler

ANFİS, Toz Metalurjisi, Mg Alaşımı, Sıkıştırılabilirlik

Investigation of Prediction Performance of Compressibility of Mg Alloys with ANFIS Model

Öz

In this study, powder mixtures of Mg alloys with different Zn (5% and 10% by weight) ratios are attained, and the test and training data for the ANFIS model with the aid of the raw densities, which is calculated by compressing at different compression pressures, are determined. The test and training data obtained is handled with ANFIS in the Matlab program, and the results are analyzed. In the pieces of training performed, trimf is selected as the input membership function type, 2 2, 3 3, 4 4, 5 5 is selected as the membership function numbers, and the output membership function is selected as constant in the ANFIS model. The estimation performances of the membership functions chosen regarding MAPE, MSE, and RMSE are checked. The results obtained showed the usability of the ANFIS model in the compressibility of Mg-Zn powder mixtures.

Anahtar Kelimeler

ANFIS, Powder Metallurgy, Mg Alloy, Compressibility

Kaynakça

• Basmaci, G., 2018. Optimization of machining parameters for the turning process of AISI 316 L stainless steel and Taguchi design. Acta Physica Polonica A, 134, 1, 260- 264.
• Bouvard, D., 2000. Densification behaviour of mixtures of hard and soft powders under pressure. Powder technology, 111, 3, 231-239.
• Brondino, N. C. M. and Silva, A., 1999. Combining artificial neural networks and GIS for land valuation purposes. Proceedings of the Computers in Urban Planning and Urban Management, India, 10.
• Buyukbingol, E. et al., 2007. Adaptive neuro-fuzzy inference system (ANFIS): a new approach to predictive modeling in QSAR applications: a study of neuro-fuzzy modeling of PCP-based NMDA receptor antagonists. Bioorganic & medicinal chemistry, 15, 12, 4265-4282.
• Caner, M. and Akarslan, E., 2009. Mermer Kesme İşleminde Spesifik Enerji Faktörünün ANFIS ve YSA Yöntemleri ile Tahmini. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 15, 2, 221-226.
• Chatfield, C., (2000). Time-series forecasting, Chapman and Hall/CRC.
• Chen, X. et al., 2015. Microstructure, electromagnetic shielding effectiveness and mechanical properties of Mg–Zn–Cu–Zr alloys. Materials Science and Engineering: B, 197,67-74.
• Çelik, E. and Kıvak, T., 2016. 17-4 PH Paslanmaz çeliğin tornalanmasinda minimum miktarda yağlamanin yüzey pürüzlülüğü üzerindeki etkileri. 7th International Symposium On Machining,İstanbul.214- 221.
• Demirel, O. et al., 2010. Electric energy load forecasting using ANFIS and ARMA methods. Journal of the Faculty of Engineering and Architecture of Gazi University, 25, 3.
• Denny, P., 2002. Compaction equations: a comparison of the Heckel and Kawakita equations. Powder technology, 127, 2, 162-172.
• Erdirencelebi, D. and Yalpir, S., 2011. Adaptive network fuzzy inference system modeling for the input selection and prediction of anaerobic digestion effluent quality. Applied mathematical modelling, 35, 8, 3821-3832.
• Ergül, E. and Kurt, H., 2021. Al Matrisli Kompozitlere ANFIS, ANN ve Taguchi Yaklaşımları Uygulanarak Özelliklerin Karşılaştırılması. International Journal of Engineering Research and Development, 13, 2, 406- 416.
• Gaitonde, V. et al., 2008. Taguchi approach for achieving better machinability in unreinforced and reinforced polyamides. Journal of Reinforced Plastics and Composites, 27, 9, 909-924.
• German, R. M., 2007. Toz metalurjisi ve parçacıklı malzeme işlemleri. Çeviri Editörleri, Sarıtaş, S., Türker, M., Durlu N., Türk Toz Metalurjisi Derneği Yayınları, Ankara,60-80.
• Ghofrani, M. and Alolayan, M., (2018). Time series and renewable energy forecasting, IntechOpen.
• Ghose, J. et al., 2011. Taguchi-fuzzy based mapping of EDM-machinability of aluminium foam. Technical Gazette, 18, 4, 595-600.
• Gujarati, D. N., (2021). Essentials of econometrics, SAGE Publications.
• Gupta, M. and Ling, S. N. M., (2011). Magnesium, magnesium alloys, and magnesium composites, John Wiley & Sons.
• Hafizpour, H. et al., 2009. Analysis of the effect of reinforcement particles on the compressibility of Al–SiC composite powders using a neural network model. Materials & Design, 30, 5, 1518-1523.
• Haznedar, B. et al., 2017. Karaciğer mikrodizi kanser verisinin sınıflandırılması için genetik algoritma kullanarak ANFIS’in eğitilmesi. Sakarya Üniversitesi Fen bilimleri Enstitüsü Dergisi, 10.
• Hossain, M. S. J. and Ahmad, N., 2014. A neuro-fuzzy approach to select cutting parameters for commercial die manufacturing. Procedia Engineering, 90,753-759.
• Jang, J. S. and Sun, C.-T., 1995. Neuro-fuzzy modeling and control. Proceedings of the IEEE, 83, 3, 378-406. Jang, J. S. R., 1993. Anfis - Adaptive-Network-Based Fuzzy Inference System. Ieee Transactions on Systems Man and Cybernetics, 23, 3, 665-685.
• Jang, J. S. R. et al., 1997. Neuro-fuzzy and soft computinga computational approach to learning and machine intelligence [Book Review]. IEEE Transactions on automatic control, 42, 10, 1482-1484.
• Jeyaprakash, N. et al., 2020. Machinability study on CFRP composite using Taguchi based grey relational analysis. Materials Today: Proceedings, 211425-1431.
• Jiang, J. et al., 2012. Microstructure and mechanical properties of the motorcycle cylinder body of AM60B magnesium alloy formed by combining die casting and forging. Materials & Design, 37202-210.
• Kara, F. et al. (2017). Optimization by Taguchi method of surface roughness and vibration in turning of AISI 4140 steel. II. International Academic Research Congress-(INES 2017), Antalya, Türkiye.
• Karabıçak, Ç. et al., 2018. Determination of demand estimation methods by values and variability measures for stock items in a cleaning paper company. Journal of Current Researches on Engineering Science and Technology, 4, 1, 47-68.
• Karaboga, D. and Kaya, E. (2014). Training ANFIS using artificial bee colony algorithm for nonlinear dynamic systems identification. 2014 22nd Signal Processing and Communications Applications Conference (SIU), IEEE.
• Kassa, Y. et al. (2016). Short term wind power prediction using ANFIS. 2016 IEEE international conference on power and renewable energy (ICPRE), IEEE.
• Kayır, Y. et al., 2013. AISI 316Ti paslanmaz çeliğin tornalanmasında kesici uç etkisinin Taguchi yöntemi ile analizi. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 28, 2.
• Kechagias, J. D. et al., 2020. A comparative investigation of Taguchi and full factorial design for machinability prediction in turning of a titanium alloy. Measurement, 151,107213.
• Lewis, C., 1982. International and Business Forecasting Methods Butterworths: London.
• Lokshina, I. et al. (2003). Applications of artificial intelligence methods for real estate valuation and decision support. Hawaii International Conference on Business.
• Lund, J., 1982. Origins of green strength in iron P/M compacts. Int. J. Powder Metall. Powder Technol., 18, 2, 117-127.
• Mahdavi, S. and Akhlaghi, F., 2011. Effect of SiC content on the processing, compaction behavior, and properties of Al6061/SiC/Gr hybrid composites. Journal of Materials Science, 46, 5, 1502-1511.
• Maher, I. et al., 2014. Investigation of the effect of machining parameters on the surface quality of machined brass (60/40) in CNC end milling—ANFIS modeling. The International Journal of Advanced Manufacturing Technology, 74, 1, 531-537.
• Marya, M. et al., 2006. Microstructural effects of AZ31 magnesium alloy on its tensile deformation and failure behaviors. Materials science and engineering: A, 418, 1-2, 341-356.
• Mordike, B. and Ebert, T., 2001. Magnesium: properties— applications—potential. Materials Science and Engineering: A, 302, 1, 37-45.
• Moreno, I. et al., 2001. Microstructural characterization of a die-cast magnesium-rare earth alloy. Scripta Materialia, 45, 12, 1423-1429.
• Özarslan, S. et al., 2019. Microstructure, mechanical and corrosion properties of novel Mg-Sn-Ce alloys produced by high pressure die casting. Materials Science and Engineering: C, 105,110064.
• Özcan, E., 2021. Kükürt Gİderme İşlemİ İçİn Kullanilan Malzeme Mİktarinin Makİne Öğrenme Yöntemlerİ İle Tahmİnİ.
• Perez, P., 2001. Prediction of sulfur dioxide concentrations at a site near downtown Santiago, Chile. Atmospheric Environment, 35, 29, 4929-4935.
• Piero, P., 2002. Bonissone adaptive neural fuzzy inference systems (ANFIS): analysis and applications.
• Polmear, I. et al., (2017). Light alloys: metallurgy of the light metals, Butterworth-Heinemann.
• Shivakoti, I. et al., 2019. ANFIS based prediction and parametric analysis during turning operation of stainless steel 202. Materials and Manufacturing Processes, 34, 1, 112-121.
• Upadhyaya, G. S., (1999). Sintered metallic and ceramic materials: preparation, properties, and applications, Wiley.
• Uzundurukan, S., 2006. Determining and modelling of principal parameters affecting swelling properties of soils. Suleyman Demirel.
• Wang, J. et al., 2011. A study of the effect of antimony content on damping capacity of ZA84 magnesium alloy. Materials & Design, 32, 8-9, 4567-4572.
• Witt, S. F. and Witt, C. A., (1992). Modeling and forecasting demand in tourism, Academic Press.
• Wu, W. et al., 2000. Experimental and numerical investigation of idealized consolidation: Part 1: Static compaction. Acta materialia, 48, 17, 4323-4330.
• Yalpir, S. and Ozkan, G., 2018. Knowledge-based FIS and ANFIS models development and comparison for residential real estate valuation. International journal of strategic property management, 22, 2, 110-118.
• Yazdi, H. S. et al., 2010. Neuro-fuzzy based constraint programming. Applied mathematical modelling, 34, 11, 3547-3559.
• Yıldırım, Ç. V., 2019. Grafit parçacık takviyeli nano akışkan kullanılarak AISI 316’nın frezelenmesinde yüzey pürüzlülüğü ve kesme sıcaklığının optimizasyonu. Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 7, 1, 326-341.
• Yilmaz, M., 2010. Adaptive network based on fuzzy inference system estimates of geoid heights interpolation. Scientific research and essays, 5, 16, 2148-2154.
• Zhang, W. et al., 2012. Effects of Sr and Sn on microstructure and corrosion resistance of Mg–Zr–Ca magnesium alloy for biomedical applications. Materials & Design, 39,379-383.