Taguchi Dizayn ile Belirlenen Optimum ANN Kullanarak Kriyojenik İşlem Uygulanmış ve Uygulanmamış Kesici Takımlarla Elde Edilen Kesme Kuvvetlerinin Tahmini

Year 2023, Volume: 13 Issue: 2, 13 - 27, 31.12.2023

Şehmus Baday , Hüseyin Gürbüz , Onur Ersöz

https://doi.org/10.55024/buyasambid.1367269

Abstract

Bu deneysel ve istatiksel çalışma, Taguchi Dizayn dayalı optimum Yapay Sinir Ağları kullanarak kesme kuvvetlerinin tahminini ele almaktadır. Bu amaçla, S/N oranları ile optimum ANN değerlendirmek için çıkış parametreleri olarak Ortalama Kareleri Hatası seçilirken, kontrol parametreleri olarak ise giriş ve çıkış transfer fonksiyonları ve eğitim fonksiyonları seçilmiştir. ANN yapısı, tüm eğitim fonksiyonlarının uygulanması için 5 setten oluşan Taguchi L9 ortogonal dizilim seçilerek optimize edilmiştir. S/N oranların MSE değerlerine göre, kesme kuvveti değerlerini optimum yapan tahminleri elde etmek için her bir set birbirleri ile karşılaştırılmıştır. Her bir set için optimum ANN yapısında kullanılan gizli ve çıkış katmanlarındaki transfer fonksiyonları ve eğitim fonksiyonları belirlenmiştir. Tornalama deneylerinde elde edilen kesme kuvvetlerini optimum yapan ANN yapısı gizli katmanda transfer fonksiyonu logsig, eğitim fonksiyonu Tlm ve çıkış katmanda transfer fonksiyonu pureline olduğunda R kare değeri 0,999945 bulunmuştur. Deney sonuçları değerlendirildiğinde, Taguchi ortogonal dizilime dayalı ANN yapısı başarılı olduğu bulunmuştur.

Keywords

Kriyojenik Isıl İşlem, Kesme Kuvvetleri, ANN, Taguchi Tasarımı, ANOVA

Project Number

BTÜBAP-2019-YL-07

Thanks

The authors would like to thank Batman University Scientific Research Projects Coordination Unit (Project Number: BTÜBAP-2019-YL-07) for their support in this study.

Prediction of Cutting Forces Obtained through Cryo-Treated and Untreated Cutting Tools Using Optimum ANN Determined by Taguchi Design

Abstract

This experimental and statistical study addresses the prediction of cutting forces by using the optimum Artificial Neural Network employed by Taguchi design. For this purpose, input and output transfer function and training algorithm were selected as control parameters, while Mean Square Error was chosen as output parameters for evaluating optimum ANN structure with S/N ratios. ANN structure was optimized through Taguchi L9 orthogonal design, which occurred 5 set-up for utilizing all training function. According to MSE values of S/N ratios, each set-up was compared with the obtained prediction of making values of cutting forces to the optimal result. For each set, the hidden transfer function, output transfer function and training function used in the optimal ANN structure were determined. The optimal ANN structure for cutting forces obtained in turning experiments were logsig transfer function in hidden layer, Tlm training function and pureline transfer function in output layer, while R square was at 0.999945. It was found that ANN based Taguchi orthogonal design was successful in evaluating the experimental results.

Keywords

Cryogenically heat treatment, Cutting force, ANN, Taguchi design

Project Number

BTÜBAP-2019-YL-07

References

• Asilturk, I., Kahramanli, H., & Mounayri, H. E. (2012). Prediction of cutting forces and surface roughness using artificial neural network (ANN) and support vector regression (SVR) in turning 4140 steel. Materials Science and Technology, 28(8), 980-986.
• Baday, Ş., & Ersöz, O. (2020). Estimation of Cutting Forces Obtained by Machining AISI 1050 Steel with Cryo-Treated and Untreated Cutting Tool Insert by Using Artificial Neural Network. Journal of Soft Computing and Artificial Intelligence, 1(2), 59-68.
• Baday, Ş. (2016). Küreselleştirme ısıl işlemi uygulanmış AISI 1050 çeliğin tornalanmasında esas kesme kuvvetlerinin yapay sinir ağları ile modellenmesi. Technological Applied Sciences, 11(1), 1-9.
• Başak, H., & Baday, Ş. (2016). Küreselleştirilmiş orta karbonlu bir çeliğin işlenmesinde, kesme parametrelerinin kesme kuvvetleri ve yüzey pürüzlülüğüne etkilerinin regresyon analizi ile modellenmesi. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 22(4), 253-258.
• Çelik, Y. H., & Türkan, C. (2020). Investigation of mechanical characteristics of GFRP composites produced from chopped glass fiber and application of taguchi methods to turning operations. SN Applied Sciences, 2, 1-12.
• Gurbuz, H., Kurt, A., & Seker, U. (2012). Investigation of the effects of different chip breaker forms on the cutting forces using artificial neural networks. Gazi University Journal of Science, 25(3), 803-814.
• Gürbüz, H., & Baday, Ş. (2022). Determination of the Effect of Tailstock and Chuck Pressure on Vibratıon and Surface Roughness in Turning Operatıons with Gray Relatıonal Analysıs Method. In ŞAHİN Y., et al. (Ed.), Mechanical Engineering, Materials Science Research And Applications (44-73) Güven Plus, Türkiye: İstanbul.
• Gürbüz, H., & Gönülaçar, Y.E. (2021). Analysis of Experimental Values Obtained at Different Cutting Parameters and MQL Flows with S/N Ratios and ANN. Journal of Polytechnic, 24(3), 1093-1107.
• Gürbüz, H., Sözen, A. & Şeker, U. (2016). Modelling of effects of various chip breaker forms on surface roughness in turning operations by utilizing artificial neural networks. Journal of Polytechnic, 19 (1), 71-83.
• Hanief, M., Wani, M.F., & Charoo, M.S. (2017). Modeling and prediction of cutting forces during the turning of red brass (C23000) using ANN and regression analysis. Engineering science and technology, an international journal, 20(3), 1220-1226.
• Jeyakumar, S., Marimuthu, K., & Ramachandran, T. (2013). Prediction of cutting force, tool wear and surface roughness of Al6061/SiC composite for end milling operations using RSM. Journal of Mechanical Science and Technology, 27, 2813-2822.
• Kara, F., Aslantas, K., & Çiçek, A. (2015). ANN and multiple regression method-based modelling of cutting forces in orthogonal machining of AISI 316L stainless steel. Neural Computing and Applications, 26, 237-250.
• Karabulut, Ş. (2015). Optimization of surface roughness and cutting force during AA7039/Al2O3 metal matrix composites milling using neural networks and Taguchi method. Measurement, 66, 139-149.
• Kilickap, E., Yardimeden, A., & Çelik, Y. H. (2017). Mathematical modelling and optimization of cutting force, tool wear and surface roughness by using artificial neural network and response surface methodology in milling of Ti-6242S. Applied Sciences, 7(10), 1064.
• Kurt A., Sürücüler, S., & Kirik, A. (2010). Kesme kuvvetlerinin tahmini için matematiksel bir model geliştirme. Politeknik Dergisi, 13(1), 15-20.
• Madić, M.J., & Radovanović, M.R. (2011). Optimal selection of ANN training and architectural parameters using Taguchi method: A case study. FME Transactions, 39(2), 79-86.
• Özkan A.İ., Sarıtaş İ., & Yaldız S., “Tornalama İşleminde Kesme Kuvvetlerinin ve Takım Ucu Sıcaklığının Yapay Sinir Ağı ile Tahmin Edilmesi, 5. Uluslararası İleri Teknolojiler Sempozyumu (IATS’09), Karabük, Türkiye, 2009, pp. 13-15.
• Patel, T.M., & Bhatt, N.M. (2018). Optimizing neural network parameters using Taguchi’s design of experiments approach: an application for equivalent stress prediction model of automobile chassis. Automotive Innovation, 1(4), 381-389.
• Sugiono, Wu, M.H., & Oraifige, I. (2012). Employ the Taguchi method to optimize BPNN’s architectures in car body design system. American Journal of Computational and Applied Mathematics, 2(4), 140-151.
• Ulas, H.B. & Ozkan, M.T. (2019). Turning processes investigation of materials austenitic, martensitic and duplex stainless steels and prediction of cutting forces using artificial neural network (ANN) techniques. Indian Journal of Engineering and Materials Sciences, 26(2), 93-104.
• Yalcin, U., Karaoglan, A. D., & Korkut, I. (2013). Optimization of cutting parameters in face milling with neural networks and Taguchi based on cutting force, surface roughness and temperatures. International Journal of Production Research, 51(11), 3404-3414.