Yüksek İlerleme ile Frezeleme İşlemi Esnasında Oluşan Kesme Kuvvetinin ve İş Parçası Yüzey Pürüzlülüğünün Yapay Sinir Ağları ile Modellenmesi

Year 2021, Volume: 7 Issue: 1, 58 - 66, 30.04.2021

Ramazan Cakıroglu Gültekin Uzun

Abstract

Bu çalışma üç aşamadan oluşmaktadır. İlk aşamada vermüküler grafitli dökme demir numunelerine farklı östemperleme işlemi uygulayarak üç farklı sertlikte (42.77, 44.07 ve 45.6 HRC ) malzemeler elde edilmiştir. İkinci aşamada frezeleme deneyleri yüksek ilerleme (High-Feed) (0.6-0.9 ve 1.2 mm/dev) değerlerinde, üç farklı kesme hızında (50-70 ve 98 m/dak) ve 0.5 mm kesme derinliğinde gerçekleştirilerek bileşke kuvvet (Fr) ve ortalama yüzey pürüzlülüğü (Ra) değerleri elde edilmiştir. Deneyler sonucunda Ra değeri 0.461 µm ile 4.635 µm değerleri arasında değişirken, Fr değerleri 1310 N ile 2563 N arasında oluşmuştur. Son aşamada ise elde edilen Fr ve Ra değerleri kullanılarak yapay sinir ağları (YSA) yöntemiyle matematiksel formül geliştirilmiştir. Elde edilen denklem sonucu tahmin edilen değerler ile deney sonuçları arasında uyum olduğu görülmüştür.

Keywords

Östemperleme, yüksek ilerleme (High-Feed), bileşke kuvvet, yüzey pürüzlülüğü, yapay sinir ağları

Modeling of the Cutting Force and Workpiece Surface Roughness During the Milling Process with High Feed Using Artificial Neural Networks

Abstract

This study consists of three stages. In the first stage, materials of three different hardness (42.77, 44.07 and 45.6 HRC) were obtained by applying different austempering process to cast iron samples with vermicular graphite. In the second stage, milling experiments are performed at high feed (0.6-0.9 and 1.2 mm/rev), three different cutting speeds (50-70 and 98 m/min) and 0.5 mm cutting depth, and the resultant force (Fr) and average Surface roughness (Ra) values were obtained. As a result of the experiments, Ra value varied between 0.461 µm and 4.635 µm, while Fr values were between 1310 N and 2563 N. In the last stage, a mathematical formula was developed by using the artificial neural networks (ANN) method using the obtained Fr and Ra values. As a result of the obtained equation, it was observed that there was a harmony between the estimated values and the experimental results.

Keywords

Austempering, High-Feed, cutting force, surface roughness, artificial neural networks

References

• 1. Keller, J., Fridrici, V., Kapsa, P., Vidaller, S., & Huard, J. F. “Influence of chemical composition and microstructure of gray cast iron on wear of heavy duty diesel engines cylinder liners,” Wear, 263(7-12), 1158-1164, September 2007. Doi:https://doi.org/10.1016/j.wear.2007.01.091
• 2. Uzun, G. “Analysis of grey relational method of the effects on machinability performance on austempered vermicular graphite cast irons,” Measurement, 142, 122-130, August 2019. Doi: https://doi.org/10.1016/j.measurement.2019.04.059
• 3. A, Mavi, and I, Korkut. "The effects of austempering temperature and time on the machinability of vermicular graphite iron," Materials Testing 56.4 289-293, September 2014.
• 4. Lin, Y., He, S., Lai, D., Wei, J., Ji, Q., Huang, J., & Pan, M. “Wear mechanism and tool life prediction of high-strength vermicular graphite cast iron tools for high-efficiency cutting,” Wear, 454, 203319, August 2020. Doi: https://doi.org/10.1016/j.wear.2020.203319
• 5. Holmgren, D. Review of thermal conductivity of cast iron. International Journal of Cast Metals Research, 18(6), 331-345, November 2005. Doi: https://doi.org/10.1179/136404605225023153
• 6. Dodd, J., & Gundlach, R. B. “Advances in process technology and new applications of ADI”. In Proc. of Bcira conference on development of Future Foundry Prosperity, University of Warwick, 1984.
• 7. Denkena, B., Böß, V., Nespor, D., & Samp, A. “Kinematic and stochastic surface topography of machined TiAl6V4-parts by means of ball nose end milling,” Procedia Engineering, 19, 81-87, 2011. Doi: https://doi.org/10.1016/j.proeng.2011.11.083
• 8. Ryu, S. H., Choi, D. K., & Chu, C. N. “Roughness and texture generation on end milled surfaces,” International Journal of Machine Tools and Manufacture, 46(3-4), 404-412, 2006. Doi: https://doi.org/10.1016/j.ijmachtools.2005.05.010
• 9. D. Biermann, P. Kersting, T. Surmann. “A general approach to simulating workpiece vibrations during five-axis milling of turbine blades. CIRP Ann,” Manuf Technol 59(1):125–128, 2010. Doi: https://doi.org/10.1016/j.cirp.2010.03.057
• 10. Hense, R., Wels, C., Kersting, P., Vierzigmann, U., Löffler, M., Biermann, D., & Merklein, M. “High-feed milling of tailored surfaces for sheet-bulk metal forming tools,” Production Engineering, 9(2), 215-223, September 2015. Doi: https://doi.org/10.1007/s11740-014-0597-0
• 11. Amigo, F. J., Urbikain, G., Pereira, O., Fernández-Lucio, P., Fernández-Valdivielso, A., & de Lacalle, L. L.Combination of high feed turning with cryogenic cooling on Haynes 263 and Inconel 718 superalloys. Journal of Manufacturing Processes, 58, 208-222, October 2020. Doi: https://doi.org/10.1016/j.jmapro.2020.08.029
• 12. Zabel A, Surmann T, Peuker A. “Surface structuring and tool path planning for efficient milling of dies,” In: 7th international conference on high speed machining proceedings, Bamberg, pp 155–160, 2008. 13. Tillmann, W., Stangier, D., Hagen, L., Biermann, D., Freiburg, D., & Meijer, A. “Tribological investigation of surface structures processed by high-feed milling on HVOF sprayed WC-12Co coatings,” Surface and Coatings Technology, 395, 125945, August 2020. Doi: https://doi.org/10.1016/j.surfcoat.2020.125945
• 14. Tillmann, W., Stangier, D., Laemmerhirt, I. A., Biermann, D., & Freiburg, D. “Investigation of the tribological properties of high-feed milled structures and Cr-based hard PVD-coatings,” Vacuum, 131, 5-13, Sempember 2016. Doi: https://doi.org/10.1016/j.vacuum.2016.05.024
• 15. Zhang, T., Liu, Z., Sun, X., Xu, J., Dong, L., & Zhu, G. “Investigation on specific milling energy and energy efficiency in high-speed milling based on energy flow theory,” Energy, 192, 116596, February 2020. Doi: https://doi.org/10.1016/j.energy.2019.116596
• 16. Lin, Y., He, S., Lai, D., Wei, J., Ji, Q., Huang, J., & Pan, M. “Wear mechanism and tool life prediction of high-strength vermicular graphite cast iron tools for high-efficiency cutting,” Wear, 454, 203319, August 2020. Doi: https://doi.org/10.1016/j.wear.2020.203319
• 17. Mundada, V., & Narala, S. K. R. “Optimization of milling operations using artificial neural networks (ANN) and simulated annealing algorithm (SAA),” Materials Today: Proceedings, 5(2), 4971-4985, 2018. Doi: https://doi.org/10.1016/j.matpr.2017.12.075
• 18. Çakıroğlu, R., Yağmur, S., Acır, A., & Şeker, U. Modelling of Drill Bit Temperature and Cutting Force in Drilling Process Using Artificial Neural Networks, pages: 333-340. Politeknik Dergisi, 20(2), 333-340, 2017. Doi: https://doi.org/10.2339/2017.20.2 333-340
• 19. Parmar, J. G., Dave, K. G., Gohil, A. V., & Trivedi, H. S. Prediction of end milling process parameters using artificial neural network. Materials Today: Proceedings. Vol. 38, Part 5, 3168-3176, 2020. Doi: https://doi.org/10.1016/j.matpr.2020.09.644
• 20. Ç. ELMAS. Yapay Sinir Ağları. Ankara: Seçkin Yayıncılık 2003, pp.192 21. Hagan, M. T., Demuth, H. B., Beale, M. H., & De Jesús, O., “Neural network design” Boston: PWS publishing company, 20, 1996.