UĞUR EŞME, İREM ERSÖZ KAYA, Funda KAHRAMAN, Aysun SAĞBAŞ, AYÇA ÇAKMAK PEHLİVANLI, TURGAY İBRİKÇİ

Comparative modeling in low plasticity burnishing (LPB) process using back-propagation (BPN) and General Regression Networks (GRNN)

Galetaj ile soğuk yüzey isleme yüzey kalitesini arttırdığından günümüzde popular bir soğuk isleme prosesi haline gelmistir. Bu yüzden galetaj parametrelerinin doğru ve net bir sekilde seçilmedi gerekmektedir. Bu çalısmada geri yayılmalı ve genel regresyonlu yapay sinir ağları kullanılarak galetaj parametrelerinin (baskı kuvveti, paso sayısı, ilerleme hızı ve galetaj hızı) yüzey pürüzlülüğü üzerindeki etkileri kıyaslamalı bir model ile açıklanmaya çalısılmıstır. Sonuç olarak geri yayılmalı yapay sinir eğları ile tahmin edilen sonuçların gerçek sonuçlara çok yakın olduğu görülmüstür.

Galetaj işleminin geri yayılmalı ve genel regresyonlu yapay sinir ağlarıyla kıyaslamalı modeli

Low plasticity burnishing (LPB), a plastic deformation process, is becoming more popular as a finishing process: thus, how to select the burnishing parameters to reduce the surface roughness and to increase the surface quality is especially crucial. This paper reports the use of back-propagation (BPN) and General Regression Neural Networks (GRNN) techniques to model the burnishing process. The ANN models of surface roughness parameters is developed with the burnishing conditions such as burnishing force, number of tool passes, feed rate and burnishing speed. The experimental results showed that predicted results obtained by BPN were closest to the actual results.

PDF

___

1. Kukielka,L., “Designating the field areas for the contact of a rotary burnishing element with the rough part, providing a high-quality product”, Journal of Mechanical Technology 19, 319–356, 1989.
2. Axir,M.H., “An investigation into roller burnishing”, International Journal of Machine Tools & Manufacture 40, 1603–1617, 2000.
3. Loh,N.H., Tam,S.C., Miyazawa,S., “A study of the effects of ball-burnishing parameters on surface roughness using factorial design”, Journal of Mechanical Working Technology 18, 53–61, 1989.
4. Hassan,A.M., “The effects of ball- and roller-burnishing on the surface roughness and hardness of some non-ferrous metals”, Journal of Materials Processing Technology, (72), 385–391, 1997.
5. Wick,C., Veilleux,R.F., “Tool and manufacturing engineers handbook”, Soc. Manuf Eng, 16–38, 1985.
6. Hassan,A.M., AL-Bsharat,A.S., “Influence of burnishing process on surface roughness hardness and microstructure of some nonferrous metals”, Wear 199,1–8, 1996.
7. Ezugwu,E.O., Fadarea,D.A., Bonneya,J. Da Silva,R.B., Sales,W.F., “Modelling the correlation between cutting and process parameters in high-speed machining of Inconel 718 alloy using an artificial neural network”, International Journal of Machine Tools & Manufacture 45, 1375–1385, 2005.
8. Ezugwu,E.O., Arthur,S.J., Hines,E.L., “Tool-wear prediction using artificial neural Networks”, J. Mater. Process. Technol. 49, 255–264, 1995.
9. Dimla Sr.,D.E., “Application of perceptron neural networks to toolstate classification in a metal-turning operation”, Eng. Appl. Artif. Intell. 12,471–477, 1999.
10. Sick,B., “On-line and indirect tool wear monitoring in turning with artificial neural networks: a review of more than a decade of research”, Mech. Syst. Signal Process. 16 (4), 487–546, 2002.
11. Dimla Jr.D.E., Lister,P.M., Leighton,N:J., “Neural network solution to the tool condition monitoring problem in metal cutting-a critical review of methods”, Int. J.Mach.Tools Manuf.37(9),1219–1241, 1997.
12. Petropoulos,G.A, Torrance,A., Pandazaras,C.N., “Abbott curves characteristics of turned surfaces”, Int J Mach Tool Manuf , 43, 237–243, 2003.
13. Nalbant,M., Gokkaya,H., Toktas,I., Sur,G., “The experimental investigation of the effects of uncoated, PVD- and CVD-coated cemented carbide inserts and cutting parameters on surface roughness in CNC turning and its prediction using artificial neural Networks”, Robot Comput Integr Manuf., doi:10.1016/j.rcim.2007.11.004, 2008.
14. MATLAB 6.5, “The Language of Technical Computing release 13”, Natick, The MathWorks, Inc., 2002.
15. Juang,S.C., Tarng,Y.S., Lii,H.R., “A comparison between the back-propagation counter-propagation networks in the modeling welding process”, Journal of Materials Processing Technology 75, 54–62, 1998.
16. McClelland,J., Rumelhart,D., “Parallel Distributed Processing”, vol. 1, MIT Press, Cambridge, MA, 1986.
17. Specht,D.F., “A General Regression Neural Network”, IEEE Trans. Neural Networks, 2, 568-576, 1991.
18. Parzen,E., “On Estimation of a Probability Density Function and Mode”, Ann. Math. Stat., 33, 1065-1076, 1962.
19. Tomandl,D., Schober,A., “A Modified General Regression Neural Network (MGRNN) with New, Efficient Training Algorithms as a Robust ‘black box’-tool for Data Analysis”, Neural Networks, 14, 1023-1034, 2001.
20. Cacoullos,T., “Estimation of a multivariate density. Annals of the Institute of Statistical Mathematics”, 18, 179-189, 1966.
21. Ersoz,I., Ibrikci,T., Cakmak,A., Ersoy,O.K., “Secondary Structure Prediction of Hemoglobin by Neural Networks”, ANNIE 2004 Artificial Neural Networks in Engineering, University of Missouri-Rolla, Missouri, USA, 2004.
22. Arcaklıoglu,E., “Performance comparison of CFCs with their substitutes using artificial neural network”, I J Energy Res 28, 1113–1125, 2004.
23. Sozen,A., Arcaklıoglu,E., Ozalp,M., Caglar,N., “Forecasting based on neural network approach of solar potential in Turkey”, Renewable Energy 30, 1075–90, 2005.
24. Sozen,A., Arcaklıoglu,E., Ozkaymak,M., “Turkey’s net energy consumption”, Appl.Energy 81, 209–221, 2005.
25. Toktas,I., Akturk,N., “A new approach using artificial neural Networks for conceptual design of cylindrical helical gears”, In: Proceedings of the MTET 2005 1st international vocational and technical education technologies congress, Marmara University, 754–62, 5–7, Istanbul/Turkey, September 2005.