Abstract
The present paper focuses on two techniques, namely regression and neural network techniques, for predicting surface roughness in ball burnishing process. Values of surface roughness predicted by the two techniques were compared with experimental values. Also, the effects of the main burnishing parameters on surface roughness have been determined. Surface roughness (Ra) was taken as response (output) variable and burnishing force, number of passes, feed rate, and burnishing speed were taken as input parameters. Relationship between the surface roughness and burnishing parameters was found out for direct measurement of the surface roughness. Results showed the application of the regression and neural network models to accurately predict the surface roughness.
Kurzfassung
Der vorliegende Beitrag beleuchtet zwei der Techniken, nämlich die Regressionsanalyse und die Technik der Neuronalen Netze, um die Oberflächenrauheit bei einem Kugelstrahlprozess vorherzusagen. Die so ermittelte Oberflächenrauheiten wurden mit experimentell bestimmten Werten verglichen. Außerdem wurden die Auswirkungen der Hauptparameter des Polierens bezüglich Oberflächenrauheit bestimmt. Die Oberflächenrauheit (Ra) wurde als Antwortvariable und die Polierkraft, die Zahl der Polierdurchgänge, die Vorschubgeschwindigkeit und die Poliergeschwindigkeit wurden als Inputparameter herangezogen. Die Beziehung zwischen der Oberflächenrauheit und den Polierparametern wurde für die direkte Messung der Oberflächenrauheit herausgefunden. Die Ergebnisse zeigen die Anwendungsmöglichkeiten der Regressionsanalyse und des Modells der Neuronalen Netze, um die Oberflächenrauheit exakt vorherzusagen.
References
1 A. M.Hassan: The effects of ball- and roller-burnishing on the surface roughness and hardness of some non-ferrous metals, Journal of Materials Processing Technology72 (1997), pp. 385–39110.1016/S0924-0136(97)00199-4Search in Google Scholar
2 C.Wick, R. F.Veilleux: Tool and Manufacturing Engineers Handbook, Soc. Manuf. Eng.3 (1985), pp. 16–38Search in Google Scholar
3 U.Esme: Use of grey based Taguchi method in ball burnishing process for the optimization of surface roughness and microhardness of AA 7075 aluminum alloy, Materials Testing44 (2010), pp. 129–135Search in Google Scholar
4 T. SivaPrasad, B.Kotiveerachari: External burnishing of aluminum components, J. Inst. Eng.69 (1988), pp. 55–58Search in Google Scholar
5 G. Y.Shneider: Classification of metal-burnished methods and tools, Machines and Tooling XL1 (1989), pp. 35–37Search in Google Scholar
6 M. H.El-Axir: An investigation of roller burnishing, International Journal of Machine Tools & Manufacture,40 (2000), pp. 1603–161710.1016/S0890-6955(00)00019-5Search in Google Scholar
7 A. N.Niberg: Wear resistance of sideways strengthened by burnishing, Soviet Engineering Research7 (1987), pp. 67–70Search in Google Scholar
8 P. C.Michael, N.Saka, ERabinowicz: Burnishing and adhesive wear of an electrically conductive polyester – carbon film, Wear132 (1989), pp. 265–27310.1016/0043-1648(89)90077-XSearch in Google Scholar
9 N. H.Loh, S. C.Tam, S.Miyazawa: Statistical analyses of the effects of ball burnishing parameters on surface hardness, Wear129 (1989), pp. 235–24310.1016/0043-1648(89)90261-5Search in Google Scholar
10 I.Yashcheritsyn, E. I.Pyatosin, V. V.Votchuga: Hereditary influence of pre-treatment on oller-burnishing surface wear resistance, Soviet Journal of Friction and Wear8 (1987), pp. 87–90Search in Google Scholar
11 M.Fattouh, M. H.El-Axir, S. M.Serage: Investigation of the burnishing of external cylindrical surface of 70/30 Cu-Zn-alloy, Wear127 (1988), pp. 123–137Search in Google Scholar
12 S.Datta, A.Bandyopadhyay, P. K.Pal: Grey-based Taguchi method for optimization of bead geometry in submerged arc bead-on-plate welding, Int. J. Adv. Manuf. Technol.39 (2008), pp. 1136–114310.1007/s00170-007-1283-6Search in Google Scholar
13 S.Ozgun: Use of Artificial Neural Network in Ball Burnishing Process for the Prediction of Surface Roughness of AA 7075 aluminum alloy, MSc Thesis, Mersin University (2010)Search in Google Scholar
14 V.Gunaraj, N.Murugan: Prediction and optimization of weld bead, Volume for the Submerged Arc Process Part 1, Welding Journal,9 (2000), pp. 286–294Search in Google Scholar
15 U.Esme, A.Sagbas, F.Kahraman: Prediction of surface roughness in wire electrical discharge machining using design of experiments and neural networks, Iranian Journal of Science & Technology, Transaction B, Engineering,33 (2009), pp. 231–240Search in Google Scholar
16 U.Caydas, A.Hascalik, S.Ekici: An Adaptive Neuro-Fuzzy Inference System (ANFIS) Model for Wire- EDM, Expert Systems with Applications36 (2009), pp. 6135–6139Search in Google Scholar
17 F.Kahraman, U.Esme, M. K.Kulekci, Y.Kazancoglu: Regression based neural network modelling for forecasting of the metal volume removal rate in turning operations, Materials Testing54 (2012), pp. 266–270Search in Google Scholar
18 J. A.Freeman, D. M.Skapura: Neural networks, Algorithms, application and programming techniques, Wesley, New York, USA (1991)Search in Google Scholar
© 2013, Carl Hanser Verlag, München
