Regression Based Neural Network Modeling for Forecasting of the Metal Volume Removal Rate in Turning Operations

Funda Kahraman; Ugur Esme; Mustafa Kemal Kulekci; Yigit Kazancoglu

doi:10.3139/120.110328

Artikel

Regression Based Neural Network Modeling for Forecasting of the Metal Volume Removal Rate in Turning Operations

Funda Kahraman , Ugur Esme , Mustafa Kemal Kulekci und Yigit Kazancoglu

Veröffentlicht/Copyright: 26. Mai 2013

Veröffentlicht von

Veröffentlichen auch Sie bei De Gruyter Brill

Manuskript einreichen Informationen für Autor*innen

Aus der Zeitschrift Materials Testing Band 54 Heft 4

Abstract

The present paper focuses on two techniques, namely regression and neural network, for predicting tool wear. Predicted values of tool wear by both techniques were compared with experimental values. Also, the effects of the main machining variables on tool wear have been determined. The metal volume removed (MVR) was taken as response (output) variable and cutting speed, feed rate, depth of cut and hardness were taken as input parameters, respectively. The relationship between tool wear and machining parameters was found out by direct measurement of the tool wear by MVR. The results showed the ability of regression and neural network models to predict the tool wear, accurately.

Kurzfassung

Die diesem Beitrag zugrunde liegende Studie fokussiert sich auf zwei Technologien, und zwar der Regressionsanalyse und Neural Network Modellierungen, um den Werkzeugabtrag vorherzusagen. Die mit beiden Technologien vorhergesagten Abtragswerte wurden mit experimentellen Ergebnissen verglichen. Außerdem wurden die Effekte der Haupt-Maschinenvariablen auf den Werkzeugabtrag bestimmt. Der Metallvolumenabtrag (metal volume removed – MVR) wurde dabei als Antwort bzw. Output-Variable und die Schnittgeschwindigkeit, Vorschubrate, Schnitttiefe und Härte wurden dabei als Input-Parameter herangezogen. Es wurde ein Bezug zwischen dem Werkzeugabtrag und den Maschinenparametern hergestellt, in dem der Werkzeugabtrag direkt mittels MVR gemessen wurde. Die Ergebnisse zeigen die Möglichkeit der Regression und der Neural Network Modelle zur direkten Vorhersage des Werkzeugabtrages.

Funda Kahraman is assistant professor Dr. in Mersin University Tarsus Technical Education Faculty. She received her BS and MBA degree from İstanbul Technical University Engineering Faculty Department of Metallurgical Engineering, PhD degree from Cukurova University Engineering and Architecture Faculty Department of Mechanical Engineering. Her research areas include metallurgy, welding and design. She has number of publications on these subjects.

Ugur Esme is assistant professor Dr. in Mersin University Tarsus Technical Education Faculty. He obtained his PhD degree from Cukurova University Department of Mechanical Engineering in 2006. His research areas include CAD/CAM technology, welding, modelling, designing and water jet cutting applications.

Mustafa Kemal Kulekci is professor of the Faculty of Tarsus Technical Education, Department of Machine Education, Mersin University, Mersin, Turkey. He obtained his PhD degree from Gazi University in 2000. His research interests include CAD/CAM, friction stir welding, machinability of materials, and water-jet cutting applications.

Yigit Kazancoglu is assistant professor Dr. in Izmir University of Economics, Dept. of business Administration. He received his BS degree from Industrial Engineering Dept. of Eastern Mediterranean University, MBA degree from Coventry Univertsity and Izmir University of Economics and PhD degree in Ege University in operations management. His work at the university involves giving courses and conducting research in the areas of production planning, operations management and operations research. He is the author of a number of international publications on these subjects.

References

1 S.K.Choudhury, I.V.Appa Rao: Optimization of cutting parameters for maximizing tool life, Machine Tools & Manufacture39 (1999), pp. 343–35310.1016/S0890-6955(98)00028-5Suche in Google Scholar

2 L.Dan, J.Mathew: Tool wear and failure monitoring techniques for turning-a review, International J. of Machine Tools & Manufacturing30 (1990), No. 4, pp. 579–59810.1016/0890-6955(90)90009-8Suche in Google Scholar

3 G.H.Lim: Tool wear monitoring in machine turning, Journal of Materials Processing Technology51 (1995), pp. 2536–254010.1016/0924-0136(94)01354-4Suche in Google Scholar

4 Y.Koren, A.G.Ulsoy, K.Danai: Tool wear and breakage detection using a process model, Annals CIRP35 (1986), No. 1, p. 283–28810.1016/S0007-8506(07)61889-7Suche in Google Scholar

5 K.C.Fan, Y.H.Chao: In process dimensional control of the workpiece during turning, Prec. Eng.13 (1991)No. 1, pp. 27–3210.1016/0141-6359(91)90218-8Suche in Google Scholar

6 J.E.Kaye, D.H.Yan, N.Popplewell, S.Balakrishnan: Predicting tool flank wear using spindle speed change, International Journal of Machine Tools & Manufacturing35 (1995), No. 9, pp. 1309–131210.1016/0890-6955(94)E0031-DSuche in Google Scholar

7 W.L.Jin, P.K.Venuvinıd, X.Wang: An optical fibre sensor based cutting force measuring device, Int. J. Mach. Tools & Manufact35 (1995); No. 6, pp. 877–88310.1016/0890-6955(94)E0025-ESuche in Google Scholar

8 J.Kopac, S.Sali: Tool wear monitoring during the turning process, Journal of Materials Processing Technology113 (2001), pp. 312–31610.1016/S0924-0136(01)00621-5Suche in Google Scholar

9 J.I.El Gomayel, K.D.Bregger: Online tool wear sensing for turning operations, J. Eng Ind.108 (1986), pp. 44–4910.1115/1.3187040Suche in Google Scholar

10 I.A.Choudhury, M.A.El-Baradie: Tool life prediction model by design of experiments for turning high strength steel (290 BHN), Journal of Materials Processing Technology77 (1998), pp. 319–32610.1016/S0924-0136(97)00435-4Suche in Google Scholar

11 S.K.Choudhury, V.K.Jain, V.V.Rama Rao: On-line monitoring of tool wear in turning using a neural network, International Journal of Machine Tools & Manufacture39 (1999), pp. 489–504.10.1016/S0890-6955(98)00032-7Suche in Google Scholar

12 R. G.Silva, K. J.Baker, S. J.Wilcox, R. L.Reuben: The adaptability of a tool wear monitoring system under changing cutting conditions, Mechanical Systems and Signal Processing14 (2000), No. 2, pp. 287–29810.1006/mssp.1999.1286Suche in Google Scholar

13 A.Ghasempoor, J.Jeswiet, T.N.Moore: Real time implementation of on-line tool condition monitoring in turning, International Journal of Machine Tools & Manufacture39 (1999), pp. 1883–190210.1016/S0890-6955(99)00035-8Suche in Google Scholar

14 S.K.Choudhury, G.Bartarya: Role of temperature and surface finish in predicting tool wear using neural network and design of experiments, International Journal of Machine Tools & Manufacture43 (2003), pp. 747–75310.1016/S0890-6955(02)00166-9Suche in Google Scholar

15 R.H.Myers, D.C.Montgomery: Response Surface Methodology: Process and Product Optimization Using Designed Experiments, John Wiley & Sons Inc., New York (2002)Suche in Google Scholar

16 S.C.Juang, Y.S.Tarng, H.R.Li: A comparison between the back propagation-counter propagation networks in the modeling welding process, Journal of Materials Processing Technology75 (1998), pp. 54–6210.1016/S0924-0136(97)00292-6Suche in Google Scholar

17 J. A.Freeman, D. M.Skapura: Neural Networks: Algorithms, Application and Programming Techniques, Wesley, New York (1991)Suche in Google Scholar

Published Online: 2013-05-26

Published in Print: 2012-04-01

Sie haben derzeit keinen Zugang zu diesem Inhalt.

Artikel in diesem Heft

https://doi.org/10.3139/120.110328