Soft Modeling of Wire Electrical Discharge Machining of WC-Co Composite

Abstract:

The prediction of optimal machining conditions for required surface roughness and material removal rate (MRR) plays a very significant role in process planning of wire electrical discharge machining (WEDM). Artificial neural networks (ANN) are widely applied to predict the performance characteristics of complex machining process like WEDM very accurately. This present work deals with the features of cutting operation by WEDM of tungsten carbide- cobalt composite(WC – Co) and an artificial neural networks(ANN) model in terms of machining parameters, developed to predict surface roughness(Ra) and material removal rate (MRR).The experiment was planned as per Taguchi’s L 27 orthogonal array. The predictive capacity of the models was validated. The test results indicate that the proposed models could adequately describe the performance indicators with the limits of the factors that are being investigated. Finally the accuracy of the developed ANN model was compared to the experimental values. It was observed that the proposed ANN model is good.

• Periodical: Advanced Materials Research (Volumes 335-336)
• Pages: 535-540
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.335-336.535
• Online since: September 2011
• Authors: Veluswamy Muthuraman, Raju Ramakrishnan
• Keywords: Artificial Neural Network (ANN), MRR, Surface Roughness (SR), WC-Co, WEDM

References

[1] WEDM charmilles technologies manual (205960/E/25.09.1/1999)

[2] Liao YS,Huang JT,and Su HC, in:A study on the machining parameters optimization of wire electrical discharge machining. Journel of Materials Processing Technology Vol. 71,p.487–494 (1997)

DOI: 10.1016/s0924-0136(97)00117-9

[3] Karthikeyan R, Narayanan PRL, and Naagarazan RS in: Mathematical modeling for electric discharge machining of alumimium-silicon carbide particulate composites. Journel of Materials Processing Technology,Vol. 87, p.59–63(1999)

DOI: 10.1016/s0924-0136(98)00332-x

[4] Spedding T.A, Wang Z.G.in: Parametric optimization and surface characteristic of wire electrical discharge machining processes, Precision Engineering,Vol. 20,pp.5-15(1997)

DOI: 10.1016/s0141-6359(97)00003-2

[5] Spedding T.A, Wang Z.Q.in: Study on modeling of wire EDM process,Journel of Material Processing Technology,Vol.69 pp.18-28(1997)

DOI: 10.1016/s0924-0136(96)00033-7

[6] Tarng.Y.S, MaS.C and ChungL.K.in:Determination of optimal cutting parameters in wire electrical discharge machining, International Journal of Machine Tools &Manufacture,Vol.35, 1693-1701(1995)

DOI: 10.1016/0890-6955(95)00019-t

[7] Sarkar.S, Mitra.S, Bhattacharyya.B.in:Parametric optimization of wire electrical discharge machining of ﻻ titanium aluminide alloy through an artificial neural network model, International Journel of Advanced Manufacturing Technology,Vol. 27,pp.505-508 (2006).

DOI: 10.1007/s00170-004-2203-7

[8] Bonny.K, De Baets.P, Ost.W, Huang.S, Vleugels.J, Liu.W and Lauwers.B in : Influence of electrical discharge machining on the reciprocating sliding friction and wear response of WC–Co cemented carbides', International Journel of Refractory Metals and Hard Materials,Vol. 27,pp.350-359(2009)

DOI: 10.1016/j.ijrmhm.2008.09.002

[9] Freeman J.A. and Skapura D.M,"Neural Networks: Algorithms, Applications and Programming Techniques'', Addison Wesley Longman, Inc. (1999)

[10] Ramakrishnan.R, Karunamoorthy.L.in:Modeling and Multi Response Optimization of Inconel718 on Machining of CNC WEDM Process, Journel of Materials Processing Technology, Vol. 207, pp.343-349(2008)

DOI: 10.1016/j.jmatprotec.2008.06.040

[11] Dimla.Jr D.E, Lister P.M and Leighton N.J.in: Neural network solutions to the tool condition monitoring problem in metal cutting -A critical review of methods, International Journel of Machine Tools & Manufacture,Vol. 37, pp.1219-1241(1997)

DOI: 10.1016/s0890-6955(97)00020-5