A Mathematical Model for Wire Cut Electrical Discharge Machine Parameters Using Artificial Neural Network

Abstract:

Unconventional machining process finds heavy application in aerospace, automobile and in production industries where accuracy is most needed. This process is chosen over other traditional methods because of the advent of composite and high strength materials, multifaceted parts and also because of its elevated precision. Regularly in unconventional machines, trial and error method is used to fix the values of process parameters. An algorithm incorporating Artificial Neural Network (ANN) is proposed to create mathematical model functionally relating process parameters and operating parameters of a wire cut electric discharge machine (WEDM) and copper is the work piece. This is accomplished by training a learning algorithm of feed forward neural network with back propagation. The required data used for training and testing the ANN is obtained by conducting trial runs in wire cut electric discharge machine. Proposed algorithm paves reduction in time for fixing the values for the process parameters and thus reduces the production time along with reduction in cost of machining processes and thereby increases the production as well as the efficiency. The programs for training and testing the neural network are developed, using matlab 7.0.1 package.

• Periodical: Advanced Materials Research (Volumes 984-985)
• Pages: 9-14
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.984-985.9
• Online since: July 2014
• Authors: G. Sankara Narayanan*, Vasudevan D
• Keywords: Artificial Neural Network (ANN), Copper, Mathematical Modeling, WEDM

References

[1] Kumar Sandeep (2013), Current Trends in Electrical Discharge Machining: A Review, Res.J. Engineering Sci, Volume 2, Issue 2, Pages 56- 60.

[2] Bhavesh A. Patel, D.S. Patel (2013).

[3] K. Kumar, R. Ravikumar (2013), Modeling and Optimization of Wire EDM process, International Journal of Modern Engineering Research, Volume 3, Issue 3, Pages 1645-1648.

[4] Parveen Kumar, Bharat Bhusan and Dr.R.K. Gupta (2013), A Literature Review on optimization of Input Machining Parameters of Wire- EDM, International Journal of Research in Management, Economics and Commerce, Volume 3, Issue 9, Pages 24 -32.

[5] Anand Pandey, Shankar Singh (2010), Current Research Trends in variants of Electrical Discharge Machining: A Review, International Journal of Engineering Science and Technology, Volume 2(6), Pages: 2172-2191.

[6] P. Vijaya Bhaskara Reddy, Ch R Vikram Kumar and K Hemachandra Reddy (2013).

[7] Arindam Majumder (2010) Comparison of ANN wirh RSM in predicting surface roughness with respect to process parameters in Nd: Yag Laser Drilling' Int. Journal of Engineering Science and Technology, Volume 2(10), Pages 5175-5186.

[8] Qing GAO, Qin-he ZHANG, Shu-peng, Jian-hua ZHANG (2007) Parameter optimization model in electrical discharge machining process, J. Zhejiang Univ Sci A 2008 9(1), Pages104-108.

DOI: 10.1631/jzus.a071242

[9] J. Prohazka, A.G. Mamlis, N.M. Vaxevanidis, (1997), The effect of electrode material on machinablility in Wire electro discharge machining, Journal of Materials Processing Technology, 69 (1997), pages 233-237.

DOI: 10.1016/s0924-0136(97)00024-1

[10] Mehrotra. K, Mohan.C. K and Renga. S 1997 Elements of Artfifical Neural Network, Cambridge, MA, MIT Press.

[11] D. Vasudevan, V. Selladurai and P. Nagaraj (2004), Determination of Closed Form Solution for Acceptance Sampling Using ANN, Quality Assurance, Volume 11, Issue 1, Pages 43-61.

DOI: 10.1080/10529410590930002

[12] Cybenko,G. 1989, Approximations of superposition of sigmoidal function,. Mathematics of control, signal and systems Volume 2; Pages 303- 314.

[13] Hal,S. Stern. 1996. Neural networks in Applied Statistics,. Technometrics Volume 38 Issue 3 Pages 205-220.

[14] Kwot, T.Y. and Yeung, D.Y. 1997, Constructive algorithms for structure learning in feed-forward neural network for regression problems, IEEE transactions on neural Networks Volume 8 pages 654-662.

DOI: 10.1109/72.572102