A Hybrid Approach for Process Optimization in Taper Cutting Operation Using Wire Electrical Discharge Machining

Abstract:

Angular error is a major concern for the tool engineers during the taper cutting operation in wire electrical discharge machining (WEDM) process. Due to the complexity and non-linearity involved in the process, it is difficult to obtain good functional relationship between responses and process parameters. To address this issue, the present study proposes artificial neural network (ANN) model to determine the relationship between input parameters and output response. Bayesian regularization is adopted for selection of optimum network architecture because of its ability to fix number of network parameters irrespective of network size. Levenberg-Marquardt algorithm has been used to train the ANN model and the resulting network has good generalization capability minimizing the chance of over fitting. The model is developed based on the data obtained from a laboratory scale experimental set up. A set of six important input parameters such as part thickness, taper angle, pulse duration, discharge current, wire speed and wire tension is chosen to study the tapering operation in WEDM. Finally, a recent meta-heuristic approach known as Bat algorithm is used to suggest the optimum parametric combination for minimizing the angular error during taper cutting process in WEDM.

• Periodical: Applied Mechanics and Materials (Volume 619)
• Pages: 83-88
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.619.83
• Online since: August 2014
• Authors: Bijaya Bijeta Nayak*, Siba Sankar Mahapatra
• Keywords: Angular Error, Bat Algorithm, L-M Algorithm, Taper Cutting

References

[1] N. Kinoshita, M. Fukui and T. Fujii, Study on Wire-EDM: Accuracy in taper cut, CIRP Annals- Manufacturing Technology Vol. 36 (1987), p.119.

DOI: 10.1016/s0007-8506(07)62567-0

[2] J.A. Sanchez, S. Plaza, N. Ortega, M. Marcos and J. Albizuri, Experimental and numerical study of angular error in wire-EDM taper cutting. International Journal of Machine Tools and Manufacture Vol. 48 (2008, p.1420.

DOI: 10.1016/j.ijmachtools.2008.04.011

[3] S. Plaza, N. Ortega, J.A. Sanchez, I. Pombo, A. Mendikute, Original models for the prediction of angular error in Wire-EDM taper-cutting, The International Journal of Advanced Manufacturing Technology Vol. 44 (2009), p.529.

DOI: 10.1007/s00170-008-1842-5

[4] J.A. Sanchez, L.A. Lopez de Lacalle, Lamikiz A, Computer simulation of wire-EDM taper-cutting, International Journal of Computer Integrated Manufacturing 19 (2006) p.727.

DOI: 10.1080/09511920600628855

[5] S.G. Peace, Taguchi methods: a hands on approach. Addison-Wesley, New York. (1993).

[6] J.S. Torrecilla, L. Otero and P.D. Sanz, Optimization of an artificial neural network for thermal/pressure food processing: evaluation of training algorithms. Computers and Electronics in Agriculture. Vol. 56 (2007), p.101.

DOI: 10.1016/j.compag.2007.01.005

[7] S.S. Mahapatra and A. K. Sood, Bayesian regularization-based Levenberg Marquardt neural model combined with BFOA for improving surface finish of FDM processed part. International Journal of Advanced Manufacturing Technology, Vol. 60 (2012).

DOI: 10.1007/s00170-011-3675-x

[8] X.S. Yang. A new Metaheuristic Bat-Inspired Algorithm Nature Inspired Cooperative Strategies for Optimization (NISCO 2010). Springer Vol. 284 (2010), p.65.

DOI: 10.1007/978-3-642-12538-6_6