Title: Comparison of electrode wear in wire EDM for P-20, EN-19 and Stavax materials using artificial neural networks

Authors: G. Ugrasen; H.V. Ravindra; G.V. Naveen Prakash; D.L. Vinay

Addresses: Department of Mechanical Engineering, BMS College of Engineering, Bangalore-560 019, India ' Department of Mechanical Engineering, PES College of Engineering, Mandya-571 401, India ' Department of Mechanical Engineering, Vidya Vardhaka College of Engineering, Mysore-570 002, India ' Department of Mechanical Engineering, Dayananda Sagar Academy of Technology & Management, Bangalore-560 082, India

Abstract: This paper focuses on prediction and comparison of electrode wear during wire electrical discharge machining (WEDM) of P-20, EN-19 and Stavax tool steel materials. The control factors considered for the studies are pulse-on time, pulse-off time, current and bed speed. Process parameters have been selected based on Taguchi's L'16 orthogonal array. Electrode wear prediction was carried out successfully for 50%, 60% and 70% of the training set for all the three materials using artificial neural networks (ANNs). For all the materials studied, 80-90% of the predicted values are within the 95% of measured values. Thus, predicted electrode wear of 70% training set correlates well with the measured electrode wear.

Keywords: WEDM; electrode wear; wear prediction; ANNs; artificial neural networks; precision engineering; wire EDM; electrical discharge machining; electro-discharge machining; pulse-on time; pulse-off time; current; bed speed; tool steel; Taguchi methods; orthogonal arrays.

DOI: 10.1504/IJPTECH.2014.067738

International Journal of Precision Technology, 2014 Vol.4 No.3/4, pp.148 - 161

Received: 30 May 2014
Accepted: 18 Nov 2014

Published online: 28 Feb 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article