Experimental investigation and optimisation of WEDM process for machining maraging steel using neural network based Jaya algorithm
by Ruma Sen; Bikash Choudhuri; John Deb Barma; Prasun Chakraborti
International Journal of Machining and Machinability of Materials (IJMMM), Vol. 20, No. 4, 2018

Abstract: Wire electric discharge machining has become one of the popular machining processes used for generating complex geometry on electrically conductive materials. Due to its complex behaviour, a correlation between parameters and machining characteristics has been established by a neural network model. This study also recommends an optimal setting of process parameters with an aim to improve machining performance, which is achieved by using Jaya algorithm. Experiments were conducted on maraging steel 300 using silver coated brass wire to study the effects of process parameters (pulse on time, pulse off time, peak current, and servo voltage and wire tension) on the performance characteristics such as root mean square roughness, cutting speed, and kerf width. From the study, it is revealed that pulse on time is the predominant factor that mostly influences the machining characteristics. According to the analysis of results, the most suitable parametric combinations which obtained from Jaya algorithm offer the best performance characteristics.

Online publication date: Fri, 14-Sep-2018

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Machining and Machinability of Materials (IJMMM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com