No Cover Image

Journal article 229 views 359 downloads

Prediction of surface roughness and material removal rate in wire electrical discharge machining on aluminum based alloys/composites using Taguchi coupled Grey Relational Analysis and Artificial Neural Networks

Titus Thankachan, K. Soorya Prakash, R Malini, S. Ramu, Prabhu Sundararaj, Sivakumar Rajandran, Devaraj Rammasamy, Sathiskumar Jothi Orcid Logo

Applied Surface Science

Swansea University Author: Sathiskumar Jothi Orcid Logo

Abstract

In this research, a novel aluminum alloy and metal matrix composite was designed and developed for self healing purpose. Tin at varying weight percentages (5, 10, 15 & 20 wt %) was alloyed into aluminum along with other alloying elements to form a new set of metal alloy and 5 wt% of SiC particle...

Full description

Published in: Applied Surface Science
ISSN: 01694332
Published: 2018
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa40726
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: In this research, a novel aluminum alloy and metal matrix composite was designed and developed for self healing purpose. Tin at varying weight percentages (5, 10, 15 & 20 wt %) was alloyed into aluminum along with other alloying elements to form a new set of metal alloy and 5 wt% of SiC particles was dispersed to the above said combinations to develop new sets of composite materials. Optical microscope of the developed set of samples reveals a modification in the grain structure with dispersion of tin element and with respect to increment of tin content the hardness value tends to decrease. Investigated the effect of wire electric discharge machining (WEDM) process parameters such as Pulse On time (PON), Pulse Off time (POFF), wire feed rate (WFR) along with the material elemental composition parameters Sn wt% and SiC wt% using Taguchi coupled Grey Relational Analysis. On behalf of the above said parameters a L32 orthogonal array based experimental design was finalized and based on the experimental studies single and multi criteria based optimization was conceded. Significance of each processing parameters over the output responses Material Removal Rate (MRR) and surface roughness (Ra) was examined through ANOVA method. Machine learning techniques was used and Neural Network models was developed to predict the MRR and Ra values and the experimental confirmations identified the effectiveness of the developed models.
Keywords: Surface Roughness; Machine Learning; Artificial Neural Network; Aluminum alloys; Metal matrix composites; wire electric discharge machining; Parametric optimization
College: Faculty of Science and Engineering