A Hybrid Methodology of ANN-NSGA-II for Optimization of the Process Parameters of Slotted-Electrical Discharge Abrasive Grinding Process

A Hybrid Methodology of ANN-NSGA-II for Optimization of the Process Parameters of Slotted-Electrical Discharge Abrasive Grinding Process

Ravindra Nath Yadav (Department of Mechanical Engineering, BBD University Lucknow, India) and Vinod Yadava (Department of Mechanical Engineering, Motilal Nehru National Institute of Technology, Allahabad, India)
DOI: 10.4018/ijmfmp.2014070102
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Slotted-Electrical Discharge Abrasive Grinding (S-EDAG) is a new innovative hybrid machining process, which is developed by comprising the Electrical Discharge Grinding (EDG) and Abrasive Grinding (AG) where both the processes occur alternatively. The selection of the suitable combination of process parameters is much difficult due to non-linear relation between input and output. The aim of this study is to apply a hybrid approach of Artificial Neural Network (ANN) and Non-Dominated Sorting Genetic Algorithm (NSGA-II) to optimize the process parameters of S-EDAG process during machining of Al/SiC/B4C composite. ANN architecture with back propagation algorithm has been used for modeling, which is trained and tested with experimental data. The experimental data have been collected after exhaustive experimentation considering the effect of current, pulse duration, pulse interval, wheel RPM and abrasive grit number on material removal rate (MRR) and average surface roughness (Ra). The developed ANN model has been coupled with NSGA-II to generate the population and evaluate the objective functions during optimization. The results have been shown that hybrid approach of ANN-NSGA-II provides set of optimal solution that helps to manufacturer to select the appropriate combination of input parameters and reduce the product manufacturing cost.
Article Preview

1. Introduction

Metal matrix composites (MMCs) are widely used in automobile, aerospace and military due to their light weight and high specific strength (Mohan et al., 2004). These materials are consisting two phases viz. matrix and reinforcement. The matrix materials are soft metals or alloys as copper, aluminium or magnesium while reinforcement materials are ceramic as Al2O3, SiC, ZrO2, B4C or TiC. The reinforcement of additional phase of ceramics into MMCs makes them hybrid-MMCs, which become necessary to achieve the combined advantages of the reinforcements. The performances of hybrid-MMCs are better as compared to the conventional MMCs which are reinforced with single ceramic (Zhong, 2003; Mahmoud et al., 2010). The machining of MMCs is always a difficult task due to the presence of hard and brittle ceramic particles, which lead to excessive cutting forces and tool wears (Hung, 1994). Increasing the additional phase of reinforcement into matrix enhances the products quality and effective service life but simultaneously lead to poor machinability as which the widespread use of these materials are limited. Generally, diamond or diamond coated cutting tools are used for machining of these materials but the coated tool wear rapidly when the coating is ruptured (Davim, 2002). Instead of machining by cutting, the diamond grinding (DG) is widely used for machining of MMCs (Zhong & Hung, 2002; Kopac & Krajnik, 2006). The cracks formation, generation of residual stresses and rapid wheel loading during grinding of MMCs are major issues (Kim et al., 1997; Hegeman et al., 2001). Thus, as an alternative of conventional machining processes, researchers are focusing their efforts to develop innovative source of energies for machining such difficult to machine materials, which is known as unconventional machining processes.

Many researchers have applied unconventional machining processes for machining of MMCs. Muller and Monaghan (2000; 2001) experimentally investigated that the performance of Electrical Discharge Machining (EDM) is better than abrasive jet and laser beam machining but productivity is low. The formation of recast layer and subsurface cracks are major problem of EDM process, which need secondary processing. Mohan et al. (2002; 2004) investigated that rotational tool electrode gives better performance than stationary electrode during EDM of Al/SiC composite. Abothula et al. (2010) proved that rotational speed of tool electrode enhanced the flushing efficiency of EDM process resulting high material removal rate (MRR) with better surface finish. Instead of conventional and unconventional machining processes, several researchers are tested the performance of hybrid machining of electro-discharge grinding (EDG) and DG named as electro-discharge diamond grinding (EDDG) for machining of difficult to machine materials. Wei and Rajurkar (1995) compared the performance of EDDG with EDG and found high MRR with better surface finish with EDDG process. Koshy et al. (1996) claimed that grinding forces and specific energy decreases in EDDG process due to the thermal softening of work material. Choudhury et al. (1999) investigated that lower discharge voltage is more suitable for EDDG process. Yadav et al. (2008) investigated that wheel speed is more important input parameter of EDDG process during machining of HSS workpiece. Singh et al. (2010) found that material removal capability of diamond wheel declines at low current and at high wheel speed due wheel glazing. Ji et al. (2010) claimed that combined machining of EDM and grinding process gives better performances as compared to the EDM and grinding processes. But no any published research has been found related to Slotted-Electrical Discharge Abrasive Grinding (S-EDAG) process, which is developed for alternative application of EDG and mechanical grinding during machining with application slotted abrasive grinding wheel.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 5: 2 Issues (2018): 1 Released, 1 Forthcoming
Volume 4: 2 Issues (2017)
Volume 3: 2 Issues (2016)
Volume 2: 2 Issues (2015)
Volume 1: 2 Issues (2014)
View Complete Journal Contents Listing