Artificial Neural Network Modeling for Electrical Discharge Machining Parameters

Artificial Neural Network Modeling for Electrical Discharge Machining Parameters

Raja Das (VIT University, India) and M. K. Pradhan (Maulana Azad National Institute of Technology, India)
Copyright: © 2014 |Pages: 22
DOI: 10.4018/978-1-4666-4940-8.ch014
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

The objective of the chapter is to present the application of Artificial Neural Network (ANN) modelling of the Electrical Discharge Machining (EDM) process. It establishes the best ANN model by comparing the prediction from different models under the effect of process parameters. In EDM, the motivation is frequently to get better Material Removal Rate (MRR) with fulfilling better surface quality of machined components. The vital requirements are as small a radial overcut with minimal tool wear rate. The quality of a machined surface is very important to fulfilling the growing demands of higher component performance, durability, and reliability. To improve the reliability of the machine component, it is necessary to have in depth knowledge of the effect of parameters on the aforesaid responses of the components. An extensive chain of experiments has been conducted over a wide range of input parameters, using the full factorial design. More than 150 experiments have been conducted on AISI D2 work piece materials using copper electrodes to get the data for training and testing. The additional experiments were obtained to validate the model predictions. The performance of three neural network models is discussed in the evaluation of the generalization ability of the trained neural network. It was observed that the artificial neural network models could predict the process performance with reasonable accuracy, under varying machining conditions.
Chapter Preview
Top

Introduction

Owing to the growing trend to use light, slim and compact mechanical component in recent years, there has been an increased curiosity in advanced high hardness, temperature resistance, and high strength to weight ratio materials. However, these materials are mostly unable to process by traditional manufacturing process called “difficult to machine material. Electrical Discharge Machining (EDM) has been a mainstay of manufacturing for more than six decades, providing unique capabilities to machine difficult to machine” materials with desire shape, size, and required dimensional accuracy. It is the most widely and successfully applied machining high hardness, temperature resistance, and high strength to weight ratio materials, used in mould and die making industries, aerospace component, medical appliance, and automotive industries.

It is a thermal process of eroding electrically conductive materials with a series of successive electric sparks and the complex phenomenon involving several disciplines of science and branches of engineering. The formation of the plasma channel between the tool and the workpiece, thermodynamics of the repetitive spark causing melting and evaporating the electrodes, micro-structural changes, and metallurgical transformations of material, are still not clearly understood.

Since this process is complex and stochastic in nature there are several modelling attempts have been made to understand this process. But full prospective of the process is not exploited yet. However, the relationship between input process parameter and response may be established using mathematical, empirical, and statistical modelling. Several modeling attempts have been made to characterize the EDM process based on electro-thermal theory since 1971. Many researchers have analyzed in terms of the temperature distribution, crater geometry, and material removal at the cathode Yeo et al. (2008); Dibitono et al. (1989); Patel et al. (1989); Eubank et al. (1989), semi-empirical models Wang and Tsai (2001); Valentincic and Junkar (2004), mathematical analysis Kanagarajan et al. (2008); Kuppan et al. (2007); Puertas et al. (2004); Khan et al. (2009); Khan (2008); Karthikeyan et al. (1999), and statistical analysis Pradhan and Biswas (2011a, 2008a); Dhar et al. (2007); Dvivedi et al. (2008); Wang (2009); Kiyak and Cakir (2007); Jaharah et al. (2008); Caydas and Hascalik (2008); Keskin et al. (2006); Salonitis et al. (2009); Tsai and Wang (2001b)

The EDM process has some deficiencies, such as high specific energy consumption, lower machining performance (productivity) and accuracy of the dimensions. These are the some important aspects that constrict its applications. Researchers and Investigators are thus, mesmerized towards the process modelling and picking proper machining parameters. Traditionally, these are carried out by EDM operator's expertise or conventional technical data offered by the manufacturers that confines the machining performance. Modelling of the process is generally required for its better understanding of the impact of the machining parameters on the responses. An exact model will help the experimenter to trim down the experimental cost associated with it and optimize the process by setting the required objective.

Complete Chapter List

Search this Book:
Reset