Bio-Inspired Meta-Heuristic Multi-Objective Optimization of EDM Process

Bio-Inspired Meta-Heuristic Multi-Objective Optimization of EDM Process

Goutam Kumar Bose (Haldia Institute of Technology, India), Pritam Pain (Haldia Institute of Technology, India) and Supriyo Roy (Haldia Institute of Technology, India)
DOI: 10.4018/978-1-5225-8223-6.ch014

Abstract

Modern-day engineering is trending toward complex devices with high accuracy and precision while at the same time the workpiece materials are becoming harder and more complex alloys. Non-conventional machining helps to sustain industries in this challenging environment. Electric discharge machining is one such precision machining that can produce complex product with great accuracy. This machine can be utilized in the manufacturing of complicated shaped die for plastic molding, automobile parts, aerospace, and other applications. In solving real-world problems like engineering design, business planning, and network design, challenges are being faced due to highly non-linear data and limited resources like time and money. Optimization is the best choice to solve such practical problems efficiently. This chapter deals with the optimization of EDM process parameters using two different bio-inspired optimization algorithms, namely, artificial bee colony algorithm and whale optimization algorithm, for both single as well as multiple responses and compares the results.
Chapter Preview
Top

Introduction

As the modern-day engineering is trending for the complex device with high accuracy and precision and at the same time the workpiece material is becoming harder and more complex alloy. It is very difficult to machining those products by only employing conventional machining process. Non-conventional machining helps to sustain those industries in this challenging environment. Electric Discharge Machining (EDM) is one such precision machining which can produce complex product with great accuracy. This machine can be utilised in the manufacturing of complicated shaped die for plastic moulding, automobile parts, aerospace and other applications. This machining process involves thermo chemical reaction in between toll and the workpiece. Both the cathode tool and the anode workpiece are submerged in the dielectric fluid and separated by a small gap, commonly known as spark gap. When the current flows, high number of electrons flows from tool to workpiece and as a result the thrust energy of the electron converted into heat energy and melt and vaporised the workpiece material instantly regardless of the hardness of the material. The temperature range during machining in between 80000C to 120000C.As the machining condition does not involve the hardness of the workpiece material, this EDM is very useful for machining hard electricalconductive material with high precision. The main influencing parameters for EDM are Pulse on Time (TON), Duty factor, Pulse off Time (TOFF), sensitivity of the dielectric fluid, Spark Gap (SG), Gap Current (GI), flow of the dielectric fluid etc. AISI EN-24 is one such hard steel material which is very difficult to machining by conventional machining process.

In solving real-world problems like, engineering design, business planning, network design, even in case of holiday planning, challenges are being faced due to highly non-linear data and limited resources like, time and money. Optimization is the best choice to solve such practical problems efficiently. Optimization means to find out the best possible outcome on the basis of self-contradictory input parameters. Thus, optimization problems can be classified as constrained minimization problem in case of cost, business loss, energy consumption, surface roughness, machining time etc. and also as constrained maximization problem in case of profit, energy output, efficiency etc. During past years, several optimization algorithms have been developed by researchers to cope up the challenges of real-world problems. It is noteworthy, the recent development in computer simulation technology is essential to carry out those optimization algorithms successfully.

Inspired by the various intelligent activities spread over within nature, researchers have developed various nature-based optimization algorithms to solve non-linear problems. Some of these algorithms are based on intelligent behaviour of biological (living) characters are called bio-inspired algorithm. Within the bio-inspired algorithms, some are based on intelligent foraging behaviour of a group of biological characters known as Swarm Intelligence (SI-based) algorithm and some algorithms which are not based on swarm intelligent behaviour of biological character known as not SI-based algorithm. Some examples of SI-based algorithms are, Artificial Ant Colony (AAC), Artificial Bee Colony (ABC), Cuckoo Search (CS), Artificial Fish Swarm (AFS), Firefly Algorithm (FA) etc. Examples of not SI-based algorithms are Dolphin Echolocation (DE), Whale Optimization (WO), etc. EDM is one such complex machining process which involves various control parameters to optimize various different contradictory responses like Material Removal Rate (MRR), Surface Roughness (Ra), Overcut (OC) etc. It is very important to optimize this machining process within the given resources.

Complete Chapter List

Search this Book:
Reset