ABSTRACT
Genetic Algorithm, a meta-heuristic form of optimization, belongs to a class called Evolutionary Algorithm. It is inspired by genetic evolution. In this, for each new ‘child’ to be brought forth, a pair of ‘parent’ data is selected from the pool of data. Using the methods of ‘crossover’ and ‘mutation’, the ‘child’ is created, which obviously shares most of the properties of its ‘parents’ but is advanced in nature. This ‘Child’ interacts with a new ‘Parent’, i.e., Data to come out with a more refined ‘Child’ and so on till no further improvement is noticed. This technique resembles genetic biology, and hence the coinage of the name. In this chapter, a revised and more versatile version of Genetic Algorithm, NSGA (non-dominated sorting genetic algorithm), has been used for optimizing the input parameters of a non-traditional machining technique—electro-chemical machining (ECM). ECM offers several unique features, such as higher machining rate and better surface finish, and it is suitable for machining a wide range of materials. In this regard, an attempt has been made to develop a mathematical model for responses, i.e., material removal rate (MRR) and surface roughness (SR) using Taguchi’s Design of Experiments. Analysis of variance test was performed to check the appropriateness of the developed mathematical models. Multi-objective optimization of performance of ECM process was performed using NSGA-II for maximizing the MRR and minimizing the SR.
