Predicting of Machining Quality in Electric Discharge Machining using Intelligent Optimization Techniques

Abstract

This paper presents the development and application of fuzzy logic, neural network and genetic algorithm in EDM (Electrical Discharge Machining) for prediction of machining quality. Machining quality is the main indicator of technological performances of a component for EDM. The experiments are carried out on manganese alloyed cold-work tool steel, processed with electrodes made of copper. Experiments were conducted by varying the discharge current and pulse duration and the corresponding values of surface roughness were measured. The values of machining quality predicted by these models are then compared. All models show good agreement with experimental results. The results indicate that the genetic programming technique gives slightly smaller deviation of the measured values of model than fuzzy logic and neural network.