Multi response optimization for micro-EDM machining of AISI D2 die steel using RSM and neural network

Abstract

Abstract Micro parts play an important role in the growing micro- industry such as in electronics field and MEMS applications. In precision industry, micro-hole machining is very much required, such as fuel injection nozzles. Micro Electrical Discharge Machining (Micro-EDM) is defined as an un-conventional manufacturing process for the materials having electrical conductivity. It is widely used in die and tool making. In this paper, the effect of various machining parameters used like pulse on time, pulse off time, peak current, spark gap voltage, pulse peak voltage and current output on machining hardened AISI D2 die steel using copper electrodes of 600 µm diameter have been analysed. Metal Removal Rate (MRR) and Tool Wear Rate (TWR) are the responses to be measured. The experiments are conducted by Central Composite Design (CCD) of Response Surface Methodology (RSM) and using three level RSM Design of Experiment (DOE) approach. Models for the output responses have been developed. Desirability function approach is used for optimization of multi response by fitting regression model using the experimental values, after that the parameters of optimal machining are verified experimentally. The optimum predicted response values of MRR, and TWR are 1663.4564 µg/min and 166.7949 µg/min respectively and it is found that experimental values are close to optimized responses.