Deep Learning Based Metal Removal Rate Investigation on Superni 90 Super Alloy Using Al 7178 Tool on Die-Sink Edm

Abstract

Aluminum being the light material, its alloy materials are used in most of the aerospace and automotive fields. From the Literature it is observed, that a tool material of AL 7178 for the Electro Discharge Machining Process is not adopted though it is favorable material for tool. In this work an attempt is made to investigate the various input parameters of Electro Discharge Machining Process which affects the Material Removal Rate (MRR), Surface Roughness (SR) and Tool Wear rate (TWR) For the experimentation AL 7178 is employed as tool material for machining of Nickel based alloy (Superni90). The investigation of the experimentation is compared with conventional tool material of Copper (Cu). And it is observed that AL 7178 yields that AL 7178 is superior performance. Further results of the experimentation machine learning and Deep learning models are developed for better understanding of the process with AL 7178 tool for real life applications which can minimize the cost of experimentation. Apart from these studies, an attempt is made to see the accuracy of geometry of the material removal on the workpiece with respect to tool geometry by using image analysis concept avialble in Mat Lab Software.