Modeling the effect of CNT concentration in dielectric fluid on EDM performance using neural network

Electrical discharge machining (EDM) is one of the most reliable and precise manufacturing processes that applicable for creating complex geometries. However, the high heat produce on the electrically discharged material during the EDM process will minimize the surface quality of final product. Carb...

Full description

Bibliographic Details
Main Authors: Khan, Ahsan Ali, Al Hazza, Muataz Hazza Faizi, Adesta, Erry Yulian Triblas, Mohd. Fauzey, Nur Fadhilah
Format: Conference or Workshop Item
Language:English
English
Published: The Institute of Electrical and Electronics Engineers, Inc. 2016
Subjects:
Online Access:http://irep.iium.edu.my/47432/
http://irep.iium.edu.my/47432/
http://irep.iium.edu.my/47432/
http://irep.iium.edu.my/47432/1/47432_modeling_the_effect_of_CNT.pdf
http://irep.iium.edu.my/47432/4/47432_Modeling%20the%20Effect_Scopus.pdf
Description
Summary:Electrical discharge machining (EDM) is one of the most reliable and precise manufacturing processes that applicable for creating complex geometries. However, the high heat produce on the electrically discharged material during the EDM process will minimize the surface quality of final product. Carbon nanotubes possess unexpected strength and unique electrical and thermal properties. On the account of this, multi-wall carbon nanotubes (MWCNTs) are added to the dielectric used in the EDM process to improve its performance when machining the stainless steel using copper electrodes. In this research the effect of the concentration of MWCNTs and the peak current on the surface quality of stainless steel was investigated. The experimental result gained proved that addition of MWCNTs reduce the surface roughness and increase the material removal rate of work material. Due the number of experiment, the experiments have been simulated using JMP simulator with 500 run using the real results. The simulation results have been used in next step to develop the neural network model. The validation between the predicted and the simulation reseals show a high accuracy.