Prediction of EDM Process Parameters for AISI 1020 Steel using RSM, GRA and ANN
R. Rajesh1, M. Dev Anand2
1R. Rajesh, Associate Professor, Department of Mechanical Engineering, Noorul Islam Centre for Higher Education, Kumaracoil, (Tamil Nadu), India.
2M. Dev Anand, Professor and Deputy Director, Academic Affairs, Department of Mechanical Engineering, Noorul Islam Centre for Higher Education, Kumaracoil (Tamil Nadu), India.
Manuscript received on 16 July 2019 | Revised Manuscript received on 01 August 2019 | Manuscript Published on 10 August 2019 | PP: 51-63 | Volume-8 Issue-2S3 July 2019 | Retrieval Number: B10100782S319/2019©BEIESP | DOI: 10.35940/ijrte.B1010.0782S319
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: AISI 1020 Steel is hard while machining because of its nature of harness and brittleness. Electrical Discharge Machining (EDM) is a significant technique to machine such materials. Current research examines the pulse current effect (A), discharge voltage (B), pulse on time (C), pulse off time (D),Oil pressure (E)and spark gap(F) on Metal Removal Rate (MRR) and Surface Roughness on EDM of AISI 1020 Steel. Experiments have been carried out in a methodical type taking up nearly 54 successive trails utilizing an EDM machine and a copper electrode of 10mm diameter. Three factors, three levels, Box Bekhen through response surface methodology design was utilized to analyze the outcomes. Gray relational analysis techniques are adopted for finding parameter influencing range for MRR and SR. A multi regression mathematical model was brought up in launching the association between parameters of machining and artificial neural network techniques are used for predicting the optimized parameters.
Keywords: Electro Discharge Machining, Response Surface Methodology, Gray Relational Analysis, Artificial Neural Network, Material Removal Rate, Surface Roughness.
Scope of the Article: Manufacturing Processes