Artificial Neural Network approach in modelling of EDM process

Gopal Indurkhya, K. P. Rajurkar

Research output: Contribution to conferencePaper

25 Scopus citations

Abstract

The complexity and stochastic nature of the Electro discharge machining (EDM) process has defied numerous attempts of modeling it accurately. This paper reports an attempt of modeling the EDM process through Artificial Neural Networks. For orbital EDM modeling, the 9-9-2 size back propagation neural network has been developed. Machining depth, tool radius, orbital radius, radial step, vertical step, offset depth, pulse ontime, pulse offtime and discharge current are selected as input parameters. The material removal rate (MRR) and surface roughness (Ra) are output parameters for the model. Results of the neural network model have been compared with estimates obtained by multiple regression analysis. Experiments have also been performed to check the validity of the neural network model. It is concluded that the artificial neural network model for EDM provide faster and more accurate results.

Original languageEnglish (US)
Pages845-850
Number of pages6
StatePublished - 1992
EventProceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92 - St.Louis, MO, USA
Duration: Nov 15 1992Nov 18 1992

Other

OtherProceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92
CitySt.Louis, MO, USA
Period11/15/9211/18/92

ASJC Scopus subject areas

  • Software

Fingerprint Dive into the research topics of 'Artificial Neural Network approach in modelling of EDM process'. Together they form a unique fingerprint.

  • Cite this

    Indurkhya, G., & Rajurkar, K. P. (1992). Artificial Neural Network approach in modelling of EDM process. 845-850. Paper presented at Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92, St.Louis, MO, USA, .