Artificial Neural Network approach in modelling of EDM process

Gopal Indurkhya, K. P. Rajurkar

Research output: Contribution to conferencePaper

25 Citations (Scopus)

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 - Dec 1 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

Fingerprint

Electric discharge machining
Neural networks
Backpropagation
Regression analysis
Machining
Surface roughness
Experiments

ASJC Scopus subject areas

  • Software

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, .

Artificial Neural Network approach in modelling of EDM process. / Indurkhya, Gopal; Rajurkar, K. P.

1992. 845-850 Paper presented at Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92, St.Louis, MO, USA, .

Research output: Contribution to conferencePaper

Indurkhya, G & Rajurkar, KP 1992, 'Artificial Neural Network approach in modelling of EDM process', Paper presented at Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92, St.Louis, MO, USA, 11/15/92 - 11/18/92 pp. 845-850.
Indurkhya G, Rajurkar KP. Artificial Neural Network approach in modelling of EDM process. 1992. Paper presented at Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92, St.Louis, MO, USA, .
Indurkhya, Gopal ; Rajurkar, K. P. / Artificial Neural Network approach in modelling of EDM process. Paper presented at Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92, St.Louis, MO, USA, .6 p.
@conference{9b3fe5d46fe84809845351efbbf4bd6f,
title = "Artificial Neural Network approach in modelling of EDM process",
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.",
author = "Gopal Indurkhya and Rajurkar, {K. P.}",
year = "1992",
month = "12",
day = "1",
language = "English (US)",
pages = "845--850",
note = "Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92 ; Conference date: 15-11-1992 Through 18-11-1992",

}

TY - CONF

T1 - Artificial Neural Network approach in modelling of EDM process

AU - Indurkhya, Gopal

AU - Rajurkar, K. P.

PY - 1992/12/1

Y1 - 1992/12/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0027105510&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027105510&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0027105510

SP - 845

EP - 850

ER -