An artificial neural network approach for pulse classification in electro chemical discharge machining (ECDM) – designing of neural network architecture

T. K.K.R. Mediliyegedara, Anjali K.M. De Silva, David K. Harrison, J. A. McGeough

Research output: Contribution to journalArticle

Abstract

This paper presents the pulse classification of the ECDM process using artificial neural networks (ANN). An Electro Discharge Machining (EDM) machine was modified by incorporating an electrolyte system and by modifying the control system. Gap voltage and working current waveforms were obtained. By observing the waveforms, pulses were classified into five groups. A feed forward neural network was trained to classify pulses. Various neural network architectures were considered by changing the number of neurons in the hidden layer. The trained neural networks were simulated. A quantitative analysis was performed to evaluate various neural network architectures.

Original languageEnglish
JournalInternational Journal of Manufacturing Science and Technology
Publication statusPublished - 1 Jan 2005

Fingerprint

Electric discharge machining
Network architecture
Neural networks
Feedforward neural networks
Neurons
Electrolytes
Control systems
Electric potential
Chemical analysis

Keywords

  • electrochemical machining
  • pulse classification
  • ECM
  • neural network architecture

Cite this

@article{837ef91df50e4b32944a7ef26de14fa9,
title = "An artificial neural network approach for pulse classification in electro chemical discharge machining (ECDM) – designing of neural network architecture",
abstract = "This paper presents the pulse classification of the ECDM process using artificial neural networks (ANN). An Electro Discharge Machining (EDM) machine was modified by incorporating an electrolyte system and by modifying the control system. Gap voltage and working current waveforms were obtained. By observing the waveforms, pulses were classified into five groups. A feed forward neural network was trained to classify pulses. Various neural network architectures were considered by changing the number of neurons in the hidden layer. The trained neural networks were simulated. A quantitative analysis was performed to evaluate various neural network architectures.",
keywords = "electrochemical machining, pulse classification, ECM, neural network architecture",
author = "Mediliyegedara, {T. K.K.R.} and {De Silva}, {Anjali K.M.} and Harrison, {David K.} and McGeough, {J. A.}",
note = "Originally published in: International Journal of Manufacturing Science and Technology (2005), 7 (1), pp.58-67.",
year = "2005",
month = "1",
day = "1",
language = "English",

}

An artificial neural network approach for pulse classification in electro chemical discharge machining (ECDM) – designing of neural network architecture. / Mediliyegedara, T. K.K.R.; De Silva, Anjali K.M.; Harrison, David K.; McGeough, J. A.

In: International Journal of Manufacturing Science and Technology, 01.01.2005.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An artificial neural network approach for pulse classification in electro chemical discharge machining (ECDM) – designing of neural network architecture

AU - Mediliyegedara, T. K.K.R.

AU - De Silva, Anjali K.M.

AU - Harrison, David K.

AU - McGeough, J. A.

N1 - Originally published in: International Journal of Manufacturing Science and Technology (2005), 7 (1), pp.58-67.

PY - 2005/1/1

Y1 - 2005/1/1

N2 - This paper presents the pulse classification of the ECDM process using artificial neural networks (ANN). An Electro Discharge Machining (EDM) machine was modified by incorporating an electrolyte system and by modifying the control system. Gap voltage and working current waveforms were obtained. By observing the waveforms, pulses were classified into five groups. A feed forward neural network was trained to classify pulses. Various neural network architectures were considered by changing the number of neurons in the hidden layer. The trained neural networks were simulated. A quantitative analysis was performed to evaluate various neural network architectures.

AB - This paper presents the pulse classification of the ECDM process using artificial neural networks (ANN). An Electro Discharge Machining (EDM) machine was modified by incorporating an electrolyte system and by modifying the control system. Gap voltage and working current waveforms were obtained. By observing the waveforms, pulses were classified into five groups. A feed forward neural network was trained to classify pulses. Various neural network architectures were considered by changing the number of neurons in the hidden layer. The trained neural networks were simulated. A quantitative analysis was performed to evaluate various neural network architectures.

KW - electrochemical machining

KW - pulse classification

KW - ECM

KW - neural network architecture

M3 - Article

ER -