Architecture and training algorithm of feed forward arti cial neural network to predict material removal rate of electrical discharge machining process

Authors

1 Department of Electrical Engineering, Diponegoro Universiti, Jalan Prof. H Soedharto, Tembalang, Semarang, 50275, Indonesia

2 Faculty of Biosciences & Medical Engineering, Universiti Teknologi Malaysia, 81310 UTM Johor Bahru, Johor, Malaysia

3 Faculty of Electrical Engineering, Universiti Teknologi Malaysia, 81310 UTM Johor Bahru, Johor, Malaysia

4 Faculty of Electrical Engineering, Universiti Teknologi Malaysia, 81310 UTM Johor Bahru, Johor, Malaysia.

Abstract

This paper presents a model of a feed forward arti cial neural network to predict the material removal rate of an electrical discharge machine process. A new modi ed architecture and training algorithm is proposed by segmenting the roughing and fi nishing machining parameters of the process. The segmentation is performed in order to obtain a lower di erence between the actual and predicted material removal rates. Through comparative analysis and results obtained between the two architectures, it is found that the new modi ed feed forward arti cial neural network produces lower error between the experimental and predicted material removal rates, thus, improving the accuracy of the prediction model.

Keywords

Scientia Iranica
Volume 21, Issue 6 - Serial Number 6
Transactions on Computer Science & Engineering and Electrical Engineering (D)
December 2014
Pages 2224-2231

Files

History

  • Receive Date: 31 December 2014
  • Revise Date: 21 December 2024
  • Accept Date: 27 July 2017

Share

How to cite

Statistics