Title: An integrated approach for prediction of radial overcut in electro discharge machining using fuzzy graph recurrent neural network

Authors: Amrut Ranjan Jena; Raja Das; D.P. Acharjya

Addresses: School of Computer Science and Engineering, VIT, Vellore-632014, Tamilnadu, India ' School of Advanced Sciences, VIT, Vellore-632014, Tamilnadu, India ' School of Computer Science and Engineering, VIT, Vellore-632014, Tamilnadu, India

Abstract: Manufacturing of goods relies on the design methodology and the process parameters. The parameters used in manufacturing process play an important role to build a quality product. Initially heuristic techniques are used for parameter selection. Much research has been conducted to predict the radial overcut using neural networks. Besides, fuzzy neural network gains more popularity due to presence of fuzzyness in machining process. In this paper fuzzy graph recurrent neural network architecture is used for modelling and predicting the radial overcut in electro discharge machining. The proposed model is analysed over the information system obtained from VIT, Vellore, India. Moreover, it is also compared with fuzzy graph neural network and traditional neural network and found to be better in terms of accuracy.

Keywords: recurrent neural network; RNN; fuzzy graph; mean square error; MSE; radial overcut; electro discharge machining; EDM.

DOI: 10.1504/IJES.2021.117945

International Journal of Embedded Systems, 2021 Vol.14 No.4, pp.345 - 354

Received: 08 Apr 2020
Accepted: 02 Jul 2020
Published online: 05 Oct 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article