Staff View: Prediction of material removal rate and tool wear rate in electrical discharge machining using feedforward neural network / Zaid Mohd Hanapiah.

Prediction of material removal rate and tool wear rate in electrical discharge machining using feedforward neural network / Zaid Mohd Hanapiah.

Electrical discharge machining (EDM) is one of the widely used non-traditional machining techniques for manufacturing geometrically complex or hard material parts. The EDM process uses repeated electrical discharges between electrode and workpiece to remove material which are submerged in a dielectr...

Full description

Saved in:

Bibliographic Details
Main Author:	Mohd Hanapiah, Zaid
Format:	Thesis
Language:	English
Published:	2009
Subjects:	Mechanics applied to machinery. Dynamics Machine design and drawing
Online Access:	http://ir.uitm.edu.my/id/eprint/38954/1/38954.pdf http://ir.uitm.edu.my/id/eprint/38954/
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.uitm.ir.38954
record_format	eprints
spelling	my.uitm.ir.389542020-12-09T08:03:09Z http://ir.uitm.edu.my/id/eprint/38954/ Prediction of material removal rate and tool wear rate in electrical discharge machining using feedforward neural network / Zaid Mohd Hanapiah. Mohd Hanapiah, Zaid Mechanics applied to machinery. Dynamics Machine design and drawing Electrical discharge machining (EDM) is one of the widely used non-traditional machining techniques for manufacturing geometrically complex or hard material parts. The EDM process uses repeated electrical discharges between electrode and workpiece to remove material which are submerged in a dielectric medium. There are many researchers carried out investigation for improving the process performance by modeling the EDM process. Neural network (NN) is one of the most extensively used methods for prediction and modeling EDM process parameters. In this study, the prediction machining performance such as material removal rate (MRR) and tool wear rate (TWR) in EDM was conducted by using Matlab 7.6 (R2008a) NN Toolbox 6.0. The NN architecture that had been used in this project is multilayer feed forward with back propagation learning algorithm. The machining parameters, discharge current (I), pulse on time (Ton), and pulse off time (T0ff) was used as input data with MRR and TWR as output data. The experimental result with various machining and output parameters in this study was referred to journal of "Modeling of electrical discharge machining process using back propagation neural network and multi-objective optimization using non-dominating sorting genetic algorithm-II" by D. Mandal et al [21]. There are 78 experimental data that are used for training and testing with different number of hidden layer and nodes. The finest NN architecture is obtained by comparing their training and testing performance. From the experiment, network with 3-10-10-2 architecture was found to be the most suitable architecture to predict the MRR and TWR. The architecture will be a model that can be used to predict the machining output; MRR and TWR with a given input; Ton, T0ff and I, for C40 steel workpiece. 2009-11 Thesis NonPeerReviewed text en http://ir.uitm.edu.my/id/eprint/38954/1/38954.pdf Mohd Hanapiah, Zaid (2009) Prediction of material removal rate and tool wear rate in electrical discharge machining using feedforward neural network / Zaid Mohd Hanapiah. Degree thesis, Universiti Teknologi MARA.
institution	Universiti Teknologi Mara
building	Tun Abdul Razak Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Teknologi Mara
content_source	UiTM Institutional Repository
url_provider	http://ir.uitm.edu.my/
language	English
topic	Mechanics applied to machinery. Dynamics Machine design and drawing
spellingShingle	Mechanics applied to machinery. Dynamics Machine design and drawing Mohd Hanapiah, Zaid Prediction of material removal rate and tool wear rate in electrical discharge machining using feedforward neural network / Zaid Mohd Hanapiah.
description	Electrical discharge machining (EDM) is one of the widely used non-traditional machining techniques for manufacturing geometrically complex or hard material parts. The EDM process uses repeated electrical discharges between electrode and workpiece to remove material which are submerged in a dielectric medium. There are many researchers carried out investigation for improving the process performance by modeling the EDM process. Neural network (NN) is one of the most extensively used methods for prediction and modeling EDM process parameters. In this study, the prediction machining performance such as material removal rate (MRR) and tool wear rate (TWR) in EDM was conducted by using Matlab 7.6 (R2008a) NN Toolbox 6.0. The NN architecture that had been used in this project is multilayer feed forward with back propagation learning algorithm. The machining parameters, discharge current (I), pulse on time (Ton), and pulse off time (T0ff) was used as input data with MRR and TWR as output data. The experimental result with various machining and output parameters in this study was referred to journal of "Modeling of electrical discharge machining process using back propagation neural network and multi-objective optimization using non-dominating sorting genetic algorithm-II" by D. Mandal et al [21]. There are 78 experimental data that are used for training and testing with different number of hidden layer and nodes. The finest NN architecture is obtained by comparing their training and testing performance. From the experiment, network with 3-10-10-2 architecture was found to be the most suitable architecture to predict the MRR and TWR. The architecture will be a model that can be used to predict the machining output; MRR and TWR with a given input; Ton, T0ff and I, for C40 steel workpiece.
format	Thesis
author	Mohd Hanapiah, Zaid
author_facet	Mohd Hanapiah, Zaid
author_sort	Mohd Hanapiah, Zaid
title	Prediction of material removal rate and tool wear rate in electrical discharge machining using feedforward neural network / Zaid Mohd Hanapiah.
title_short	Prediction of material removal rate and tool wear rate in electrical discharge machining using feedforward neural network / Zaid Mohd Hanapiah.
title_full	Prediction of material removal rate and tool wear rate in electrical discharge machining using feedforward neural network / Zaid Mohd Hanapiah.
title_fullStr	Prediction of material removal rate and tool wear rate in electrical discharge machining using feedforward neural network / Zaid Mohd Hanapiah.
title_full_unstemmed	Prediction of material removal rate and tool wear rate in electrical discharge machining using feedforward neural network / Zaid Mohd Hanapiah.
title_sort	prediction of material removal rate and tool wear rate in electrical discharge machining using feedforward neural network / zaid mohd hanapiah.
publishDate	2009
url	http://ir.uitm.edu.my/id/eprint/38954/1/38954.pdf http://ir.uitm.edu.my/id/eprint/38954/
_version_	1685651619120676864
score	13.211869

Prediction of material removal rate and tool wear rate in electrical discharge machining using feedforward neural network / Zaid Mohd Hanapiah.

Similar Items