Monitoring and prediction of bearing failure by acoustic emission and neural network

The purpose of this research is to develop an appropriate ANN model of bearing failure prediction. Acoustic emission (AE) represented the technique of collecting the data that was collected from the bearing and this data were measured in term of decibel (dB) and Distress level. The data was th...

Full description

Saved in:

Bibliographic Details
Main Author:	Mahamad, Abd Kadir
Format:	Thesis
Language:	English English English
Published:	2005
Subjects:	TJ Mechanical engineering and machinery TJ1040-1119 Machinery exclusive of prime movers
Online Access:	http://eprints.uthm.edu.my/7938/1/24p%20ABD%20KADIR%20MAHAMAD.pdf http://eprints.uthm.edu.my/7938/2/ABD%20KADIR%20MAHAMAD%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/7938/3/ABD%20KADIR%20MAHAMAD%20WATERMARK.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uthm-ep.7938
record_format	uketd_dc
spelling	my-uthm-ep.79382022-10-30T08:05:38Z Monitoring and prediction of bearing failure by acoustic emission and neural network 2005-03 Mahamad, Abd Kadir TJ Mechanical engineering and machinery TJ1040-1119 Machinery exclusive of prime movers The purpose of this research is to develop an appropriate ANN model of bearing failure prediction. Acoustic emission (AE) represented the technique of collecting the data that was collected from the bearing and this data were measured in term of decibel (dB) and Distress level. The data was then used to develop thc model using ANN for bearing fault prediction model. An experimental rig was setup to collect data on bearing by using Machine Health Checker (MI-IC) Memo assist with MHC Analysis software. In the development of ANN modeling, the result obtained shows that the optimum model was Elman network with training algorithm. Levenberg-Marquardt Back-propagation and the suitable transfer function for hidden node and output node was logsig/purelin combination. Four models were built in this research for multiple step ahead prediction, that were one day ahead model (Modell), seven days ahead model (Model 2), fourteen days ahead (Model 3) and thirty days ahead model (Model 4). In the application part, a computer program was written on bearing failure prediction. This program was implementcd using graphical user interface (OUI) features that can be implemented by using a MA TLAB OUr. In the end, the user was able to use this program as a tool to operate or simulate bcaring failure prediction 2005-03 Thesis http://eprints.uthm.edu.my/7938/ http://eprints.uthm.edu.my/7938/1/24p%20ABD%20KADIR%20MAHAMAD.pdf text en public http://eprints.uthm.edu.my/7938/2/ABD%20KADIR%20MAHAMAD%20COPYRIGHT%20DECLARATION.pdf text en staffonly http://eprints.uthm.edu.my/7938/3/ABD%20KADIR%20MAHAMAD%20WATERMARK.pdf text en validuser mphil masters Kolej Universiti Teknologi Tun Hussein Onn Fakulti Kejuruteraan Elektrik dan Elektronik
institution	Universiti Tun Hussein Onn Malaysia
collection	UTHM Institutional Repository
language	English English English
topic	TJ Mechanical engineering and machinery TJ1040-1119 Machinery exclusive of prime movers
spellingShingle	TJ Mechanical engineering and machinery TJ1040-1119 Machinery exclusive of prime movers Mahamad, Abd Kadir Monitoring and prediction of bearing failure by acoustic emission and neural network
description	The purpose of this research is to develop an appropriate ANN model of bearing failure prediction. Acoustic emission (AE) represented the technique of collecting the data that was collected from the bearing and this data were measured in term of decibel (dB) and Distress level. The data was then used to develop thc model using ANN for bearing fault prediction model. An experimental rig was setup to collect data on bearing by using Machine Health Checker (MI-IC) Memo assist with MHC Analysis software. In the development of ANN modeling, the result obtained shows that the optimum model was Elman network with training algorithm. Levenberg-Marquardt Back-propagation and the suitable transfer function for hidden node and output node was logsig/purelin combination. Four models were built in this research for multiple step ahead prediction, that were one day ahead model (Modell), seven days ahead model (Model 2), fourteen days ahead (Model 3) and thirty days ahead model (Model 4). In the application part, a computer program was written on bearing failure prediction. This program was implementcd using graphical user interface (OUI) features that can be implemented by using a MA TLAB OUr. In the end, the user was able to use this program as a tool to operate or simulate bcaring failure prediction
format	Thesis
qualification_name	Master of Philosophy (M.Phil.)
qualification_level	Master's degree
author	Mahamad, Abd Kadir
author_facet	Mahamad, Abd Kadir
author_sort	Mahamad, Abd Kadir
title	Monitoring and prediction of bearing failure by acoustic emission and neural network
title_short	Monitoring and prediction of bearing failure by acoustic emission and neural network
title_full	Monitoring and prediction of bearing failure by acoustic emission and neural network
title_fullStr	Monitoring and prediction of bearing failure by acoustic emission and neural network
title_full_unstemmed	Monitoring and prediction of bearing failure by acoustic emission and neural network
title_sort	monitoring and prediction of bearing failure by acoustic emission and neural network
granting_institution	Kolej Universiti Teknologi Tun Hussein Onn
granting_department	Fakulti Kejuruteraan Elektrik dan Elektronik
publishDate	2005
url	http://eprints.uthm.edu.my/7938/1/24p%20ABD%20KADIR%20MAHAMAD.pdf http://eprints.uthm.edu.my/7938/2/ABD%20KADIR%20MAHAMAD%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/7938/3/ABD%20KADIR%20MAHAMAD%20WATERMARK.pdf
_version_	1776103274074603520

Monitoring and prediction of bearing failure by acoustic emission and neural network

Similar Items