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

Mahamad , Abd Kadir (2005) Monitoring and prediction of bearing failure by acoustic emission and neural network. Masters thesis, Kolej Universiti Teknologi Tun Hussein Onn.

[img]PDF
645Kb

Abstract

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 the 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.

Item Type:Thesis (Masters)
Subjects:T Technology > TJ Mechanical engineering and machinery
ID Code:745
Deposited By:Norfauzan Md Sarwin
Deposited On:04 Apr 2011 08:53
Last Modified:29 Apr 2011 14:41

Repository Staff Only: item control page