Welcome To UTPedia

We would like to introduce you, the new knowledge repository product called UTPedia. The UTP Electronic and Digital Intellectual Asset. It stores digitized version of thesis, dissertation, final year project reports and past year examination questions.

Browse content of UTPedia using Year, Subject, Department and Author and Search for required document using Searching facilities included in UTPedia. UTPedia with full text are accessible for all registered users, whereas only the physical information and metadata can be retrieved by public users. UTPedia collaborating and connecting peoples with university’s intellectual works from anywhere.

Disclaimer - Universiti Teknologi PETRONAS shall not be liable for any loss or damage caused by the usage of any information obtained from this web site.Best viewed using Mozilla Firefox 3 or IE 7 with resolution 1024 x 768.


Yahya, Muhammad Ariff (2007) NEURAL NETWORK APPLIED FOR THE FAULT DIAGNOSIS OF AN AC MOTOR. Universiti Teknologi PETRONAS. (Unpublished)

[img] PDF
Download (1136Kb)


There are many failures of AC motors in the industry for different reasons and huge losses are affected. This failure takes some time to happen and the cause slowly affects the motors. In this project report, the neural network comes with a solution to the problem. The neural networks able to diagnosis the incipient AC motors faults. The network collects all the possible causes to any failure and analyzes it with existing trained datato determine the statusof the motor. For example if the motorhaving degradation on the winding insulation resistance, the network will collect the status of the insulation resistance and compare it with the allowable value of the insulation resistance, thus the output states the future failure with the current value ofthe insulation resistance on the motor's winding. This project report covers onthree fault outputs which are bearing fault, winding fault and overheating fault. All these outputs depend on certain inputs where the inputs are the cause towards the failure. The artificial neural network has various types of usage. For the prediction purposes, feedfoward-back propagation network topology will be used. This topology will be is with appropriate training function. The training function for example, Resilient-Backpropagation will be trained and provides values for weights and biases of the network topology. The biases and weights are used to analyze any input fed to this network and come out with its prediction. Furthermore the project report also deals with MATLAB simulation and toolbox. TheMATLAB software is able to tolerate the neural networks where all the command and application are in MATLAB based.

Item Type: Final Year Project
Academic Subject : Academic Department - Electrical And Electronics - Pervasisve Systems - Digital Electronics - Prototyping
Subject: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Engineering > Electrical and Electronic
Depositing User: Users 2053 not found.
Date Deposited: 24 Oct 2013 14:48
Last Modified: 25 Jan 2017 09:45
URI: http://utpedia.utp.edu.my/id/eprint/9699

Actions (login required)

View Item View Item

Document Downloads

More statistics for this item...