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, 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.

Self-Adaptive Autoreclosing Scheme usingI Artificial Neural Network and Taguchi's Methodology in Extra High Voltage Transmission Systems

Desta, Zahlay Fitiwi (2009) Self-Adaptive Autoreclosing Scheme usingI Artificial Neural Network and Taguchi's Methodology in Extra High Voltage Transmission Systems. Masters thesis, UNIVERSITI TEKNOLOGIPETRONAS.

[img] PDF
Download (4MB)


Conventional automatic reclosures blindly operate for permanent, semi-permanent or transient faults on an overhead line without any discrimination after allowing some estimated time delay. Reclosing onto a line with uncleared fault often results in, not only loss of stability and synchronism but also damage to system equipments, as a consequence. The thesis focuses on methods to discriminate a temporary fault from a permanent one, and accurately determine fault extinctiontime in an extra high voltage (EHV) transmission line in a bid to develop a self-adaptive automatic reclosing scheme. The fault identification prior to reclosing is based on optimized artificial neural network associated with three training algorithms, namely, Standard Error Back-Propagation, Levenberg Marquardt and Resilient Back-Propagation algorithms. In addition, Taguchi's methodology is employed in optimizing the parameters of each algorithm used for training, and in deciding the number of hidden neurons of the neural network. To get data for training the neural networks, a range of faults are simulated on two case studies -single machine -infinite bus model (connected via EHVtransmission line) and a benchmark IEEE 9-bus electric system. The spectra of the fault voltage data are analyzed using Fast Fourier Transform, and it has been found out that the DC, the fundamental and the first four harmonic components can sufficiently and uniquely represent the condition of each fault. In each case study, the neural network is fed with the normalized energies of the DC, the fundamental and the first four harmonics of the faulted voltages, effectively trained with a set of training data, and verified with a dedicated testing data obtained from fault voltage signals generated on IEEE 14-bus electric system model. The results show the efficacy of the developed adaptive automatic reclosing scheme. This effectively means it is possible to avoid reclosing before any fault on a transmission line (be it temporary or permanent) is totally cleared.

Item Type: Thesis (Masters)
Academic Subject : Academic Department - Electrical And Electronics - Pervasisve Systems - Digital Electronics - Design
Subject: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Engineering > Electrical and Electronic
Depositing User: Users 2053 not found.
Date Deposited: 22 Oct 2013 12:09
Last Modified: 22 Oct 2013 12:09
URI: http://utpedia.utp.edu.my/id/eprint/9392

Actions (login required)

View Item View Item

Document Downloads

More statistics for this item...