Author ORCID Identifier

https://orcid.org/0000-0001-7142-9347

Date Available

12-14-2022

Year of Publication

2022

Document Type

Master's Thesis

Degree Name

Master of Electrical Engineering (MEE)

College

Engineering

Department/School/Program

Electrical and Computer Engineering

Advisor

Dr. Yuan Liao

Abstract

Fault location remains an extremely pivotal feature of the electric power grid as it ensures efficient operation of the grid and prevents large downtimes during fault occurrences. This will ultimately enhance and increase the reliability of the system. Since the invention of the electric grid, many approaches to fault location have been studied and documented. These approaches are still effective and are implemented in present times, and as the power grid becomes even more broadened with new forms of energy generation, transmission, and distribution technologies, continued study on these methods is necessary. This thesis will focus on adopting the artificial neural network method for fault location for a high-impedance grounded system, where fault currents are small for single phase to ground faults. This approach will be performed on a single 2-terminal distribution network. This thesis will also give a comprehensive explanation on the process of developing artificial neural networks (ANN) using MATLAB’s neural network app designers. The main objective of the experimental approach is to investigate the effects of different variations in ANN structures (such as number of neurons, number of hidden layers, input features, and data preprocessing) on predicting fault locations. Study results from the simulations have been presented to show performance of each ANN structure for fault location on the sample distribution system.

Digital Object Identifier (DOI)

https://doi.org/10.13023/etd.2022.408

Download

Share

COinS