Login | Register

Fault Detection and Isolation of Wind Turbines using Immune System Inspired Algorithms

Title:

Fault Detection and Isolation of Wind Turbines using Immune System Inspired Algorithms

AliZadeh, Esmaeil (2016) Fault Detection and Isolation of Wind Turbines using Immune System Inspired Algorithms. Masters thesis, Concordia University.

[thumbnail of AliZadeh_MASc_S2017.pdf]
Preview
Text (application/pdf)
AliZadeh_MASc_S2017.pdf - Accepted Version
Available under License Spectrum Terms of Access.
7MB

Abstract

Recently, the research focus on renewable sources of energy has been growing intensively. This is mainly due to potential depletion of fossil fuels and its associated environmental concerns, such as pollution and greenhouse gas emissions. Wind energy is one of the fastest growing sources of renewable energy, and policy makers in both developing and developed countries have built their vision on future energy supply based on and by emphasizing the wind power. The increase in the number of wind turbines, as well as their size, have led to undeniable care and attention to health and condition monitoring as well as fault diagnosis of wind turbine systems and their components.

In this thesis, two main immune inspired algorithms are used to perform Fault Detection and Isolation (FDI) of a Wind Turbine (WT), namely the Negative Selection Algorithm (NSA) as well as the Dendritic Cell Algorithm (DCA).

First, an NSA-based fault diagnosis methodology is proposed in which a hierarchical bank of NSAs is used to detect and isolate both individual as well as simultaneously occurring faults common to the wind turbines. A smoothing moving window filter is then utilized to further improve the reliability and performance of the proposed FDI scheme. Moreover, the performance of the proposed scheme is compared with the state-of-the-art data-driven technique, namely Support Vector Machine (SVM) to demonstrate and illustrate the superiority and advantages of the proposed NSA-based FDI scheme. Finally, a nonparametric statistical comparison test is implemented to evaluate the proposed methodology with that of the SVM under various fault severities.

In the second part, another immune inspired methodology, namely the Dendritic Cell Algorithm (DCA) is used to perform online sensor fault FDI. A noise filter is also designed to attenuate the measurement noise, resulting in better FDI results. The proposed DCA-based FDI scheme is then compared with the previously developed NSA-based FDI scheme, and a nonparametric statistical comparison test is also performed.

Both of the proposed immune inspired frameworks are applied to a well-known wind turbine benchmark model in order to validate the effectiveness of the proposed methodologies.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Electrical and Computer Engineering
Item Type:Thesis (Masters)
Authors:AliZadeh, Esmaeil
Institution:Concordia University
Degree Name:M.A. Sc.
Program:Electrical and Computer Engineering
Date:November 2016
Thesis Supervisor(s):Khorasani, Khashayar and Meskin, Nader
ID Code:982044
Deposited By: ESMAEIL ALI ZADEH
Deposited On:09 Jun 2017 14:05
Last Modified:18 Jan 2018 17:54
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top