Date of Award

3-10-2019

Publication Type

Master Thesis

Degree Name

M.A.Sc.

Department

Mechanical, Automotive, and Materials Engineering

First Advisor

Rupp Carriveau

Second Advisor

David Ting

Keywords

blades, condition monitoring, performance, SCADA, wind turbine

Rights

info:eu-repo/semantics/openAccess

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Abstract

As wind turbines continue to age, wind farm operators face the challenge of optimizing maintenance scheduling to reduce the associated operation and maintenance (O&M) costs. Wind farm operators typically use conservative maintenance scheduling in order to maximize the uptime of their wind turbines. In most cases however, maintenance may not be necessary and the components could operate for longer before repairs are required. This work presents three papers that collectively focus on providing potentially useful information to aid wind farm operators in making maintenance decisions. In the first paper, the utilization of Geographic Information Systems (GIS) to illustrate data trends across wind farms is introduced to better understand an operation’s signature performance characteristics. It is followed by a paper that presents an improved condition monitoring system for the wind turbine blades through the use of the principal component analysis (PCA). The final paper introduces another condition monitoring system using a k-means clustering algorithm to determine the performance state of wind turbine blades.

Share

COinS