Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Identification of ice mass accumulated on wind turbine blades using its natural frequencies:

Identification of ice mass accumulated on wind turbine blades using its natural frequencies: This work demonstrates a technique to identify information about the ice mass accumulation on wind turbine blades using its natural frequencies, and these frequencies reduce differently depending on the spatial distribution of ice mass along the blade length. An explicit relation to the natural frequencies of a 1-kW wind turbine blade is defined in terms of the location and quantity of ice mass using experimental modal analyses. An artificial neural network model is trained with a data set (natural frequencies and ice masses) generated using that explicit relation. After training, this artificial neural network model is given an input of natural frequencies of the iced blade (identified from experimental modal analysis) corresponding to 18 test cases, and it identified ice masses’ location and quantity with a weighted average percentage error value of 17.53%. The proposed technique is also demonstrated on the NREL 5-MW wind turbine blade data. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Wind Engineering SAGE

Identification of ice mass accumulated on wind turbine blades using its natural frequencies:

Loading next page...
 
/lp/sage/identification-of-ice-mass-accumulated-on-wind-turbine-blades-using-foJqNCxP0O
Publisher
SAGE
Copyright
Copyright © 2022 by SAGE Publications
ISSN
0309-524X
eISSN
2048-402X
DOI
10.1177/0309524x17723207
Publisher site
See Article on Publisher Site

Abstract

This work demonstrates a technique to identify information about the ice mass accumulation on wind turbine blades using its natural frequencies, and these frequencies reduce differently depending on the spatial distribution of ice mass along the blade length. An explicit relation to the natural frequencies of a 1-kW wind turbine blade is defined in terms of the location and quantity of ice mass using experimental modal analyses. An artificial neural network model is trained with a data set (natural frequencies and ice masses) generated using that explicit relation. After training, this artificial neural network model is given an input of natural frequencies of the iced blade (identified from experimental modal analysis) corresponding to 18 test cases, and it identified ice masses’ location and quantity with a weighted average percentage error value of 17.53%. The proposed technique is also demonstrated on the NREL 5-MW wind turbine blade data.

Journal

Wind EngineeringSAGE

Published: Aug 21, 2017

Keywords: Wind turbine blade; ice detection; natural frequency; experimental modal analysis; artificial neural network

There are no references for this article.