Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Investigating How an Artificial Neural Network Model Can Be Used to Detect Added Mass on a Non-Rotating Beam Using Its Natural Frequencies: A Possible Application for Wind Turbine Blade Ice Detection
Luleå University of Technology, Department of Engineering Sciences and Mathematics, Product and Production Development.ORCID iD: 0000-0001-8216-9464
Luleå University of Technology, Department of Engineering Sciences and Mathematics, Product and Production Development.
Luleå University of Technology, Department of Engineering Sciences and Mathematics, Product and Production Development.ORCID iD: 0000-0001-6016-6342
Number of Authors: 32017 (English)In: Energies, ISSN 1996-1073, E-ISSN 1996-1073, Vol. 10, no 2, article id 184Article in journal (Refereed) Published
Abstract [en]

Structures vibrate with their natural frequencies when disturbed from their equilibrium position. These frequencies reduce when an additional mass accumulates on their structures, like ice accumulation on wind turbines installed in cold climate sites. The added mass has two features: the location and quantity of mass. Natural frequencies of the structure reduce differently depending on these two features of the added mass. In this work, a technique based on an artificial neural network (ANN) model is proposed to identify added mass by training the neural network with a dataset of natural frequencies of the structure calculated using different quantities of the added mass at different locations on the structure. The proposed method is demonstrated on a non-rotating beam model fixed at one end. The length of the beam is divided into three zones in which different added masses are considered, and its natural frequencies are calculated using a finite element model of the beam. ANN is trained with this dataset of natural frequencies of the beam as an input and corresponding added masses used in the calculations as an output. ANN approximates the non-linear relationship between these inputs and outputs. An experimental setup of the cantilever beam is fabricated, and experimental modal analysis is carried out considering a few added masses on the beam. The frequencies estimated in the experiments are given as an input to the trained ANN model, and the identified masses are compared against the actual masses used in the experiments. These masses are identified with an error that varies with the location and the quantity of added mass. The reason for these errors can be attributed to the unaccounted stiffness variation in the beam model due to the added mass while generating the dataset for training the neural network. Therefore, the added masses are roughly estimated. At the end of the paper, an application of the current technique for detecting ice mass on a wind turbine blade is studied. A neural network model is designed and trained with a dataset of natural frequencies calculated using the finite element model of the blade considering different ice masses. The trained network model is tested to identify ice masses in four test cases that considers random mass distributions along the blade. The neural network model is able to roughly estimate ice masses, and the error reduces with increasing ice mass on the blade.

Place, publisher, year, edition, pages
MDPI, 2017. Vol. 10, no 2, article id 184
Keywords [en]
artificial neural network, ice mass, detection, wind turbine blade, natural frequency
National Category
Applied Mechanics Other Mechanical Engineering
Research subject
Computer Aided Design
Identifiers
URN: urn:nbn:se:ltu:diva-61885DOI: 10.3390/en10020184ISI: 000395469200038Scopus ID: 2-s2.0-85014095862OAI: oai:DiVA.org:ltu-61885DiVA, id: diva2:1072923
Projects
Wind power in cold climates
Funder
Swedish Energy Agency
Note

Validerad; 2017; Nivå 2; 2017-02-15 (andbra)

Available from: 2017-02-09 Created: 2017-02-09 Last updated: 2019-10-21Bibliographically approved
In thesis
1. Detection of blade icing and its influence on wind turbine vibrations
Open this publication in new window or tab >>Detection of blade icing and its influence on wind turbine vibrations
2019 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Wind turbine installations in extreme conditions like cold climate have increased over thelast few years and expected to grow in future in North America, Europe, and Asia regions due to good wind resources and land availability. Their installed capacity could reach 186 GW by the end of 2020. The cold climate sites impose the risk of ice accumulation on turbines during the winter due to the humidity at low temperatures. Since the atmospheric and operating conditions of the wind turbine leading to blade icing vary stochastically in space and time, the resulting ice accumulation is completely random, it is even different for turbines within the same site. Ice accumulation alters aerofoil shapes of the blade, affecting their aeroelastic behavior. The icing severity at different locations of the blade and their non-uniform distribution on blades have a distinct influence on turbine power output and vibrations. The current thesis proposes a methodology to investigate such behavior of wind turbines by considering the structural and aerodynamic property changes in the blade due to icing. An automated procedure is used to scale simulated/measured ice shape on aerofoil sections of the blade according to a specified ice mass distribution. The aeroelastic behavior of the blades is simulated considering the static aerodynamic coefficients of the iced aerofoil sections. The proposed methodology is demonstrated on the National Renewable Energy Laboratory (NREL) 5 MW baseline wind turbine model. The method can be leveraged to analyze the influence of icing on any wind turbine model. De/Anti-icing systems are installed on the turbines to mitigate the risks associated with icing. It is essential to detect icing at the early stage and initiate these systems to avoid production losses and limit the risks associated with ice throw. Ice accumulation increases blade mass and its spatial distribution changes natural frequencies of the blade. A detection technique is proposed in this thesis to characterize ice mass distribution on the blades based on its natural frequencies. The detection technique is validated using experiments on a small-scale cantilever beam and 1-kW wind turbine blade set-ups and its effectiveness is also verified on large-scale wind turbine blades using numerical models. The proposed technique has the potential for detecting ice masses on large wind turbines operating in cold climate as it requires only first few natural frequencies of the blade. These natural frequencies are usually excited by the turbulent wind in operation/standstill conditions and they can be estimated from the vibration measurements of the blade.

Place, publisher, year, edition, pages
Luleå University of Technology, 2019
Series
Doctoral thesis / Luleå University of Technology 1 jan 1997 → …, ISSN 1402-1544
National Category
Applied Mechanics Other Mechanical Engineering
Research subject
Computer Aided Design
Identifiers
urn:nbn:se:ltu:diva-76460 (URN)978-91-7790-482-3 (ISBN)978-91-7790-483-0 (ISBN)
Public defence
2019-12-06, E632, Lulea, 09:00 (English)
Opponent
Supervisors
Available from: 2019-10-22 Created: 2019-10-21 Last updated: 2019-11-14Bibliographically approved

Open Access in DiVA

fulltext(2562 kB)331 downloads
File information
File name FULLTEXT01.pdfFile size 2562 kBChecksum SHA-512
36e5fa7da3945e46de7e8f3842de9b191ca2c10f895b42ed5b185dafabef55cd5cffe3df7c0a642dc119153cb3ccaefc43d994140a353b4ead64a7493c3fd6b6
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records BETA

Gantasala, SudhakarLuneno, Jean-ClaudeAidanpää, Jan-Olov

Search in DiVA

By author/editor
Gantasala, SudhakarLuneno, Jean-ClaudeAidanpää, Jan-Olov
By organisation
Product and Production Development
In the same journal
Energies
Applied MechanicsOther Mechanical Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 331 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 552 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf