Use of Digital Image Correlation and Machine Learning for the Optimal Strain Placement in a Full Scale Composite Tidal Turbine Blade

Jude McLoughlin; Marek Munko; Miguel Angel Valdivia Camacho; Fergus Cuthill; Sergio Lopez Dubon

doi:10.1784/cm2023.2d4

Use of Digital Image Correlation and Machine Learning for the Optimal Strain Placement in a Full Scale Composite Tidal Turbine Blade

Jude McLoughlin, Marek Munko, Miguel Angel Valdivia Camacho, Fergus Cuthill, Sergio Lopez Dubon^*

^*Corresponding author for this work

School of Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

One of the challenges testing and health monitoring of large structures represents is obtaining as much information as possible from a specimen with a limited number of sensors. In this work, a data-driven approach was pursued to decide the optimal location of single-point strain gauges using machine learning algorithms (MLAs) and information from digital image correlation (DIC) measurements. The optimal strain gauge placement was computed for a range of sensor numbers and the presence of sensors in the high-gradient regions was identified. Strain maps of almost 40,000 measurements were reconstructed successfully with fewer than twenty measured values using the method employed. However, certain loss of image contrast was identified, which is likely to have resulted from the treatment of non-numerical values.

Original language	English
Title of host publication	Nineteenth International Conference on Condition Monitoring and Asset Management
Publisher	British Institute of Non-Destructive Testing
Number of pages	12
ISBN (Electronic)	978 0 903132 81 7
DOIs	https://doi.org/10.1784/cm2023.2d4
Publication status	E-pub ahead of print - 17 Sept 2023
Event	Nineteenth International Conference on Condition Monitoring and Asset Management: The Future of Condition Monitoring - Northampton, United Kingdom Duration: 12 Sept 2023 → 14 Oct 2023 https://www.bindt.org/events-and-awards/cm-2023/

Conference

Conference	Nineteenth International Conference on Condition Monitoring and Asset Management
Abbreviated title	CM 2023
Country/Territory	United Kingdom
City	Northampton
Period	12/09/23 → 14/10/23
Internet address	https://www.bindt.org/events-and-awards/cm-2023/

Access to Document

10.1784/cm2023.2d4

2D4-FULL.Lopez.Dubon Sergio

Cite this

McLoughlin, J., Munko, M., Valdivia Camacho, M. A., Cuthill, F., & Lopez Dubon, S. (2023). Use of Digital Image Correlation and Machine Learning for the Optimal Strain Placement in a Full Scale Composite Tidal Turbine Blade. In Nineteenth International Conference on Condition Monitoring and Asset Management British Institute of Non-Destructive Testing. Advance online publication. https://doi.org/10.1784/cm2023.2d4

@inproceedings{7b29d7331b5f4989aea896b03c7f3180,

title = "Use of Digital Image Correlation and Machine Learning for the Optimal Strain Placement in a Full Scale Composite Tidal Turbine Blade",

abstract = "One of the challenges testing and health monitoring of large structures represents is obtaining as much information as possible from a specimen with a limited number of sensors. In this work, a data-driven approach was pursued to decide the optimal location of single-point strain gauges using machine learning algorithms (MLAs) and information from digital image correlation (DIC) measurements. The optimal strain gauge placement was computed for a range of sensor numbers and the presence of sensors in the high-gradient regions was identified. Strain maps of almost 40,000 measurements were reconstructed successfully with fewer than twenty measured values using the method employed. However, certain loss of image contrast was identified, which is likely to have resulted from the treatment of non-numerical values.",

author = "Jude McLoughlin and Marek Munko and {Valdivia Camacho}, {Miguel Angel} and Fergus Cuthill and {Lopez Dubon}, Sergio",

note = "Funding Information: Sergio Lopez Dubon: This project has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Sk{\l}odowska-Curie grant agreement No 801215 and the University of Edinburgh Data-Driven Innovation programme, part of the Edinburgh and South East Scotland City Region Deal. Marek Jan Munko: The doctoral research project has been funded by Babcock International and The Data Lab. All authors: The authors also wish to thank the Supergen ORE Hub for funding received through the Flexible Fund Award FF2020-1063. Publisher Copyright: Copyright {\textcopyright} 2023 International Conference on Condition Monitoring and Asset Management; Nineteenth International Conference on Condition Monitoring and Asset Management : The Future of Condition Monitoring, CM 2023 ; Conference date: 12-09-2023 Through 14-10-2023",

year = "2023",

month = sep,

day = "17",

doi = "10.1784/cm2023.2d4",

language = "English",

booktitle = "Nineteenth International Conference on Condition Monitoring and Asset Management",

publisher = "British Institute of Non-Destructive Testing",

address = "United Kingdom",

url = "https://www.bindt.org/events-and-awards/cm-2023/",

}

McLoughlin, J, Munko, M, Valdivia Camacho, MA, Cuthill, F & Lopez Dubon, S 2023, Use of Digital Image Correlation and Machine Learning for the Optimal Strain Placement in a Full Scale Composite Tidal Turbine Blade. in Nineteenth International Conference on Condition Monitoring and Asset Management. British Institute of Non-Destructive Testing, Nineteenth International Conference on Condition Monitoring and Asset Management, Northampton, United Kingdom, 12/09/23. https://doi.org/10.1784/cm2023.2d4

Use of Digital Image Correlation and Machine Learning for the Optimal Strain Placement in a Full Scale Composite Tidal Turbine Blade. / McLoughlin, Jude; Munko, Marek; Valdivia Camacho, Miguel Angel et al.
Nineteenth International Conference on Condition Monitoring and Asset Management. British Institute of Non-Destructive Testing, 2023.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Use of Digital Image Correlation and Machine Learning for the Optimal Strain Placement in a Full Scale Composite Tidal Turbine Blade

AU - McLoughlin, Jude

AU - Munko, Marek

AU - Valdivia Camacho, Miguel Angel

AU - Cuthill, Fergus

AU - Lopez Dubon, Sergio

N1 - Funding Information: Sergio Lopez Dubon: This project has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 801215 and the University of Edinburgh Data-Driven Innovation programme, part of the Edinburgh and South East Scotland City Region Deal. Marek Jan Munko: The doctoral research project has been funded by Babcock International and The Data Lab. All authors: The authors also wish to thank the Supergen ORE Hub for funding received through the Flexible Fund Award FF2020-1063. Publisher Copyright: Copyright © 2023 International Conference on Condition Monitoring and Asset Management

PY - 2023/9/17

Y1 - 2023/9/17

N2 - One of the challenges testing and health monitoring of large structures represents is obtaining as much information as possible from a specimen with a limited number of sensors. In this work, a data-driven approach was pursued to decide the optimal location of single-point strain gauges using machine learning algorithms (MLAs) and information from digital image correlation (DIC) measurements. The optimal strain gauge placement was computed for a range of sensor numbers and the presence of sensors in the high-gradient regions was identified. Strain maps of almost 40,000 measurements were reconstructed successfully with fewer than twenty measured values using the method employed. However, certain loss of image contrast was identified, which is likely to have resulted from the treatment of non-numerical values.

AB - One of the challenges testing and health monitoring of large structures represents is obtaining as much information as possible from a specimen with a limited number of sensors. In this work, a data-driven approach was pursued to decide the optimal location of single-point strain gauges using machine learning algorithms (MLAs) and information from digital image correlation (DIC) measurements. The optimal strain gauge placement was computed for a range of sensor numbers and the presence of sensors in the high-gradient regions was identified. Strain maps of almost 40,000 measurements were reconstructed successfully with fewer than twenty measured values using the method employed. However, certain loss of image contrast was identified, which is likely to have resulted from the treatment of non-numerical values.

UR - https://www.bindt.org/events-and-awards/cm-2023/abstract-2d4/

UR - https://www.bindt.org/shopbindt/conference-proceedings/proceedings-of-cm-2023.html

U2 - 10.1784/cm2023.2d4

DO - 10.1784/cm2023.2d4

M3 - Conference contribution

BT - Nineteenth International Conference on Condition Monitoring and Asset Management

PB - British Institute of Non-Destructive Testing

T2 - Nineteenth International Conference on Condition Monitoring and Asset Management

Y2 - 12 September 2023 through 14 October 2023

ER -

McLoughlin J, Munko M, Valdivia Camacho MA, Cuthill F , Lopez Dubon S. Use of Digital Image Correlation and Machine Learning for the Optimal Strain Placement in a Full Scale Composite Tidal Turbine Blade. In Nineteenth International Conference on Condition Monitoring and Asset Management. British Institute of Non-Destructive Testing. 2023 Epub 2023 Sept 17. doi: 10.1784/cm2023.2d4

Use of Digital Image Correlation and Machine Learning for the Optimal Strain Placement in a Full Scale Composite Tidal Turbine Blade

Abstract

Conference

Access to Document

Other files and links

Fingerprint

TRAIN@Ed: Transnational Research and Innovation Network at Edinburgh

Cite this

Use of Digital Image Correlation and Machine Learning for the Optimal Strain Placement in a Full Scale Composite Tidal Turbine Blade

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Projects

TRAIN@Ed: Transnational Research and Innovation Network at Edinburgh

Cite this