Abstract

This research will investigate the use of Machine Learning techniques in various applications within the field of Wind Energy The general approach to Machine Learning follows the steps shown on the right Model selection is done through literature review, which depends on the data used This data is then processed and cleaned, through clustering and removal of outliers Features are extracted from the data, either from univariate statistics to find the feature with the least variance from the target, or PCA to reduce the number of features to two abstract features with no physical meaning This data is then used to train and test the model(s) The results produced are then analysed, either using existing alarm data, or through k folds cross validation These results can also inform on model selection

Conference

ConferenceFuture Wind and Marine
CountryUnited Kingdom
CityGlasgow
Period7/03/19 → …

Fingerprint

Wind turbines
Learning systems
Wind power
Statistics

Keywords

  • machine learning
  • anomaly detection techniques
  • operations & maintenance
  • neural networks
  • One Class Support Vector Machines (OCSVM)

Cite this

Mckinnon, C., Carroll, J., McDonald, A., & Koukoura, S. (2019). Machine learning in wind turbine O&M. Poster session presented at Future Wind and Marine, Glasgow, United Kingdom.
Mckinnon, Conor ; Carroll, James ; McDonald, Alasdair ; Koukoura, Sofia. / Machine learning in wind turbine O&M. Poster session presented at Future Wind and Marine, Glasgow, United Kingdom.
@conference{7ed16e1cb5134a11b2d27e9fb76db447,
title = "Machine learning in wind turbine O&M",
abstract = "This research will investigate the use of Machine Learning techniques in various applications within the field of Wind Energy The general approach to Machine Learning follows the steps shown on the right Model selection is done through literature review, which depends on the data used This data is then processed and cleaned, through clustering and removal of outliers Features are extracted from the data, either from univariate statistics to find the feature with the least variance from the target, or PCA to reduce the number of features to two abstract features with no physical meaning This data is then used to train and test the model(s) The results produced are then analysed, either using existing alarm data, or through k folds cross validation These results can also inform on model selection",
keywords = "machine learning, anomaly detection techniques, operations & maintenance, neural networks, One Class Support Vector Machines (OCSVM)",
author = "Conor Mckinnon and James Carroll and Alasdair McDonald and Sofia Koukoura",
year = "2019",
month = "3",
day = "7",
language = "English",
note = "Future Wind and Marine ; Conference date: 07-03-2019",

}

Mckinnon, C, Carroll, J, McDonald, A & Koukoura, S 2019, 'Machine learning in wind turbine O&M' Future Wind and Marine, Glasgow, United Kingdom, 7/03/19, .

Machine learning in wind turbine O&M. / Mckinnon, Conor; Carroll, James; McDonald, Alasdair; Koukoura, Sofia.

2019. Poster session presented at Future Wind and Marine, Glasgow, United Kingdom.

Research output: Contribution to conferencePoster

TY - CONF

T1 - Machine learning in wind turbine O&M

AU - Mckinnon, Conor

AU - Carroll, James

AU - McDonald, Alasdair

AU - Koukoura, Sofia

PY - 2019/3/7

Y1 - 2019/3/7

N2 - This research will investigate the use of Machine Learning techniques in various applications within the field of Wind Energy The general approach to Machine Learning follows the steps shown on the right Model selection is done through literature review, which depends on the data used This data is then processed and cleaned, through clustering and removal of outliers Features are extracted from the data, either from univariate statistics to find the feature with the least variance from the target, or PCA to reduce the number of features to two abstract features with no physical meaning This data is then used to train and test the model(s) The results produced are then analysed, either using existing alarm data, or through k folds cross validation These results can also inform on model selection

AB - This research will investigate the use of Machine Learning techniques in various applications within the field of Wind Energy The general approach to Machine Learning follows the steps shown on the right Model selection is done through literature review, which depends on the data used This data is then processed and cleaned, through clustering and removal of outliers Features are extracted from the data, either from univariate statistics to find the feature with the least variance from the target, or PCA to reduce the number of features to two abstract features with no physical meaning This data is then used to train and test the model(s) The results produced are then analysed, either using existing alarm data, or through k folds cross validation These results can also inform on model selection

KW - machine learning

KW - anomaly detection techniques

KW - operations & maintenance

KW - neural networks

KW - One Class Support Vector Machines (OCSVM)

M3 - Poster

ER -

Mckinnon C, Carroll J, McDonald A, Koukoura S. Machine learning in wind turbine O&M. 2019. Poster session presented at Future Wind and Marine, Glasgow, United Kingdom.