A Machine Learning Method for Modeling Wind Farm Fatigue Load
Wake steering control can significantly improve the overall power production of wind farms. However, it also increases fatigue damage on downstream wind turbines. Therefore, optimizing fatigue loads in wake steering control has become a hot research topic. Accurately predicting farm fatigue loads ha...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-07-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/15/7392 |
_version_ | 1797414819478896640 |
---|---|
author | Yizhi Miao Mohsen N. Soltani Amin Hajizadeh |
author_facet | Yizhi Miao Mohsen N. Soltani Amin Hajizadeh |
author_sort | Yizhi Miao |
collection | DOAJ |
description | Wake steering control can significantly improve the overall power production of wind farms. However, it also increases fatigue damage on downstream wind turbines. Therefore, optimizing fatigue loads in wake steering control has become a hot research topic. Accurately predicting farm fatigue loads has always been challenging. The current interpolation method for farm-level fatigue loads estimation is also known as the look-up table (LUT) method. However, the LUT method is less accurate because it is challenging to map the highly nonlinear characteristics of fatigue load. This paper proposes a machine-learning algorithm based on the Gaussian process (GP) to predict the farm-level fatigue load under yaw misalignment. Firstly, a series of simulations with yaw misalignment were designed to obtain the original load data, which considered the wake interaction between turbines. Secondly, the rainflow counting and Palmgren miner rules were introduced to transfer the original load to damage equivalent load. Finally, the GP model trained by inputs and outputs predicts the fatigue load. GP has more accurate predictions because it is suitable for mapping the nonlinear between fatigue load and yaw misalignment. The case study shows that compared to LUT, the accuracy of GP improves by 17% (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>R</mi><mi>M</mi><mi>S</mi><mi>E</mi></mrow></semantics></math></inline-formula>) and 0.6% (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>M</mi><mi>A</mi><mi>E</mi></mrow></semantics></math></inline-formula>) at the blade root edgewise moment and 51.87% (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>R</mi><mi>M</mi><mi>S</mi><mi>E</mi></mrow></semantics></math></inline-formula>) and 1.78% (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>M</mi><mi>A</mi><mi>E</mi></mrow></semantics></math></inline-formula>) at the blade root flapwise moment. |
first_indexed | 2024-03-09T05:39:30Z |
format | Article |
id | doaj.art-bf05fce5b9ff47e6b05010ea62487b32 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-09T05:39:30Z |
publishDate | 2022-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-bf05fce5b9ff47e6b05010ea62487b322023-12-03T12:26:38ZengMDPI AGApplied Sciences2076-34172022-07-011215739210.3390/app12157392A Machine Learning Method for Modeling Wind Farm Fatigue LoadYizhi Miao0Mohsen N. Soltani1Amin Hajizadeh2AAU Energy, Aalborg University, 6700 Esbjerg, DenmarkAAU Energy, Aalborg University, 6700 Esbjerg, DenmarkAAU Energy, Aalborg University, 6700 Esbjerg, DenmarkWake steering control can significantly improve the overall power production of wind farms. However, it also increases fatigue damage on downstream wind turbines. Therefore, optimizing fatigue loads in wake steering control has become a hot research topic. Accurately predicting farm fatigue loads has always been challenging. The current interpolation method for farm-level fatigue loads estimation is also known as the look-up table (LUT) method. However, the LUT method is less accurate because it is challenging to map the highly nonlinear characteristics of fatigue load. This paper proposes a machine-learning algorithm based on the Gaussian process (GP) to predict the farm-level fatigue load under yaw misalignment. Firstly, a series of simulations with yaw misalignment were designed to obtain the original load data, which considered the wake interaction between turbines. Secondly, the rainflow counting and Palmgren miner rules were introduced to transfer the original load to damage equivalent load. Finally, the GP model trained by inputs and outputs predicts the fatigue load. GP has more accurate predictions because it is suitable for mapping the nonlinear between fatigue load and yaw misalignment. The case study shows that compared to LUT, the accuracy of GP improves by 17% (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>R</mi><mi>M</mi><mi>S</mi><mi>E</mi></mrow></semantics></math></inline-formula>) and 0.6% (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>M</mi><mi>A</mi><mi>E</mi></mrow></semantics></math></inline-formula>) at the blade root edgewise moment and 51.87% (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>R</mi><mi>M</mi><mi>S</mi><mi>E</mi></mrow></semantics></math></inline-formula>) and 1.78% (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>M</mi><mi>A</mi><mi>E</mi></mrow></semantics></math></inline-formula>) at the blade root flapwise moment.https://www.mdpi.com/2076-3417/12/15/7392machine learningGaussian processdamage equivalent load |
spellingShingle | Yizhi Miao Mohsen N. Soltani Amin Hajizadeh A Machine Learning Method for Modeling Wind Farm Fatigue Load Applied Sciences machine learning Gaussian process damage equivalent load |
title | A Machine Learning Method for Modeling Wind Farm Fatigue Load |
title_full | A Machine Learning Method for Modeling Wind Farm Fatigue Load |
title_fullStr | A Machine Learning Method for Modeling Wind Farm Fatigue Load |
title_full_unstemmed | A Machine Learning Method for Modeling Wind Farm Fatigue Load |
title_short | A Machine Learning Method for Modeling Wind Farm Fatigue Load |
title_sort | machine learning method for modeling wind farm fatigue load |
topic | machine learning Gaussian process damage equivalent load |
url | https://www.mdpi.com/2076-3417/12/15/7392 |
work_keys_str_mv | AT yizhimiao amachinelearningmethodformodelingwindfarmfatigueload AT mohsennsoltani amachinelearningmethodformodelingwindfarmfatigueload AT aminhajizadeh amachinelearningmethodformodelingwindfarmfatigueload AT yizhimiao machinelearningmethodformodelingwindfarmfatigueload AT mohsennsoltani machinelearningmethodformodelingwindfarmfatigueload AT aminhajizadeh machinelearningmethodformodelingwindfarmfatigueload |