Virtual sensors for wind turbines with machine learning‐based time series models
Abstract Modern wind turbines have multiple sensors installed and provide constant data stream outputs; however, there are some important quantities where installing physical sensors is either impractical or the sensor technology is not sufficiently advanced. An example of such a problem is, for exa...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-09-01
|
| Series: | Wind Energy |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/we.2762 |
| _version_ | 1811322093749403648 |
|---|---|
| author | Nikolay Dimitrov Tuhfe Göçmen |
| author_facet | Nikolay Dimitrov Tuhfe Göçmen |
| author_sort | Nikolay Dimitrov |
| collection | DOAJ |
| description | Abstract Modern wind turbines have multiple sensors installed and provide constant data stream outputs; however, there are some important quantities where installing physical sensors is either impractical or the sensor technology is not sufficiently advanced. An example of such a problem is, for example, sensing the shape and location of wake‐induced wind deficits caused by upwind turbines—a feature which would have relevant application in wind farm control; however, it is hard to detect physically due to the need of scanning the airflow in front of the turbine in multiple locations. Another control‐related example is monitoring and predicting the blade tip‐tower clearance. A “virtual sensor” can be created instead, by establishing a mathematical relationship between the quantity of interest and other, measurable quantities such as readings from already available sensors (e.g., SCADA, lidars, and met‐masts). Machine Learning (ML) approaches are suitable for this task as ML algorithms are capable of learning and representing complex relationships. This study details the concept of ML‐based virtual sensors and showcases three specific examples: blade root bending moment prediction, detection of wind turbine wake center location, and forecasting of blade tip‐tower clearance. All examples utilize sequence models (Long Short‐Term Memory, LSTM) and use aeroelastic load simulations to generate wind turbine response time series and test model performance. The data types used in the examples correspond to channels that would be available from high‐frequency SCADA data combined with a blade and tower load measurement system. The resulting model performance demonstrates the feasibility of the ML‐based virtual sensor approach. |
| first_indexed | 2024-04-13T13:29:04Z |
| format | Article |
| id | doaj.art-2f978804646e45939d32c2964ae2ad84 |
| institution | Directory Open Access Journal |
| issn | 1095-4244 1099-1824 |
| language | English |
| last_indexed | 2024-04-13T13:29:04Z |
| publishDate | 2022-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | Wind Energy |
| spelling | doaj.art-2f978804646e45939d32c2964ae2ad842022-12-22T02:45:02ZengWileyWind Energy1095-42441099-18242022-09-012591626164510.1002/we.2762Virtual sensors for wind turbines with machine learning‐based time series modelsNikolay Dimitrov0Tuhfe Göçmen1DTU Wind and Energy Systems Technical University of Denmark Roskilde DenmarkDTU Wind and Energy Systems Technical University of Denmark Roskilde DenmarkAbstract Modern wind turbines have multiple sensors installed and provide constant data stream outputs; however, there are some important quantities where installing physical sensors is either impractical or the sensor technology is not sufficiently advanced. An example of such a problem is, for example, sensing the shape and location of wake‐induced wind deficits caused by upwind turbines—a feature which would have relevant application in wind farm control; however, it is hard to detect physically due to the need of scanning the airflow in front of the turbine in multiple locations. Another control‐related example is monitoring and predicting the blade tip‐tower clearance. A “virtual sensor” can be created instead, by establishing a mathematical relationship between the quantity of interest and other, measurable quantities such as readings from already available sensors (e.g., SCADA, lidars, and met‐masts). Machine Learning (ML) approaches are suitable for this task as ML algorithms are capable of learning and representing complex relationships. This study details the concept of ML‐based virtual sensors and showcases three specific examples: blade root bending moment prediction, detection of wind turbine wake center location, and forecasting of blade tip‐tower clearance. All examples utilize sequence models (Long Short‐Term Memory, LSTM) and use aeroelastic load simulations to generate wind turbine response time series and test model performance. The data types used in the examples correspond to channels that would be available from high‐frequency SCADA data combined with a blade and tower load measurement system. The resulting model performance demonstrates the feasibility of the ML‐based virtual sensor approach.https://doi.org/10.1002/we.2762forecastingmachine learningneural networkssequence modelstime seriesvirtual sensors |
| spellingShingle | Nikolay Dimitrov Tuhfe Göçmen Virtual sensors for wind turbines with machine learning‐based time series models Wind Energy forecasting machine learning neural networks sequence models time series virtual sensors |
| title | Virtual sensors for wind turbines with machine learning‐based time series models |
| title_full | Virtual sensors for wind turbines with machine learning‐based time series models |
| title_fullStr | Virtual sensors for wind turbines with machine learning‐based time series models |
| title_full_unstemmed | Virtual sensors for wind turbines with machine learning‐based time series models |
| title_short | Virtual sensors for wind turbines with machine learning‐based time series models |
| title_sort | virtual sensors for wind turbines with machine learning based time series models |
| topic | forecasting machine learning neural networks sequence models time series virtual sensors |
| url | https://doi.org/10.1002/we.2762 |
| work_keys_str_mv | AT nikolaydimitrov virtualsensorsforwindturbineswithmachinelearningbasedtimeseriesmodels AT tuhfegocmen virtualsensorsforwindturbineswithmachinelearningbasedtimeseriesmodels |