An official website of the United States government
In cold climates, ice formation on wind turbines causes power reduction produced by a wind farm. This paper introduces a framework to predict icing at the farm level based on our recently developed Temporal Convolutional Network prediction model for a single turbine using SCADA data.First, a cross-validation study is carried out to evaluate the extent predictors trained on a single turbine of a wind farm can be used to predict icing on the other turbines of a wind farm. This fusion approach combines multiple turbines, thereby providing predictions at the wind farm level. This study shows that such a fusion approach improves prediction accuracy and decreases fluctuations across different prediction horizons when compared with single-turbine prediction. Two approaches are considered to conduct farm-level icing prediction: decision fusion and feature fusion. In decision fusion, icing prediction decisions from individual turbines are combined in a majority voting manner. In feature fusion, features of individual turbines are averaged first before conducting prediction. The results obtained indicate that both the decision fusion and feature fusion approaches generate farm-level icing prediction accuracies that are 7% higher with lower standard deviations or fluctuations across different prediction horizons when compared with predictions for a single turbine.
more »
« less
Prediction of Icing on Wind Turbines Based on SCADA Data via Temporal Convolutional Network
Icing on the blades of wind turbines during winter seasons causes a reduction in power and revenue losses. The prediction of icing before it occurs has the potential to enable mitigating actions to reduce ice accumulation. This paper presents a framework for the prediction of icing on wind turbines based on Supervisory Control and Data Acquisition (SCADA) data without requiring the installation of any additional icing sensors on the turbines. A Temporal Convolutional Network is considered as the model to predict icing from the SCADA data time series. All aspects of the icing prediction framework are described, including the necessary data preprocessing, the labeling of SCADA data for icing conditions, the selection of informative icing features or variables in SCADA data, and the design of a Temporal Convolutional Network as the prediction model. Two performance metrics to evaluate the prediction outcome are presented. Using SCADA data from an actual wind turbine, the model achieves an average prediction accuracy of 77.6% for future times of up to 48 h.
more »
« less
- Award ID(s):
- 1916776
- PAR ID:
- 10561780
- Publisher / Repository:
- MDPI
- Date Published:
- Journal Name:
- Energies
- Volume:
- 17
- Issue:
- 9
- ISSN:
- 1996-1073
- Page Range / eLocation ID:
- 2175
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
A field campaign was carried out to investigate ice accretion features on large turbine blades (50 m in length) and to assess power output losses of utility-scale wind turbines induced by ice accretion. After a 30-h icing incident, a high-resolution digital camera carried by an unmanned aircraft system was used to capture photographs of iced turbine blades. Based on the obtained pictures of the frozen blades, the ice layer thickness accreted along the blades’ leading edges was determined quantitatively. While ice was found to accumulate over whole blade spans, outboard blades had more ice structures, with ice layers reaching up to 0.3 m thick toward the blade tips. With the turbine operating data provided by the turbines’ supervisory control and data acquisition systems, icing-induced power output losses were investigated systematically. Despite the high wind, frozen turbines were discovered to rotate substantially slower and even shut down from time to time, resulting in up to 80% of icing-induced turbine power losses during the icing event. The research presented here is a comprehensive field campaign to characterize ice accretion features on full-scaled turbine blades and systematically analyze detrimental impacts of ice accumulation on the power generation of utility-scale wind turbines. The research findings are very useful in bridging the gaps between fundamental icing physics research carried out in highly idealized laboratory settings and the realistic icing phenomena observed on utility-scale wind turbines operating in harsh natural icing conditions.more » « less
-
Abstract Quantification of the performance degradation on the annual energy production (AEP) of a wind farm due to leading‐edge (LE) erosion of wind turbine blades is important to design cost‐effective maintenance plans and timely blade retrofit. In this work, the effects of LE erosion on horizontal axis wind turbines are quantified using infrared (IR) thermographic imaging of turbine blades, as well as meteorological and SCADA data. The average AEP loss of turbines with LE erosion is estimated from SCADA and meteorological data to be between 3% and 8% of the expected power capture. The impact of LE erosion on the average power capture of the turbines is found to be higher at lower hub‐height wind speeds (peak around 50% of the turbine rated wind speed) and at lower turbulence intensity of the incoming wind associated with stable atmospheric conditions. The effect of LE erosion is investigated with IR thermography to identify the laminar to turbulent transition (LTT) position over the airfoils of the turbine blades. Reduction in the laminar flow region of about 85% and 87% on average in the suction and pressure sides, respectively, is observed for the airfoils of the investigated turbines with LE erosion. Using the observed LTT locations over the airfoils and the geometry of the blade, an average AEP loss of about 3.7% is calculated with blade element momentum simulations, which is found to be comparable with the magnitude of AEP loss estimated through the SCADA data.more » « less
-
This paper presents regression and classification methods to estimate wind direction in a wind farm from operational data. Two neural network models are trained using supervised learning. The data are generated using high-fidelity large eddy simulations (LES) of a virtual wind farm with 16 turbines, which are representative of the data available in actual SCADA systems. The simulations include the high-fidelity flow physics and turbine dynamics. The LES data used for training and testing the neural network models are the rotor angular speeds of each turbine. Our neural network models use sixteen angular speeds as inputs to produce an estimate of the wind direction at each point in time. Training and testing of the neural network models are done for seven discrete wind directions, which span the most interesting cases due to symmetry of the wind farm layout. The results of this paper are indicative of the potential that existing neural network models have to obtain estimates of wind direction in real time.more » « less
-
Abstract One‐way nested mesoscale to microscale simulations of an onshore wind farm have been performed nesting the Weather Research and Forecasting (WRF) model and our in‐house high‐resolution large‐eddy simulation code (UTD‐WF). Each simulation contains five nested WRF domains, with the largest domain spanning the north Texas Panhandle region with a 4 km resolution, while the highest resolution (50 m) nest simulates microscale wind fluctuations and turbine wakes within a single wind farm. The finest WRF domain in turn drives the UTD‐WF LES higher‐resolution domain for a subset of six turbines at a resolution of ∼5 m. The wind speed, direction, and boundary layer profiles from WRF are compared against measurements obtained with a met‐tower and a scanning Doppler wind LiDAR located within the wind farm. Additionally, power production obtained from WRF and UTD‐WF are assessed against supervisory control and data acquisition (SCADA) system data. Numerical results agree well with the experimental measurements of the wind speed, direction, and power production of the turbines. UTD‐WF high‐resolution domain improves significantly the agreement of the turbulence intensity at the turbines location compared with that of WRF. Velocity spectra have been computed to assess how the nesting allows resolving a wide range of scales at a reasonable computational cost. A domain sensitivity analysis has been performed. Velocity spectra indicate that placing the inlet too close to the first row of turbines results in an unrealistic peak of energy at the rotational frequency of the turbines. Spectra of the power production of a single turbine and of the cumulative power of the array have been compared with analytical models.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/en17092175
