This page has only limited features, please log in for full access.
The estimation of variables that are normally not measured or are unmeasurable could improve control and condition monitoring of wind turbines. A cost-effective estimation method that exploits machine learning is introduced in this paper. The proposed method allows a potentially expensive sensor, for example, a LiDAR sensor, to be shared between multiple turbines in a cluster. One turbine in a cluster is equipped with a sensor and the remaining turbines are equipped with a nonlinear estimator that acts as a sensor, which significantly reduces the cost of sensors. The turbine with a sensor is used to train the estimator, which is based on an artificial neural network. The proposed method could be used to train the estimator to estimate various different variables; however, this study focuses on wind speed and aerodynamic torque. A new controller is also introduced that uses aerodynamic torque estimated by the neural network-based estimator and is compared with the original controller, which uses aerodynamic torque estimated by a conventional aerodynamic torque estimator, demonstrating improved results.
Sung-Ho Hur; Yiza-Srikanth Reddy. Neural Network-Based Cost-Effective Estimation of Useful Variables to Improve Wind Turbine Control. Applied Sciences 2021, 11, 5661 .
AMA StyleSung-Ho Hur, Yiza-Srikanth Reddy. Neural Network-Based Cost-Effective Estimation of Useful Variables to Improve Wind Turbine Control. Applied Sciences. 2021; 11 (12):5661.
Chicago/Turabian StyleSung-Ho Hur; Yiza-Srikanth Reddy. 2021. "Neural Network-Based Cost-Effective Estimation of Useful Variables to Improve Wind Turbine Control." Applied Sciences 11, no. 12: 5661.
Wind speed prediction could play an important role in improving the performance of wind turbine control and condition monitoring. For example, by predicting or forecasting the upcoming wind in advance, fluctuations in wind power output in above rated wind speed could be reduced without causing an increase in pitch activity, and anomalies such as an extreme gust could be detected before it reaches the wind turbine, allowing appropriate control actions to take place to minimise any potential damage that could be incurred by the anomalies. A novel wind speed prediction scheme is presented in this paper that comprises mainly two stages, estimation and prediction. Estimation is first carried out using an Extended Kalman filter, which is designed based on a 3 dimensional wind field model and a nonlinear rotor model. Prediction is subsequently performed in two steps, extrapolation and machine learning. The wind speed prediction scheme is tested using data obtained from a high-fidelity aeroelastic model.
Sung-Ho Hur. Short-term wind speed prediction using Extended Kalman filter and machine learning. Energy Reports 2020, 7, 1046 -1054.
AMA StyleSung-Ho Hur. Short-term wind speed prediction using Extended Kalman filter and machine learning. Energy Reports. 2020; 7 ():1046-1054.
Chicago/Turabian StyleSung-Ho Hur. 2020. "Short-term wind speed prediction using Extended Kalman filter and machine learning." Energy Reports 7, no. : 1046-1054.
The power converter is among the most vulnerable wind turbine components. It is thus important to improve its reliability, especially when wind turbines are offshore because they are often exposed to severe weather conditions. A wind turbine is normally regulated using a dedicated controller, coupled with a power converter, but the control strategy proposed here requires a group (or cluster) of turbines to share a controller/converter between several turbines. The shared controller/converter would be placed somewhere more accessible, such as a substation. The potential benefits include improved reliability of each turbine due to the simplification (having removed its vulnerable power converter) and greater energy yield as a result of improved accessibility (which would lead to reduced downtime). The Matlab/Simulink model of Supergen Wind 5 MW exemplar wind turbine is employed to simulate each turbine. In order to simulate a cluster of multiple turbines, each Supergen model is first discretised and, in turn, converted to C to reduce the simulation time, ensuring at the same time that the complexity of each turbine model is not compromised.
Sung-Ho Hur. Reliable and cost-effective wind farm control strategy for offshore wind turbines. Renewable Energy 2020, 163, 1265 -1276.
AMA StyleSung-Ho Hur. Reliable and cost-effective wind farm control strategy for offshore wind turbines. Renewable Energy. 2020; 163 ():1265-1276.
Chicago/Turabian StyleSung-Ho Hur. 2020. "Reliable and cost-effective wind farm control strategy for offshore wind turbines." Renewable Energy 163, no. : 1265-1276.
Sung-Ho Hur. Estimation of Useful Variables in Wind Turbines and Farms Using Neural Networks and Extended Kalman Filter. IEEE Access 2019, 7, 24017 -24028.
AMA StyleSung-Ho Hur. Estimation of Useful Variables in Wind Turbines and Farms Using Neural Networks and Extended Kalman Filter. IEEE Access. 2019; 7 ():24017-24028.
Chicago/Turabian StyleSung-Ho Hur. 2019. "Estimation of Useful Variables in Wind Turbines and Farms Using Neural Networks and Extended Kalman Filter." IEEE Access 7, no. : 24017-24028.
Sung-Ho Hur. Modelling and control of a wind turbine and farm. Energy 2018, 156, 360 -370.
AMA StyleSung-Ho Hur. Modelling and control of a wind turbine and farm. Energy. 2018; 156 ():360-370.
Chicago/Turabian StyleSung-Ho Hur. 2018. "Modelling and control of a wind turbine and farm." Energy 156, no. : 360-370.
The typical task of the supervisory controller is to set the operating mode of each turbine, in particular the active and reactive power setâpoints, in response to what is needed by the electric grid for frequency and voltage stability. A wind farm supervisory controller has objectives that can be grouped into four categories: maximize energy production, minimize fluctuating loads on the wind turbines, provide ancillary services to the electric grid, and handle faults. Wind turbines are equipped with a supervisory control and data acquisition (SCADA) system that sends sensor measurements to the wind farm operator. The design of a wind farm supervisory control algorithm requires a model of the wind farm system. This chapter introduces a wind farm level control that can be used to more intelligently operate a wind farm to allow both better integration with the grid and more flexible operation.
Karl Merz; Olimpo Anaya-Lara; William E. Leithead; Sung-Ho Hur. Supervisory Wind Farm Control. Offshore Wind Energy Technology 2018, 305 -344.
AMA StyleKarl Merz, Olimpo Anaya-Lara, William E. Leithead, Sung-Ho Hur. Supervisory Wind Farm Control. Offshore Wind Energy Technology. 2018; ():305-344.
Chicago/Turabian StyleKarl Merz; Olimpo Anaya-Lara; William E. Leithead; Sung-Ho Hur. 2018. "Supervisory Wind Farm Control." Offshore Wind Energy Technology , no. : 305-344.
S. Hur; L. Recalde-Camacho; W.E. Leithead. Detection and compensation of anomalous conditions in a wind turbine. Energy 2017, 124, 74 -86.
AMA StyleS. Hur, L. Recalde-Camacho, W.E. Leithead. Detection and compensation of anomalous conditions in a wind turbine. Energy. 2017; 124 ():74-86.
Chicago/Turabian StyleS. Hur; L. Recalde-Camacho; W.E. Leithead. 2017. "Detection and compensation of anomalous conditions in a wind turbine." Energy 124, no. : 74-86.
The power converter is one of the most vulnerable components of a wind turbine. When the converter of an offshore wind turbine malfunctions, it could be difficult to resolve due to poor accessibility. A turbine generally has a dedicated controller that regulates its operation. In this paper, a collective control approach that allows a cluster of turbines to share a single converter, hence a single controller, that could be placed in a more accessible location. The resulting simplified turbines are constant-speed stall-regulated with standard asynchronous generators. Each cluster is connected by a mini-AC network, whose frequency can be varied through a centralised AC-DC-AC power converter. Potential benefits include improved reliability of each turbine due to simplification of the turbines and enhanced profit owing to improved accessibility. A cluster of 5 turbines is assessed compared to the situation with each turbine having its own converter. A collective control strategy that acts in response to the poorest control is proposed, as opposed to acting in response to the average control. The strategy is applied to a cluster model, and simulation results demonstrate that the control strategy could be more cost-effective than each turbine having its own converter, especially with optimal rotor design
S. Hur; W.E. Leithead. Collective control strategy for a cluster of stall-regulated offshore wind turbines. Renewable Energy 2016, 85, 1260 -1270.
AMA StyleS. Hur, W.E. Leithead. Collective control strategy for a cluster of stall-regulated offshore wind turbines. Renewable Energy. 2016; 85 ():1260-1270.
Chicago/Turabian StyleS. Hur; W.E. Leithead. 2016. "Collective control strategy for a cluster of stall-regulated offshore wind turbines." Renewable Energy 85, no. : 1260-1270.