AI-Based Wind Tracking and Yaw Control System for Optimizing Wind Turbine Efficiency

Yaw control is an important part of the control system of a horizontal shaft wind turbine. After the installation of the wind turbine, the turbulence influence of the wind turbine blades and the azimuth of the wind turbine will cause yaw error which directly affects the economic and the safety of the wind turbine. This article introduces a method for aligning the yaw error of a wind turbine mounted with a LiDAR anemometer, in which the power and the yaw azimuth of the wind turbine, recorded by a SCADA system, are divided into 22 power segments and 12 yaw azimuth sectors respectively. Combining the yaw error angles measured by the LiDAR, a 3D table of yaw error angles is prepared based on the power segments and yaw azimuth sectors of the wind turbine. Using the table of the yaw error angles, the wind turbine yaw error is aligned for capturing the maximum wind energy. According to the analysis of the data measured on-site, the proposed method is found effective in improving the AEP of the aligned wind turbine. Furthermore, taking the alignment of yaw error in a 48.6MW wind farm as an example, the economy and feasibility of the proposed method are analyzed.

Owing to its being an important component of renewable energy, wind energy is a kind of power generation method with the most mature, highly developed technologies and broad commercial prospects. The stable and efficient conversion of wind energy by wind turbines depends not only on the reliability of the wind power generation equipment itself, but also on the wind turbine control system, which, in turn, contributes to long-term safe and reliable operation of the wind farm fleet. It is exactly the wind turbine control system that is the main subject of this study. The key to efficient and stable operation of the entire wind energy conversion system is the control technology, which includes yaw control, pitch angle control, and maximum power point tracking control. The active yaw control system is one of the important components of a horizontal axis wind turbine's control system. To eliminate the uncertainty of wind direction influence on the turbine power output, a composite yaw control system has been checked. By using an active yaw system and maximum power point tracking system, the turbine position and its rotation speed are adjusted to enable the wind turbine to accurately track the wind direction and capture the wind energy to the fullest extent.

Multi-rotor system (MRS) wind turbines can provide a competitive alternative to large-scale wind turbines due to their significant advantages in reducing capital, transportation, and operating costs. The main challenges of MRS wind turbines include the complexity of the supporting structure, mathematical modeling of the aerodynamic interaction between the rotors, and the yaw control mechanism. In this work, MATLAB 2018b/Simulink® software was used to model and simulate a twin-rotor wind turbine (TRWT), and an NREL 5 MW wind turbine was used to verify the model outputs. Different random signals of wind velocities and directions were used as inputs to each rotor to generate different thrust loads, inducing twisting moments on the main tower. A yaw controller system was adapted to ensure that the turbine constantly faced the wind to maximize the power output. A DC motor was used as the mechanism’s actuator. The goal was to achieve a compromise between aligning the rotors with the wind direction and reducing the torque induced on the main tower. A comparison between linear and nonlinear controllers was performed to test the yaw system actuator’s response at different wind speeds and directions. Sliding mode control (SMC) was chosen, as it was suitable for the nonlinearity of the system, and its performance showed a faster response compared with the PID controller, with a settling time of 0.17 sec and a very low overshoot. The controller used the transfer function of the motor to generate a sliding surface. The dynamic responses of the controlled angle are shown and discussed. The controller showed promising results, with a suitable response and low chattering signals.

As an important component of renewable energy, wind energy is a kind of power generation method with the most mature, most developed conditions and broad commercial prospects in renewable energy technology. The development of wind power has continuously exceeded its expected development speed and has maintained the status of the world’s fastest-growing energy source. To ensure the stable and efficient conversion of wind energy by wind turbines, not only depends on the reliability of the wind power generation equipment itself, but also the wind turbine control system is also an important factor for the wind energy conversion system, or even become a long-term safe and reliable operation of the wind farm. Therefore, the control system has become a research hotspot. The key to the efficient and stable operation of the entire wind energy conversion system is control technology, including yaw control, pitch angle control, and maximum power point tracking control. The active yaw control system is one of the important components of the horizontal axis wind turbine control system. To eliminate the uncertainty of the influence of wind direction on turbine power, this paper verifies a composite yaw control system. Through an active yaw system and maximum power point tracking system, the turbine position and rotation speed are adjusted to enable the wind turbine to accurately track the wind direction, capture wind energy to the greatest extent. The results show that the active yaw system can accurately track the wind direction, effectively use wind energy, and meet the control requirements of the yaw system.

Maximum power extraction for wind turbines through a novel yaw control solution using predicted wind directions

Electrical Parts, Control Systems and Power Electronics of Wind Turbines

Flicker emission, voltage fluctuations, and mechanical loads for small-scale stall- and yaw-controlled wind turbines

To reduce the downtime of wind turbine caused by the fault of pitch system that usually has a high failure rate, a fault early warning method based on long short-term memory (LSTM) neural network is proposed. According to the operation characteristics of the pitch system, monitoring parameters recorded by SCADA, such as wind speed, generator speed, rotor speed, wind direction, pitch angle and output power, are utilized to establish the fault early warning model. Compared with the model based on BP neural network, the prediction accuracy of the LSTM model is effectively improved. The weights and thresholds of the LSTM neural network are optimized, and a reasonable threshold is set to determine the fault early warning criterion for the pitch system. To verify the effectiveness of the proposed method, the LSTM model is applied to the fault early warning for a 1.5MW wind turbine pitch system. The results show that the LSTM model can give early warning about two and a half days before the fault occurs, verifying the feasibility of the proposed method.

Bearings are the most prevalent and easily damaged mechanical components in mechanical systems. Nowadays, Deep learning emerges as a very efficient artificial intelligence method that offers a new approach to feature extraction from raw data. Long short-term memory (LSTM) neural network is a promising type of deep learning, which is mainly used for the diagnosis of faults. In this work, a new intelligent fault diagnosis and classification method based on Long Short-Term Memory (LSTM) neural network is developed. The developed model correctly classifies the different types of faults at different running conditions in real operation conditions, and the results are compared with existing techniques. The performance of the model is evaluated with various performance metrics such as Precision, Recall, F1 score, Receiver Operating Characteristics, Area under Curve, and Accuracy. The best results are obtained from the developed LSTM model than from the existing work.

The Western mill was the first wind turbine which operated completely automatic, “without a human supervisor”. But the tasks of the control system and the supervisory system were strongly interwoven. The main vane which adjusts the rotor to the wind direction is in fact a simple “all-in-one” control system: it is sensor to register the deviation between the wind direction and the rotor axis, and at the same time it is the actuator producing the forces for the correction of the deviation from the demand value, Fig. 12-1. Together with the transverse vane it controls the turbine in the entire operating range from standstill to storm protection: For very strong winds the spring extends and the rotor is turned to increase the angle between rotor axis and wind direction. Rotational speed, power extraction and thrust are reduced, see also Fig. 12-7 (yaw angle β), and annex I of this chapter. In this annex additional examples of simple mechanical control systems for small wind turbines are presented.

Study on turbidity prediction method of reservoirs based on long short term memory neural network

This paper introduces a novel data driven yaw control algorithm synthesis method based on Reinforcement Learning (RL) for a variable pitch variable speed wind turbine. Yaw control has not been extendedly studied in the literature; in fact, most of the currently considered developments in the scope of the wind energy are oriented to the pitch and speed control. The most important drawbacks of the yaw control are the very large time constants and the strict yaw angle change rate constraints due to the high mechanical loads when the wind turbine angle is changed in order to adequate it to the wind speed orientation. An optimal yaw control algorithm needs to be designed in order to adapt the rotor orientation depending on the wind turbine dynamics and the local wind speed regime. Consequently, the biggest challenge of the yaw control algorithm is to decide the moment and the quantity of the wind turbine orientation variation to achieve the highest quantity of power at each instant, taking into account the constraints derived from the mechanical limitations of the yawing system and the mechanical loads. In this paper, a novel based algorithm based on the RL Q-Learning algorithm is introduced. The first step is to obtain a model of the power generated by the wind turbine (a real onshore wind turbine in this paper) through a power curve, that in conjunction with a conventional proportional regulator will be used to obtain a dataset that explains the actual behaviour of the real wind turbine when a variety of different yaw control commands are imposed. That knowledge is then used to learn the best control action for each different state of the wind turbine with respect to the wind direction represented by the yaw angle, storing that knowledge in a matrix Q(s,a). The last step is to model that matrix through a MultiLayer Perceptron with BackPropagation (MLP-BP) Artificial Neural Network (ANN) to avoid large matrix management and quantification problems. Once that the optimal yaw controller has been synthetized, its performance has been assessed using a number of wind speed realizations obtained using the software application TurbSim, in order to analyze how the introduced novel algorithm deals with different wind speed scenarios.

Abstract. This paper investigates the accuracy of wind direction measurements for horizontal-axis wind turbines and their impact on yaw control. The yaw controller is crucial for aligning the rotor with the wind direction and optimizing energy extraction. Wind direction is conventionally measured by one or two wind vanes located on the nacelle, but the proximity of the rotor can interfere with these measurements. The authors show that the conventional corrections, including low-pass filters and calibrated offset correction, are inadequate to correct a systematic overestimation of the wind direction deviation caused by the rotor misalignment. This measurement error can lead to an overcorrection of the yaw controller and, thus, to an oscillating yaw behaviour, even if the wind direction is relatively steady. The authors present a theoretical basis and methods for quantifying the wind vane measurement error and validate their findings using computational fluid dynamics simulations and operational data from two commercial wind turbines. Additionally, the authors propose a correction function that improves the wind vane measurements and demonstrate its effectiveness in two free-field experiments. Overall, the paper provides new insights into the accuracy of wind direction measurements and proposes solutions to improve the yaw control for horizontal-axis wind turbines.

Model predictive yaw control (MPYC) using the future wind direction information could improve energy conversion efficiency of wind turbines. However, the performance of MPYC system is closely related to the wind direction prediction of which the accuracy is actually difficult to improve. In this paper, we propose a stochastic model predictive yaw control (SMPYC) based on multi-scenario optimization to solve the uncertainty of future wind direction prediction. Meanwhile, in order to reduce computational burden during the model solving, the synchronous backward substitution method is used to cut down the scenarios with guaranteed precision. Then, the performance of the proposed SMPYC method is demonstrated by the simulation tests comparing with baseline control method (MPYC). Finally, our results show that the overall performance including power production and yaw actuator usage of SMPYC is enhanced.

Natural wind is stochastic, being characterized by its speed and direction which change randomly and frequently. Because of the certain lag in control systems and the yaw body itself, wind turbines cannot be accurately aligned toward the wind direction when the wind speed and wind direction change frequently. Thus, wind turbines often suffer from a series of engineering issues during operation, including frequent yaw, vibration overruns and downtime. This paper aims to study the effects of yaw error on wind turbine running characteristics at different wind speeds and control stages by establishing a wind turbine model, yaw error model and the equivalent wind speed model that includes the wind shear and tower shadow effects. Formulas for the relevant effect coefficients Tc, Sc and Pc were derived. The simulation results indicate that the effects of the aerodynamic torque, rotor speed and power output due to yaw error at different running stages are different and that the effect rules for each coefficient are not identical when the yaw error varies. These results may provide theoretical support for optimizing the yaw control strategies for each stage to increase the running stability of wind turbines and the utilization rate of wind energy.