Control device, control method, and control program for a horizontal-axis wind turbine

Abstract

This technology provides control for horizontal-axis wind turbines that responds accurately and quickly to changes in wind direction and appropriately controls the yaw angle of the nacelle to maximize power generation efficiency. [Solution] In a horizontal-axis wind turbine 1 having a blade 2 that rotates in response to wind, a nacelle 4 that rotatably supports the blade, a tower 5 that yaw-rotates the nacelle 4, and an anemometer 15 installed on the nacelle 4, a plurality of first devices 30 are fixed around the wind turbine, and a second device 40 is installed at a position offset from the rotation axis of the anemometer 15. Based on the bidirectional transmission and reception times between each of the first devices 30 and the second device 40, the distance between each of the first devices 30 and the second device 40 is calculated to identify the position of the second device 40, and the wind direction is calculated based on that. The obtained wind direction data and the installation position information of the horizontal-axis wind turbine 1 are input into a learning model that has learned the correlation with the optimal yaw angle of the nacelle that maximizes power generation efficiency to estimate the optimal yaw angle of the nacelle, and the yaw angle of the nacelle 4 is adjusted to achieve that optimal yaw angle.

Description

Technical Field

[0001] The present invention relates to a control device, a control method, and a control program for automatically adjusting the yaw angle of a nacelle of a horizontal axis wind turbine used in wind power generation equipment. Background Art

[0002] A horizontal axis wind turbine is a structure for efficiently converting wind energy into electric power. As a main configuration, there are blades that receive wind to generate rotational motion, and a nacelle, which is a machine room that supports the rotation of the blades, is arranged behind the rotational axis of the blades. Housed inside the nacelle are a generator that converts rotational energy into electric power, a gearbox that converts the low-speed rotation of the blades into the high-speed rotation required by the generator, and a yaw system that rotates the nacelle in accordance with the wind direction to adjust the orientation of the blades.

[0003] Further, an anemoscope and an anemometer for measuring wind direction and wind speed are installed on the top of the nacelle, whereby the operation of the entire equipment is optimally controlled. The control system adjusts the orientation of the nacelle and the pitch angle of the blades according to the wind direction and wind speed, and also optimizes the power generation amount by performing output control and overload prevention. Furthermore, there is a power grid connection device for connecting the generated power to the power transmission grid, which includes transformers and cables. These components cooperate to allow the wind power generation equipment to convert wind energy into electric power (see Patent Documents 1 to 3, etc.). Prior Art Literature Patent Literature

[0004] Patent Document 1 Japanese Unexamined Patent Application Publication No. 2016-094879 Patent Document 2 Japanese Unexamined Patent Application Publication No. 2020-67046 Patent Document 3 Japanese Unexamined Patent Application Publication No. 2015-203387 Summary of the Invention Problem to be Solved by the Invention

[0005] In horizontal-axis wind turbines used in such wind power generation facilities, the yaw angle of the nacelle (the angle at which the nacelle rotates around the vertical axis; in this specification, the yaw angle of the nacelle is defined on a geographical basis and represents the azimuth angle of the nacelle) significantly affects power generation efficiency. Therefore, it is desirable to adjust the yaw angle of the nacelle appropriately and quickly according to the wind direction.

[0006] However, conventional wind direction measurement methods have difficulty keeping up with rapid changes in wind direction, causing delays in nacelle rotation control and making it difficult to maintain the optimal yaw angle. In fact, if the system cannot respond appropriately and quickly to changes in wind direction and speed, power generation efficiency will decrease. Furthermore, when multiple horizontal-axis wind turbines are installed, insufficient information sharing and synchronization between these turbines prevents proper consideration of the wake effect caused by the upwind turbine, leading to a decrease in the power generation efficiency of the downwind turbine.

[0007] Although there are systems that measure wind direction using wind vanes, it is difficult to accurately and instantly capture rapid changes in wind direction and the effects of turbulence in real time. As a result, conventional nacelle yaw angle control based on wind direction measurement data suffers from measurement delays by the wind vanes and rotational response delays of the nacelle, making it difficult to quickly adjust to the optimal yaw angle (lack of efficient yaw angle control technology).

[0008] Furthermore, if proper control is not implemented during operation in strong winds, there is a risk of equipment damage or failure (insufficient consideration of wind speed). In particular, a delay in response to rapid changes in wind speed can not only place excessive load on the blades, but also concentrate the load on the generator and gearbox, potentially increasing the risk of equipment damage. For this reason, proper pitch angle adjustment and rotational speed control are also required.

[0009] Furthermore, when multiple wind power generation facilities are installed, each wind power generation facility operates independently, making efficient coordination between upwind and downwind power generation facilities impossible. This prevents minimizing the decrease in power generation efficiency due to the wake effect (insufficient coordination between facilities). In particular, the wind speed reduction and turbulence created by the upwind wind turbine affect the downwind wind turbine. Therefore, in order to optimize the power generation efficiency of the entire facility group, it is necessary to strengthen information sharing between facilities and implement control that takes the wake effect into consideration.

[0010] This invention has been made in view of the above circumstances, and its main objective is to provide a control device, control method, and control program for a horizontal-axis wind turbine that can respond accurately and quickly to changes in wind direction and maximize power generation efficiency by appropriately controlling the yaw angle of the nacelle. Furthermore, challenges include maintaining safe and stable power generation by appropriately controlling wind speed fluctuations, and improving the overall operational efficiency of wind power generation facilities when multiple horizontal-axis wind turbines are installed. [Means for solving the problem]

[0011] To achieve the above objectives, the control device for a horizontal-axis wind turbine according to the present invention comprises a blade that rotates in response to wind, a nacelle that rotatably supports the blade, a tower that yaw-rotatably supports the nacelle, and a wind vane provided on the nacelle and rotatably supported about a vertical axis of rotation, An optimal yaw angle estimation means estimates the optimal yaw angle of the nacelle that maximizes power generation efficiency by inputting input information, including the wind direction detected by the wind vane and the installation position of the horizontal-axis wind turbine, into a learning model that has been pre-trained to determine the correlation between the optimal yaw angle of the nacelle that maximizes power generation efficiency (the direction of the rotor's rotation axis, i.e., the normal direction of the blade rotation surface), A yaw angle adjustment means for adjusting the yaw angle of the nacelle so that it becomes the optimal yaw angle calculated by the optimal yaw angle estimation means, It is characterized by possessing the following features.

[0012] Therefore, according to the control device for this horizontal-axis wind turbine, the optimal yaw angle estimation means uses a learning model that has been pre-trained to determine the correlation between input information, including the wind direction detected by the wind vane and the installation position of the horizontal-axis wind turbine, and the optimal yaw angle of the nacelle that maximizes power generation efficiency (the direction of the rotor's rotation axis, i.e., the normal direction of the blade rotation surface). As a result, the optimal yaw angle information can be obtained with high accuracy, and the yaw angle of the nacelle is adjusted to the optimal yaw angle based on this information, making it possible to accurately control the yaw angle of the nacelle to the optimal yaw angle according to the wind direction detected by the wind vane.

[0013] Furthermore, in order to achieve the above objectives, the control device for a horizontal-axis wind turbine according to the present invention comprises a blade that rotates in response to wind, a nacelle that rotatably supports the blade, a tower that yaw-rotatably supports the nacelle, and a wind vane provided on the nacelle and rotatably supported about a vertical axis of rotation, The system comprises a plurality of first devices fixed around the horizontal axis wind turbine and capable of determining their position, and a second device fixed to the wind vane and positioned offset from the wind vane's rotation axis, capable of transmitting and receiving signals with the first devices. A second device positioning means calculates the distance between each of the plurality of first devices and the second device in real time based on the bidirectional transmission and reception times of information or signals between each of the plurality of first devices and the second device, and identifies the position of the second device based on the distance between each first device and the second device and the position information of each of the first devices, A wind direction calculation means that calculates the wind direction based on the position of the second device identified by the second device position identification means, A yaw angle adjustment means for adjusting the yaw angle of the nacelle so that the wind direction is calculated by the wind direction calculation means, It is characterized by possessing the following features.

[0014] Here, the installation method of the first device is not particularly limited. It may be installed on existing fixed objects (utility poles, streetlights, buildings, etc.) located around a horizontal-axis wind turbine whose location can be identified, on newly constructed fixed objects (installation poles, etc.), on immovable natural objects (rocks, etc.), or even embedded in these fixed objects. Furthermore, "location information can be identified" includes not only cases where the location information of the first device can be identified by itself, but also cases where it can be identified by subsequent measurements. In addition, the identified location information of the first device may be stored in a readable manner in its own memory, or it may be compiled into a database and stored in another storage device.

[0015] The position information of the first device may be 3D position information, but since it is sufficient to accurately determine the 2D wind direction on a plane parallel to the ground surface, 2D position information may also be used. Furthermore, the position information of the first device may be determined using a geocentric Cartesian coordinate system, a geodetic coordinate system, or a coordinate system independently established at the work site.

[0016] The second device, which is fixed to the wind vane and positioned offset from the wind vane's axis of rotation, may be mounted on the surface of the wind vane or embedded in it. For example, it may be mounted near the tail fin of the wind vane offset from the axis of rotation.

[0017] Therefore, the second device positioning means calculates the distance between each of the multiple first devices and the second device in real time based on the bidirectional transmission and reception times of information or signals between each of the multiple first devices and the second device. Based on the distance between each first and second device and the position information of each first device, the position of the second device is determined. The wind direction calculation means calculates the wind direction based on the position of this second device, and the yaw angle of the nacelle is adjusted by the yaw angle adjustment means to achieve the calculated wind direction. In this way, since the wind direction is calculated quickly using wireless bidirectional time synchronization technology, it becomes possible to quickly control the yaw angle of the nacelle.

[0018] Here, the calculation of the distance between the first device and the second device is specifically, a difference between a time on a clock of the first device when information or a signal is transmitted from the first device, and a time on a clock of the second device when the second device receives the information or the signal transmitted from the first device; a difference between a time on the clock of the second device when information or a signal is transmitted from the second device, and a time on the clock of the first device when the first device receives the information or the signal transmitted from the second device; it is preferable to calculate the propagation time of the information or signal between the first device and the second device based on the above, and calculate the distance between the first device and the second device based on this propagation time. In such a configuration, calculating the distance between the first device and the second device based on the transmission and reception times of information or signals in both directions between the first device and the second device makes it possible to accurately calculate the distance between the first device and the second device even when time synchronization is not established between the first device and the second device.

[0019] Furthermore, in order to achieve the above object, a control device for a horizontal axis wind turbine according to the present invention comprises: A control device for a horizontal axis wind turbine, the horizontal axis wind turbine comprising: a blade that rotates by receiving wind; a nacelle that rotatably supports the blade; a tower that supports the nacelle to be capable of yaw rotation; and a wind vane provided on the nacelle and rotatably supported around a vertical rotation shaft, the control device comprising: a plurality of first devices fixed around the horizontal axis wind turbine; and a second device fixed to the wind vane, provided at a position offset from the rotation shaft of the wind vane, and capable of transmitting and receiving with the first devices, second device position specifying means that calculates in real time the distance between each of the plurality of first devices and the second device based on the transmission and reception times of information or signals in both directions between each of the plurality of first devices and the second device, and specifies the position of the second device based on the distance between each first device and the second device and the position information of each first device; wind direction calculating means that calculates a wind direction based on the position of the second device specified by the second device position specifying means; optimal yaw angle estimating means for estimating an optimal yaw angle of the nacelle that maximizes power generation efficiency by inputting input information including the wind direction calculated by said wind direction calculating means and the installation position of said horizontal axis wind turbine into a learning model which has learned in advance the correlation between said input information and the optimal yaw angle of the nacelle that maximizes power generation efficiency; yaw angle adjusting means for adjusting the yaw angle of said nacelle so as to achieve the optimal yaw angle calculated by said optimal yaw angle estimating means; comprising:

[0020] Therefore, the second device position specifying means calculates in real time the distance between each of the plurality of first devices and the second device based on the transmission and reception times of bidirectional information or signals between each of the plurality of first devices and the second device, and specifies the position of the second device based on the distance between each first device and the second device and the position information of each first device. Then, the wind direction calculating means calculates the wind direction based on the position of the second device. Thereafter, using a learning model which has learned in advance the correlation between input information including the calculated wind direction and the installation position of the horizontal axis wind turbine, and the optimal yaw angle of the nacelle that maximizes power generation efficiency (the direction of the rotation axis of the rotor, that is, the normal direction of the blade rotation plane), the optimal yaw angle of the nacelle that maximizes power generation efficiency is estimated from said input information. Accordingly, information on the optimal yaw angle can be obtained accurately and quickly, and the yaw angle of the nacelle is adjusted to the optimal yaw angle by the yaw angle adjusting means. Therefore, the yaw angle of the nacelle can be accurately and quickly controlled to the optimal yaw angle in accordance with changes in wind direction.

[0021] As a specific method for calculating the wind direction based on the position of the second device by said wind direction calculating means, a third device is provided which is fixed to said nacelle, provided at a position offset from the yaw rotation axis of said nacelle, and capable of transmitting and receiving signals to and from said first device, A third device positioning means calculates the distance between each of the plurality of first devices and the third device in real time based on the bidirectional transmission and reception times of information or signals between each of the plurality of first devices and the third device, and identifies the position of the third device based on the distance between each first device and the third device and the position information of each of the first devices, A nacelle azimuth angle calculation means calculates the yaw angle of the nacelle from the position of the third device identified by the third device position identification means and the position of the yaw rotation axis of the nacelle, The system includes a wind vane rotation axis position determination means for determining the position of the wind vane's rotation axis from the yaw angle of the nacelle calculated by the nacelle azimuth angle calculation means, The wind direction may be calculated from the position of the wind vane's rotation axis, determined by the wind vane rotation axis position determination means, and the position of the second device, determined by the second device position determination means.

[0022] Another method for calculating wind direction based on the position of the second device is to install a fifth device having the same function as the second device on the rotation axis of the wind vane, similarly calculate the position information of this fifth device (the rotation axis of the wind vane) using wireless two-way time synchronization technology, and then determine the wind direction by calculating the direction of the straight line connecting the position information of the rotation axis of this wind vane and the position information of the second device.

[0023] Furthermore, the system includes an anemometer provided in the nacelle, and a fourth device provided at a position of the wind receiving section offset from the rotation axis of the anemometer, which is capable of transmitting and receiving signals with the first device. A fourth device positioning means calculates the distance between each of the plurality of first devices and the fourth device in real time based on the bidirectional transmission and reception times of information or signals between each of the plurality of first devices and the fourth device, and identifies the position of the fourth device based on the distance between each of the first devices and the fourth device and the position information of each of the first devices, The system further includes a wind speed calculation means for calculating wind speed based on the amount of angular displacement per unit time of the position of the fourth device identified by the fourth device position identification means (or the number of times the fourth device rotates per unit time around the rotation center of the anemometer based on this), The system may further include a wind speed confirmation means for confirming that the wind speed calculated by the wind speed calculation means is within the rated wind speed. By providing such a wind speed monitoring mechanism, it becomes possible to quickly detect changes in wind speed. Furthermore, as long as the wind speed remains within the rated range, it becomes possible to maintain the nacelle's yaw angle at the optimal yaw angle and appropriately adjust the blade's pitch angle, thereby maximizing power generation efficiency.

[0024] In contrast, if the wind speed calculated by the wind speed calculation means exceeds the rated wind speed, it is preferable to provide a protective control means that changes the angle of the blade or stops the rotation of the blade. By providing such protective control measures, it is possible to prevent overloading of the blades and generators during strong winds, ensuring the safety of the wind power generation equipment and improving the durability of the equipment during long-term operation. Furthermore, by appropriately controlling the output through blade angle adjustment, stable power generation can be maintained even in the event of sudden wind speed fluctuations such as gusts.

[0025] Furthermore, if multiple horizontal-axis wind turbines are provided, a yaw angle tracking means may be provided to adjust the yaw angles of the nacelles of the other horizontal-axis wind turbines based on the estimated optimal yaw angle of the nacelle that maximizes power generation efficiency, when the optimal yaw angle of the nacelle that maximizes power generation efficiency is estimated by the optimal yaw angle estimation means for any one of the horizontal-axis wind turbines. By providing such a yaw angle tracking mechanism, it is possible to improve the overall power generation efficiency of the wind power generation facility. In particular, by adjusting the yaw angle of the downwind turbine based on the optimal yaw angle of the upwind turbine's nacelle, the decrease in power generation efficiency of the downwind turbine due to the wake effect can be suppressed, and the overall energy conversion efficiency can be maximized. Furthermore, compared to cases where each turbine adjusts its yaw angle independently, coordinated control between turbines becomes possible, contributing to improved responsiveness to wind direction fluctuations and stabilization of control. [Effects of the Invention]

[0026] As described above, the control device, control method, and control program for a horizontal-axis wind turbine according to the present invention enable rapid and accurate responses to changes in wind direction and appropriate control of the nacelle's yaw angle, thereby maximizing power generation efficiency. In particular, by using a learning model that takes measured or calculated wind direction and wind turbine installation position information as input and learns the correlation with the optimal nacelle yaw angle that maximizes power generation efficiency, more accurate yaw angle estimation becomes possible. As a result, the nacelle's yaw angle can be quickly adjusted even in response to fluctuations in wind direction, and an improvement in power generation efficiency can be expected compared to conventional technology.

[0027] Furthermore, by employing a wind direction determination method that utilizes wireless bidirectional time synchronization technology, it is possible to respond to changes in wind direction in real time, compared to conventional control that relies on anemometers, enabling more accurate nacelle yaw angle control. In addition, this invention introduces an optimal yaw angle estimation means that utilizes machine learning technology, enabling more adaptive yaw angle control by learning from long-term operational data. As a result, it can flexibly respond to the installation environment of the equipment and seasonal changes in wind direction, and a significant improvement in power generation efficiency is expected compared to conventional technology.

[0028] In addition, by implementing appropriate control in response to fluctuations in wind speed, the safety of the equipment can be ensured and stable power generation can be maintained. In particular, if the wind speed exceeds the rated wind speed, the blade angle can be changed or the rotation of the blades can be stopped to prevent overloading of the blades and generator, thereby improving the durability of the equipment. This enables safe operation even in strong winds and improves the long-term operational efficiency of the equipment.

[0029] Furthermore, when multiple horizontal-axis wind turbines are installed, a yaw angle tracking mechanism can be provided that adjusts the yaw angle of the nacelles of other wind turbines based on the optimal yaw angle of the nacelle calculated by the optimal yaw angle estimation mechanism. This strengthens the coordination between wind turbines and improves the overall power generation efficiency of the facility. In particular, by adjusting the yaw angle of the downwind wind turbine based on the yaw angle of the upwind wind turbine, the decrease in power generation efficiency of the downwind wind turbine due to the wake effect can be suppressed, and the energy conversion efficiency of the entire facility can be maximized. This improves the power generation performance of the wind power plant as a whole, enabling more efficient energy supply.

[0030] Therefore, by applying the control device, control method, and control program of the present invention for horizontal-axis wind turbines, it is possible to improve the power generation efficiency of wind power generation facilities, ensure stable operation, extend the lifespan of the facilities, and improve overall energy conversion efficiency through coordinated control between wind turbines. As a result, it becomes possible to supply electricity in a more economical and environmentally friendly way for the entire wind power generation facility. [Brief explanation of the drawing]

[0031] [Figure 1] This figure shows an example of a wind farm equipped with multiple horizontal-axis wind turbines according to the present invention. [Figure 2] (a) is a diagram showing an example of a horizontal-axis wind turbine according to the present invention, (b) is a diagram showing an example of an anemometer installed on the nacelle, and (c) is a diagram showing an example of a wind vane installed on the nacelle. [Figure 3](a) is a diagram showing an example of a machine learning device that forms a learning model for estimating the optimal yaw angle of the nacelle of a horizontal-axis wind turbine according to the present invention, and (b) is a flowchart illustrating the control flow for controlling the nacelle to the optimal yaw angle using the learning model. [Figure 4] This diagram shows the relationship between the first device arranged around the horizontal axis wind turbine, the second device installed on the wind vane, the third device installed on the nacelle, and the fourth device installed on the anemometer. [Figure 5] This is a block diagram showing an example configuration of the first device. [Figure 6] This is a block diagram showing example configurations for the second to fourth devices. [Figure 7] This is a block diagram showing the configuration of the server device. [Figure 8] This is a flowchart showing the distance calculation process. [Figure 9] This is a flowchart showing the location identification process. [Figure 10] This diagram explains the method for calculating wind direction. [Figure 11] This is a flowchart explaining the procedure for calculating wind direction. [Figure 12] This flowchart illustrates the control flow for controlling the nacelle to the optimal yaw angle using a learning model. [Figure 13] This flowchart shows the calculation of wind speed and an example of action processing based on wind speed. [Modes for carrying out the invention]

[0032] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.

[0033] Figure 1 shows a wind power generation facility with multiple horizontal-axis wind turbines 1 installed. Each horizontal-axis wind turbine is positioned at appropriate intervals to minimize wake effects (reduction in power generation efficiency due to downwind wind speed reduction and turbulence). Furthermore, the optimal placement is selected considering topography, wind conditions, land constraints, and environmental impacts. Each horizontal-axis wind turbine (propeller-type wind turbine) 1, as shown in Figure 2(a), comprises a nacelle 4 that rotatably supports a rotor 3 with multiple blades 2, and a tower 5 that supports the nacelle 4. The nacelle 4 is attached to the upper end of the tower 5 and installed at a height of several tens of meters above the ground.

[0034] Inside the nacelle 4 are a speed increaser 6, a braking device 7, and a generator 8. A main shaft 9 transmits the rotational power of the rotor 3 to the speed increaser 6, and a high-speed shaft 10 transmits the increased rotational speed from the speed increaser 6 to the generator 8. Furthermore, the nacelle 4 is rotatably supported by a yaw bearing 16 at the top of the tower 5, and the yaw angle of the nacelle can be adjusted according to the wind direction by a yaw drive device (yaw motor and control system) not shown.

[0035] The rotor 3 has multiple blades 2 (three in this example), a hub 11, and the main shaft 9 on which the hub 11 is housed. Each blade 2 is arranged radially around the hub 11 and connected to the main shaft 9 by the hub 11. The main shaft 9 is rotatably supported by a main bearing (not shown) in the nacelle 4 and transmits rotational force via a speed increaser 6. The output shaft (high-speed shaft 10) of the speed increaser 6 is connected to the generator 8 via a brake device 7. In this example, the brake device 7 is provided on the high-speed shaft 10, but it may also be provided on the main shaft 9. As a result, when the blades 2 receive wind and rotate, the rotor 3 rotates, and the rotational force is transmitted to the speed increaser 6 via the main shaft 9. The speed increaser 6 increases the rotational speed, and this is transmitted to the generator 8. The generator 8 converts the rotational energy of the rotor 3 into electrical energy and outputs it.

[0036] The generator 8 is electrically connected to a grid connection facility (not shown) installed on the ground via a power supply path (not shown) that runs through the tower 5. As a result, the electricity generated by the horizontal-axis wind turbine 1 is sent to the grid connection facility through the power supply path.

[0037] Furthermore, each blade 2 is equipped with a variable pitch mechanism 12, which allows the pitch angle to be optimally adjusted according to the wind speed and power generation conditions. A pitch control device (not shown) located inside the nacelle controls the angle (pitch angle) of the blades 2 with high precision using electric or hydraulic actuators.

[0038] In addition, the horizontal-axis wind turbine 1 is equipped with an anemometer 13 on top of the nacelle 4 to measure wind direction and speed, enabling appropriate control according to the wind direction and speed. This anemometer 13 supplies important data for controlling the yaw angle and pitch of the wind turbine, playing a crucial role in optimizing power generation efficiency and ensuring the safety of the equipment. The wind direction and speed meter 13 may be an integrated type or a separator type in which the wind direction meter and wind speed meter are separated. In this example, a separator type is used, and the wind speed meter 14 and wind direction meter 15 are installed side by side in close proximity.

[0039] As shown in Figure 2(b), the anemometer 14 is mounted on a rotating shaft 14a that is vertically positioned on the top of the nacelle 4 and has the main structure for measuring wind speed. A rotating part 14b (composed of a propeller or cups, in this example cups) is attached to this rotating shaft 14a, which rotates when it receives wind, and generates a rotational speed corresponding to the wind speed. If the rotating part 14b is a cup, it is usually composed of three or four cups and is designed to efficiently capture wind. This generates a constant rotational motion proportional to the wind speed, which is transmitted through the rotating shaft 14a to an internal sensor and measured as wind speed data. Anemometers 14 come in analog and digital types. In the analog type, the speed of the rotating shaft 14a is output as a voltage change, while in the digital type, it is converted into a pulse signal via an electromagnetic induction sensor or optical encoder. Digital anemometers process wind speed data in real time and transmit it to the turbine control system to support the optimal operation of the wind turbine. Thus, the anemometer 14 mounted on the vertical rotating shaft 14a at the top of the nacelle plays an important role in the efficient operation of the wind power generation equipment.

[0040] As shown in Figure 2(c), the wind vane 15 is mounted on a rotating shaft 15a that is vertically installed on the top of the nacelle 4, and its role is to measure the direction of the wind. Angle sensors such as potentiometers (variable resistance type) and optical encoders (pulse count type) are attached to the rotating shaft 15a, and accurate angle data is acquired in response to changes in wind direction. This data is converted into a digital signal and transmitted to the wind turbine control system, where it is used as data for yaw control. A wind direction indicator (vane) 15b is attached to this rotating shaft 15a, and it rotates when it receives wind, indicating the correct direction according to the wind direction. The wind direction indicator 15b is designed with a small tip 15c that points upwind and a large tail 15d on the leeward side. This shape allows it to naturally align in a stable position when it receives wind. The rotating shaft 15a incorporates a high-precision bearing, which allows for smooth operation with reduced friction, enabling immediate response to changes in wind direction.

[0041] The anemometer 14 and wind vane 15 are installed at the very top of the nacelle 4 to minimize the influence of the tower 5 and to accurately measure the surrounding wind direction. Furthermore, these sensors (anemometer 14, wind vane 15) are positioned on the central axis of the rear end (leeward side) of the nacelle 4 to minimize the effects of turbulence caused by the wake effect (wake flow) of the blades 2. This arrangement makes it easier for the anemometer 14 and wind vane 15 to acquire stable wind direction and speed data. However, since sensors installed at the rear end of the nacelle may be affected by the wake effect, the measurement data is corrected. Based on the corrected data, highly accurate yaw control is achieved, optimizing the power generation efficiency of the wind turbine.

[0042] In the above configuration, in wind power generation, it is essential to appropriately control the yaw angle of the nacelle 4 (the direction of the rotation axis of the blades 2) in order to maximize power generation efficiency and ensure the safety of the equipment. The yaw angle of the nacelle 4 refers to the orientation of the nacelle, that is, the direction normal to the rotation plane of the blades (the direction of the rotor's main axis), and by maintaining this at an optimal angle, wind energy can be utilized to the fullest extent. Therefore, the following describes methods for controlling the yaw angle of the nacelle according to wind direction. In particular, we will focus on the following three methods and describe their characteristics and advantages in detail. • Methods using machine learning equipment (learning model-based approach) • A method for rapidly measuring wind direction in real time and controlling the yaw angle of the nacelle based on the measured wind direction (using wireless bidirectional time synchronization technology). • A method for rapidly measuring wind direction in real time and controlling the optimal nacelle yaw angle using a learned model based on the measured wind direction (using wireless bidirectional time synchronization technology + learned model).

[0043] (Embodiment 1) Method using a machine learning device (learning model utilization type) In this example, to appropriately control the yaw angle of the nacelle 4 (the normal direction to the rotation plane of the blades 2) using wind direction data measured by the wind vane 15, a learning model 25 is formed using a machine learning device 20, and this learning model 25 is used to estimate the optimal yaw angle of the nacelle 4. As shown in Figure 3(a), the machine learning device 20 is configured as a device connected to a communication network N and includes an input data acquisition unit 21 that acquires data sets including wind direction data measured by an anemometer 15 and installation position information of the horizontal axis wind turbine 1 as input data, a label acquisition unit 22 that acquires data sets including the optimal yaw angle of the nacelle 4 that maximizes power generation efficiency as labels, and a learning model construction unit 23 that constructs a learning model 25 by performing supervised learning using the input data and label pairs as training data.

[0044] Here, the input data to be input to the input data acquisition unit 51 may be input directly from each sensor via the communication network N, or the data from each sensor may be temporarily stored in a data storage unit (not shown) of the control center, and this stored data may be used as input data. By using such a learning model 25, yaw control of the nacelle 4 is performed as shown in Figure 3(b). Specifically, wind direction data obtained from the wind vane 15 is acquired along with the installation position information of the horizontal axis wind turbine 1 and the current yaw angle data of the nacelle 4 (step S21), and the learning model is used to estimate the optimal yaw angle of the nacelle that maximizes power generation efficiency, using the wind direction data from the wind vane and the installation position information of the horizontal axis wind turbine 1 as input data (step S22).

[0045] The wind direction detected by the wind vane 15 is not necessarily the optimal yaw angle that maximizes power generation efficiency. In basic yaw control (simple wind direction following control), after the wind direction is determined by the wind vane, the yaw angle of the nacelle 4 is adjusted to match the wind direction. However, considering the wake effect (decrease in wind speed and turbulence downstream of the wind turbine), it may be possible to improve power generation efficiency by slightly offsetting the yaw angle rather than simply aligning it directly with the wind direction. Furthermore, when the wind direction changes rapidly, energy loss increases if the nacelle continues to rotate constantly, so it is considered effective to consider a delay in the optimal yaw angle (yaw response delay). In addition, a yaw angle that deviates from the wind direction determined by various other factors may become the optimal yaw angle.

[0046] Therefore, the optimal yaw angle of the nacelle 4 that maximizes power generation efficiency under various conditions is learned in advance, and the optimal yaw angle of the nacelle 4 is estimated from input data including wind direction data from the wind vane 15 and installation position information of the horizontal axis wind turbine 1 using the learned model 25. It is then determined whether the current yaw angle of the nacelle 4 matches the estimated optimal yaw angle (step S23), and if they do not match, the nacelle 4 is driven to rotate toward the optimal yaw angle (step S24). This enables highly accurate yaw angle control that responds immediately to changes in wind direction, maximizing the power generation efficiency of wind turbines.

[0047] Furthermore, unlike conventional simple real-time control of wind direction data, utilizing machine learning models allows for the estimation of the optimal yaw angle considering past wind direction patterns and environmental factors, thus improving adaptability to sudden wind direction changes. This suppresses unnecessary rotation of the nacelle while ensuring that the blades are always positioned for the optimal wind direction, thereby reducing wasted energy consumption. Furthermore, this method allows for optimal control that takes into account not only wind speed and direction, but also topographical factors specific to each installation site and the influence of surrounding wind turbines (wake effect). Compared to conventional fixed yaw control methods, it can maximize power generation efficiency with higher precision. In addition, by utilizing predictive control based on machine learning, it is possible to detect the occurrence of gusts and turbulence in advance and coordinate the control of the blade pitch angle and yaw, thereby reducing the load on the wind turbine and minimizing mechanical stress. This also contributes to improving the durability of wind power generation equipment and reducing maintenance costs. Therefore, the present invention enables advanced yaw angle control using machine learning, simultaneously achieving improved power generation efficiency, extended equipment lifespan, and reduced operating costs for wind power generation facilities.

[0048] (Embodiment 2) Method for rapidly measuring wind direction in real time (using wireless bidirectional time synchronization technology) Next, we will explain yaw angle control using wireless bidirectional time synchronization technology. In horizontal-axis wind turbines, rapid response to changes in wind direction is essential for maximizing power generation efficiency and ensuring equipment safety. In particular, in environments where wind direction changes frequently, if the yaw angle adjustment of the nacelle is delayed, the angle of attack of the blades will not be properly maintained, which can not only reduce power generation efficiency but also potentially place excessive load on the blades and generator. Therefore, with conventional methods involving periodic data collection and control, there were times when it was difficult to maintain optimal power generation efficiency due to delays in responding to changes in wind direction.

[0049] This method utilizes wireless bidirectional time synchronization technology to accurately acquire wind direction data measured by the anemometer 15 in real time and immediately reflect it in the yaw angle adjustment of the nacelle. Conventional wired network systems sometimes experienced communication delays due to the widespread distribution of wind power generation equipment. However, this method, by accurately synchronizing the time of wireless communication, enables multiple wind turbines to acquire and share wind direction data almost simultaneously, allowing for immediate coordinated control. This technology makes it possible to improve the wind direction adaptability not only of individual wind turbines but also of the entire wind power plant. For example, when multiple wind turbines are installed, by adjusting the yaw angle of each nacelle while considering the effects of wind speed and wind direction (wake effect) between the turbines, the entire wind turbine group can achieve optimal power generation efficiency. Furthermore, because it can respond immediately to strong winds and sudden changes in wind direction, it reduces the load on the blades and generators, and contributes to improving the durability of the equipment.

[0050] Based on the above background, this method utilizes wireless bidirectional time synchronization technology to improve the accuracy of wind direction data acquisition while achieving rapid yaw angle control. The wind direction control system that realizes this is described in detail below. As shown in Figure 1, the wind direction control system S includes a first device 30 positioned within a distance that allows transmission and reception to as many horizontal-axis wind turbines as possible on the site where the horizontal-axis wind turbines are located, a second device 40 fixed to the tail of the wind direction indicator 15b of the wind vane 15 provided on each horizontal-axis wind turbine, that is, the part opposite to the tip of the wind direction support part with respect to the rotation axis of the wind vane 15, a third device 50 fixed to the part of the nacelle opposite to the blade 2 with respect to the rotation axis, a fourth device 60 fixed to the movable part of the anemometer 14, specifically the wind receiving part that is off the rotation axis, and a server device 70. The first device 30 may be fixed to nearby transmission towers, utility poles, or streetlights, or to a dedicated mounting pole P fixed to the ground. It may also be installed on the surface of artificial fixed objects such as observation decks, huts, observatories, rest areas, bridges, stairs, signposts, and information boards, or on natural fixed objects such as mountains and rocks. Furthermore, it may be embedded in these fixed objects in a manner that allows it to communicate with the outside.

[0051] These first devices 30 can acquire their own three-dimensional position information using GPS or the like. This three-dimensional position information of the first device 30 may be acquired in advance and stored in a readable format inside the first device 30, or it may be acquired retrospectively by some means after the system has been started. Furthermore, the three-dimensional position information of the first device 30 may be compiled into a database and stored in the memory unit (storage unit 73 described later) of the server device 70. Here, the three-dimensional position information may be represented, for example, by latitude, longitude, and ellipsoidal height in the WGS8 coordinate system, or by a unique three-dimensional coordinate system set up for each area indoors.

[0052] The second device 40 is preferably positioned parallel to or on a virtual line (for example, on the wind direction indicator) that passes the rotation axis of the wind vane, in order to accurately measure the wind direction. The third device 50 is preferably positioned on a virtual line parallel to the main shaft 9 that passes the rotation axis of the nacelle 4 (for example, at the rear end of the nacelle located on the extension of the main shaft) in order to accurately measure the yaw angle of the nacelle.

[0053] The first device 30 and the second device 40, the first device 30 and the third device 50, and the first device 30 and the fourth device 60 can communicate directly with each other. In addition, the first device 30 can be connected to the server device 70 via the communication network N, and the second devices 40 to the fourth devices 60 can also be connected to the server device 70 via the communication network N. Each of the first device 30, second device 40, third device 50, and fourth device 60 has an internal clock, and these internal clocks can be synchronized to a reference time by a method described later. Furthermore, the first device 30 can function as the first device 30 in relation to multiple second devices 40, third devices 50, and fourth devices 60.

[0054] (Regarding the first device) As shown in Figure 5, the first device 30 comprises a control unit 31, an RF chip 32, and an oscillator 33, each connected by a bus. It also includes a RAM 34 and a storage unit 35, each connected to the control unit 31 by a bus.

[0055] The control unit 31 consists of a CPU and ROM, and executes programs stored in ROM to control the first device 30. The RF chip 32 is equipped with at least a clock 36, but may also be equipped with a phase detector. The RF chip 32 also has the function of processing the transmission and reception of wireless signals, and the data received by the RF chip 32 is subject to calculation processing by the control unit 31. The RAM 34 is the work area of ​​the control unit 31, and the storage unit 35 is a storage area for saving programs, data, etc.

[0056] The oscillator 33 oscillates at a predetermined frequency and outputs a signal to provide the operating timing for each part of the device. A crystal oscillator or an atomic oscillator can be used as the oscillator 33. The clock 36 keeps time using the output signal of the oscillator 33 as the source oscillation and outputs the time. The time kept by the clock 36 is controlled by the control unit 31 to be transmitted to the second device 40 (or the third device 50 or the fourth device 60) via the RF chip 32. If a phase detector is also provided, it detects the phase of the carrier wave that constitutes the information received from the second device 40 (or the third device 50 or the fourth device 60), and also detects the phase of the signal transmitted by the oscillator 33 of the first device 30.

[0057] The RF chip 32 is capable of sending and receiving data with other computer devices. Data received by the RF chip 32 is stored in the RAM 34 or storage unit 35 and is subject to calculation processing by the control unit 31. When the three-dimensional position information of the first device 30 is received via the RF chip 32, it is stored in the RAM 34 or storage unit 35 and controlled by the control unit 31 to be transmitted via the RF chip 32 to the second device 40 (or the third device 50 or the fourth device 60).

[0058] In this wind power generation facility S, the installation location of the first device 30 is not particularly limited, but since the installation location of the horizontal axis wind turbine 1 is specified, it is preferable to install it in a location that has a good line of sight from as many horizontal axis wind turbines as possible, and the location should be appropriately selected according to the surrounding infrastructure conditions, etc.

[0059] In order to obtain three-dimensional positional information of the second device 40, the first device 30 does not need to be installed on the same plane, and it is preferable that adjacent first devices 30 be installed at different heights. For example, even when the first device 30 is attached to a nearby fixed object, it is preferable to make the mounting height of the first device 30 different for each fixed object.

[0060] Furthermore, the location information of the installation site of the first device 30 may be stored in its own storage unit 35 in association with identification information that can identify the first device 30, or stored in the storage unit 73 of the server device 70, or it may be made available via the communication network N from another management server that manages location information.

[0061] (Regarding the second device) Since the second device 40, the third device 50, and the fourth device 60 have similar configurations, we will explain the configuration of the second device 40, and omit the explanations for the third device 50 and the fourth device 60. The second device 40 is attached to the wind vane 15 of the horizontal axis wind turbine 1, and may be fixed to the surface of the wind vane 15, for example, the wind direction indicator 15b, by an appropriate adhesive means, or it may be embedded in the wind vane 15.

[0062] As shown in Figure 6, the second device 40 comprises a control unit 41, an RF chip 42, and an oscillator 43, each connected by a bus. It also includes a RAM 44 and a storage unit 45, each connected to the control unit 41 by a bus.

[0063] The RF chip 42 includes at least a clock 46, but may also include a phase detector if necessary.

[0064] The control unit 41 is configured with a CPU and ROM, and executes programs stored in the storage unit 45 to control the second device 40. The RAM 44 is the work area of ​​the control unit 41, and the storage unit 45 is a storage area for saving programs and data. The control unit 41 performs calculation processing based on programs and data read from the RAM 44 and the storage unit 45, as well as data input from an input unit (not shown).

[0065] The RF chip 42 is capable of sending and receiving data with other computer devices. The data received by the RF chip 42 is loaded into the RAM 44 and subjected to calculation processing by the control unit 41.

[0066] The oscillator 43 oscillates at a predetermined frequency and outputs a signal to provide the operating timing for each part of the device. A crystal oscillator or an atomic oscillator can be used as the oscillator 43. The clock 46 uses the output signal of the oscillator 43 as the source oscillation and outputs the time. The time marked by the clock is controlled by the control unit 41 to be transmitted to the first device 30 via the RF chip 42. If a phase detector is also present, it detects the phase of the carrier wave that constitutes the information received from the first device 30, and also detects the phase of the signal oscillated by the oscillator 43 of the second device 40.

[0067] The third device 50 and the fourth device 60 have the same configuration as the second device 40. They transmit and receive signals or information with the first device 30, calculate the distance to the first device 30 based on the transmission and reception times, and calculate the positions of the third device 50 and the fourth device 60 in real time based on that distance and the position information of the first device 30.

[0068] (Regarding server equipment) Next, the server device 70 of the present invention will be described. The server device 70 can acquire location information from the second device 40, the third device 50, and the fourth device 60.

[0069] The acquired location information of each device is transmitted to the server device 70, associated with identification information that can identify each device and the time when the location information was determined. The server device 70 may also enable communication between each device (the first device 30 and the second device 40, the first device 30 and the third device 50, and the first device 30 and the fourth device 60) via smart meters installed in houses, electrical equipment, etc., around the horizontal axis wind turbine 1.

[0070] Figure 7 is a block diagram showing the configuration of a server device 70 according to an embodiment of the present invention. The server device 70 comprises at least a control unit 71, a RAM 72, a storage unit 73, and a communication interface 74, each connected by an internal bus. It also includes a database 75 for storing information received from the first device 30 and the second to fourth devices 40 to 60. The location information of the first device 30 may also be stored in this database 75.

[0071] The control unit 71 consists of a CPU, ROM, etc., and executes programs stored in the storage unit 73 to control the server device 70. The control unit 71 also has an internal timer for measuring time. The RAM 72 is the work area of ​​the control unit 71. The storage unit 73 is a storage area for saving programs and data. The control unit 71 reads programs and data from the storage unit 73 and RAM 72, and, based on information received from the first device 30 or the second device 40, executes various control processes in the control unit according to the program.

[0072] (Distance calculation process) Using the above configuration, the process for calculating the distance between the first device 30 and the second device 40 will now be explained. The processes for calculating the distances between the first device 30 and the third device 50, and between the first device 30 and the fourth device 60 are similar and will therefore be omitted.

[0073] This distance calculation process calculates the distance between each of the first devices 30 and the second device 40 based on the propagation time Tp of the information or signal between each of the first devices 30 and the second device 40, provided that the first devices 30 and the second device 40 are within a distance range from which they can mutually send and receive information or signals.

[0074] The distance calculation process is performed at predetermined time intervals (for example, every 10 seconds) or whenever predetermined conditions are met, and the processes in steps S1 to S16 shown in Figure 8 are carried out. For convenience, here we will explain the case of calculating the distance between one first device 30 and one second device 40.

[0075] First, information or signals are transmitted from the first device 30 to the second device 40 (step S1). The information or signals transmitted from the first device 30 to the second device 40 are not particularly limited.

[0076] In the first device 30, the time (T11) when information or a signal was transmitted in step S1 is recorded (step S2), and this recorded time is stored in the memory or storage unit 35 within the control unit 31 (step S3).

[0077] Subsequently, the second device 40 receives the information or signal from the first device 30 (step S4). The second device 40 records the time (T21) when the information or signal was received in step S4 (step S5). The recorded time (including the measured phase if one is measured) is then stored in the memory or storage unit 45 of the control unit 41 (step S6).

[0078] Next, the second device 40 transmits information or a signal to the first device 30 (step S7). The information or signal transmitted from the second device 40 to the first device 30 is not particularly limited. The second device 40 records the time (T22) when the information or signal was transmitted in step S7 (step S8). Then, the recorded time is stored in the memory or storage unit 45 of the control unit 41 (step S9).

[0079] The first device 30 receives the information or signal transmitted in step S7 (step S10). The first device 30 records the time (T12) at which it received the information or signal in step S10 (step S11). The recorded time (including the measured phase if the phase is measured) is then stored in the memory or storage unit 35 of the control unit 31 (step S12).

[0080] Subsequently, the first device 30 transmits to the second device 40 via its RF chip 32 the information stored in step S3 regarding the time (T11) when the signal was transmitted in step S1, and the information stored in step S12 regarding the time (T12) when the signal was received in step S10 (step S13). At this time, the position information of the first device 30 is also transmitted to the second device 40.

[0081] Then, the second device 40 receives information regarding the time (T11) when the first device 30 transmitted information or a signal in step S1, and information regarding the time (T12) when the first device 30 received information or a signal in step S10 (step S14).

[0082] Next, the second device 40 calculates the distance between the first device 30 and the second device 40 (step S15). This distance is calculated in the following manner.

[0083] Information regarding the time (T11) of the first device 30 is transmitted to the second device 40 via radio waves. The difference between the time (T21) of the second device 40's clock at the time of receiving this information and the time (T11) of the second device 40 is recorded as ΔTa on the second device side. That is, if we define the time of the first device 30's clock at the time of transmission of information or a signal from the first device 30 to the second device 40 as T11, and the time of the second device 40's clock at the time of transmission of information or a signal from the first device 30 to the second device 40 as T21, and the difference between them as ΔTa, then this ΔTa (the difference in transmission and reception times when information or a signal is transmitted from the first device 30 to the second device 40) is the difference between the time of the first device 30's clock and the second device 40's clock (time difference: T20-T10) plus the propagation time (propagation delay) Tp, resulting in the relationship shown in Equation 1. This time difference (T20-T10) would be zero if the clocks of the first device 30 and the second device 40 were synchronized, but here we assume that a time difference (T20-T10) exists (they are not synchronized). [Formula 1] ΔTa=T21-T11=(T20-T10)+Tp

[0084] To determine this propagation time Tp, the second device 40 also sends information about the time of its clock (T22) to the first device 30, and the difference between this information and the time of the first device 30's clock (T12) when the first device 30 receives it is recorded as ΔTb on the first device side. That is, if we define the time of the second device 40's clock when it transmits information or a signal from the second device 40 to the first device 30 as T22, and the time of the first device 30's clock when it receives the information or signal transmitted from the second device 40 and sets time as T12, and the difference between them as ΔTb, then this ΔTb (the difference in transmission and reception times when information or a signal is transmitted from the second device 40 to the first device 30) is the difference between the time of the first device 30's clock and the second device 40's clock (time difference: T10-T20) plus the propagation time (propagation delay) Tp, resulting in the relationship shown in Equation 2. Here too, the time difference (T10-T20) would be zero if the clocks of the first device 30 and the second device 40 were synchronized, but here we assume that a time difference (T10-T20) exists (they are not synchronized). [Formula 2] ΔTb=T12−T22=(T10−T20)+Tp

[0085] The time differences between the two clocks, (T20-T10) and (T10-T20), are added when transmitting from the first device 30 to the second device 40. When transmitting from the second device 40 to the first device 30, the same amount of time difference is subtracted. Therefore, to find the propagation time Tp, by summing equations 1 and 2, the terms for the time differences (T20-T10) and (T10-T20) cancel each other out, resulting in the relationship shown in equation 3. [Formula 3] Tp=(ΔTa+ΔTb) / 2 =((T21-T11)+(T12-T22)) / 2

[0086] Therefore, the propagation time Tp can be calculated based only on the time read by the clock of the first device 30 and the time read by the clock of the second device 40.

[0087] Incidentally, the time difference (T10-T20) between the clock of the first device 30 and the clock of the second device 40 is given by the relationship in Equation 4, obtained by [Equation 1] - [Equation 2]. [Formula 4] (T10-T20)=(ΔTa−ΔTb) / 2

[0088] Subsequently, the distance between the first device 30 and the second device 40 is calculated by multiplying the propagation time calculated using Equation 3 by the propagation speed of the information or signal (e.g., high speed) (step S15).

[0089] Then, the distance between the first device 30 and the second device 40 calculated in step S15 is stored in the memory or storage unit 45 of the control unit 41 and transmitted to the server device 70 (step S16). By executing step S16, the distance calculation process is completed.

[0090] Therefore, since equation (3) for calculating the propagation time Tp does not include a term for the time difference (time difference: T20-T10) between the clocks of the first device 30 and the second device 40, it is possible to calculate the propagation time for information or signals to propagate between the first device 30 and the second device 40, regardless of whether there is a time difference between the clocks of the first device 30 and the second device 40 (independent of the time difference (time difference: T10-T20) between the clocks of the first device 30 and the second device 40).

[0091] [Location identification process] Next, the process for determining the position of the second device 40 will be described. This position determination process determines the position of the second device 40 based on the distances between each of the multiple first devices 30 and the second device 40, which were calculated in the distance calculation process. Since the second device 40 is located at the tail end of the wind direction indicator 15b of the wind vane 15, this process can be described as determining the position of the tail end of the wind vane 15 (the direction of the second device 40 with respect to the rotation axis 15a of the wind vane 15).

[0092] It is desirable that this position determination process be performed immediately after the distance calculation process is completed. Furthermore, in order to determine the position of the second device 40, it is assumed that the distance calculation device has calculated the distance to each of the multiple first devices 30 for each of the second devices 40.

[0093] In other words, when obtaining positional information (planar positional information) of the second device (when obtaining x and y coordinates), the position of the second device 40 can be determined by a well-known multipoint surveying calculation method based on the distance between one second device 40 and at least three first devices 30, and the positional information of each of the three first devices 30 used to calculate this distance. Therefore, since this system can determine the two-dimensional position of the second device 40 if it can obtain three or more data points of the distance between the first device 30 and the second device 40, it is necessary to appropriately distribute the first devices 30 so that information or signals can be sent and received between at least three first devices 30 for each horizontal axis wind turbine 1.

[0094] Figure 9 shows a flowchart of the location determination process according to an embodiment of the present invention. This location determination process can be performed on either the first device 30, the second device 40, or the server device 70. When the location determination process is performed on the first device 30 or the server device 70, the distance between each of the multiple first devices 30 and the second device 40, as well as the location information of the first devices 30, can be associated with the identification information of the second device 40, transmitted to the first device 30 or the server device 70, and used. Here, an example of performing the location determination process on the server device 70 will be described.

[0095] First, the position determination process does not require three-dimensional positional information; wind direction can be determined if two-dimensional positional information (positional information in the horizontal plane) is known. Therefore, it is necessary that distance information for at least three different first devices 30 and second devices 40 be obtained at the same time or close together. Here, close together means that the time at which the distances of the three first devices 30 and second devices 40 used to determine the position of the second device 40 were calculated is within a range that does not hinder the capture of the movement of the second device 40. If the calculations are not made at the same time or close together (for example, if the time at which the propagation time of information or signals between each of the multiple first devices 30 and the second device 40 was measured is the same time or close together), it becomes difficult to accurately determine the position of the second device 40, assuming that it is moving.

[0096] Therefore, first, it is determined whether or not three or more data points of the distance between the first device 30 and the second device 40 have been acquired within a predetermined time range (step S31).

[0097] If three or more distance data points between the first device 30 and the second device 40 are not acquired within a predetermined time frame, accurate two-dimensional positional information cannot be obtained using this positioning method, and the subsequent calculations will be terminated. In contrast, if three or more distance data points between the first device 30 and the second device 40 can be acquired within a predetermined time range, three-dimensional position information can be obtained with high accuracy using this position determination method utilizing wireless bidirectional time comparison, and the current position of the second device 40 can be determined using the multi-point surveying calculation method described above (step 32). At the same time, it is preferable to store the position information of the second device 40 along with the time it was calculated in the storage unit 73 of the server device 70 for use in subsequent processing (step 33). Therefore, the position of the displaced second device 40 can be captured in real time.

[0098] (Calculation of wind direction using an anemometer) By the way, in order to determine the wind direction of the wind vane 15, the position of the rotation axis 15a of the wind vane 15 needs to be determined. However, the position of the rotation axis 15a of the wind vane 15 is also displaced around the yaw bearing 16 by the yaw control of the nacelle, as shown in Figure 10. Therefore, even if the precise position of the second device 40 can be determined, if the position of the rotation axis 15a of the wind vane 15 at that time is different, the wind direction will be different. Therefore, since the position of the rotation axis 15a of the wind vane 15 on the nacelle 4 is fixed, if the orientation (yaw angle) of the nacelle 4 is known, the position of the rotation axis 15a of the wind vane 15 can be determined from the orientation of the nacelle 4, and the accurate wind direction can be calculated from this determined position of the rotation axis 15a of the wind vane 15 and the position of the second device 40.

[0099] Based on the above, first, in order to determine the orientation of the nacelle, the position of the third device 50 is identified as shown in Figure 11, and the direction of the straight line connecting the position of the third device 50 and the rotation center C of the nacelle (center of the yaw bearing) (the yaw angle of the nacelle) is calculated. As mentioned above, the third device 50 is located on a virtual line parallel to the main shaft 9 that passes the rotation axis of the nacelle 4 (the rear end of the nacelle located on the extension of the main shaft), so first, the position of the third device 50 is identified using the method shown in Figure 8 (step S41).

[0100] Once the position of the third device 50 is determined, the rotation center C of the nacelle is a predetermined fixed position. Therefore, the orientation of the nacelle 4 (yaw angle of the nacelle) is determined by the straight line connecting the rotation center C of the nacelle and the position of the third device 50 (step S42). Once the yaw angle of the nacelle 4 is determined, the position of the rotation center of the wind vane located on top of the nacelle in that orientation can be determined (step S43). By calculating the direction of the straight line connecting the calculated position of the second device 40 and the rotation center of the wind vane, the accurate wind direction can be calculated (step S44).

[0101] After the wind direction is calculated in this manner, the yaw drive device is driven and controlled to match the current orientation of the nacelle (the direction connecting the position of the third device and the rotation center C of the nacelle) to the wind direction calculated in the previous step (step S45). By employing this type of control, it becomes possible to instantly change the orientation of the nacelle to match the wind direction.

[0102] (Embodiment 3) A method for rapidly measuring wind direction in real time and controlling the optimal nacelle yaw angle using a learning model based on the measured wind direction (using wireless bidirectional time synchronization technology + learning model). Incidentally, in the above configuration, the wind direction was determined using wireless bidirectional time synchronization technology, and the yaw angle of the nacelle was controlled to match that wind direction. This is because, theoretically, this arrangement is considered optimal for the blades to receive the wind head-on. However, such control alone does not necessarily maximize power generation efficiency.

[0103] As mentioned earlier, when multiple horizontal-axis wind turbines are arranged in a row, considering the wake effect (decrease in wind speed and turbulence downstream of the turbine), it is sometimes possible to improve power generation efficiency by slightly offsetting the turbines rather than simply aligning them directly with the wind direction. For example, by slightly offsetting the nacelle from the wind direction (yaw offset control), the effects of the wake (downstream) can be minimized, and interference with adjacent turbines can be reduced. Furthermore, when wind direction changes drastically, continuous rotation of the nacelle leads to significant energy loss; therefore, it is effective to consider an optimal yaw angle delay (yaw response delay).

[0104] Therefore, after calculating the wind direction and nacelle orientation using the method described above, it is advisable to estimate the nacelle yaw angle that maximizes power generation efficiency using the machine learning device 20 shown in Figure 2(a). In other words, the machine learning device 20 includes an input data acquisition unit 21 that acquires past wind direction data and installation position information of the horizontal axis wind turbine 1 as input data, a label acquisition unit 22 that acquires a data set including the optimal yaw angle of the nacelle (normal direction of the blade rotation surface) at the time of data acquisition as labels, and a learning model construction unit 23 that constructs a learning model 25 by performing supervised learning using the input data and label set as training data. Using the learning model 25 formed by such a machine learning device 20, the optimal nacelle yaw angle (direction of the blade rotation axis) that maximizes power generation efficiency for the wind conditions and installation location may be estimated from wind direction, nacelle orientation, and horizontal axis wind turbine installation location information identified using wireless bidirectional time synchronization technology.

[0105] By using such a learning model 25, yaw control of the nacelle 4 is performed as shown in Figure 12. Specifically, the wind direction data obtained in step 44 is acquired along with the installation position information of the horizontal axis wind turbine 1 and the current yaw angle data of the nacelle 4 (step S51), and the learning model 25 is used to estimate the optimal yaw angle of the nacelle that maximizes power generation efficiency, using the wind direction data from the anemometer 15 and the installation position information of the horizontal axis wind turbine 1 as input data (step S52). Then, it is determined whether the current yaw angle of the nacelle 4 matches the estimated optimal yaw angle (step S53). If they do not match, the nacelle 4 is driven to rotate toward the optimal yaw angle (step S54).

[0106] This enables rapid acquisition of wind direction data and high-precision yaw angle control that responds immediately to changes in wind direction, thereby maximizing the power generation efficiency of wind power generation equipment. Furthermore, unlike conventional simple real-time control of wind direction data, utilizing machine learning models allows for the estimation of the optimal yaw angle considering past wind direction patterns and environmental factors, thus improving adaptability to sudden wind direction changes. This suppresses unnecessary rotation of the nacelle while ensuring that the blades are always positioned for the optimal wind direction, thereby reducing wasted energy consumption.

[0107] In the above system, when calculating wind direction, the position of the second device 40 is identified, and the position of the third device 50 is identified to determine the orientation of the nacelle 4, thereby calculating the position of the rotation axis 15a of the wind vane 15. The wind direction is then calculated from the position of the rotation axis 15a of the wind vane 15 and the position of the second device 40. However, a fifth device similar to the second device 40 may be attached to the rotation axis 15a of the wind vane 15, and the position of the rotation axis of the wind vane may be directly identified using the aforementioned bidirectional time synchronization technology. The wind direction may then be calculated from the position of the rotation axis 15a of the wind vane 15 and the position of the second device 40.

[0108] Furthermore, the above yaw angle control methods omitted the wind speed parameter. However, by incorporating wind speed information, the following additional control methods may be added. Wind speed information may be obtained using a conventional anemometer 14, but in this example, as shown in Figure 13, a fourth device 60 provided on the rotating part 14b (e.g., cup) of the anemometer 14 may be used to capture the position of the fourth device 60 in real time using the wireless bidirectional time synchronization method shown in Figure 8 (step S61), and the wind speed may be calculated from the change in the position of the fourth device 60 per unit time (number of rotations per unit time) (step S62).

[0109] Then, by monitoring the displacement of this fourth device 60, it is determined whether the wind speed obtained is within the rated wind speed (step S63). If it is within the rated wind speed, the current state is maintained (step S64). On the other hand, if it is determined that the wind speed exceeds the rated wind speed, protective control is performed, such as changing the pitch angle of the blade 2 or stopping the rotation of the blade (step S65).

[0110] This ensures the optimal yaw angle of the blades for maximum power generation efficiency, while limiting the rotational speed by changing the blade pitch angle to the feathering direction when the wind speed significantly exceeds the rated wind speed. If the wind speed increases further and reaches a dangerous level, the safety of the wind turbine is ensured by activating the braking device. In addition, when gusts or sudden changes in wind direction are detected, the nacelle yaw angle and blade pitch angle are adjusted in advance to reduce the load, enabling long-term stable operation of the power generation equipment.

[0111] (Coordinated control between wind turbines) Furthermore, when multiple horizontal-axis wind turbines are installed in a wind power generation facility, it is possible to perform the yaw control described above on each turbine independently. However, individual control that does not consider the influence between wind turbines may lead to a decrease in power generation efficiency due to the wake effect. Therefore, for example, it may be possible to maximize the overall energy conversion efficiency of the facility by adopting linked control that uses the yaw angle of the upwind wind turbine as a reference and adjusts the orientation of the nacelle of the downwind wind turbine accordingly. In implementing this linked control system, the yaw angle of the wind turbine on the windward side is determined based on real-time wind direction and wind speed. Furthermore, using anemometer data and wind turbine installation location information as input data, a machine learning model is used to estimate the yaw angle that maximizes power generation efficiency. In addition to simple wind direction tracking control, it is possible to calculate the optimal yaw angle considering the wake effect and activate the yaw motor to adjust the nacelle to the appropriate direction. After the yaw angle of the upwind wind turbine is determined, the yaw angle of the upwind wind turbine's nacelle is obtained and transmitted to the downwind wind turbine to adjust the direction of its nacelle appropriately. While simple wind direction tracking is possible, adaptive control that takes the yaw angle of the upwind wind turbine into account can achieve more precise yaw angle control.

[0112] Additionally, the yaw angle may be adjusted according to the distance between wind turbines to minimize the wake effect's impact on downwind turbines. For example, downwind turbines close to upwind turbines may use almost the same yaw angle as the upwind turbines, and gradually adjust it as the distance increases to suppress energy loss. Furthermore, by utilizing wireless bidirectional time synchronization technology, wind direction measurement data can be shared between wind turbines in real time, reducing delays in information transmission between turbines and enabling more accurate coordinated control. This technology makes it possible to respond quickly to wind direction changes that were previously difficult to address with conventional periodic data collection and control methods, thereby optimizing the power generation efficiency of the entire wind turbine group. Thus, in the coordinated control of the present invention, while using the yaw angle of the upwind wind turbine as a reference, the downwind wind turbine is adjusted to maintain the optimal orientation of its nacelle. This maximizes the power generation efficiency of the entire wind power generation facility, optimizes the load on the facility, and ensures long-term operational reliability.

[0113] Furthermore, the aforementioned work site management system S can also be provided in the form of a program (work site management program) that causes a computer to execute each step of the work site management method described above. [Explanation of Symbols]

[0114] 1 Horizontal axis wind turbine 2 Blades 3 rotors 4 Nasser 5 Towers 14 Anemometer 15 Wind vane 15a Rotation axis 20 Machine Learning Devices 21 Input data acquisition unit 22 Label acquisition unit 23 Learning Model Construction Department 25 Learning Models 30 1st device 40 Second device 50 Third device 60 4th device 70 Server Devices

Claims

1. A control device for a horizontal-axis wind turbine, comprising: a blade that rotates in response to wind; a nacelle that rotatably supports the blade; a tower that yaw-rotatably supports the nacelle; and a wind vane provided on the nacelle and rotatably supported about a vertical axis of rotation, An optimal yaw angle estimation means estimates the optimal yaw angle of the nacelle that maximizes power generation efficiency by inputting input information, including the wind direction detected by the wind vane and the installation position of the horizontal-axis wind turbine, into a learning model that has been pre-trained to determine the correlation between the optimal yaw angle of the nacelle that maximizes power generation efficiency (the direction of the rotor's rotation axis, i.e., the normal direction of the blade rotation surface), A yaw angle adjustment means for adjusting the yaw angle of the nacelle so that it becomes the optimal yaw angle calculated by the optimal yaw angle estimation means, A control device for a horizontal-axis wind turbine, characterized by comprising the following:

2. A control device for a horizontal-axis wind turbine, comprising: a blade that rotates in response to wind; a nacelle that rotatably supports the blade; a tower that yaw-rotatably supports the nacelle; and a wind vane provided on the nacelle and rotatably supported about a vertical axis of rotation, The system comprises a plurality of first devices fixed around the horizontal axis wind turbine, and a second device fixed to the wind vane and positioned offset from the wind vane's rotation axis, and capable of transmitting and receiving signals with the first devices. A second device positioning means calculates the distance between each of the plurality of first devices and the second device in real time based on the bidirectional transmission and reception times of information or signals between each of the plurality of first devices and the second device, and identifies the position of the second device based on the distance between each of the first devices and the second device and the position information of each of the first devices, A wind direction calculation means that calculates the wind direction based on the position of the second device identified by the second device position identification means, A yaw angle adjustment means for adjusting the yaw angle of the nacelle so that the wind direction is calculated by the wind direction calculation means, A control device for a horizontal-axis wind turbine, characterized by comprising the following:

3. A control device for a horizontal-axis wind turbine, comprising: a blade that rotates in response to wind; a nacelle that rotatably supports the blade; a tower that yaw-rotatably supports the nacelle; and a wind vane provided on the nacelle and rotatably supported about a vertical axis of rotation, The system comprises a plurality of first devices fixed around the horizontal axis wind turbine, and a second device fixed to the wind vane and positioned offset from the wind vane's rotation axis, and capable of transmitting and receiving signals with the first devices. A second device positioning means calculates the distance between each of the plurality of first devices and the second device in real time based on the bidirectional transmission and reception times of information or signals between each of the plurality of first devices and the second device, and identifies the position of the second device based on the distance between each of the first devices and the second device and the position information of each of the first devices, A wind direction calculation means that calculates the wind direction based on the position of the second device identified by the second device position identification means, An optimal yaw angle estimation means estimates the optimal yaw angle of the nacelle that maximizes power generation efficiency by inputting input information, including the wind direction calculated by the wind direction calculation means and the installation position of the horizontal axis wind turbine, into a learning model that has been pre-trained to recognize the correlation between this information and the optimal yaw angle of the nacelle that maximizes power generation efficiency. A yaw angle adjustment means for adjusting the yaw angle of the nacelle so that it becomes the optimal yaw angle calculated by the optimal yaw angle estimation means, A control device for a horizontal-axis wind turbine, characterized by comprising the following:

4. A third device is provided which is fixed to the nacelle and positioned offset from the yaw rotation axis of the nacelle, and which is capable of transmitting and receiving with the first device. A third device positioning means calculates the distance between each of the plurality of first devices and the third device in real time based on the bidirectional transmission and reception times of information or signals between each of the plurality of first devices and the third device, and identifies the position of the third device based on the distance between each first device and the third device and the position information of each of the first devices, A nacelle azimuth angle calculation means calculates the yaw angle of the nacelle from the position of the third device identified by the third device position identification means and the position of the yaw rotation axis, The system includes a wind vane rotation axis position determination means for determining the position of the wind vane's rotation axis from the yaw angle of the nacelle calculated by the nacelle azimuth angle calculation means, The wind direction calculation means calculates the wind direction from the position of the rotation axis of the wind vane, which is determined by the wind vane rotation axis position determination means, and the position of the second device, which is determined by the second device position determination means. The control device for a horizontal-axis wind turbine according to feature 2.

5. The nacelle includes an anemometer, and a fourth device provided at a position of the wind receiving section offset from the rotation axis of the anemometer, which is capable of transmitting and receiving with the first device. A fourth device positioning means calculates the distance between each of the multiple first devices and the fourth device in real time based on the bidirectional transmission and reception times of information or signals between each of the multiple first devices and the fourth device, and identifies the position of the fourth device based on the distance between each of the first devices and the fourth device and the position information of each of the first devices. The system further includes a wind speed calculation means that calculates the wind speed based on the amount of angular displacement per unit time of the position of the fourth device identified by the fourth device position identification means, The control device for a horizontal-axis wind turbine according to claim 2, further comprising wind speed confirmation means for confirming that the wind speed calculated by the wind speed calculation means is within the rated wind speed.

6. If the wind speed calculated by the wind speed calculation means exceeds the rated wind speed, the system includes a protective control means that changes the angle of the blade or stops the rotation of the blade. The control device for a horizontal-axis wind turbine according to claim 5.

7. A control device for a horizontal-axis wind turbine according to claim 1 or 3, wherein a plurality of horizontal-axis wind turbines are provided, and when the optimal yaw angle of the nacelle that maximizes power generation efficiency is estimated by the optimal yaw angle estimation means for any one of the horizontal-axis wind turbines, the control device for a horizontal-axis wind turbine is provided with a yaw angle tracking means that adjusts the yaw angle of the nacelles of the other horizontal-axis wind turbines based on the estimated optimal yaw angle of the nacelle.

8. A control method for a horizontal-axis wind turbine having a blade that rotates in response to wind, a nacelle that rotatably supports the blade, a tower that yaw-rotatably supports the nacelle, and a wind vane provided on the nacelle and rotatably supported about a vertical axis of rotation, The optimal yaw angle estimation step involves inputting input information, including the wind direction detected by the wind vane and the installation position of the horizontal-axis wind turbine, into a learning model that has been pre-trained to determine the correlation between this information and the optimal yaw angle of the nacelle that maximizes power generation efficiency (the azimuth angle of the rotor's rotation axis, i.e., the normal direction of the blade rotation plane, for example, the geographically-based yaw angle), thereby estimating the optimal yaw angle of the nacelle that maximizes power generation efficiency. A yaw angle adjustment step, which adjusts the yaw angle of the nacelle so that it becomes the optimal yaw angle calculated in the optimal yaw angle estimation step, A control method for a horizontal-axis wind turbine, characterized by comprising the following:

9. A control method for a horizontal-axis wind turbine having a blade that rotates in response to wind, a nacelle that rotatably supports the blade, a tower that yaw-rotatably supports the nacelle, and a wind vane provided on the nacelle and rotatably supported about a vertical axis of rotation, The system comprises a plurality of first devices fixed around the horizontal axis wind turbine, and a second device fixed to the wind vane and positioned offset from the wind vane's rotation axis, and capable of transmitting and receiving signals with the first devices. A second device positioning step involves calculating the distance between each of the multiple first devices and the second device in real time based on the bidirectional transmission and reception times of information or signals between each of the multiple first devices and the second device, and determining the position of the second device based on the distance between each first device and the second device and the position information of each of the first devices. A wind direction calculation step that calculates the wind direction based on the position of the second device identified by the second device position identification step, A yaw angle adjustment step, which adjusts the yaw angle of the nacelle so that it matches the wind direction calculated in the wind direction calculation step, A control method for a horizontal-axis wind turbine, characterized by comprising the following:

10. A control method for a horizontal-axis wind turbine having a blade that rotates in response to wind, a nacelle that rotatably supports the blade, a tower that yaw-rotatably supports the nacelle, and a wind vane provided on the nacelle and rotatably supported about a vertical axis of rotation, The system comprises a plurality of first devices fixed around the horizontal axis wind turbine, and a second device fixed to the wind vane and positioned offset from the wind vane's rotation axis, and capable of transmitting and receiving signals with the first devices. A second device positioning step involves calculating the distance between each of the multiple first devices and the second device in real time based on the bidirectional transmission and reception times of information or signals between each of the multiple first devices and the second device, and determining the position of the second device based on the distance between each first device and the second device and the position information of each of the first devices. A wind direction calculation step that calculates the wind direction based on the position of the second device identified by the second device position identification step, The optimal yaw angle estimation step involves inputting input information, including the wind direction calculated in the wind direction calculation step and the installation position of the horizontal-axis wind turbine, into a learning model that has been pre-trained to determine the correlation between this information and the optimal yaw angle of the nacelle that maximizes power generation efficiency, thereby estimating the optimal yaw angle of the nacelle that maximizes power generation efficiency. A yaw angle adjustment step, which adjusts the yaw angle of the nacelle to the optimal yaw angle estimated by the optimal yaw angle estimation step, A control method for a horizontal-axis wind turbine, characterized by comprising the following:

11. A third device is provided which is fixed to the nacelle and positioned offset from the yaw rotation axis of the nacelle, and which is capable of transmitting and receiving with the first device. A third device positioning step involves calculating the distance between each of the multiple first devices and the third device in real time based on the bidirectional transmission and reception times of information or signals between each of the multiple first devices and the third device, and determining the position of the third device based on the distance between each first device and the third device and the position information of each of the first devices. A nacelle azimuth angle calculation step, which calculates the yaw angle of the nacelle from the position of the third device identified in the third device position identification step and the position of the yaw rotation axis, The system includes a wind vane rotation axis position determination step, which determines the position of the wind vane's rotation axis from the yaw angle of the nacelle calculated by the nacelle azimuth angle calculation step, The wind direction calculation step calculates the wind direction from the position of the rotation axis of the wind vane, which was determined by the wind vane rotation axis position determination step, and the position of the second device, which was determined by the second device position determination step. Control method for a horizontal-axis wind turbine according to feature 9.

12. The nacelle includes an anemometer, and a fourth device provided at a position of the wind receiving section offset from the rotation axis of the anemometer, which is capable of transmitting and receiving with the first device. A fourth device positioning step involves calculating the distance between each of the multiple first devices and the fourth device in real time based on the bidirectional transmission and reception times of information or signals between each of the multiple first devices and the fourth device, and determining the position of the fourth device based on the distance between each first device and the fourth device and the position information of each first device. The system further includes a wind speed calculation step that calculates the wind speed based on the amount of angular displacement per unit time of the position of the fourth device identified by the fourth device position identification step, The control method for a horizontal-axis wind turbine according to claim 9, further comprising a wind speed confirmation step for confirming that the wind speed calculated in the wind speed calculation step is within the rated wind speed.

13. If the wind speed calculated in the wind speed calculation step exceeds the rated wind speed, the system includes a protective control step that changes the angle of the blade or stops the rotation of the blade. A control method for a horizontal-axis wind turbine according to claim 12, characterized by its features.

14. A control method for a horizontal-axis wind turbine according to claim 8 or 10, characterized in that a plurality of horizontal-axis wind turbines are provided, and when the optimal yaw angle of the nacelle that maximizes power generation efficiency is estimated for any one of the horizontal-axis wind turbines by the optimal yaw angle estimation step, the method includes a yaw angle tracking step that adjusts the yaw angle of the nacelles of the other horizontal-axis wind turbines based on the estimated optimal yaw angle of the nacelle.

15. A control program for a horizontal-axis wind turbine, for causing a computer to perform each step of the control method for a horizontal-axis wind turbine according to any one of claims 8 to 13.

Images