Method and device for determining corrected value of yaw angle of unit

Abstract

The invention provides a method and a device for determining a yaw angle correction value of a unit. The determination method comprises the following steps: acquiring an orthoimage of a cabin of the wind generating set; inputting the orthoimage into a yaw angle identification model to obtain a first yaw angle of the cabin relative to the true north direction; a second yaw angle measured by the wind generating set at a specific moment is obtained, and the specific moment is the shooting moment of the orthoimage; the difference value between the first yaw angle and the second yaw angle serves as a yaw angle correction value of the wind generating set; wherein the yaw angle correction value is used for representing the angle difference of the initial installation orientation of the cabin relative to the true north direction.

Description

Technical Field

[0001] The present disclosure generally relates to the field of wind power generation technology, and more specifically, to a method and device for determining a yaw angle correction value of a wind turbine. Background Art

[0002] It is very important for wind turbines (hereinafter referred to as turbines) to obtain accurate wind direction information during the power generation process. The turbine will yaw in real time according to the wind direction, so that the impeller surface is as close to the wind flow direction as possible to maximize the power generation. In the actual operation of wind farms, a wind vane or a wind laser radar is generally installed behind the impeller surface of the turbine cabin to obtain wind direction data relative to the yaw direction of the turbine, so as to perform yaw action when the relative wind direction deviation is large.

[0003] In most wind farms today, due to limitations in hoisting technology, the orientation of the nacelle cannot be determined during installation, i.e., it cannot be guaranteed that the nacelle will face the true north direction (i.e., true north direction) when initially installed. This results in different initial installation orientations (i.e., yaw zero direction) for each unit in the wind farm, and each unit is independent in operation control, which brings many inconveniences to the control and subsequent maintenance of the wind farm group. Summary of the invention

[0004] An exemplary embodiment of the present disclosure provides a method and device for determining a yaw angle correction value of a unit, which can conveniently and effectively determine the angle difference of the initial installation orientation of the nacelle relative to the true north direction.

[0005] According to a first aspect of an embodiment of the present disclosure, a method for determining a yaw angle correction value of a wind turbine is provided, the determination method comprising: obtaining an orthophoto of a cabin of a wind turbine; inputting the orthophoto into a yaw angle recognition model to obtain a first yaw angle of the cabin relative to the true north direction; obtaining a second yaw angle measured by the wind turbine at a specific moment, wherein the specific moment is the shooting moment of the orthophoto; using the difference between the first yaw angle and the second yaw angle as the yaw angle correction value of the wind turbine; wherein the yaw angle correction value is used to characterize the angle difference of the initial installation orientation of the cabin relative to the true north direction.

[0006] Optionally, the determination method further includes: sending the yaw angle correction value to the wind turbine generator set, so that the wind turbine generator set achieves true north direction reference calibration based on the yaw angle correction value.

[0007] Optionally, the step of acquiring the orthophoto of the cabin of the wind turbine generator set includes: acquiring the orthophoto by controlling a drone to photograph the cabin; or acquiring the orthophoto from a satellite remote sensing image.

[0008] Optionally, the step of acquiring the orthophoto by controlling a drone to photograph the cabin includes: controlling the drone to fly to a specific position, wherein the specific position is directly above the cabin and at least higher than the impeller radius of the wind turbine relative to the cabin; after the drone flies to the specific position, controlling the nose of the drone to face the true north; after the nose of the drone faces the true north, controlling the drone to photograph the cabin to obtain the orthophoto; wherein the vertical upward direction of the orthophoto corresponds to the true north.

[0009] Optionally, the yaw angle recognition model includes a cabin detection model and an angle detection model; wherein, the step of inputting the orthophoto image into the yaw angle recognition model to obtain a first yaw angle of the cabin relative to the true north direction includes: inputting the orthophoto image into the cabin detection model to obtain position information of the cabin in the orthophoto image and position information of the nose of the cabin in the orthophoto image; inputting the position information of the cabin and the position information of the nose into the angle detection model to obtain the first yaw angle; wherein, the first yaw angle is the angle between the central axis of the cabin along the nose direction and the true north direction.

[0010] Optionally, the position information of the cabin includes: coordinate information of the bounding box of the cabin in the orthophoto image; the position information of the nose includes: coordinate information of the bounding box of the nose in the orthophoto image; wherein the angle detection model is used to identify the rotation angle of the central axis of the bounding box of the cabin along the direction of the nose relative to the vertical upward direction of the orthophoto image.

[0011] Optionally, the determination method also includes: using multiple orthophoto image samples to train the yaw angle recognition model; wherein each orthophoto image sample is an orthophoto image of the cabin with annotations, wherein the annotations include: coordinate information of the cabin's bounding box, coordinate information of the nose's bounding box, and the rotation angle of the central axis of the cabin's bounding box along the nose direction relative to the vertical upward direction of the orthophoto image sample.

[0012] Optionally, after the drone flies to the specific location, the step of controlling the nose of the drone to face the true north direction includes: after the drone flies to the specific location, using a magnetic compass or an automatic north pointing system installed on the drone itself to control the nose of the drone to face the true north direction.

[0013] According to a second aspect of an embodiment of the present disclosure, a device for determining a yaw angle correction value of a wind turbine is provided, the device comprising: an image acquisition unit, configured to acquire an orthophoto of a cabin of a wind turbine; a first yaw angle acquisition unit, configured to input the orthophoto into a yaw angle recognition model to obtain a first yaw angle of the cabin relative to the true north direction; a second yaw angle acquisition unit, configured to acquire a second yaw angle measured at a specific moment for the wind turbine, wherein the specific moment is the shooting moment of the orthophoto; a yaw angle correction value determination unit, configured to use the difference between the first yaw angle and the second yaw angle as the yaw angle correction value of the wind turbine; wherein the yaw angle correction value is used to characterize the angular difference of the initial installation orientation of the cabin relative to the true north direction.

[0014] Optionally, the determining device further includes: a sending unit configured to send the yaw angle correction value to the wind turbine generator set, so that the wind turbine generator set achieves true north direction reference calibration based on the yaw angle correction value.

[0015] Optionally, the image acquisition unit is configured to: acquire the orthophoto by controlling a drone to photograph the cabin; or acquire the orthophoto from a satellite remote sensing image.

[0016] Optionally, the image acquisition unit is configured to: control the UAV to fly to a specific position, wherein the specific position is directly above the cabin and at least higher than the impeller radius of the wind turbine relative to the cabin; after the UAV flies to the specific position, control the nose of the UAV to face the true north; after the nose of the UAV faces the true north, control the UAV to photograph the cabin to obtain the orthophoto; wherein the vertical upward direction of the orthophoto corresponds to the true north.

[0017] Optionally, the yaw angle recognition model includes a cabin detection model and an angle detection model; wherein, the first yaw angle acquisition unit is configured to: input the orthophoto into the cabin detection model to obtain the position information of the cabin in the orthophoto and the position information of the nose of the cabin in the orthophoto; input the position information of the cabin and the position information of the nose into the angle detection model to obtain the first yaw angle; wherein, the first yaw angle is the angle between the central axis of the cabin along the nose direction and the true north direction.

[0018] Optionally, the position information of the cabin includes: coordinate information of the bounding box of the cabin in the orthophoto image; the position information of the nose includes: coordinate information of the bounding box of the nose in the orthophoto image; wherein the angle detection model is used to identify the rotation angle of the central axis of the bounding box of the cabin along the direction of the nose relative to the vertical upward direction of the orthophoto image.

[0019] Optionally, the determination device also includes: a training unit configured to use multiple orthophoto image samples to train the yaw angle recognition model; wherein each orthophoto image sample is an orthophoto image of the cabin with annotations, wherein the annotations include: coordinate information of the bounding box of the cabin, coordinate information of the bounding box of the nose, and a rotation angle of the central axis of the bounding box of the cabin along the direction of the nose relative to the vertical upward direction of the orthophoto image sample.

[0020] Optionally, the image acquisition unit is configured to: after the drone flies to the specific location, use a magnetic compass or an automatic north pointing system installed on the drone itself to control the nose of the drone to face the true north direction.

[0021] According to a third aspect of an embodiment of the present disclosure, a computer-readable storage medium storing a computer program is provided. When the computer program is executed by a processor, the processor is prompted to execute the method for determining the yaw angle correction value of the unit as described above.

[0022] According to a fourth aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a memory storing a computer program, wherein when the computer program is executed by the processor, the processor is prompted to execute the method for determining the yaw angle correction value of the unit as described above.

[0023] According to the method and device for determining the yaw angle correction value of the unit of the exemplary embodiment of the present disclosure, it is possible to conveniently and effectively determine the angle difference of the initial installation orientation of the nacelle relative to the true north direction, so as to realize the true north direction reference calibration of each unit in the wind farm, and obtain the yaw angle of each unit relative to the true north direction, thereby facilitating the group control and subsequent maintenance of the wind farm.

[0024] Additional aspects and / or advantages of the present general inventive concept will be set forth in part in the following description and in part will be apparent from the description or may be learned through practice of the present general inventive concept. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above and other objects and features of the exemplary embodiments of the present disclosure will become more apparent through the following description in conjunction with the accompanying drawings which exemplarily illustrate the embodiments, in which:

[0026] Figure 1 A flow chart showing a method for determining a yaw angle correction value of a unit according to an exemplary embodiment of the present disclosure;

[0027] Figure 2 A flowchart showing a method for acquiring an orthophoto by controlling a drone to photograph a cabin according to an exemplary embodiment of the present disclosure;

[0028] Figure 3 An example of a shooting position of a drone according to an exemplary embodiment of the present disclosure is shown;

[0029] Figure 4 An example of an orthophoto of a cabin photographed by a drone according to an exemplary embodiment of the present disclosure is shown;

[0030] Figure 5 An example of an orthophoto of a cabin obtained from a satellite remote sensing image according to an exemplary embodiment of the present disclosure is shown;

[0031] Figure 6 shows an example of a cabin bounding box with a rotation angle according to an exemplary embodiment of the present disclosure;

[0032] Figure 7 A flow chart showing a method for determining a yaw angle correction value of a unit according to another exemplary embodiment of the present disclosure;

[0033] Figure 8 A structural block diagram of a device for determining a yaw angle correction value of a unit according to an exemplary embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0034] Reference will now be made in detail to the embodiments of the present disclosure, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like parts throughout. The embodiments will be described below with reference to the drawings in order to explain the present disclosure.

[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0036] It should be noted that the phrase "at least one of the items" in the present disclosure includes three types of parallel situations: "any one of the items", "a combination of any number of the items", and "all of the items". For example, "including at least one of A and B" includes the following three parallel situations: (1) including A; (2) including B; (3) including A and B. Another example is "executing at least one of step 1 and step 2" which means the following three parallel situations: (1) executing step 1; (2) executing step 2; (3) executing step 1 and step 2.

[0037] Figure 1 A flow chart showing a method for determining a yaw angle correction value of a crew according to an exemplary embodiment of the present disclosure.

[0038] As an example, the method for determining the yaw angle correction value of the unit according to the exemplary embodiment of the present disclosure may be performed by an electronic device with data processing capabilities, for example, the electronic device may be a terminal (such as a personal notebook, a desktop, etc.), or a server (such as an independent server, a server cluster, a cloud platform, etc.). In addition, it may also be performed by a wind farm controller.

[0039] Reference Figure 1 In step S101, an orthophoto of a nacelle of a wind turbine generator set is obtained.

[0040] As an example, an orthophoto of the cabin can be obtained by controlling a drone to photograph the cabin (e.g., Figure 4 The following will combine Figure 2 To describe the exemplary embodiment of this example, the description is not expanded here.

[0041] As another example, an orthophoto of the cabin may be obtained from satellite remote sensing images (e.g., Figure 5 For example, an orthophoto of the cabin of a wind turbine generator set may be captured from a satellite remote sensing image. For example, the satellite remote sensing image may be a high-resolution satellite remote sensing image taken by a commercial satellite or a high-resolution satellite (e.g., Gaofen-2).

[0042] In addition, the orthophoto image of the cabin may also be obtained by other appropriate methods, for example, the orthophoto image of the cabin may be obtained by photographing the cabin using a helicopter or other flying equipment.

[0043] As an example, an orthophoto of the nacelle of each wind turbine in the wind farm may be obtained.

[0044] In step S102, the orthophoto is input into the yaw angle recognition model to obtain the first yaw angle yaw of the cabin relative to the true north direction. UAV .

[0045] The true north direction is also the due north direction of the geographical location.

[0046] As an example, the vertical upward direction of the orthophoto image obtained in step S101 corresponds to the true north direction (for example, Figure 4 and Figure 5 As shown in the direction mark in the figure), the data processing amount of step S102 can be effectively reduced. Otherwise, operations such as camera coordinate system transformation need to be performed in step S102, which will increase the data processing amount and may also reduce the accuracy of the recognition result.

[0047] As an example, the first yaw angle is the angle between the central axis of the nacelle along the nose direction and the true north direction.

[0048] As an example, the yaw angle recognition model is used to recognize the rotation angle of the central axis of the bounding box of the cabin in the orthophoto along the nose direction relative to the vertical upward direction of the orthophoto (that is, the first yaw angle of the cabin relative to the true north direction). Figure 6 shown.

[0049] As an example, the yaw angle recognition model may include a nacelle detection model and an angle detection model.

[0050] Step S102 may include: inputting the orthophoto image into a cabin detection model to obtain position information of the cabin in the orthophoto image and position information of the nose of the cabin in the orthophoto image; then, the position information of the cabin and the position information of the nose may be input into an angle detection model to obtain a first yaw angle.

[0051] As an example, the cabin detection model is essentially a target object detection model, which is used to detect the position of the cabin and its nose in the orthophoto.

[0052] As an example, the position information of the cabin may be: the coordinate information of the cabin's bounding box (eg, the target identification box BoundingBox) (eg, the coordinates of the four vertices of the cabin's bounding box). As an example, the position information of the nose may be: the coordinate information of the nose's bounding box.

[0053] As an example, the angle detection model is used to identify the rotation angle of the central axis of the bounding box of the cabin along the nose direction relative to the vertical upward direction of the orthophoto.

[0054] As an example, a suitable machine learning algorithm may be used to construct a cabin detection model and an angle detection model. For example, a neural network may be used to construct a cabin detection model and an angle detection model.

[0055] In addition, as an example, a plurality of orthophoto samples can be used to train a yaw angle recognition model. Each orthophoto sample is an orthophoto of the cabin with annotations, wherein the annotations include: coordinate information of the cabin bounding box, coordinate information of the nose bounding box, and the rotation angle of the central axis of the cabin bounding box along the nose direction relative to the vertical upward direction of the orthophoto sample.

[0056] It should be understood that the above-mentioned multiple orthophoto image samples may be orthophoto images of nacelles of multiple wind turbine generator sets.

[0057] In step S103, a second yaw angle yaw measured by the wind turbine generator set at a specific time is obtained. SCADA .

[0058] The specific time is the time when the above-mentioned orthophoto is taken.

[0059] As an example, when the orthophoto image is an orthophoto image taken by a drone, the specific moment is the moment when the drone photographs the cabin to obtain the orthophoto image. As another example, when the orthophoto image is an orthophoto image of the cabin obtained from a satellite remote sensing image, the specific moment is the moment when the satellite remote sensing image was taken.

[0060] As an example, the second yaw angle may be the yaw angle of the wind turbine generator set measured in real time by a measuring device of the wind turbine generator set. For example, the second yaw angle measured by the wind turbine generator set at a specific moment may be obtained from data of the wind turbine generator set operation status monitoring system SCADA, that is, the second yaw angle is the yaw angle of the wind turbine generator set at a specific moment recorded in the SCADA file.

[0061] In step S104, the difference between the first yaw angle and the second yaw angle is used as a yaw angle correction value Δyaw of the wind turbine generator set.

[0062] That is, Δyaw=yaw UAV -yaw SCADA The yaw angle correction value Δyaw is used to characterize the angle difference of the initial installation orientation of the nacelle relative to the true north direction. The initial installation orientation of the nacelle is the orientation of the nacelle after the nacelle is initially installed.

[0063] In addition, as an example, the method for determining the yaw angle correction value of the unit according to the exemplary embodiment of the present disclosure may also include: sending the yaw angle correction value to the corresponding wind turbine generator set so that the wind turbine generator set can achieve true north direction reference calibration based on the yaw angle correction value.

[0064] Specifically, as an example, the wind turbine generator set can realize the true north direction reference calibration of the yaw angle based on the received yaw angle correction value. For example, the yaw angle measured by the wind turbine generator set is the yaw angle relative to the initial installation direction of the nacelle (that is, the default zero direction after initial installation), and the yaw angle correction value can be used to correct the measured yaw angle, and the corrected yaw angle is the yaw angle of the unit relative to the true north direction, so that the reference (that is, the zero direction) of the corrected yaw angle is the true north direction.

[0065] As an example, the sum of the yaw angle correction value and the measured yaw angle may be used as the corrected yaw angle.

[0066] In addition, as an example, the method for determining the yaw angle correction value of the unit according to the exemplary embodiment of the present disclosure may also include: obtaining the corrected yaw angle of each unit, and performing field group control based on the corrected yaw angle of each unit. For example, wake control is performed based on the corrected yaw angle of each unit.

[0067] According to the exemplary embodiment of the present disclosure, the yaw angle of each unit in the wind farm relative to the true north direction (that is, the yaw angle of each unit when the yaw zero direction is consistent (unified as the true north direction)) can be obtained, which facilitates the group control and subsequent maintenance of the wind farm.

[0068] Figure 2 A flow chart showing a method for acquiring orthophotos by controlling a drone to photograph a cabin according to an exemplary embodiment of the present disclosure.

[0069] Reference Figure 2 In step S201, the drone is controlled to fly to a specific location (ie, a shooting location).

[0070] The specific position is directly above the nacelle and at least higher than the rotor radius of the wind turbine relative to the nacelle. Figure 3 As shown. This can protect the drone from the influence of the impeller and the generator magnetic field.

[0071] As an example, the drone can be controlled to fly to a specific location by inputting the crew machine site coordinates and altitude information on the drone control terminal.

[0072] In step S202, after the drone flies to a specific location, the nose of the drone is controlled to face the true north direction, so that the vertical upward direction of the image taken by the drone corresponds to the true north direction.

[0073] As an example, after the drone flies to a specific location, the drone's nose can be controlled to face the true north direction using a magnetic compass or an automatic north pointing system installed on the drone itself.

[0074] In step S203, after the nose of the drone is directed toward the true north, the drone is controlled to photograph the cabin to obtain an orthographic image of the cabin.

[0075] As an example, the drone is controlled to photograph the cabin through its own photographing device (eg, camera).

[0076] Figure 7 A flow chart showing a method for determining a yaw angle correction value of a crew according to another exemplary embodiment of the present disclosure.

[0077] In terms of time cost, assuming that there are 50 units in a wind farm, if two operation and maintenance personnel perform manual calibration (for example, using tools such as a magnetic compass to manually climb to the top of the cabin and manually measure the current yaw angle of the unit; or manually carry a handheld receiver, use the satellite GNSS measurement method on the top of the cabin, and calculate the current yaw angle of the unit through the coordinate points at the head and tail of the cabin), each person calibrates 2 to 3 units per day, and it takes about one to two weeks to calibrate the entire field. According to the exemplary embodiment of the present disclosure, only one drone operator is required to complete the calibration of the entire field within one day; if high-resolution remote sensing images are used, there is no need to go to the wind farm for on-site measurement to obtain satellite orthophotos, and basically no time cost is required to obtain data.

[0078] In terms of accuracy, manual calibration may cause interference to the magnetic compass and other equipment when the generator is operated on the top of the cabin due to the strong magnetic field in the generator, making the measurement result inaccurate. However, according to the exemplary embodiments of the present disclosure, the measurement accuracy of the first yaw angle can be effectively improved.

[0079] In terms of labor costs, manual calibration takes longer, so the labor costs of the operation and maintenance personnel will be higher. According to the exemplary embodiment of the present disclosure, the cost is 1-2 days of travel expenses for a UAV operator; if satellite images are used, there is basically no labor cost, only the cost of purchasing high-resolution satellite image data.

[0080] In terms of downtime costs, according to the exemplary embodiments of the present disclosure, no downtime operation is required, and there is no downtime cost.

[0081] In terms of the subsequent operation of the wind farm, after the true north calibration, the wind farm can apply relevant wake control or farm group control solutions during operation to further improve the power generation efficiency.

[0082] Figure 8 A structural block diagram of a device for determining a yaw angle correction value of a unit according to an exemplary embodiment of the present disclosure is shown.

[0083] like Figure 8As shown, the device for determining the yaw angle correction value of the crew according to the exemplary embodiment of the present disclosure includes: an image acquisition unit 101, a first yaw angle acquisition unit 102, a second yaw angle acquisition unit 103, and a yaw angle correction value determination unit 104.

[0084] Specifically, the image acquisition unit 101 is configured to acquire an orthophoto of the nacelle of the wind turbine generator set.

[0085] The first yaw angle acquisition unit 102 is configured to input the orthophoto into a yaw angle recognition model to obtain a first yaw angle of the cabin relative to the true north direction.

[0086] The second yaw angle acquisition unit 103 is configured to acquire a second yaw angle of the wind turbine generator set measured at a specific moment, wherein the specific moment is a shooting moment of the orthophoto.

[0087] The yaw angle correction value determination unit 104 is configured to use the difference between the first yaw angle and the second yaw angle as the yaw angle correction value of the wind turbine generator set.

[0088] The yaw angle correction value is used to represent the angle difference of the initial installation orientation of the nacelle relative to the true north direction.

[0089] As an example, the determining device may further include: a sending unit (not shown), the sending unit being configured to send the yaw angle correction value to the wind turbine generator set so that the wind turbine generator set can achieve true north direction reference calibration based on the yaw angle correction value.

[0090] As an example, the image acquisition unit 101 may be configured to: acquire the orthophoto by controlling a drone to photograph the cabin; or acquire the orthophoto from a satellite remote sensing image.

[0091] As an example, the image acquisition unit 101 can be configured to: control the drone to fly to a specific position, wherein the specific position is directly above the cabin and at least higher than the impeller radius of the wind turbine relative to the cabin; after the drone flies to the specific position, control the nose of the drone to face the true north; after the nose of the drone faces the true north, control the drone to photograph the cabin to obtain the orthophoto; wherein the vertical upward direction of the orthophoto corresponds to the true north.

[0092] As an example, the yaw angle recognition model may include a cabin detection model and an angle detection model; wherein, the first yaw angle acquisition unit 102 may be configured to: input the orthophoto into the cabin detection model to obtain the position information of the cabin in the orthophoto and the position information of the nose of the cabin in the orthophoto; input the position information of the cabin and the position information of the nose into the angle detection model to obtain the first yaw angle; wherein, the first yaw angle is the angle between the central axis of the cabin along the nose direction and the true north direction.

[0093] As an example, the position information of the cabin may include: coordinate information of the bounding box of the cabin in the orthophoto image; the position information of the nose may include: coordinate information of the bounding box of the nose in the orthophoto image; wherein the angle detection model is used to identify the rotation angle of the central axis of the bounding box of the cabin along the direction of the nose relative to the vertical upward direction of the orthophoto image.

[0094] As an example, the determination device may also include: a training unit (not shown), the training unit is configured to use multiple orthophoto image samples to train the yaw angle recognition model; wherein each orthophoto image sample is an orthophoto image of the cabin with annotations, wherein the annotations include: coordinate information of the bounding box of the cabin, coordinate information of the bounding box of the nose, and the rotation angle of the central axis of the bounding box of the cabin along the direction of the nose relative to the vertical upward direction of the orthophoto image sample.

[0095] As an example, the image acquisition unit 101 may be configured to: after the drone flies to the specific location, use a magnetic compass or an automatic north-pointing system installed on the drone itself to control the nose of the drone to face the true north direction.

[0096] It should be understood that the specific processing performed by the device for determining the yaw angle correction value of the unit according to the exemplary embodiment of the present disclosure has been referred to. Figures 1 to 7 The details have been described in detail and will not be repeated here.

[0097] It should be understood that the various units in the apparatus for determining the yaw angle correction value of the unit according to the exemplary embodiment of the present disclosure may be implemented as hardware components and / or software components. Those skilled in the art may implement the various units, for example, using a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC) according to the processing performed by the various units defined.

[0098] An exemplary embodiment of the present disclosure provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to execute the method for determining the yaw angle correction value of the unit as described in the above exemplary embodiment. The computer-readable storage medium is any data storage device that can store data read by a computer system. Examples of computer-readable storage media include: read-only memory, random access memory, read-only optical disk, magnetic tape, floppy disk, optical data storage device, and carrier wave (such as data transmission through the Internet via a wired or wireless transmission path).

[0099] An electronic device according to an exemplary embodiment of the present disclosure includes: a processor (not shown) and a memory (not shown), wherein the memory stores a computer program, and when the computer program is executed by the processor, it prompts the processor to execute the method for determining the yaw angle correction value of the unit as described in the above exemplary embodiment.

[0100] As an example, the electronic device may be an electronic device with data processing capability, for example, the electronic device may be a terminal (such as a personal notebook, a desktop, etc.), or a server (such as an independent server, a server cluster, a cloud platform, etc.). In addition, it may also be a wind farm controller.

[0101] Although some exemplary embodiments of the present disclosure have been shown and described, it will be appreciated by those skilled in the art that modifications may be made to these embodiments without departing from the principles and spirit of the present disclosure, the scope of which is defined by the claims and their equivalents.

Claims

1. A method for determining a yaw angle correction value of a unit, characterized in that: The determination method comprises: Obtain orthophotos of the nacelle of the wind turbine; Inputting the orthophoto into a yaw angle recognition model to obtain a first yaw angle of the cabin relative to the true north direction; Acquire a second yaw angle of the wind turbine generator set measured at a specific moment, wherein the specific moment is the shooting moment of the orthophoto; Using the difference between the first yaw angle and the second yaw angle as a yaw angle correction value of the wind turbine generator set; The yaw angle correction value is used to represent the angle difference of the initial installation orientation of the nacelle relative to the true north direction.

2. The determination method according to claim 1, characterized in that: The determination method further comprises: The yaw angle correction value is sent to the wind turbine generator set, so that the wind turbine generator set can achieve true north direction reference calibration based on the yaw angle correction value.

3. The determination method according to claim 1, characterized in that: The step of obtaining an orthophoto of the nacelle of the wind turbine generator set comprises: Acquire the orthophoto by controlling a drone to photograph the cabin; Alternatively, the orthophoto is obtained from satellite remote sensing images.

4. The determination method according to claim 3, characterized in that: The step of acquiring the orthophoto by controlling the drone to photograph the cabin comprises: Controlling the UAV to fly to a specific position, wherein the specific position is directly above the nacelle and at least higher than the impeller radius of the wind turbine generator set relative to the nacelle; After the UAV flies to the specific location, controlling the nose of the UAV to face the true north direction; After the nose of the UAV is directed toward the true north, controlling the UAV to photograph the cabin to obtain the orthophoto; The vertical upward direction of the orthophoto corresponds to the true north direction.

5. The determination method according to claim 1, characterized in that: The yaw angle recognition model includes a cabin detection model and an angle detection model; The step of inputting the orthophoto into a yaw angle recognition model to obtain a first yaw angle of the cabin relative to the true north direction comprises: Inputting the orthophoto into the cabin detection model to obtain position information of the cabin in the orthophoto and position information of the nose of the cabin in the orthophoto; Inputting the position information of the cabin and the position information of the nose into the angle detection model to obtain the first yaw angle; The first yaw angle is the angle between the central axis of the nacelle along the nose direction and the true north direction.

6. The determination method according to claim 5, characterized in that: The position information of the cabin includes: coordinate information of the bounding box of the cabin in the orthophoto image; the position information of the nose includes: coordinate information of the bounding box of the nose in the orthophoto image; The angle detection model is used to identify the rotation angle of the central axis of the boundary box of the cabin along the nose direction relative to the vertical upward direction of the orthophoto.

7. The determination method according to claim 6, characterized in that: The determination method further comprises: Using a plurality of orthophoto samples, training the yaw angle recognition model; Each orthophoto image sample is an orthophoto image of the cabin with annotations, wherein the annotations include: coordinate information of the bounding box of the cabin, coordinate information of the bounding box of the nose, and the rotation angle of the central axis of the bounding box of the cabin along the direction of the nose relative to the vertical upward direction of the orthophoto image sample.

8. The determination method according to claim 4, characterized in that: After the UAV flies to the specific location, the step of controlling the nose of the UAV to face the true north direction includes: After the UAV flies to the specific location, the nose of the UAV is controlled to face the true north direction using a magnetic compass or an automatic north pointing system installed on the UAV itself.

9. A device for determining a yaw angle correction value of a unit, characterized in that: The determining device comprises: An image acquisition unit is configured to acquire an orthophoto of a nacelle of a wind turbine generator set; A first yaw angle acquisition unit is configured to input the orthophoto into a yaw angle recognition model to obtain a first yaw angle of the cabin relative to the true north direction; A second yaw angle acquisition unit is configured to acquire a second yaw angle of the wind turbine generator set measured at a specific moment, wherein the specific moment is a shooting moment of the orthophoto; a yaw angle correction value determination unit, configured to use a difference between the first yaw angle and the second yaw angle as a yaw angle correction value of the wind turbine generator set; The yaw angle correction value is used to represent the angle difference of the initial installation orientation of the nacelle relative to the true north direction.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is prompted to execute the method for determining a yaw angle correction value of an assembly as claimed in any one of claims 1 to 8.

11. An electronic device, characterized in that: The electronic device comprises: processor; A memory stores a computer program, which, when executed by a processor, prompts the processor to execute the method for determining a yaw angle correction value of a unit as claimed in any one of claims 1 to 8.

Images