Wind turbine generator tower drum state monitoring method and device based on target image recognition

Abstract

The invention discloses a wind turbine generator tower drum state monitoring method based on target image recognition, which comprises the following steps of: installing a target device on the lower surface of a top platform of each layer of tower drum, arranging a high-definition camera on a bottom platform of the tower drum below each target, and enabling a lens of the high-definition camera to face the target device upwards; each layer of high-definition camera acquires image data of the target above in real time and transmits the image data to the central processing unit through the data acquisition module; the central processing unit carries out image recognition processing on the image data of each layer and recognizes the state of the tower drum; and carrying out safety early warning according to the tower drum state. The invention further discloses a target device, the target device comprises a lampshade and a group of lamp wicks in the lampshade, and a hollowed-out light-transmitting area is arranged on a lampshade panel. According to the method, the displacement, the deflection angle, the displacement speed and the deflection angular speed of the target position of each layer of tower drum platform can be clearly analyzed, the state of the tower drum is accurately monitored, and safety early warning is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind turbine tower monitoring, and in particular to a method and device for monitoring the status of a wind turbine tower based on target image recognition. Background Art

[0002] A wind turbine is a device that converts wind energy into mechanical energy and then electrical energy by rotating its impellers against the wind. The tower is one of the key load-bearing components of a wind turbine. Maintaining a normal and safe state of the wind turbine tower is the basic guarantee for the normal operation of the wind turbine. If the wind turbine tower has problems such as tilt, deformation, and vibration to a certain extent, it may lead to a serious accident of tower collapse.

[0003] In recent years, wind turbines have been developing towards large-scale and intelligent development, and online fault monitoring systems are increasingly being used in wind turbines. For example, CN112268542A discloses a method and device for detecting the inclination angle of a wind turbine tower, which monitors the deviation between a laser beam and a laser target. First, the laser equipment has a high transmission power, and the cost of using it for monitoring large wind turbine towers is high; second, the laser equipment has a single recognition target, and it is difficult to achieve comprehensive monitoring of the tower deformation, displacement and other conditions.

[0004] Condition monitoring based on image recognition technology is also an important technical direction. At present, many units have proposed technical solutions for wind turbine tower condition monitoring based on image recognition technology. For example, patent publications CN116398381A and CN111075665A respectively proposed wind turbine tower monitoring solutions related to image recognition technology, which can play a certain role in real-time monitoring and early detection of serious tower failure risks. However, there are problems in that the tower deformation and displacement contrast within the monitoring range are not obvious enough, which may cause large monitoring deviations.

[0005] Therefore, how to monitor the deformation and displacement status of the tower with low cost and high precision is a technical problem that needs to be solved urgently. Summary of the invention

[0006] In order to address the deficiencies in the prior art, the present invention provides a method and device for monitoring the tower status of a wind turbine generator set based on target image recognition. A target is installed on the lower surface of the top platform of each tower layer near the outer edge, and a high-definition camera is arranged on the bottom platform of the tower below each target. The lens of the high-definition camera faces the target upward, and cooperates with the image analysis and processing of the central processor to clearly analyze the displacement, deflection angle, displacement speed and deflection angular velocity of the target position of each tower platform, accurately monitor the tower status, and achieve safety warning.

[0007] The embodiment of the present invention provides the following solution: In a first aspect, an embodiment of the present invention provides a method for monitoring the status of a wind turbine tower based on target image recognition, the method comprising: Step 1: Arrange monitoring equipment: install a target device on the lower surface of the top platform of each tower layer, and set a high-definition camera on the bottom platform of the tower below each target device, with the lens of the high-definition camera facing the target device upward; the target device includes a lampshade and a group of LED wicks inside the lampshade, and the surface of the lampshade is provided with a light-transmitting area and a non-light-transmitting area; Step 2: Data collection: High-definition cameras on each floor collect image data of the target above in real time and transmit it to the central processor through the data acquisition module; Step 3: The central processing unit performs image recognition processing on the image data of each layer to identify the tower status; Step 4: Issue safety warning based on tower status.

[0008] In an optional embodiment, step three includes static calibration and dynamic monitoring.

[0009] In an optional embodiment, the static calibration is performed by processing an image collected when the wind turbine generator set is not in operation, and includes the following steps: a3.1. Preliminary identification of the target device based on the grayscale index and shape characteristics of each area in the image; a3.2. Based on the grayscale index and shape characteristics of the light-transmitting area and the non-light-transmitting area of ​​the target device, determine the origin O, the positions of the x-axis and the y-axis, and the y-axis deflection angle of the target device in the static reference orientation.

[0010] In an optional embodiment, the dynamic monitoring is performed by processing images collected when the wind turbine is in working state, and includes the following process: b3.1. For any tower section i, 1≤i≤n, n is the number of tower sections, obtain the lateral displacement D of the origin O of the target device in the image relative to the origin O of the quasi-static reference position of the target platform on the top of the tower _i_x , longitudinal displacement D _i_y , and the y-axis deflection angle A _i_y ; b3.2, according to the lateral displacement D _i_x , longitudinal displacement D _i_y and the y-axis deflection angle A _i_y Determine the tower status.

[0011] In an optional embodiment, the tower status determination described in step b3.2 includes determining whether the tower deformation is obviously abnormal, determining whether the overall deformation of the wind turbine tower is obviously abnormal, and determining whether the tower target position movement speed or deflection angular velocity is obviously abnormal.

[0012] In an optional embodiment, the tower deformation obviously abnormal determination includes the following process: if any of the following conditions is met, it is determined that the tower deformation of the i-th section is obviously abnormal: Condition 1, |D _i_x |≥D _i_x_limit ; Condition 2, |D _i_y |≥D _i_x_limit ; Condition three, |A _i_y |≥A _i_y_limit ; Among them, D _i_x_limit , D _i_y_limit and A _i_y_limit They are the lateral displacement warning setting threshold, longitudinal displacement warning setting threshold, and y-axis deflection angle warning setting threshold of the i-th tower section.

[0013] In an optional embodiment, the determination of whether the overall deformation of the wind turbine tower is obviously abnormal includes the following process: if any of the following conditions is met, it is determined that the overall deformation of the wind turbine tower is obviously abnormal: Condition 1, | |≥D _i_x_limit_total ; Condition two, | |≥D _i_y_limit_total ; Condition three, | |≥A _i_y_limit_total ; Among them, D _i_x_limit_total , D _i_y_limit_total and A _i_y_limit_total They are respectively the overall lateral deformation warning setting threshold, the overall longitudinal deformation warning setting threshold, and the total y-axis deflection warning setting threshold of the wind turbine tower.

[0014] In an optional embodiment, the tower target position moving speed or deflection angular velocity obviously abnormal determination includes the following process: based on the time interval △t between two adjacent frames of images taken, calculate D within △t time _i_x , D _i_y and A _i_y By dividing each change value by the time interval △t, we can get the moving speed V of the origin O of the tower target device along the x-axis direction. _i_x_△t , the moving speed V along the y-axis _i_y_△t , and the deflection angular velocity ω of the tower target y axis _i_y_△t If any of the following conditions is met, the moving speed or deflection angular velocity of the target position of the tower section i is judged to be obviously abnormal: Condition 1, |V _i_x_△t |≥V _i_x_△t_limit; Condition 2, |V _i_y_△t |≥D _i_y_△t_limit ; Condition 3: |ω _i_y_△t |≥ω _i_y_△t_limit ; Among them, V _i_x_△t_limit 、V _i_y_△t_limit and ω _i_y_△t_limit They are respectively the lateral moving speed warning setting threshold, the longitudinal moving speed warning setting threshold, and the y-axis deflection angular velocity warning setting threshold of the i-th tower section.

[0015] In the second aspect, an embodiment of the present invention further provides a target device based on the aforementioned wind turbine tower status monitoring method, the target device comprising: a lampshade and a group of wicks inside the lampshade, the lampshade comprising a bottom plate, side plates on the sides of the bottom plate and a panel on the top of the bottom plate, the panel being provided with a hollow light-transmitting area.

[0016] In an optional embodiment, the light-transmitting area is a cross-shaped light-transmitting area, the lateral and longitudinal light-transmitting lengths of the cross-shaped light-transmitting area are different, and a circular non-light-transmitting area is provided at the center of the cross-shaped light-transmitting area.

[0017] The beneficial effects of the present invention based on its technical solution are: (1) The wind turbine tower status monitoring method based on target image recognition provided by the present invention installs a target on the lower surface of each tower top platform near the outer edge, and sets a high-definition camera on the tower bottom platform below each target. The high-definition camera lens faces the target upwards, and cooperates with the central processor to analyze and process the image. The displacement, deflection angle, displacement speed, and deflection angular velocity of the target position on each tower platform can be clearly analyzed, and the tower status can be accurately monitored to achieve safety warning; (2) The target device provided by the present invention has different lengths in the x-axis direction and the y-axis direction, so the x-axis and y-axis of the target can be clearly identified, which is convenient for analyzing the deflection angle of the target; (3) The edge of the non-light-transmitting area of ​​the target device provided by the present invention can be provided with a certain inclination angle, and the inclination angle is ≥30°. When the target is displaced with the tower, the influence of the edge of the non-light-transmitting area of ​​the target on the imaging width of the light-transmitting area caused by the displacement can be avoided, thereby reducing the adverse effect of the deformation of the tower on the quality of the captured image; (4) The light-transmitting area of ​​the target device provided by the present invention has a larger dimension in the y-axis direction than in the x-axis direction. When installing the target, the x-axis direction is parallel to the main wind direction, and the y-axis deflection angle of the target is used as the monitoring angle, which can improve the recognition accuracy of the target deflection angle. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 The present invention is a flow chart of a method and device for monitoring the tower status of a wind turbine generator system based on target image recognition provided in an embodiment.

[0020] Figure 2 This is a schematic diagram of the target device installation location.

[0021] Figure 3 It is a schematic diagram of the structure of the target device.

[0022] Figure 4 It is a schematic diagram of the structure of the lampshade.

[0023] Figure 5 This is a schematic diagram of the wick arrangement.

[0024] Figure 6 is a schematic diagram of the edge inclination angle.

[0025] Figure 7 It is a schematic diagram of the relationship between the target device layout direction and the main wind direction.

[0026] In the figure: 1-target device, 11-lamp cover, 12-wick, 13-bottom plate, 14-panel, 15-side plate, 16-light-transmitting area, 17-circular non-light-transmitting area, 18-edge, 2-high-definition camera. DETAILED DESCRIPTION

[0027] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention belong to the scope of protection of the embodiments of the present invention.

[0028] Reference Figure 1 The embodiment of the present invention provides a method for monitoring the tower state of a wind turbine generator system based on target image recognition, the method comprising: Step 1: Arrange monitoring equipment: refer to Figure 2 A target device 1 is installed on the lower surface of the top platform of each tower layer, and a high-definition camera 2 is set on the bottom platform of the tower below each target device, and the lens of the high-definition camera is facing the target device upward.

[0029] Reference Figure 3The target device described in this embodiment includes: a lampshade 11 and a group of wicks 12 inside the lampshade. Figure 4 The lampshade includes a bottom plate 13, a side plate 15 on the side of the bottom plate, and a panel 14 on the top of the bottom plate, and the panel is provided with a hollow light-transmitting area 16. The partial light-transmitting design can effectively improve the contrast between the light-transmitting area and the non-light-transmitting area, which is convenient for image analysis.

[0030] The light-transmitting area is a cross-shaped light-transmitting area, and the horizontal and vertical light-transmitting lengths of the cross-shaped light-transmitting area are different. A circular non-light-transmitting area 17 is provided at the center of the cross-shaped light-transmitting area to facilitate image recognition, and can clearly identify the target x-axis and y-axis, which is convenient for target deflection angle analysis. The internal wick arrangement is as follows Figure 5 shown.

[0031] Reference Figure 6 The edge 18 of the non-light-transmitting area of ​​the inner surface of the target lampshade panel, which is adjacent to the light-transmitting area, is provided with a certain inclination angle, and the inclination angle is ≥30°. When the target produces a certain displacement with the tower, the influence of the edge of the non-light-transmitting area of ​​the target on the imaging width of the light-transmitting area caused by the displacement can be avoided, thereby reducing the adverse effect of the deformation of the tower on the quality of the captured image.

[0032] The center of the non-translucent circular area in the center of the target is the origin O, the center line of the shorter light-transmitting band in the target light-transmitting area is the x-axis, and the center line of the longer light-transmitting band in the target light-transmitting area is the y-axis. When installing, make the x-axis of the target parallel to the main wind direction, such as Figure 7 shown.

[0033] Step 2: Data collection: The high-definition cameras on each floor collect image data of the target above in real time and transmit it to the central processor through the data acquisition module.

[0034] Step 3: The central processor performs image recognition processing on the image data of each layer to identify the tower status. This step includes static calibration and dynamic monitoring. Static calibration takes the images collected when the wind turbine is not working and processes them, including the following processes: a3.1. Use image recognition technology to determine the target device based on the grayscale index and shape characteristics of each area in the image, and exclude the parts other than the target device in the image; a3.2. Use image recognition technology to finely identify the target device in the image, and determine the origin O, x-axis and y-axis positions and angle orientations of the target device in the static reference orientation based on the grayscale index and shape characteristics of the light-transmitting and non-light-transmitting areas of the target device. That is, the center of the non-light-transmitting circular area in the center of the target is the origin O, the center line of the shorter light-transmitting band in the light-transmitting area of ​​the target is the x-axis, the center line of the longer light-transmitting band in the light-transmitting area of ​​the target is the y-axis, and the angle of the y-axis relative to the x-axis is the y-axis deflection angle.

[0035] Dynamic monitoring takes images collected when the wind turbine is in operation and processes them, including the following steps: b3.1. For any tower section i, 1≤i≤n, n is the number of tower sections, obtain the lateral displacement D of the origin O of the target device in the image relative to the origin O of the quasi-static reference position of the target platform on the top of the tower _i_x , longitudinal displacement D _i_y , and the y-axis deflection angle A _i_y ; b3.2, according to the lateral displacement D _i_x , longitudinal displacement D _i_y and the y-axis deflection angle A _i_y Determine the tower status.

[0036] The tower state determination includes the determination of obvious abnormality of tower deformation, the determination of obvious abnormality of overall deformation of wind turbine tower, and the determination of obvious abnormality of tower target position moving speed or deflection angular velocity: (1) The determination of obvious abnormality in tower deformation includes the following process: If any of the following conditions is met, the tower deformation of section i is determined to be obviously abnormal: Condition 1, |D _i_x |≥D _i_x_limit ; Condition 2, |D _i_y |≥D _i_x_limit ; Condition three, |A _i_y |≥A _i_y_limit ; Among them, D _i_x_limit , D _i_y_limit and A _i_y_limit They are the lateral displacement warning setting threshold, longitudinal displacement warning setting threshold, and y-axis deflection angle warning setting threshold of the i-th tower section.

[0037] (2) The determination of whether the overall deformation of the wind turbine tower is obviously abnormal includes the following process: If any of the following conditions is met, it is determined that the overall deformation of the wind turbine tower is obviously abnormal: Condition 1, | |≥D _i_x_limit_total ; Condition two, | |≥D _i_y_limit_total ; Condition three, | |≥A _i_y_limit_total ; Among them, D _i_x_limit_total , D _i_y_limit_total and A _i_y_limit_totalThey are respectively the overall lateral deformation warning setting threshold, the overall longitudinal deformation warning setting threshold, and the total y-axis deflection warning setting threshold of the wind turbine tower.

[0038] (3) The determination of obvious abnormality in the moving speed or deflection angular velocity of the tower target position includes the following process: based on the time interval △t between two adjacent frames of images taken, calculate the D _i_x , D _i_y and A _i_y By dividing each change value by the time interval △t, we can get the moving speed V of the origin O of the tower target device along the x-axis direction. _i_x_△t , the moving speed V along the y-axis _i_y_△t , and the deflection angular velocity ω of the tower target y axis _i_y_△t If any of the following conditions is met, the moving speed or deflection angular velocity of the target position of the tower section i is judged to be obviously abnormal: Condition 1, |V _i_x_△t |≥V _i_x_△t_limit ; Condition 2, |V _i_y_△t |≥D _i_y_△t_limit ; Condition 3: |ω _i_y_△t |≥ω _i_y_△t_limit ; Among them, V _i_x_△t_limit 、V _i_y_△t_limit and ω _i_y_△t_limit They are respectively the lateral moving speed warning setting threshold, the longitudinal moving speed warning setting threshold, and the y-axis deflection angular velocity warning setting threshold of the i-th tower section.

[0039] Step 4: Issue safety warning based on tower status.

[0040] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0041] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (modules, systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0042] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0043] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0044] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0045] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A wind turbine tower status monitoring method based on target image recognition, characterized in that: The method comprises: Step 1: Arrange monitoring equipment: install a target device on the lower surface of the top platform of each tower layer, and set a high-definition camera on the bottom platform of the tower below each target device, with the lens of the high-definition camera facing the target device upward; the target device includes a lampshade and a group of LED wicks inside the lampshade, and the surface of the lampshade is provided with a light-transmitting area and a non-light-transmitting area; Step 2: Data collection: High-definition cameras on each floor collect image data of the target above in real time and transmit it to the central processor through the data acquisition module; Step 3: The central processing unit performs image recognition processing on the image data of each layer to identify the tower status; Step 4: Issue safety warning based on tower status.

2. The wind turbine tower status monitoring method based on target image recognition according to claim 1 is characterized in that: Step three includes static calibration and dynamic monitoring.

3. The wind turbine tower status monitoring method based on target image recognition according to claim 2 is characterized in that: The static calibration is performed by processing images collected when the wind turbine generator set is not in operation. The process includes: a3.

1. Preliminary identification of the target device based on the grayscale index and shape characteristics of each area in the image; a3.

2. Based on the grayscale index and shape characteristics of the light-transmitting area and the non-light-transmitting area of ​​the target device, determine the origin O, the positions of the x-axis and the y-axis, and the y-axis deflection angle of the target device in the static reference orientation.

4. The wind turbine tower status monitoring method based on target image recognition according to claim 3 is characterized in that: The dynamic monitoring is performed by processing images collected when the wind turbine is in operation. The process includes: b3.

1. For any tower section i, 1≤i≤n, n is the number of tower sections, obtain the lateral displacement D of the origin O of the target device in the image relative to the origin O of the quasi-static reference position of the target platform on the top of the tower _i_x , longitudinal displacement D _i_y , and the y-axis deflection angle A _i_y ; b3.2, according to the lateral displacement D _i_x , longitudinal displacement D _i_y and the y-axis deflection angle A _i_y Determine the tower status.

5. The wind turbine tower status monitoring method based on target image recognition according to claim 4 is characterized in that: The tower status determination described in step b3.2 includes the determination of obvious abnormality in tower deformation, the determination of obvious abnormality in overall deformation of the wind turbine tower, and the determination of obvious abnormality in the moving speed or deflection angular velocity of the tower target position.

6. The wind turbine tower status monitoring method based on target image recognition according to claim 5 is characterized in that: The tower deformation obviously abnormal determination includes the following process: if any of the following conditions is met, it is determined that the tower deformation of the i-th section is obviously abnormal: Condition 1, |D _i_x |≥D _i_x_limit ; Condition 2, |D _i_y |≥D _i_x_limit ; Condition 3: |A _i_y |≥A _i_y_limit ; Among them, D _i_x_limit , D _i_y_limit and A _i_y_limit They are the lateral displacement warning setting threshold, longitudinal displacement warning setting threshold, and y-axis deflection angle warning setting threshold of the i-th tower section.

7. The wind turbine tower status monitoring method based on target image recognition according to claim 5 is characterized in that: The determination of whether the overall deformation of the wind turbine tower is obviously abnormal includes the following process: if any of the following conditions is met, it is determined that the overall deformation of the wind turbine tower is obviously abnormal: Condition 1, | |≥D _i_x_limit_total ; Condition 2, | |≥D _i_y_limit_total ; Condition three, | |≥A _i_y_limit_total ; Among them, D _i_x_limit_total , D _i_y_limit_total and A _i_y_limit_total They are respectively the overall lateral deformation warning setting threshold, the overall longitudinal deformation warning setting threshold, and the total y-axis deflection warning setting threshold of the wind turbine tower.

8. The wind turbine tower status monitoring method based on target image recognition according to claim 5 is characterized in that: The tower target position moving speed or deflection angular velocity obviously abnormal judgment includes the following process: based on the time interval △t of two adjacent frames of images taken, calculate the D _i_x , D _i_y and A _i_y By dividing each change value by the time interval △t, we can get the moving speed V of the origin O of the tower target device along the x-axis direction. _i_x_△t , the moving speed V along the y-axis _i_y_△t , and the deflection angular velocity ω of the tower target y axis _i_y_△t If any of the following conditions is met, the moving speed or deflection angular velocity of the target position of the tower section i is judged to be obviously abnormal: Condition 1, |V _i_x_△t |≥V _i_x_△t_limit ; Condition 2, |V _i_y_△t |≥D _i_y_△t_limit ; Condition 3: |ω _i_y_△t |≥ω _i_y_△t_limit ; Among them, V _i_x_△t_limit 、V _i_y_△t_limit and ω _i_y_△t_limit They are respectively the lateral moving speed warning setting threshold, the longitudinal moving speed warning setting threshold, and the y-axis deflection angular velocity warning setting threshold of the i-th tower section.

9. A target device based on the wind turbine tower status monitoring method according to claim 1, characterized in that: The target device comprises: a lampshade and a group of wicks inside the lampshade, wherein the lampshade comprises a bottom plate, side plates on the sides of the bottom plate and a panel on the top of the bottom plate, and the panel is provided with a hollow light-transmitting area.

10. The target device according to claim 9, characterized in that: The light-transmitting area is a cross-shaped light-transmitting area, the horizontal and vertical light-transmitting lengths of the cross-shaped light-transmitting area are different, and a circular non-light-transmitting area is arranged at the center of the cross-shaped light-transmitting area.

Images