Tower drum detection method and device, electronic equipment and storage medium

Abstract

The invention relates to a tower drum detection method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring target point cloud data and image data of the internal surface of the tower drum; wherein the target point cloud data is data obtained by scanning the internal surface of the tower drum; based on the target point cloud data, determining the deformation condition of the tower drum; and determining the defect condition of the tower drum based on the image data. According to the method provided by the embodiment of the invention, the deformation condition and the defect condition of the tower drum can be determined, so that the tower drum is detected from multiple aspects, the safety of the tower drum in the use process is improved, and normal operation of a wind turbine generator is ensured.

Description

Technical Field

[0001] The present application relates to the technical field of equipment detection, and in particular to a tower detection method, device, electronic equipment and storage medium. Background Art

[0002] The tower of a wind turbine is an important part of a wind turbine. It bears the weight of the nacelle, blades, etc., ensuring the stable operation of the entire wind turbine. However, under the action of pressure loads and dynamic loads, the tower may have safety issues, thus affecting the operation of the wind turbine. For example, if the inclination of the tower exceeds the safe inclination, the wind turbine is at risk of tilting. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present application provides a tower detection method, device, electronic equipment and storage medium.

[0004] According to a first aspect of an embodiment of the present application, a tower detection method is provided, comprising:

[0005] Acquire target point cloud data and image data of the inner surface of the tower; wherein the target point cloud data is data obtained by scanning the inner surface of the tower;

[0006] Determining the deformation of the tower based on the target point cloud data;

[0007] Based on the image data, a defect condition of the tower is determined.

[0008] In some embodiments, the acquiring target point cloud data includes:

[0009] Determining a laser scanning mode based on the internal state of the tower and the height of the tower;

[0010] Based on the laser scanning method, a laser scanning operation is performed on the inner surface of the tower to obtain the target point cloud data.

[0011] In some embodiments, determining the laser scanning mode based on the internal state of the tower and the height of the tower includes:

[0012] When the height of the tower is greater than a preset height threshold, determining that the laser scanning mode is a drone laser scanning mode; or,

[0013] When the internal state of the tower meets the preset conditions and the height of the tower is less than or equal to the preset height threshold, the laser scanning mode is determined to be a drone laser scanning mode; or,

[0014] When the interior of the tower does not meet the preset conditions and the height of the tower is less than or equal to the preset height threshold, determining that the laser scanning mode is a wall-climbing robot laser scanning mode;

[0015] The preset condition is used to indicate that there is damage on the inner surface of the tower and / or the number of obstacles inside the tower is greater than a preset number threshold.

[0016] In some embodiments, determining the deformation of the tower based on the target point cloud data includes:

[0017] Based on the target point cloud data, a target three-dimensional model of the tower is generated; the target three-dimensional model is used to represent the three-dimensional model of the tower in the current state;

[0018] Based on the target three-dimensional model and the preset three-dimensional model, the deformation of the tower is determined; the preset three-dimensional model is used to characterize the three-dimensional model of the tower under an ideal state.

[0019] In some embodiments, the target three-dimensional model corresponds to a target shape parameter, the preset three-dimensional model corresponds to a preset shape parameter, and determining the deformation of the tower based on the target three-dimensional model and the preset three-dimensional model includes:

[0020] The target shape parameters are compared with the preset shape parameters to obtain the deformation of the tower.

[0021] In some embodiments, determining the defect condition of the tower based on the image data includes:

[0022] Based on the image data, generating a three-dimensional image corresponding to the inner surface of the tower;

[0023] A defect detection operation is performed on the three-dimensional image to obtain the defect status of the tower.

[0024] In some embodiments, the method further comprises:

[0025] The defects of the tower are marked in the three-dimensional image.

[0026] According to a second aspect of an embodiment of the present application, a tower detection device is provided, comprising:

[0027] An acquisition module is configured to acquire target point cloud data and image data of the inner surface of the tower; wherein the target point cloud data is data obtained by scanning the inner surface of the tower;

[0028] A first determination module is configured to determine the deformation of the tower based on the target point cloud data;

[0029] The second determination module is configured to determine the defect condition of the tower based on the image data.

[0030] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the tower detection method as described in the first aspect are implemented.

[0031] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the tower detection method described in the first aspect are implemented.

[0032] The technical solution provided by the embodiments of the present application may include the following beneficial effects: the method provided by the embodiments of the present application can determine the deformation and defect conditions of the tower, thereby realizing comprehensive inspection of the tower from multiple aspects, improving the safety of the tower during use, and thereby ensuring the normal operation of the wind turbine.

[0033] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0035] Figure 1 The figure is a flow chart of a tower detection method according to an exemplary embodiment.

[0036] Figure 2 It is a schematic diagram showing a marking method according to an exemplary embodiment.

[0037] Figure 3 It is a schematic diagram of a drone laser scanning method according to an exemplary embodiment.

[0038] Figure 4 It is a schematic diagram of a laser scanning method of a wall-climbing robot according to an exemplary embodiment.

[0039] Figure 5 The figure is a flow chart of a tower detection method according to an exemplary embodiment.

[0040] Figure 6 It is a block diagram of a tower detection device according to an exemplary embodiment.

[0041] Figure 7is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0042] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0043] The tower of a wind turbine is an important part of a wind turbine. It bears the weight of the nacelle, blades, etc., ensuring the stable operation of the entire wind turbine. However, under the action of pressure loads and dynamic loads, the tower may have safety issues, thus affecting the operation of the wind turbine. For example, if the inclination of the tower exceeds the safe inclination, the wind turbine is at risk of tilting.

[0044] In order to solve the above problems, the present application provides a tower detection method, which can obtain target point cloud data and image data of the inner surface of the tower; wherein the target point cloud data is data obtained by scanning the inner surface of the tower; based on the target point cloud data, the deformation of the tower is determined; based on the image data, the defect of the tower is determined. The method provided in the embodiment of the present application can determine the deformation and defect of the tower, thereby realizing comprehensive detection of the tower from multiple aspects, improving the safety of the tower during use, and thus ensuring the normal operation of the wind turbine.

[0045] The exemplary embodiment of the present application provides a tower detection method, which can be applied to electronic devices, and the electronic devices can be smart devices such as mobile phones, tablet computers, notebooks, smart robots, smart wearable devices, etc., and can also be used for detection equipment. In addition, the electronic device is also provided with various hardware resources, and energy storage devices that provide power for the operation of various hardware resources. Various detection devices and communication devices are also provided on the detection equipment, wherein the detection device is used to realize data detection, and the communication device is used to realize signal transmission and reception.

[0046] like Figure 1 As shown, the tower detection method shown in this embodiment includes:

[0047] S101, acquiring target point cloud data and image data of the inner surface of the tower; wherein the target point cloud data is data obtained by scanning the inner surface of the tower.

[0048] S102: Determine the deformation of the tower based on the target point cloud data.

[0049] S103: Determine the defect condition of the tower based on the image data.

[0050] In step S101, point cloud data can be used to represent the surface shape of the scanned object. Point cloud data is a discrete set of geometric information of the surface of an object in three-dimensional space, and is composed of a series of three-dimensional coordinate points. Each point usually includes its position information in the three-dimensional coordinate system and other attributes. Point cloud data is disordered and unstructured. Disorder means that the order of data points in the point cloud can be arbitrary, while unstructured means that the point cloud data does not have a regular matrix structure.

[0051] Optionally, the three-dimensional coordinate system may be a Cartesian coordinate system, which is composed of three mutually perpendicular coordinate axes, and the position of each point may be represented by a coordinate value (x, y, z). For a tower, the center point of the bottom surface of the tower may be determined as the origin, and the x-axis, y-axis, and z-axis may be established based on the origin to obtain a three-dimensional coordinate system.

[0052] In some embodiments, point cloud data of the inner surface of the tower may be acquired based on a laser scanning operation.

[0053] It should be noted that compared with the external space of the tower, the internal space of the tower is small and irregular, and there are multiple platforms inside the tower, each of which can carry different equipment and pipelines, and the layout of the internal space of the tower is complex. In some embodiments, the laser scanning method is determined based on the internal state of the tower and the height of the tower. Then, based on the laser scanning method, the internal surface of the tower is laser scanned to obtain target point cloud data. The target point cloud data refers to the point cloud data of the complete tower, and the data points in the target point cloud data are selected and determined based on the laser emission mode of the laser scanning method. The laser emission mode may include parameters such as the interval of the laser beam and the distance between the laser and the object to be detected. For example, when the laser beam interval is larger, the data points in the point cloud data are sparser. In this way, for the internal surface of the tower in different states, the laser scanning method suitable for the internal surface of the current tower can be determined in a targeted manner, so as to obtain more accurate target point cloud data.

[0054] In some embodiments, the laser scanning method may include a UAV laser scanning method and a wall-climbing robot laser scanning method. Among them, the UAV laser scanning method refers to setting a laser scanning device on a UAV. The scanning process of the UAV laser scanning method includes: the laser scanning device on the UAV emits a laser beam, and the laser beam is reflected when it encounters the inner surface of the tower, and the laser scanning device can receive the reflected laser signal. For each laser signal, the laser scanning device can determine the distance between the laser scanning device and the data point based on the reflection time and light speed of the laser signal, thereby determining the spatial position of the data point. A communication connection (such as a wireless communication connection) is set between the laser scanning device and the electronic device (such as a detection device), and then the laser scanning device can send the spatial position of each data point to the electronic device through the communication connection, and the electronic device can receive the spatial position of each data point, that is, to achieve the acquisition of point cloud data. The wall-climbing robot laser scanning method refers to setting the laser scanning device on a wall-climbing robot (the wall-climbing robot can be adsorbed on the inner surface of the tower). The scanning process of the wall-climbing robot laser scanning method is similar to that of the UAV laser scanning method, which will not be repeated here. Optionally, the laser scanning device can be a laser scanner, a time-of-flight scanner, or other devices.

[0055] Drones can quickly reach high altitudes and perform long-distance, contactless scanning operations. In addition, drones can flexibly shuttle in the air and avoid various obstacles, which can effectively improve the efficiency of laser scanning operations. Wall-climbing robots have strong adsorption capabilities and precise mobile control. The laser scanning method of wall-climbing robots can scan the inner surface of the tower more carefully, thereby obtaining more accurate point cloud data.

[0056] Combining the characteristics of the UAV laser scanning method and the wall-climbing robot laser scanning method, the following gives three situations for determining the laser scanning method based on the internal state of the tower and the height of the tower:

[0057] In the first case, when the height of the tower is greater than a preset height threshold, the laser scanning mode is determined to be a drone laser scanning mode.

[0058] The size of the preset height threshold may be set and selected based on actual needs. For example, the preset height threshold may be 20 meters, 30 meters, etc.

[0059] It should be noted that drones can easily reach high altitudes and have fast response capabilities. Therefore, for laser scanning scenarios where the tower height is greater than the preset height threshold, considering the convenience and timeliness of laser scanning operations, drone laser scanning can be used to scan the inner surface of the tower to obtain comprehensive and intuitive point cloud data of the inner surface of the tower.

[0060] In the second case, when the internal state of the tower meets the preset conditions and the height of the tower is less than or equal to the preset height threshold, the laser scanning mode is determined to be the drone laser scanning mode.

[0061] The preset condition is used to indicate that there is damage on the inner surface of the tower and / or the number of obstacles inside the tower is greater than a preset number threshold.

[0062] Optionally, the damage on the inner surface of the tower may include the presence of breakage, potholes, paint damage, rust, etc. inside the tower. For obstacles that are convenient to count, the number of obstacles inside the tower being greater than a preset number threshold may include the total number of obstacles being greater than a preset number threshold, which may be 5, 6, etc. For example, for equipment arranged inside the tower, the total number of equipment may be counted, and the size relationship between the total number of equipment and the preset number threshold may be determined; and for obstacles that are inconvenient to count, the number of obstacles inside the tower being greater than a preset number threshold may include the total area of ​​obstacles inside the tower being greater than a preset area threshold, which may be 20 square meters, 30 square meters, etc. For example, for pipelines arranged inside the tower, since the pipelines may be deployed in multiple areas inside the tower and it is inconvenient to count the number of pipelines, the area of ​​the area where the pipelines are deployed inside the tower may be determined, and the size relationship between the area and the preset area threshold may be determined.

[0063] When the internal state of the tower meets the preset conditions, if the wall-climbing robot laser scanning method is used, the wall-climbing robot may cause secondary damage to the internal surface of the tower, thereby increasing the risk of damage to the internal surface of the tower. In addition, when there are many obstacles inside the tower, it takes a lot of time to control the wall-climbing robot to avoid obstacles, and the scanning operation may not be able to be carried out smoothly. In some embodiments, for the scene where the internal state of the tower meets the preset conditions, the drone laser scanning method can realize laser scanning at a long distance and without contact, that is, the drone will not contact the internal surface of the tower, so the drone will not cause secondary damage to the internal surface of the tower. In addition, the drone can move flexibly in the air to avoid various obstacles. Therefore, for the laser scanning scene where the internal state of the tower meets the preset conditions and the height of the tower is less than or equal to the preset height threshold, the drone laser scanning method can be used to scan the internal surface of the tower, thereby improving the safety and scanning efficiency during the laser scanning process.

[0064] In the third case, when the interior of the tower does not meet the preset conditions and the height of the tower is less than or equal to the preset height threshold, the laser scanning mode is determined to be the wall-climbing robot laser scanning mode.

[0065] When the interior of the tower does not meet the preset conditions, it can be determined that there is no obvious damage, potholes, paint damage or rust inside the tower and / or the number of obstacles inside the tower is small. In this case, the wall-climbing robot will not cause secondary damage to the inner surface of the tower and can successfully avoid obstacles. In addition, the wall-climbing robot can fit closely to the inner surface of the tower, so the laser scanning device installed on the wall-climbing robot can perform more detailed laser scanning, thereby obtaining more accurate point cloud data.

[0066] Therefore, for laser scanning scenarios where the interior of the tower does not meet the preset conditions and the height of the tower is less than or equal to the preset height threshold, a wall-climbing robot laser scanning method can be used to scan the internal surface of the tower.

[0067] The embodiment of the present application can use a variety of methods to obtain image data of the inner surface of the tower. Optionally, the laser scanning device can obtain image data while obtaining point cloud data, that is, the laser scanning device can be used to obtain image data of the inner surface of the tower. Among them, the laser scanning method for obtaining image data can be consistent with the laser scanning method for obtaining point cloud data, and the specific process of determining the laser scanning method is not repeated here.

[0068] In some embodiments, image data of the inner surface of the tower can be obtained based on an image acquisition operation. In one example, an image acquisition device (different from a laser scanning device) can be used to perform an image acquisition operation to obtain image data of the inner surface of the tower. The image acquisition device can be set on a drone or a wall-climbing robot, and accordingly, the method of obtaining image data of the inner surface of the tower also includes a drone acquisition method and a wall-climbing robot acquisition method. The image acquisition method for obtaining image data can be consistent with the laser scanning method for obtaining point cloud data, and the specific process of determining the image acquisition method will not be repeated here.

[0069] In some embodiments, the point cloud data can be converted into a depth image, which includes the distance information between each point in the point cloud and the laser scanning device. Through a preset algorithm and parameters, the point cloud data can be projected onto a two-dimensional image plane to obtain image data. In one example, image data of the inner surface of the tower can be determined based on the point cloud data.

[0070] In step S102, a target three-dimensional model of the tower can be generated based on the target point cloud data, and the deformation of the tower can be determined based on the target three-dimensional model and a preset three-dimensional model; the preset three-dimensional model is used to characterize the three-dimensional model of the tower in an ideal state.

[0071] In some embodiments, the target point cloud data may be input into an application for generating a three-dimensional model, so as to generate a target three-dimensional model of the tower based on the target point cloud data.

[0072] In some embodiments, the preset three-dimensional model may be determined based on the design drawings of the tower or the historical data of the inner surface of the tower. For example, the design drawings of the tower include various dimensional parameters of the tower in an ideal state, and the preset three-dimensional model may be determined based on the various dimensional parameters.

[0073] In some embodiments, the target shape parameters corresponding to the target three-dimensional model are compared with the preset shape parameters corresponding to the preset three-dimensional model to obtain the deformation of the tower. In one example, the absolute value of the difference between the target shape parameters and the preset shape parameters can be calculated, and the absolute value can be determined as the deformation of the tower. Optionally, the deformation of the tower includes: the change of the inclination of the tower, the change of the ellipticity, and the change of the concentricity.

[0074] The shape parameters of the three-dimensional model can be determined based on the type of deformation of the tower to be determined. In one example, if the change in the inclination of the tower needs to be determined, the target inclination parameter corresponding to the target three-dimensional model and the preset inclination parameter corresponding to the preset three-dimensional model are obtained, and the target inclination parameter and the preset inclination parameter are compared to obtain the change in the inclination of the tower. For example, if the preset inclination parameter is 0.054° and the target inclination parameter is 0.055°, the change in the inclination of the tower is 0.001°. In one example, if the change in the ellipticity of the tower needs to be determined, the target ellipticity parameter corresponding to the target three-dimensional model and the preset ellipticity parameter corresponding to the preset three-dimensional model are obtained, and the target ellipticity parameter and the preset ellipticity parameter are compared to obtain the change in the ellipticity of the tower. For example, if the preset ellipticity parameter is 0.5% and the target ellipticity parameter is 0.48%, the change in the ellipticity of the tower is 0.02%.

[0075] In one example, each deformation parameter corresponds to its own deformation range. For example, the preset deformation range of the inclination parameter is [0.001°, 0.004°], and the preset deformation range of the ellipticity parameter is [0.001%, 0.02%]. Accordingly, the deformation of the tower can be compared with the preset deformation range. When the deformation of the tower does not exceed the preset deformation range, it can be determined that the deformation of the tower is normal, and there is no need to conduct further inspection and maintenance of the tower temporarily; on the contrary, when the deformation of the tower exceeds the preset deformation range, it can be determined that the deformation of the tower is abnormal, and the inspection personnel are prompted to conduct further inspection and / or maintenance of the tower to ensure the safe operation of the tower and the wind turbine. For example, the inclination change of the tower in the above text is 0.001°, and the inclination change is within the preset deformation range of the inclination parameter. It can be determined that the inclination change is normal deformation. For another example, the ovality change of the tower in the above text is 0.02%, which is within the preset deformation range of the ovality parameter, and it can be determined that the ovality change is a normal deformation.

[0076] In addition, it should be noted that the target three-dimensional model can be divided into multiple three-dimensional models, and the deformation of each three-dimensional model can be determined separately, so that the deformation of the tower at different heights can be obtained more accurately, so as to more comprehensively evaluate the actual deformation of the tower. For example, the target three-dimensional model is divided into four three-dimensional models, and for each three-dimensional model, each three-dimensional model is divided into 8-10 measurement layers, and the deformation of each measurement layer is determined separately. The process of determining the deformation of each three-dimensional model can be referred to above, and will not be repeated here.

[0077] In step S103, in some embodiments, a three-dimensional image corresponding to the inner surface of the tower may be generated based on the image data; a defect detection operation may be performed on the three-dimensional image to obtain the defect status of the tower.

[0078] A three-dimensional image refers to an image created and displayed in a three-dimensional space, and a three-dimensional image can provide depth information to make the image more three-dimensional. In some embodiments, the image data can be input into an application for generating a three-dimensional image to obtain a three-dimensional image corresponding to the inner surface of the tower.

[0079] In some embodiments, a defect detection operation can be performed on a three-dimensional image through a defect detection algorithm to obtain the defect status of the tower. This embodiment does not limit the type of defect detection algorithm. Optionally, the defect detection algorithm can be a defect detection algorithm based on deep learning, a defect detection algorithm based on image similarity, a defect detection algorithm based on a segmentation network, etc. It should be noted that the above algorithm is an algorithm model obtained by training based on a large amount of sample image data. The process of using a defect detection algorithm to perform defect detection operations on a three-dimensional image is not specifically described here.

[0080] In one example, the defect detection operation may include detection of defect types, wherein the defect types may include cracks, rust, corrosion, deformation, etc. Accordingly, the defect condition of the tower may include the defect type of the inner surface of the tower. In addition, optionally, the defect condition of the tower may also include the position of the defect, the height of the defect, the angle of the defect, etc.

[0081] In some embodiments, the defects of the tower can be marked in the three-dimensional image, so that the inspector can quickly locate the defect location and quickly obtain the defect type, thereby saving the inspector's time and energy. For example, the defects on the inner surface of the tower can be marked by highlighting, border selection, and annotation. Figure 2 A schematic diagram of a marking method is shown in FIG. Figure 2 The black area in the figure is the defect area. Figure 2 The defect is selected by a border, and the defect type (type) of the defect is annotated as rust, the height (high) of the defect is 22.43m, and the angle (ang) of the defect is -35.3°-35.4°.

[0082] In addition, in some embodiments, the three-dimensional image can be combined with virtual reality (VR) technology to obtain a VR image, which can not only provide depth information, but also interact with the user's head movement, perspective change, etc. in real time, thereby providing the user with a more realistic and immersive viewing effect. Through the VR image, the user can more intuitively view the details of the inner surface of the tower, and the user can also freely move and zoom the perspective in the virtual reality environment, so as to more accurately analyze the defects on the inner surface of the tower, and thus determine a repair method that is more suitable for the current defects.

[0083] In one example, two-dimensional images of different areas of the inner surface of the tower can be generated based on the image data, and defect detection operations can be performed on the two-dimensional images to obtain the defect status of the tower. The specific process of performing defect detection operations on the two-dimensional images will not be repeated here. In addition, defects can be marked and / or annotated in the two-dimensional images, and the specific process will not be repeated here.

[0084] Or, in another example, the area including the defect in the three-dimensional image may be automatically captured to obtain a two-dimensional image corresponding to the defect, and the two-dimensional image may or may not include marks and / or annotations.

[0085] The 3D image can provide complete defect information of each defect on the inner surface of the tower, such as the type of defect, the angle of the defect, the height of the defect, the precise location of the defect, etc., while the 2D image can specifically display the details of a defect. In some embodiments, the inspector can combine the 2D image and the 3D image to further analyze the defects on the inner surface of the tower, so as to more accurately determine the defect type, size (length, width and depth of the defect) and specific location of the defect, so as to determine the repair method for the defect.

[0086] In some embodiments, a tower inspection report can be generated based on the deformation and defects of the tower. Accordingly, maintenance personnel can further inspect or repair the tower based on the inspection report. Optionally, in the tower inspection report, the deformation of abnormal deformation and the defect location and defect type of defects on the inner surface of the tower can be highlighted. For example, the key display content can be marked in the inspection report to facilitate the inspection personnel to quickly locate the content to be further inspected and repaired.

[0087] The method provided in the embodiment of the present application can determine the deformation and defects of the tower, thereby realizing the detection of the tower. In this way, it can provide reliable data support for the safety assessment of the tower, and timely determine the safety problems existing in the tower during the detection process, so as to further inspect and repair the tower, thereby ensuring the normal operation of the tower and the wind turbine.

[0088] In addition, it is difficult to detect the complete data of the internal space of the tower with the current detection method. The reasons include the following: the internal space of the tower is relatively small, and as the height of the tower increases, the internal space of the tower becomes more cramped; there are multiple platforms inside the tower, and each platform is connected by stairs or ladders, which increases the complexity of the internal space of the tower; the interior of the tower may have irregular shapes based on equipment layout or structural design requirements. The method provided in the embodiment of the present application can determine the laser scanning method suitable for the current state based on the different states of the tower, and obtain complete and high-precision point cloud data and image data of the internal surface of the tower, thereby solving the problem of difficulty in collecting internal data of the tower and providing technical support for data acquisition.

[0089] The specific scanning process of the UAV laser scanning method and the wall-climbing robot laser scanning method is explained below.

[0090] For UAV laser scanning methods, such as Figure 3 The schematic diagram of the UAV laser scanning method shown in the figure, the UAV can be operated inside the tower. The UAV can hover at different points inside the tower, and the laser scanning device can perform laser scanning operations. Optionally, the UAV can rotate 360 ​​degrees at different points, and the laser scanning device can emit laser beams during the movement of the UAV to obtain point cloud data corresponding to the inner surface of the tower.

[0091] For the laser scanning method of the wall-climbing robot, such as Figure 4 Schematic diagram of the laser scanning method of the wall-climbing robot shown, the wall-climbing robot is attached to the inner surface of the tower. Optionally, the wall-climbing robot can move along a horizontal circular path at different heights, and the laser scanning device can emit a laser beam during the movement of the wall-climbing robot to obtain point cloud data corresponding to the inner surface of the tower.

[0092] The exemplary embodiment of the present application provides a tower detection method, such as Figure 5 As shown, a tower detection method shown in this application includes:

[0093] S501. Determine a laser scanning method based on the internal state of the tower and the height of the tower.

[0094] S502: Based on the laser scanning method, a laser scanning operation is performed on the inner surface of the tower to obtain target point cloud data.

[0095] S503: Based on the laser scanning method, a laser scanning operation is performed on the inner surface of the tower to obtain image data of the inner surface of the tower.

[0096] S504: Generate a target three-dimensional model of the tower based on the target point cloud data.

[0097] S505: Compare the target shape parameters with the preset shape parameters to obtain the deformation of the tower.

[0098] S506: Generate a three-dimensional image corresponding to the inner surface of the tower based on the image data.

[0099] S507: Perform defect detection operations on the three-dimensional image to obtain the defect status of the tower.

[0100] S508. Determine the inspection report of the tower based on the deformation and defect conditions.

[0101] Step S502 and step S503 may be executed simultaneously or one after another. Correspondingly, steps S504-S505 and steps S506-S507 may be executed simultaneously or one after another, which is not limited here.

[0102] In step S508, the inspection report is provided to the inspection personnel so that the inspection personnel can repair the tower.

[0103] The exemplary embodiment of the present application provides a tower detection device, such as Figure 6 As shown, this application shows a block diagram of a tower detection device.

[0104] The block diagram includes an acquisition module 601, a first determination module 602, and a second determination module 603. The acquisition module 601 is configured to acquire target point cloud data and image data of the inner surface of the tower; wherein the target point cloud data is data obtained by scanning the inner surface of the tower; the first determination module 602 is configured to determine the deformation of the tower based on the target point cloud data;

[0105] The second determination module 603 is configured to determine the defect condition of the tower based on the image data.

[0106] In some embodiments, the acquisition module 601 is configured to:

[0107] Determine the laser scanning method based on the internal state of the tower and the height of the tower;

[0108] Based on the laser scanning method, the internal surface of the tower is laser scanned to obtain the target point cloud data.

[0109] In some embodiments, the acquisition module 601 is configured to:

[0110] When the height of the tower is greater than a preset height threshold, the laser scanning mode is determined to be a drone laser scanning mode; or,

[0111] When the internal state of the tower meets the preset conditions and the height of the tower is less than or equal to the preset height threshold, the laser scanning mode is determined to be the drone laser scanning mode; or,

[0112] When the interior of the tower does not meet the preset conditions and the height of the tower is less than or equal to the preset height threshold, determining that the laser scanning mode is a wall-climbing robot laser scanning mode;

[0113] The preset condition is used to indicate that there is damage on the inner surface of the tower and / or the number of obstacles inside the tower is greater than a preset number threshold.

[0114] In some embodiments, the first determining module 602 is configured to:

[0115] Based on the target point cloud data, a target three-dimensional model of the tower is generated; the target three-dimensional model is used to represent the three-dimensional model of the tower in the current state;

[0116] The deformation of the tower is determined based on the target three-dimensional model and the preset three-dimensional model; the preset three-dimensional model is used to characterize the three-dimensional model of the tower under an ideal state.

[0117] In some embodiments, the target three-dimensional model corresponds to the target shape parameters, the preset three-dimensional model corresponds to the preset shape parameters, and the first determining module 602 is configured to:

[0118] The target shape parameters are compared with the preset shape parameters to obtain the deformation of the tower.

[0119] In some embodiments, the second determining module 603 is configured to:

[0120] Based on the image data, a three-dimensional image corresponding to the inner surface of the tower is generated;

[0121] Perform defect detection operations on the three-dimensional image to obtain the defect status of the tower.

[0122] In some embodiments, the second determining module 603 is further configured to:

[0123] Mark tower defects in the 3D image.

[0124] Each module in the tower detection device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in an electronic device in the form of hardware, or can be stored in a memory in an electronic device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0125] In an exemplary embodiment, an electronic device is provided, including a processor and a memory, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any of the above tower detection methods are implemented.

[0126] In an exemplary embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of any of the tower detection methods described above are implemented. The computer readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0127] refer to Figure 7, now a block diagram of the structure of the electronic device of the present application will be described, the electronic device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 to a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0128] Multiple components in the electronic device 700 are connected to the I / O interface 705, including: an input unit 706, an output unit 707, a storage unit 708, and a communication unit 709. The input unit 706 can be any type of device that can input information to the electronic device 700. The input unit 706 can receive input digital or character information and generate key signal input related to user settings and / or function control of the electronic device 700, and can include but is not limited to a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and / or a remote controller. The output unit 707 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 708 can include but is not limited to a disk, an optical disk. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0129] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as the tower detection method. For example, in some embodiments, the tower detection method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the tower detection method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the tower detection method in any other appropriate manner (e.g., by means of firmware).

[0130] The electronic device 700 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above-mentioned tower detection method.

[0131] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in this application. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0132] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A tower detection method, characterized in that: include: Acquire target point cloud data and image data of the inner surface of the tower; wherein the target point cloud data is data obtained by scanning the inner surface of the tower; Determining the deformation of the tower based on the target point cloud data; Based on the image data, a defect condition of the tower is determined.

2. The tower detection method according to claim 1, characterized in that: The step of acquiring target point cloud data comprises: Determining a laser scanning mode based on the internal state of the tower and the height of the tower; Based on the laser scanning method, a laser scanning operation is performed on the inner surface of the tower to obtain the target point cloud data.

3. The tower detection method according to claim 2, characterized in that: The determining of the laser scanning mode based on the internal state of the tower and the height of the tower includes: When the height of the tower is greater than a preset height threshold, determining that the laser scanning mode is a drone laser scanning mode; or, When the internal state of the tower meets the preset conditions and the height of the tower is less than or equal to the preset height threshold, the laser scanning mode is determined to be a drone laser scanning mode; or, When the interior of the tower does not meet the preset conditions and the height of the tower is less than or equal to the preset height threshold, determining that the laser scanning mode is a wall-climbing robot laser scanning mode; The preset condition is used to indicate that there is damage on the inner surface of the tower and / or the number of obstacles inside the tower is greater than a preset number threshold.

4. The tower detection method according to claim 1, characterized in that: The step of determining the deformation of the tower based on the target point cloud data includes: Based on the target point cloud data, a target three-dimensional model of the tower is generated; the target three-dimensional model is used to represent the three-dimensional model of the tower in the current state; Based on the target three-dimensional model and the preset three-dimensional model, the deformation of the tower is determined; the preset three-dimensional model is used to characterize the three-dimensional model of the tower under an ideal state.

5. The tower detection method according to claim 4, characterized in that: The target three-dimensional model corresponds to a target shape parameter, the preset three-dimensional model corresponds to a preset shape parameter, and the deformation of the tower is determined based on the target three-dimensional model and the preset three-dimensional model, including: The target shape parameters are compared with the preset shape parameters to obtain the deformation of the tower.

6. The tower detection method according to claim 1, characterized in that: The step of determining the defect of the tower based on the image data includes: Based on the image data, generating a three-dimensional image corresponding to the inner surface of the tower; A defect detection operation is performed on the three-dimensional image to obtain the defect status of the tower.

7. The tower detection method according to claim 6, characterized in that: The method further comprises: The defects of the tower are marked in the three-dimensional image.

8. A tower detection device, characterized in that: include: An acquisition module is configured to acquire target point cloud data and image data of the inner surface of the tower; wherein the target point cloud data is data obtained by scanning the inner surface of the tower; A first determination module is configured to determine the deformation of the tower based on the target point cloud data; The second determination module is configured to determine the defect condition of the tower based on the image data.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the tower detection method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the tower detection method according to any one of claims 1 to 7 are implemented.

Images