An intelligent inspection system for wind turbine hubs based on AR devices

Abstract

The present invention provides an intelligent inspection system for wind turbine hubs based on AR devices, including a cloud server, a drone, an AR device, a permission management module, a positioning module, a sensing module and an acquisition module. The positioning module is used to locate the real-time positioning data of the drone and the inspection position of the wind turbine hub. The sensing module is used to sense the distance between the drone and the obstacle. The sensing module evaluates the inspection route of the drone based on the collected distance data, the real-time positioning data of the drone collected by the positioning module and the inspection position of the wind turbine hub, so as to dynamically adjust the inspection route and direction of the drone. The acquisition module is used to collect image and video data of the wind turbine hub and synchronize the collected image and video data to the cloud server. The permission management module is used to grant the AR device an access permission code to access the cloud server, and the AR device views the image and video data stored in the cloud server based on the access permission code.

Description

Technical Field

[0001] The present invention relates to the technical field of monitoring and testing of wind turbines, and in particular to an AR device-based intelligent inspection system for wind turbine hubs. Background Art

[0002] With the development of the wind power industry, the number and scale of wind farms are constantly increasing. However, the wind turbine hub is one of the components most prone to failure and damage in wind turbines. Therefore, regular inspection and maintenance of wind turbine hubs is particularly important. Traditional wind turbine hub inspection methods mostly rely on manual inspection, which is inefficient and inaccurate.

[0003] For example, the prior art CN114394236A discloses a drone for inspecting wind turbine blades. Generally speaking, in the traditional mode, wind turbine blade inspections require manual work with a hanging basket or a high-power telescope to identify cracks on the blades with the naked eye. This method is time-consuming and labor-intensive, and the recognition accuracy is low. At present, some manufacturers have developed technical solutions for inspecting wind turbine blades using drones. However, most of the current solutions use a predetermined inspection route to control the drone to capture images of the blade area, and then perform splicing and image recognition processing on the captured images. However, due to the large actual coverage area of ​​wind turbine blades, the spliced ​​images obtained in this way often cannot accurately reflect the specific information of the blades, and when blade defects are found, the defects cannot be located very accurately.

[0004] Another typical example is the drone-based wind turbine blade inspection route planning method disclosed in CN114442665A. Currently, some manufacturers have developed technical solutions for wind turbine blade inspection using drones. However, most current solutions use a predetermined inspection route, control the drone to capture images of the blade area, and then perform image splicing and image recognition processing on the captured images. However, the predetermined route setting is often a theoretically optimized route and cannot be adjusted according to actual conditions. In particular, flexible and intelligent adjustments cannot be achieved when there are multiple wind turbines.

[0005] The present invention is made in order to solve the common problems in this field, such as low intelligence, inability to locate the position of hub defects, poor real-time performance, untimely data transmission, poor interactivity, and inability to actively adjust the inspection route. Summary of the Invention

[0006] The purpose of the present invention is to address the current deficiencies and propose an intelligent inspection system for wind turbine hubs based on AR equipment.

[0007] In order to overcome the deficiencies of the prior art, the present invention adopts the following technical solutions:

[0008] A wind turbine hub intelligent inspection system based on AR equipment, the wind turbine hub intelligent inspection system comprising a cloud server and a drone, characterized in that the wind turbine hub intelligent inspection system further comprises an AR device, a rights management module, a positioning module, a sensing module and a collection module, the cloud server being connected to the drone, the AR device, the rights management module, the positioning module, the sensing module and the collection module respectively, and the sensing module and the collection module being arranged on the drone;

[0009] The positioning module is used to locate the real-time positioning data of the drone and the inspection position of the wind turbine hub. The sensing module is used to sense the distance between the drone and the obstacle. The sensing module evaluates the inspection route of the drone based on the collected distance data, the real-time positioning data of the drone collected by the positioning module, and the inspection position of the wind turbine hub, so as to dynamically adjust the inspection route and direction of the drone. The acquisition module is used to collect image and video data of the wind turbine hub and synchronize the collected image and video data to the cloud server. The permission management module is used to grant the AR device an access permission code to access the cloud server, and the AR device views the image and video data stored in the cloud server according to the access permission code.

[0010] The sensing module includes a sensing unit and an evaluation unit. The sensing unit obtains obstacle data around the drone. The evaluation unit evaluates the drone's inspection route based on the obstacle data collected by the sensing unit, the inspection position data collected by the positioning module, and the drone's real-time positioning data, so as to dynamically adjust the drone's inspection route and direction.

[0011] The user wears the AR device and accesses the cloud server in real time to view the image and video data collected by the collection module.

[0012] Optionally, the AR device includes AR glasses and a networking unit, and the networking unit establishes a data transmission link between the AR glasses and the cloud server after obtaining authorization from the authority management module;

[0013] Before accessing the cloud server, the AR glasses need the access permission code granted by the permission management module to authorize the AR device to access the cloud server and establish a data transmission link between the AR glasses and the cloud server through the networking unit.

[0014] Optionally, the positioning module includes an interaction unit and a positioning unit, the interaction unit includes an interactor and a data storage device, the interactor is used to interact with the wind turbine hub to obtain the inspection position of the wind turbine hub, and the data storage device is used to store the inspection position collected by the interactor;

[0015] After locating the position of the UAV, the positioning unit transmits the real-time position of the UAV and the inspection position data of the wind turbine hub to the evaluation unit.

[0016] Optionally, the evaluation unit dynamically adjusts the inspection route and direction of the drone according to the following steps:

[0017] STEP 1: Use the real-time location coordinates of the drone as the starting coordinates and the specified inspection coordinates in the inspection location set as the end coordinates;

[0018] STEP 2: Calculate the distance between the starting point and the specified inspection coordinates and determine whether it is less than or equal to the safety inspection distance.

[0019] STEP 3: Divide the distance between the starting point and the end point into several equal segments, with each segment length not exceeding the safe inspection distance, to obtain multiple drone inspection points;

[0020] STEP 4: The drone goes to the inspection points in turn for inspection. During the process of going to each inspection point, it is necessary to continuously update the real-time position coordinates of the drone and calculate the inspection route and direction based on the real-time position coordinates and the coordinates of the next inspection point;

[0021] STEP 5: During the inspection process, it is necessary to monitor the status of the drone and environmental conditions in real time to ensure the safety and stability of the inspection process;

[0022] STEP 6: After the inspection, the drone returns to the base or designated location and uploads the inspection data and report.

[0023] Optionally, in step STEP2, the distance between the starting point and the end point is calculated according to the following formula:

[0024]

[0025] Where (x1, y1) is the starting point coordinate, (x b ,y b ) is the specified inspection coordinate in the inspection coordinate set;

[0026] The evaluation unit compares the distance between the starting point and the end point with the safety inspection distance safety;

[0027] If distance≤safety, the drone goes directly to the inspection location;

[0028] If distance>safety, it needs to be divided into multiple inspection points;

[0029] The safety inspection distance safety is set by the operator / system or according to the distance between the UAV and the wind turbine hub.

[0030] Optionally, in step STEP3, the evaluation unit performs distance segmentation according to the following formula:

[0031]

[0032] In the formula, segment_num is the number of segments, distance is the distance between the starting point and the specified inspection coordinate, and safety is the safety inspection distance, whose value is set by the system. is the rounding symbol;

[0033] Optionally, in STEP 4, set the current coordinates of the drone to (x u ,y u ), the coordinates of the next inspection point are (x v ,y v ), then the direction angle θ of the inspection route is calculated by the vector (x u -x v ,y u -y v ) is obtained, that is:

[0034] θ=arctan(y v -y u ,x v -x u ).

[0035] The beneficial effects achieved by the present invention are:

[0036] 1. Through the cooperation between the acquisition module and the drone, the drone can inspect the wind turbine hub, ensuring that defects of the wind turbine hub can be queried, thereby improving the intelligence of the entire inspection process;

[0037] 2. Through the cooperation between the interaction unit and the positioning unit, the drone can interact with the wind turbine hub being inspected, thereby improving the accuracy and efficiency of wind turbine hub inspection. The interaction between the drone and the wind turbine hub is also taken into account, so that the drone's inspection route can be accurately adjusted;

[0038] 3. Through the cooperation between the rights management module and the AR device, the AR device can perform identity authentication, ensuring the security of data viewing and ensuring that the inspection image and video data can be checked, further improving the inspection quality;

[0039] 4. By coordinating the direction of the drone inspection route and the inspection points, the inspection position of the drone can be actively and dynamically adjusted according to the real-time position of the drone, so as to improve the safety of the entire drone inspection process and prevent the inspection process from causing new damage to the wind turbine hub. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but rather the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0041] Figure 1 It is an overall block diagram of the present invention.

[0042] Figure 2 The figure is a block diagram of the UAV, collection probe and wind turbine hub of the present invention.

[0043] Figure 3 It is a block diagram of the interaction unit and the positioning unit of the present invention.

[0044] Figure 4 It is a block diagram of the analysis unit and the early warning unit of the present invention.

[0045] Figure 5 Schematic diagram of the radius and safety distance of the wind turbine hub of the present invention.

[0046] Description of the accompanying figures: 1- Wind turbine hub. DETAILED DESCRIPTION

[0047] The following is an explanation of the embodiments of the present invention through specific embodiments. Those skilled in the art can understand the advantages and effects of the present invention from the contents disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and the details in this specification can also be modified and changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. In addition, the drawings of the present invention are only simple schematic illustrations and are not depicted in actual size. It is stated in advance. The following embodiments will further explain the relevant technical content of the present invention in detail, but the disclosed content is not intended to limit the scope of protection of the present invention.

[0048] Example 1: According to Figure 1 、 Figure 2 、 Figure 3 、 Figure 4 、 Figure 5 As shown, this embodiment provides a wind turbine hub intelligent inspection system based on AR equipment, which includes a cloud server, a drone, an AR device, a rights management module, a positioning module, a sensing module, and a collection module. The cloud server is respectively connected to the drone, the AR device, the rights management module, the positioning module, the sensing module, and the collection module. The sensing module and the collection module are arranged on the drone.

[0049] The positioning module is used to locate the real-time positioning data of the drone and the inspection position of the wind turbine hub, the sensing module is used to sense the distance between the drone and the obstacle, and the sensing module evaluates the inspection route of the drone based on the collected distance data, the real-time positioning data of the drone collected by the positioning module, and the inspection position of the wind turbine hub, so as to dynamically adjust the inspection route and direction of the drone, wherein the inspection position data of the wind turbine hub is obtained in a specific manner: when the drone flies near the wind turbine hub, the positioning module sends a positioning instruction to the wind turbine hub, so that the wind turbine hub can return the position of the wind turbine hub to the positioning module based on the positioning instruction, thereby obtaining the inspection position of the wind turbine hub; the acquisition module is used to collect image and video data of the wind turbine hub, and synchronize the collected image and video data to the cloud server, the permission management module is used to grant the AR device an access permission code to access the cloud server, and the AR device views the image and video data stored in the cloud server according to the access permission code;

[0050] The wind turbine hub intelligent inspection system also includes a central processing unit, which is respectively connected to the cloud server, the drone, the AR device, the authority management module, the positioning module, the sensing module and the acquisition module, and centrally controls the drone, the AR device, the authority management module, the positioning module, the sensing module and the acquisition module based on the central processing unit;

[0051] The acquisition module includes an acquisition unit and a data upload unit, wherein the acquisition unit is used to acquire image and video data of the wind turbine hub, and the data upload unit uploads the image and video data acquired by the acquisition unit to the cloud server;

[0052] The acquisition unit includes an acquisition probe and a posture adjustment component, wherein the acquisition probe is used to acquire image and video data of the wind turbine hub, and the posture adjustment component is used to adjust the posture of the acquisition probe; the posture adjustment component includes an adjustment seat, an adjustment drive mechanism and a rotation detection member, and the adjustment seat is provided with a rotation cavity;

[0053] The acquisition probe is arranged in the rotation chamber and is hinged to the inner side wall of the rotation chamber via a rotation rod. The adjustment drive mechanism and the rotation rod rotate along the hinge position to adjust the pitch angle and collection angle of the acquisition probe. The rotation detection member is used to detect the rotation angle of the acquisition probe.

[0054] In this embodiment, each time the acquisition unit acquires the image and video data of the wind turbine hub, it sends a synchronization instruction to the data upload unit, so that the data upload unit transmits the image and video data acquired by the acquisition unit to the cloud server;

[0055] In addition, the data uploading unit synchronizes the data to the cloud server, which is a technical field well known to those skilled in the art. Those skilled in the art can refer to relevant technical manuals to learn about the technology, so it will not be described in detail in this embodiment.

[0056] In this embodiment, the acquisition module cooperates with the drone, so that the drone can inspect the wind turbine hub, ensuring that defects of the wind turbine hub can be queried, thereby improving the intelligence of the entire inspection process;

[0057] The positioning module includes an interaction unit and a positioning unit, wherein the interaction unit is used to interact with the wind turbine hub at the inspection position to obtain the inspection position of the wind turbine hub, and the positioning unit is used to perform real-time positioning of the UAV to obtain real-time positioning data of the UAV;

[0058] The interaction unit includes an interactor, a communicator, and an activity range determination unit. The communicator is used to establish communication between the interactor, the activity range determination unit, and the positioning unit. The interactor receives an interaction instruction from the positioning unit, so that the activity range determination unit packages the safety distance corresponding to the wind turbine hub, the activity range data of the blades corresponding to the hub, and the safety distance related to the hub activity range through the communicator and transmits them directly to the positioning unit.

[0059] The activity range determination unit determines the activity range of the corresponding blade according to the model of the wind turbine hub, determines the safety distance corresponding to the wind turbine hub according to the activity range, and determines the inspection position set of the wind turbine hub according to the activity range and the safety distance; the safety distance is the distance between the drone and the wind turbine hub to ensure safe operation during the inspection;

[0060] like Figure 5 As shown, the activity range determining unit determines the activity range according to the following formula, and establishes a rotating plane coordinate system corresponding to the blade with the wind turbine hub as the coordinate origin;

[0061]

[0062] In the formula, range is the safe distance that the UAV approaches the wind turbine hub during inspection, and its value is set by the system. R0 is the radius of the wind turbine hub corresponding to the blade rotation range. (x a ,y a ) is the coordinate of the ath inspection position of the wind turbine hub;

[0063] The positioning unit includes a locator and a transmitter, wherein the locator collects the real-time position of the UAV and transmits the collected data to the sensing module via the transmitter;

[0064] In this embodiment, the positioning unit is provided on the drone;

[0065] Through the cooperation between the interaction unit and the positioning unit, the drone can interact with the wind turbine hub to be inspected, thereby improving the accuracy and efficiency of the wind turbine hub inspection. The interaction between the drone and the wind turbine hub is also taken into account, so that the inspection route of the drone can be accurately adjusted.

[0066] The sensing module includes a sensing unit and an evaluation unit. The sensing unit obtains obstacle data around the drone. The evaluation unit evaluates the drone's inspection route based on the obstacle data collected by the sensing unit, the inspection position data collected by the positioning module, and the drone's real-time positioning data, so as to dynamically adjust the drone's inspection route and direction.

[0067] The user wears the AR device and accesses the cloud server in real time to view the image and video data collected by the collection module;

[0068] The sensing unit includes at least two matrix radars and two support bases, each matrix radar is respectively arranged on the corresponding support base to form a detection part, wherein the detection part is symmetrically arranged on the drone to detect obstacles in the flight direction of the drone;

[0069] If there is an obstacle in the inspection flight direction of the drone and the distance between the drone and the obstacle area is less than the safe distance, the drone is stopped from moving forward;

[0070] Optionally, the AR device includes AR glasses and a networking unit, and the networking unit establishes a data transmission link between the AR glasses and the cloud server after obtaining authorization from the authority management module;

[0071] Before accessing the cloud server, the AR glasses need the access permission code granted by the permission management module to authorize the AR device to access the cloud server and establish a data transmission link between the AR glasses and the cloud server through the networking unit;

[0072] After obtaining authorization from the authority management module, the networking unit connects the AR glasses to the cloud server, so that the AR glasses can obtain image and video data of the drone's acquisition module inspection;

[0073] The rights management module includes a basic database and an authorization terminal. The basic database is used to store the identity identification code of the AR device, the level of the AR glasses, and the identity information data of the user. The identity identification code and the identity information data need to be processed to obtain a sequence with the same number of bits as the access permission code. The identity identification code is processed to obtain an identity identification sequence, and the identity information data is processed to obtain an identity information sequence. The number of bits of the access permission code is preset by the system. The identity identification code and the identity information data can be processed using a hash function, such as MD5, SHA, etc., or an encryption algorithm, such as AES, RSA, etc. The authorization terminal generates the access permission code based on the stored data in the basic database:

[0074]

[0075] code(b) is the value corresponding to the bth bit of the access permission code. L is the level of the connection line, which is set by the actual situation of the connected AR device. For example, if the level of the AR device to be accessed is level 1, then L = 1; if the level of the AR device to be accessed is level 2, then L = 2. ID(b) is the value of the bth bit of the identity identification sequence of the AR glasses. M is the number of connections of the AR glasses on that day. Identity(b) is the value of the bth bit of the identity information sequence of the user. is the floor rounding symbol;

[0076] When the user needs to use the AR glasses, he needs to transmit his own identity information data to the cloud server or the AR glasses. The identity information data can be obtained by the fingerprint recognition module on the AR glasses and sent to the cloud server (for example, the fingerprint recognition module collects the user's fingerprint image and sends it to the cloud server), or by the iris recognition module on the AR glasses (for example, the iris recognition module collects the user's iris image and sends it to the cloud server), or by the data input module on the AR glasses and sends it to the cloud server (for example, the user enters the ID number), or by a smart device connected to the AR glasses and the server data and sends it to the cloud server (for example, the user connects to the AR glasses via a mobile phone and enters the ID number through the mobile phone APP and sends it to the cloud server). The cloud server can obtain the user's identity information by comparing the pre-stored identity information data with the collected identity information data. This embodiment enables the cloud server or the AR glasses to grasp the user's identity information data and process the identity information data to obtain an identity information sequence.

[0077] When the AR glasses can access the cloud server, the inspector can directly view the image and video data uploaded to the cloud server by the drone by wearing the AR glasses remotely;

[0078] Through the cooperation between the rights management module and the AR glasses, the AR glasses can perform identity authentication, ensure the security of data viewing, and ensure that the image and video data of the inspection can be checked, further improving the quality of the inspection;

[0079] Optionally, the interaction unit includes a data storage device, and the data storage device is used to store the inspection positions collected by the interactor;

[0080] Optionally, the evaluation unit dynamically adjusts the inspection route and direction of the drone according to the following steps:

[0081] STEP 1: Use the real-time location coordinates of the drone as the starting coordinates and the specified inspection coordinates in the inspection location set as the end coordinates;

[0082] STEP 2: Calculate the distance between the starting point and the specified inspection coordinates and determine whether it is less than or equal to the safe inspection distance safety. For example, the safe inspection distance safety can be a distance that ensures the quality of communication between the drone and the wind turbine hub under safe operation conditions, or a distance that ensures the collection of valid wind turbine hub image data under safe operation conditions. The specific setting can be based on actual needs and is not limited here.

[0083] Optionally, in step STEP2, the distance between the starting point and the end point is calculated according to the following formula:

[0084]

[0085] Where (x1, y1) is the starting point coordinate, (x b ,y b ) is a designated inspection coordinate in the inspection coordinate set; the designated inspection coordinate can be the inspection position closest to the real-time position of the drone automatically selected by the activity range determination unit, or can be determined by the user or administrator according to needs. The determined inspection position can be sent to the cloud server via an AR device or other smart device, and then processed by the cloud server and sent to the drone. It can also be sent to the drone via an AR device or other smart device, without limitation.

[0086] The evaluation unit compares the distance between the starting point and the end point with the safety inspection distance, which is set by the operator / system or based on the distance between the drone and the wind turbine hub. Setting the safety inspection distance can also effectively prevent the time difference consumed during signal transmission from causing a safety accident caused by the drone's movement deviation.

[0087] If distance≤safety, the drone goes directly to the inspection location;

[0088] If distance>safety, multiple inspection points need to be divided;

[0089] STEP 3: Divide the distance between the starting point and the end point into several equal segments, with each segment length not exceeding the safe inspection distance, to obtain multiple drone inspection points;

[0090] STEP 4: The drone goes to the inspection points in turn for inspection. In the process of going to each inspection point, it is necessary to continuously update the real-time position coordinates of the drone and determine the inspection route and direction based on the real-time position coordinates and the coordinates of the next inspection point;

[0091] STEP 5: During the inspection process, it is necessary to monitor the status of the drone and environmental conditions in real time to ensure the safety and stability of the inspection process;

[0092] STEP 6: After the inspection, the drone returns to the base or designated location and uploads the inspection data and report;

[0093] Optionally, in step STEP3, the evaluation unit performs distance segmentation according to the following formula:

[0094]

[0095] In the formula, segment_num is the number of segments, distance is the distance between the starting point and the specified inspection coordinate, and safety is the safety inspection distance, whose value is set by the system. is the rounding symbol;

[0096] Optionally, after the drone inspects the coordinates of the inspection point calculated in step STEP3, it continues to fly in a clockwise direction toward the coordinates of other unselected inspection positions in the inspection position set to continue the inspection;

[0097] Optionally, in STEP 4, set the current coordinates of the drone to (x u ,y u ), the coordinates of the next inspection point are (x v ,y v ), then the direction angle θ of the inspection route is calculated by the vector (x u -x v ,y u -y v ) is obtained, that is:

[0098] θ=arctan(y v -y u ,x v -x u );

[0099] By coordinating the direction of the drone inspection route and the inspection points, the inspection position of the drone can be actively and dynamically adjusted according to the real-time position of the drone, so as to improve the safety of the entire drone inspection process and prevent the inspection process from causing new damage to the wind turbine hub.

[0100] Example 2:

[0101] This embodiment should be understood to include all the features of any of the above embodiments and to be further improved on the basis of the above embodiments. Figure 1 、 Figure 2 、 Figure 3 、 Figure 4 、 Figure 5 As shown, the wind turbine hub intelligent inspection system further includes an early warning module, which is used to analyze the image and video data collected by the collection module and trigger an early warning according to the analysis result, so as to realize active early warning of defects of the wind turbine hub;

[0102] The early warning module includes an analysis unit and an early warning unit. The analysis unit analyzes the image and video data collected by the collection module to form an analysis result. The early warning unit triggers an early warning of the wind turbine hub defect according to the analysis result.

[0103] The analysis unit analyzes the wind turbine hub according to the following steps:

[0104] S1: Acquire image and video data acquired by the acquisition module;

[0105] S2: Processing the image and video data to convert the video data into a sequence of images, and preprocessing the images, wherein the preprocessing includes grayscale conversion, denoising, edge detection, edge extraction, and feature extraction to obtain a wind turbine hub area;

[0106] S3: extracting defects on the blades in the wind turbine hub area by image processing technology (using computer vision technology, such as Hough transform, morphological processing, binary image segmentation, etc., to detect the location and shape of the cracks) to obtain the number of cracks p, crack length length, and crack depth depth on the blades;

[0107] S4: Crack depth uses grayscale difference to calculate the crack depth. Common methods include: color space-based method, gradient-based method, texture-based method, etc.

[0108] In step S3, edge detection algorithms (such as the Canny algorithm) or morphological processing algorithms (such as opening and closing operations) in digital image processing are used to extract the edge of the crack curve and convert it into a series of coordinate points. For the calculation of the crack length, the length of each straight line can be added together. Assume that the curve is cut into n straight lines, and the length of each straight line is l1, l2, ..., l n , then the crack length is: length = l1 + l2 + ... + l n ; The length of each straight line can be obtained by calculating the Euclidean distance between two points;

[0109] The crack depth and crack length can also be obtained by other technical means of those skilled in the art. This is one approach provided in this embodiment. Of course, those skilled in the art can obtain a crack depth and crack length based on image processing technology for optimization or replacement, which will not be described in detail here.

[0110] S5: Based on step S4, calculate the imperfection index:

[0111]

[0112] In the formula, defect u is the defect value of the fan blade of the u-th wind turbine hub, u is the fan blade of the u-th wind turbine hub, R is the total number of fan blades of the wind turbine hub, length is the crack length, whose value is directly obtained from the result of computer image processing, depth is the crack depth, whose value is directly obtained from the result of computer image processing, η is the position factor, and satisfies:

[0113] η=cos(θ-α);

[0114] Where θ is the angle between the crack direction and the set reference direction, and its value is determined according to the actual situation of the crack and the set reference direction. α is a constant representing the reference direction, and its value is set according to the system.

[0115] μ is the direction factor, satisfying:

[0116]

[0117] Wherein, λ is the angle between the crack direction and the direction of the maximum principal stress of the blade of the wind turbine hub, wherein the direction of the maximum principal stress of the blade of the wind turbine hub is the direction perpendicular to the blade axis. The specific value is directly obtained according to the result of image processing. τ is a constant used to control the attenuation rate of the directional factor. According to the empirical method, the value is determined. This embodiment provides a value range of [0.1, 0.23]. The value of τ should be adjusted according to the actual situation. If the value of τ is too small, the directional factor will be too sensitive, which may lead to misjudgment; if the value of τ is too large, the directional factor will be too slow, which may lead to missed detection. In actual applications, it is necessary to conduct experiments and adjustments according to the specific situation to find the most suitable τ value. Therefore, it is not described in detail in this embodiment.

[0118] If the defect index Imperfection exceeds the set monitoring threshold monitor, the early warning unit is triggered to issue an early warning and prompt the inspector to replace the wind turbine hub;

[0119] If the defect index Imperfection is less than the set monitoring threshold monitor, the early warning unit is triggered to issue an early warning and prompt the inspector to perform maintenance or repair on the wind turbine hub;

[0120] The monitoring threshold value monitor is set by the system, which is a technical means well known to those skilled in the art. Those skilled in the art can refer to relevant technical manuals to learn about the technology, so it will not be described in detail in this embodiment.

[0121] In this embodiment, the early warning unit may trigger an early warning to prompt the inspector through sound, indicator light or other tangible means, so that the inspector can grasp the early warning information of the wind turbine hub;

[0122] Through the cooperation between the analysis unit and the early warning unit, defects of the wind turbine hub can be grasped and early warnings can be triggered to inspectors in a timely manner, thereby improving the intelligence level and interactive comfort of the entire system.

[0123] The contents disclosed above are only preferred feasible embodiments of the present invention and do not limit the scope of protection of the present invention. Therefore, all equivalent technical changes made using the contents of the present invention description and drawings are included in the scope of protection of the present invention. In addition, the elements therein can be updated as technology develops.

Claims

1. An AR-based wind turbine hub intelligent inspection system, comprising a cloud server and a drone, characterized in that: The wind turbine hub intelligent inspection system also includes an AR device, a rights management module, a positioning module, a sensing module and a collection module. The cloud server is connected to the drone, the AR device, the rights management module, the positioning module, the sensing module and the collection module respectively. The sensing module and the collection module are arranged on the drone. The positioning module is used to locate the real-time positioning data of the drone and the inspection position of the wind turbine hub. The sensing module is used to sense the distance between the drone and the obstacle. The sensing module evaluates the inspection route of the drone based on the collected distance data, the real-time positioning data of the drone collected by the positioning module, and the inspection position of the wind turbine hub, so as to dynamically adjust the inspection route and direction of the drone. The acquisition module is used to collect image and video data of the wind turbine hub and synchronize the collected image and video data to the cloud server. The permission management module is used to grant the AR device an access permission code to access the cloud server, and the AR device views the image and video data stored in the cloud server according to the access permission code. The sensing module includes a sensing unit and an evaluation unit. The sensing unit obtains obstacle data around the drone. The evaluation unit evaluates the drone's inspection route based on the obstacle data collected by the sensing unit, the inspection position data collected by the positioning module, and the drone's real-time positioning data, so as to dynamically adjust the drone's inspection route and direction. The user wears the AR device and accesses the cloud server in real time to view the image and video data collected by the collection module; The evaluation unit dynamically adjusts the inspection route and direction of the drone according to the following steps: STEP 1: Use the real-time location coordinates of the drone as the starting coordinates and the specified inspection coordinates in the inspection location set as the end coordinates; STEP 2: Calculate the distance between the starting point and the specified inspection coordinates and determine whether it is less than or equal to the safety inspection distance. STEP 3: Divide the distance between the starting point and the end point into several equal segments, with each segment length not exceeding the safe inspection distance, to obtain multiple drone inspection points; STEP 4: The drone goes to the inspection points in turn for inspection. During the process of going to each inspection point, it is necessary to continuously update the real-time position coordinates of the drone and calculate the inspection route and direction based on the real-time position coordinates and the coordinates of the next inspection point; STEP 5: During the inspection process, it is necessary to monitor the status of the drone and environmental conditions in real time to ensure the safety and stability of the inspection process; STEP 6: After the inspection, the drone returns to the base or designated location and uploads the inspection data and report; The wind turbine hub intelligent inspection system further includes an early warning module, which includes an analysis unit and an early warning unit. The analysis unit analyzes the wind turbine hub according to the following steps: S1: Acquire image and video data acquired by the acquisition module; S2: Processing the image and video data to convert the video data into a sequence of images, and preprocessing the images, wherein the preprocessing includes grayscale conversion, denoising, edge detection, edge extraction, and feature extraction to obtain a wind turbine hub area; S3: extracting defects on the blades in the wind turbine hub region by image processing technology to obtain the number p of cracks on the blades, the length of the cracks, and the depth of the cracks; S4: Crack depth depth uses grayscale difference to calculate the crack depth; S5: Based on step S4, calculate the imperfection index: In the formula, defect u is the defect value of the fan blade of the u-th wind turbine hub, u is the fan blade of the u-th wind turbine hub, R is the total number of fan blades of the wind turbine hub, length is the crack length, whose value is directly obtained from the result of computer image processing, depth is the crack depth, whose value is directly obtained from the result of computer image processing, η is the position factor, and satisfies: η=cos(θ-α); Where θ is the angle between the crack direction and the set reference direction, and its value is determined according to the actual situation of the crack and the set reference direction. α is a constant representing the reference direction, and its value is set according to the system. μ is the direction factor, satisfying: Where λ is the angle between the crack direction and the direction of the maximum principal stress of the blade of the wind turbine hub. The direction of the maximum principal stress of the blade of the wind turbine hub is the direction perpendicular to the blade axis. The specific value is directly obtained based on the result of image processing. τ is a constant used to control the attenuation rate of the directional factor and is determined based on empirical methods. If the defect index Imperfection exceeds the set monitoring threshold monitor, the early warning unit is triggered to issue an early warning and prompt the inspector to replace the wind turbine hub.

2. The wind turbine hub intelligent inspection system based on AR equipment according to claim 1 is characterized in that: The AR device includes AR glasses and a networking unit, and after obtaining authorization from the rights management module, the networking unit establishes a data transmission link between the AR glasses and the cloud server; Before accessing the cloud server, the AR glasses need the access permission code granted by the permission management module to authorize the AR device to access the cloud server and establish a data transmission link between the AR glasses and the cloud server through the networking unit.

3. The wind turbine hub intelligent inspection system based on AR equipment according to claim 2 is characterized in that: The positioning module includes an interaction unit and a positioning unit. The interaction unit includes an interactor and a data storage device. The interactor is used to interact with the wind turbine hub to obtain the inspection position of the wind turbine hub. The data storage device is used to store the inspection position collected by the interactor. After locating the position of the UAV, the positioning unit transmits the real-time position of the UAV and the inspection position data of the wind turbine hub to the evaluation unit.

4. The wind turbine hub intelligent inspection system based on AR equipment according to claim 3 is characterized in that: In step STEP2, the distance between the starting point and the end point is calculated according to the following formula: Where (x1, y1) is the starting point coordinate, (x b ,y b ) is the specified inspection coordinate in the inspection coordinate set; The evaluation unit compares the distance between the starting point and the end point with the safety inspection distance safety; If distance≤safety, the drone goes directly to the inspection location; If distance>safety, it needs to be divided into multiple inspection points; The safety inspection distance safety is set by the operator / system or according to the distance between the UAV and the wind turbine hub.

5. The wind turbine hub intelligent inspection system based on AR equipment according to claim 4 is characterized in that: In step STEP3, the evaluation unit performs distance segmentation according to the following formula: In the formula, segment_num is the number of segments, distance is the distance between the starting point and the specified inspection coordinate, and safety is the safety inspection distance, whose value is set by the system. The symbol for rounding up.

6. The wind turbine hub intelligent inspection system based on AR equipment according to claim 5 is characterized in that: In STEP4, let the current coordinates of the drone be (x u ,y u ), the coordinates of the next inspection point are (x v ,y v ), then the direction angle θ of the inspection route is calculated by the vector (x u -x v ,y u -y v ) is obtained, that is: θ=arctan(y v -and u ,x v -x u )。

Images