Intelligent defect identification system for overhead line of wind farm based on unmanned aerial vehicle autonomous inspection

Abstract

The present application relates to the technical field of defect identification system, and specifically relates to a wind farm overhead line defect intelligent identification system based on unmanned aerial vehicle autonomous inspection, which comprises an unmanned aerial vehicle control module, a data processing module, an image acquisition module, an image processing module, a defect identification module, a data storage module and a user interaction module; the data processing module obtains information about whether the unmanned aerial vehicle flight is safe, and transmits the information about whether the unmanned aerial vehicle flight is safe to the user interaction module; the user interaction module provides a visual interface, and sends a signal for starting or stopping the image acquisition module after the user inquires about the information about whether the unmanned aerial vehicle flight is safe; the image acquisition module implements shooting according to the starting or stopping signal; the image processing module pre-processes the collected images; and the defect identification module outputs the type and position of defects. The above ensures the safety of the unmanned aerial vehicle inspection process and improves the collection accuracy of the image acquisition module.

Description

Technical Field

[0001] This invention relates to the technical field of defect identification systems, and more specifically to an intelligent defect identification system for overhead lines in wind farms based on autonomous drone inspections. Background Technology

[0002] The intelligent defect identification system is a high-tech system integrating drone inspection, image recognition, data analysis, and intelligent decision-making. It is specifically designed for defect detection and maintenance of overhead lines (such as transmission lines, insulators, and fittings) within wind farms. This system aims to replace traditional manual inspections, improve inspection efficiency, reduce labor costs, and ensure accuracy and timeliness of detection even in complex environments.

[0003] The system generally consists of the following components: a drone platform, an intelligent identification module, a data processing and analysis module, a cloud platform, and a control platform. The drone platform is equipped with various sensors such as high-definition cameras, infrared imaging equipment, and lidar to collect images, temperature data, and 3D structural information. It has autonomous flight control capabilities and can automatically inspect overhead power lines in wind farm areas according to preset routes. It is also equipped with GPS and inertial navigation systems for precise positioning and route control. The intelligent identification module can analyze the images collected by the drone based on machine learning and deep learning algorithms (such as convolutional neural networks (CNN) and object detection algorithms) to identify overhead power lines. Defects, such as insulator aging, hardware corrosion, line wear, loosening, and foreign object entanglement, are identified. The data processing and analysis module is responsible for processing the data collected by the drone, including image enhancement, noise reduction, and data format conversion. Through data analysis and statistics, it generates inspection reports, listing the location, type, and severity of defects to help maintenance personnel develop repair plans. The cloud platform is used for centralized data processing and storage. The cloud uses big data and artificial intelligence technologies to analyze historical and current inspection data and predict potential future defects and faults. The control platform provides a graphical interface, allowing maintenance personnel to view inspection progress, analysis results, and defect information in real time.

[0004] Application document CN117291872A discloses a system and method for identifying defects in power line inspection using unmanned aerial vehicles (UAVs). The system includes a central control module, a data acquisition module, and a defect early warning module connected to the central control module. The defect early warning module provides early warnings for identified equipment defects via a smart terminal. The system is characterized by: the central control module identifying several power transmission devices on the power line to be inspected and matching the corresponding equipment defects; evaluating and sorting equipment defects based on historical data to obtain a defect catalog of several power transmission devices; sequentially extracting equipment defects from the defect catalog and setting a collection feature sequence for each defect; wherein the historical data includes historical inspection data and historical environmental data; and selecting several target defects corresponding to each power transmission device from the defect catalog, integrating the target defects with the corresponding collection feature sequence into a target feature sequence; controlling the data acquisition module to acquire image data based on the target feature sequence, and determining whether the power transmission device has a defect based on the image data; wherein the collection feature sequence includes the defect location, acquisition location, and image type.

[0005] Existing technologies lack safety monitoring of drone flight status, which affects the accuracy of image acquisition and consequently the precision of defect identification. Summary of the Invention

[0006] The purpose of this invention is to monitor the flight status of drones to improve the accuracy of image acquisition. In view of the above-mentioned shortcomings, an intelligent identification system for defects in overhead lines of wind farms based on drone autonomous inspection is proposed.

[0007] The present invention adopts the following technical solution:

[0008] This system is an intelligent defect identification system for overhead lines in wind farms based on drone autonomous inspection. The system includes a drone control module, a data processing module, an image acquisition module, a defect identification module, a data storage module, and a user interaction module. The drone control module sets the drone's inspection path, takeoff, and target area. The data processing module collects flight and environmental data during the inspection process, derives a safe flight factor based on the data, and transmits this information to the user interaction module. The user interaction module provides a visual interface; users can query the drone's flight safety information and then signal the start / stop of the image acquisition module. The image acquisition module takes pictures based on the start / stop signal. The image processing module preprocesses the acquired images. The defect identification module inputs the preprocessed images into a machine learning model for defect classification and identification, and outputs the defect type and location. The data storage module stores the defect type and location and transmits this information to the user interaction module.

[0009] Optionally, the data processing module includes an information storage submodule, an environmental detection submodule, a flight detection submodule, a control submodule, and a safety determination submodule. The information storage submodule stores the air pressure, speed, sea-level air pressure, molar mass of air, gravitational acceleration, gas constant, maximum and minimum flight altitude of the drone under ideal operating conditions, air density, drag coefficient, and windward area of ​​the drone under ideal operating conditions, and transmits this information to the control submodule. The environmental detection submodule detects and calculates the absolute ambient temperature, real-time wind speed, and drone wind direction angle for each detection, and transmits this information to the control submodule. The flight detection submodule detects and calculates the drone's airspeed (detected by an airspeed meter), real-time flight altitude, heading angle, and speed (detected by GPS), and transmits this information to the control submodule. The control submodule calculates the angle between the drone and the wind direction based on the drone's wind direction angle and heading angle, and calculates the drone's drag coefficient, air density, windward area, and windward area based on the drone's wind direction angle and wind direction angle. The system calculates air resistance based on the drone's speed. It then calculates the drone's real-time speed based on real-time wind speed, airspeed detected by the airspeed meter, the angle between the drone and the wind direction, and air resistance. The system calculates the total number of absolute temperature measurements based on the drone's real-time altitude, maximum altitude under ideal operating conditions, and minimum altitude under ideal operating conditions. Finally, it calculates the average absolute temperature based on the total number of measurements and the absolute temperature measured each time. The system calculates the air pressure at the drone's real-time altitude based on sea level pressure, the molar mass of air, gravitational acceleration, the drone's real-time altitude, the gas constant, and the average absolute temperature. Finally, it calculates the drone's safe flight factor based on the air pressure at the drone's real-time altitude, the air pressure under ideal operating conditions, the drone's real-time speed, and the speed under ideal operating conditions. This safe flight factor is then transmitted to the safety assessment submodule. The safety assessment submodule uses this safe flight factor to determine whether the drone's flight is safe and transmits this information to the user interaction module.

[0010] Optionally, the environmental detection submodule includes a temperature detection unit and an anemometer; the temperature detection unit is used to detect and obtain the absolute environmental temperature each time it is detected, and transmit it to the control submodule; the anemometer is used to detect and obtain the real-time wind speed and the wind direction angle of the UAV, and transmit it to the control submodule.

[0011] Optionally, the flight detection submodule includes an airspeed meter and a positioning unit; the airspeed meter is used to detect and obtain the airspeed of the UAV detected by the airspeed meter, and transmit it to the control submodule; the positioning unit is used to detect and obtain the real-time altitude of the UAV, the heading angle of the UAV, and the speed of the UAV detected by GPS, and transmit them to the control submodule.

[0012] Optionally, when the control submodule calculates the safe flight factor of the UAV, it satisfies the following formula:

[0013]

[0014] Wherein, Hth is the safe flight factor of the drone, AP is the air pressure index of the drone at real-time altitude, ap is the air pressure corresponding to the drone under ideal working conditions, VEV is the real-time speed index of the drone, and vev is the speed corresponding to the drone under ideal working conditions; when the safe flight factor of the drone is greater than or equal to the selection threshold of the safe flight factor of the drone, it indicates that the drone is flying unsafely; when the safe flight factor of the drone is less than the selection threshold of the safe flight factor of the drone, it indicates that the drone is flying safely.

[0015] The beneficial effects achieved by this invention are:

[0016] 1. Real-time monitoring of UAV flight status, calculation of safe flight factors based on flight data and environmental data, ensuring the safety of UAV inspection process, and improving the acquisition accuracy of image acquisition module;

[0017] 2. The user interaction module provides users with a visual interface, allowing them to view the drone's flight safety information and inspection defect information in real time, and control the start or stop of the image acquisition module as needed, thus improving the system's interactivity and feedback capabilities.

[0018] 3. The data storage module saves the types and locations of defects detected during the inspection process, which facilitates subsequent data analysis and trend prediction.

[0019] To further understand the features and technical content of the present invention, please refer to the following detailed description and drawings of the present invention. However, the drawings provided are for reference and illustration only and are not intended to limit the present invention. Attached Figure Description

[0020] Figure 1 This is a schematic diagram of the overall structure of the present invention;

[0021] Figure 2 This is a schematic diagram of the data processing module in this invention;

[0022] Figure 3This is a schematic diagram of the environmental detection submodule in this invention;

[0023] Figure 4 This is a schematic diagram of the flight detection submodule in this invention;

[0024] Figure 5 This is a relationship diagram from Embodiment 1 of the present invention;

[0025] Figure 6 This is a schematic diagram of the overall structure of Embodiment 2 of the present invention;

[0026] Figure 7 This is a schematic diagram of the image quality analysis module in Embodiment 2 of the present invention;

[0027] Figure 8 This is a relationship diagram in Embodiment 2 of the present invention. Detailed Implementation

[0028] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can understand the advantages and effects of the present invention from the content disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and various details in this specification can also be modified and changed based on different viewpoints and applications without departing from the spirit of the present invention. Furthermore, the accompanying drawings of the present invention are for simple illustrative purposes only and are not depictions of actual dimensions; this is stated in advance. The following embodiments will further describe 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.

[0029] Example 1: This example provides an intelligent defect identification system for overhead lines in wind farms based on autonomous drone inspection, combined with... Figures 1 to 5 As shown.

[0030] This system is an intelligent defect identification system for overhead lines in wind farms based on drone autonomous inspection. The system includes a drone control module, a data processing module, an image acquisition module, a defect identification module, a data storage module, and a user interaction module. The drone control module sets the drone's inspection path, takeoff, and target area. The data processing module collects flight and environmental data during the inspection process, derives a safe flight factor based on the data, and transmits this information to the user interaction module. The user interaction module provides a visual interface; users can query the drone's flight safety information and then signal the start / stop of the image acquisition module. The image acquisition module takes pictures based on the start / stop signal. The image processing module preprocesses the acquired images. The defect identification module inputs the preprocessed images into a machine learning model for defect classification and identification, and outputs the defect type and location. The data storage module stores the defect type and location and transmits this information to the user interaction module.

[0031] Optionally, the data processing module includes an information storage submodule, an environmental detection submodule, a flight detection submodule, a control submodule, and a safety determination submodule. The information storage submodule stores the air pressure, speed, sea-level air pressure, molar mass of air, gravitational acceleration, gas constant, maximum and minimum flight altitude of the drone under ideal operating conditions, air density, drag coefficient, and windward area of ​​the drone under ideal operating conditions, and transmits this information to the control submodule. The environmental detection submodule detects and calculates the absolute ambient temperature, real-time wind speed, and drone wind direction angle for each detection, and transmits this information to the control submodule. The flight detection submodule detects and calculates the drone's airspeed (detected by an airspeed meter), real-time flight altitude, heading angle, and speed (detected by GPS), and transmits this information to the control submodule. The control submodule calculates the angle between the drone and the wind direction based on the drone's wind direction angle and heading angle, and calculates the drone's drag coefficient, air density, windward area, and windward area based on the drone's wind direction angle and wind direction angle. The system calculates air resistance based on the drone's speed. It then calculates the drone's real-time speed based on real-time wind speed, airspeed detected by the airspeed meter, the angle between the drone and the wind direction, and air resistance. The system calculates the total number of absolute temperature measurements based on the drone's real-time altitude, maximum altitude under ideal operating conditions, and minimum altitude under ideal operating conditions. Finally, it calculates the average absolute temperature based on the total number of measurements and the absolute temperature measured each time. The system calculates the air pressure at the drone's real-time altitude based on sea level pressure, the molar mass of air, gravitational acceleration, the drone's real-time altitude, the gas constant, and the average absolute temperature. Finally, it calculates the drone's safe flight factor based on the air pressure at the drone's real-time altitude, the air pressure under ideal operating conditions, the drone's real-time speed, and the speed under ideal operating conditions. This safe flight factor is then transmitted to the safety assessment submodule. The safety assessment submodule uses this safe flight factor to determine whether the drone's flight is safe and transmits this information to the user interaction module.

[0032] Specifically, the safety judgment submodule refers to the following principles when making judgments: when the drone's safe flight factor is greater than or equal to the selection threshold of the drone's safe flight factor, it indicates that the drone's flight is unsafe; when the drone's safe flight factor is less than the selection threshold of the drone's safe flight factor, it indicates that the drone's flight is safe. The selection threshold of the drone's safe flight factor is set by those skilled in the art. Safe flight conditions ensure that the drone can effectively perform the inspection task of the wind farm's overhead lines, identify defects in a timely and accurate manner, thereby improving the safety and efficiency of maintenance. Therefore, closely integrating the calculation of the drone's safe flight factor with the inspection system is crucial for achieving efficient and intelligent drone inspections. Based on the information of unsafe drone flight, the number of defect detections can be adjusted or detections can be temporarily suspended. The specific subsequent operation steps are set by those skilled in the art.

[0033] Optionally, the environmental detection submodule includes a temperature detection unit and an anemometer; the temperature detection unit is used to detect and obtain the absolute environmental temperature each time it is detected, and transmit it to the control submodule; the anemometer is used to detect and obtain the real-time wind speed and the wind direction angle of the UAV, and transmit it to the control submodule.

[0034] Optionally, the flight detection submodule includes an airspeed meter and a positioning unit; the airspeed meter is used to detect and obtain the airspeed of the UAV detected by the airspeed meter, and transmit it to the control submodule; the positioning unit is used to detect and obtain the real-time altitude of the UAV, the heading angle of the UAV, and the speed of the UAV detected by GPS, and transmit them to the control submodule.

[0035] Optionally, when the control submodule calculates the safe flight factor of the UAV, it satisfies the following formula:

[0036]

[0037] Where Hth is the safe flight factor of the drone, AP is the air pressure index of the drone at real-time altitude, ap is the air pressure corresponding to the drone under ideal working conditions, VEV is the real-time speed index of the drone, and vev is the speed corresponding to the drone under ideal working conditions.

[0038] Optionally, the control submodule may perform calculations that satisfy the following formula:

[0039]

[0040] VEV = V air -V wind ×cos(θ)-F;

[0041]

[0042] Where qy is the sea level air pressure, m is the molar mass of air, g is the gravitational acceleration, h is the real-time altitude of the UAV, r is the gas constant, and Δtemp is the average absolute temperature of the environment.

[0043] temp a Let A be the absolute ambient temperature detected in the a-th test, and A be the total number of absolute ambient temperature tests.

[0044] h min h is the maximum altitude at which the drone flies under ideal operating conditions. max The minimum altitude at which a drone can fly under ideal operating conditions;

[0045] V air V is the airspeed of the drone detected by the airspeed meter. wind θ represents the real-time wind speed, θ represents the angle between the drone and the wind direction, and F represents the air resistance index.

[0046] ρ is the air density, zl is the drag coefficient of the drone, s is the frontal area of ​​the drone, and v gps The speed of the drone detected by GPS.

[0047] Referring to the graph showing the relationship between the drone's real-time altitude air pressure index / real-time speed index and the drone's safe flight factor, the lighter the color (closer to yellow), the higher the safe flight factor value, and the darker the color (closer to blue), the lower the safe flight factor value. The graph shows that the influence of the drone's real-time altitude air pressure index / real-time speed index on the drone's safe flight factor is not strictly proportional, but exhibits some fluctuation. This fluctuation may be due to several reasons: because of the formula... It is not a direct linear relationship. The absolute value and fractional operations in the formula will introduce a certain nonlinear effect. Theoretically, the air pressure index of the drone at real-time altitude / the real-time speed index of the drone has a positive influence on the safe flight factor of the drone. However, due to the influence of nonlinear formula, ideal value setting and multiplication effect, the safe flight factor of the drone in the figure fluctuates. This fluctuation does not completely violate the direct proportional trend, but is affected by the formula structure and parameter relationship.

[0048] When performing calculations in the control submodule, refer to the following code:

[0049]

[0050]

[0051]

[0052] Specifically, the "ideal operating state" mentioned in "air pressure corresponding to the drone under ideal operating conditions" and "speed corresponding to the drone under ideal operating conditions" can be understood as the operating state of the drone under the optimal flight conditions designed or expected. Under this state, the drone's built-in sensors are less affected by interference and can perform its tasks efficiently and safely, such as inspection, photography, or other operations. The air pressure and speed corresponding to the drone under ideal operating conditions can be obtained through querying; the unit of air pressure corresponding to the drone under ideal operating conditions is hectopascals; the unit of speed corresponding to the drone under ideal operating conditions is meters per second.

[0053] The value of sea level air pressure is 1013.25 hPa; the unit of molar mass of air is kilograms per mole; the value of gravitational acceleration is 9.81 meters per second squared; the unit of real-time altitude of the UAV is meters; the value of gas constant is 287 J / (kg·kg·K); and the unit of average absolute temperature of the environment is Kelvin.

[0054] The unit of each measured ambient absolute temperature is Kelvin.

[0055] The units for the maximum and minimum flight altitudes of a drone under ideal operating conditions are both meters. These altitudes can be obtained through a query.

[0056] The airspeed and real-time wind speed of the drone, as measured by the airspeed meter, are both in meters per second. The angle between the drone and the wind direction can be understood as the angle between the drone's flight direction and the wind speed. For example, when the wind is a headwind (opposite to the drone's direction of travel), the angle between the drone and the wind direction is 0°. When the wind is a tailwind (in the same direction as the drone's direction of travel), the angle between the drone and the wind direction is 180°. The air resistance index can be understood as the effect of air resistance on the drone's flight.

[0057] The drag coefficient of a drone can be measured through wind tunnel testing. For example, a scaled-down model of the drone can be created, a wind tunnel can be selected, the wind speed can be adjusted, multiple wind speed points can be set for testing, and the data can be collected to calculate the corresponding value. The windward area of ​​a drone is measured in square meters. Since drones have complex shapes, they can be simulated using computer-aided design (CAD) software and computational fluid dynamics (CFD) software. A 3D model of the drone can be built using CAD software (such as SolidWorks, AutoCAD, etc.). In CFD software, the CAD model can be imported and the boundary conditions of the fluid, such as flow velocity and direction, can be set, and the model can be meshed for numerical calculation. The simulation can be run in CFD software to obtain the airflow distribution and pressure field. The software usually provides functions to calculate the windward area or directly extract data from the projected area of ​​the model. The speed of a drone detected by GPS is measured in meters per second.

[0058] The above units are just examples. Those skilled in the art can set different units according to actual needs when implementing this solution.

[0059] This embodiment solves the problem of poor image acquisition accuracy in traditional recognition systems. Through the cooperation of the UAV control module, data processing module, image acquisition module, defect recognition module, data storage module, and user interaction module, the UAV's flight status is monitored in real time. Based on flight data and environmental data, a safe flight factor is calculated to ensure the safety of the UAV inspection process and improve the acquisition accuracy of the image acquisition module.

[0060] Example 2: This example includes all the content of Example 1, providing an intelligent defect identification system for overhead lines in wind farms based on UAV autonomous inspection, combined with... Figures 6 to 8 As shown.

[0061] When a user queries information about drone flight safety, the user sends a signal to activate the image acquisition module. At this time, the image acquisition module starts working, and the subsequent image processing module and defect recognition module also work synchronously to realize the defect recognition operation.

[0062] This wind farm overhead line defect intelligent identification system, based on UAV autonomous inspection, also includes an image quality analysis module. This module analyzes images and derives information on brightness, color, effective feature points, and edge intensity. Based on these parameters, it calculates a comprehensive image quality evaluation index and determines whether the image quality is acceptable. This information is then transmitted to the user interaction module. The user interaction module allows users to query the image quality status through a visual interface. Upon querying the image quality status, the user sends signals to start and stop the image processing and defect identification modules. If the image quality is acceptable, the image processing and defect identification modules continue operating; otherwise, they are suspended.

[0063] Optionally, the image quality analysis module includes an ideal value setting submodule, an image parameter detection submodule, a data analysis submodule, and an image quality judgment submodule. The ideal value setting submodule is used to set the ideal average value of image brightness and transmit it to the data analysis submodule. The image parameter detection submodule is used to detect and obtain the image's edge intensity, the total number of effective feature points in the image, the standard deviation of image brightness, the measured average value of image brightness, the maximum color component in the image, the minimum color component in the image, the maximum value of image brightness, and the minimum value of image brightness, and transmit them to the data analysis submodule. The data analysis submodule calculates the image contrast based on the maximum and minimum values ​​of image brightness, and derives a comprehensive image quality evaluation index based on the image's edge intensity, the total number of effective feature points in the image, the standard deviation of image brightness, the measured average value of image brightness, the ideal average value of image brightness, the image contrast, the maximum color component in the image, and the minimum color component in the image, and transmits the comprehensive image quality evaluation index to the image quality judgment submodule. The image quality judgment submodule determines whether the image quality is qualified based on the comprehensive image quality evaluation index and transmits the information on whether the image quality is qualified to the user interaction module.

[0064] Specifically, the image quality assessment submodule refers to the following principles when making judgments: when the comprehensive image quality evaluation index is greater than or equal to the selection threshold of the comprehensive image quality evaluation index, the image quality is considered qualified; when the comprehensive image quality evaluation index is less than the selection threshold of the comprehensive image quality evaluation index, the image quality is considered unqualified. The selection threshold of the comprehensive image quality evaluation index is set by those skilled in the art. Judging whether the image quality is qualified or unqualified directly affects the subsequent defect recognition effect and recognition accuracy. The role of image quality assessment includes: ensuring data accuracy: high-quality images can more clearly display the defect features on the line (such as damage, corrosion, cracks, etc.), thereby improving the accuracy of the recognition algorithm; avoiding misjudgment and missed judgment: low-quality images may cause the algorithm to misjudge or miss defects, reducing the reliability of the system; improving system efficiency: by assessing image quality, the system can re-acquire images in a timely manner when unqualified images are acquired, avoiding invalid data in subsequent analysis and processing, and improving overall efficiency.

[0065] Optionally, when calculating the comprehensive image quality evaluation index, the data analysis submodule shall satisfy the following formula:

[0066]

[0067] T = I max -I min .

[0068] Where Q is the comprehensive image quality evaluation index, E is the edge intensity of the image, N is the total number of effective feature points in the image, σ is the standard deviation of the image brightness, and μ s The measured average value of the image brightness, μ r Let T be the ideal average value of the image brightness, and let c be the image contrast. max c is the largest color component in the image. min The smallest color component in the image;

[0069] I max I represents the maximum brightness in the image. min This represents the minimum brightness value in the image.

[0070] Referring to the graph showing the relationship between the total number of effective feature points in a reference image and the overall image quality evaluation index, it can be seen that the overall image quality evaluation index increases with the total number of effective feature points. This indicates that increasing the number of effective feature points in an image improves the overall image quality evaluation index.

[0071] When performing calculations in the data analysis submodule, refer to the following code:

[0072]

[0073]

[0074] Specifically, the ideal average value of image brightness is set by those skilled in the art; the calculation of the "maximum color component in the image" and the "minimum brightness in the image" can measure the intensity and purity of color, and color saturation can assess the quality of the image; the total number of effective feature points in the image can reflect the richness of information in the image. The larger the total number of effective feature points in the image, the more details and identifiable elements the image contains, thus improving the image quality; the measured average value of image brightness can reflect the overall brightness level of the image. When the measured average value of image brightness is too high, it will cause the image to be overexposed. When the measured average value of image brightness is too low, it will cause the image to be less recognizable; the standard deviation of image brightness can indicate the degree to which the brightness deviates from the mean. The larger the standard deviation value of image brightness, the more contrast there is in the image, and the more obvious the brightness changes, such as obvious shadows and bright areas. Such images often have high contrast, rich details, and can present more layers; regarding image contrast, high contrast indicates that the brightness difference of the image is significant, and it can clearly distinguish objects and backgrounds, making the image more vivid.

[0075] The above units are just examples. Those skilled in the art can set different units according to actual needs when implementing this solution.

[0076] This embodiment solves the problem of traditional recognition systems having relatively simple analysis methods. By analyzing the brightness, color, feature points, and edge intensity of images, the system can filter out low-quality images, ensuring that the images entering the defect recognition module are clear and have complete details.

[0077] The content disclosed above is only a preferred and feasible embodiment of the present invention, and is not intended to limit the scope of protection of the present invention. Therefore, all equivalent technical changes made based on the content of the present invention specification and drawings are included within the scope of protection of the present invention. Furthermore, the elements therein can be updated as technology develops.

Claims

1. A wind farm overhead line defect intelligent identification system based on UAV autonomous inspection, characterized in that, The system includes a drone control module, a data processing module, an image acquisition module, an image processing module, a defect identification module, a data storage module, and a user interaction module; The drone control module is used to set the drone inspection path, takeoff, and target area; The data processing module is used to collect flight data and environmental data of the UAV during the inspection process, derive the safe flight factor of the UAV based on the flight data and environmental data, obtain information on whether the UAV is safe to fly based on the safe flight factor, and transmit the information on whether the UAV is safe to fly to the user interaction module. The user interaction module provides a visual interface, and after the user queries information on whether the drone flight is safe, it sends a signal to start and stop the image acquisition module. The image acquisition module takes pictures according to the start / stop signal; The image processing module preprocesses the acquired images; The defect identification module inputs the preprocessed image into the machine learning model for defect classification and identification, and outputs the type and location of the defect; The data storage module is used to store the type and location of defects and transmit the type and location of defects to the user interaction module; The data processing module includes an information storage submodule, an environmental detection submodule, a flight detection submodule, a control submodule, and a safety determination submodule. The information storage submodule is used to store the air pressure, speed, sea level air pressure, molar mass of air, gravitational acceleration, gas constant, maximum flight altitude, minimum flight altitude, air density, drag coefficient, and frontal area of ​​the UAV under ideal operating conditions, and transmit them to the control submodule. The environmental detection submodule is used to detect and obtain the absolute ambient temperature, real-time wind speed and UAV wind direction angle for each detection, and transmit them to the control submodule. The flight detection submodule is used to detect and obtain the UAV airspeed detected by the airspeed meter, the UAV's real-time flight altitude, the UAV's heading angle, and the UAV's speed detected by the GPS, and transmit them to the control submodule. The control submodule calculates the angle between the UAV and the wind direction based on the UAV's wind direction angle and heading angle; it calculates the air resistance index based on the UAV's drag coefficient, air density, frontal area, and speed detected by GPS; it calculates the UAV's real-time speed index based on real-time wind speed, airspeed detected by airspeed meter, the angle between the UAV and the wind direction, and the air resistance index; it calculates the total number of environmental absolute temperature measurements based on the UAV's real-time flight altitude, maximum flight altitude under ideal operating conditions, and minimum flight altitude under ideal operating conditions; it calculates the average environmental absolute temperature based on the total number of environmental absolute temperature measurements and the environmental absolute temperature measured each time; it calculates the air pressure index at the UAV's real-time altitude based on sea level air pressure, molar mass of air, gravitational acceleration, UAV's real-time flight altitude, gas constant, and the average environmental absolute temperature; and it calculates the UAV's safe flight factor based on the air pressure index at the UAV's real-time altitude, the air pressure corresponding to the UAV under ideal operating conditions, the UAV's real-time speed index, and the speed corresponding to the UAV under ideal operating conditions, and transmits the UAV's safe flight factor to the safety judgment submodule. The safety determination submodule determines whether the drone is safe to fly based on the drone's safe flight factors, and transmits this information to the user interaction module.

2. The intelligent identification system for wind farm overhead line defects based on UAV autonomous inspection as described in claim 1, characterized in that, The environmental monitoring submodule includes a temperature detection unit and an anemometer; The temperature detection unit is used to detect and obtain the absolute ambient temperature each time it is detected, and transmit it to the control submodule; The anemometer is used to detect and obtain real-time wind speed and the wind direction angle of the UAV, and transmit them to the control submodule.

3. The intelligent identification system for wind farm overhead line defects based on UAV autonomous inspection as described in claim 2, characterized in that, The flight detection submodule includes an airspeed meter and a positioning unit; The airspeed meter is used to detect and obtain the airspeed of the UAV detected by the airspeed meter, and transmit it to the control submodule. The positioning unit is used to detect and obtain the real-time altitude of the UAV, the heading angle of the UAV, and the speed of the UAV detected by GPS, and transmit them to the control submodule.

4. The intelligent identification system for wind farm overhead line defects based on UAV autonomous inspection as described in claim 3, characterized in that, When the control submodule calculates the safe flight factor of the UAV, it satisfies the following formula: ； in, For the safe flight factors of drones, This refers to the air pressure readings at the drone's real-time altitude. This represents the air pressure corresponding to the drone's ideal operating conditions. This refers to the real-time speed indicator of the drone. The speed corresponds to the drone under ideal operating conditions. When the drone's safe flight factor is greater than or equal to the selection threshold of the drone's safe flight factor, it indicates that the drone is flying unsafely. When the drone's safe flight factor is less than the selection threshold of the drone's safe flight factor, it indicates that the drone is flying safely.

Images