An unmanned aerial vehicle inspection-based fan blade infrared monitoring system and method

Abstract

The application discloses a kind of fan blade infrared monitoring system and method based on unmanned aerial vehicle inspection, it is related to image recognition technical field, solve the problem that the infrared image processing mode of fan blade in prior art is not enough to adapt to the temperature change of blade caused by varied environment.The infrared thermal imaging of fan blade is obtained by the infrared camera carried by unmanned aerial vehicle, the highest temperature and the lowest temperature of each infrared thermal imaging are calculated by temperature inversion, and then the temperature difference of fan blade is obtained, in addition, the infrared thermal imaging of each fan blade number in the same area is also obtained, and the highest temperature and the lowest temperature of each infrared thermal imaging are calculated, the temperature analysis set is constructed and the overall standard deviation is calculated to judge the dispersion degree of temperature in the area, and finally the health evaluation coefficient is established based on temperature difference and dispersion condition and other factors, to provide quantitative data reference for managers and decision makers, to facilitate subsequent management and decision-making work.

Description

Technical Field

[0001] This invention relates to the field of image recognition technology, and in particular to an infrared monitoring system and method for wind turbine blades based on unmanned aerial vehicle (UAV) inspection. Background Technology

[0002] Drones play a crucial role in the inspection of wind turbine blades. Because wind turbine blades are frequently exposed to extreme weather and corrosive environments, they are the most vulnerable parts of a wind power system. Therefore, regular inspection and maintenance of the blades are essential for the stable operation of a wind farm. The use of drones greatly improves the efficiency of blade inspection and reduces the risks associated with personnel working at high altitudes. Equipped with high-resolution cameras and advanced sensors, they can conduct comprehensive inspections of the blades from different distances and perspectives, thereby improving the accuracy and automation of the inspection work.

[0003] Currently, the processing of infrared images of wind turbine blades acquired by drones primarily focuses on determining whether the internal temperature of the drone is abnormal. For example, identifying the hottest areas and checking if the highest temperature exceeds a set threshold to determine if there is abnormal temperature rise in the wind turbine blades. While this method can identify some abnormal temperature rises, it does not analyze the temperature uniformity of the wind turbine blades themselves, nor does it consider the temperature of the blades in relation to the geographical environment. These are all important factors affecting the temperature of the wind turbine blades, thus impacting the accuracy of the judgment. In other words, current methods for processing infrared images of wind turbine blades do not analyze the temperature of the environment or the overall temperature of the wind turbine blades, making them insufficient to address the diverse temperature variations caused by different environments.

[0004] Therefore, there is a need for an infrared monitoring system and method for wind turbine blades based on drone inspection. Summary of the Invention

[0005] To address the problem that existing infrared image processing methods for wind turbine blades are insufficient to adapt to the diverse temperature variations caused by varying environments, this invention provides a wind turbine blade infrared monitoring system and method based on UAV inspection. This system can acquire infrared thermal images of wind turbine blades using UAVs, and then obtain the temperature differences between the blades based on these images. Furthermore, it performs a comprehensive analysis of different wind turbine blades within the same area, obtaining the standard deviation of blade temperatures within that area, thus revealing the temperature dispersion. Finally, based on factors such as temperature differences and dispersion, a health evaluation coefficient is established, providing quantitative data references for managers and decision-makers, facilitating subsequent management and decision-making. The specific technical solution is as follows:

[0006] An infrared monitoring system for wind turbine blades based on drone inspection includes:

[0007] The image acquisition unit includes a drone and an infrared camera and an image storage module mounted on the drone. The infrared camera is used to acquire several infrared thermal images of the wind turbine blades and store them in the image storage module.

[0008] An image recognition unit, connected to the image acquisition unit, includes a temperature difference recognition module. This module is used to identify temperature differences in infrared thermal imaging based on temperature inversion. Specifically, the temperature recognition module acquires the temperature difference as follows:

[0009] Acquire infrared thermal images from the image storage module;

[0010] Obtain the mapping table or conversion formula between grayscale values ​​and temperature provided by the infrared camera manufacturer;

[0011] Based on a conversion formula or mapping table, obtain a set of temperatures from several images of the same wind turbine blade number at the same timestamp, and find the highest temperature by finding the maximum value. T max =max( T Similarly, the lowest temperature is obtained by finding the minimum value. T min =min( T );

[0012] The corresponding timestamp-fan blade number-temperature difference is obtained, where the formula for calculating the temperature difference is as follows:

[0013]

[0014] in, For temperature difference, The highest temperature, The lowest temperature;

[0015] The image recognition unit also includes a uniformity recognition module. This module acquires several infrared thermal images of each wind turbine blade number within the same area, then uniformly calculates the highest and lowest temperatures for each image, constructs a temperature analysis set, and calculates the overall standard deviation based on the temperature analysis set to assess the degree of temperature dispersion within the area. The uniformity recognition module performs the following operations:

[0016] Divide the area into different regions based on geographical location, and obtain all infrared thermal imaging data within the same region;

[0017] Obtain the mapping table or conversion formula between grayscale values ​​and temperature provided by the infrared camera manufacturer;

[0018] Based on conversion formulas or mapping tables, obtain the blade number of the same wind turbine under the same timestamp. iThe highest temperature is obtained by finding the maximum value from a set of temperatures in several images. T max ( i )=max( T Similarly, the lowest temperature is obtained by finding the minimum value. T min ( i )=min( T );

[0019] The population standard deviation is calculated using the following formula:

[0020]

[0021] in, Wind turbine blade number i The set of the highest and lowest temperatures, i.e. N is the total number of wind turbine blade numbers in the area. m It is the overall average, that is, the average of the highest and lowest temperatures of all wind turbine blades in the region;

[0022] The evaluation and management unit is used to evaluate the health coefficient of the wind turbine blades, and the calculation formula is as follows:

[0023]

[0024] In the formula, Z represents the health coefficient. The temperature difference of the wind turbine blades at the current moment. The standard deviation of the region where the leaf is located. Year For service life, N t To set the number of failures within a set period, These are the weighting coefficients for temperature difference, standard deviation, service life, and number of failures, respectively.

[0025] Preferably, the image recognition unit further includes an alarm module, which has a temperature difference threshold. i 温度差 Alarm threshold for sum and standard deviation i 标准差 By acquiring infrared thermal images of the motor blades in real time, the temperature difference between the motor blades can be obtained in real time, and compared with a threshold temperature difference. i 温度差 The system performs a comparison and issues a first alarm signal when the temperature difference between the motor blades exceeds a set threshold; and an alarm signal is issued when the temperature standard deviation within the area exceeds a temperature difference threshold. i 温度差 If this occurs, a second alarm signal will be issued.

[0026] Preferably, it also includes a terminal feedback unit, which is used to receive the first alarm signal and the second alarm signal, and go to the site to troubleshoot and handle the fault based on the different alarm signals, and report the troubleshooting status and response status to the evaluation and management unit; the troubleshooting status is to confirm that the alarm signal is correct or to confirm that the alarm signal is incorrect, and the response status is to indicate that the fault has been handled or the fault has not been handled.

[0027] An infrared monitoring method for wind turbine blades based on drone inspection includes the following steps:

[0028] The drone is equipped with an infrared camera to acquire several infrared thermal images of the wind turbine blades and store them in the image storage module. The data storage method is: timestamp-geographical location-wind turbine blade number-several images of the wind turbine blade under the current number of the corresponding timestamp. Each infrared thermal image contains a corresponding timestamp label and a wind turbine blade number label.

[0029] By temperature inversion, the highest and lowest temperatures of each infrared thermal image are calculated, and then the highest and lowest temperatures under the corresponding timestamp and wind turbine blade number are obtained, finally obtaining the temperature difference of wind turbine blade number i under the corresponding timestamp.

[0030] Several infrared thermal images of each wind turbine blade number within the same area are obtained, and then the highest and lowest temperatures of each infrared thermal image are calculated in a unified manner to construct a temperature analysis set. Based on the temperature analysis set, the overall standard deviation is calculated to evaluate the degree of temperature dispersion within the area.

[0031] Set the threshold for temperature difference i 温度差 Alarm threshold for sum and standard deviation i 标准差 By acquiring infrared thermal images of the motor blades in real time, the temperature difference between the motor blades can be obtained in real time, and compared with a threshold temperature difference. i 温度差 The system performs a comparison and issues a first alarm signal when the temperature difference between the motor blades exceeds a set threshold; and an alarm signal is issued when the temperature standard deviation within the area exceeds a temperature difference threshold. i 温度差 If this occurs, a second alarm signal will be issued;

[0032] Receive the first alarm signal and the second alarm signal, and go to the site to troubleshoot and handle the fault based on the different alarm signals. Then, report the troubleshooting status and response status to the evaluation and management unit. The troubleshooting status is to confirm that the alarm signal is correct or to confirm that the alarm signal is wrong. The response status is to indicate that the fault has been handled or the fault has not been handled.

[0033] The health coefficient of the wind turbine blades is calculated using the following formula:

[0034]

[0035] In the formula, Z For health index, The temperature difference of the wind turbine blades at the current moment. The standard deviation of the region where the leaf is located. Year For service life, N t To set the number of failures within a set period, These are the weighting coefficients for temperature difference, standard deviation, service life, and number of failures, respectively.

[0036] A computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the above-described UAV-based wind turbine blade infrared monitoring system.

[0037] A processor for running a program, wherein the program executes, as described above, a wind turbine blade infrared monitoring system based on UAV inspection.

[0038] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0039] This invention uses an infrared camera mounted on a drone to acquire and store several infrared thermal images of wind turbine blades. Through temperature inversion, the highest and lowest temperatures of each infrared thermal image are calculated, yielding the temperature difference for wind turbine blade number i at the corresponding timestamp. Furthermore, several infrared thermal images of wind turbine blade numbers within the same area are acquired, and the highest and lowest temperatures of each image are calculated uniformly to construct a temperature analysis set. Based on this set, the overall standard deviation is calculated to assess the degree of temperature dispersion within the area. Finally, a health evaluation coefficient is established based on the temperature difference and dispersion, providing quantitative data references for managers and decision-makers, facilitating subsequent management and decision-making. Attached Figure Description

[0040] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0041] Figure 1 This is a schematic diagram of the overall system framework of the present invention;

[0042] Figure 2 This is a flowchart of the operation of the temperature difference recognition module of the present invention;

[0043] Figure 3 This is a flowchart of the operation of the uniformity recognition module of the present invention;

[0044] Figure 4 This is a flowchart of the method of the present invention. Detailed Implementation

[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0047] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0048] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0049] In one embodiment of the present invention, an infrared monitoring system for wind turbine blades based on unmanned aerial vehicle (UAV) inspection is provided, such as... Figure 1 As shown, it includes:

[0050] I. Image Acquisition Unit

[0051] The image acquisition unit includes a drone and an infrared camera and image storage module mounted on the drone. The infrared camera acquires several infrared thermal images of the wind turbine blades and stores them in the image storage module. Furthermore, the infrared thermal images are used for subsequent monitoring of the wind turbine blades to check for internal overheating or other damage. The data storage method in the image storage module is: timestamp-geographical location-wind turbine blade number-several images of the wind turbine blade under the current number corresponding to the timestamp. That is, each infrared thermal image contains a corresponding timestamp label and a wind turbine blade number label.

[0052] II. Image Recognition Unit

[0053] The image recognition unit is connected to the image acquisition unit to acquire images stored in the storage module, including a temperature difference recognition module, a uniformity recognition module, and an alarm module. These three modules are further described below.

[0054] The temperature difference recognition module calculates the highest and lowest temperatures for each infrared thermal image through temperature inversion, thereby obtaining the highest and lowest temperatures under the corresponding timestamp and wind turbine blade number, and finally obtaining the temperature difference of wind turbine blade number i under the corresponding timestamp. For example... Figure 2 As shown, the temperature difference recognition module performs the following operations:

[0055] Step 1: Obtain the infrared thermal image from the image storage module;

[0056] Step 2: Obtain the grayscale value to temperature mapping table or conversion formula provided by the infrared camera manufacturer. The conversion formula includes a linear relationship, as shown below:

[0057]

[0058] in, T It refers to temperature (degrees Celsius). G It is a grayscale value (0-255), a and b These are calibration parameters;

[0059] Step 3: Based on the conversion formula or mapping table, obtain the temperature set of several images with the same wind turbine blade number at the same timestamp, and find the maximum value to obtain the highest temperature. T max =max( T Similarly, the lowest temperature is obtained by finding the minimum value. T min =min( T );

[0060] Step 4: Return the corresponding timestamp-fan blade number-temperature difference, where the formula for calculating the temperature difference is as follows:

[0061]

[0062] in, For temperature difference, The highest temperature, This is the lowest temperature.

[0063] Because different geographical locations bring different environmental conditions such as temperature and humidity, temperature difference between day and night, and altitude, the temperature changes of wind turbines will show a strong correlation with geographical location. Therefore, when analyzing wind turbine temperature changes, if the wind turbine data from all geographical locations are merged together for analysis, the data cannot be measured under a single standard due to the different geographical environments. Therefore, dividing the data into geographical locations and processing it according to different geographical locations will make the alarm analysis more accurate.

[0064] The uniformity identification module acquires several infrared thermal images of each wind turbine blade number within the same area (distinguished by geographical location), then uniformly calculates the highest and lowest temperatures of each infrared thermal image, constructs a temperature analysis set, and calculates the overall standard deviation based on the temperature analysis set to assess the degree of temperature dispersion within the area. For example... Figure 3 As shown, the uniformity recognition module performs the following operations:

[0065] Step 01: Divide the area into different regions based on geographical location, and obtain all infrared thermal imaging data within the same region;

[0066] Step 02: Obtain the grayscale value to temperature mapping table or conversion formula provided by the infrared camera manufacturer. The conversion formula includes a linear relationship, as shown below:

[0067]

[0068] in, T It refers to temperature (degrees Celsius). G It is a grayscale value (0-255), a and b These are calibration parameters;

[0069] Step 03: Based on the conversion formula or mapping table, obtain the blade number of the same wind turbine under the same timestamp. i The highest temperature is obtained by finding the maximum value from a set of temperatures in several images. T max ( i )=max( T Similarly, the lowest temperature is obtained by finding the minimum value. T min ( i )=min( T );

[0070] Step 04: Calculate the population standard deviation. The formula is as follows:

[0071]

[0072] in, Wind turbine blade number i The set of the highest and lowest temperatures, i.e. N is the total number of wind turbine blade numbers in the area. m It is the overall average, that is, the average of the highest and lowest temperatures of all wind turbine blades in the region.

[0073] The alarm module includes a temperature difference threshold. i 温度差 Alarm threshold for sum and standard deviation i 标准差 By acquiring infrared thermal images of the motor blades in real time, the temperature difference between the motor blades can be obtained in real time, and compared with a threshold temperature difference. i 温度差 The system compares the temperatures of the motor blades and issues a first alarm signal when the temperature difference exceeds a set threshold. Furthermore, it collects infrared thermal images of individual motor blades within the area and calculates the overall standard deviation of the highest and lowest temperatures for each blade. This analysis examines the temperature dispersion within the area and compares it to a set threshold. If the standard deviation exceeds the set temperature difference threshold, an alarm is triggered. i 温度差 If the first alarm signal is triggered, a second alarm signal will be issued. The information carried by the first alarm signal and the second alarm signal is different. The first alarm signal carries information about the abnormal temperature of the corresponding click blade, while the second alarm signal carries information about the abnormal temperature dispersion within the area.

[0074] Furthermore, in a preferred embodiment of the present invention, the specific calculation of temperature can also utilize Planck's formula to convert the sensor radiant intensity value corresponding to the image pixel into the corresponding luminance temperature value. The formula is as follows:

[0075]

[0076] in, Here, DN represents the luminance temperature value (in Kelvin), and DN represents the spectral radiance value obtained after image preprocessing. K 1 and K 2 is a constant.

[0077] III. Terminal Processing and Feedback Unit

[0078] The terminal processing unit is used to receive the first alarm signal and the second alarm signal, and based on the different alarm signals, to go to the site to troubleshoot and handle the fault, and to report the troubleshooting and response status to the evaluation and management unit.

[0079] The fault diagnosis status is confirmed as either correct or incorrect; the response processing status is either fault processed or fault not processed.

[0080] IV. Evaluation and Management Unit

[0081] The evaluation and management unit uses the health factor for wind turbine blades, and the formula for calculating the health factor is as follows:

[0082]

[0083] In the formula, Z represents the health coefficient. The temperature difference of the wind turbine blades at the current moment. Here, represents the standard deviation of the region where the blade is located; Year represents the service life; and Nt represents the number of failures within the set period. These are the weighting coefficients for temperature difference, standard deviation, service life, and number of failures, respectively.

[0084] In one embodiment of the present invention, a method for infrared monitoring of wind turbine blades based on unmanned aerial vehicle (UAV) inspection is provided, such as... Figure 4 As shown, it includes the following steps:

[0085] S1: Using an infrared camera mounted on a drone, acquire several infrared thermal images of the wind turbine blades and store them in the image storage module. The data storage method is: timestamp-geographical location-wind turbine blade number-several images of the wind turbine blade under the current number corresponding to the timestamp. Each infrared thermal image contains a corresponding timestamp label and a wind turbine blade number label.

[0086] S2: By temperature inversion, the highest and lowest temperatures of each infrared thermal image are calculated, and then the highest and lowest temperatures under the corresponding timestamp and wind turbine blade number are obtained, and finally the temperature difference of wind turbine blade number i under the corresponding timestamp is obtained.

[0087] S3: Obtain several infrared thermal images of each wind turbine blade number in the same area, then uniformly calculate the highest and lowest temperatures of each infrared thermal image, construct a temperature analysis set, and calculate the overall standard deviation based on the temperature analysis set to evaluate the degree of temperature dispersion in the area.

[0088] S4: Set the threshold for temperature difference i 温度差 Alarm threshold for sum and standard deviation i 标准差By acquiring infrared thermal images of the motor blades in real time, the temperature difference between the motor blades can be obtained in real time, and compared with a threshold temperature difference. i 温度差 The system performs a comparison and issues a first alarm signal when the temperature difference between the motor blades exceeds a set threshold; and an alarm signal is issued when the temperature standard deviation within the area exceeds a temperature difference threshold. i 温度差 If this occurs, a second alarm signal will be issued;

[0089] S5: Receive the first alarm signal and the second alarm signal, and go to the site to troubleshoot and handle the fault based on the different alarm signals, and report the troubleshooting status and response status. The troubleshooting status is to confirm that the alarm signal is correct or to confirm that the alarm signal is wrong. The response status is to indicate that the fault has been handled or the fault has not been handled.

[0090] S6: Calculate the health coefficient of the wind turbine blades. The formula for calculating the health coefficient is as follows:

[0091]

[0092] In the formula, Z represents the health coefficient. The temperature difference of the wind turbine blades at the current moment. Here, represents the standard deviation of the region where the blade is located; Year represents the service life; and Nt represents the number of failures within the set period. Weighting coefficients for temperature difference, standard deviation, service life, and number of failures, respectively.

[0093] In summary, this invention uses an infrared camera mounted on a drone to acquire and store several infrared thermal images of wind turbine blades. Through temperature inversion, the highest and lowest temperatures of each infrared thermal image are calculated, yielding the temperature difference for wind turbine blade number i at the corresponding timestamp. Furthermore, several infrared thermal images of wind turbine blade numbers within the same area are acquired, and the highest and lowest temperatures of each image are calculated uniformly to construct a temperature analysis set. Based on this set, the overall standard deviation is calculated to assess the degree of temperature dispersion within the area. Finally, a health evaluation coefficient is established based on the temperature difference and dispersion, providing quantitative data references for managers and decision-makers, facilitating subsequent management and decision-making.

[0094] Those skilled in the art will recognize that the units of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the invention.

[0095] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical functional division. In actual implementation, there may be other division methods, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored.

[0096] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0097] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A wind turbine blade infrared monitoring system based on UAV inspection, characterized in that, include: The image acquisition unit includes a drone and an infrared camera and an image storage module mounted on the drone. The infrared camera is used to acquire several infrared thermal images of the wind turbine blades and store them in the image storage module. An image recognition unit, connected to the image acquisition unit, includes a temperature difference recognition module. This module is used to identify temperature differences in infrared thermal imaging based on temperature inversion. Specifically, the temperature recognition module acquires the temperature difference as follows: Acquire infrared thermal images from the image storage module; Obtain the mapping table or conversion formula between grayscale values ​​and temperature provided by the infrared camera manufacturer; Based on a conversion formula or mapping table, obtain a set of temperatures from several images of the same wind turbine blade number at the same timestamp, and find the highest temperature by finding the maximum value. T max =max( T Similarly, the lowest temperature is obtained by finding the minimum value. T min =min( T ); The corresponding timestamp-fan blade number-temperature difference is obtained, where the formula for calculating the temperature difference is as follows: in, For temperature difference, The highest temperature, The lowest temperature; The image recognition unit also includes a uniformity recognition module. This module acquires several infrared thermal images of each wind turbine blade number within the same area, then uniformly calculates the highest and lowest temperatures for each image, constructs a temperature analysis set, and calculates the overall standard deviation based on the temperature analysis set to assess the degree of temperature dispersion within the area. The uniformity recognition module performs the following operations: Divide the area into different regions based on geographical location, and obtain all infrared thermal imaging data within the same region; Obtain the mapping table or conversion formula between grayscale values ​​and temperature provided by the infrared camera manufacturer; Based on conversion formulas or mapping tables, obtain the blade number of the same wind turbine under the same timestamp. i The highest temperature is obtained by finding the maximum value from a set of temperatures in several images. T max ( i )=max( T Similarly, the lowest temperature is obtained by finding the minimum value. T min ( i )=min( T ); The population standard deviation is calculated using the following formula: in, Wind turbine blade number i The set of the highest and lowest temperatures, i.e. N is the total number of wind turbine blade numbers in the area. μ It is the overall average, that is, the average of the highest and lowest temperatures of all wind turbine blades in the region; The evaluation and management unit is used to evaluate the health coefficient of the wind turbine blades, and the calculation formula is as follows: In the formula, Z is the health coefficient. The temperature difference of the wind turbine blades at the current moment. The standard deviation of the region where the leaf is located. Year For service life, N t To set the number of failures within a set period, These are the weighting coefficients for temperature difference, standard deviation, service life, and number of failures, respectively.

2. The wind turbine blade infrared monitoring system based on UAV inspection according to claim 1, characterized in that, The image recognition unit also includes an alarm module, which has a temperature difference threshold. θ 温度差 Alarm threshold for sum and standard deviation θ 标准差 By acquiring infrared thermal images of the motor blades in real time, the temperature difference between the motor blades can be obtained in real time, and compared with a threshold temperature difference. θ 温度差 The system performs a comparison and issues a first alarm signal when the temperature difference between the motor blades exceeds a set threshold; and an alarm signal is issued when the temperature standard deviation within the area exceeds a temperature difference threshold. θ 温度差 If this occurs, a second alarm signal will be issued.

3. The wind turbine blade infrared monitoring system based on UAV inspection according to claim 2, characterized in that, It also includes a terminal feedback unit, which is used to receive the first alarm signal and the second alarm signal, and go to the site to troubleshoot and handle the fault based on the different alarm signals, and report the troubleshooting status and response status to the evaluation and management unit; the troubleshooting status is to confirm that the alarm signal is correct or to confirm that the alarm signal is incorrect, and the response status is to indicate that the fault has been handled or the fault has not been handled.

4. A method for infrared monitoring of wind turbine blades based on UAV inspection, applied to a wind turbine blade infrared monitoring system based on UAV inspection as described in any one of claims 1-3, characterized in that, Includes the following steps: The drone is equipped with an infrared camera to acquire several infrared thermal images of the wind turbine blades and store them in the image storage module. The data storage method is: timestamp-geographical location-wind turbine blade number-several images of the wind turbine blade under the current number of the corresponding timestamp. Each infrared thermal image contains a corresponding timestamp label and a wind turbine blade number label. By temperature inversion, the highest and lowest temperatures of each infrared thermal image are calculated, and then the highest and lowest temperatures under the corresponding timestamp and wind turbine blade number are obtained, finally obtaining the temperature difference of wind turbine blade number i under the corresponding timestamp. Several infrared thermal images of each wind turbine blade number within the same area are obtained, and then the highest and lowest temperatures of each infrared thermal image are calculated in a unified manner to construct a temperature analysis set. Based on the temperature analysis set, the overall standard deviation is calculated to evaluate the degree of temperature dispersion within the area. Set the threshold for temperature difference θ 温度差 Alarm threshold for sum and standard deviation θ 标准差 By acquiring infrared thermal images of the motor blades in real time, the temperature difference between the motor blades can be obtained in real time, and compared with a threshold temperature difference. θ 温度差 The system performs a comparison and issues a first alarm signal when the temperature difference between the motor blades exceeds a set threshold; and an alarm signal is issued when the temperature standard deviation within the area exceeds a temperature difference threshold. θ 温度差 If this occurs, a second alarm signal will be issued; Receive the first alarm signal and the second alarm signal, and go to the site to troubleshoot and handle the fault based on the different alarm signals. Then, report the troubleshooting status and response status to the evaluation and management unit. The troubleshooting status is to confirm that the alarm signal is correct or to confirm that the alarm signal is wrong. The response status is to indicate that the fault has been handled or the fault has not been handled. The health coefficient of the wind turbine blades is calculated using the following formula: In the formula, Z For health index, The temperature difference of the wind turbine blades at the current moment. The standard deviation of the region where the leaf is located. Year For service life, N t To set the number of failures within a set period, These are the weighting coefficients for temperature difference, standard deviation, service life, and number of failures, respectively.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to execute the wind turbine blade infrared monitoring system based on UAV inspection as described in any one of claims 1 to 3.

6. A processor, characterized in that, The processor is used to run a program, wherein the program executes the wind turbine blade infrared monitoring system based on UAV inspection as described in any one of claims 1 to 3.

Images