Photovoltaic module temperature anomaly diagnosis method based on unmanned aerial vehicle inspection

By carrying an infrared camera on a drone, collecting infrared images of photovoltaic modules and correcting them, and normalizing temperatures with environmental monitoring data, solving the accuracy of temperature abnormality diagnosis of photovoltaic modules, realizing the temperature abnormality positioning and visualization of photovoltaic power stations. It provides an important basis for the intelligent operation and maintenance of photovoltaic power plants.

CN118913456APending Publication Date: 2024-11-08SOUTHEAST UNIV
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410968568.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing technology fails to fully consider the impact of environmental factors on the temperature of photovoltaic modules, resulting in the diagnosis of temperature abnormalities of photovoltaic modules that is not accurate enough, high-quality infrared image acquisition and correction cannot be achieved, and normalized diagnosis of photovoltaic modules under different environmental conditions cannot be achieved. .

Method used

The drone is equipped with an infrared camera to collect infrared images of photovoltaic modules, correct radial distortion and perspective deformation, and normalize the temperature matrix with environmental monitor data to analyze the structure of photovoltaic modules to diagnose temperature abnormalities.

Benefits of technology

It realizes accurate diagnosis of temperature abnormalities of photovoltaic modules, provides a smart operation and maintenance basis for photovoltaic power stations, can locate and visualize temperature abnormalities, and improves the temperature monitoring accuracy of photovoltaic modules.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118913456A_ABST
    Figure CN118913456A_ABST
Patent Text Reader

Abstract

The invention discloses a photovoltaic module temperature anomaly diagnosis method based on unmanned aerial vehicle inspection, and the method comprises the following steps: an unmanned aerial vehicle carries an infrared camera, carries out the inspection of a photovoltaic power station, and collects an infrared image of a photovoltaic module; correcting the radial distortion of the infrared image according to the parameters of the infrared camera; correcting perspective deformation of the photovoltaic module in the infrared image, and extracting a temperature matrix of the photovoltaic module; normalizing the temperature matrix of the photovoltaic module according to irradiance, temperature and wind speed data collected by the environment monitor; and analyzing the structure of the photovoltaic module and the normalized temperature matrix, and diagnosing temperature abnormity. According to the method, the positioning and matching technology of the photovoltaic module and the panoramic splicing technology of the photovoltaic power station can be combined, positioning and visualization of the temperature anomaly of the photovoltaic module are achieved, and an important basis is provided for intelligent operation and maintenance of the photovoltaic power station.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a photovoltaic component temperature anomaly diagnosis technology based on unmanned aerial vehicle inspection, and belongs to the field of photovoltaic power station inspection and operation and maintenance technology. Background Art

[0002] Photovoltaic modules may have defects during transportation, installation, and operation. Defects in photovoltaic modules not only cause output power loss, but may even cause fires and affect the stability of the photovoltaic system. Therefore, the diagnosis of photovoltaic module defects has received more and more attention. The solar energy absorbed by photovoltaic modules is converted into electrical energy and thermal energy, which means that defects often cause power loss and are often accompanied by temperature anomalies. Infrared thermal imaging is an important way to diagnose temperature anomalies in photovoltaic modules.

[0003] It is worth noting that environmental factors can affect the temperature of photovoltaic modules. When the irradiance received on the surface of photovoltaic modules is higher, more solar energy is absorbed per unit time, more electrical energy and thermal energy are converted, and the module temperature is higher; when the ambient temperature is lower and the wind speed is higher, there is more heat transfer and thermal radiation between the photovoltaic modules and the surrounding environment, and the module temperature is lower. In addition, the temperature anomaly diagnosis of photovoltaic modules depends on high-quality infrared image acquisition, while radial distortion and perspective deformation may interfere with the temperature feature extraction of photovoltaic modules.

[0004] The existing technology has studied the identification of photovoltaic modules based on infrared images and the preliminary detection of temperature anomalies. However, the existing technology has not fully considered the impact of environmental factors on the temperature of photovoltaic modules and cannot achieve accurate diagnosis of temperature anomalies. How to collect high-quality infrared images of photovoltaic modules, correct radial distortion and perspective deformation, normalize the temperature of photovoltaic modules under different environmental conditions, and diagnose temperature anomalies of photovoltaic modules are important issues that need to be considered for intelligent inspection and intelligent operation and maintenance of photovoltaic power stations. Summary of the invention

[0005] Technical problem: The present invention aims to solve the deficiencies in the prior art, fully consider the impact of environmental factors on the temperature of photovoltaic modules, combine high-quality infrared image acquisition, radial distortion and perspective deformation correction, and provide a photovoltaic module temperature anomaly diagnosis method based on drone inspection.

[0006] Technical solution: A photovoltaic module temperature anomaly diagnosis method based on drone inspection of the present invention comprises the following steps in sequence:

[0007] S1: The drone is equipped with an infrared camera and inspects the photovoltaic power station to collect infrared images of the photovoltaic modules;

[0008] S2: Correct the radial distortion of the infrared image according to the parameters of the infrared camera;

[0009] S3: Correct the perspective deformation of the photovoltaic module in the infrared image and extract the temperature matrix of the photovoltaic module;

[0010] S4: Normalize the temperature matrix of the photovoltaic module according to the irradiance, temperature and wind speed data collected by the environmental monitoring instrument;

[0011] S5: Analyze the structure of the PV module and the normalized temperature matrix to diagnose temperature anomalies.

[0012] Furthermore, in step S1, the drone inspection is carried out on a sunny day, and the irradiance is not less than 200W / m 2 , under the condition that the wind speed does not exceed 10m / s; the angle between the optical axis of the infrared camera and the surface of the photovoltaic module is between 60° and 90°; the infrared image collection avoids solar reflection and drone projection; each cell of the photovoltaic module occupies at least 4 pixels in the infrared image.

[0013] Furthermore, in step S2, x=(u,v,1) T represents the pixel homogeneous coordinates of the infrared image, where u and v represent the horizontal and vertical coordinates of the pixel point X in the infrared image respectively; o = (u o ,v o ,1) T represents the homogeneous coordinates of the center of the infrared image, where u o With v o Respectively represent the horizontal and vertical coordinates of the infrared image center O; r =(u r ,v r ,1) T Represents the homogeneous coordinates after radial distortion correction, where u r With v r Respectively represent the horizontal and vertical coordinates of pixel point X after radial distortion correction, and calculate x r as follows:

[0014] x r =o+(xo)(1+λ1·r 2 +λ2·r 4 )

[0015] Among them, λ1 and λ2 represent the radial distortion parameters of the infrared camera, r represents the distance from the pixel to the center of the infrared image,

[0016]

[0017] Furthermore, in step S3, H represents the perspective deformation matrix of the front surface of the photovoltaic module projected onto the infrared image plane, and the matrix is ​​a non-singular third-order square matrix; p =(u p,v p ,1) T Represents the homogeneous coordinates after perspective deformation correction, where u p With v p Respectively represent the horizontal and vertical coordinates of pixel point X after perspective correction, and calculate x p as follows:

[0018] x p =H -1 x r

[0019] The weighted K nearest neighbor algorithm is used to generate the corrected temperature image. The image processing method is used to identify the rectangular area occupied by the front surface of the photovoltaic module in the temperature image and extract the temperature matrix T of the photovoltaic module.

[0020] Furthermore, in step S4, ε represents the emissivity of the surface of the photovoltaic module, ε s represents the emissivity of the sky, β represents the emissivity ratio term, σ represents the Stefan-Boltzmann constant, and h represents the convective heat transfer coefficient on the surface of the photovoltaic module.

[0021]

[0022] σ=5.67×10 -8 W / (m 2 ·K 4 )

[0023] h=k0+k1·w

[0024] Among them, k0 and k1 are constants, and w represents wind speed.

[0025] Furthermore, in step S4, the actual irradiance collected by the environmental monitoring instrument is G and the ambient temperature is T a , wind speed is w; sky temperature is T s ; Normalized irradiance is G0, ambient temperature is T a,0 , wind speed is w0, sky temperature is T s,0 ; T i,j Represents the elements in the temperature matrix T of the photovoltaic module, T i,j Normalized temperature T i,j,0 Satisfies the following relationship:

[0026]

[0027] Among them, η represents the proportional coefficient of irradiance absorbed by the photovoltaic module, e and e0 represent correction terms, b and b0 represent heat transfer coefficient terms that are not directly related to wind speed,

[0028]

[0029] Furthermore, in step S5, the photovoltaic module includes a plurality of substrings. represents the expected normalized average temperature of the substring in the case of an open circuit or short circuit fault; represents the average value of the corresponding element of a substring after the temperature matrix T of the photovoltaic module is normalized; δ represents the standard deviation of the corresponding element of a substring after the temperature matrix T of the photovoltaic module is normalized; ξ1 and ξ2 represent error terms; if And δ<ξ2, then the substring is diagnosed as having a temperature abnormality caused by an open circuit or short circuit fault.

[0030] Furthermore, in step S5, the substring includes a plurality of battery cells. It indicates the expected normalized average temperature of the battery cell under normal working conditions; It represents the maximum value of the element corresponding to a certain cell after the temperature matrix T of the photovoltaic module is normalized; θ represents the threshold value; if The cell is then diagnosed as having a hot spot.

[0031] Beneficial effects: The present invention provides a method for diagnosing abnormal temperature of photovoltaic modules based on drone inspection, which fully considers the influence of environmental factors on the temperature of photovoltaic modules, combines high-quality infrared image acquisition, radial distortion and perspective deformation correction, photovoltaic module temperature matrix extraction and normalization, and realizes accurate diagnosis of abnormal temperature of photovoltaic modules. This method can be combined with the positioning and matching technology of photovoltaic modules and the panoramic stitching technology of photovoltaic power stations to realize the positioning and visualization of abnormal temperature of photovoltaic modules, providing an important basis for the intelligent operation and maintenance of photovoltaic power stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of the overall process of the embodiment;

[0033] Figure 2 This is an example of an infrared image of a photovoltaic module;

[0034] Figure 3 This is an example of an infrared image after perspective deformation correction;

[0035] Figure 4 The following are examples of temperature anomalies in photovoltaic modules, where (a) is a temperature anomaly caused by a substring short circuit failure; (b) is a case where a hot spot exists on the cell. DETAILED DESCRIPTION

[0036] The specific implementation modes of the present invention will be further described in detail below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited to the embodiments. Figure 1 As shown, a photovoltaic module temperature abnormality diagnosis method based on drone inspection in this embodiment includes the following steps in sequence:

[0037] S1: The drone is equipped with an infrared camera and inspects the photovoltaic power station to collect infrared images of the photovoltaic modules.

[0038] In this embodiment, the drone inspection is carried out on a sunny day, and the irradiance is not less than 200W / m 2 , under the condition that the wind speed does not exceed 10m / s; the angle between the optical axis of the infrared camera and the surface of the photovoltaic module is between 60° and 90°; the infrared image collection avoids solar reflection and drone projection; each cell of the photovoltaic module occupies at least 4 pixels in the infrared image.

[0039] S2: Correct the radial distortion of the infrared image according to the parameters of the infrared camera.

[0040] In this embodiment, x=(u,v,1) T represents the pixel homogeneous coordinates of the infrared image, where u and v represent the horizontal and vertical coordinates of the pixel point X in the infrared image respectively; o = (u o ,v o ,1) T represents the homogeneous coordinates of the center of the infrared image, where u o With v o Respectively represent the horizontal and vertical coordinates of the infrared image center O; r =(u r ,v r ,1) T Represents the homogeneous coordinates after radial distortion correction, where u r With v r Respectively represent the horizontal and vertical coordinates of pixel point X after radial distortion correction, and calculate x r as follows:

[0041] x r =o+(xo)(1+λ1·r 2 +λ2·r 4 )

[0042] Among them, λ1 and λ2 represent the radial distortion parameters of the infrared camera, r represents the distance from the pixel to the center of the infrared image,

[0043]

[0044] S3: Correct the perspective deformation of the photovoltaic module in the infrared image and extract the temperature matrix of the photovoltaic module.

[0045] In this embodiment, H represents the perspective deformation matrix of the front surface of the photovoltaic module projected onto the infrared image plane, and the matrix is ​​a non-singular third-order square matrix; x p =(u p,v p ,1) T Represents the homogeneous coordinates after perspective deformation correction, where u p With v p Respectively represent the horizontal and vertical coordinates of pixel point X after perspective correction, and calculate x p as follows:

[0046] x p =H -1 x r

[0047] The weighted K nearest neighbor algorithm is used to generate the corrected temperature image. The image processing method is used to identify the rectangular area occupied by the front surface of the photovoltaic module in the temperature image and extract the temperature matrix T of the photovoltaic module.

[0048] S4: Normalize the temperature matrix of the photovoltaic module according to the irradiance, temperature, and wind speed data collected by the environmental monitoring instrument.

[0049] In this embodiment, ε represents the emissivity of the photovoltaic module surface, ε s represents the emissivity of the sky, β represents the emissivity ratio term, σ represents the Stefan-Boltzmann constant, and h represents the convective heat transfer coefficient on the surface of the photovoltaic module.

[0050]

[0051] σ=5.67×10 -8 W / (m 2 ·K 4 )

[0052] h=k0+k1·w

[0053] Among them, k0 and k1 are constants, and w represents wind speed.

[0054] The actual irradiance collected by the environmental monitor is G and the ambient temperature is T a , wind speed is w; sky temperature is T s ; Normalized irradiance is G0, ambient temperature is T a,0 , wind speed is w0, sky temperature is T s,0 ; T i,j Represents the elements in the temperature matrix T of the photovoltaic module, T i,j Normalized temperature T i,j,0 Satisfies the following relationship:

[0055]

[0056] Among them, η represents the proportional coefficient of irradiance absorbed by the photovoltaic module, e and e0 represent correction terms, b and b0 represent heat transfer coefficient terms that are not directly related to wind speed,

[0057]

[0058] S5: Analyze the structure of the PV module and the normalized temperature matrix to diagnose temperature anomalies.

[0059] In this embodiment, the photovoltaic module includes a plurality of substrings. represents the expected normalized average temperature of the substring in the case of an open circuit or short circuit fault; S represents the average value of the corresponding element of a substring after the temperature matrix T of the photovoltaic module is normalized; δ represents the standard deviation of the corresponding element of a substring after the temperature matrix T of the photovoltaic module is normalized; ξ1 and ξ2 represent error terms; if And δ<ξ2, then the substring is diagnosed as having a temperature abnormality caused by an open circuit or short circuit fault.

[0060] A substring includes several cells. It indicates the expected normalized average temperature of the battery cell under normal working conditions; It represents the maximum value of the element corresponding to a certain cell after the temperature matrix T of the photovoltaic module is normalized; θ represents the threshold value; if The cell is then diagnosed as having a hot spot.

[0061] Figure 2 An infrared image provided by an embodiment of the present invention. In this embodiment, according to the method described in step S2, the radial distortion of the infrared image is corrected; according to the method described in step S3, the perspective deformation of the photovoltaic module in the infrared image is corrected. Figure 3 This is the infrared image after perspective deformation correction.

[0062] Figure 4 This is an abnormal temperature condition of a photovoltaic module provided by an embodiment of the present invention. In this embodiment, Figure 4 (a) is the temperature abnormality caused by substring short circuit fault; Figure 4 (b) is the case where there is a hot spot on the battery cell.

[0063] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for diagnosing abnormal temperature of photovoltaic modules based on drone inspection, characterized in that: The following steps are included in sequence: S1: The drone is equipped with an infrared camera and inspects the photovoltaic power station to collect infrared images of the photovoltaic modules; S2: Correct the radial distortion of the infrared image according to the parameters of the infrared camera; S3: Correct the perspective deformation of the photovoltaic module in the infrared image and extract the temperature matrix of the photovoltaic module; S4: Normalize the temperature matrix of the photovoltaic module according to the irradiance, temperature and wind speed data collected by the environmental monitoring instrument; S5: Analyze the structure of the PV module and the normalized temperature matrix to diagnose temperature anomalies.

2. The method for diagnosing abnormal temperature of photovoltaic modules based on drone inspection according to claim 1 is characterized by: In step S1, the drone inspection is carried out on a sunny day, and the irradiance is not less than 200W / m 2 , under the condition that the wind speed does not exceed 10m / s; the angle between the optical axis of the infrared camera and the surface of the photovoltaic module is between 60° and 90°; the infrared image collection avoids solar reflection and drone projection; each cell of the photovoltaic module occupies at least 4 pixels in the infrared image.

3. The method for diagnosing abnormal temperature of photovoltaic modules based on drone inspection according to claim 2 is characterized in that: In step S2, x=(u,v,1) T represents the pixel homogeneous coordinates of the infrared image, where u and v represent the horizontal and vertical coordinates of the pixel point X in the infrared image respectively; o = (u o ,v o ,1) T represents the homogeneous coordinates of the center of the infrared image, where u o With v o Respectively represent the horizontal and vertical coordinates of the infrared image center O; r =(u r ,v r ,1) T Represents the homogeneous coordinates after radial distortion correction, where u r With v r Respectively represent the horizontal and vertical coordinates of pixel point X after radial distortion correction, and calculate x r as follows: x r =o+(x-o)(1+λ1·r 2 +λ2·r 4 ) Among them, λ1 and λ2 represent the radial distortion parameters of the infrared camera, r represents the distance from the pixel to the center of the infrared image, 4. The method for diagnosing abnormal temperature of photovoltaic modules based on drone inspection according to claim 3 is characterized by: In step S3, H represents the perspective deformation matrix of the front surface of the photovoltaic module projected onto the infrared image plane, and the matrix is ​​a non-singular third-order square matrix; p =(u p ,v p ,1) T Represents the homogeneous coordinates after perspective deformation correction, where u p With v p Respectively represent the horizontal and vertical coordinates of pixel point X after perspective correction, and calculate x p as follows: x p =H -1 x r The weighted K nearest neighbor algorithm is used to generate the corrected temperature image. The image processing method is used to identify the rectangular area occupied by the front surface of the photovoltaic module in the temperature image and extract the temperature matrix T of the photovoltaic module.

5. The method for diagnosing abnormal temperature of photovoltaic modules based on drone inspection according to claim 4 is characterized in that: In step S4, ε represents the emissivity of the surface of the photovoltaic module, ε s represents the emissivity of the sky, β represents the emissivity ratio term, σ represents the Stefan-Boltzmann constant, and h represents the convective heat transfer coefficient on the surface of the photovoltaic module. σ=5.67×10 -8 W / (m 2 ·K 4 ) h=k0+k1·w Among them, k0 and k1 are constants, and w represents wind speed.

6. A photovoltaic module temperature anomaly diagnosis method based on drone inspection according to claim 5, characterized in that: In step S4, the actual irradiance collected by the environmental monitor is G, and the ambient temperature is T a , wind speed is w; sky temperature is T s ; Normalized irradiance is G0, ambient temperature is T a,0 , wind speed is w0, sky temperature is T s,0 ; T i,j Represents the elements in the temperature matrix T of the photovoltaic module, T i,j Normalized temperature T i,j,0 Satisfies the following relationship: Among them, η represents the proportional coefficient of irradiance absorbed by the photovoltaic module, e and e0 represent correction terms, b and b0 represent heat transfer coefficient terms that are not directly related to wind speed, 7. A photovoltaic module temperature anomaly diagnosis method based on drone inspection according to claim 6, characterized in that: In step S5, the photovoltaic module includes a plurality of substrings. represents the expected normalized average temperature of the substring in the case of an open circuit or short circuit fault; represents the average value of the corresponding element of a substring after the temperature matrix T of the photovoltaic module is normalized; δ represents the standard deviation of the corresponding element of a substring after the temperature matrix T of the photovoltaic module is normalized; ξ1 and ξ2 represent error terms; if And δ<ξ2, then the substring is diagnosed as having a temperature abnormality caused by an open circuit or short circuit fault.

8. The method for diagnosing abnormal temperature of photovoltaic modules based on drone inspection according to claim 7 is characterized by: In step S5, the substring includes a plurality of battery cells. It indicates the expected normalized average temperature of the battery cell under normal working conditions; It represents the maximum value of the element corresponding to a certain cell after the temperature matrix T of the photovoltaic module is normalized; θ represents the threshold value; if The cell is then diagnosed as having a hot spot.

Citation Information

Cited By

  • Non-contact photovoltaic module power generation efficiency evaluation method

    CN119561490A