Hot spot detection system and method for photovoltaic power station assembly

Abstract

The invention relates to a hot spot detection system and method for a photovoltaic power station assembly, and the system comprises a photovoltaic assembly array which comprises a plurality of photovoltaic assemblies distributed in an array manner; the thermal imaging unmanned aerial vehicle comprises an unmanned aerial vehicle body, and an infrared thermal imaging camera is carried on the unmanned aerial vehicle; the unmanned aerial vehicle body cruises the photovoltaic modules according to a preset path, the preset path is provided with a plurality of route point locations, and the route point locations are in one-to-one correspondence with the positions of the photovoltaic modules; in the cruising process, when a corresponding route point position is reached, thermal imaging images of the surface of the corresponding photovoltaic module are collected through an infrared thermal imaging camera; and the upper computer is used for receiving the thermal imaging image acquired by the thermal imaging unmanned aerial vehicle, analyzing by adopting an image processing algorithm, identifying a temperature abnormal region, determining the position of the photovoltaic module and sending out alarm information. Compared with the prior art, the method has the advantages that the detection efficiency is remarkably improved, and the method is high and accurate.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of hot spot detection of photovoltaic modules, in particular to a hot spot detection system and method for photovoltaic power station modules. BACKGROUND

[0002] Hot spot is a local overheating phenomenon caused by partial shading or damage of some cells in photovoltaic modules, which not only reduces the efficiency of the cells, but also may cause fire hazards and other safety hazards. Through infrared thermal imaging technology, the temperature distribution on the surface of the photovoltaic panel can be directly displayed, and the high-temperature area can be quickly identified, so that the hot spot problem can be found and handled in time. In most photovoltaic power station operation and maintenance work, hot spot detection is achieved by manually holding an infrared imager to conduct a comprehensive inspection of the power station. This way is time-consuming and labor-intensive. The low quality of inspection caused by human factors may lead to incomplete detection. The artificial inspection cycle is generally long and cannot achieve the purpose of timely discovery of hidden dangers.

[0003] The application with publication number CN115051646A discloses a photovoltaic module temperature sampling device and a hot spot detection system, which comprises a power supply, at least one infrared array sensor and a wireless communication unit; the power supply is used to power the infrared array sensor and the wireless communication unit; the infrared array sensor is used to collect the temperature of each part of the surface of the photovoltaic module and send it out through the wireless communication unit. The device uses an infrared array sensor device to detect the temperature of each part of the surface of the photovoltaic module, and the matrix type temperature measurement of the infrared array sensor is well connected with the matrix type temperature distribution of the photovoltaic module. The cost of the infrared array sensor is much lower than that of the infrared imager, so it can be widely used in the photovoltaic area.

[0004] In the above-mentioned scheme, the hot spot image is collected by the infrared array sensor, which belongs to a fixed thermal imager scheme, and has the defects of low detection efficiency, small coverage range and low flexibility. SUMMARY

[0005] The purpose of the present application is to overcome the defects of the prior art, such as low inspection quality, incomplete detection and low detection efficiency, and to provide a hot spot detection system and method for photovoltaic power station modules.

[0006] The purpose of the present application can be achieved by the following technical solutions:

[0007] A hot spot detection system for photovoltaic power station modules comprises:

[0008] A photovoltaic module array comprises a plurality of photovoltaic modules arranged in an array.

[0009] The thermal imaging unmanned aerial vehicle comprises a unmanned aerial vehicle body, and the unmanned aerial vehicle is provided with an infrared thermal imaging camera; the unmanned aerial vehicle body patrols a photovoltaic module according to a preset path, the preset path is set based on the distribution position of the photovoltaic module, and a plurality of route points are arranged, each route point corresponds to the position of each photovoltaic module; in the process of the patrol, when the corresponding route point is reached, the infrared thermal imaging camera is used to collect the thermal imaging image of the surface of the corresponding photovoltaic module.

[0010] The upper computer is used to receive the thermal imaging image collected by the thermal imaging unmanned aerial vehicle, analyze the thermal imaging image by using an image processing algorithm, identify the temperature abnormal area, judge whether there is a hot spot according to a preset hot spot detection threshold, if there is a hot spot, determine the position of the photovoltaic module according to the route point corresponding to the thermal imaging image, and send an alarm information.

[0011] Further, in the process of image collection of the infrared thermal imaging camera, the distance between the infrared thermal imaging camera and the photovoltaic module is within the range of 5-12 m.

[0012] Further, a gimbal support is arranged at the bottom of the unmanned aerial vehicle body, and the gimbal support is used to fix the infrared thermal imaging camera.

[0013] Further, the determination process of the hot spot detection threshold comprises:

[0014] For the photovoltaic module, a thermal balance equation is established, and the expression of the thermal balance equation is:

[0015] Q sun +Q elec =Q rad +Q conv +Q cond

[0016] In the formula, Q sun is the solar radiation absorption heat, Q elec is the electric energy loss heat, Q rad is the radiation heat dissipation heat, Q conv is the convection heat dissipation heat, and Q cond is the conduction heat dissipation heat.

[0017] According to the thermal balance equation, the temperature of the photovoltaic module under normal working condition and the temperature of the photovoltaic module under hot spot condition are calculated, and the corresponding temperature distribution is expressed in the form of normal distribution.

[0018] The temperature distribution of the photovoltaic module under normal working condition is taken as the background temperature, and the background mean value and the background standard deviation of the corresponding normal distribution are determined; the temperature distribution of the photovoltaic module under hot spot condition is taken as the hot spot temperature, and the hot spot mean value and the hot spot standard deviation of the corresponding normal distribution are determined.

[0019] According to the proportional value of the background mean value and the background standard deviation and the hot spot mean value and the hot spot standard deviation, the background mean value and the background standard deviation increase coefficient is added, so as to determine the hot spot detection threshold.

[0020] Further, the hot spot detection threshold is a normal distribution threshold, the mean value of the normal distribution threshold is a*mu background , and the standard deviation is b*sigma background , wherein mu background is the background mean value, sigma background is the background standard deviation, a is the mean value coefficient, and b is the standard deviation coefficient.

[0021] Further, the hot spot detection threshold is determined by multiple simulation simulations of the normal operation and hot spot state of the photovoltaic module, wherein the mean value coefficient and the standard deviation coefficient are determined.

[0022] Further, the alarm information includes the photovoltaic module position, the model, the running time and the thermal imaging image.

[0023] Further, the thermal imaging unmanned aerial vehicle uploads the collected thermal imaging image to the host computer after returning.

[0024] Further, the preset path fully covers the photovoltaic module array.

[0025] The application also provides a hot spot detection method based on the hot spot detection system of the photovoltaic power station module as described above, comprising the following steps:

[0026] According to the array distribution form of the photovoltaic module, the preset path is determined, and a plurality of route points are set to correspond to the positions of the photovoltaic modules one by one.

[0027] The thermal imaging unmanned aerial vehicle patrols the photovoltaic module according to the preset path, and in the process of patrolling, when the corresponding route point is reached, the thermal imaging image of the surface of the corresponding photovoltaic module is collected by the infrared thermal imaging camera.

[0028] After returning, the thermal imaging image collected by the thermal imaging unmanned aerial vehicle is transmitted to the host computer, and in the host computer, an image processing algorithm is used for analysis, temperature abnormal area is identified, and whether there is a hot spot is judged according to the preset hot spot detection threshold, if there is a hot spot, the position of the photovoltaic module is determined according to the corresponding route point of the thermal imaging image, and an alarm information is sent.

[0029] Compared with the prior art, the application has the following advantages:

[0030] (1) The present application realizes large-area and high-efficiency inspection by combining advanced unmanned aerial vehicle technology, high-precision thermal imaging equipment and intelligent image processing algorithms, using unmanned aerial vehicles carrying infrared thermal imaging cameras; uses computer vision algorithms to intelligently analyze and hot spot recognition of collected thermal images; establishes an automatic data processing and alarm system to realize real-time monitoring and fault warning; provides an efficient and accurate solution for photovoltaic module hot spot detection. The system not only can significantly improve the detection efficiency, but also can timely find potential problems, and provide strong guarantee for the safe operation of photovoltaic power station.

[0031] (2) The technical scheme of the present application for photovoltaic module hot spot detection by unmanned aerial vehicle can realize daily inspection, reduce operation and maintenance cost and workload, realize intelligent inspection, reduce measurement error caused by human factors, and achieve no omission and no dead angle for hot spot detection; The safety benefit is remarkable, especially avoiding the accident hidden danger caused by manual inspection in mountainous area, and timely finding hot spots; The power generation efficiency is improved, and the hot spot fault is timely eliminated through early warning to improve the component power generation efficiency.

[0032] It has obvious advantages in detection efficiency, coverage range and flexibility; although it is slightly inferior to the fixed thermal imager scheme in data precision, but through optimizing flight parameters and image processing algorithm, the detection precision can be significantly improved; considering the scale and distribution characteristics of photovoltaic power station, the unmanned aerial vehicle scheme is more suitable for the detection demand of large ground power station and scattered roof photovoltaic system.

[0033] (3) The present application proposes a method for determining the hot spot detection threshold value, first analyzes the temperature of the photovoltaic module under normal working condition and the temperature under hot spot condition according to the heat balance equation, and expresses the background temperature and hot spot temperature in the form of normal distribution, proposes to determine the final normal distribution threshold value as the hot spot detection threshold value according to the proportion value of the mean value and standard deviation of the background temperature and hot spot temperature, and combines multiple simulation experiments, which can realize comprehensive matching comparison for the normal distribution hot spot temperature, and greatly improves the detection accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0034] Figure 1 is a part structure schematic view of a hot spot detection system of a photovoltaic power station component provided in the embodiment of the present application;

[0035] Figure 2 is a flowchart of a hot spot detection method of a hot spot detection system of a photovoltaic power station component provided in the embodiment of the present application;

[0036] In the figure, 1 is a thermal imaging unmanned aerial vehicle, 2 is a photovoltaic module array, and 3 is a preset path. DETAILED DESCRIPTION

[0037] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some but not all of the embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations.

[0038] Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but only represents selected embodiments of the application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0039] It should be noted that similar reference numerals and letters refer to similar items in the following drawings, and therefore, once an item is defined in one drawing, it need not be further defined and explained in subsequent drawings.

[0040] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the present application is usually placed, and are only for the convenience of describing the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the indicated device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application.

[0041] It should be noted that the terms "first", "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0042] In addition, the terms "horizontal", "vertical" and the like do not mean that the components must be absolutely horizontal or vertical, but can be slightly inclined. For example, "horizontal" only means that its direction is relatively more horizontal than "vertical", and does not mean that the structure must be completely horizontal, but can be slightly inclined.

[0043] Embodiment 1

[0044] As shown in Figure 1 The present embodiment provides a hot spot detection system for a photovoltaic power station assembly, comprising:

[0045] The photovoltaic module array 2 comprises a plurality of photovoltaic modules distributed in an array form;

[0046] The thermal imaging unmanned aerial vehicle 1 comprises a unmanned aerial vehicle body, and the unmanned aerial vehicle body is provided with an infrared thermal imaging camera; the unmanned aerial vehicle body patrols the photovoltaic module according to a preset path 3, the preset path is set based on the distribution position of the photovoltaic module, and a plurality of route points are arranged on the preset path, and each route point corresponds to the position of each photovoltaic module; in the process of the patrol, when the corresponding route point is reached, the infrared thermal imaging camera is used to collect the thermal imaging image of the surface of the corresponding photovoltaic module.

[0047] The host computer is used to receive the thermal imaging image collected by the thermal imaging unmanned aerial vehicle, analyze the thermal imaging image by using an image processing algorithm, identify the temperature abnormal area, and determine whether there is a hot spot according to a preset hot spot detection threshold; if there is a hot spot, the position of the photovoltaic module is determined according to the route point corresponding to the thermal imaging image, and an alarm information is sent.

[0048] Specifically, in the process of image collection by the infrared thermal imaging camera, the distance between the infrared thermal imaging camera and the photovoltaic module is within the range of 5-12 m, so that close-range aerial photography is realized; in the embodiment, the infrared thermal imaging camera performs aerial photography on the photovoltaic module at a height of 10 m.

[0049] The preset path covers the whole photovoltaic power station, and the route points are associated with the arrangement positions of the photovoltaic modules.

[0050] In the embodiment, the photovoltaic module array is in the form of a plurality of rows of photovoltaic modules arranged in parallel, and the preset path starts from one end of the photovoltaic module array and sequentially traverses the photovoltaic modules of each row.

[0051] Optionally, a gimbal support is arranged at the bottom of the unmanned aerial vehicle body, and the gimbal support is used to fix the infrared thermal imaging camera, so that the infrared thermal imaging camera can face the surface of the photovoltaic module.

[0052] When the thermal imaging unmanned aerial vehicle returns, aerial photography data is uploaded to the host computer, the host computer automatically analyzes the image, and filters the hot spot imaging position.

[0053] The thermal imaging camera can capture the temperature distribution of the surface of an object, and the hot spot area in the photovoltaic module usually shows local high temperature. By analyzing the temperature abnormality in the thermal image, the hot spot can be effectively identified according to the preset threshold.

[0054] The determination process of the above hot spot detection threshold comprises:

[0055] For the photovoltaic module, a heat balance equation is established, and the expression of the heat balance equation is:

[0056] Q sun +Q elec =Qrad +Q conv +Q cond

[0057] wherein Q sun is the heat absorbed by solar radiation, Q elec is the heat dissipated by electrical energy, Q rad is the heat dissipated by radiation, Q conv is the heat dissipated by convection, and Q cond is the heat dissipated by conduction.

[0058] According to the heat balance equation, the temperature of the photovoltaic module under normal operation and the temperature under the hot spot state are calculated, and the corresponding temperature distribution is expressed in the form of normal distribution.

[0059] The temperature distribution of the photovoltaic module under normal operation is taken as the background temperature, and the background mean and the background standard deviation of the corresponding normal distribution are determined. The temperature distribution of the photovoltaic module under the hot spot state is taken as the hot spot temperature, and the hot spot mean and the hot spot standard deviation of the corresponding normal distribution are determined.

[0060] According to the proportion value of the background mean and the background standard deviation to the hot spot mean and the hot spot standard deviation, the background mean and the background standard deviation are increased by a coefficient, so as to determine the hot spot detection threshold.

[0061] Specifically, the hot spot detection threshold is a normal distribution threshold, the mean of the normal distribution threshold is a*μ background , and the standard deviation is b*σ background , wherein μ background is the background mean, σ background is the background standard deviation, a is the mean coefficient, and b is the standard deviation coefficient.

[0062] Preferably, the hot spot detection threshold is determined by simulating the normal operation and the hot spot state of the photovoltaic module multiple times, and the mean coefficient and the standard deviation coefficient are determined.

[0063] In this embodiment, the hot spot temperature is subject to a normal distribution with μ of 65 degrees Celsius and σ of 5 degrees Celsius, the background temperature is subject to a normal distribution with μ of 42 degrees Celsius and σ of 2 degrees Celsius, and finally the hot spot detection threshold determined by 1000 times of simulation is subject to a normal distribution with μ of 42 degrees Celsius and σ of 6 degrees Celsius, and the detection accuracy is above 97%.

[0064] Preferably, the alarm information includes the position, the model, the running time and the thermal imaging image of the photovoltaic module.

[0065] As shown in FIG. Figure 2 , the embodiment also provides a hot spot detection method of a hot spot detection system of a photovoltaic power station module based on the above, comprising the following steps:

[0066] S1: according to the array distribution form of the photovoltaic module, a preset path is determined, and a plurality of route points are set to correspond to the positions of the photovoltaic modules one by one;

[0067] S2: the thermal imaging unmanned aerial vehicle is used to cruise the photovoltaic module according to the preset path, and when the corresponding route point is reached in the cruising process, the infrared thermal imaging camera is used to collect the thermal imaging image of the surface of the corresponding photovoltaic module;

[0068] S3: after returning, the thermal imaging image collected by the thermal imaging unmanned aerial vehicle is transmitted to the upper computer, in the upper computer, the image processing algorithm is used for analysis, the temperature abnormal area is recognized, and whether there is a hot spot is judged according to the preset hot spot detection threshold value, if there is a hot spot, the position of the photovoltaic module is determined according to the route point corresponding to the thermal imaging image, and an alarm information is sent, if no hot spot is found, the identification of other images is continued;

[0069] S4: the operation and maintenance personnel replace the hot spot component.

[0070] The above describes the preferred embodiments of the application in detail. It should be understood that those skilled in the art can make many modifications and changes without creative labor according to the concept of the application. Therefore, any technical solution obtained by logical analysis, reasoning or limited experiment on the basis of the prior art by those skilled in the art according to the concept of the application shall be within the protection scope determined by the claims.

Claims

1. A hot spot detection system for photovoltaic power station modules, characterized in that, include: A photovoltaic module array, comprising multiple photovoltaic modules arranged in an array; A thermal imaging drone includes a drone body equipped with an infrared thermal imaging camera. The drone body cruises a photovoltaic module along a preset path. The preset path is set based on the distribution location of the photovoltaic module and has multiple route points, each of which corresponds to the location of a photovoltaic module. During the cruise, when the corresponding route point is reached, the infrared thermal imaging camera acquires thermal images of the surface of the corresponding photovoltaic module. The host computer receives thermal imaging images collected by the thermal imaging drone, analyzes them using image processing algorithms, identifies areas of abnormal temperature, and determines whether hot spots exist based on a preset hot spot detection threshold. If hot spots are found, the location of the photovoltaic module is determined based on the route points corresponding to the thermal imaging image, and an alarm message is issued.

2. The hot spot detection system for photovoltaic power station modules according to claim 1, characterized in that, During the image acquisition process, the distance between the infrared thermal imaging camera and the photovoltaic module is within the range of 5-12m.

3. The hot spot detection system for photovoltaic power station modules according to claim 1, characterized in that, The bottom of the drone body is equipped with a gimbal bracket, which is used to fix the infrared thermal imaging camera.

4. The hot spot detection system for photovoltaic power station modules according to claim 1, characterized in that, The process of determining the hot spot detection threshold includes: For photovoltaic modules, a heat balance equation is established, and its expression is as follows: Q sun +Q elec =Q rad +Q conv +Q cond In the formula, Q sun Q absorbs heat from solar radiation. elec Q is the heat lost due to electrical energy. rad Q is the heat dissipated by radiation. conv To dissipate heat via convection, Q cond To conduct heat dissipation; Based on the heat balance equation, the temperature of the photovoltaic module under normal operation and the temperature under hot spot condition are calculated, and the corresponding temperature distribution is expressed in the form of a normal distribution. The temperature distribution of the photovoltaic module under normal operation is used as the background temperature, and the background mean and standard deviation of the corresponding normal distribution are determined; the temperature distribution of the photovoltaic module under hot spot condition is used as the hot spot temperature, and the hot spot mean and standard deviation of the corresponding normal distribution are determined. The hot spot detection threshold is determined by adding a coefficient to the background mean and background standard deviation based on the ratio of the background mean and background standard deviation to the hot spot mean and hot spot standard deviation.

5. The hot spot detection system for photovoltaic power station modules according to claim 4, characterized in that, The hot spot detection threshold is a normally distributed threshold with a mean of a*μ. background The standard deviation is b*σ background , where μ background σ is the background mean. background denoted as the background standard deviation, a as the mean coefficient, and b as the standard deviation coefficient.

6. The hot spot detection system for photovoltaic power station modules according to claim 5, characterized in that, The hot spot detection threshold is determined by performing multiple simulations on the normal operation of the photovoltaic module and the hot spot state, including the mean coefficient and standard deviation coefficient.

7. The hot spot detection system for photovoltaic power station modules according to claim 1, characterized in that, The alarm information includes the location, model, operating time, and thermal imaging image of the photovoltaic module.

8. The hot spot detection system for photovoltaic power station modules according to claim 1, characterized in that, After returning to base, the thermal imaging drone uploads the collected thermal images to the host computer.

9. A hot spot detection system for photovoltaic power station modules according to claim 1, characterized in that, The preset path fully covers the photovoltaic module array.

10. A hot spot detection method based on a hot spot detection system for photovoltaic power station modules as described in any one of claims 1-9, characterized in that, Includes the following steps: Based on the array distribution of photovoltaic modules, a preset path is determined, and multiple route points are set to correspond one-to-one with the location of each photovoltaic module. A thermal imaging drone cruises the photovoltaic modules along a preset path. During the cruise, when the corresponding route points are reached, thermal imaging images of the corresponding photovoltaic module surfaces are collected by an infrared thermal imaging camera. After returning to base, the thermal imaging images collected by the thermal imaging drone are transmitted to the host computer. The host computer uses image processing algorithms to analyze the images, identify areas with abnormal temperatures, and determine whether hot spots exist based on preset hot spot detection thresholds. If hot spots are found, the location of the photovoltaic modules is determined based on the route points corresponding to the thermal imaging images, and an alarm message is issued.

Images