Shielding identification method and system for photovoltaic module

Abstract

The invention relates to the technical field of photovoltaic modules, and particularly discloses a shielding identification method and system for a photovoltaic module, and the method comprises the steps: obtaining image data of the photovoltaic module, carrying out the graying processing of the image data of the photovoltaic module, obtaining a gray image of the photovoltaic module, and recognizing a shadow region of the photovoltaic module according to the gray image of the photovoltaic module; acquiring the illumination condition of the photovoltaic module, and determining the expected generating capacity of the current photovoltaic module according to the illumination condition of the photovoltaic module; acquiring the actual generating capacity of the current photovoltaic module, and performing abnormality judgment on the generating capacity of the photovoltaic module according to the actual generating capacity of the current photovoltaic module; and determining the influence degree of the shadow area on the photovoltaic module according to the abnormity judgment result of the photovoltaic module, and judging whether to carry out shielding alarm or not according to the influence degree of the shadow area on the photovoltaic module. By monitoring the image of the photovoltaic module, shadow shielding influencing power generation of the photovoltaic module is identified, shielding alarm is given in time, manpower resources are saved, and the detection efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of photovoltaic modules, and more specifically, to a method and system for identifying occlusion of photovoltaic modules. Background Art

[0002] With the continuous development of the photovoltaic industry and the increasing installed capacity of photovoltaic new energy, the gradual realization of digital operation of photovoltaic power plants has become an important breakthrough direction. The normal operation of photovoltaic modules is the basis for ensuring the continuous, stable and efficient power generation of photovoltaic power stations. Photovoltaic modules are the most numerous equipment in photovoltaic power stations. To ensure the normal operation of modules, it is necessary to monitor the operating status of the modules in a timely manner and issue early warnings in case of abnormal operating status, which can not only save operation and maintenance costs, but also greatly improve the work efficiency of operation and maintenance personnel, and enable operation and maintenance personnel to accurately and quickly find problematic modules.

[0003] Among the many factors that affect the power generation of photovoltaic power generation systems, shadowing is the most common one. Common blocking factors include natural and artificial obstructions, which can affect the light transmittance and reduce the amount of light radiation on the surface of the components. In severe cases, they can form hot spot effects in the components, affecting the power generation efficiency and service life of photovoltaic components, and even causing partial burning of components, forming permanent damage such as dark spots, which poses a safety hazard. Summary of the invention

[0004] The present invention provides a photovoltaic module shielding recognition method and system, which is used to solve the problem in the prior art that photovoltaic modules cannot timely issue warnings for shielding factors, including:

[0005] Acquire image data of the photovoltaic module, perform grayscale processing on the image data of the photovoltaic module to obtain a grayscale image of the photovoltaic module, and identify a shadow area of ​​the photovoltaic module according to the grayscale image of the photovoltaic module;

[0006] Obtain the lighting conditions of the photovoltaic modules, and determine the expected power generation of the current photovoltaic modules according to the lighting conditions of the photovoltaic modules;

[0007] Obtain the actual power generation of the current photovoltaic module, and make an abnormal judgment on the power generation of the photovoltaic module based on the actual power generation of the current photovoltaic module;

[0008] The influence degree of the shadow area on the photovoltaic module is determined according to the abnormal judgment result of the photovoltaic module, and whether to issue an obstruction alarm is determined according to the influence degree of the shadow area on the photovoltaic module.

[0009] Further, the identifying the shadow area of ​​the photovoltaic assembly according to the photovoltaic assembly grayscale image includes:

[0010] Performing histogram equalization processing on the photovoltaic module grayscale image, and obtaining a grayscale value histogram of the photovoltaic module grayscale image according to the processing result;

[0011] Draw a gray value change curve according to the gray value histogram of the gray image of the photovoltaic module, and count the maximum extreme value point and the minimum extreme value point of the gray value change curve;

[0012] The minimum value point closest to the maximum extreme value point is screened out, and the gray value of the minimum value point closest to the maximum extreme point is set as the maximum gray value threshold;

[0013] Get the current cloud thickness above the photovoltaic module and modify the maximum grayscale threshold according to the cloud thickness;

[0014] Pixels whose grayscale values ​​in the grayscale image of the photovoltaic module are less than the maximum grayscale threshold are screened out to obtain the shadow area of ​​the photovoltaic module.

[0015] Furthermore, the correcting the maximum grayscale threshold according to the cloud thickness includes: correcting the maximum grayscale threshold according to a maximum grayscale threshold correction formula, wherein the maximum grayscale threshold correction formula is specifically:

[0016]

[0017] Among them, G p is the maximum grayscale threshold after correction, G max is the maximum grayscale threshold, H α is the preset cloud thickness, H is the current cloud thickness above the PV module, R is the preset range coefficient, and exp is the natural exponential function.

[0018] Furthermore, determining the expected power generation of the current photovoltaic assembly according to the illumination condition of the photovoltaic assembly includes:

[0019] Obtain historical lighting conditions and corresponding power generation of photovoltaic modules, and establish historical lighting condition data sets and power generation data sets based on the historical lighting conditions and corresponding power generation of photovoltaic modules;

[0020] Preprocessing the historical lighting condition data set and the power generation data set to obtain a preprocessed historical lighting condition data set and a power generation data set;

[0021] An initial power generation prediction model is established, and the initial power generation prediction model is trained according to the preprocessed historical light condition data set and power generation data set to obtain a trained power generation prediction model;

[0022] The current lighting conditions of the photovoltaic module are input into the trained power generation prediction model to obtain the expected power generation of the current photovoltaic module.

[0023] Furthermore, the abnormality judgment of the power generation of the photovoltaic assembly according to the actual power generation of the current photovoltaic assembly includes:

[0024] The difference between the expected power generation and the actual power generation is calculated based on the actual power generation of the current photovoltaic module to obtain the power generation deviation, and the difference between the power generation deviation and the preset allowable power generation deviation is calculated;

[0025] Determine whether the difference between the power generation deviation and the preset allowable power generation deviation is greater than a first preset threshold value, and if the difference between the power generation deviation and the preset allowable power generation deviation is greater than the first preset threshold value, determine that the photovoltaic module is abnormal;

[0026] If the difference between the power generation deviation and the preset allowable power generation deviation is less than or equal to the first preset threshold, determining whether the difference between the power generation deviation and the preset allowable power generation deviation is greater than the second preset threshold;

[0027] If the difference between the power generation deviation and the preset allowable power generation deviation is greater than a second preset threshold, it is determined that the photovoltaic component is suspected to be abnormal;

[0028] If the difference between the power generation deviation and the preset allowable power generation deviation is less than or equal to the second preset threshold, it is determined that there is no abnormality in the photovoltaic component.

[0029] Furthermore, the step of determining the degree of influence of the shadow area on the photovoltaic module according to the abnormality judgment result of the photovoltaic module includes:

[0030] Calculate the area of ​​the shadow area according to the shadow area of ​​the photovoltaic module, detect the change of the shadow area in real time, and draw a shadow area change curve according to the change of the shadow area;

[0031] Perform curve fitting on the shadow area change curve, and predict the time required for the shadow area to reach the shadow impact threshold according to the curve fitting result;

[0032] The time required for the shadow area to reach the shadow impact threshold is set as the impact of the shadow area on the photovoltaic module.

[0033] Furthermore, judging whether to issue a shading alarm according to the degree of influence of the shadow area on the photovoltaic module includes:

[0034] A shadow impact threshold is set according to the abnormal judgment result of the photovoltaic module. If the time required for the shadow area to reach the shadow impact threshold is less than a third preset threshold, a photovoltaic module shading alarm is issued;

[0035] If the time required for the shadow area to reach the shadow impact threshold is greater than or equal to the third preset threshold, no photovoltaic component shading alarm is issued.

[0036] Furthermore, the setting of the shadow impact threshold according to the abnormality judgment result of the photovoltaic module includes:

[0037] Obtain a first shadow influence threshold, a second shadow influence threshold, and a third shadow influence threshold, and set the first shadow influence threshold < the second shadow influence threshold < the third shadow influence threshold;

[0038] When the abnormality judgment result of the photovoltaic component is that an abnormality exists, setting a first shadow influence threshold as the shadow influence threshold of the photovoltaic component;

[0039] When the abnormality judgment result of the photovoltaic component is suspected to be abnormal, setting the second shadow influence threshold as the shadow influence threshold of the photovoltaic component;

[0040] When the abnormality determination result of the photovoltaic assembly is that there is no abnormality, the third shadow influence threshold is set as the shadow influence threshold of the photovoltaic assembly.

[0041] In order to achieve the above object, the present invention further provides a photovoltaic module shielding recognition system, comprising:

[0042] The first module is used to obtain image data of the photovoltaic module, perform grayscale processing on the image data of the photovoltaic module to obtain a grayscale image of the photovoltaic module, and identify a shadow area of ​​the photovoltaic module according to the grayscale image of the photovoltaic module;

[0043] The second module is used to obtain the lighting conditions of the photovoltaic components and determine the expected power generation of the current photovoltaic components according to the lighting conditions of the photovoltaic components;

[0044] The third module is used to obtain the actual power generation of the current photovoltaic module and make an abnormal judgment on the power generation of the photovoltaic module according to the actual power generation of the current photovoltaic module;

[0045] The fourth module is used to determine the influence of the shadow area on the photovoltaic module according to the abnormal judgment result of the photovoltaic module, and determine whether to issue an obstruction alarm according to the influence of the shadow area on the photovoltaic module.

[0046] The beneficial effects of the present invention are:

[0047] By applying the above technical scheme, the present invention can accurately identify the shadow area blocked by the photovoltaic module through processing the image data of the photovoltaic module, effectively eliminate the influence of cloudy weather on the identification of the shadow area of ​​the photovoltaic module, and at the same time, timely issue an occlusion alarm according to the influence of the shadow area on the photovoltaic module. The inspection can be completed without a lot of manpower, thereby ensuring the normal operation of the photovoltaic module and providing more accurate and comprehensive decision-making information for the operation and maintenance of the photovoltaic module. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 The overall flow chart of a photovoltaic module shielding identification method proposed in an embodiment of the present invention is shown;

[0050] Figure 2 A schematic structural diagram of a photovoltaic module shielding recognition system proposed in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0052] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0053] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0054] The present application embodiment provides a method for identifying shading of a photovoltaic module, such as Figure 1 As shown, including:

[0055] S101, acquiring image data of a photovoltaic module, performing grayscale processing on the image data of the photovoltaic module to obtain a grayscale image of the photovoltaic module, and identifying a shadow area of ​​the photovoltaic module according to the grayscale image of the photovoltaic module;

[0056] In some embodiments of the present application, the method of identifying the shadow area of ​​a photovoltaic module based on a grayscale image of a photovoltaic module includes: performing histogram equalization processing on the grayscale image of the photovoltaic module, and obtaining a grayscale value histogram of the grayscale image of the photovoltaic module based on the processing result; drawing a grayscale value change curve based on the grayscale value histogram of the grayscale image of the photovoltaic module, and counting the maximum extreme value point and the minimum extreme value point of the grayscale value change curve; screening out the minimum value point closest to the maximum extreme value point, and setting the grayscale value of the minimum value point closest to the maximum extreme value point as the maximum grayscale threshold; obtaining the cloud thickness above the current photovoltaic module, and correcting the maximum grayscale threshold according to the cloud thickness; screening out pixel points in the grayscale image of the photovoltaic module whose grayscale values ​​are less than the maximum grayscale threshold, and obtaining the shadow area of ​​the photovoltaic module.

[0057] In this embodiment, the images of the photovoltaic modules are captured by camera groups arranged at multiple positions in the photovoltaic power station, and the image data of the photovoltaic modules are obtained by fusing the overlapping areas of the images of the photovoltaic modules.

[0058] In this embodiment, the contrast between the shadow area and the illuminated area of ​​the photovoltaic panel is enhanced by performing histogram equalization processing on the grayscale image of the photovoltaic module. The maximum extreme point of the histogram is the dropped object on the photovoltaic panel, and the grayscale value of the minimum point closest to the maximum extreme point is the maximum grayscale value of the occluding shadow projected on the photovoltaic module. The maximum grayscale threshold is corrected by the cloud thickness to obtain the shadow area of ​​the photovoltaic module.

[0059] In some embodiments of the present application, the correction of the maximum grayscale threshold according to the cloud thickness includes: correcting the maximum grayscale threshold according to a maximum grayscale threshold correction formula, wherein the maximum grayscale threshold correction formula is specifically:

[0060]

[0061] Among them, G p is the maximum grayscale threshold after correction, G max is the maximum grayscale threshold, H α is the preset cloud thickness, H is the current cloud thickness above the PV module, R is the preset range coefficient, and exp is the natural exponential function.

[0062] In this embodiment, the maximum grayscale threshold is corrected based on the maximum grayscale threshold correction formula according to the cloud thickness, so as to prevent the illuminated part of the photovoltaic panel with a lower grayscale value from being mistakenly identified as the shadow of an obstruction when the grayscale value of the photovoltaic panel is reduced due to cloud cover, thereby achieving accurate identification of the shadow part.

[0063] S102, obtaining the lighting conditions of the photovoltaic modules, and determining the expected power generation of the current photovoltaic modules according to the lighting conditions of the photovoltaic modules;

[0064] In some embodiments of the present application, determining the expected power generation of the current photovoltaic component based on the lighting conditions of the photovoltaic component includes: obtaining the historical lighting conditions and the corresponding power generation of the photovoltaic component, and establishing a historical lighting condition data set and a power generation data set based on the historical lighting conditions and the corresponding power generation of the photovoltaic component; preprocessing the historical lighting condition data set and the power generation data set to obtain a preprocessed historical lighting condition data set and a power generation data set; establishing an initial power generation prediction model, and training the initial power generation prediction model based on the preprocessed historical lighting condition data set and the power generation data set to obtain a trained power generation prediction model; and inputting the lighting conditions of the current photovoltaic component into the trained power generation prediction model to obtain the expected power generation of the current photovoltaic component.

[0065] In this embodiment, the lighting condition of the photovoltaic module is the light intensity of the environment surrounding the photovoltaic module. An initial power generation prediction model of the photovoltaic module is established based on a deep learning neural network model, and the prediction model is trained through a data set consisting of historical lighting conditions and corresponding power generation to obtain a trained power generation prediction model. By inputting the light intensity of the current environment surrounding the photovoltaic module into the trained power generation prediction model, the expected power generation can be predicted.

[0066] S103, obtaining the actual power generation of the current photovoltaic assembly, and judging the power generation of the photovoltaic assembly as abnormal according to the actual power generation of the current photovoltaic assembly;

[0067] In some embodiments of the present application, the abnormality judgment of the power generation of the photovoltaic module based on the actual power generation of the current photovoltaic module includes: calculating the difference between the expected power generation and the actual power generation based on the actual power generation of the current photovoltaic module to obtain the power generation deviation, and calculating the difference between the power generation deviation and the preset allowable power generation deviation; judging whether the difference between the power generation deviation and the preset allowable power generation deviation is greater than a first preset threshold value, if the difference between the power generation deviation and the preset allowable power generation deviation is greater than the first preset threshold value, determining that there is an abnormality in the photovoltaic module; if the difference between the power generation deviation and the preset allowable power generation deviation is less than or equal to the first preset threshold value, judging whether the difference between the power generation deviation and the preset allowable power generation deviation is greater than the second preset threshold value; if the difference between the power generation deviation and the preset allowable power generation deviation is greater than the second preset threshold value, judging that there is a suspected abnormality in the photovoltaic module; if the difference between the power generation deviation and the preset allowable power generation deviation is less than or equal to the second preset threshold value, judging that there is no abnormality in the photovoltaic module.

[0068] In this embodiment, the abnormal state of the photovoltaic module is judged based on the difference between the power generation deviation and the preset allowable power generation deviation. When the power generation deviation is too large, it is determined that the current photovoltaic module is abnormal or suspected to be abnormal, which facilitates the subsequent calculation of the impact degree of the shadow area.

[0069] S104, determining the influence degree of the shadow area on the photovoltaic assembly according to the abnormal judgment result of the photovoltaic assembly, and determining whether to issue an obstruction alarm according to the influence degree of the shadow area on the photovoltaic assembly.

[0070] In some embodiments of the present application, the method of determining the degree of influence of the shadow area on the photovoltaic module based on the abnormal judgment result of the photovoltaic module includes: calculating the area of ​​the shadow area based on the shadow area of ​​the photovoltaic module, detecting the change of the area of ​​the shadow area in real time, and drawing a shadow area change curve according to the change of the area of ​​the shadow area; performing curve fitting on the shadow area change curve, and predicting the time required for the area of ​​the shadow area to reach the shadow influence threshold according to the curve fitting result; and setting the time required for the area of ​​the shadow area to reach the shadow influence threshold as the degree of influence of the shadow area on the photovoltaic module.

[0071] In this embodiment, the shadow area of ​​the photovoltaic module is monitored in real time to obtain the shadow area change curve, and the shadow area change curve is linearly fitted based on the least squares method to predict the future change trend of the shadow area. The degree of influence of the shadow area on the photovoltaic module is calculated according to the time required for the shadow area to reach the shadow influence threshold.

[0072] In some embodiments of the present application, the method of judging whether to issue an occlusion alarm based on the degree of influence of the shadow area on the photovoltaic module includes: setting a shadow influence threshold according to the abnormal judgment result of the photovoltaic module, and if the time required for the shadow area to reach the shadow influence threshold is less than a third preset threshold, a photovoltaic module occlusion alarm is issued; if the time required for the shadow area to reach the shadow influence threshold is greater than or equal to the third preset threshold, no photovoltaic module occlusion alarm is issued.

[0073] In this embodiment, a shading alarm is issued based on the time required for the shadow area to reach the shadow impact threshold. When the time required for the shadow impact threshold is too low, a shading alarm is issued in time to ensure the normal operation of the photovoltaic module.

[0074] In some embodiments of the present application, the shadow impact threshold is set according to the abnormal judgment result of the photovoltaic component, including: obtaining a first shadow impact threshold, a second shadow impact threshold, and a third shadow impact threshold, and setting the first shadow impact threshold < the second shadow impact threshold < the third shadow impact threshold; when the abnormal judgment result of the photovoltaic component is that an abnormality exists, setting the first shadow impact threshold as the shadow impact threshold of the photovoltaic component; when the abnormal judgment result of the photovoltaic component is that an abnormality is suspected to exist, setting the second shadow impact threshold as the shadow impact threshold of the photovoltaic component; when the abnormal judgment result of the photovoltaic component is that there is no abnormality, setting the third shadow impact threshold as the shadow impact threshold of the photovoltaic component.

[0075] In this embodiment, a shadow impact threshold is set based on the abnormal judgment result of the photovoltaic component. The higher the probability of abnormality of the photovoltaic component, the lower the set shadow impact threshold is, and the easier it is for an occlusion alarm to occur. The occlusion abnormality of the photovoltaic component can be promptly alarmed to ensure the normal operation of the photovoltaic component.

[0076] Based on the same technical concept, such as Figure 2 As shown, the present invention also provides a photovoltaic module shielding recognition system, comprising:

[0077] The first module is used to obtain image data of photovoltaic modules, grayscale the image data of photovoltaic modules to obtain grayscale images of photovoltaic modules, and identify shadow areas of photovoltaic modules based on the grayscale images of photovoltaic modules; the second module is used to obtain lighting conditions of photovoltaic modules, and determine the expected power generation of current photovoltaic modules based on the lighting conditions of photovoltaic modules; the third module is used to obtain the actual power generation of current photovoltaic modules, and make abnormal judgments on the power generation of photovoltaic modules based on the actual power generation of current photovoltaic modules; the fourth module is used to determine the degree of influence of shadow areas on photovoltaic modules based on the abnormal judgment results of photovoltaic modules, and judge whether to issue an occlusion alarm based on the degree of influence of shadow areas on photovoltaic modules.

[0078] By applying the above technical scheme, the present invention obtains the image data of the photovoltaic module, grayscales the image data of the photovoltaic module, obtains the grayscale image of the photovoltaic module, identifies the shadow area of ​​the photovoltaic module according to the grayscale image of the photovoltaic module; obtains the lighting conditions of the photovoltaic module, determines the expected power generation of the current photovoltaic module according to the lighting conditions of the photovoltaic module; obtains the actual power generation of the current photovoltaic module, and makes an abnormal judgment on the power generation of the photovoltaic module according to the actual power generation of the current photovoltaic module; determines the degree of influence of the shadow area on the photovoltaic module according to the abnormal judgment result of the photovoltaic module, and judges whether to issue an occlusion alarm according to the degree of influence of the shadow area on the photovoltaic module. By monitoring the image of the photovoltaic module, the shadow occlusion that affects the power generation of the photovoltaic module can be identified, and the occlusion alarm can be issued in time, saving human resources and improving detection efficiency.

[0079] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present invention.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for identifying shading of a photovoltaic module, characterized in that: The method comprises: Acquire image data of the photovoltaic module, perform grayscale processing on the image data of the photovoltaic module to obtain a grayscale image of the photovoltaic module, and identify a shadow area of ​​the photovoltaic module according to the grayscale image of the photovoltaic module; Obtain the lighting conditions of the photovoltaic modules, and determine the expected power generation of the current photovoltaic modules according to the lighting conditions of the photovoltaic modules; Obtain the actual power generation of the current photovoltaic module, and make an abnormal judgment on the power generation of the photovoltaic module based on the actual power generation of the current photovoltaic module; The influence degree of the shadow area on the photovoltaic module is determined according to the abnormal judgment result of the photovoltaic module, and whether to issue an obstruction alarm is determined according to the influence degree of the shadow area on the photovoltaic module.

2. The photovoltaic module shading identification method according to claim 1, characterized in that: The step of identifying the shadow area of ​​the photovoltaic assembly according to the photovoltaic assembly grayscale image comprises: Performing histogram equalization processing on the photovoltaic module grayscale image, and obtaining a grayscale value histogram of the photovoltaic module grayscale image according to the processing result; Draw a gray value change curve according to the gray value histogram of the gray image of the photovoltaic module, and count the maximum extreme value point and the minimum extreme value point of the gray value change curve; The minimum value point closest to the maximum extreme value point is screened out, and the gray value of the minimum value point closest to the maximum extreme point is set as the maximum gray value threshold; Get the current cloud thickness above the photovoltaic module and modify the maximum grayscale threshold according to the cloud thickness; Pixels whose grayscale values ​​in the grayscale image of the photovoltaic module are less than the maximum grayscale threshold are screened out to obtain the shadow area of ​​the photovoltaic module.

3. The photovoltaic module shading identification method according to claim 2, characterized in that: The method of correcting the maximum grayscale threshold according to the cloud thickness includes: The maximum grayscale threshold is corrected according to the maximum grayscale threshold correction formula, and the maximum grayscale threshold correction formula is specifically: Among them, G p is the maximum grayscale threshold after correction, G max is the maximum grayscale threshold, H α is the preset cloud thickness, H is the current cloud thickness above the PV module, R is the preset range coefficient, and exp is the natural exponential function.

4. The photovoltaic module shading identification method according to claim 1, characterized in that: The method of determining the expected power generation of the current photovoltaic assembly according to the illumination conditions of the photovoltaic assembly includes: Obtain historical lighting conditions and corresponding power generation of photovoltaic modules, and establish historical lighting condition data sets and power generation data sets based on the historical lighting conditions and corresponding power generation of photovoltaic modules; Preprocessing the historical lighting condition data set and the power generation data set to obtain a preprocessed historical lighting condition data set and a power generation data set; An initial power generation prediction model is established, and the initial power generation prediction model is trained according to the preprocessed historical light condition data set and power generation data set to obtain a trained power generation prediction model; The current lighting conditions of the photovoltaic module are input into the trained power generation prediction model to obtain the expected power generation of the current photovoltaic module.

5. The photovoltaic module shielding identification method according to claim 4, characterized in that: The abnormality judgment of the power generation of the photovoltaic module according to the actual power generation of the current photovoltaic module includes: The difference between the expected power generation and the actual power generation is calculated based on the actual power generation of the current photovoltaic module to obtain the power generation deviation, and the difference between the power generation deviation and the preset allowable power generation deviation is calculated; Determine whether the difference between the power generation deviation and the preset allowable power generation deviation is greater than a first preset threshold value, and if the difference between the power generation deviation and the preset allowable power generation deviation is greater than the first preset threshold value, determine that the photovoltaic module is abnormal; If the difference between the power generation deviation and the preset allowable power generation deviation is less than or equal to the first preset threshold, determining whether the difference between the power generation deviation and the preset allowable power generation deviation is greater than the second preset threshold; If the difference between the power generation deviation and the preset allowable power generation deviation is greater than a second preset threshold, it is determined that the photovoltaic component is suspected to be abnormal; If the difference between the power generation deviation and the preset allowable power generation deviation is less than or equal to the second preset threshold, it is determined that there is no abnormality in the photovoltaic component.

6. The photovoltaic module shielding identification method according to claim 5, characterized in that: The step of determining the influence of the shadow area on the photovoltaic module according to the abnormality judgment result of the photovoltaic module includes: Calculate the area of ​​the shadow area according to the shadow area of ​​the photovoltaic module, detect the change of the shadow area in real time, and draw a shadow area change curve according to the change of the shadow area; Perform curve fitting on the shadow area change curve, and predict the time required for the shadow area to reach the shadow impact threshold according to the curve fitting result; The time required for the shadow area to reach the shadow impact threshold is set as the impact of the shadow area on the photovoltaic module.

7. The photovoltaic module shielding identification method according to claim 6, characterized in that: The determining whether to issue a shading alarm according to the degree of influence of the shadow area on the photovoltaic module includes: A shadow impact threshold is set according to the abnormal judgment result of the photovoltaic module. If the time required for the shadow area to reach the shadow impact threshold is less than a third preset threshold, a photovoltaic module shading alarm is issued; If the time required for the shadow area to reach the shadow impact threshold is greater than or equal to the third preset threshold, no photovoltaic component shading alarm is issued.

8. The photovoltaic module shielding identification method according to claim 7, characterized in that: The step of setting the shadow impact threshold according to the abnormality judgment result of the photovoltaic module includes: Obtain a first shadow influence threshold, a second shadow influence threshold, and a third shadow influence threshold, and set the first shadow influence threshold < the second shadow influence threshold < the third shadow influence threshold; When the abnormality judgment result of the photovoltaic component is that an abnormality exists, setting a first shadow influence threshold as the shadow influence threshold of the photovoltaic component; When the abnormality judgment result of the photovoltaic component is suspected to be abnormal, setting the second shadow influence threshold as the shadow influence threshold of the photovoltaic component; When the abnormality determination result of the photovoltaic assembly is that there is no abnormality, the third shadow influence threshold is set as the shadow influence threshold of the photovoltaic assembly.

9. A photovoltaic module shading recognition system, characterized in that: include: The first module is used to obtain image data of the photovoltaic module, perform grayscale processing on the image data of the photovoltaic module to obtain a grayscale image of the photovoltaic module, and identify a shadow area of ​​the photovoltaic module according to the grayscale image of the photovoltaic module; The second module is used to obtain the lighting conditions of the photovoltaic components and determine the expected power generation of the current photovoltaic components according to the lighting conditions of the photovoltaic components; The third module is used to obtain the actual power generation of the current photovoltaic module and make an abnormal judgment on the power generation of the photovoltaic module according to the actual power generation of the current photovoltaic module; The fourth module is used to determine the influence of the shadow area on the photovoltaic module according to the abnormal judgment result of the photovoltaic module, and determine whether to issue an obstruction alarm according to the influence of the shadow area on the photovoltaic module.

Images