Pollutant identification and cleaning method, device and equipment for photovoltaic power station and medium

Abstract

The invention discloses a pollutant identifying and cleaning method, device and equipment for a photovoltaic power station and a medium, is applied to the field of photovoltaic technology, and solves the problem that the pollutant condition of a photovoltaic module cannot be accurately identified in the pollutant cleaning process of the photovoltaic power station in the prior art. The method comprises the following steps: acquiring predicted total active power data, actual total active power data, actual environment temperature data and actual solar altitude data of a photovoltaic inverter to be analyzed in a preset time period; according to the predicted total active power data, the actual total active power data, the actual environment temperature data and the actual solar altitude data in the preset time period, determining the type of a reason for reducing the total active power of the photovoltaic inverter to be analyzed; and under the condition that the reason category is pollutant accumulation, the photovoltaic module connected to the to-be-analyzed photovoltaic inverter is determined as the to-be-cleaned photovoltaic module, so that accurate positioning of the to-be-cleaned photovoltaic module is realized, and improvement of cleaning efficiency and saving of cleaning cost and water resources are facilitated.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic technology, and in particular to a pollutant identification and cleaning method, device, electronic equipment and computer-readable storage medium for a photovoltaic power station. Background Art

[0002] Currently, daily management of power plant operations can be carried out based on power plant inverter data. For example, by using drones equipped with high-definition cameras, infrared sensors and other equipment, high-definition images and temperature distribution data can be obtained to promptly detect problems such as component failures and pollutant accumulation.

[0003] In the related art, when identifying contamination of photovoltaic modules by pollutants, one method is to install pollutant detection equipment on individual photovoltaic modules in the photovoltaic power station. On the one hand, the equipment cost is high. On the other hand, due to the uneven distribution of pollution in photovoltaic modules, the pollution status of individual photovoltaic modules installed with pollutant detection equipment cannot represent the pollution status of the entire photovoltaic power station modules. Another method is to obtain large-scale visible light images during the whole-station inspection by drones, and perform component-free task analysis on the visible light images obtained during these inspections. Due to the wide range and high flight altitude of the whole-station inspection, it is difficult to accurately identify the accumulation of pollutants in photovoltaic modules through the visible light images obtained during the inspection. Since the related art cannot accurately identify the accumulation of pollutants in photovoltaic modules, it is impossible to accurately locate which photovoltaic modules need to be cleaned. Therefore, in order to make the cleaning more complete, a whole-station cleaning method will be adopted. Whole-station cleaning not only has low cleaning efficiency, but also leads to a waste of cleaning costs and water resources.

[0004] In view of this, how to improve the accuracy of pollutant identification in photovoltaic power plants and improve the effectiveness of pollutant cleaning has become a problem that needs to be solved by those skilled in the art. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide a pollutant identification and cleaning method, device, electronic device and computer-readable storage medium for a photovoltaic power station, which can accurately locate the photovoltaic components to be cleaned during use, so as to achieve small-scale fixed-point cleaning of the photovoltaic components to be cleaned, which is conducive to improving cleaning efficiency and saving cleaning costs and water resources.

[0006] To solve the above technical problems, the embodiments of the present invention provide the following technical solutions:

[0007] In one aspect, the present invention provides a method for identifying and cleaning pollutants in a photovoltaic power station, comprising:

[0008] Acquiring predicted total active power data of the photovoltaic inverter to be analyzed within a preset time period, and acquiring actual total active power data, actual ambient temperature data, and actual solar altitude angle data of the photovoltaic inverter to be analyzed within the preset time period;

[0009] Determining a cause category of a decrease in total active power of the photovoltaic inverter to be analyzed based on the predicted total active power data, the actual total active power data, the actual ambient temperature data, and the actual solar altitude angle data within the preset time period;

[0010] When the cause category is accumulation of pollutants, it is determined that the photovoltaic assembly connected to the photovoltaic inverter to be analyzed is a photovoltaic assembly to be cleaned, so as to clean the pollutants from the photovoltaic assembly to be cleaned.

[0011] In one embodiment, determining the cause category of the total active power reduction of the photovoltaic inverter to be analyzed based on the predicted total active power data, the actual total active power data, the actual ambient temperature data, and the actual solar altitude angle data within the preset time period includes:

[0012] Determining, based on the predicted total active power data and the actual total active power data within the preset time period, an absolute error between the predicted total active power value at each moment and the corresponding actual total active power value;

[0013] determining an absolute error growth rate according to a curve of the predicted total active power data and a curve of the actual total active power data;

[0014] If the absolute errors at each moment fluctuate positively or negatively, and the absolute value of the first Pearson correlation parameter between the curve of the actual total active power data and the curve of the actual ambient temperature data is greater than or equal to a preset threshold, the cause category is meteorological influence;

[0015] When the absolute value of the second Pearson correlation parameter between the curve of the actual total active power data and the curve of the actual sun altitude angle data is greater than or equal to the preset threshold, the cause category is shadow obstruction;

[0016] If, among the absolute error growth rates at various moments, the absolute error growth rates at various moments after the first moment are all greater than a first preset percentage, the cause category is a photovoltaic system failure;

[0017] When the absolute error growth rate at each moment is less than the first preset percentage, the cause category is pollutant accumulation.

[0018] In one embodiment, when the cause category is pollutant accumulation, determining that the photovoltaic assembly connected to the photovoltaic inverter to be analyzed is the photovoltaic assembly to be cleaned includes:

[0019] If the cause category includes only pollutant accumulation, and it is determined based on the predicted total active power data that the total active power percentage of the photovoltaic inverter to be analyzed has decreased to a second preset percentage, sending a task verification instruction to a drone carrying an image acquisition device; the task verification instruction includes geographic location information of the photovoltaic modules connected to the photovoltaic inverter to be analyzed;

[0020] Acquire a visible light image related to the photovoltaic component acquired by the drone through the image acquisition device;

[0021] performing image analysis on the visible light image to determine weight information of pollutants in the photovoltaic module;

[0022] When it is determined based on the pollutant weight information that the accumulated pollutant weight reaches a limited pollutant accumulated weight value, the photovoltaic assembly is determined to be a photovoltaic assembly to be cleaned.

[0023] In one embodiment, performing image analysis on the visible light image to determine the weight information of the pollutants in the photovoltaic module includes:

[0024] The visible light image is analyzed using a pre-established pollutant accumulation degree identification model to obtain a pollutant weight level; wherein the pollutant accumulation degree identification model is trained based on a historical pollutant weight dataset of photovoltaic modules connected to each photovoltaic inverter and historical sample visible light images of the corresponding photovoltaic modules.

[0025] In one embodiment, obtaining predicted total active power data of the photovoltaic inverter to be analyzed within a preset time period includes:

[0026] For each moment in the preset time period, the predicted PV module irradiance at the current moment is determined based on the current time, the latitude of the PV power station to be analyzed, the tilt angle of the PV modules, and the azimuth angle of the PV module array;

[0027] Obtaining a predicted total active power value of the photovoltaic inverter to be analyzed at the current moment based on the predicted photovoltaic module irradiance at the current moment, the rated power of the photovoltaic module connected to the photovoltaic inverter to be analyzed under standard test conditions, the module irradiance under standard test conditions, the relationship coefficient between module power and temperature, the photovoltaic operating temperature under standard test conditions, and the predicted implementation ambient temperature;

[0028] The predicted total active power data of the photovoltaic inverter to be analyzed within the preset time period is obtained according to the predicted total active power values corresponding to each moment within the preset time period.

[0029] In one embodiment, determining the predicted photovoltaic module irradiance at the current moment based on the current time, the latitude of the photovoltaic power station to be analyzed, the photovoltaic module inclination angle, and the photovoltaic module azimuth angle includes:

[0030] The predicted photovoltaic module irradiance at the current moment is determined based on the current time, the latitude of the photovoltaic power station to be analyzed, the photovoltaic module inclination, and the azimuth of the photovoltaic module array in combination with the first calculation formula, where the first calculation formula is:

[0031] ; ;

[0032] ;

[0033] Among them, AM is the air quality coefficient, is the solar altitude angle, G T is the predicted value of the module irradiance at time T, β is the tilt angle of the photovoltaic module, is the azimuth angle of the photovoltaic array, C F is the correlation factor, is the declination angle, is the latitude of the photovoltaic power station, is the solar hour angle.

[0034] In one embodiment, after determining that the photovoltaic assembly connected to the photovoltaic inverter to be analyzed is a photovoltaic assembly to be cleaned, the method further includes:

[0035] The geographical location information of the photovoltaic assembly to be cleaned is sent to a cleaning drone, so that the cleaning drone performs a task of cleaning the photovoltaic assembly to be cleaned based on the geographical location information.

[0036] An embodiment of the present invention further provides a pollutant identification and cleaning device for a photovoltaic power station, comprising:

[0037] an acquisition module, configured to acquire predicted total active power data of the photovoltaic inverter to be analyzed within a preset time period, and to acquire actual total active power data, actual ambient temperature data, and actual solar altitude angle data of the photovoltaic inverter to be analyzed within the preset time period;

[0038] a first determining module, configured to determine a cause category of a total active power reduction of the photovoltaic inverter to be analyzed based on the predicted total active power data, the actual total active power data, the actual ambient temperature data, and the actual solar altitude angle data within the preset time period;

[0039] The second determining module is configured to determine, when the cause category is pollutant accumulation, that the photovoltaic assembly connected to the photovoltaic inverter to be analyzed is a photovoltaic assembly to be cleaned, so as to clean the pollutants from the photovoltaic assembly to be cleaned.

[0040] An embodiment of the present invention further provides an electronic device, including:

[0041] memory for storing computer programs;

[0042] The processor is configured to implement the steps of the above-mentioned method for identifying and cleaning pollutants in a photovoltaic power station when executing the computer program.

[0043] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the pollutant identification and cleaning method for a photovoltaic power station as described above are implemented.

[0044] It can be seen from the above technical solutions that the embodiments of the present invention have the following advantages:

[0045] In an embodiment of the present invention, a pollutant identification and cleaning method for a photovoltaic power station is provided, comprising: obtaining predicted total active power data of a photovoltaic inverter to be analyzed within a preset time period, and obtaining actual total active power data, actual ambient temperature data, and actual solar altitude angle data of the photovoltaic inverter to be analyzed within the preset time period; determining a cause category for a reduction in total active power of the photovoltaic inverter to be analyzed based on the predicted total active power data, the actual total active power data, the actual ambient temperature data, and the actual solar altitude angle data within the preset time period; and when the cause category is pollutant accumulation, determining that a photovoltaic module connected to the photovoltaic inverter to be analyzed is a photovoltaic module to be cleaned, so that pollutants in the photovoltaic module to be cleaned are cleaned.

[0046] It can be seen that in this application, by obtaining the predicted total active power data, actual total active power data, actual ambient temperature data and actual solar altitude angle data of the photovoltaic inverter to be analyzed within a preset time period, the cause category of the reduction in total active power of the photovoltaic inverter to be analyzed can be determined based on these data. If the cause category is pollutant accumulation, it can be determined that the photovoltaic component connected to the photovoltaic inverter to be analyzed is the photovoltaic component to be cleaned, so that the photovoltaic component to be cleaned can be accurately positioned, thereby realizing small-scale fixed-point cleaning of the photovoltaic component to be cleaned, which is conducive to improving cleaning efficiency and saving cleaning costs and water resources.

[0047] In addition, the present invention also provides corresponding implementation devices, electronic devices and computer-readable storage media for the pollutant identification and cleaning method of a photovoltaic power station, further making the method more practical, and the devices, electronic devices and computer-readable storage media have corresponding advantages. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the prior art and the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 A schematic diagram of the process of a pollutant identification and cleaning method for a photovoltaic power station provided by an embodiment of the present invention;

[0050] Figure 2 A schematic diagram of the process of another pollutant identification and cleaning method for a photovoltaic power station provided by an embodiment of the present invention;

[0051] Figure 3 A comparison diagram of absolute error changes between the actual total active power curve and the predicted total active power curve of a photovoltaic inverter under different influencing factors provided by an embodiment of the present invention;

[0052] Figure 4 A schematic diagram of the solar altitude angle, azimuth angle, and solar hour angle relative to a photovoltaic module provided by an embodiment of the present invention;

[0053] Figure 5 A schematic diagram of the structure of a pollutant identification and cleaning device for a photovoltaic power station provided by an embodiment of the present invention;

[0054] Figure 6 A schematic structural diagram of an electronic device provided by an embodiment of the present invention;

[0055] Figure 7 A schematic structural diagram of a computer-readable storage medium provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The embodiments of the present invention provide a pollutant identification and cleaning method, device, electronic device and computer-readable storage medium for a photovoltaic power station. During use, the photovoltaic components to be cleaned can be accurately positioned so as to achieve small-scale fixed-point cleaning of the photovoltaic components to be cleaned, which is beneficial to improving cleaning efficiency and saving cleaning costs and water resources.

[0057] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0058] Please refer to Figure 1 , Figure 1 A schematic flow chart of a method for identifying and cleaning pollutants in a photovoltaic power station according to an embodiment of the present invention. The method includes:

[0059] S110: Obtaining predicted total active power data of the photovoltaic inverter to be analyzed within a preset time period, and obtaining actual total active power data, actual ambient temperature data, and actual solar altitude angle data of the photovoltaic inverter to be analyzed within the preset time period;

[0060] It should be noted that for any photovoltaic inverter to be analyzed in the photovoltaic power station to be analyzed, the preset total active power data, actual total active power data, actual ambient temperature data and actual solar altitude angle data of the photovoltaic inverter to be analyzed within a preset time period can be obtained, wherein the preset total active power data includes the preset total active power value at each moment in the preset time period, the actual total active power data includes the actual total active power value at each moment in the preset time period, the actual ambient temperature data includes the actual ambient temperature value at each moment in the preset time period, and the actual solar altitude angle data includes the actual solar altitude angle value at each moment in the preset time period. The preset time period in this application can be the current time of multiple consecutive days.

[0061] S120: Determine the cause of the total active power reduction of the photovoltaic inverter to be analyzed based on the predicted total active power data, the actual total active power data, the actual ambient temperature data, and the actual solar altitude angle data within a preset time period;

[0062] It is understandable that under external influences, the total active power of the photovoltaic inverter will decrease. In this application, based on the predicted total active power data, actual total active power data, actual ambient temperature data and actual solar altitude angle data corresponding to the photovoltaic inverter to be analyzed within the preset time period, the cause category of the reduction in the total active power of the photovoltaic inverter to be analyzed can be further determined, that is, which factor has affected the total active power of the photovoltaic inverter to be analyzed.

[0063] S130: When the cause category is accumulation of pollutants, determining that the photovoltaic components connected to the photovoltaic inverter to be analyzed are photovoltaic components to be cleaned, so as to clean the photovoltaic components to be cleaned of pollutants.

[0064] Specifically, when it is determined that the cause of the reduction in the total active power of the photovoltaic inverter to be analyzed is the accumulation of pollutants, it means that the factor of pollutant accumulation has affected the total active power of the photovoltaic inverter to be analyzed. At this time, the photovoltaic component connected to the inverter to be analyzed can be determined as the photovoltaic component to be cleaned. That is, the exact location of the photovoltaic component to be cleaned can be further determined based on the geographical location of the photovoltaic component connected to the inverter to be analyzed, so that the pollutants of the photovoltaic component to be cleaned can be cleaned more accurately. Of course, in actual applications, each photovoltaic inverter to be analyzed in the photovoltaic power station to be analyzed can be analyzed through the above analysis to determine each photovoltaic component to be cleaned. The geographical location of each photovoltaic component to be cleaned can be used to determine the area where multiple photovoltaic components to be cleaned that are geographically adjacent to each other as the area to be cleaned, so that the pollutants of each photovoltaic component to be cleaned in the area to be cleaned can be uniformly cleaned, thereby achieving small-scale positioning cleaning of photovoltaic components.

[0065] It should be noted that in actual applications, the factors that cause the total active power of photovoltaic inverters to decrease include photovoltaic system failures (such as component and equipment failures), meteorological influences, shadow obstruction caused by changes in the solar altitude angle over time, and accumulation of pollutants. In this application, the impact of the cause category that causes the total active power of the photovoltaic inverter to be analyzed can be specifically identified.

[0066] While the various factors that contribute to the reduction in an inverter's total active power are understandably complex, each factor exhibits distinguishable characteristics. The key to identifying pollutant accumulation lies in the unique trend in the total active power of the PV inverter being identified as pollutants accumulate. The downward trend in the PV inverter's total active power under the influence of pollutants gradually accumulates, and the percentage of power reduction is positively correlated with the amount of pollutant accumulation. Pollutant accumulation can be distinguished from other influencing factors by looking at the absolute error between the actual and predicted total active power curves of the PV inverter being analyzed over a preset time period.

[0067] Based on the above examples, please refer to Figure 2 , the embodiments of this application further illustrate and introduce the technical solution.

[0068] In one embodiment, the process of determining the cause category of the total active power reduction of the photovoltaic inverter to be analyzed in the above S120 based on the predicted total active power data, the actual total active power data, the actual ambient temperature data, and the actual solar altitude angle data within a preset time period is described in detail:

[0069] Determine the absolute error between the predicted total active power value and the corresponding actual total active power value at each moment based on the predicted total active power data and the actual total active power data within a preset time period; determine the absolute error growth rate based on the curve of the predicted total active power data and the curve of the actual total active power data;

[0070] In actual application, please refer to Figure 3 The actual total active power data of the photovoltaic inverter to be analyzed (including the actual total active power at each moment) can be obtained through the photovoltaic power station operation and maintenance platform. ), actual ambient temperature data F T , actual solar altitude angle data α T , and draw the corresponding curves respectively to obtain the curve of actual total active power data, the curve of actual ambient temperature data, and the curve of actual solar altitude angle data. The predicted total active power curve is obtained by drawing the predicted total active power data within the preset time period .

[0071] The absolute error between the predicted total active power value at time T and the corresponding actual total active power value can be calculated based on the predicted total active power value corresponding to each moment and the actual total active power value corresponding to each moment. and the absolute error growth rate ,in:

[0072] ;

[0073] ;

[0074] in, It represents the predicted total active power value of the photovoltaic inverter to be analyzed at time T, It represents the actual total active power value of the photovoltaic inverter to be analyzed at time T, s represents the serial number of the photovoltaic inverter to be analyzed, is the absolute error at time T, is the absolute error growth rate at time T.

[0075] If the absolute error at each moment fluctuates positively or negatively, and the absolute value of the first Pearson correlation parameter between the curve of the actual total active power data and the curve of the actual ambient temperature data is greater than or equal to a preset threshold, the cause category is meteorological influence;

[0076] It should be noted that if there are positive and negative fluctuations in the absolute error values between the curve of the actual total active power and the curve of the predicted total active power, that is, the absolute error values are both positive and negative, it can be further determined whether the absolute value of the first Pearson correlation parameter between the curve of the actual total active power data and the curve of the actual ambient temperature data is greater than the preset threshold. If the absolute value of the first Pearson correlation parameter between the curve of the actual total active power data and the curve of the actual ambient temperature data is greater than the preset threshold, it means that the category of causes for the reduction in total active power of the photovoltaic inverter to be analyzed includes meteorological influences.

[0077] Among them, the first Pearson correlation parameter between the curve of actual total active power data and the curve of actual ambient temperature data is It can be obtained through the following relationship:

[0078] , where x is the number of data up to time T; For x The average value of the data, For x F T The mean of the data.

[0079] The preset threshold in this application can be 0.7, that is, when it is determined that the absolute error at each moment has positive and negative fluctuations, and the first Pearson correlation parameter between the curve of the actual total active power data and the curve of the actual ambient temperature data is In this case, the category of reasons for the reduction of total active power of the photovoltaic inverter to be analyzed includes meteorological influence.

[0080] When the absolute value of the second Pearson correlation parameter between the curve of the actual total active power data and the curve of the actual sun altitude angle data is greater than or equal to a preset threshold, the cause category is shadowing;

[0081] It should be noted that in this application, it can be determined whether the absolute value of the second Pearson correlation parameter between the curve of the actual total active power data and the curve of the actual solar altitude angle data is greater than a preset threshold. If the absolute value of the second Pearson correlation parameter between the curve of the actual total active power data and the curve of the actual solar altitude angle data is greater than the preset threshold, it means that the category of causes for the reduction in total active power of the photovoltaic inverter to be analyzed includes shadow shading.

[0082] Among them, the second Pearson correlation parameter between the curve of actual total active power data and the curve of actual solar altitude angle data is It can be calculated by the following relationship:

[0083] ,in, For x The mean of the data.

[0084] The preset threshold in this application can be 0.7, that is, In this case, the categories of reasons that cause the total active power of the photovoltaic inverter to be analyzed to decrease include shadow shading.

[0085] If, among the absolute error growth rates at various moments, the absolute error growth rates at various moments after the first moment are all greater than a first preset percentage, the cause category is a photovoltaic system failure;

[0086] It can be understood that if the absolute error growth rate between the actual total active power curve and the predicted total active power curve is If it is greater than a first preset percentage (eg, 100%) at a first moment and remains greater than 100% at each subsequent moment, it can be determined that the cause of the reduction in total active power of the photovoltaic inverter to be analyzed includes a photovoltaic system failure.

[0087] When the absolute error growth rate at each moment is less than the first preset percentage, the cause category is pollutant accumulation.

[0088] It can be understood that if the absolute error growth rate between the actual total active power curve and the predicted total active power curve is If the values of the total active power of the photovoltaic inverter to be analyzed are both less than the first preset percentage and remain less than the first preset percentage (for example, 100%), it can be determined that the cause of the reduction in the total active power of the photovoltaic inverter to be analyzed includes pollutant accumulation.

[0089] In one embodiment, when the cause category is accumulation of pollutants, the process of determining that the photovoltaic assembly connected to the photovoltaic inverter to be analyzed is the photovoltaic assembly to be cleaned in S130 may include:

[0090] When the cause category includes only pollutant accumulation and it is determined based on the predicted total active power data that the total active power percentage of the photovoltaic inverter to be analyzed has decreased to a second preset percentage, a task verification instruction is sent to the drone carrying the image acquisition device; the task verification instruction includes geographic location information of the photovoltaic modules connected to the photovoltaic inverter to be analyzed;

[0091] Obtaining visible light images related to photovoltaic components collected by the UAV through an image acquisition device;

[0092] Perform image analysis on visible light images to determine the weight of pollutants on photovoltaic modules;

[0093] When it is determined based on the pollutant weight information that the accumulated pollutant weight reaches a limited value of the accumulated pollutant weight, the photovoltaic assembly is determined to be a photovoltaic assembly to be cleaned.

[0094] It should be noted that in order to accurately determine whether the reduction in the total active power of the photovoltaic inverter to be analyzed is caused by the accumulation of pollutants, the present application can further determine whether the photovoltaic module connected to the photovoltaic inverter to be analyzed is a photovoltaic module to be cleaned, if the above analysis determines that the cause of the reduction in the total active power of the photovoltaic inverter to be analyzed only includes the accumulation of pollutants (i.e., there are no other superimposed factors). Specifically, it can be further determined based on the predicted total active power data of the photovoltaic inverter to be analyzed whether the total active power percentage of the photovoltaic inverter to be analyzed is decreasing. If it is decreasing, and the total active power percentage of the photovoltaic inverter to be analyzed decreases to a second preset percentage, a drone equipped with an image acquisition device can be further notified to conduct a mission verification to accurately determine the extent of pollutant accumulation on the photovoltaic module, thereby determining whether the photovoltaic module needs to be cleaned. If cleaning is determined to be necessary, the photovoltaic module is determined to be a photovoltaic module to be cleaned.

[0095] Specifically, when the total active power percentage of the PV inverter to be analyzed decreases to a second preset percentage, a task verification instruction can be sent to a drone equipped with an image acquisition device (such as a visible light camera). The task verification instruction carries the geographic location information of the PV module. The drone flies to the corresponding location based on the geographic location information and to an altitude where it can clearly capture the pollutant information on the PV module. It then captures an image of the PV module to obtain a visible light image of the PV module. The visible light image is then identified using a pre-trained pollutant accumulation degree recognition model to obtain a pollutant weight level. Multiple visible light images (such as visible light images from 11:30 to 13:30) can be obtained. By identifying and analyzing the multiple visible light images, a final pollutant weight level is determined. The pollutant weight level is also the pollutant weight information. The pollutant weight information is then used to determine whether the pollutant accumulation weight reaches the pollutant accumulation weight limit. If the pollutant accumulation weight limit is reached, the PV module is determined as a PV module to be cleaned.

[0096] It should also be noted that the specific values of the pollutant cumulative weight limit and the second preset percentage can be predetermined in this application, wherein the pollutant cumulative weight limit can be 0.233 g / m 2 The second preset percentage can be 20%. The following describes how to determine the pollutant cumulative weight limit and the second preset percentage:

[0097] After the entire photovoltaic power station to be analyzed is cleaned in the early stage, the natural accumulation of pollutants will be monitored. During the entire monitoring period, no cleaning measures will be performed if pollutants accumulate naturally. A test glass plate with a surface area of S0 and the same material as the photovoltaic module surface glass panel is installed around the components connected to each photovoltaic inverter to be analyzed at the same inclination angle as the photovoltaic module. A high-precision electronic balance with a range of 500g and an accuracy of 0.001g is used to measure the initial weight of the test glass plate, recorded as G0, and the test glass plate is reweighed every i-th day, recorded as G i The surface area of the photovoltaic modules connected to the photovoltaic inverter to be analyzed is S PV , the weight of pollutants in the photovoltaic modules connected to the photovoltaic inverter to be analyzed G PV,i The calculation formula is as follows:

[0098] ;

[0099] In practical applications, the historical actual total active power P of each photovoltaic inverter in the photovoltaic power station can be obtained at daily intervals. i (kW) data set, corresponding to the daily pollutant weight G of the photovoltaic modules connected to each photovoltaic inverter PV,i (g / m 2 ) dataset, and the visible light images of the photovoltaic modules connected to each photovoltaic inverter during the time period of 11:30 to 13:30 every day (the sunlight incident angle has little impact on the module image imaging during this period) are used as the pollutant image dataset X.

[0100] The maximum power P in the historical actual total active power data set of each photovoltaic inverter is max As the target value 100%, calculate the historical total active power percentage R of each PV inverter i (%) data set, where the calculation formula for the historical total active power percentage of the PV inverter is as follows: .

[0101] The curve fitting tool in MATLAB software can be used to perform polynomial curve fitting and plot the historical total active power percentage R of the photovoltaic inverter to be analyzed and the pollutant weight G of the photovoltaic module connected to the photovoltaic inverter to be analyzed at the corresponding time. PV The relationship curve: .

[0102] In practical applications, in order to analyze the instantaneous rate of change of the image of the fitting formula, the first-order derivative of the fitting formula is calculated: .

[0103] when When , the first-order derivative of the fitting formula is less than 0, and the fitting formula shows a negative growth rate, which is consistent with the rule that the weight of pollutants will cause the percentage of total active power of the photovoltaic inverter to be analyzed to decrease. Among them, Not applicable to this formula.

[0104] The second-order derivative formula of the fitting formula is: ; The second derivative of the fitting formula is is negative, is positive, the first-order derivative is When the extreme value is reached, the negative growth rate of the fitting formula is the largest, and the percentage reduction of the total active power of the photovoltaic inverter caused by the weight of the pollutants is the largest. PV is the weight of the pollutant, in g / m 2 .

[0105] It can be seen that the pollutant weight accumulation G PV =0.233g / m 2 When the total active power percentage of the inverter to be analyzed is reduced by 20%, the inverter to be analyzed reaches the pollutant accumulation limit value (0.233g / m 2 ) and the power percentage reduction limit value (ie, the second preset percentage is 20%).

[0106] The following is an introduction to the training process of the pollutant accumulation degree identification model: the pollutant accumulation degree identification model in the embodiment of the present application is trained based on the historical pollutant weight dataset of the photovoltaic components connected to each photovoltaic inverter and the corresponding historical sample visible light images of the photovoltaic components.

[0107] It should be noted that in actual applications, the historical pollutant weight (g / m 2 ) Dataset G PV,i As well as a pollutant image dataset X corresponding to the historical pollutant weight, multiple groups (for example, 10 groups) of different pollutant weight levels and corresponding historical visible light images with increasing pollutant weight can be screened from these data sets as image recognition training sets, and a pollutant accumulation degree recognition model can be constructed using the Canny edge detector and the ResNet-50 model.

[0108] Specifically, 1) a Gaussian filter can be used to smooth the input historical visible light image to reduce image noise and improve model training accuracy. 2) The Sobel edge detection operator is used to process the smoothed historical visible light image, and convolution is performed with the image in the horizontal and vertical directions to calculate the image brightness gradient and obtain a gradient intensity matrix to highlight the component edge areas with large gradient amplitudes. 3) Non-maximum suppression (NMS) is used to refine the edges, retaining only the local maximum points in the gradient direction and suppressing all other non-maximum gradient values in the gradient intensity matrix to zero. 4) Double threshold screening is performed using a hysteresis threshold. Strong edges are retained when the gradient value in the gradient intensity matrix processed in step 3 is greater than the high threshold, weak edges are discarded when the gradient value is less than the low threshold, and intermediate edges are retained when the low threshold ≤ gradient value ≤ high threshold and the gradient value is connected to a strong edge, so as to generate an accurate edge image. 5) PV panels were cropped from the original historical visible light images based on edge images, and regions of interest (ROIs) were created and saved. These images were then uniformly resized to the ResNet-50 input size (224×224) and saved as a panel image set, which served as input for the subsequent training phase of the pollutant accumulation level identification model. 6) The training dataset for the pollutant accumulation level identification model included the historical visible light image set of panels and the corresponding target category data annotation files. The LabelMe image annotation tool was used to annotate each image with the pollutant weight level. 7) A ResNet-50 model was adapted for the pollutant weight level classification task. Model optimization training was performed through mixed precision training and gradient clipping to obtain the trained pollutant accumulation level identification model.

[0109] In practical applications, the visible light image of the photovoltaic module connected to the photovoltaic inverter to be analyzed can be input into the pollutant accumulation degree identification model to obtain the corresponding pollutant weight level. According to the pollutant weight level, it can be determined whether the pollutant accumulation weight reaches the pollutant accumulation weight limit value. When the pollutant accumulation weight limit value is reached, the photovoltaic module is determined to be a photovoltaic module to be cleaned.

[0110] In one embodiment, the process of obtaining the predicted total active power data of the photovoltaic inverter to be analyzed within a preset time period may include:

[0111] For each moment in the preset time period, the predicted PV module irradiance at the current moment is determined based on the current time, the latitude of the PV power station to be analyzed, the tilt angle of the PV modules, and the azimuth angle of the PV module array;

[0112] It is understandable that in the embodiment of the present application, the predicted photovoltaic module irradiance at the current moment can be determined based on the current time, the latitude of the photovoltaic power station to be analyzed, the inclination angle of the photovoltaic module, and the azimuth angle of the photovoltaic module array in combination with the first calculation formula, wherein the first calculation formula is:

[0113] ; ;

[0114] ;

[0115] Among them, AM is the air quality coefficient, is the solar altitude angle, G T is the predicted value of the module irradiance at time T, β is the tilt angle of the photovoltaic module, is the azimuth angle of the photovoltaic array, C F is the correlation factor, is the declination angle, is the latitude of the photovoltaic power station, The solar hour angle is the angle between the sun in the sky and the meridian of the observation point on the earth. It is related to the time T. The noon hour angle is 0, the morning hour angle is negative, and the afternoon hour angle is positive. The corresponding hour angle is 15 degrees per hour. The schematic diagram of the solar altitude angle, azimuth angle, and solar hour angle is as follows: Figure 4 shown.

[0116] , n is the date, that is, the day is the number of the year.

[0117] .

[0118] The predicted total active power value of the PV inverter to be analyzed at the current moment is obtained based on the predicted PV module irradiance at the current moment, the rated power of the PV modules connected to the PV inverter to be analyzed under standard test conditions, the module irradiance under standard test conditions, the relationship coefficient between module power and temperature, the PV operating temperature under standard test conditions, and the predicted implementation ambient temperature.

[0119] In order to obtain a more accurate prediction of the total active power in this application, the predicted total active power of the photovoltaic inverter to be analyzed can be obtained according to the following photovoltaic inverter total active power prediction relationship:

[0120] ;in, is the predicted total active power of the inverter to be analyzed at time T; The rated power of the PV modules connected to the inverter to be analyzed under standard test conditions; is the predicted value of component irradiance at time T; is the component irradiance under standard test conditions, which is 1000 W / m 2 ; is the coefficient of relationship between component power and temperature, which is 0.005; The photovoltaic operating temperature under standard test conditions is 25°C; is the real-time ambient temperature forecast value, which is obtained from the meteorological station configured by the PV power station or the local meteorological agency; s is the number of the inverter to be analyzed.

[0121] According to the predicted total active power values corresponding to each moment in the preset time period, the predicted total active power data of the photovoltaic inverter to be analyzed in the preset time period is obtained.

[0122] In one embodiment, after determining that the photovoltaic assembly connected to the photovoltaic inverter to be analyzed is the photovoltaic assembly to be cleaned, the method further includes:

[0123] The geographical location information of the photovoltaic assembly to be cleaned is sent to a cleaning drone, so that the cleaning drone performs the task of cleaning the photovoltaic assembly to be cleaned based on the geographical location information.

[0124] It should be noted that in order to improve the cleaning efficiency of photovoltaic modules, in this application, after determining the photovoltaic modules to be cleaned, the geographical location information of the photovoltaic modules to be cleaned can also be sent to a cleaning drone. The cleaning drone may include a drone, a power supply device, an electric motor, a water pump, a water tank, a water supply spray rod and a nozzle. The cleaning drone can fly to the location area of the photovoltaic modules to be cleaned according to the geographical location information and perform the cleaning task of the photovoltaic modules, thereby achieving efficient cleaning in a small range.

[0125] It can be seen that in this application, by obtaining the predicted total active power data, actual total active power data, actual ambient temperature data and actual solar altitude angle data of the photovoltaic inverter to be analyzed within a preset time period, the cause category of the reduction in total active power of the photovoltaic inverter to be analyzed can be determined based on these data. If the cause category is pollutant accumulation, it can be determined that the photovoltaic component connected to the photovoltaic inverter to be analyzed is the photovoltaic component to be cleaned, so that the photovoltaic component to be cleaned can be accurately positioned, thereby realizing small-scale fixed-point cleaning of the photovoltaic component to be cleaned, which is conducive to improving cleaning efficiency and saving cleaning costs and water resources.

[0126] The present invention also provides a corresponding device for the pollutant identification and cleaning method of a photovoltaic power station, which further makes the method more practical. Among them, the device can be described from the perspective of functional modules and hardware. The following is an introduction to the pollutant identification and cleaning device for a photovoltaic power station provided by the present invention. The device is used to implement the pollutant identification and cleaning method for a photovoltaic power station provided by the present invention. In this embodiment, the pollutant identification and cleaning device for a photovoltaic power station may include or be divided into one or more program modules, and the one or more program modules are stored in a storage medium and executed by one or more processors to complete the pollutant identification and cleaning method for a photovoltaic power station disclosed in the above embodiment. The program module referred to in the present invention refers to a series of computer program instruction segments that can complete specific functions, which is more suitable for describing the execution process of the pollutant identification and cleaning device for a photovoltaic power station in a storage medium than the program itself. The following description will specifically introduce the functions of each program module of this embodiment. The pollutant identification and cleaning device for a photovoltaic power station described below and the pollutant identification and cleaning method based on a photovoltaic power station described above can be referenced to each other.

[0127] From the perspective of functional modules, see Figure 5 , Figure 5 This is a structural diagram of a pollutant identification and cleaning device for a photovoltaic power station provided by the present invention in a specific embodiment. The device may include:

[0128] An acquisition module 11 is configured to acquire predicted total active power data of the photovoltaic inverter to be analyzed within a preset time period, and to acquire actual total active power data, actual ambient temperature data, and actual solar altitude angle data of the photovoltaic inverter to be analyzed within the preset time period;

[0129] a first determining module 12, configured to determine a cause category of a total active power reduction of the photovoltaic inverter to be analyzed based on the predicted total active power data, the actual total active power data, the actual ambient temperature data, and the actual solar altitude angle data within the preset time period;

[0130] The second determining module 13 is configured to, when the cause category is pollutant accumulation, determine that the photovoltaic assembly connected to the photovoltaic inverter to be analyzed is a photovoltaic assembly to be cleaned, so as to clean the pollutants from the photovoltaic assembly to be cleaned.

[0131] In one embodiment, the first determining module 12 includes:

[0132] A first determining unit is configured to determine an absolute error between a predicted total active power value and a corresponding actual total active power value at each moment based on the predicted total active power data and the actual total active power data within a preset time period;

[0133] a second determining unit, configured to determine an absolute error growth rate according to a curve of the predicted total active power data and a curve of the actual total active power data;

[0134] a third determining unit, configured to determine that the cause category is meteorological influence if there is positive and negative fluctuation in the absolute error at each moment and the absolute value of a first Pearson correlation parameter between a curve of actual total active power data and a curve of actual ambient temperature data is greater than or equal to a preset threshold;

[0135] a fourth determining unit, configured to determine, when an absolute value of a second Pearson correlation parameter between a curve of actual total active power data and a curve of actual sun altitude angle data is greater than or equal to a preset threshold, that the cause category is shadow obstruction;

[0136] a fifth determining unit, configured to, if the absolute error growth rates at the respective moments after the first moment are all greater than a first preset percentage, determine that the cause category is a photovoltaic system failure;

[0137] The sixth determining unit is configured to determine, when the absolute error growth rate at each moment is less than a first preset percentage, that the cause category is pollutant accumulation.

[0138] In one embodiment, the second determining module 13 includes:

[0139] a sending unit, configured to send a task verification instruction to a drone carrying an image acquisition device, when the cause category includes only pollutant accumulation and it is determined based on the predicted total active power data that the total active power percentage of the photovoltaic inverter to be analyzed has decreased to a second preset percentage; the task verification instruction includes geographic location information of the photovoltaic modules connected to the photovoltaic inverter to be analyzed;

[0140] an acquisition unit, configured to acquire a visible light image related to the photovoltaic module acquired by the UAV through an image acquisition device;

[0141] a seventh determination unit, configured to perform image analysis on the visible light image to determine weight information of pollutants on the photovoltaic module;

[0142] The eighth determining unit is configured to determine that the photovoltaic assembly is a photovoltaic assembly to be cleaned when it is determined based on the pollutant weight information that the accumulated weight of the pollutants reaches a limited value of the accumulated weight of the pollutants.

[0143] In one embodiment, the eighth determining unit is specifically configured to:

[0144] A pre-established pollutant accumulation degree identification model is used to perform image analysis on visible light images to obtain pollutant weight levels. The pollutant accumulation degree identification model is trained based on the historical pollutant weight dataset of the photovoltaic modules connected to each photovoltaic inverter and the corresponding historical sample visible light images of the photovoltaic modules.

[0145] In one embodiment, the acquisition module 11 includes:

[0146] a ninth determining unit configured to determine, for each moment within a preset time period, a predicted photovoltaic module irradiance at the current moment based on the current time, the latitude of the photovoltaic power station to be analyzed, the photovoltaic module inclination, and the azimuth of the photovoltaic module array;

[0147] an acquisition unit, configured to obtain a predicted total active power value of the photovoltaic inverter to be analyzed at the current moment based on the predicted photovoltaic module irradiance at the current moment, the rated power of the photovoltaic module connected to the photovoltaic inverter to be analyzed under standard test conditions, the module irradiance under standard test conditions, the relationship coefficient between module power and temperature, the photovoltaic operating temperature under standard test conditions, and the predicted implementation ambient temperature;

[0148] The tenth determining unit is configured to obtain the predicted total active power data of the photovoltaic inverter to be analyzed within the preset time period according to the predicted total active power values corresponding to each moment within the preset time period.

[0149] In one embodiment, the ninth determining unit is specifically configured to:

[0150] The predicted photovoltaic module irradiance at the current moment is determined based on the current time, the latitude of the photovoltaic power station to be analyzed, the photovoltaic module inclination, and the azimuth of the photovoltaic module array in combination with the first calculation formula, where the first calculation formula is:

[0151] ; ;

[0152] ;

[0153] Among them, AM is the air quality coefficient, is the solar altitude angle, G T is the predicted value of the module irradiance at time T, β is the tilt angle of the photovoltaic module, is the azimuth angle of the photovoltaic array, C F is the correlation factor, is the declination angle, is the latitude of the photovoltaic power station, is the solar hour angle;

[0154] , n is the date, that is, the day is the number of the year.

[0155] .

[0156] In one embodiment, the device further comprises:

[0157] The sending module is used to send the geographical location information of the photovoltaic components to be cleaned to the cleaning drone, so that the cleaning drone performs the task of cleaning the photovoltaic components to be cleaned based on the geographical location information.

[0158] It should be noted that the pollutant identification and cleaning device of the photovoltaic power station has the same beneficial effects as the pollutant identification and cleaning method of the photovoltaic power station provided in the above embodiment, and for the introduction of the pollutant identification and cleaning method of the photovoltaic power station involved in this embodiment, please refer to the above embodiment, and this application will not repeat it here.

[0159] The pollutant identification and cleaning device for the photovoltaic power station mentioned above is described from the perspective of functional modules. Furthermore, the present invention also provides an electronic device, which is described from the perspective of hardware. Figure 6 A structural diagram of an electronic device provided in an embodiment of the present application, such as Figure 6 As shown, the electronic device includes: a memory 20 for storing computer programs;

[0160] The processor 21 is configured to implement the steps of the pollutant identification and cleaning method for a photovoltaic power station in the above embodiment when executing a computer program.

[0161] The electronic device provided in this embodiment may include but is not limited to a smart phone, a tablet computer, a laptop computer, or a desktop computer.

[0162] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0163] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include high-speed random access memory and non-volatile memory, such as one or more magnetic disk storage devices or flash memory storage devices. In some embodiments, the memory 20 may be an internal storage unit of the electronic device, such as a server's hard drive. In other embodiments, the memory 20 may also be an external storage device of the electronic device, such as a plug-in hard drive equipped on a server, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the memory 20 may include both an internal storage unit and an external storage device of the electronic device. The memory 20 may be used not only to store application software installed in the electronic device and various data, such as the code of the program executing the photovoltaic power station contaminant identification and cleaning method, but also to temporarily store data that has been output or is about to be output. In this embodiment, the memory 20 is used to store at least the following computer program 201, which, when loaded and executed by the processor 21, is capable of implementing the relevant steps of the photovoltaic power station contaminant identification and cleaning method disclosed in any of the aforementioned embodiments. In addition, resources stored in memory 20 may include an operating system 202 and data 203. Storage may be either transient or permanent. Operating system 202 may include Windows, Unix, or Linux. Data 203 may include, but is not limited to, data corresponding to the results of pollutant identification and cleaning in a photovoltaic power plant.

[0164] In some embodiments, the electronic device may further include a display screen 22, an input / output interface 23, a communication interface 24, a power supply 25, and a communication bus 26. Among them, the display screen 22 and the input / output interface 23, such as a keyboard, are user interfaces, and the optional user interface may also include a standard wired interface, a wireless interface, etc. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device, etc. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface. The communication interface 24 may optionally include a wired interface and / or a wireless interface, such as a WI-FI interface, a Bluetooth interface, etc., which is generally used to establish a communication connection between the electronic device and other electronic devices. The communication bus 26 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0165] Those skilled in the art will understand that Figure 6 The structure shown in the figure does not constitute a limitation of the electronic device, and may include more or fewer components than shown in the figure.

[0166] It is understandable that if the pollutant identification and cleaning method for the photovoltaic power station in the above embodiment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and executes all or part of the steps of the methods of each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), electrically erasable programmable ROM, register, hard disk, removable disk, CD-ROM, magnetic disk or optical disk, and other media that can store program code.

[0167] Based on this, Figure 7As shown, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program 31 is stored. When the computer program 31 is executed by a processor, the steps of the pollutant identification and cleaning method of the photovoltaic power station as described above are implemented.

[0168] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0169] It should also be noted that, in this specification, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

[0170] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for identifying and cleaning pollutants in a photovoltaic power station, characterized in that: include: Acquiring predicted total active power data of the photovoltaic inverter to be analyzed within a preset time period, and acquiring actual total active power data, actual ambient temperature data, and actual solar altitude angle data of the photovoltaic inverter to be analyzed within the preset time period; Determining a cause category of a decrease in total active power of the photovoltaic inverter to be analyzed based on the predicted total active power data, the actual total active power data, the actual ambient temperature data, and the actual solar altitude angle data within the preset time period; When the cause category is accumulation of pollutants, it is determined that the photovoltaic assembly connected to the photovoltaic inverter to be analyzed is a photovoltaic assembly to be cleaned, so as to clean the pollutants from the photovoltaic assembly to be cleaned.

2. The pollutant identification and cleaning method for a photovoltaic power station according to claim 1, characterized in that: The determining, based on the predicted total active power data, the actual total active power data, the actual ambient temperature data, and the actual solar altitude angle data within the preset time period, of a cause of a decrease in the total active power of the photovoltaic inverter to be analyzed includes: Determining, based on the predicted total active power data and the actual total active power data within the preset time period, an absolute error between the predicted total active power value at each moment and the corresponding actual total active power value; determining an absolute error growth rate according to a curve of the predicted total active power data and a curve of the actual total active power data; If the absolute errors at each moment fluctuate positively or negatively, and the absolute value of the first Pearson correlation parameter between the curve of the actual total active power data and the curve of the actual ambient temperature data is greater than or equal to a preset threshold, the cause category is meteorological influence; When the absolute value of the second Pearson correlation parameter between the curve of the actual total active power data and the curve of the actual sun altitude angle data is greater than or equal to the preset threshold, the cause category is shadow obstruction; If, among the absolute error growth rates at various moments, the absolute error growth rates at various moments after the first moment are all greater than a first preset percentage, the cause category is a photovoltaic system failure; When the absolute error growth rate at each moment is less than the first preset percentage, the cause category is pollutant accumulation.

3. The pollutant identification and cleaning method for a photovoltaic power station according to claim 1, characterized in that: When the cause category is accumulation of pollutants, determining that the photovoltaic assembly connected to the photovoltaic inverter to be analyzed is the photovoltaic assembly to be cleaned includes: If the cause category includes only pollutant accumulation, and it is determined based on the predicted total active power data that the total active power percentage of the photovoltaic inverter to be analyzed has decreased to a second preset percentage, sending a task verification instruction to a drone carrying an image acquisition device; the task verification instruction includes geographic location information of the photovoltaic modules connected to the photovoltaic inverter to be analyzed; Acquire a visible light image related to the photovoltaic component acquired by the drone through the image acquisition device; performing image analysis on the visible light image to determine weight information of pollutants in the photovoltaic module; When it is determined based on the pollutant weight information that the accumulated pollutant weight reaches a limited pollutant accumulated weight value, the photovoltaic assembly is determined to be a photovoltaic assembly to be cleaned.

4. The pollutant identification and cleaning method for a photovoltaic power station according to claim 3, characterized in that: The performing image analysis on the visible light image to determine the weight information of the pollutants in the photovoltaic module includes: The visible light image is analyzed using a pre-established pollutant accumulation degree identification model to obtain the pollutant weight level; wherein the pollutant accumulation degree identification model is trained based on the historical pollutant weight dataset of the photovoltaic modules connected to each photovoltaic inverter and the corresponding historical sample visible light images of the photovoltaic modules.

5. The pollutant identification and cleaning method for a photovoltaic power station according to claim 1, characterized in that: The obtaining of predicted total active power data of the photovoltaic inverter to be analyzed within a preset time period includes: For each moment in the preset time period, the predicted PV module irradiance at the current moment is determined based on the current time, the latitude of the PV power station to be analyzed, the PV module inclination, and the azimuth of the PV module array; Obtaining a predicted total active power value of the photovoltaic inverter to be analyzed at the current moment based on the predicted photovoltaic module irradiance at the current moment, the rated power of the photovoltaic module connected to the photovoltaic inverter to be analyzed under standard test conditions, the module irradiance under standard test conditions, the relationship coefficient between module power and temperature, the photovoltaic operating temperature under standard test conditions, and the predicted implementation ambient temperature; The predicted total active power data of the photovoltaic inverter to be analyzed within the preset time period is obtained according to the predicted total active power values corresponding to each moment within the preset time period.

6. The pollutant identification and cleaning method for a photovoltaic power station according to claim 1, characterized in that: The step of determining the predicted photovoltaic module irradiance at the current moment based on the current time, the latitude of the photovoltaic power station to be analyzed, the photovoltaic module inclination angle, and the photovoltaic module azimuth angle includes: The predicted photovoltaic module irradiance at the current moment is determined based on the current time, the latitude of the photovoltaic power station to be analyzed, the photovoltaic module inclination, and the azimuth of the photovoltaic module array in combination with the first calculation formula, where the first calculation formula is: ； ； ； Among them, AM is the air quality coefficient, is the solar altitude angle, G T is the predicted value of the module irradiance at time T, β is the tilt angle of the photovoltaic module, is the azimuth angle of the photovoltaic array, C F is the correlation factor, is the declination angle, is the latitude of the photovoltaic power station, is the solar hour angle.

7. The pollutant identification and cleaning method for a photovoltaic power station according to any one of claims 1 to 6, characterized in that: After determining that the photovoltaic assembly connected to the photovoltaic inverter to be analyzed is the photovoltaic assembly to be cleaned, the method further includes: The geographical location information of the photovoltaic assembly to be cleaned is sent to a cleaning drone, so that the cleaning drone performs a task of cleaning the photovoltaic assembly to be cleaned based on the geographical location information.

8. A pollutant identification and cleaning device for a photovoltaic power station, characterized in that: include: an acquisition module, configured to acquire predicted total active power data of the photovoltaic inverter to be analyzed within a preset time period, and to acquire actual total active power data, actual ambient temperature data, and actual solar altitude angle data of the photovoltaic inverter to be analyzed within the preset time period; a first determining module, configured to determine a cause category of a total active power reduction of the photovoltaic inverter to be analyzed based on the predicted total active power data, the actual total active power data, the actual ambient temperature data, and the actual solar altitude angle data within the preset time period; The second determining module is configured to determine, when the cause category is pollutant accumulation, that the photovoltaic assembly connected to the photovoltaic inverter to be analyzed is a photovoltaic assembly to be cleaned, so as to clean the pollutants from the photovoltaic assembly to be cleaned.

9. An electronic device, characterized in that: include: Memory for storing computer programs; A processor is configured to implement the steps of the pollutant identification and cleaning method for a photovoltaic power station as claimed in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the pollutant identification and cleaning method for a photovoltaic power station according to any one of claims 1 to 7.

Images