A method and system for evaluating the photovoltaic power generation efficiency based on drone detection data

Abstract

The present invention relates to the technical field of photovoltaic power generation, and a method and system for evaluating the photovoltaic power generation efficiency based on drone detection data, including: obtaining a reference coordinate set by using a reference photovoltaic power generation unit group, obtaining a fitting detection path sequence based on the reference coordinate set, successively driving a detection drone by using the fitting detection paths in the fitting detection path sequence, and real-time monitoring the drone coordinates of the detection drone during driving. When the drone coordinates are the detection coordinates, obtaining a target photovoltaic image based on the detection angles corresponding to the detection nodes, obtaining an evaluation loss coefficient by using the target photovoltaic image, a data collection unit, a data analysis unit and a data evaluation unit, obtaining a reference power generation efficiency based on the reference photovoltaic power generation unit corresponding to the detection node, calculating the product of the evaluation loss coefficient and the reference power generation efficiency to obtain an evaluation power generation efficiency. The present invention can intelligently and accurately evaluate the photovoltaic power generation efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation, and particularly to a method and system for evaluating the photovoltaic power generation efficiency based on drone detection data. Background Art

[0002] With the continuous growth of the global demand for clean energy, photovoltaic power generation, as an important renewable energy technology, has been widely used. Correspondingly, how to accurately and intelligently evaluate the photovoltaic power generation efficiency has become an urgent problem to be solved.

[0003] Currently, traditional methods for evaluating photovoltaic power generation efficiency mostly use monitoring devices pre-installed on the ground to evaluate the power generation efficiency of photovoltaic power generation units through the monitoring devices, or adopt the form of manual inspection to evaluate the power generation efficiency of photovoltaic power generation units by testing each photovoltaic power generation unit.

[0004] Although the above methods can evaluate the photovoltaic power generation efficiency, when evaluating the power generation efficiency of photovoltaic power generation units, they consume a large amount of human and material resources and have relatively large limitations. Therefore, intelligently and accurately evaluating the photovoltaic power generation efficiency has become an urgent problem to be solved. Summary of the Invention

[0005] The present invention provides a method for evaluating the photovoltaic power generation efficiency based on drone detection data and a computer-readable storage medium, and its main purpose is to intelligently and accurately evaluate the photovoltaic power generation efficiency.

[0006] To achieve the above object, a method for evaluating the photovoltaic power generation efficiency based on drone detection data provided by the present invention includes:

[0007] Receiving an efficiency evaluation instruction, and confirming an efficiency evaluation environment based on the efficiency evaluation instruction. The efficiency evaluation environment includes a detection drone, a reference photovoltaic power generation unit group, and an efficiency evaluation system. The efficiency evaluation system includes: a data collection unit, a data analysis unit, a data evaluation unit, and a result feedback unit. The reference photovoltaic power generation unit group includes multiple reference photovoltaic power generation units;

[0008] Using the reference photovoltaic power generation unit group to obtain a reference coordinate set, where the reference coordinate set includes multiple reference coordinates, and the reference coordinates correspond to the reference photovoltaic power generation units one by one. Based on the reference coordinate set, obtaining a fitting detection path sequence, where the fitting detection path sequence includes one or more fitting detection paths, and each fitting detection path includes multiple detection nodes, and the detection nodes include detection angles and detection coordinates;

[0009] Drive the detection UAV in sequence using the fitting detection paths in the fitting detection path sequence, and monitor the UAV coordinates of the detection UAV in real time during driving. After the UAV coordinates are the detection coordinates, obtain the target photovoltaic image based on the detection angle corresponding to the detection node;

[0010] Obtain the evaluation loss coefficient using the target photovoltaic image, data collection unit, data analysis unit, and data evaluation unit;

[0011] Obtain the reference power generation efficiency based on the reference photovoltaic power generation unit corresponding to the detection node;

[0012] Calculate the product of the evaluation loss coefficient and the reference power generation efficiency to obtain the evaluation power generation efficiency. Use the result feedback unit to send the evaluation power generation efficiency to the initiator of the efficiency evaluation instruction to realize the evaluation of the power generation efficiency of the reference photovoltaic power generation unit group.

[0013] Optionally, the obtaining the fitting detection path sequence based on the reference coordinate set includes:

[0014] Identify the reference regression coordinates as the starting point and the ending point, and use the pre-constructed clustering method to cluster the reference coordinates in the reference coordinate set to obtain one or more clustering coordinate sets;

[0015] Identify one or more cluster center coordinates based on one or more clustering coordinate sets, where the cluster center coordinates correspond one-to-one with the clustering coordinate sets. Calculate the Euclidean distance between each cluster center coordinate in the one or more cluster center coordinates and the reference regression coordinates to obtain the retrieval order distance. Summarize the retrieval order distances to obtain a retrieval order distance set. Sort the retrieval order distances in the retrieval order distance set in ascending order to obtain a retrieval order sequence. Obtain a retrieval coordinate group sequence based on the retrieval order sequence, where the retrieval coordinate group sequence includes one or more retrieval coordinate groups, and the retrieval coordinate groups correspond one-to-one with the retrieval order distances in the retrieval order sequence, and the retrieval coordinate groups correspond one-to-one with the clustering coordinate sets;

[0016] Extract the retrieval coordinate groups from the retrieval coordinate group sequence in sequence, and perform the following operations on the extracted retrieval coordinate groups:

[0017] Obtain an identification coordinate group based on the retrieval coordinate group, where the identification coordinate group includes multiple identification coordinates, and the identification coordinates correspond one-to-one with the reference coordinates;

[0018] Obtain a path fitting model for fitting a path, use the path fitting model and the identification coordinate group to obtain a fitted path, use the identification coordinates in the identification coordinate group to identify multiple detection nodes in the fitted path to obtain an initial divided path, obtain a fitted detection path based on the initial divided path and the reference regression coordinates, identify the set of detected coordinates of the fitted detection path, remove the set of detected coordinates from the reference coordinate set, and use the reference coordinate set after removing the set of detected coordinates as the reference coordinate set, and return the step of clustering the reference coordinates in the reference coordinate set using a pre-constructed clustering method to obtain one or more clustering coordinate sets, summarize the fitted detection paths to obtain a fitted detection path set, and sort the fitted detection paths in the fitted detection path set in the order of the time corresponding to the obtained fitted detection paths to obtain a fitted detection path sequence.

[0019] Optionally, the obtaining the fitted detection path based on the initial divided path and the reference regression coordinates includes:

[0020] Identify the first detection node in the initial divided path to obtain an initial detection node, use the identification coordinates corresponding to the initial detection node and the reference regression coordinates to obtain an initial flight distance, and use the initial detection node and a preset node step size to identify a fitted divided path in the initial divided path;

[0021] Extract the last detection node in the fitted divided path to obtain a regression detection node, and use the identification coordinates corresponding to the regression detection node and the reference regression coordinates to obtain a regression flight distance;

[0022] Identify the number of detection nodes in the fitted divided path to obtain the number of detection nodes, obtain the initial energy consumption of the detection UAV, and calculate the detection energy consumption based on the initial flight distance, the regression flight distance, the fitted divided path, and the number of detection nodes;

[0023] Calculate the product of the initial energy consumption and a preset energy consumption ratio to obtain a safety energy consumption threshold, and obtain the fitted detection path based on the detection energy consumption and the safety energy consumption threshold.

[0024] Optionally, the calculating the detection energy consumption based on the initial flight distance, the regression flight distance, the fitted divided path, and the number of detection nodes includes:

[0025] Obtain a fitted detection distance based on the fitted divided path, and calculate the detection energy consumption using the fitted detection distance and a pre-constructed energy consumption evaluation relationship, where the energy consumption evaluation relationship is as follows: ;

[0026] Where represents the detection energy consumption, 、 are a preset flight coefficient and a hovering coefficient respectively, represents the number of detection nodes, represents the mass of the detection UAV, represents the distance that the detection UAV needs to fly during detection, 、 、 respectively represent the fitted detection distance, the initial flight distance and the return flight distance, represents the propulsion efficiency of the detection UAV, represents the optimal cruise speed, represents the flight speed of the UAV, represents the preset single hovering time.

[0027] Optionally, obtaining the fitted detection path based on the detection energy consumption and the safety energy consumption threshold includes:

[0028] Compare the detection energy consumption with the safety energy consumption threshold. If the detection energy consumption is less than or equal to the safety energy consumption threshold, update the node step size using a preset iterative step value, and use the updated node step size as the node step size, and return to the step of using the initial detection node and the preset node step size to confirm the fitted division path in the initial division path until it is confirmed that the detection energy consumption is greater than the safety energy consumption threshold, and then summarize the detection energy consumption to obtain a detection energy consumption set;

[0029] Perform the following operations on each detection energy consumption in the detection energy consumption set:

[0030] Calculate the difference between the safety energy consumption threshold and the detection energy consumption to obtain the evaluation energy consumption, summarize the evaluation energy consumption to obtain an evaluation energy consumption set, and confirm the target evaluation energy consumption based on the evaluation energy consumption set, where the target evaluation energy consumption is greater than or equal to 0, and the target evaluation energy consumption is the smallest evaluation energy consumption in the evaluation energy consumption set, and the fitted detection path is the fitted division path corresponding to the target evaluation energy consumption.

[0031] Optionally, obtaining the target photovoltaic image based on the detection angle corresponding to the detection node includes:

[0032] Obtain an initial monitoring image based on a preset detection angle, and use a pre-constructed photovoltaic recognition model to extract an initial photovoltaic image from the initial monitoring image;

[0033] Use the detection angle and the detection angle corresponding to the detection node to correct the initial photovoltaic image to obtain the target photovoltaic image.

[0034] Optionally, using the target photovoltaic image, the data collection unit, the data analysis unit and the data evaluation unit to obtain the evaluation loss coefficient includes:

[0035] Confirm the receipt of the data collection instruction from the data collection unit, parse the data collection instruction, and obtain a grayscale gradient set, where the grayscale gradient set includes multiple gradient grayscale values;

[0036] Confirm the receipt of the data evaluation instruction from the data evaluation unit, parse the data evaluation instruction, and obtain the reference grayscale range;

[0037] Obtain multiple first reference grayscale values based on the preset extraction value and the reference grayscale range, and perform the following operations on each of the multiple first reference grayscale values:

[0038] Identify the fitted photovoltaic unit based on the first reference grayscale value, obtain the fitted loss efficiency using the fitted photovoltaic unit, associate the first reference grayscale value and the fitted loss efficiency to obtain the fitted coordinates, and summarize the fitted coordinates to obtain the fitted coordinate set;

[0039] Confirm the receipt of the data analysis instruction from the data analysis unit, parse the data analysis instruction, obtain the curve fitting model, map all the fitted coordinates in the fitted coordinate set to the pre-constructed reference coordinate system to obtain the mapped coordinate set, and use the curve fitting model and the mapped coordinate set to obtain the fitted loss curve;

[0040] Perform grayscale transformation on the target photovoltaic image to obtain the target grayscale image;

[0041] Obtain one or more groups of fitted region images based on the target grayscale image, the pre-constructed region growing algorithm, and the grayscale gradient set. Each group of fitted region images includes one or more initial fitted region images, and the groups of fitted region images correspond one-to-one with the gradient grayscale values;

[0042] Perform the following operations on each group of fitted region images in the one or more groups of fitted region images:

[0043] Obtain the fitted image area based on the one or more initial fitted region images corresponding to the group of fitted region images, obtain the target image area of the target photovoltaic image, calculate the ratio of the fitted image area to the target image area to obtain the fitted ratio;

[0044] Obtain the fitted grayscale mean value based on the group of fitted region images, and use the fitted grayscale mean value to retrieve the target loss efficiency in the fitted loss curve;

[0045] Associate the target loss efficiency and the fitted ratio to obtain the target loss node, summarize the target loss nodes to obtain the target loss node set, and use the target loss node set to calculate the evaluation loss coefficient.

[0046] Optionally, the calculation formula for using the target loss node set to calculate the evaluation loss coefficient is as follows: ;

[0047] Wherein, represents the evaluation depreciation coefficient, represents that there are target depreciation nodes in the target depreciation node set, , respectively represent the fitting ratio and the target depreciation efficiency corresponding to the th target depreciation node in the target depreciation node set.

[0048] Optionally, obtaining the reference power generation efficiency based on the reference photovoltaic power generation unit corresponding to the detection node includes:

[0049] Obtaining the reference environmental data of the reference photovoltaic power generation unit, wherein the reference environmental data includes: irradiation intensity, environmental temperature, and environmental humidity;

[0050] Obtaining the predicted power generation efficiency based on the reference environmental data and the pre-trained efficiency prediction model;

[0051] Obtaining the service life of the reference photovoltaic power generation unit, obtaining the service life depreciation coefficient based on the service life, and calculating the product of the service life depreciation coefficient and the predicted power generation efficiency to obtain the reference power generation efficiency.

[0052] To achieve the above object, the present invention also provides a photovoltaic power generation efficiency evaluation system based on drone detection data, including:

[0053] An evaluation environment confirmation module, configured to receive an efficiency evaluation instruction, and confirm an efficiency evaluation environment based on the efficiency evaluation instruction. The efficiency evaluation environment includes a detection drone, a reference photovoltaic power generation unit group, and an efficiency evaluation system. The efficiency evaluation system includes: a data collection unit, a data analysis unit, a data evaluation unit, and a result feedback unit. The reference photovoltaic power generation unit group includes a plurality of reference photovoltaic power generation units;

[0054] A detection path fitting module, configured to obtain a reference coordinate set by using the reference photovoltaic power generation unit group. The reference coordinate set includes a plurality of reference coordinates, and the reference coordinates correspond to the reference photovoltaic power generation units one by one. Based on the reference coordinate set, a fitting detection path sequence is obtained. The fitting detection path sequence includes one or more fitting detection paths. The fitting detection path includes a plurality of detection nodes, and the detection nodes include a detection angle and a detection coordinate;

[0055] A photovoltaic image detection module, configured to sequentially drive the detection drone by using the fitting detection paths in the fitting detection path sequence, and real-time monitor the drone coordinates of the detection drone during driving. When the drone coordinates are the detection coordinates, obtain a target photovoltaic image based on the detection angle corresponding to the detection node;

[0056] A power generation efficiency evaluation module, configured to obtain an evaluation loss coefficient by using a target photovoltaic image, a data collection unit, a data analysis unit, and a data evaluation unit;

[0057] Obtain a reference power generation efficiency based on the reference photovoltaic power generation unit corresponding to the detection node;

[0058] Calculate the product of the evaluation loss coefficient and the reference power generation efficiency to obtain an evaluation power generation efficiency, and use the result feedback unit to send the evaluation power generation efficiency to the initiator of the efficiency evaluation instruction, so as to realize the evaluation of the power generation efficiency of the reference photovoltaic power generation unit group.

[0059] To solve the above problems, the present invention further provides an electronic device, which includes:

[0060] A memory that stores at least one instruction; and a processor that executes the instruction stored in the memory to implement the above-mentioned photovoltaic power generation efficiency evaluation method based on drone detection data.

[0061] To solve the above problems, the present invention further provides a computer-readable storage medium, in which at least one instruction is stored, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned photovoltaic power generation efficiency evaluation method based on drone detection data.

[0062] To solve the problems described in the background art, the embodiments of the present invention utilize a reference photovoltaic power generation unit group to obtain a reference coordinate set. Among them, the reference coordinate set includes multiple reference coordinates, and the reference coordinates correspond one-to-one with the reference photovoltaic power generation units. Based on the reference coordinate set, a fitting detection path sequence is obtained. Among them, the fitting detection path sequence includes one or more fitting detection paths. The fitting detection path includes multiple detection nodes, and the detection nodes include detection angles and detection coordinates. It can be seen that in the embodiments of the present invention, before evaluating the power generation efficiency of the reference photovoltaic power generation unit, it is considered that the positions of the reference photovoltaic power generation units may be different. Therefore, the embodiments of the present invention combine the energy consumption that the detection unmanned aerial vehicle can store and plan a path for realizing the reference photovoltaic power generation units in the reference photovoltaic power generation unit group. Furthermore, through the fitting detection path, it is possible to detect the reference photovoltaic power generation unit and ensure the safety of the detection unmanned aerial vehicle and reduce the energy consumption required for detecting the reference photovoltaic power generation unit. Furthermore, the intelligence level of the embodiments of the present invention is improved. The embodiments of the present invention use the fitting detection paths in the fitting detection path sequence to drive the detection unmanned aerial vehicle in sequence and real-time monitor the unmanned aerial vehicle coordinates of the detection unmanned aerial vehicle during driving. When the unmanned aerial vehicle coordinates are the detection coordinates, a target photovoltaic image is obtained based on the detection angle corresponding to the detection node. The evaluation loss coefficient is obtained by using the target photovoltaic image, the data collection unit, the data analysis unit, and the data evaluation unit. The reference power generation efficiency is obtained based on the reference photovoltaic power generation unit corresponding to the detection node. The product of the evaluation loss coefficient and the reference power generation efficiency is calculated to obtain the evaluation power generation efficiency. It can be seen that when evaluating the power generation efficiency of the reference photovoltaic power generation unit, the embodiments of the present invention consider the ash covering situation, service life, ambient temperature, ambient humidity, and irradiation intensity of the reference photovoltaic power generation unit, and combine the factors that may affect the reference photovoltaic power generation unit to fit different loss coefficients. Furthermore, the accuracy of evaluating the power generation efficiency of the reference photovoltaic power generation unit is improved. Therefore, the present invention can intelligently and accurately evaluate the photovoltaic power generation efficiency. Description of the Drawings

[0063] Figure 1 It is a schematic flowchart of a method for evaluating photovoltaic power generation efficiency based on unmanned aerial vehicle detection data provided by an embodiment of the present invention;

[0064] Figure 2 It is a functional module diagram of a system for evaluating photovoltaic power generation efficiency based on unmanned aerial vehicle detection data provided by an embodiment of the present invention;

[0065] Figure 3 It is a schematic structural diagram of an electronic device for implementing the method for evaluating photovoltaic power generation efficiency based on unmanned aerial vehicle detection data provided by an embodiment of the present invention.

[0066] Description of the Reference Numerals:

[0067] 1. Electronic device; 10. Processor; 11. Memory; 12. Bus;

[0068] 100. Photovoltaic power generation efficiency evaluation system based on drone detection data; 101. Evaluation environment confirmation module; 102. Detection path fitting module; 103. Photovoltaic image detection module; 104. Power generation efficiency evaluation module.

[0069] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Specific embodiments

[0070] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0071] An embodiment of the present application provides a method for evaluating the photovoltaic power generation efficiency based on drone detection data. The execution subject of the method for evaluating the photovoltaic power generation efficiency based on drone detection data includes, but is not limited to, at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for evaluating the photovoltaic power generation efficiency based on drone detection data can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0072] Refer to Figure 1 As shown, it is a flowchart of a method for evaluating the photovoltaic power generation efficiency based on drone detection data provided by an embodiment of the present invention. In this embodiment, the method for evaluating the photovoltaic power generation efficiency based on drone detection data includes:

[0073] S1. Receive an efficiency evaluation instruction, and confirm an efficiency evaluation environment based on the efficiency evaluation instruction. Among them, the efficiency evaluation environment includes a detection drone, a reference photovoltaic power generation unit group and an efficiency evaluation system. Among them, the efficiency evaluation system includes: a data collection unit, a data analysis unit, a data evaluation unit and a result feedback unit. Among them, the reference photovoltaic power generation unit group includes a plurality of reference photovoltaic power generation units.

[0074] It should be explained that the efficiency evaluation instruction refers to the instruction used to evaluate the photovoltaic power generation efficiency. The efficiency evaluation environment refers to the necessary environment for evaluating the photovoltaic power generation efficiency, and the efficiency evaluation environment includes a detection drone, a reference photovoltaic power generation unit group, and an efficiency evaluation system. The detection drone refers to the drone used to collect data on the reference photovoltaic power generation unit group in the efficiency evaluation environment. The reference photovoltaic power generation unit group refers to the set of reference photovoltaic power generation units to be evaluated for efficiency. The reference photovoltaic power generation unit refers to the photovoltaic power generation unit, which is the core part of the photovoltaic power generation system and is responsible for converting the photon energy in sunlight into electrical energy. The efficiency evaluation system refers to the APP or applet used to evaluate the efficiency of the reference photovoltaic power generation unit group, and the efficiency evaluation system includes: a data collection unit, a data analysis unit, a data evaluation unit, and a result feedback unit. For the specific application of the unit, please refer to the following embodiments.

[0075] Exemplarily, as the person in charge of the photovoltaic power generation system, in order to improve the power generation efficiency of the photovoltaic power generation system, Zhang issues the efficiency evaluation instruction after installing the photovoltaic power generation unit, and Zhang confirms the efficiency evaluation environment. By adjusting the angles of the reference photovoltaic power generation units in the reference photovoltaic power generation unit group in the efficiency evaluation environment, the angle with the highest power generation efficiency of each reference photovoltaic power generation unit in the reference photovoltaic power generation unit group can be determined, and the reference photovoltaic power generation unit is adjusted at this angle to improve the power generation efficiency of the photovoltaic power generation system.

[0076] S2. Obtain a reference coordinate set by using the reference photovoltaic power generation unit group. Among them, the reference coordinate set includes multiple reference coordinates, and the reference coordinates correspond to the reference photovoltaic power generation units one by one. Based on the reference coordinate set, obtain a fitting detection path sequence. Among them, the fitting detection path sequence includes one or more fitting detection paths, and the fitting detection path includes multiple detection nodes, and the detection nodes include detection angles and detection coordinates.

[0077] It should be explained that the reference coordinate refers to the coordinate used to represent the reference photovoltaic power generation unit. Optionally, a three-dimensional coordinate is used as the reference coordinate.

[0078] Furthermore, the obtaining of the fitting detection path sequence based on the reference coordinate set includes:

[0079] Confirm the reference regression coordinates as the starting point and the ending point, and use the pre-constructed clustering method to cluster the reference coordinates in the reference coordinate set to obtain one or more clustering coordinate sets;

[0080] One or more cluster center coordinates are identified based on one or more sets of cluster coordinates, where the cluster center coordinates correspond one-to-one with the sets of cluster coordinates. The Euclidean distance between each cluster center coordinate in the one or more cluster center coordinates and a reference regression coordinate is calculated to obtain a retrieval order distance. The retrieval order distances are aggregated to obtain a set of retrieval order distances. The retrieval order distances in the set of retrieval order distances are sorted in ascending order to obtain a retrieval order sequence. A retrieval coordinate group sequence is obtained based on the retrieval order sequence, where the retrieval coordinate group sequence includes one or more retrieval coordinate groups, and the retrieval coordinate groups correspond one-to-one with the retrieval order distances in the retrieval order sequence, and the retrieval coordinate groups correspond one-to-one with the sets of cluster coordinates.

[0081] Retrieval coordinate groups are sequentially extracted from the retrieval coordinate group sequence, and the following operations are performed on the extracted retrieval coordinate groups:

[0082] An identification coordinate group is obtained based on the retrieval coordinate group, where the identification coordinate group includes a plurality of identification coordinates, and the identification coordinates correspond one-to-one with the reference coordinates.

[0083] A path fitting model for fitting a path is obtained. The fitting path is obtained by using the path fitting model and the identification coordinate group. A plurality of detection nodes are identified in the fitting path by using the identification coordinates in the identification coordinate group to obtain an initial divided path. A fitting detection path is obtained based on the initial divided path and the reference regression coordinate. The set of detected coordinates of the fitting detection path is identified. The set of detected coordinates is removed from the reference coordinate set, and the reference coordinate set after removing the set of detected coordinates is used as the reference coordinate set. Return to the step of clustering the reference coordinates in the reference coordinate set by using the pre-constructed clustering method to obtain one or more sets of cluster coordinates. The fitting detection paths are aggregated to obtain a set of fitting detection paths. The fitting detection paths in the set of fitting detection paths are sorted in the order of the time corresponding to obtaining the fitting detection paths from the earliest to the latest to obtain a fitting detection path sequence.

[0084] It should be explained that the reference regression coordinate refers to the coordinates corresponding to the position when the detection UAV departs and returns. For example, the detection UAV takes off from the base station, and after completing the detection of the reference photovoltaic power generation unit, it returns to the base station. Then the three-dimensional coordinates corresponding to the base station are the reference regression coordinates. The set of cluster coordinates refers to the set of reference coordinates after clustering obtained by clustering the reference coordinates in the reference coordinate set by using a clustering algorithm. Generally, the number of sets of cluster coordinates is related to the clustering algorithm adopted and the reference coordinates in the reference coordinate set. Optionally, the k-means clustering algorithm is used as the clustering method. The same effect can be achieved by using other technologies, which will not be elaborated here. For example, if the reference coordinates in the reference coordinate set are clustered into 3 clusters by using the k-means clustering algorithm, then the reference coordinates included in each cluster constitute the set of cluster coordinates.

[0085] Furthermore, the cluster center coordinates refer to the coordinates of the cluster center corresponding to the cluster coordinate set. The technology for identifying the cluster center coordinates in the cluster coordinate set is prior art and will not be elaborated here. The path fitting model refers to a model or method that can fit a path. Optionally, the ant colony algorithm is used as the path fitting model, and the same effect can be achieved by using other technologies, which will not be elaborated here. The identification coordinates refer to the reference coordinates after identification. The purpose of identifying the reference coordinates here is to distinguish the reference coordinates, and further improve the accuracy of path planning for the detection UAV. For example, if the retrieval coordinate group includes three reference coordinates, namely (1, 2, 1), (3, 2, 2), and (3, 5, 6), then identifying each of the three reference coordinates can obtain three identification coordinates, namely: 1-(1, 2, 1), 2-(3, 2, 2), and 3-(3, 5, 6).

[0086] It should be explained that the fitted path refers to the path obtained by using the path fitting model with each identification coordinate in the identification coordinate group as a necessary passing point. The detection node refers to the node corresponding to each reference photovoltaic power generation unit, and this node includes a detection angle for characterizing the inclination angle corresponding to the reference photovoltaic power generation unit and a detection coordinate for characterizing the coordinate corresponding to the reference photovoltaic power generation unit. The set of detected coordinates refers to the set of detection coordinates included in the fitted detection path. Here, the definition of the detection coordinate is the same as the definition of the reference coordinate and will not be elaborated here. Generally, when installing a photovoltaic power generation unit, the coordinates and inclination angle of the installed photovoltaic power generation unit will be recorded.

[0087] Furthermore, obtaining the fitted detection path based on the initial divided path and the reference regression coordinates includes:

[0088] Identify the first detection node in the initial divided path to obtain the initial detection node, use the identification coordinate and the reference regression coordinate corresponding to the initial detection node to obtain the initial flight distance, and use the initial detection node and the preset node step length to identify the fitted divided path in the initial divided path;

[0089] Extract the last detection node in the fitted divided path to obtain the regression detection node, and use the identification coordinate and the reference regression coordinate corresponding to the regression detection node to obtain the regression flight distance;

[0090] Identify the number of detection nodes in the fitted divided path to obtain the number of detection nodes, obtain the initial energy consumption of the detection UAV, and calculate the detection energy consumption based on the initial flight distance, the regression flight distance, the fitted divided path, and the number of detection nodes;

[0091] Calculate the product of the initial energy consumption and the preset energy consumption ratio to obtain the safe energy consumption threshold, and obtain the fitting detection path based on the detected energy consumption and the safe energy consumption threshold.

[0092] It can be understood that the initial flight distance refers to the distance required for the detection UAV to fly from the starting point to the first detection node that needs to be detected. Generally, before using the detection UAV for detection, relevant parameters of the detection UAV will be set. The relevant parameters include but are not limited to: the flight altitude of the detection UAV, the flight speed of the detection UAV, and the flight path of the detection UAV. Therefore, the initial flight distance can be calculated through the set relevant parameters, identification coordinates, and reference regression coordinates. For ease of understanding, here both the identification coordinates and the reference regression coordinates are processed as two-dimensional coordinates, and the flight path of the detection UAV is a straight line. Therefore, the path from the starting point of the detection UAV to the initial detection node can be divided into one or more line segments, and the distances of each line segment are accumulated to obtain the initial flight path.

[0093] It should be explained that the node progression step length refers to the number of detection nodes that can be selected in the initial divided path. For example, the value corresponding to the initial detection node in the initial divided path is 1, indicating that the initial detection node is the first detection node in the initial divided path. If the node progression step length is 1, the fitting divided path includes the first detection node in the initial divided path and the second detection node in the initial divided path. Here, the second detection node is the regression detection node, that is, the fitting divided path including two detection nodes can be confirmed in the initial divided path by using the node progression step length. Generally, the method for obtaining the regression flight distance is the same as the method for obtaining the initial flight distance, which will not be elaborated here.

[0094] Furthermore, the calculating the detected energy consumption based on the initial flight distance, regression flight distance, fitting divided path, and the number of detection nodes includes:

[0095] Obtain the fitting detection distance based on the fitting divided path, and calculate the detected energy consumption by using the fitting detection distance and a pre-constructed energy consumption evaluation relationship. The energy consumption evaluation relationship is as follows: ;

[0096] Wherein, represents the detected energy consumption, 、 are respectively the preset flight coefficient and hover coefficient, represents the number of detection nodes, represents the mass of the detection UAV, represents the distance that the detection UAV needs to fly during detection, 、 、 respectively represent the fitting detection path, the initial flight path, and the return flight path. represents the propulsion efficiency of the detection UAV. represents the optimal cruise speed. represents the flight speed of the UAV. represents the preset single hover time.

[0097] It should be explained that the acquisition method of the fitting detection path is the same as that of the initial flight path, which will not be elaborated here. The propulsion efficiency refers to the efficiency of the detection UAV during detection. Among them, the propulsion efficiency includes, but is not limited to: the propeller efficiency of the detection UAV, the motor efficiency of the detection UAV. Optionally, the propulsion efficiency is obtained through experiments. The same effect can be achieved by using other technologies, which will not be elaborated here. The flight coefficient refers to the parameters that will affect the flight of the detection UAV. Among them, the factors that will affect the flight of the detection UAV include, but are not limited to: the starting resistance coefficient of the detection UAV, the windward area of the detection UAV. The hover coefficient refers to the parameters that will affect the hover of the detection UAV. Among them, the factors that will affect the hover of the detection UAV include, but are not limited to: gravitational acceleration, air density. Optionally, the flight coefficient and the hover coefficient are respectively obtained by using the experimental calibration method. The same effect can be achieved by using other technologies, which will not be elaborated here. The optimal cruise speed is the speed at which the fuel consumption rate of the detection UAV is the lowest, the endurance time is the longest, or the comprehensive performance is the best under specific conditions. The flight speed refers to the actual set speed of the detection UAV during flight. The purpose of setting the single hover time is: to collect images of the environment where the reference photovoltaic power generation unit is located, and to measure the relevant coefficients of the environment where the reference photovoltaic power generation unit is located. Among them, the relevant coefficients include: irradiance intensity, ambient temperature, ambient humidity.

[0098] Further, the obtaining of the fitting detection path based on the detection energy consumption and the safety energy consumption threshold includes:

[0099] Compare the detection energy consumption with the safety energy consumption threshold. If the detection energy consumption is less than or equal to the safety energy consumption threshold, update the node step length using the preset iterative step value, and use the updated node step length as the node step length, and return to the step of using the initial detection node and the preset node step length to confirm the fitting division path in the initial division path until it is confirmed that the detection energy consumption is greater than the safety energy consumption threshold, and then summarize the detection energy consumption to obtain a detection energy consumption set;

[0100] Perform the following operations on each detection energy consumption in the detection energy consumption set:

[0101] Calculate the difference between the secure energy consumption threshold and the detection energy consumption to obtain the evaluation energy consumption. Aggregate the evaluation energy consumption to obtain an evaluation energy consumption set. Based on the evaluation energy consumption set, confirm the target evaluation energy consumption, where the target evaluation energy consumption is greater than or equal to 0, and the target evaluation energy consumption is the smallest evaluation energy consumption in the evaluation energy consumption set, and the fitting detection path is the fitting division path corresponding to the target evaluation energy consumption.

[0102] Understandably, when the detection energy consumption is less than the secure energy consumption threshold, it indicates that the detection UAV can complete the preset task and return safely. The iterative step value refers to the value used to increase the node step size. For example, if the node step size is 1 and the iterative step value is 2, the updated node step size is 3. Generally, each time the detection UAV conducts detection, it needs to fly over the initial flight distance and the return flight distance. Therefore, by combining the initial energy consumption of the detection UAV and maximizing the detection of detection nodes, the efficiency of the detection UAV during operation can be improved. Here, the form of confirming the fitting division path is adopted to improve the efficiency of the detection UAV during operation. The purpose of setting the energy consumption ratio is to improve the safety of the detection UAV during detection, that is, to ensure that the detection UAV can return safely. Optionally, the energy consumption ratio is a manually set value, and the same effect can be achieved using other technologies, which will not be elaborated here. The initial energy consumption refers to the energy stored in the detection UAV.

[0103] S3. Use the fitting detection paths in the fitting detection path sequence to drive the detection UAV in sequence, and real-time monitor the UAV coordinates of the detection UAV during driving. When the UAV coordinates are the detection coordinates, obtain the target photovoltaic image based on the detection angle corresponding to the detection node.

[0104] It should be understood that each fitting detection path in the fitting detection path sequence includes one or more detection nodes. Therefore, the fitting detection paths in the fitting detection path sequence can be used to drive the detection UAV in sequence, thereby realizing the detection of the reference photovoltaic power generation unit group. Generally, the embodiments of the present invention can also use multiple detection UAVs to detect the reference photovoltaic power generation units included in the fitting detection paths in the fitting detection path sequence, which will not be elaborated here. Optionally, the position of the detection UAV is detected by a GPS unit pre-installed in the detection UAV, that is, the UAV coordinates of the detection UAV are obtained in real time through the GPS unit. Generally, the UAV coordinates being the detection coordinates here means that the detection coordinates are the same as the UAV coordinates. For example, both the UAV coordinates and the detection coordinates are represented in the form of longitude and latitude. Then, when the longitude and latitude corresponding to the UAV coordinates are the same as the longitude and latitude corresponding to the detection coordinates, it is confirmed that the UAV coordinates are the detection coordinates.

[0105] It should be noted that obtaining the target photovoltaic image based on the detection angle corresponding to the detection node includes:

[0106] Obtaining an initial monitoring image based on a preset detection angle, and using a pre-constructed photovoltaic recognition model to extract an initial photovoltaic image from the initial monitoring image;

[0107] Using the detection angle corresponding to the detection node and the detection angle to correct the initial photovoltaic image to obtain the target photovoltaic image.

[0108] Furthermore, the detection angle refers to the angle used to implement photographing the environment. For example, by adopting the direction perpendicular to the ground to realize the acquisition of images in the environment. Therefore, the angle corresponding to the direction perpendicular to the ground is the detection angle, and the image in the environment collected is the initial monitoring image. The photovoltaic recognition model refers to a model that can recognize and extract the image corresponding to the reference photovoltaic power generation unit in the initial monitoring image. Optionally, a pre-trained neural network model is used as the photovoltaic recognition model. The same effect can be achieved by using other technologies, which will not be elaborated here. The initial photovoltaic image refers to the image used to represent the reference photovoltaic power generation unit recognized by the photovoltaic recognition model in the initial detection image. Using the detection angle corresponding to the detection node and the detection angle to correct the initial photovoltaic image means: correcting the initial photovoltaic image into an image used to represent the front of the reference photovoltaic power generation unit, that is, when the corrected initial photovoltaic image is perpendicular to the reference photovoltaic power generation unit, the photographed image. Here, the corrected initial photovoltaic image is the target photovoltaic image. Optionally, the correction of the initial photovoltaic image is realized by combining the detection angle and the detection angle through a geometric correction method. The same effect can be achieved by using other technologies, which will not be elaborated here.

[0109] It can be understood that when collecting images of the reference photovoltaic power generation unit, directly photographing the reference photovoltaic power generation unit at an angle perpendicular to the reference photovoltaic power generation unit may also cause noise in the initial photovoltaic image due to sunlight reflection. Therefore, by adopting the form of setting the detection angle to obtain the initial photovoltaic image, the accuracy of the initial photovoltaic image can be improved, and further, it lays a foundation for the subsequent evaluation of the power generation efficiency of the reference photovoltaic power generation unit.

[0110] S4. Obtaining an evaluation loss coefficient by using the target photovoltaic image, the data collection unit, the data analysis unit and the data evaluation unit.

[0111] It should be noted that obtaining the evaluation loss coefficient by using the target photovoltaic image, the data collection unit, the data analysis unit and the data evaluation unit includes:

[0112] Confirm receiving the data collection instruction from the data collection unit, parse the data collection instruction to obtain a grayscale gradient set, where the grayscale gradient set includes multiple gradient grayscale values;

[0113] Confirm receiving the data evaluation instruction from the data evaluation unit, parse the data evaluation instruction to obtain a reference grayscale range;

[0114] Obtain multiple first reference grayscale values based on the preset extraction value and the reference grayscale range, and perform the following operations on each of the multiple first reference grayscale values:

[0115] Identify the fitted photovoltaic unit based on the first reference grayscale value, obtain the fitted loss efficiency using the fitted photovoltaic unit, associate the first reference grayscale value and the fitted loss efficiency to obtain a fitted coordinate, and summarize the fitted coordinates to obtain a fitted coordinate set;

[0116] Confirm receiving the data analysis instruction from the data analysis unit, parse the data analysis instruction to obtain a curve fitting model, map all the fitted coordinates in the fitted coordinate set to a pre-constructed reference coordinate system to obtain a mapped coordinate set, and use the curve fitting model and the mapped coordinate set to obtain a fitted loss curve;

[0117] Perform grayscale transformation on the target photovoltaic image to obtain a target grayscale image;

[0118] Obtain one or more fitted region image groups based on the target grayscale image, the pre-constructed region growing algorithm, and the grayscale gradient set. The fitted region image group includes one or more initial fitted region images, and the fitted region image group corresponds one-to-one with the gradient grayscale value;

[0119] Perform the following operations on each of the one or more fitted region image groups:

[0120] Obtain the fitted image area based on the one or more initial fitted region images corresponding to the fitted region image group, obtain the target image area of the target photovoltaic image, calculate the ratio of the fitted image area to the target image area to obtain a fitted ratio;

[0121] Obtain the fitted grayscale mean value based on the fitted region image group, and use the fitted grayscale mean value to retrieve the target loss efficiency in the fitted loss curve;

[0122] Associate the target loss efficiency and the fitted ratio to obtain a target loss node, summarize the target loss nodes to obtain a target loss node set, and use the target loss node set to calculate the evaluation loss coefficient.

[0123] It is understandable that the gradient gray value is the gray value used to evaluate the ash covering condition on the surface of the reference photovoltaic power generation unit. The reference gray range is the range of gray values of the surface of the reference photovoltaic power generation unit after ash covering. Optionally, the reference gray range is obtained by manual setting. Optionally, using the linear interval method and the extracted value, multiple first reference gray values are extracted from the reference gray range. For example, if the reference gray range is (0, 10) and the extracted value is 5, then using the linear interval method, 5 first reference gray values can be extracted from the reference gray range, and the 5 first reference gray values are respectively: 0, 2.5, 5, 7.5, and 10. The fitting photovoltaic power generation unit refers to a photovoltaic power generation unit with ash covering on its surface, and the gray value of the image corresponding to the ash covering condition of the fitting photovoltaic power generation unit is the first reference gray value. Optionally, a fitting photovoltaic power generation unit is constructed using dust simulation materials, photovoltaic power generation units, and the first reference gray value.

[0124] It should be explained that the fitting loss efficiency refers to the ratio of the actual power of the fitting photovoltaic power generation unit to the rated power. The curve fitting model is a model used to fit multiple discrete points into a curve. Optionally, a polynomial fitting model is used as the curve fitting model. The same effect can be achieved using other techniques and will not be elaborated here. Optionally, a two-dimensional coordinate system is used as the reference coordinate system. The same effect can be achieved using other techniques and will not be elaborated here. The region growing algorithm is an existing technology and will not be elaborated here.

[0125] It should be understood that the fitting image area is used to characterize the total area of the initial fitting area images in the fitting area image group. Optionally, the number of pixel points is used as the fitting image area. The same effect can be achieved using other techniques and will not be elaborated here. Generally, the fitting image area corresponding to one or more fitting area image groups is the target image area. The target image area is used to characterize the area of the target photovoltaic image, and the acquisition method of the target image area is the same as that of the fitting image area and will not be elaborated here. Gray-scale transformation refers to the technology of converting a color image into a gray image, and gray-scale transformation is an existing technology and will not be elaborated here.

[0126] Furthermore, the fitting gray mean value is the mean value of the gray values of one or more initial fitting area images corresponding to the fitting area image group. For example, if the fitting area image group includes 3 initial fitting area images, then the fitting gray mean value is the mean value of the gray values corresponding to the 3 initial fitting area images.

[0127] It is understandable that retrieving the target loss efficiency in the fitting loss curve using the fitting gray mean value means: retrieving the fitting loss efficiency corresponding to the gray value equal to the fitting gray mean value in the fitting loss curve.

[0128] Further, the evaluation loss coefficient is calculated by using the target loss node set, and the calculation formula is as follows: ;

[0129] wherein, represents the evaluation loss coefficient, represents that there are target loss nodes in the target loss node set, , respectively represent the fitting ratio and the target loss efficiency corresponding to the th target loss node in the target loss node set.

[0130] S5. Obtain the reference power generation efficiency based on the reference photovoltaic power generation unit corresponding to the detection node.

[0131] It should be explained that obtaining the reference power generation efficiency based on the reference photovoltaic power generation unit corresponding to the detection node includes:

[0132] Obtain the reference environmental data of the reference photovoltaic power generation unit, wherein the reference environmental data includes: irradiation intensity, environmental temperature and environmental humidity;

[0133] Obtain the predicted power generation efficiency based on the reference environmental data and the pre-trained efficiency prediction model;

[0134] Obtain the service life of the reference photovoltaic power generation unit, obtain the service life loss coefficient based on the service life, and calculate the product of the service life loss coefficient and the predicted power generation efficiency to obtain the reference power generation efficiency.

[0135] It can be understood that the service life refers to the time when the reference photovoltaic power generation unit is put into use. Optionally, the service life loss coefficient is obtained through an empirical model and the service life. The same effect can be achieved by using other technologies, which will not be elaborated here. The service life loss coefficient is a parameter related to the service life, and this parameter is used to express the ratio of the actual power generation power of the reference photovoltaic power generation unit to the rated power after a period of time.

[0136] Further, the efficiency prediction model is a model used to predict the ratio between the actual power generation power and the rated power generation power of the reference photovoltaic power generation unit under the reference environmental data. Optionally, a short-term prediction digital twin model is used as the efficiency prediction model. The same effect can be achieved by using other technologies, which will not be elaborated here. The predicted power generation efficiency is the ratio between the actual power generation power and the rated power generation power of the reference photovoltaic power generation unit under the reference environmental data.

[0137] It should be noted that the irradiation intensity refers to the solar irradiation energy received per unit area per unit time of the reference photovoltaic power generation unit. The ambient temperature and ambient humidity respectively refer to the temperature and humidity in the environment corresponding to the reference photovoltaic power generation unit.

[0138] S6. Calculate the product of the evaluation loss coefficient and the reference power generation efficiency to obtain the evaluation power generation efficiency, and use the result feedback unit to send the evaluation power generation efficiency to the initiator of the efficiency evaluation instruction, so as to realize the evaluation of the power generation efficiency of the reference photovoltaic power generation unit group.

[0139] It should be noted that the evaluation power generation efficiency is used to represent the ratio of the power generation power of the reference photovoltaic power generation unit to the rated power.

[0140] To solve the problems described in the background art, the embodiments of the present invention use a reference photovoltaic power generation unit group to obtain a reference coordinate set. Among them, the reference coordinate set includes multiple reference coordinates, and the reference coordinates correspond to the reference photovoltaic power generation units one by one. Based on the reference coordinate set, a fitting detection path sequence is obtained. Among them, the fitting detection path sequence includes one or more fitting detection paths, and the fitting detection path includes multiple detection nodes, and the detection nodes include detection angles and detection coordinates. It can be seen that in the embodiments of the present invention, before realizing the evaluation of the power generation efficiency of the reference photovoltaic power generation unit, it is considered that the positions of the reference photovoltaic power generation units may be different. Therefore, the embodiments of the present invention combine the energy consumption that the detection unmanned aerial vehicle can store and plan a path for realizing the reference photovoltaic power generation unit in the reference photovoltaic power generation unit group. Furthermore, through the fitting detection path, the detection of the reference photovoltaic power generation unit can be realized, and the safety of the detection unmanned aerial vehicle can be ensured and the energy consumption required for detecting the reference photovoltaic power generation unit can be reduced. Furthermore, the degree of intelligence of the embodiments of the present invention is improved. The embodiments of the present invention use the fitting detection paths in the fitting detection path sequence to drive the detection unmanned aerial vehicle in turn, and monitor the unmanned aerial vehicle coordinates of the detection unmanned aerial vehicle in real time during the driving. When the unmanned aerial vehicle coordinates are the detection coordinates, a target photovoltaic image is obtained based on the detection angle corresponding to the detection node. An evaluation loss coefficient is obtained by using the target photovoltaic image, the data collection unit, the data analysis unit and the data evaluation unit. The reference power generation efficiency is obtained based on the reference photovoltaic power generation unit corresponding to the detection node. The product of the evaluation loss coefficient and the reference power generation efficiency is calculated to obtain the evaluation power generation efficiency. It can be seen that in the embodiments of the present invention, when evaluating the power generation efficiency of the reference photovoltaic power generation unit, the dust covering condition, service life, ambient temperature, ambient humidity and irradiation intensity of the reference photovoltaic power generation unit are considered, and different loss coefficients are fitted in combination with the factors that may affect the reference photovoltaic power generation unit. Furthermore, the accuracy of evaluating the power generation efficiency of the reference photovoltaic power generation unit is improved. Therefore, the present invention can intelligently and accurately realize the evaluation of the photovoltaic power generation efficiency.

[0141] Such asFigure 2 As shown in the figure, it is a functional block diagram of a photovoltaic power generation efficiency evaluation system based on UAV detection data provided by an embodiment of the present invention.

[0142] The photovoltaic power generation efficiency evaluation system 100 based on UAV detection data of the present invention can be installed in an electronic device. According to the realized functions, the photovoltaic power generation efficiency evaluation system 100 based on UAV detection data can include an evaluation environment confirmation module 101, a detection path fitting module 102, a photovoltaic image detection module 103, and a power generation efficiency evaluation module 104. The modules of the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

[0143] The evaluation environment confirmation module 101 is configured to receive an efficiency evaluation instruction, and confirm an efficiency evaluation environment based on the efficiency evaluation instruction. The efficiency evaluation environment includes a detection UAV, a reference photovoltaic power generation unit group, and an efficiency evaluation system. The efficiency evaluation system includes: a data collection unit, a data analysis unit, a data evaluation unit, and a result feedback unit. The reference photovoltaic power generation unit group includes multiple reference photovoltaic power generation units;

[0144] The detection path fitting module 102 is configured to obtain a reference coordinate set by using the reference photovoltaic power generation unit group. The reference coordinate set includes multiple reference coordinates, and the reference coordinates correspond to the reference photovoltaic power generation units one by one. Based on the reference coordinate set, a fitting detection path sequence is obtained. The fitting detection path sequence includes one or more fitting detection paths. The fitting detection path includes multiple detection nodes, and the detection nodes include detection angles and detection coordinates;

[0145] The photovoltaic image detection module 103 is configured to sequentially drive the detection UAV by using the fitting detection paths in the fitting detection path sequence, and real-time monitor the UAV coordinates of the detection UAV during driving. When the UAV coordinates are the detection coordinates, a target photovoltaic image is obtained based on the detection angle corresponding to the detection node;

[0146] The power generation efficiency evaluation module 104 is configured to obtain an evaluation loss coefficient by using the target photovoltaic image, the data collection unit, the data analysis unit, and the data evaluation unit;

[0147] Obtain a reference power generation efficiency based on the reference photovoltaic power generation unit corresponding to the detection node;

[0148] Calculate the product of the evaluation loss coefficient and the reference power generation efficiency to obtain an evaluation power generation efficiency, and use the result feedback unit to send the evaluation power generation efficiency to the initiator of the efficiency evaluation instruction to realize the evaluation of the power generation efficiency of the reference photovoltaic power generation unit group.

[0149] Specifically, when the modules in the photovoltaic power generation efficiency evaluation system 100 based on UAV detection data in the embodiments of the present invention are used, they adopt the same technical means as those in the above Figure 1 photovoltaic power generation efficiency evaluation method based on UAV detection data, and can produce the same technical effects, which will not be elaborated here.

[0150] As Figure 3 shown, it is a schematic structural diagram of an electronic device for implementing the photovoltaic power generation efficiency evaluation method based on UAV detection data provided by an embodiment of the present invention.

[0151] The electronic device 1 may include a processor 10, a memory 11, and a bus 12, and may further include a computer program stored in the memory 11 and executable on the processor 10, such as a photovoltaic power generation efficiency evaluation method program based on UAV detection data.

[0152] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disc, etc. The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as the mobile hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 1. Further, the memory 11 also includes the internal storage unit of the electronic device 1 and the external storage device. The memory 11 can not only be used to store application software installed on the electronic device 1 and various types of data, such as the code of the photovoltaic power generation efficiency evaluation method program based on UAV detection data, but also be used to temporarily store data that has been output or will be output.

[0153] In some embodiments, the processor 10 may be composed of an integrated circuit. For example, it may be composed of a single packaged integrated circuit, or may be composed of multiple packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, connecting various components of the entire electronic device through various interfaces and circuits, and by running or executing programs or modules stored in the memory 11 (such as a program for evaluating the photovoltaic power generation efficiency based on drone detection data, etc.), and calling the data stored in the memory 11, to execute various functions of the electronic device 1 and process data.

[0154] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is set to enable connection communication between the memory 11 and at least one processor 10, etc.

[0155] Figure 3 Only the electronic device with components is shown. Those skilled in the art can understand that Figure 3 the shown structure does not constitute a limitation on the electronic device 1, and it may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0156] For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for powering each component. Preferably, the power source can be logically connected to the at least one processor 10 through a power management system, so as to implement functions such as charge management, discharge management, and power consumption management through the power management system. The power source may also include any components such as one or more DC or AC power sources, a recharge system, a power failure detection circuit, a power converter or inverter, a power status indicator, etc. The electronic device 1 may also include various sensors, a Bluetooth module, a Wi-Fi module, etc., which will not be elaborated here.

[0157] Furthermore, the electronic device 1 may further include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used to establish a communication connection between the electronic device 1 and other electronic devices.

[0158] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display the information processed in the electronic device 1 and to display a visual user interface.

[0159] The program of the photovoltaic power generation efficiency evaluation method based on the drone detection data stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0160] Receive an efficiency evaluation instruction, and confirm an efficiency evaluation environment based on the efficiency evaluation instruction. Among them, the efficiency evaluation environment includes a detection drone, a reference photovoltaic power generation unit group, and an efficiency evaluation system. The efficiency evaluation system includes: a data collection unit, a data analysis unit, a data evaluation unit, and a result feedback unit. Among them, the reference photovoltaic power generation unit group includes multiple reference photovoltaic power generation units;

[0161] Use the reference photovoltaic power generation unit group to obtain a reference coordinate set. Among them, the reference coordinate set includes multiple reference coordinates, and the reference coordinates correspond to the reference photovoltaic power generation units one by one. Based on the reference coordinate set, obtain a fitting detection path sequence. Among them, the fitting detection path sequence includes one or more fitting detection paths, and the fitting detection path includes multiple detection nodes, and the detection nodes include detection angles and detection coordinates;

[0162] Use the fitting detection paths in the fitting detection path sequence to drive the detection drone in sequence, and real-time monitor the drone coordinates of the detection drone during the driving. When the drone coordinates are the detection coordinates, obtain a target photovoltaic image based on the detection angle corresponding to the detection node;

[0163] Use the target photovoltaic image, the data collection unit, the data analysis unit, and the data evaluation unit to obtain an evaluation loss coefficient;

[0164] Obtain a reference power generation efficiency based on the reference photovoltaic power generation unit corresponding to the detection node;

[0165] Calculate the product of the evaluation loss coefficient and the reference power generation efficiency to obtain an evaluation power generation efficiency, and use the result feedback unit to send the evaluation power generation efficiency to the initiator of the efficiency evaluation instruction, so as to realize the evaluation of the power generation efficiency of the reference photovoltaic power generation unit group.

[0166] Specifically, for the specific implementation method of the above instructions by the processor 10, reference may be made to Figures 1 to 3 the description of the relevant steps in the corresponding embodiment, which will not be elaborated here.

[0167] Furthermore, if the modules / units integrated in the electronic device 1 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or system capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory).

[0168] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by the processor of the electronic device, it can implement:

[0169] Receiving an efficiency evaluation instruction, and determining an efficiency evaluation environment based on the efficiency evaluation instruction. The efficiency evaluation environment includes a detection unmanned aerial vehicle (UAV), a reference photovoltaic power generation unit group, and an efficiency evaluation system. The efficiency evaluation system includes: a data collection unit, a data analysis unit, a data evaluation unit, and a result feedback unit. The reference photovoltaic power generation unit group includes multiple reference photovoltaic power generation units;

[0170] Obtaining a reference coordinate set by using the reference photovoltaic power generation unit group. The reference coordinate set includes multiple reference coordinates, and the reference coordinates correspond to the reference photovoltaic power generation units one by one. Obtaining a fitted detection path sequence based on the reference coordinate set. The fitted detection path sequence includes one or more fitted detection paths. The fitted detection path includes multiple detection nodes, and the detection nodes include detection angles and detection coordinates;

[0171] Driving the detection UAV in sequence by using the fitted detection paths in the fitted detection path sequence, and real-time monitoring the UAV coordinates of the detection UAV during driving. When the UAV coordinates are the detection coordinates, obtaining a target photovoltaic image based on the detection angle corresponding to the detection node;

[0172] Obtaining an evaluation loss coefficient by using the target photovoltaic image, the data collection unit, the data analysis unit, and the data evaluation unit;

[0173] Obtaining a reference power generation efficiency based on the reference photovoltaic power generation unit corresponding to the detection node;

[0174] Calculate the product of the evaluation depreciation coefficient and the reference power generation efficiency to obtain the evaluation power generation efficiency, and use the result feedback unit to send the evaluation power generation efficiency to the initiator of the efficiency evaluation instruction, so as to realize the evaluation of the power generation efficiency of the reference photovoltaic power generation unit group.

[0175] In several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and there may be other partitioning methods in actual implementation.

[0176] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0177] In addition, the functional modules in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a hardware plus software functional module.

[0178] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0179] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A photovoltaic power generation efficiency evaluation method based on drone detection data, characterized in that: The method comprises: receiving an efficiency evaluation instruction, and confirming an efficiency evaluation environment based on the efficiency evaluation instruction, wherein the efficiency evaluation environment includes a detection drone, a reference photovoltaic power generation unit group, and an efficiency evaluation system, wherein the efficiency evaluation system includes: a data collection unit, a data analysis unit, a data evaluation unit, and a result feedback unit, wherein the reference photovoltaic power generation unit group includes a plurality of reference photovoltaic power generation units; A reference coordinate set is obtained by using a reference photovoltaic power generation unit group, wherein the reference coordinate set includes a plurality of reference coordinates, and the reference coordinates correspond to the reference photovoltaic power generation units one by one, and a fitting detection path sequence is obtained based on the reference coordinate set, wherein the fitting detection path sequence includes one or more fitting detection paths, the fitting detection path includes a plurality of detection nodes, and the detection nodes include detection angles and detection coordinates; The acquiring of a fitting detection path sequence based on the reference coordinate set comprises: Identify reference regression coordinates as a starting point and an end point, and cluster the reference coordinates in the reference coordinate set using a pre-constructed clustering method to obtain one or more clustered coordinate sets; One or more cluster center coordinates are identified based on one or more cluster coordinate sets, wherein the cluster center coordinates correspond one-to-one to the cluster coordinate sets, the Euclidean distance between each of the one or more cluster center coordinates and the reference regression coordinates is calculated to obtain a retrieval order distance, the retrieval order distances are summarized to obtain a retrieval order distance set, the retrieval order distances in the retrieval order distance set are sorted in ascending order to obtain a retrieval order sequence, and a retrieval coordinate group sequence is obtained based on the retrieval order sequence, wherein the retrieval coordinate group sequence includes one or more retrieval coordinate groups, and the retrieval coordinate groups correspond one-to-one to the retrieval order distances in the retrieval order sequence, and the retrieval coordinate groups correspond one-to-one to the cluster coordinate sets; Extracting retrieval coordinate groups from the retrieval coordinate group sequence in sequence, and performing the following operations on the extracted retrieval coordinate groups: Acquire an identification coordinate group based on the search coordinate group, wherein the identification coordinate group includes a plurality of identification coordinates, and the identification coordinates correspond to the reference coordinates one by one; Obtain a path fitting model for fitting the path, obtain the fitting path using the path fitting model and the identification coordinate group, identify multiple detection nodes in the fitting path using the identification coordinates in the identification coordinate group to obtain an initial partition path, obtain a fitting detection path based on the initial partition path and the reference regression coordinates, identify an explored coordinate set of the fitting detection path, eliminate the explored coordinate set in the reference coordinate set, and use the reference coordinate set from which the explored coordinate set is eliminated as the reference coordinate set, return to the step of clustering the reference coordinates in the reference coordinate set using the pre-constructed clustering method to obtain one or more clustered coordinate sets, summarize the fitting detection paths to obtain a fitting detection path set, sort the fitting detection paths in the fitting detection path set in the order of the time corresponding to the acquisition of the fitting detection paths from the earliest to the latest, and obtain a fitting detection path sequence; The detection drones are sequentially driven using the fitting detection paths in the fitting detection path sequence, and the drone coordinates of the driving detection drones are monitored in real time, and when the drone coordinates are the detection coordinates, a target photovoltaic image is acquired based on the detection angle corresponding to the detection node; Obtaining an evaluation loss factor using a target photovoltaic image, a data collection unit, a data analysis unit, and a data evaluation unit; Acquiring a reference power generation efficiency based on a reference photovoltaic power generation unit corresponding to the detection node; The product of the evaluation loss coefficient and the reference power generation efficiency is calculated to obtain the evaluation power generation efficiency, and the result feedback unit is used to send the evaluation power generation efficiency to the initiator of the efficiency evaluation instruction to realize the power generation efficiency evaluation of the reference photovoltaic power generation unit group.

2. The photovoltaic power generation efficiency evaluation method based on drone detection data according to claim 1, characterized in that: The acquiring of the fitting detection path based on the initial segmentation path and the reference regression coordinates includes: Identify the first detection node in the initial partition path to obtain the initial detection node, obtain the initial flight distance using the identification coordinates and reference regression coordinates corresponding to the initial detection node, and identify the fitting partition path in the initial partition path using the initial detection node and the preset node progressive length; The last detection node is extracted from the fitting partition path to obtain a regression detection node, and the regression flight distance is obtained using the identification coordinates corresponding to the regression detection node and the reference regression coordinates; Identify the number of detection nodes in the fitting partition path, obtain the number of detection nodes, obtain the initial energy consumption of the detection UAV, and calculate the detection energy consumption based on the initial flight distance, the regression flight distance, the fitting partition path and the number of detection nodes; The product of the initial energy consumption and the preset energy consumption ratio is calculated to obtain a safe energy consumption threshold, and a fitting detection path is obtained based on the detection energy consumption and the safe energy consumption threshold.

3. The photovoltaic power generation efficiency evaluation method based on drone detection data as claimed in claim 2, characterized in that: The calculation of detection energy consumption based on the initial flight distance, the regression flight distance, the fitting division path and the number of detection nodes includes: The fitting detection distance is obtained based on the fitting partition path, and the detection energy consumption is calculated using the fitting detection distance and the pre-constructed energy consumption evaluation relationship, wherein the energy consumption evaluation relationship is as follows: ； in, represents the detection energy consumption, , They are the preset flight coefficient and hover coefficient respectively. Indicates the number of detection nodes, represents the quality of the detection drone, It indicates the distance that the detection drone needs to fly when conducting detection. , , They represent the fitting detection distance, the initial flight distance and the regression flight distance respectively, represents the propulsion efficiency of the detection drone, represents the optimal cruising speed, Indicates the flight speed of the drone. Indicates the preset single hover time.

4. The photovoltaic power generation efficiency evaluation method based on drone detection data as claimed in claim 3 is characterized in that: The acquiring a fitting detection path based on the detection energy consumption and the safety energy consumption threshold comprises: Compare the detected energy consumption with the safety energy consumption threshold. If the detected energy consumption is less than or equal to the safety energy consumption threshold, update the node incremental length using the preset iterative step value, and use the updated node incremental length as the node incremental length. Return to the step of using the initial detected node and the preset node incremental length to confirm the fitting partition path in the initial partition path, until it is confirmed that the detected energy consumption is greater than the safety energy consumption threshold, summarize the detected energy consumption, and obtain a detected energy consumption set. The following operations are performed for each detection energy consumption in the detection energy consumption set: Calculate the difference between the safety energy consumption threshold and the detection energy consumption to obtain the evaluation energy consumption, summarize the evaluation energy consumption, obtain the evaluation energy consumption set, and confirm the target evaluation energy consumption based on the evaluation energy consumption set, wherein the target evaluation energy consumption is greater than or equal to 0, and the target evaluation energy consumption is the minimum evaluation energy consumption in the evaluation energy consumption set, and the fitted detection path is the fitted partitioning path corresponding to the target evaluation energy consumption.

5. The photovoltaic power generation efficiency evaluation method based on drone detection data according to claim 4 is characterized in that: The step of acquiring a target photovoltaic image based on a detection angle corresponding to a detection node includes: An initial monitoring image is acquired based on a preset detection angle, and an initial photovoltaic image is extracted from the initial monitoring image using a pre-built photovoltaic recognition model; The initial photovoltaic image is corrected using the detection angle and detection angle corresponding to the detection node to obtain the target photovoltaic image.

6. The photovoltaic power generation efficiency evaluation method based on drone detection data according to claim 5, characterized in that: The method of obtaining the evaluation loss coefficient by using the target photovoltaic image, the data collection unit, the data analysis unit and the data evaluation unit includes: Confirming receipt of a data collection instruction from a data collection unit, parsing the data collection instruction, and obtaining a grayscale gradient set, wherein the grayscale gradient set includes a plurality of gradient grayscale values; Confirming receipt of a data evaluation instruction from a data evaluation unit, parsing the data evaluation instruction, and obtaining a reference grayscale range; A plurality of first reference grayscale values ​​are obtained based on a preset extraction value and a reference grayscale range, and the following operation is performed on each of the plurality of first reference grayscale values: Identify a fitted photovoltaic power generation unit based on a first reference grayscale value, obtain a fitted loss efficiency using the fitted photovoltaic power generation unit, associate the first reference grayscale value and the fitted loss efficiency to obtain a fitted coordinate, and summarize the fitted coordinates to obtain a fitted coordinate set; Confirming receipt of a data analysis instruction from a data analysis unit, parsing the data analysis instruction, obtaining a curve fitting model, mapping all fitting coordinates in the fitting coordinate set to a pre-constructed reference coordinate system to obtain a mapping coordinate set, and obtaining a fitting loss curve using the curve fitting model and the mapping coordinate set; Performing grayscale transformation on the target photovoltaic image to obtain a target grayscale image; Based on the target grayscale image, a pre-constructed region growing algorithm and a grayscale gradient set, one or more fitting region image groups are obtained, wherein the fitting region image groups include one or more initial fitting region images, and the fitting region image groups correspond to the gradient grayscale values ​​one by one; The following operations are performed on each of the one or more fitted region image groups: Acquire a fitting image area based on one or more initial fitting region images corresponding to the fitting region image group, acquire a target image area of ​​a target photovoltaic image, calculate a ratio of the fitting image area to the target image area, and obtain a fitting ratio; Obtaining a fitting grayscale mean value based on the fitting region image group, and using the fitting grayscale mean value to retrieve a target loss efficiency from the fitting loss curve; The target loss efficiency and the fitting ratio are associated to obtain a target loss node, the target loss nodes are summarized to obtain a target loss node set, and the target loss node set is used to calculate the evaluation loss coefficient.

7. The photovoltaic power generation efficiency evaluation method based on drone detection data according to claim 6, characterized in that: The target loss node set is used to calculate the evaluation loss coefficient, and the calculation formula is as follows: ； in, represents the assessment impairment coefficient, Indicates that the target damaged nodes have target damage nodes, , They represent the target damaged node set. The fitting ratio and target loss efficiency corresponding to each target loss node.

8. The photovoltaic power generation efficiency evaluation method based on drone detection data according to claim 7, characterized in that: The obtaining of a reference power generation efficiency based on a reference photovoltaic power generation unit corresponding to the detection node comprises: Acquire reference environmental data of a reference photovoltaic power generation unit, wherein the reference environmental data includes: irradiation intensity, ambient temperature and ambient humidity; Obtaining predicted power generation efficiency based on the reference environmental data and a pre-trained efficiency prediction model; The service life of the reference photovoltaic power generation unit is obtained, and the age depreciation coefficient is obtained based on the service life. The product of the age depreciation coefficient and the predicted power generation efficiency is calculated to obtain the reference power generation efficiency.

9. A photovoltaic power generation efficiency evaluation system based on drone detection data, characterized in that: The system comprises: An evaluation environment confirmation module is used to receive an efficiency evaluation instruction and confirm an efficiency evaluation environment based on the efficiency evaluation instruction, wherein the efficiency evaluation environment includes a detection drone, a reference photovoltaic power generation unit group and an efficiency evaluation system, wherein the efficiency evaluation system includes: a data collection unit, a data analysis unit, a data evaluation unit and a result feedback unit, wherein the reference photovoltaic power generation unit group includes a plurality of reference photovoltaic power generation units; A detection path fitting module is used to obtain a reference coordinate set using a reference photovoltaic power generation unit group, wherein the reference coordinate set includes a plurality of reference coordinates, and the reference coordinates correspond to the reference photovoltaic power generation units one by one, and obtain a fitting detection path sequence based on the reference coordinate set, wherein the fitting detection path sequence includes one or more fitting detection paths, and the fitting detection path includes a plurality of detection nodes, and the detection nodes include detection angles and detection coordinates; The acquiring of a fitting detection path sequence based on the reference coordinate set comprises: Identify reference regression coordinates as a starting point and an end point, and cluster the reference coordinates in the reference coordinate set using a pre-constructed clustering method to obtain one or more clustered coordinate sets; One or more cluster center coordinates are identified based on one or more cluster coordinate sets, wherein the cluster center coordinates correspond one-to-one to the cluster coordinate sets, the Euclidean distance between each of the one or more cluster center coordinates and the reference regression coordinates is calculated to obtain a retrieval order distance, the retrieval order distances are summarized to obtain a retrieval order distance set, the retrieval order distances in the retrieval order distance set are sorted in ascending order to obtain a retrieval order sequence, and a retrieval coordinate group sequence is obtained based on the retrieval order sequence, wherein the retrieval coordinate group sequence includes one or more retrieval coordinate groups, and the retrieval coordinate groups correspond one-to-one to the retrieval order distances in the retrieval order sequence, and the retrieval coordinate groups correspond one-to-one to the cluster coordinate sets; Extracting retrieval coordinate groups from the retrieval coordinate group sequence in sequence, and performing the following operations on the extracted retrieval coordinate groups: Acquire an identification coordinate group based on the search coordinate group, wherein the identification coordinate group includes a plurality of identification coordinates, and the identification coordinates correspond to the reference coordinates one by one; Obtain a path fitting model for fitting the path, obtain the fitting path using the path fitting model and the identification coordinate group, identify multiple detection nodes in the fitting path using the identification coordinates in the identification coordinate group to obtain an initial partition path, obtain a fitting detection path based on the initial partition path and the reference regression coordinates, identify an explored coordinate set of the fitting detection path, eliminate the explored coordinate set in the reference coordinate set, and use the reference coordinate set from which the explored coordinate set is eliminated as the reference coordinate set, return to the step of clustering the reference coordinates in the reference coordinate set using the pre-constructed clustering method to obtain one or more clustered coordinate sets, summarize the fitting detection paths to obtain a fitting detection path set, sort the fitting detection paths in the fitting detection path set in the order of the time corresponding to the acquisition of the fitting detection paths from the earliest to the latest, and obtain a fitting detection path sequence; A photovoltaic image detection module is used to sequentially drive the detection drone using the fitting detection paths in the fitting detection path sequence, and to monitor the drone coordinates of the driving detection drone in real time, and to obtain a target photovoltaic image based on the detection angle corresponding to the detection node when the drone coordinates are the detection coordinates; A power generation efficiency evaluation module, used to obtain an evaluation loss factor using a target photovoltaic image, a data collection unit, a data analysis unit, and a data evaluation unit; Acquiring a reference power generation efficiency based on a reference photovoltaic power generation unit corresponding to the detection node; The product of the evaluation loss coefficient and the reference power generation efficiency is calculated to obtain the evaluation power generation efficiency, and the result feedback unit is used to send the evaluation power generation efficiency to the initiator of the efficiency evaluation instruction to realize the power generation efficiency evaluation of the reference photovoltaic power generation unit group.

Images