Photovoltaic panel automatic cleaning system based on unmanned aerial vehicle

By using a system of drones and self-propelled cleaning robots in photovoltaic power plants to work in a photovoltaic power plant, the problems of low cleaning efficiency and poor risk resistance in large-scale photovoltaic power plants are solved, and efficient and safe photovoltaic panel cleaning is achieved.

CN118944587AActive Publication Date: 2024-11-12苏州中飞遥感技术服务有限公司

Patent Information

Application Number
CN202411404708.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-10
Publication Date
2024-11-12
Estimated Expiration
2044-10-10

AI Technical Summary

Technical Problem

In large-scale photovoltaic power plants, traditional manual cleaning methods are difficult to cover large-area photovoltaic panels, and the collaborative operation of self-propelled cleaning robots is complex, resulting in high coordination difficulty, low cleaning efficiency and poor risk resistance.

Method used

Adopting a drone-based photovoltaic panel automatic cleaning system, the communication link establishment module, real-time monitoring data acquisition module, initial cleaning strategy generation module, cleaning strategy synchronization module, collaborative operation setting module and job adaptive adjustment module to achieve unmanned The coordinated operation between the machine and the self-propelled cleaning robot is dynamically adjusted according to the stain characteristics and environmental conditions of the photovoltaic panel.

Benefits of technology

The level of collaborative operation has been optimized, cleaning efficiency and risk resistance have been improved, and the efficient cleaning and safety of photovoltaic panels have been ensured.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118944587A_ABST
    Figure CN118944587A_ABST
Patent Text Reader

Abstract

The invention discloses a photovoltaic panel automatic cleaning system based on an unmanned aerial vehicle, and relates to the technical field of photovoltaics, and the system comprises a communication link establishment module for establishing a communication network between an unmanned aerial vehicle control center and a plurality of photovoltaic self-propelled cleaning robots. And the real-time monitoring data acquisition module is connected with monitoring equipment of the photovoltaic power station and is used for acquiring a stain image of the photovoltaic panel and extracting stain characteristics. And the initial cleaning strategy generation module is used for outputting an initial cleaning strategy according to the stain characteristics. And the cleaning strategy synchronization module is used for synchronizing the initial cleaning strategy to the cleaning robot in the idle state through the communication network. And the collaborative operation setting module is used for setting a collaborative operation process according to the layout of the photovoltaic power station, the robot position information and the cleaning task distribution. And the operation self-adaptive adjustment module is used for introducing environmental conditions and setting a delayed take-off mechanism to adaptively update an initial cleaning strategy. Therefore, the technical effects of optimizing the collaborative level and improving the cleaning efficiency and the anti-risk capability are achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the field of photovoltaic technology, and in particular to an automatic cleaning system for photovoltaic panels based on an unmanned aerial vehicle. Background Art

[0002] In large-scale photovoltaic power stations, the cleaning and maintenance of photovoltaic panels is an important part of ensuring efficient power generation. The layout and environment of photovoltaic panels are not conducive to traditional manual cleaning methods, and it is difficult to cover a large area of ​​photovoltaic panels. Although self-propelled cleaning robots have improved cleaning efficiency, in large-scale photovoltaic power stations, the collaborative operation control between multiple robots is highly complex, making it difficult to complete cleaning tasks quickly and comprehensively. There are technical problems such as high difficulty in collaboration, low cleaning efficiency, and poor risk resistance. Summary of the invention

[0003] The present invention provides an automatic cleaning system for photovoltaic panels based on drones to solve the technical problems of high coordination difficulty, low cleaning efficiency and poor risk resistance in the prior art, and achieves the technical effect of optimizing the coordination level and improving the cleaning efficiency and risk resistance.

[0004] The present invention provides a photovoltaic panel automatic cleaning system based on a drone, comprising: A communication link establishment module is used to establish a two-way communication link between the drone control center and multiple photovoltaic self-propelled cleaning robots in a target photovoltaic power station, and set up a communication network.

[0005] A real-time monitoring data acquisition module is used to connect to the real-time monitoring equipment of the target photovoltaic power station, collect the photovoltaic panel stain image, and extract the photovoltaic panel stain characteristics, wherein the photovoltaic panel stain characteristics include stain distribution characteristics and pollution level characteristics.

[0006] An initial cleaning strategy generation module is used to output an initial cleaning strategy based on the photovoltaic panel stain characteristics, and the initial cleaning strategy includes a cleaning speed and customized cleaning tasks for cleaning key areas.

[0007] A cleaning strategy synchronization module, wherein the cleaning strategy synchronization module is used to synchronize the initial cleaning strategy to the multiple photovoltaic self-propelled cleaning robots based on the communication network when the drone status information received by the drone control center is in idle standby.

[0008] A collaborative operation setting module is used to set up a collaborative operation process according to the layout information of the target photovoltaic power station, the location information of the photovoltaic self-propelled cleaning robot, and the allocation information of the customized cleaning tasks.

[0009] The operation adaptive adjustment module is used to introduce environmental conditions. When the environmental conditions are not conducive to the cleaning operation, a delayed take-off mechanism is set and the initial cleaning strategy is adaptively updated with the safety of the cleaning operation as a constraint condition.

[0010] In a feasible implementation, the environmental conditions include wind speed and rainfall.

[0011] The environmental conditions are used to evaluate the degree of impact on the cleaning operation and obtain the impact factors.

[0012] The influencing factors and the environmental conditions are integrated to obtain an influencing index, and the influencing index is compared with a preset influencing index to determine whether to trigger the delayed takeoff mechanism.

[0013] In a feasible implementation, comparing the impact index with a preset impact index to determine whether to trigger the delayed takeoff mechanism includes: The data storage module is connected to extract the photovoltaic panel power generation efficiency of the target photovoltaic power station.

[0014] Based on the photovoltaic panel contamination characteristics and the photovoltaic panel power generation efficiency, a cleaning emergency constraint is generated, and the cleaning emergency constraint includes a cleaning priority mapping table.

[0015] The preset impact index is corrected by the cleaning emergency constraint.

[0016] In a feasible implementation, based on the photovoltaic panel stain characteristics and the photovoltaic panel power generation efficiency, a cleaning emergency constraint is generated, and the cleaning emergency constraint includes a cleaning priority mapping table, including: Based on the stain distribution characteristics in the photovoltaic panel stain characteristics and in combination with the photovoltaic panel power generation efficiency, a first associated node aggregation structure is generated.

[0017] Based on the pollution level feature in the photovoltaic panel stain feature and in combination with the photovoltaic panel power generation efficiency, a second associated node aggregation structure is generated.

[0018] The first associated node aggregation structure and the second associated node aggregation structure are hierarchically connected to construct a cleaning requirement network, and the time series features extracted from the cleaning requirement network form the cleaning priority mapping table.

[0019] In a feasible implementation, based on the stain distribution characteristics in the photovoltaic panel stain characteristics and in combination with the photovoltaic panel power generation efficiency, a first associated node aggregation structure is generated, including: The stain aggregation characteristics and the stain dispersion characteristics are determined by the stain distribution characteristics in the photovoltaic panel stain characteristics.

[0020] Based on the photovoltaic panel cleaning example, neighboring samples of the stain aggregation features are searched as a type of neighbor nodes.

[0021] Based on the photovoltaic panel cleaning example, neighboring samples of the stain dispersion characteristics are searched as second-class neighbor nodes.

[0022] A first associated node aggregation structure is generated by combining the first-class neighbor nodes and the second-class neighbor nodes with the photovoltaic panel power generation efficiency.

[0023] In a feasible implementation method, based on a photovoltaic panel cleaning example, neighbor nodes are collected as second-level neighbor nodes based on the first-level neighbor nodes in the first class of neighbor nodes, wherein the correlation strength between the first-level neighbor nodes in the first class of neighbor nodes and the photovoltaic panel power generation efficiency is greater than the correlation strength between the second-level neighbor nodes in the first class of neighbor nodes and the photovoltaic panel power generation efficiency.

[0024] Taking the second-level neighbor nodes as a reference, N-level neighbor nodes are repeatedly collected to determine the first-level neighbor nodes, the second-level neighbor nodes, ..., the N-level neighbor nodes in the first type of neighbor nodes.

[0025] In a feasible implementation, the first associated node aggregation structure is generated by combining the first type of neighbor nodes and the second type of neighbor nodes with the photovoltaic panel power generation efficiency, including: A positive stain influence gradient is established through the first-level neighbor nodes, the second-level neighbor nodes, ..., the N-level neighbor nodes in the first type of neighbor nodes.

[0026] A reverse stain influence gradient is established through the first-level neighbor nodes, the second-level neighbor nodes, ..., the M-level neighbor nodes in the second-level neighbor nodes.

[0027] The positive stain influence gradient and the reverse stain influence gradient are combined to generate the first associated node aggregation structure.

[0028] In a feasible implementation, a collaborative operation process is set according to the layout information of the target photovoltaic power station, the location information of the photovoltaic self-propelled cleaning robot, and the allocation information of the customized cleaning task, including: According to the layout information of the target photovoltaic power station, the photovoltaic panel inclination angle of the target photovoltaic power station is obtained.

[0029] The position information of the photovoltaic self-propelled cleaning robot is synchronized in real time through the inclination angle of the photovoltaic panel to evaluate the side slip risk probability and side slip distance.

[0030] The stability of the cleaning operation is evaluated through the sideslip risk probability and the sideslip distance. If the cleaning operation stability threshold in the safety of the cleaning operation is not met, the UAV flight assistance operation is activated to perform tilt angle adaptability optimization.

[0031] The present invention discloses an automatic cleaning system for photovoltaic panels based on drones, including: a communication link establishment module, in a target photovoltaic power station, establishes a two-way communication link between a drone control center and a plurality of photovoltaic self-propelled cleaning robots, and sets a communication network. A real-time monitoring data acquisition module connects to the monitoring equipment of the photovoltaic power station, collects the stain image of the photovoltaic panel and extracts the stain characteristics, including distribution and pollution level. An initial cleaning strategy generation module outputs an initial cleaning strategy according to the stain characteristics, including a cleaning speed and a customized cleaning task. When the drone is idle, a cleaning strategy synchronization module synchronizes the initial cleaning strategy to the cleaning robot through a communication network. A collaborative operation setting module sets a collaborative operation process according to the layout of the photovoltaic power station, the robot position information and the cleaning task allocation. An operation adaptive adjustment module introduces environmental conditions, and when the environment is not conducive to the cleaning operation, a delayed take-off mechanism is set to adaptively update the initial cleaning strategy. The automatic cleaning system for photovoltaic panels based on drones disclosed by the present invention solves the technical problems of high collaborative difficulty, low cleaning efficiency and poor risk resistance, and achieves the technical effect of optimizing the collaborative level and improving the cleaning efficiency and risk resistance. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 This is a schematic diagram of the structure of the automatic cleaning system for photovoltaic panels based on drones of the present invention; Figure 2 The present invention is a flowchart of generating cleaning emergency constraints in the unmanned aerial vehicle-based photovoltaic panel automatic cleaning system.

[0033] Explanation of the reference numerals: communication link establishing module 11 , real-time monitoring data collecting module 12 , initial cleaning strategy generating module 13 , cleaning strategy synchronization module 14 , collaborative operation setting module 15 , operation adaptive adjustment module 16 . DETAILED DESCRIPTION

[0034] The technical solution provided in the embodiments of the present invention is to solve the technical problems of high coordination difficulty, low cleaning efficiency and poor risk resistance in the prior art. The overall idea adopted is as follows: First, the communication link establishment module is used to establish a two-way communication link between the drone control center and multiple photovoltaic self-propelled cleaning robots in the target photovoltaic power station, and set up a communication network; then, the real-time monitoring data acquisition module connects to the real-time monitoring equipment of the target photovoltaic power station, collects the photovoltaic panel stain image, and extracts the stain characteristics, including the stain distribution characteristics and the pollution level characteristics; then, the initial cleaning strategy generation module outputs the initial cleaning strategy through the photovoltaic panel stain characteristics, and the strategy includes the cleaning speed and the key areas of the customized cleaning task; then, the cleaning strategy synchronization module synchronizes the initial cleaning strategy to multiple photovoltaic self-propelled cleaning robots based on the communication network when the drone status information is in idle standby; finally, the collaborative operation setting module sets up the collaborative operation process according to the layout information of the target photovoltaic power station, the location information of the cleaning robot and the customized cleaning task allocation information, and introduces the environmental conditions through the operation adaptive adjustment module, and adaptively updates the initial cleaning strategy with the safety of the cleaning operation as a constraint.

[0035] The above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods of the specification to better understand the above technical solution. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments used only to explain the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In addition, it should be noted that, for the convenience of description, only the parts related to the present invention are shown in the drawings, rather than all of them. Example

[0036] Figure 1 The structure diagram of the automatic cleaning system of photovoltaic panels based on drones of the present invention is shown in FIG. 1 , wherein the system comprises: The communication link establishing module 11 is used to establish a two-way communication link between the drone control center and a plurality of photovoltaic self-propelled cleaning robots in a target photovoltaic power station, and to set up a communication network.

[0037] Optionally, establish two-way communication between the drone control center and multiple photovoltaic self-propelled cleaning robots, including communication network architecture design, equipment connection, data transmission setting, information security protection, etc.

[0038] For example, first, select a suitable communication protocol (such as LoRa, Zigbee, Wi-Fi, etc.) to ensure the coverage and signal stability of the two-way communication link. Then, configure a communication module for each photovoltaic self-propelled cleaning robot to ensure that it can exchange data with the drone control center. Then, set the data transmission format and frequency, and information security measures to ensure the security of the communication link and prevent unauthorized access.

[0039] The real-time monitoring data acquisition module 12 is used to connect to the real-time monitoring equipment of the target photovoltaic power station, collect the photovoltaic panel stain image, and extract the photovoltaic panel stain features, wherein the photovoltaic panel stain features include stain distribution features and pollution level features.

[0040] Specifically, first connect the real-time monitoring device, where the real-time monitoring device is a high-resolution camera suitable for outdoor environments, used to obtain clear images under different lighting conditions. Optionally, the real-time monitoring device includes multiple fixed cameras installed at appropriate locations around the photovoltaic panels, or dynamic cameras installed on mobile inspection platforms (such as drones, balloons, satellites, etc.), to ensure that all photovoltaic panel areas can be covered.

[0041] Specifically, according to the set image acquisition frequency (such as once per hour), the photovoltaic panels of the target photovoltaic power station are imaged to obtain the photovoltaic panel stain images to ensure the effectiveness of real-time monitoring.

[0042] Furthermore, the photovoltaic panel stain image is preprocessed (such as denoising, contrast enhancement, etc.), and the photovoltaic panel stain feature is extracted. The photovoltaic panel stain feature includes a stain distribution feature and a pollution level feature. Optionally, the stain distribution feature includes the area, shape, and position of the stain (including the absolute position of the photovoltaic panel and the relative position of the corresponding stain on the panel). The pollution level feature is used to characterize the severity of the stain on the photovoltaic panel, and the pollution level feature is determined based on the area, position, type, and existence time of the stain.

[0043] For example, the detection of photovoltaic panel stain features first obtains a grayscale image of the photovoltaic panel stain image, and uses the Canny edge detection algorithm to identify the stain edge in the photovoltaic panel stain image. Then, use an image segmentation algorithm (such as Otsu threshold segmentation, K-means clustering segmentation) to segment the stain area from the background to obtain multiple stain area images and then extract the stain distribution characteristics; then, call the full-color images corresponding to the multiple stain area images to obtain the color characteristics of the stains, and then combine the stain distribution characteristics to determine the pollution level characteristics of the stains.

[0044] Through the above steps, real-time monitoring and feature extraction of photovoltaic panel stains can be achieved, so as to timely identify and deal with stain problems and ensure the efficient operation of photovoltaic power stations.

[0045] The initial cleaning strategy generating module 13 is used to output an initial cleaning strategy according to the photovoltaic panel stain characteristics, wherein the initial cleaning strategy includes a cleaning speed and customized cleaning tasks for cleaning key areas.

[0046] Specifically, the initial cleaning strategy includes the cleaning speed and customized cleaning tasks for key cleaning areas. The initial cleaning strategy is determined based on the characteristics of stains on the photovoltaic panel. For example, the cleaning speed of higher-level or more difficult-to-clean stains (such as oil stains or dirt) is slower to ensure the cleaning effect. For lighter stains such as dust, a faster cleaning speed is set to improve work efficiency.

[0047] Specifically, customized cleaning tasks are set according to the stain characteristics of different photovoltaic panel areas. This includes: increasing the cleaning intensity or extending the cleaning time for areas that may accumulate more dirt, such as edges, earlier construction (with large surface roughness of photovoltaic panels) or more horizontal panels. Panel areas with higher maintenance requirements have higher priority and need to be processed first.

[0048] Optionally, after the cleaning task is completed, the cleaning effect is evaluated, and the cleaning efficiency and stain removal rate are recorded, so as to further improve and adjust the cleaning strategy. Exemplary methods include modifying the cleaning speed, adjusting the cleaning priority, adjusting the customized cleaning tasks, optimizing the division of key cleaning areas, etc.

[0049] The cleaning strategy synchronization module 14 is used to synchronize the initial cleaning strategy to the multiple photovoltaic self-propelled cleaning robots based on the communication network when the drone status information received by the drone control center is in idle standby.

[0050] Specifically, the drone control center synchronizes the initial cleaning strategy to multiple photovoltaic self-propelled cleaning robots in idle standby in real time through the communication network. If the drone status information is not idle standby, the initial cleaning strategy is synchronized to the photovoltaic self-propelled cleaning robot that has switched to idle standby after the current task is completed. Through the above settings, it is ensured that the initial cleaning strategy can be applied to multiple photovoltaic self-propelled cleaning robots efficiently and timely, and at the same time, it is ensured that multiple photovoltaic self-propelled cleaning robots that are performing tasks are not disturbed, maintaining their operating efficiency and safety.

[0051] The collaborative operation setting module 15 is used to set the collaborative operation process according to the layout information of the target photovoltaic power station, the position information of the photovoltaic self-propelled cleaning robot, and the allocation information of the customized cleaning task.

[0052] Specifically, collaborative operation means that the photovoltaic self-propelled cleaning robot and the drone jointly complete the cleaning task according to the real-time posture characteristics of the photovoltaic panels, thereby ensuring that all key areas can be cleaned in a timely and effective manner. This is because the angle and orientation of the photovoltaic panels in the actual photovoltaic power station are variable, and different angles and orientations will affect the operation safety, cleaning efficiency and effect of the photovoltaic self-propelled cleaning robot. At the same time, due to location restrictions, the photovoltaic self-propelled cleaning robot may find it difficult to meet the timeliness requirements of customized cleaning tasks in key areas within the specified time.

[0053] In some embodiments, according to the layout information of the target photovoltaic power station, the location information of the photovoltaic self-propelled cleaning robot, and the allocation information of the customized cleaning task, a collaborative operation process is set, including: According to the layout information of the target photovoltaic power station, the photovoltaic panel inclination angle of the target photovoltaic power station is obtained.

[0054] The position information of the photovoltaic self-propelled cleaning robot is synchronized in real time through the inclination angle of the photovoltaic panel to evaluate the side slip risk probability and side slip distance.

[0055] The stability of the cleaning operation is evaluated through the sideslip risk probability and the sideslip distance. If the cleaning operation stability threshold in the safety of the cleaning operation is not met, the UAV flight assistance operation is activated to perform tilt angle adaptability optimization.

[0056] Specifically, first, according to the layout information of the target photovoltaic power station, the inclination data of each photovoltaic panel is obtained in real time. Then, the position information of the photovoltaic self-propelled cleaning robot is synchronized in real time, and combined with the inclination of the photovoltaic panel, the real-time inclination of the photovoltaic self-propelled cleaning robot is determined.

[0057] Furthermore, based on the panel inclination angle, the sideslip risk probability and the sideslip distance are calculated. Exemplarily, based on the ideal friction coefficient between the photovoltaic self-propelled cleaning robot and the photovoltaic panel (the friction coefficient of the clean photovoltaic panel), the ideal critical condition for sideslip is calculated to obtain the upper limit sideslip critical angle; then, based on the most unfavorable friction coefficient between the photovoltaic self-propelled cleaning robot and the photovoltaic panel (such as the friction coefficient of the photovoltaic panel covered with simulated dust), the most unfavorable critical condition for sideslip is calculated to obtain the lower limit sideslip critical angle; then, based on the lower limit sideslip critical angle and the upper limit sideslip critical angle, a sideslip risk interval is constructed. If the photovoltaic panel inclination angle is less than the lower limit sideslip critical angle, it can be considered that there is no sideslip risk. Correspondingly, in the sideslip risk interval, the larger the photovoltaic panel inclination angle (the closer to the upper limit sideslip critical angle), the greater the sideslip risk.

[0058] Furthermore, if the photovoltaic panel is located in the above-mentioned sideslip risk interval, the sideslip risk probability of the photovoltaic self-propelled cleaning robot is calculated according to the relative position of the inclination angle of the photovoltaic panel in the sideslip risk interval; at the same time, the sideslip distance is obtained, which determines the impact force received by the photovoltaic self-propelled cleaning robot when it slides to the boundary of the photovoltaic panel. If the sideslip distance is too large, the photovoltaic self-propelled cleaning robot is at risk of overturning.

[0059] Then, the safety of the cleaning operation is weightedly assessed based on the calculated sideslip risk probability and sideslip distance. The cleaning operation stability threshold is a confidence threshold determined based on the statistical analysis results of sideslip cases. For example, the cleaning operation stability value when the sideslip confidence is 95% is used as the cleaning operation stability threshold. If there is a sideslip risk, appropriate safety measures must be taken, such as adjusting the robot's driving path, reducing the working speed, or enabling drones to adjust the tilt angle.

[0060] The operation adaptive adjustment module 16 is used to introduce environmental conditions. When the environmental conditions are not conducive to the cleaning operation, a delayed take-off mechanism is set and the initial cleaning strategy is adaptively updated with the safety of the cleaning operation as a constraint condition.

[0061] In some embodiments, the environmental conditions include wind speed and rainfall.

[0062] The environmental conditions are used to evaluate the degree of impact on the cleaning operation and obtain the impact factors.

[0063] The influencing factors and the environmental conditions are integrated to obtain an influencing index, and the influencing index is compared with a preset influencing index to determine whether to trigger the delayed takeoff mechanism.

[0064] Specifically, sensors are used to monitor relevant environmental conditions in real time, such as wind speed and rainfall. Then, based on the monitored environmental conditions, the degree of influence of these conditions on the cleaning operation is analyzed based on regression, and multiple influencing factors are obtained. Then, the influencing factors are used as fusion weights to obtain the impact index under the current environmental conditions. The impact index is used to quantitatively represent the impact of the environment on the safety of cleaning operations. If the impact index is greater than the preset impact index, the drone takeoff needs to be delayed to ensure safety.

[0065] By following the above steps, the safety and effectiveness of cleaning operations can be ensured under adverse environmental conditions, potential risks can be reduced and overall operational efficiency can be improved.

[0066] In some embodiments, Figure 2 As shown, the impact index is compared with a preset impact index to determine whether to trigger the delayed takeoff mechanism, including: The data storage module is connected to extract the photovoltaic panel power generation efficiency of the target photovoltaic power station.

[0067] Based on the photovoltaic panel contamination characteristics and the photovoltaic panel power generation efficiency, a cleaning emergency constraint is generated, and the cleaning emergency constraint includes a cleaning priority mapping table.

[0068] The preset impact index is corrected by the cleaning emergency constraint.

[0069] Specifically, first, the data storage module is connected to extract the photovoltaic panel power generation efficiency data of the target photovoltaic power station. The efficiency data can indirectly reflect the necessity of the current cleaning operation. Specifically, the photovoltaic panel power generation efficiency is affected by both stains and ambient light intensity. Then, according to the stain characteristics of the photovoltaic panel (such as stain type, coverage area, etc.), its impact on power generation efficiency is evaluated to obtain the cleaning emergency constraint. Exemplarily, the cleaning emergency constraint is the efficiency reduction impact corresponding to the photovoltaic panel stain characteristics.

[0070] Specifically, the cleaning emergency constraint also includes a cleaning priority mapping table, which is used to associate different stains with corresponding cleaning priorities. A larger stain corresponds to a higher cleaning priority.

[0071] Furthermore, the cleaning emergency constraint information is used to correct the preset impact index so as to more accurately reflect the urgency of the cleaning operation. The higher the cleaning priority of the stain, the smaller the preset impact index corresponding to it. This ensures that when the cleaning operation is affected by the external environment, it can still give priority to power generation efficiency and optimize the cleaning strategy.

[0072] In some embodiments, based on the photovoltaic panel stain characteristics and the photovoltaic panel power generation efficiency, a cleaning emergency constraint is generated, and the cleaning emergency constraint includes a cleaning priority mapping table, including: Based on the stain distribution characteristics in the photovoltaic panel stain characteristics and in combination with the photovoltaic panel power generation efficiency, a first associated node aggregation structure is generated.

[0073] Based on the pollution level feature in the photovoltaic panel stain feature and in combination with the photovoltaic panel power generation efficiency, a second associated node aggregation structure is generated.

[0074] The first associated node aggregation structure and the second associated node aggregation structure are hierarchically connected to construct a cleaning requirement network, and the time series features extracted from the cleaning requirement network form the cleaning priority mapping table.

[0075] Specifically, based on the stain distribution data on the photovoltaic panel and the power generation efficiency of the photovoltaic panel, a graph neural network (GraphSAGE) is used to generate the first associated node aggregation structure. In this structure, each node represents a stain distribution feature, and the edge is connected to the corresponding power generation efficiency value, forming a dynamic weight graph.

[0076] Specifically, the impact of the pollution level of the photovoltaic panel (such as light, moderate, and severe pollution) on the power generation efficiency is evaluated, and then GraphSAGE is also used to generate the second associated node aggregation structure to describe the relationship between the pollution level and the power generation efficiency. Each pollution level node is connected to other nodes according to its characteristics and power generation efficiency loss value to form an associated network.

[0077] Furthermore, the first associated node aggregation structure is hierarchically connected with the second associated node aggregation structure to form a cleaning demand network, in which the connection between nodes reflects the complex relationship of cleaning demand, including multi-dimensional information such as stain characteristics, pollution level and power generation efficiency. The above steps can extract the features of each level through the aggregation function of GraphSAGE, and then form a higher-level cleaning demand representation.

[0078] Furthermore, the time series features are extracted from the cleaning demand network to analyze the changes in stains and fluctuations in power generation efficiency, providing a dynamic basis for cleaning decisions. Thus, a cleaning priority mapping table is constructed to assign priorities to cleaning tasks. For example, panels with high stains and low power generation efficiency are cleaned first.

[0079] In some embodiments, based on the stain distribution characteristics in the photovoltaic panel stain characteristics and in combination with the photovoltaic panel power generation efficiency, a first associated node aggregation structure is generated, including: The stain aggregation characteristics and the stain dispersion characteristics are determined by the stain distribution characteristics in the photovoltaic panel stain characteristics.

[0080] Based on the photovoltaic panel cleaning example, neighboring samples of the stain aggregation features are searched as a type of neighbor nodes.

[0081] Based on the photovoltaic panel cleaning example, neighboring samples of the stain dispersion characteristics are searched as second-class neighbor nodes.

[0082] A first associated node aggregation structure is generated by combining the first-class neighbor nodes and the second-class neighbor nodes with the photovoltaic panel power generation efficiency.

[0083] Specifically, first, the stain distribution characteristics of the photovoltaic panel are analyzed to determine the stain aggregation characteristics (such as the dense area of ​​stains) and the stain dispersion characteristics (such as the sparse distribution of stains). Then, based on the stain aggregation characteristics, historical cleaning examples similar to the current stain aggregation characteristics are retrieved. These examples are used as references to understand the impact of stain aggregation on power generation efficiency. Similarly, based on the stain dispersion characteristics, similar historical cleaning examples are retrieved to explore the impact of stain dispersion on power generation efficiency.

[0084] Specifically, the first type of neighbor nodes and the second type of neighbor nodes are integrated together to form a preliminary node set. Each node contains the stain characteristics and its corresponding cleaning effect and power generation efficiency data. Then, combined with the information of the node set, the weighted value of each node is calculated based on its actual impact on the power generation efficiency, and the first associated node aggregation structure is generated. The structure effectively represents the relationship between the stain distribution characteristics and the power generation efficiency of the photovoltaic panel, providing support for the subsequent optimization of the cleaning strategy.

[0085] In some embodiments, based on a photovoltaic panel cleaning example, neighbor nodes are collected as second-level neighbor nodes based on the first-level neighbor nodes in the first class of neighbor nodes, wherein the strength of correlation between the first-level neighbor nodes in the first class of neighbor nodes and the photovoltaic panel power generation efficiency is greater than the strength of correlation between the second-level neighbor nodes in the first class of neighbor nodes and the photovoltaic panel power generation efficiency.

[0086] Taking the second-level neighbor nodes as a reference, N-level neighbor nodes are repeatedly collected to determine the first-level neighbor nodes, the second-level neighbor nodes, ..., the N-level neighbor nodes in the first type of neighbor nodes.

[0087] Specifically, the nodes with the strongest correlation with the power generation efficiency of the photovoltaic panel are selected from a class of neighbor nodes as the first-level neighbor nodes. These nodes represent the cleaning instances with the strongest correlation with the current stain characteristics. Then, the first-level neighbor nodes are used as a benchmark to analyze the neighbor nodes with higher correlation. The correlation strength of these nodes needs to be smaller than the correlation strength between the first-level neighbor nodes and the power generation efficiency, but still maintain a strong correlation. These nodes are collected as second-level neighbor nodes to form a wider sample set for further analysis.

[0088] Specifically, taking each secondary neighbor node as a benchmark, continue to collect its neighboring nodes to generate third-level neighbor nodes. This process is carried out in sequence until the preset N-level neighbor nodes are reached. In the node collection process, the correlation strength between each level of nodes and power generation efficiency decreases step by step.

[0089] Through the above steps, the complete neighbor node hierarchy structure constructed can provide more data support for analyzing the cleaning needs of photovoltaic panels and optimizing cleaning strategies, which helps the cleaning strategy to better adapt to the complex relationship between different stain characteristics and power generation efficiency, thereby improving the overall cleaning efficiency and power generation performance of photovoltaic power stations.

[0090] In some embodiments, the first associated node aggregation structure is generated by combining the first type of neighbor nodes and the second type of neighbor nodes with the photovoltaic panel power generation efficiency, including: A positive stain influence gradient is established through the first-level neighbor nodes, the second-level neighbor nodes, ..., the N-level neighbor nodes in the first type of neighbor nodes.

[0091] A reverse stain influence gradient is established through the first-level neighbor nodes, the second-level neighbor nodes, ..., the M-level neighbor nodes in the second-level neighbor nodes.

[0092] The positive stain influence gradient and the reverse stain influence gradient are combined to generate the first associated node aggregation structure.

[0093] Specifically, a positive contamination influence gradient is established through a class of neighbor nodes (first-level neighbor nodes, second-level neighbor nodes, ..., N-level neighbor nodes). The positive contamination influence gradient determines the degree of influence of contamination concentration on the power generation efficiency of the photovoltaic panel through the contribution of each node to the pollution. Exemplarily, the positive contamination influence gradient decreases as the node distance increases.

[0094] Specifically, based on the same idea, a reverse contamination influence gradient is established through two types of neighbor nodes (first-level neighbor nodes, second-level neighbor nodes, ..., M-level neighbor nodes). This gradient can be expressed as the contribution of each node corresponding to the contamination dispersion to the power generation efficiency of the photovoltaic panel.

[0095] Specifically, first, the magnitudes of the positive and negative stain influence gradients are compared and normalized so that they can be compared on the same scale. Then, the positive stain influence gradient and the negative stain influence gradient are merged, such as simply adding the two gradients or performing weighted averaging. Finally, the merged gradient is used to generate the first associated node aggregation structure.

[0096] In summary, the automatic photovoltaic panel cleaning system based on drone provided by the present invention has the following technical effects: Through the communication link establishment module, a two-way communication link is established between the drone control center and multiple photovoltaic self-propelled cleaning robots in the target photovoltaic power station, and a communication network is set up; the real-time monitoring data acquisition module connects to the monitoring equipment of the photovoltaic power station, collects the stain image of the photovoltaic panel and extracts the stain characteristics, including distribution and pollution level; the initial cleaning strategy generation module outputs the initial cleaning strategy according to the stain characteristics, including cleaning speed and customized cleaning tasks; the cleaning strategy synchronization module synchronizes the initial cleaning strategy to the cleaning robot through the communication network when the drone is idle; the collaborative operation setting module sets the collaborative operation process according to the layout of the photovoltaic power station, the robot location information and the cleaning task allocation; the operation adaptive adjustment module introduces environmental conditions. When the environment is not conducive to the cleaning operation, a delayed take-off mechanism is set to adaptively update the initial cleaning strategy to ensure the safety of the operation. This will achieve the technical effect of optimizing the coordination level and improving the cleaning efficiency and risk resistance.

[0097] It should be understood that the embodiments disclosed in the present invention and the above description can enable those skilled in the art to use the present invention to implement the present invention. At the same time, the present invention is not limited to the above-mentioned embodiments. It should be understood that those skilled in the art can still modify the technical solutions recorded in the above-mentioned embodiments, or replace some of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. The automatic cleaning system of photovoltaic panels based on drones is characterized by: The system is in communication with a drone control center, and the drone control center is used to receive drone status information, including: A communication link establishment module, the communication link establishment module is used to establish a two-way communication link between the drone control center and a plurality of photovoltaic self-propelled cleaning robots in a target photovoltaic power station, and set up a communication network; A real-time monitoring data acquisition module, wherein the real-time monitoring data acquisition module is used to connect to the real-time monitoring equipment of the target photovoltaic power station, collect the photovoltaic panel stain image, and extract the photovoltaic panel stain feature, wherein the photovoltaic panel stain feature includes the stain distribution feature and the pollution level feature; An initial cleaning strategy generation module, the initial cleaning strategy generation module is used to output an initial cleaning strategy based on the photovoltaic panel stain characteristics, the initial cleaning strategy including a cleaning speed and a customized cleaning task for cleaning key areas; A cleaning strategy synchronization module, wherein the cleaning strategy synchronization module is used to synchronize the initial cleaning strategy to the plurality of photovoltaic self-propelled cleaning robots based on the communication network when the drone status information received by the drone control center is in idle standby; A collaborative operation setting module, the collaborative operation setting module is used to set a collaborative operation process according to the layout information of the target photovoltaic power station, the location information of the photovoltaic self-propelled cleaning robot, and the allocation information of the customized cleaning task; The operation adaptive adjustment module is used to introduce environmental conditions. When the environmental conditions are not conducive to the cleaning operation, a delayed take-off mechanism is set and the initial cleaning strategy is adaptively updated with the safety of the cleaning operation as a constraint condition.

2. The automatic cleaning system for photovoltaic panels based on drones according to claim 1, characterized in that: The environmental conditions include wind speed and rainfall; By using the environmental conditions, the degree of influence on the cleaning operation is evaluated and the influence factors are obtained; The influencing factors and the environmental conditions are integrated to obtain an influencing index, and the influencing index is compared with a preset influencing index to determine whether to trigger the delayed takeoff mechanism.

3. The automatic cleaning system for photovoltaic panels based on drones as claimed in claim 2, characterized in that: The impact index is compared with a preset impact index to determine whether to trigger the delayed takeoff mechanism, including: Connecting to a data storage module to extract the photovoltaic panel power generation efficiency of the target photovoltaic power station; Based on the contamination characteristics of the photovoltaic panel and the power generation efficiency of the photovoltaic panel, generating a cleaning emergency constraint, wherein the cleaning emergency constraint includes a cleaning priority mapping table; The preset impact index is corrected by the cleaning emergency constraint.

4. The automatic cleaning system for photovoltaic panels based on drones as claimed in claim 3, characterized in that: Based on the photovoltaic panel stain characteristics and the photovoltaic panel power generation efficiency, a cleaning emergency constraint is generated, and the cleaning emergency constraint includes a cleaning priority mapping table, including: Based on the stain distribution characteristics in the photovoltaic panel stain characteristics and in combination with the photovoltaic panel power generation efficiency, a first associated node aggregation structure is generated; Based on the pollution level feature in the photovoltaic panel stain feature and in combination with the photovoltaic panel power generation efficiency, a second associated node aggregation structure is generated; The first associated node aggregation structure and the second associated node aggregation structure are hierarchically connected to construct a cleaning requirement network, and the time series features extracted from the cleaning requirement network form the cleaning priority mapping table.

5. The automatic cleaning system for photovoltaic panels based on drones as claimed in claim 4, characterized in that: Based on the stain distribution characteristics in the photovoltaic panel stain characteristics and in combination with the photovoltaic panel power generation efficiency, a first associated node aggregation structure is generated, including: Determine the stain aggregation feature and the stain dispersion feature through the stain distribution feature in the photovoltaic panel stain feature; Based on the photovoltaic panel cleaning example, the neighboring samples of the stain aggregation features are searched as a type of neighbor nodes; Based on the photovoltaic panel cleaning example, the neighboring samples of the stain dispersion characteristics are searched as the second type of neighbor nodes; A first associated node aggregation structure is generated by combining the first-class neighbor nodes and the second-class neighbor nodes with the photovoltaic panel power generation efficiency.

6. The automatic cleaning system for photovoltaic panels based on drones as claimed in claim 5, characterized in that: Based on the photovoltaic panel cleaning example, taking the first-level neighbor nodes in the first class of neighbor nodes as a benchmark, collecting neighbor nodes as second-level neighbor nodes, wherein the correlation strength between the first-level neighbor nodes in the first class of neighbor nodes and the photovoltaic panel power generation efficiency is greater than the correlation strength between the second-level neighbor nodes in the first class of neighbor nodes and the photovoltaic panel power generation efficiency; Taking the second-level neighbor nodes as a reference, N-level neighbor nodes are repeatedly collected to determine the first-level neighbor nodes, the second-level neighbor nodes, ..., the N-level neighbor nodes in the first type of neighbor nodes.

7. The automatic cleaning system for photovoltaic panels based on drones as claimed in claim 6, characterized in that: By using the first type of neighbor nodes and the second type of neighbor nodes, combined with the photovoltaic panel power generation efficiency, a first associated node aggregation structure is generated, including: Establishing a positive stain influence gradient through the first-level neighbor nodes, the second-level neighbor nodes, ..., the N-level neighbor nodes in the first type of neighbor nodes; Establishing a reverse stain influence gradient through the first-level neighbor nodes, the second-level neighbor nodes, ..., the M-level neighbor nodes in the second-level neighbor nodes; The positive stain influence gradient and the reverse stain influence gradient are combined to generate the first associated node aggregation structure.

8. The automatic cleaning system for photovoltaic panels based on drones as claimed in claim 1, characterized in that: According to the layout information of the target photovoltaic power station, the location information of the photovoltaic self-propelled cleaning robot, and the allocation information of the customized cleaning task, a collaborative operation process is set, including: According to the layout information of the target photovoltaic power station, obtaining the photovoltaic panel inclination angle of the target photovoltaic power station; The position information of the photovoltaic self-propelled cleaning robot is synchronized in real time through the inclination angle of the photovoltaic panel to evaluate the side slip risk probability and side slip distance; The stability of the cleaning operation is evaluated through the sideslip risk probability and the sideslip distance. If the cleaning operation stability threshold in the safety of the cleaning operation is not met, the UAV flight assistance operation is activated to perform tilt angle adaptability optimization.

Citation Information

Patent Citations

  • Intelligent cleaning method and system for distributed photovoltaic system and ground station

    CN109759377A

  • Detection method and system for identifying cleanliness of photovoltaic panel based on unmanned aerial vehicle image

    CN116797944A

  • Solar photovoltaic panel surface cleaning method and system

    CN117960664A

  • Automatic cleaning method and system for photovoltaic panel

    CN118017927A

Cited By

  • Configuration generation method and device of unmanned aerial vehicle cleaning system and unmanned aerial vehicle cleaning system

    CN119414732A

  • Cleaning method for photovoltaic panel in mountain photovoltaic base station based on unmanned aerial vehicle group

    CN119813941A

  • Air-ground cooperative offshore photovoltaic cleaning and maintenance system

    CN119910002A

  • Method, device and control system for cleaning polycrystalline silicon photovoltaic panel by unmanned aerial vehicle

    CN120010562A

  • Mooring type high-pressure six-axis curtain wall cleaning unmanned aerial vehicle

    CN120052759A