Automatic inspection unmanned aerial vehicle for photovoltaic field area of power station

Abstract

The invention discloses a power station photovoltaic field area automatic inspection unmanned aerial vehicle, and relates to the technical field of unmanned aerial vehicle inspection, and the unmanned aerial vehicle comprises the following components: a meteorological self-adaptive intelligent inspection flight system, a power supply module, a rotor wing device and a communication module; the power supply module is used for providing power support for each component of the unmanned aerial vehicle; the communication module is used for realizing data interaction between the unmanned aerial vehicle and the ground control station and between the unmanned aerial vehicle and the photovoltaic field area monitoring equipment; by carrying the meteorological self-adaptive intelligent inspection flight integrated system, meteorological conditions of a photovoltaic field area can be perceived and analyzed in real time, and an inspection path and a flight attitude are dynamically optimized according to the meteorological conditions, so that the unmanned aerial vehicle can preferentially inspect an area where a problem is most likely to occur, and the inspection efficiency is remarkably improved; meanwhile, the unmanned aerial vehicle can keep stable flight under complex meteorological conditions such as strong wind, flight accidents are avoided, and the accuracy of inspection data is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle inspection, and in particular to an automatic inspection unmanned aerial vehicle for a photovoltaic field in a power station. Background Art

[0002] With the continuous growth of global demand for renewable energy, the solar photovoltaic power generation industry has ushered in unprecedented development opportunities. As an important place for solar power generation, the scale of photovoltaic fields in power stations is expanding, and the number of photovoltaic equipment is also increasing sharply. However, the operating status of photovoltaic equipment is directly related to the power generation efficiency and safety of power stations. Therefore, it is very important to carry out efficient, accurate and safe inspection and maintenance of photovoltaic equipment.

[0003] Traditional inspection methods often rely on manual labor, but this method is not only time-consuming and labor-intensive, but also difficult to ensure the comprehensiveness and accuracy of the inspection. In recent years, with the rapid development of drone technology, drone inspection has gradually become a new trend in the inspection of photovoltaic fields in power stations. Drones have shown great potential in the field of photovoltaic inspection with their advantages of high efficiency, flexibility and low cost. However, despite the many advantages of drone inspection, many problems are still exposed in the actual application process, especially under complex meteorological conditions. First, in terms of inspection path planning, existing drones often lack dynamic adaptability and cannot dynamically adjust the inspection path based on real-time meteorological information. Due to the different failure risks of photovoltaic equipment under different meteorological conditions, traditional drones lack accurate assessment and consideration of this, resulting in the inability to optimize the inspection path according to the actual situation, greatly reducing the inspection efficiency and making it difficult to quickly locate potential fault points. Secondly, in terms of flight stability, in the face of interference from meteorological factors such as wind of different intensities and directions, traditional drones are difficult to effectively maintain a stable flight attitude and trajectory, which not only affects the shooting accuracy of the shooting equipment, but also causes inaccurate inspection data, and may even cause flight accidents, posing a serious threat to the safety of the drone itself and surrounding facilities and personnel.

[0004] In view of the above problems, it is necessary to optimize the existing automatic inspection drones in the photovoltaic field of power stations, and achieve efficient and accurate inspection operations under complex weather conditions by deeply integrating dynamic adaptive inspection path planning and adaptive wind-resistant flight capabilities. Therefore, it is of great significance to develop an automatic inspection drone for the photovoltaic field of power stations that can comprehensively realize the above characteristics. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the prior art and to provide an automatic inspection drone for the photovoltaic area of ​​a power station. The drone can achieve high efficiency and accuracy in inspection operations under complex weather conditions by deeply integrating dynamic adaptive inspection path planning and adaptive wind-resistant flight capabilities. At the same time, it can further extend the flight time of the drone and improve the sustainability of the inspection operation by optimizing relevant decisions through energy management, thus providing a more intelligent, efficient and safe solution for the operation and maintenance management of the photovoltaic area of ​​the power station.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an automatic inspection drone for photovoltaic field in a power station, the drone comprising the following components: a weather adaptive intelligent inspection flight system, a power module, a rotor device and a communication module;

[0007] The power module is used to provide power support for various components of the drone;

[0008] The communication module is used to realize data interaction between the UAV and the ground control station and the photovoltaic field monitoring equipment;

[0009] The rotor device is installed around the fuselage body to provide the lift and power required for the UAV flight, and can be adjusted by the weather adaptive intelligent inspection flight system;

[0010] The weather self-adaptive intelligent inspection flight system is connected to the weather sensor array, the rotor device and the flight control system in communication, and the system includes: a data acquisition and analysis submodule, a comprehensive decision submodule and a command execution submodule;

[0011] The data acquisition and analysis submodule collects data on wind speed, wind direction, temperature and air pressure in real time through a meteorological sensor array that is set at an appropriate position on the fuselage body and has high-precision measurement capabilities. It also analyzes the impact of the differences in the failure risks of photovoltaic equipment in various regions under different meteorological conditions on the inspection route planning by combining a fault risk assessment model set according to the photovoltaic field layout and photovoltaic equipment characteristics and the UAV's own flight performance parameters. At the same time, based on the meteorological data and its own performance parameters, it uses complex mechanical analysis and flight attitude simulation algorithms to preliminarily calculate the direction and degree of flight attitude adjustment required to maintain stable flight under the current meteorological conditions.

[0012] The comprehensive decision-making submodule obtains information related to the inspection task requirements, and comprehensively considers it with the analysis results of the impact of meteorological conditions on the inspection path and flight attitude provided by the data collection and analysis submodule, and uses the priority determination algorithm to determine the inspection priority of each area, automatically increase the priority of areas that are greatly affected by wind and have high potential for faults, and adopts an intelligent algorithm to use the geographical layout of the photovoltaic field, the inspection priority of each area and the current meteorological conditions as input parameters to perform real-time dynamic optimization of the inspection path. At the same time, based on the analysis results of the data collection and analysis submodule on flight attitude adjustment, combined with the performance parameters of the drone itself and the current meteorological conditions, a calculation model is used to derive the key parameter adjustment amounts of the flight attitude and rotor speed required to maintain stable flight. In addition, by obtaining the real-time status information and meteorological conditions of the drone, the inspection energy consumption is analyzed and calculated based on the preset energy consumption calculation model, and the corresponding strategy formulation algorithm is used according to different situations to formulate an energy management optimization strategy for optimizing the inspection path;

[0013] The instruction execution submodule is responsible for receiving the inspection path optimization plan, flight attitude adjustment instructions and decision results of the energy management optimization strategy determined by the comprehensive decision-making submodule, and establishing a stable and efficient communication link with the communication module of the UAV and various related execution components to ensure accurate and timely transmission of instructions.

[0014] Furthermore, the data acquisition and analysis submodule combines the fault risk assessment model set according to the photovoltaic field layout and photovoltaic equipment characteristics and the flight performance parameters of the drone itself to analyze the impact of the differences in photovoltaic equipment failure risks in different regions under different meteorological conditions on the inspection path planning, and uses the formula Quantitatively evaluate the failure risk of photovoltaic equipment in each region, where R f (i) represents the failure risk value of the photovoltaic equipment in the i-th region, α and β are weight coefficients, n represents the number of meteorological factors that affect the failure risk of photovoltaic equipment, and W j is the weight of the jth meteorological factor, F ij represents the actual measured value of the jth meteorological factor in the ith region, S i is the structural strength parameter of the photovoltaic equipment in the i-th region, m represents the number of types of photovoltaic equipment characteristic factors that affect the failure risk of photovoltaic equipment, V k is the weight of the characteristic factor of the k-th photovoltaic device, G ik represents the actual value of the characteristic factor of the kth photovoltaic device in the ith region, T i is the performance parameter of the photovoltaic device in the i-th region.

[0015] Furthermore, the data acquisition and analysis submodule preliminarily calculates the direction and degree of flight attitude adjustment required to maintain stable flight under current meteorological conditions based on meteorological data and its own performance parameters through complex mechanical analysis and flight attitude simulation algorithm. The calculation formula is: Among them, θ a represents the flight attitude adjustment angle required for the UAV to maintain stable flight under the current meteorological conditions. γ and δ are weight coefficients used to balance the influence of different factors on the flight attitude adjustment estimation. p represents the number of meteorological factors that affect the flight attitude adjustment. X1 is the weight of the first meteorological factor. H il represents the actual measured value of the lth meteorological factor in the ith region, Z i is the spatial characteristic parameter of the ith region, r represents the number of characteristics of the UAV itself that affect the flight attitude adjustment, and Y q is the weight of the characteristic factor of the qth type of UAV, I iq represents the actual value of the characteristic factor of the qth type of UAV in the ith region, U i is the flight condition parameter of the ith area.

[0016] Furthermore, the comprehensive decision submodule uses a priority determination algorithm to determine the inspection priority of each area, and its calculation formula is: pri (i) = μ × R f (i)+v×E eff (i)+ω×P adj (i), where P pri (i) represents the inspection priority value of the ith area. The higher the value, the higher the degree to which the area should be inspected first under the current meteorological conditions and overall inspection requirements. μ, v, and ω are weight coefficients used to balance the influence of different factors on the inspection area priority determination. R f (i) represents the failure risk value of the photovoltaic equipment in the i-th region, which comprehensively reflects the failure possibility of the photovoltaic equipment in this region under the current meteorological conditions based on meteorological factors and the characteristics of the photovoltaic equipment itself. eff (i) is the impact value of the inspection efficiency of the ith region, which is obtained by comprehensively evaluating the impact of various meteorological factors on the inspection efficiency in the region. It indicates the degree of impact of the meteorological conditions in the region on the overall inspection efficiency. adj (i) is the necessity degree value of the inspection route adjustment in the i-th area, which reflects the necessity degree of adjusting the inspection route in the area under the current meteorological conditions and the status of the photovoltaic equipment.

[0017] Furthermore, in the comprehensive decision-making submodule, E eff (i) is the inspection efficiency impact value of the i-th area, and its calculation formula is: Among them, η is the weight coefficient, N represents the total number of regions divided into photovoltaic fields, and F ij represents the actual measurement value of the jth meteorological factor in the ith region, which is collected in real time by the meteorological sensor array. 0j represents the reference value of the jth meteorological factor, P adj (i) is the necessity value of the inspection path adjustment in the i-th area, and its calculation formula is: Among them, P adj The higher the value of (i), the greater the necessity to adjust the inspection path of the area under the current meteorological conditions and the state of the photovoltaic equipment. ∈ and ζ are weight coefficients, which are used to balance the influence of meteorological factors and the characteristics of the photovoltaic equipment itself on the necessity assessment of inspection path adjustment. n: represents the number of meteorological factors that affect the inspection path adjustment, including wind speed, wind direction, temperature and air pressure factors. W j is the weight of the jth meteorological factor.

[0018] Furthermore, the comprehensive decision-making submodule adopts an intelligent algorithm, takes the geographical layout of the photovoltaic field, the inspection priority of each area and the current meteorological conditions as input parameters, and performs real-time dynamic optimization of the inspection path. Specifically, let G(V, E) represent the photovoltaic field map, where V is a vertex set representing each area of ​​the photovoltaic field, E is an edge set representing the reachable relationship between the areas, let S be the starting point, that is, the take-off point of the drone or the end point of the last inspection, T is the target point, that is, the end point specified for this inspection task or a certain area that needs to be inspected, let P = {S} be the currently determined inspection path, which initially only contains the starting point, C visited (v) is the number of times vertex v has been visited. Initially, the number of times all vertices have been visited is 0. In each iteration, starting from the last vertex u of the current path P, the cost function C(u, v) from u to all unvisited vertices v is calculated. The calculation formula is: C(u, v) = α1×D(u, v)+α2×P pri (v)+α3×E eff (v), α1, α2 and α3 are weight coefficients used to balance the importance of distance, inspection priority and inspection efficiency in path selection. D(u, v) represents the distance from vertex u to vertex v. P pri (v) represents the inspection priority value of the vth area, E eff (v) is the inspection efficiency impact value of the vth area, and the vertex v with the smallest cost function C(u, v) is selected. min , add it to the current path P, that is, P = P∪{v min}, and update vertex v min Number of visits C visited (vmin )=C visited (v cin )+1, when the target point T is added to the path P or the maximum number of iterations is reached, the iteration process ends, and the path P obtained at this time is the optimized inspection path.

[0019] Furthermore, the comprehensive decision-making submodule uses a calculation model to obtain the key parameter adjustment of the flight attitude and rotor speed required to maintain stable flight based on the analysis results of the data collection and analysis submodule on the flight attitude adjustment, combined with the performance parameters of the UAV itself and the current meteorological conditions. The calculation formula of the flight attitude parameter adjustment is: The calculation formula of the rotor speed parameter adjustment is: Δθ f Represents the change in the UAV flight attitude adjustment angle calculated accurately, Δr s represents the rotor speed adjustment calculated accurately, φ and ρ are weight coefficients, p represents the number of meteorological factors that affect the flight attitude adjustment, X l is the weight of the first meteorological factor, H il represents the actual measured value of the first meteorological factor in the ith region, H 0l represents the reference value of the first meteorological factor, n represents the number of meteorological factors that affect the rotor speed adjustment, and W j is the weight of the jth meteorological factor, F ij represents the actual measured value of the jth meteorological factor in the ith region, F 0j represents the reference value of the jth meteorological factor, Z i is the spatial characteristic parameter of the ith region, S i is the structural strength parameter of the photovoltaic equipment in the i-th region.

[0020] Furthermore, the comprehensive decision-making submodule analyzes and calculates the inspection energy consumption based on the preset energy consumption calculation model, and uses the corresponding strategy formulation algorithm to formulate an energy management optimization strategy for optimizing the inspection path according to different situations, and obtains the inspection priority value P of each area. pri (i), and the distance D from the starting point to the i-th area calculated based on the geographical layout of the PV field and the flight characteristics of the UAV i , and obtain the preset weight coefficient β2, and use the strategy formula to calculate the energy consumption value of the optimized inspection path Substitute the obtained parameters into the formula, and calculate the energy consumption value E of the optimized inspection path by comprehensively considering the inspection priority of each area and the distance from the starting point to each area. path，opt , in order to optimize the inspection path.

[0021] Compared with the existing technology, this kind of automatic inspection drone for photovoltaic field in power station has the following beneficial effects:

[0022] 1. The present invention is equipped with a weather adaptive intelligent inspection flight integrated system, which can sense and analyze the meteorological conditions of the photovoltaic field in real time, and dynamically optimize the inspection path and flight attitude accordingly. It not only enables the drone to prioritize the areas where problems are most likely to occur, thereby significantly improving the inspection efficiency and quickly locating potential fault points, but also the drone can maintain stable flight under complex meteorological conditions such as strong winds, avoid flight accidents, and ensure the accuracy of inspection data.

[0023] 2. The present invention uses the energy management optimization function to analyze and calculate the energy consumption according to the current flight status, weather conditions and inspection task requirements of the UAV, and formulate corresponding optimization strategies. When the wind speed is low, the rotor speed is appropriately reduced to reduce energy consumption. When it is necessary to prioritize inspections of high-risk areas and the energy consumption is high, the inspection route is reasonably planned to reduce the total energy consumption, effectively extending the UAV's flight time and improving the sustainability of the inspection operation.

[0024] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 This is a schematic diagram of the structure of an automatic inspection drone for photovoltaic field in a power station;

[0027] Figure 2 It is a structural diagram of a weather-adaptive intelligent inspection flight system for automatic inspection of photovoltaic fields in power stations by drones;

[0028] Figure 3 This is a workflow diagram of an automatic inspection drone in a power station photovoltaic area. DETAILED DESCRIPTION

[0029] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] Embodiment 1

[0031] This embodiment describes in detail the specific application of an automatic inspection drone in the photovoltaic field of a power station in the inspection of a large-scale ground photovoltaic power station. During the inspection process, the inspection strategy can be flexibly adjusted according to the real-time meteorological conditions and the status of the photovoltaic equipment to achieve efficient and accurate inspection operations, and to promptly discover potential faults and abnormal conditions of the photovoltaic equipment. At the same time, the energy management optimization strategy is used to extend the drone's flight time and improve the sustainability of the inspection operation.

[0032] Before the inspection, a comprehensive inspection is carried out on the main body of the drone to ensure that the internal flight control system, data processing unit, power module and communication module are working normally, especially the power module is tested for power to ensure that it has sufficient power and stable power supply to meet the needs of the entire inspection task. The inspection coverage is set to the entire photovoltaic power station area. The key inspection areas include photovoltaic component areas close to wind outlets, areas with recent maintenance records, and areas with abnormal fluctuations in power generation efficiency. The inspection interval is stipulated to be once a week, and each inspection must be carried out during the day when the lighting conditions are good and the weather conditions are relatively stable.

[0033] When the UAV starts an inspection flight in the photovoltaic power station area, the meteorological sensor array collects the meteorological information of the surrounding environment in real time. After receiving the real-time meteorological data collected by the meteorological sensor array, the data acquisition and analysis submodule combines the pre-set photovoltaic equipment failure risk assessment model and the UAV's own flight performance parameters for analysis: the failure risk assessment formula is used Calculate the photovoltaic power in each area and adjust the direction and degree according to the flight attitude to preliminarily estimate the formula θ a =γ× The failure risk value of the equipment is assumed to be in a certain area. The failure risk value R of the photovoltaic equipment in the area is calculated. f (i) Relatively high. This may be because the wind speed in the area is high and the photovoltaic equipment is old, which leads to an increase in the calculated risk value. A preliminary estimate of the flight attitude adjustment angle required to maintain stable flight under the current meteorological conditions is made. For example, based on the collected wind speed, wind direction, and spatial characteristic parameters of the area, it is estimated that the drone body may need to tilt a certain angle to the northwest to maintain stable flight. The necessity assessment formula for inspection path adjustment is used. Evaluate the degree of necessity for adjusting the inspection path in each area. If the wind speed in a certain area changes significantly compared to the baseline wind speed, and the characteristics of the photovoltaic equipment itself also change to a certain extent, it is calculated that the degree of necessity for adjusting the inspection path in this area is high, indicating that the inspection path in this area needs to be adjusted.

[0034] The comprehensive decision-making submodule makes the following decisions based on the analysis results of the data collection and analysis submodule and the inspection task requirements: Formula P is determined according to the inspection area priority. pri (i) = μ × R f (i)+V×E eff (i)+ω×P adj (i) Determine the inspection priority of each area. For the areas with higher fault risk values, greater flight attitude adjustment requirements and higher necessity of inspection path adjustment, their inspection priority is significantly improved. The inspection path optimization formula is used to optimize the inspection path. During initialization, a graph G(V, E) representing the photovoltaic power station area is constructed, where V contains various photovoltaic component areas, key monitoring points, etc. as vertices, and E represents the reachable relationship between areas. The starting point is set as the take-off point of the drone, and the target point is one of the key inspection areas specified in this inspection task (such as an area with a recent maintenance record). During the iteration process, starting from the last vertex of the current path, the cost function C(u, v) = α1×D(u, v) + α2×P for all unvisited vertices is calculated. pri (v)+α3×E eff (v) Select the vertex with the smallest cost function value and add it to the current path until the target point is added to the path or the preset maximum number of iterations is reached, and the optimized inspection path is obtained. The formula is accurately calculated based on the flight attitude and rotor speed adjustment amount. and Accurately calculate the adjustment of key parameters such as flight attitude and rotor speed required to maintain stable flight. For example, calculate that the fuselage should be tilted to the northwest at a specific angle, and at the same time, the rotor speed needs to be increased to a specific speed value to increase lift to resist the influence of wind. For energy management optimization strategy, according to the inspection path planning to reduce energy consumption strategy formula By optimizing inspection routes, prioritizing inspections of high-priority areas, and reducing unnecessary detours, total energy consumption can be further reduced.

[0035] The command execution submodule accurately sends the inspection path optimization scheme, flight attitude adjustment command and energy management optimization strategy determined by the comprehensive decision-making submodule to the relevant execution components respectively: for the inspection path optimization scheme, the communication module closely cooperates with the automatic driving function of the UAV to guide the UAV to fly according to the optimized path. The automatic driving function of the UAV accurately performs inspection operations according to the new inspection path based on the received path information and its own flight control logic and algorithm. For the flight attitude adjustment command, it is sent to the rotor device and the UAV's servo and other actuators to make the fuselage tilt to the northwest according to the calculated angle to achieve the adjustment of the flight attitude. After receiving the command, the rotor device adjusts the motor speed and increases the rotor speed to the specific speed value calculated, thereby increasing the lift and maintaining the stable flight of the UAV in a strong wind environment. It can also accurately fly according to the optimized inspection path to ensure that the shooting accuracy of the shooting equipment is not affected. For the energy management optimization strategy, the control system adjusts the flight attitude according to the command to reduce energy consumption, and the rotor device reduces the rotor speed according to the command to reduce energy consumption, thereby realizing the corresponding operation according to the energy management optimization strategy to achieve the purpose of reducing energy consumption and extending the flight time.

[0036] While the drone maintains stable flight, the shooting equipment it carries (such as high-definition cameras, infrared thermal imagers, etc.) shoots and collects data on the photovoltaic modules, brackets, wiring, etc. of the photovoltaic power station according to the predetermined inspection route and shooting parameters. For example, the high-definition camera shoots the surface of the photovoltaic module at a frame rate of 10 frames per second, and the infrared thermal imager detects the temperature distribution of the module. The collected data is transmitted to the ground control station in real time through the communication module. The staff of the ground control station can view, analyze and store the data in real time, so as to promptly detect abnormal conditions in the photovoltaic power station and take corresponding measures. For example, if a photovoltaic module has obvious shadows on its surface or the temperature rises abnormally, personnel can be arranged in time for further inspection and maintenance.

[0037] Embodiment 2

[0038] This embodiment describes in detail the specific application of an automatic inspection drone in a power station photovoltaic field in the inspection of distributed rooftop photovoltaic systems. During the inspection process, the inspection strategy can be flexibly adjusted according to real-time meteorological conditions and the status of photovoltaic equipment to achieve efficient and accurate inspection operations, and to promptly discover potential faults and abnormal conditions of photovoltaic equipment. At the same time, the energy management optimization strategy is used to extend the drone's flight time and improve the sustainability of the inspection operation.

[0039] As in the first embodiment, a comprehensive inspection is performed on all components of the drone to ensure that all modules in the main body of the drone are operating normally and that the power module has sufficient power.

[0040] The inspection coverage is set to cover all registered distributed rooftop photovoltaic systems in the urban area. Key inspection areas include photovoltaic systems installed on the roofs of old buildings, photovoltaic systems whose power generation efficiency has declined recently, and photovoltaic systems located around high-rise buildings that may be affected by shading. The inspection interval is stipulated to be once a month. Each inspection can be carried out during non-peak hours on weekdays to reduce the impact on normal urban activities. The impact of meteorological conditions must also be considered.

[0041] After the drone starts the inspection flight in the area where the distributed rooftop photovoltaic system is located, the meteorological sensor array collects meteorological information in real time. After the data acquisition and analysis submodule receives the real-time meteorological data collected by the meteorological sensor array, it combines the pre-set photovoltaic equipment failure risk assessment model and the drone's own flight performance parameters for analysis, and uses the failure risk assessment formula to calculate the failure risk value of photovoltaic equipment in each area. Assuming that in a certain rooftop photovoltaic system area, it is calculated that the failure risk value of photovoltaic equipment in this area is relatively high. This may be because the temperature in this area fluctuates greatly and the photovoltaic equipment is produced by a specific manufacturer. Its performance stability under temperature changes is relatively poor, resulting in the failure risk value calculated according to the formula. The risk value increases. Based on the preliminary estimation formula for the direction and degree of flight attitude adjustment, the flight attitude adjustment angle required to maintain stable flight under current meteorological conditions is preliminarily estimated. For example, based on the collected wind speed, wind direction and spatial characteristic parameters of the area, it is estimated that the drone body may need to be slightly tilted to the southwest at a certain angle to maintain stable flight. The necessity of inspection path adjustment is evaluated in each area through the inspection path adjustment necessity evaluation formula. If the temperature in a certain area changes greatly compared with the baseline temperature, and the characteristics of the photovoltaic equipment itself also change to a certain extent, it is calculated that the necessity degree of inspection path adjustment in this area is high, indicating that the inspection path in this area needs to be adjusted.

[0042] Based on the analysis results of the data collection and analysis submodule and the inspection task requirements, the comprehensive decision-making submodule makes the following decisions: According to the inspection area priority determination formula, the inspection priority of each area is determined. For the above-mentioned areas with high fault risk values, large flight attitude adjustment requirements and high necessity of inspection path adjustment, the inspection priority is significantly improved. The inspection path optimization formula is used to optimize the inspection path, and a graph G(V, E) representing the area where the distributed rooftop photovoltaic system is located is constructed, where V contains each rooftop photovoltaic system, key monitoring points, etc. as vertices, and E represents the reachable relationship between areas. The starting point is set as the take-off point of the drone, and the target point is one of the key inspection areas specified in this inspection task (such as a photovoltaic system whose power generation efficiency has decreased recently). In the iterative process, starting from the last vertex of the current path, the cost function C(u, v) = α1×D(u, v) + α2×P of all unvisited vertices is calculated. pπi(v)+α3×E eff (v) Select the vertex with the smallest cost function value and add it to the current path until the target point is added to the path or the preset maximum number of iterations is reached, and the optimized inspection path is obtained. The formula is accurately calculated based on the flight attitude and rotor speed adjustment amount. and Accurately calculate the adjustment of key parameters such as flight attitude and rotor speed required to maintain stable flight. For example, calculate the specific angle value that the fuselage should tilt to the southwest, and at the same time, adjust the rotor speed appropriately (may be slightly increased or decreased, depending on the calculation results) to maintain stable flight. For energy management optimization strategy, according to the inspection path planning to reduce energy consumption strategy formula By optimizing inspection routes, giving priority to inspecting high-priority areas, and reducing unnecessary detours, the total energy consumption can be further reduced.

[0043] The command execution submodule accurately sends the inspection path optimization plan, flight attitude adjustment instructions and energy management optimization strategy determined by the comprehensive decision-making submodule to the relevant execution components: For the inspection path optimization plan, the communication module works closely with the drone's autopilot function to guide the drone to fly along the optimized path. The drone's autopilot function accurately performs inspection operations along the new inspection path based on the received path information and its own flight control logic and algorithm, ensuring efficient and comprehensive coverage of all key inspection areas and other rooftop photovoltaic system areas that need to be inspected. For the flight attitude adjustment instructions, they are sent to the rotor device and the drone's servo and other actuators to control the fuselage to tilt to the southwest according to the calculated angle, thereby achieving precise adjustment of the flight attitude. After receiving the instruction, the rotor device adjusts the speed of its own motor according to the rotor speed adjustment information contained in the instruction. The control module adjusts the rotor speed to an appropriate value to maintain the stable flight of the UAV in an environment with changeable wind directions, and ensures that the shooting accuracy of the shooting equipment is not affected, so that the status information of each rooftop photovoltaic system can be clearly and accurately obtained. For the energy management optimization strategy, it is sent to the rotor device, and the control system adjusts the flight attitude according to the command to reduce energy consumption. For example, in the case of large temperature fluctuations and changeable wind directions, the air resistance is reduced by fine-tuning the flight attitude, thereby reducing energy consumption. The rotor device reduces the rotor speed according to the command to reduce energy consumption. When it is determined that the appropriate reduction of the rotor speed under the current meteorological conditions such as wind speed and temperature will not affect the flight stability, it will operate according to the calculated optimized rotor speed, thereby realizing the corresponding operation according to the energy management optimization strategy, achieving the purpose of reducing energy consumption and extending the flight time, and ensuring that the UAV can maintain sufficient power support during the entire inspection task.

[0044] While the drone maintains stable flight, the shooting equipment it carries (such as high-definition cameras, infrared thermal imagers, etc.) shoots and collects data on the photovoltaic components, brackets, wiring, etc. of the distributed rooftop photovoltaic system according to the predetermined inspection route and shooting parameters. For example, the high-definition camera shoots the surface of the photovoltaic component at a frame rate of 8 frames per second, focusing on whether the component is damaged and whether the surface is clean. The infrared thermal imager detects the temperature distribution of the component to check whether there are abnormal phenomena such as local overheating. The collected data is transmitted to the ground control station in real time through the communication module.

[0045] Staff at the ground control station can view, analyze and store data in real time so as to promptly detect abnormal conditions in the distributed rooftop photovoltaic system and take corresponding measures. For example, if it is found that there are obvious stains on the surface of a component of a rooftop photovoltaic system that affects the power generation efficiency, or the component temperature in a certain area is significantly higher than other normal areas, the staff can promptly notify the relevant maintenance personnel to go to the location for cleaning or further inspection and maintenance to ensure the normal operation of the distributed rooftop photovoltaic system.

[0046] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An automatic inspection drone for photovoltaic field in a power station, characterized in that: The drone includes the following components: a weather-adaptive intelligent inspection flight system, a power module, a rotor device, and a communication module; The power module is used to provide power support for various components of the drone; The communication module is used to realize data interaction between the UAV and the ground control station and the photovoltaic field monitoring equipment; The rotor device is installed around the fuselage body to provide the lift and power required for the UAV flight, and can be adjusted by the weather adaptive intelligent inspection flight system; The weather self-adaptive intelligent inspection flight system is connected to the weather sensor array, the rotor device and the flight control system in communication, and the system includes: a data acquisition and analysis submodule, a comprehensive decision submodule and a command execution submodule; The data acquisition and analysis submodule collects data on wind speed, wind direction, temperature and air pressure in real time through a meteorological sensor array that is set at an appropriate position on the fuselage body and has high-precision measurement capabilities. It also analyzes the impact of the differences in the failure risks of photovoltaic equipment in various regions under different meteorological conditions on the inspection route planning by combining a fault risk assessment model set according to the photovoltaic field layout and photovoltaic equipment characteristics and the UAV's own flight performance parameters. At the same time, based on the meteorological data and its own performance parameters, it uses complex mechanical analysis and flight attitude simulation algorithms to preliminarily calculate the direction and degree of flight attitude adjustment required to maintain stable flight under the current meteorological conditions. The comprehensive decision-making submodule obtains information related to the inspection task requirements, and comprehensively considers it with the analysis results of the impact of meteorological conditions on the inspection path and flight attitude provided by the data collection and analysis submodule, and uses the priority determination algorithm to determine the inspection priority of each area, automatically increase the priority of areas that are greatly affected by wind and have high potential for faults, and adopts an intelligent algorithm to use the geographical layout of the photovoltaic field, the inspection priority of each area and the current meteorological conditions as input parameters to perform real-time dynamic optimization of the inspection path. At the same time, based on the analysis results of the data collection and analysis submodule on flight attitude adjustment, combined with the performance parameters of the drone itself and the current meteorological conditions, a calculation model is used to derive the key parameter adjustment amounts of the flight attitude and rotor speed required to maintain stable flight. In addition, by obtaining the real-time status information and meteorological conditions of the drone, the inspection energy consumption is analyzed and calculated based on the preset energy consumption calculation model, and the corresponding strategy formulation algorithm is used according to different situations to formulate an energy management optimization strategy for optimizing the inspection path; The instruction execution submodule is responsible for receiving the inspection path optimization plan, flight attitude adjustment instructions and decision results of the energy management optimization strategy determined by the comprehensive decision-making submodule, and establishing a stable and efficient communication link with the communication module of the UAV and various related execution components to ensure accurate and timely transmission of instructions.

2. The automatic inspection drone for photovoltaic field in power station according to claim 1 is characterized in that: The data acquisition and analysis submodule combines the fault risk assessment model set according to the photovoltaic field layout and photovoltaic equipment characteristics and the flight performance parameters of the drone itself to analyze the impact of the differences in photovoltaic equipment failure risks in various regions under different meteorological conditions on inspection path planning, and uses the formula Quantitatively evaluate the failure risk of photovoltaic equipment in each region, where R f (i) represents the failure risk value of the photovoltaic equipment in the i-th region, α and β are weight coefficients, n represents the number of meteorological factors that affect the failure risk of photovoltaic equipment, and W j is the weight of the jth meteorological factor, F ij represents the actual measured value of the jth meteorological factor in the ith region, S i is the structural strength parameter of the photovoltaic equipment in the i-th region, m represents the number of types of photovoltaic equipment characteristic factors that affect the failure risk of photovoltaic equipment, V k is the weight of the characteristic factor of the k-th photovoltaic device, G ik represents the actual value of the characteristic factor of the kth photovoltaic device in the ith region, T i is the performance parameter of the photovoltaic device in the i-th region.

3. The automatic inspection drone for photovoltaic field in power station according to claim 1 is characterized in that: The data acquisition and analysis submodule preliminarily calculates the direction and degree of flight attitude adjustment required to maintain stable flight under current meteorological conditions based on meteorological data and its own performance parameters through complex mechanical analysis and flight attitude simulation algorithm. The calculation formula is: Among them, θ a represents the flight attitude adjustment angle required for the UAV to maintain stable flight under the current meteorological conditions. γ and δ are weight coefficients used to balance the influence of different factors on the flight attitude adjustment estimation. p represents the number of meteorological factors that affect the flight attitude adjustment. l is the weight of the first meteorological factor, H il represents the actual measured value of the lth meteorological factor in the ith region, Z i is the spatial characteristic parameter of the ith region, r represents the number of characteristics of the UAV itself that affect the flight attitude adjustment, and Y q is the weight of the characteristic factor of the qth type of UAV, I iq represents the actual value of the characteristic factor of the qth type of UAV in the ith region, U i is the flight condition parameter of the ith area.

4. The automatic inspection drone for photovoltaic field in a power station according to claim 1 is characterized in that: The comprehensive decision-making submodule uses a priority determination algorithm to determine the inspection priority of each area, and its calculation formula is: pri (i) = μ × R f (i)+ν×E eff (i)+ω×P adj (i), where P pri (i) represents the inspection priority value of the ith area. The higher the value, the higher the degree to which the area should be inspected first under the current meteorological conditions and overall inspection requirements. μ, ν, and ω are weight coefficients used to balance the influence of different factors on the inspection area priority determination. R f (i) represents the failure risk value of the photovoltaic equipment in the i-th region, which comprehensively reflects the failure possibility of the photovoltaic equipment in this region under the current meteorological conditions based on meteorological factors and the characteristics of the photovoltaic equipment itself. eff (i) is the impact value of the inspection efficiency of the ith region, which is obtained by comprehensively evaluating the impact of various meteorological factors on the inspection efficiency in the region. It indicates the degree of impact of the meteorological conditions in the region on the overall inspection efficiency. adj (i) is the necessity degree value of the inspection route adjustment in the i-th area, which reflects the necessity degree of adjusting the inspection route in the area under the current meteorological conditions and the status of the photovoltaic equipment.

5. The automatic inspection drone for photovoltaic field in power station according to claim 4 is characterized in that: In the comprehensive decision-making submodule, E eff (i) is the inspection efficiency impact value of the i-th area, and its calculation formula is: Among them, η is the weight coefficient, N represents the total number of regions divided into photovoltaic fields, and F ij represents the actual measurement value of the jth meteorological factor in the ith region, which is collected in real time by the meteorological sensor array. 0j represents the reference value of the jth meteorological factor, P adj (i) is the necessity value of the inspection path adjustment in the i-th area, and its calculation formula is: Among them, P adj The higher the value of (i), the greater the necessity to adjust the inspection path of the area under the current meteorological conditions and the state of the photovoltaic equipment. ∈ and ζ are weight coefficients, which are used to balance the influence of meteorological factors and the characteristics of the photovoltaic equipment itself on the necessity assessment of inspection path adjustment. n: represents the number of meteorological factors that affect the inspection path adjustment, including wind speed, wind direction, temperature and air pressure factors. W j is the weight of the jth meteorological factor.

6. The automatic inspection drone for photovoltaic field in a power station according to claim 1, characterized in that: The comprehensive decision-making submodule adopts an intelligent algorithm, takes the geographical layout of the photovoltaic field, the inspection priority of each area and the current meteorological conditions as input parameters, and performs real-time dynamic optimization of the inspection path. Specifically, let G(V,E) represent the photovoltaic field map, where V is a vertex set representing each area of ​​the photovoltaic field, E is an edge set representing the reachable relationship between areas, let S be the starting point, that is, the take-off point of the drone or the end point of the last inspection, T is the target point, that is, the end point specified for this inspection task or a certain area that needs to be inspected, let P = {S} be the currently determined inspection path, which initially only contains the starting point, C visited (v) is the number of times vertex v has been visited. Initially, the number of times all vertices have been visited is 0. In each iteration, starting from the last vertex u of the current path P, the cost function C(u,v) from u to all unvisited vertices v is calculated. The calculation formula is: C(u,v)=α1×D(u,v)+α2×P pri (v)+α3×E eff (v), α1, α2 and α3 are weight coefficients used to balance the importance of distance, inspection priority and inspection efficiency in path selection. D(u,v) represents the distance from vertex u to vertex v. P pri (v) represents the inspection priority value of the vth area, E eff (v) is the inspection efficiency impact value of the vth area, and the vertex v with the smallest cost function C(u,v) is selected. min , add it to the current path P, that is, P = P∪{v min }, and update vertex v min Number of visits C visited (v min )=C visited (v min )+1, when the target point T is added to the path P or the maximum number of iterations is reached, the iteration process ends, and the path P obtained at this time is the optimized inspection path.

7. The automatic inspection drone for photovoltaic field in power station according to claim 1 is characterized in that: The comprehensive decision-making submodule uses a calculation model to obtain the key parameter adjustment of the flight attitude and rotor speed required to maintain stable flight based on the analysis results of the data acquisition and analysis submodule on the flight attitude adjustment, combined with the performance parameters of the UAV itself and the current meteorological conditions. The calculation formula of the flight attitude parameter adjustment is: The calculation formula of the rotor speed parameter adjustment is: Δθ f Represents the change in the UAV flight attitude adjustment angle calculated accurately, Δr s represents the rotor speed adjustment calculated accurately, φ and ρ are weight coefficients, p represents the number of meteorological factors that affect the flight attitude adjustment, and X l is the weight of the first meteorological factor, H il represents the actual measured value of the lth meteorological factor in the ith region, H 0l represents the reference value of the lth meteorological factor, n represents the number of meteorological factors that affect the rotor speed adjustment, and W j is the weight of the jth meteorological factor, F ij represents the actual measured value of the jth meteorological factor in the ith region, F 0j represents the reference value of the jth meteorological factor, Z i is the spatial characteristic parameter of the ith region, S i is the structural strength parameter of the photovoltaic equipment in the i-th region.

8. The automatic inspection drone for photovoltaic field in a power station according to claim 1, characterized in that: The comprehensive decision-making submodule analyzes and calculates the inspection energy consumption based on the preset energy consumption calculation model, and uses the corresponding strategy formulation algorithm to formulate energy management optimization strategies for optimizing inspection paths according to different situations, and obtains the inspection priority value P of each area. pri (i), and the distance D from the starting point to the i-th area calculated based on the geographical layout of the PV field and the flight characteristics of the UAV i , and obtain the preset weight coefficient β2, and use the strategy formula to calculate the energy consumption value of the optimized inspection path Substitute the obtained parameters into the formula, and calculate the energy consumption value E of the optimized inspection path by comprehensively considering the inspection priority of each area and the distance from the starting point to each area. path,opt , in order to optimize the inspection path.

Images