Photovoltaic power station inspection management system and method based on Internet of Things

Abstract

The invention discloses a photovoltaic power station inspection management system and method based on the Internet of Things, and relates to the field of photovoltaic system monitoring, and the system comprises a distributed sensing module which collects the real-time operation data of each photovoltaic unit through multiple types of sensors, and the real-time operation data comprises a current value Ii (t), a voltage value Ui (t), a temperature Ti (t) and an environment illumination intensity L (t); the dynamic decision module is used for calculating a comprehensive health index Hi (t) of the photovoltaic unit and generating a dynamic operation and maintenance priority Pi (t); and the unmanned aerial vehicle scheduling module generates three-dimensional path planning parameters according to the Pi (t). According to the invention, through mechanism fusion and algorithm innovation, full-chain optimization of photovoltaic inspection management is realized, the comprehensive health index model breaks through the limitation of a single threshold criterion, and early fault prediction is realized through dynamic weight and differential operation; and secondly, the data reliability in a complex environment is remarkably improved through a collaborative mechanism of an illumination adaptive threshold value and nonlinear historical correction.

Description

Technical Field

[0001] The present invention belongs to the field of monitoring of photovoltaic systems. More specifically, it particularly relates to an inspection management system for a photovoltaic power station based on the Internet of Things. At the same time, the present invention also relates to a method for inspecting and managing a photovoltaic power station based on the Internet of Things. Background Art

[0002] Efficient inspection of a photovoltaic power station is a core link to ensure power generation efficiency. For example, Chinese Patent CN117519291A discloses a photovoltaic panel inspection system based on multi-drone path planning. It divides regular and irregular areas through panoramic drone image segmentation and allocates multi-machine tasks based on power optimization. It adopts a coverage shooting model and an S-shaped inspection path to allocate flight tasks. However, this technology has significant limitations: First, path planning only relies on geometric topology division, ignoring the dynamic evolution characteristics of the health status of photovoltaic components. Second, power management uses a static allocation model and does not consider the abnormal power consumption fluctuations caused by increased impedance of aging components. In a multi-machine cooperation scenario, it is easy to have inaccurate power estimation, resulting in the interruption of drone tasks. Third, temperature correction relies on a fixed environmental threshold and does not establish a coupling model between light intensity and temperature rise rate. In low light intensity conditions, normal thermal inertia fluctuations are easily misjudged as faults, resulting in a high redundancy alarm rate.

[0003] Specifically, the following technical bottlenecks exist:

[0004] 1) Single dimension of health assessment; A Chinese patent with publication number CN117519291A, a photovoltaic panel inspection system based on multi-drone path planning, identifies foreign object occlusion through image analysis, but lacks real-time monitoring of current and voltage parameters and dynamic compensation of aging factors, and cannot quantify the attenuation degree of components. For example, when the output current of a photovoltaic panel is abnormal due to microcracks, the traditional solution cannot detect it in time through changes in grayscale images.

[0005] 2) Disconnection between path planning and component status; The adopted S-shaped route and reverse inspection method only use battery power as a constraint condition and do not incorporate spatio-temporal gradient parameters of the health index into the path weight calculation, resulting in insufficient coverage of high-risk areas.

[0006] 3) Fixed correction of environmental parameters; This solution adjusts the shooting area by predefined tilt angles, but does not introduce a light-adaptive threshold and a time-related aging correction factor. In dawn, dusk or cloudy weather, the static model is difficult to suppress temperature sensor noise, increasing the misjudgment rate.

[0007] Based on the above, we propose an inspection management system and method for a photovoltaic power station based on the Internet of Things to specifically solve the problems existing in the prior art. Summary of the Invention

[0008] The object of the present invention is to solve the deficiencies existing in the prior art, and a photovoltaic power station inspection management system and method based on the Internet of Things are proposed. Through mechanism integration and algorithm innovation, the whole-chain optimization of photovoltaic inspection management is realized.

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] A photovoltaic power station inspection management system based on the Internet of Things, comprising:

[0011] A distributed sensing module, which collects real-time operation data of each photovoltaic unit through multiple types of sensors, including the current value I i (t), voltage value U i (t), temperature T i (t) and environmental light intensity L(t);

[0012] A dynamic decision-making module, which is used to calculate the comprehensive health index H i (t) of the photovoltaic unit, and generate a dynamic operation and maintenance priority. The calculation formula for calculating the comprehensive health index H i (t) is:

[0013] ;

[0014] In the formula, α and β are weight coefficients, satisfying α 2 + β 2 = 1, and α = ρ·cos(θ), where ρ is the attenuation factor of the photovoltaic material and θ is the installation inclination; γ = 0.05·ln(t) is the time-related aging correction factor; ΔT i (t) is the cumulative amount of historical temperature difference;

[0015] The generation of the dynamic operation and maintenance priority P i (t), the calculation formula is:

[0016] , where dt is the differential increment of time, and dH i (t) is the differential of the health index; when P i (t) > P thre , it marks the dynamic fault determination threshold, and P thre is the dynamic fault determination threshold;

[0017] A drone scheduling module, which generates three-dimensional path planning parameters according to P i (t), and the expression is:

[0018] ; where ∇ x P i (t) and ∇ y P i(t) respectively represent the fault propagation gradient in the x - direction and the environmental coupling gradient in the y - direction.

[0019] Preferably, the calculation of the cumulative historical temperature difference of the comprehensive health index in the dynamic decision - making module adopts non - linear attenuation correction, and the expression is:

[0020] ; where τ is the time step of historical data, the tanh function is used to suppress the temperature fluctuation interference in low - light conditions, T avg is the dynamic temperature reference value, and L thre is the light - adaptation threshold;

[0021] The dynamic temperature reference value T avg , and its calculation formula is:

[0022] ;

[0023] In the formula, ( ) is the time - decay weight, τ is the time interval, N is the statistical period. Different from the traditional static temperature threshold, the dynamic reference value can reflect the historical inertia and environmental adaptability of the thermal behavior of the photovoltaic panel.

[0024] Preferably, the light - adaptation threshold L thre , which is used to distinguish the critical light intensity between normal operation and abnormal light conditions, and its value expression is:

[0025] ;

[0026] In the formula, μL(t) is the historical light - intensity mean of the current season, σL(t) is the standard deviation of light intensity, S(t) is the cloud - cover rate in the past 3 days, and S seasonal is the reference seasonal cloud - cover rate.

[0027] Preferably, when the unmanned aerial vehicle scheduling module conducts three - dimensional path planning, it preferentially normalizes and weights the fault propagation gradient ∇ x P i (t) in the x - direction and the environmental light - intensity attenuation rate, and when the trigger times of the dynamic fault - determination threshold P thre exceed the preset period, it automatically executes the calibration mode;

[0028] The value of the attenuation factor ρ of the photovoltaic material is determined in real - time by a spectral analysis device to measure the light transmittance of the glass cover plate, and a dynamic loading is performed by constructing an exponential - type correlation mapping table in combination with the installation inclination angle θ.

[0029] Preferably, the dynamic temperature reference value T avgThe value of the statistical period N is adjusted in segments according to the installation inclination angle θ of the photovoltaic module. When the inclination angle θ > 30°, N dynamically shortens the statistical window according to the seasonal light distribution.

[0030] The light-adaptive threshold L thre The reference seasonal cloud cover rate S seasonal It is updated by sliding average through the historical meteorological database, and the measured radiation value is introduced to perform feedback compensation on μL(t) in cloudy weather.

[0031] A photovoltaic power station inspection management method based on the Internet of Things. The method is implemented by using the above-mentioned photovoltaic power station inspection management system based on the Internet of Things, and includes the following steps:

[0032] S1. Distributed data collection and dynamic reference calibration. The operating parameters of each unit are periodically collected through the sensing nodes deployed in the photovoltaic matrix, including:

[0033] The current value I i (t), the voltage value U i (t), the temperature T i (t) and the ambient light intensity L(t);

[0034] S2. Dynamic health assessment and operation and maintenance decision generation. First, the comprehensive health index is integrated, then the dynamic priority is generated through differential operation, and finally it is updated according to the current season's cloud cover rate.

[0035] S3. Perform three-dimensional path planning according to the operation and maintenance decision. At the same time, the unmanned aerial vehicle is controlled by the unmanned aerial vehicle scheduling module to perform adaptive inspection.

[0036] Preferably, in step S1, the following process is executed:

[0037] S11. Perform non-linear attenuation correction on the temperature data T i (t), and the expression is:

[0038] ;

[0039] In the formula, τ is the historical data time step, T avg is the dynamic temperature reference value, L thre is the light-adaptive threshold; the tanh function is used to suppress the invalid temperature fluctuation when the light intensity L(t) < L thre ;

[0040] S12. Update the photovoltaic material attenuation factor ρ according to the measured light transmittance of the glass cover in real time, and correct the weight coefficient α according to ρ·cosθ.

[0041] Preferably, in step S2, the dynamic decision module is called to execute the following process:

[0042] S21. Calculate the comprehensive health index:

[0043] ;

[0044] Where U rated is the rated voltage, T max is the upper temperature limit of the component; γ is the time aging factor;

[0045] S22. Generate dynamic priorities through differential operations:

[0046] ;

[0047] When P i (t) > P thre , trigger the UAV scheduling and record the trigger times for calibration mode determination;

[0048] S23. Update according to the current season cloud cover rate S(t):

[0049] ;

[0050] Where ΔS = |S(t) - S seasonal |, and S seasonal is updated by moving average through the meteorological database.

[0051] Preferably, in step S3, the UAV scheduling module performs the following process:

[0052] S31. Construct gradient field parameters:

[0053] ;

[0054] Where is the ambient light intensity attenuation rate, is the light intensity change rate in the x direction;

[0055] S32. When the installation inclination angle θ > 30°, shorten the statistical period of the dynamic temperature reference T avg :

[0056] ;

[0057] S32. Trigger the calibration mode at a preset period: If the number of P thre trigger times > 3 times / period within Δt, then recalibrate the mapping table.

[0058] The technical effects and advantages of the present invention: The photovoltaic power station inspection management system and method based on the Internet of Things provided by the present invention have the following effects compared with the prior art:

[0059] The dynamic multi-dimensional health assessment improves the accuracy of operation and maintenance decisions. The dynamic decision-making module of this application constructs a comprehensive health index through four-dimensional parameters of current, voltage, temperature, and light intensity, and introduces a time-related aging correction factor and a material attenuation factor to achieve fine quantification of the state of photovoltaic units. In traditional methods, health assessment only relies on a single temperature threshold. In this application, through the dynamic adjustment of non-linear weight coefficients α and β, the installation inclination angle of the photovoltaic panel and the material aging rate are incorporated into the calculation model. When the component has excessive inclination resulting in local dust accumulation, the system automatically reduces the temperature weight β and increases the current weight α to avoid misjudgment caused by light intensity fluctuations. Through differential operation of dynamic priorities, the instantaneous change trend of the health index is captured to achieve early fault warning.

[0060] Secondly, by constructing a non-linear correction equation, it effectively distinguishes normal temperature rise from abnormal fluctuations. Traditional linear weighting methods are difficult to suppress temperature noise under low light intensity. In this application, using the saturation characteristic of the tanh function, the small-amplitude temperature fluctuations are exponentially attenuated. In rainy weather, the short-term temperature rise caused by sudden changes in cloud cover rate will be judged as invalid data to avoid triggering false alarms. At the same time, the dynamic temperature reference value is calculated through time decay weights, reflecting the thermal inertia characteristics of the photovoltaic panel.

[0061] Finally, the drone scheduling module generates a dynamic flight path by constructing a fault propagation gradient field and combining the environmental light intensity attenuation rate. Traditional path planning only considers the shortest geometric distance. In this application, through the normalization of weighted light intensity and fault gradient parameters, high-risk areas are preferentially covered. When the comprehensive health index of a certain photovoltaic unit drops sharply due to the hot spot effect, the gradient field will strengthen the drone inspection density in this area. At the same time, the design of the dynamic statistical period enables large-inclination components to obtain a higher detection frequency in the high-temperature season. Description of the Drawings

[0062] Figure 1 is the architecture diagram of the photovoltaic power station inspection management system based on the Internet of Things of the present invention;

[0063] Figure 2 is the flow chart of the photovoltaic power station inspection management method based on the Internet of Things of the present invention. Detailed Embodiments

[0064] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the following further elaborates on the present invention in conjunction with specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0065] The present invention provides an inspection management system and method for a photovoltaic power station based on the Internet of Things, which realizes the full-chain optimization of photovoltaic inspection management through mechanism integration and algorithm innovation. First, the comprehensive health index model breaks through the limitation of a single threshold criterion and realizes early fault prediction through dynamic weights and differential operations. Second, the collaborative mechanism of light-adaptive thresholds and non-linear historical corrections significantly improves data reliability in complex environments. Finally, the gradient-driven path planning technology deeply binds the allocation of UAV resources with the dynamic changes of the light field, solving the problem of resource waste in traditional static paths.

[0066] As Figure 1 shown, the inspection management system architecture of a photovoltaic power station based on the Internet of Things includes:

[0067] A distributed sensing module that collects real-time operation data of each photovoltaic unit through multiple types of sensors, including the current value I i (t), the voltage value U i (t), the temperature T i (t), and the ambient light intensity L(t);

[0068] A dynamic decision-making module for calculating the comprehensive health index H i (t) of the photovoltaic unit and generating a dynamic operation and maintenance priority. The calculation formula for the comprehensive health index H i (t) is:

[0069] ;

[0070] In the formula, α and β are weight coefficients, satisfying α 2 + β 2 = 1, and α = ρ·cos(θ), where ρ is the attenuation factor of the photovoltaic material and θ is the installation inclination angle; γ = 0.05·ln(t) is the time-related aging correction factor; ΔT i (t) is the cumulative historical temperature difference;

[0071] Generate a dynamic operation and maintenance priority P i (t), and the calculation formula is:

[0072] , where dt is the differential increment of time, and dH i (t) is the differential of the health index; when P i (t) > P thre , mark the dynamic fault determination threshold, and P thre is the dynamic fault determination threshold;

[0073] Furthermore, the calculation of the cumulative historical temperature difference of the comprehensive health index in the dynamic decision-making module adopts non-linear attenuation correction, and the expression is:

[0074] ; where τ is the time step of historical data, the tanh function is used to suppress the interference of temperature fluctuations in low light conditions, T avg is the dynamic temperature reference value, L thre is the illumination adaptive threshold; the illumination adaptive threshold L thre , which is used to distinguish the critical light intensity between normal operation and abnormal lighting state. Its value expression is:

[0075] ;

[0076] Where μL(t) is the historical mean of sunlight in the current season, σL(t) is the standard deviation of sunlight intensity, S(t) is the cloud cover rate in the past three days, and S seasonal is the baseline seasonal cloud cover;

[0077] Dynamic temperature reference value T avg , the calculation formula is:

[0078] ;

[0079] Where, ( ) is the time attenuation weight, τ is the time interval, and N is the statistical period. Different from the traditional static temperature threshold, the dynamic reference value can reflect the historical inertia and environmental adaptability of the thermal behavior of the photovoltaic panel. The dynamic temperature reference value T avg The value of the statistical period N is adjusted in sections according to the installation inclination angle θ of the photovoltaic modules. When the inclination angle θ>30°, the statistical window of N is dynamically shortened with the seasonal light distribution.

[0080] Light adaptive threshold L thre The baseline seasonal cloud cover S seasonal The sliding average iterative update is performed through the historical meteorological database, and the measured radiation value is introduced to provide feedback compensation for μL(t) in cloudy weather.

[0081] UAV dispatch module, according to P i (t) Generate three-dimensional path planning parameters, the expression is:

[0082] ; Among them, ∇ x P i (t) and ∇ y P i (t) represents the fault propagation gradient in the x direction and the environmental coupling gradient in the y direction respectively; when the UAV scheduling module performs three-dimensional path planning, the fault propagation gradient in the x direction ∇ x P i (t) is normalized and weighted with the ambient light intensity attenuation rate, and when the dynamic fault judgment threshold P threAutomatically execute the calibration mode when the number of trigger times exceeds the preset period;

[0083] The value of the attenuation factor ρ of the photovoltaic material is determined in real time by a spectral analysis device for the light transmittance of the glass cover plate, and an exponential correlation mapping table is constructed in combination with the installation inclination angle θ for dynamic loading.

[0084] This embodiment also proposes an inspection management method for a photovoltaic power station based on the Internet of Things. The method is implemented by using the above-mentioned inspection management system for a photovoltaic power station based on the Internet of Things, as Figure 2 shown, and includes the following steps:

[0085] S1. Distributed data collection and dynamic reference calibration. Periodically collect the operating parameters of each unit through the sensing nodes deployed in the photovoltaic matrix, including:

[0086] The current value I i (t), the voltage value U i (t), the temperature T i (t) and the ambient light intensity L(t);

[0087] Among them, in step S1, the following process is executed:

[0088] S11. Perform non-linear attenuation correction on the temperature data T i (t), and the expression is:

[0089] ;

[0090] In the formula, τ is the historical data time step, T avg is the dynamic temperature reference value, L thre is the light intensity adaptive threshold; the tanh function is used to suppress the invalid temperature fluctuation when the light intensity L(t) < L thre ;

[0091] S12. Update the attenuation factor ρ of the photovoltaic material according to the real-time measured light transmittance of the glass cover plate, and correct the weight coefficient α according to ρ·cosθ.

[0092] S2. Dynamic health assessment and operation and maintenance decision generation. First, synthesize the health index, then generate the dynamic priority through differential operation, and finally update according to the cloud cover rate in the current season;

[0093] Specifically, in step S2, call the dynamic decision module to execute the following process:

[0094] S21. Calculate the comprehensive health index:

[0095] ;

[0096] In the formula, U rated is the rated voltage, T maxis the upper limit of the temperature resistance of the component; γ is the time aging factor;

[0097] S22. Generate dynamic priorities through differential operations:

[0098] ;

[0099] When P i (t) > P thre Trigger the UAV scheduling and record the number of trigger times for calibration mode determination;

[0100] S23. Update according to the current season's cloud cover rate S(t):

[0101] ;

[0102] where, ΔS = |S(t) - S seasonal |, S seasonal is updated by moving average through the meteorological database.

[0103] S3. Perform three-dimensional path planning according to the operation and maintenance decision. At the same time, control the UAV for adaptive inspection through the UAV scheduling module;

[0104] It should be noted that in step S3, the UAV scheduling module performs the following process:

[0105] S31. Construct gradient field parameters:

[0106] ;

[0107] In the formula, is the environmental light intensity attenuation rate, is the light intensity change rate in the x direction;

[0108] S32. When the installation inclination angle θ > 30°, shorten the statistical period of the dynamic temperature reference T avg :

[0109] ;

[0110] S32. Trigger the calibration mode at a preset period: If the number of trigger times of P thre within Δt > 3 times / period, then recalibrate the mapping table.

[0111] In summary, compared with the prior art, the present invention has the following effects:

[0112] Dynamic multi-dimensional health assessment improves the accuracy of operation and maintenance decisions. The dynamic decision-making module of this application constructs a comprehensive health index through four-dimensional parameters of current, voltage, temperature, and light intensity, and introduces a time-related aging correction factor and a material attenuation factor to achieve fine quantification of the state of photovoltaic units. In traditional methods, health assessment only relies on a single temperature threshold. However, in this application, through the dynamic adjustment of non-linear weight coefficients α and β, the installation inclination angle of the photovoltaic panel and the material aging rate are incorporated into the calculation model. When local dust accumulation occurs due to an excessive inclination angle of the component, the system automatically reduces the temperature weight β and increases the current weight α to avoid misjudgment caused by light intensity fluctuations. Through differential operation of dynamic priorities, the instantaneous change trend of the health index is captured to achieve early fault warning.

[0113] Secondly, by constructing a non-linear correction equation, normal temperature rise and abnormal fluctuations are effectively distinguished. Traditional linear weighting methods are difficult to suppress temperature noise under low light intensity. In this application, the saturation characteristic of the tanh function is used to exponentially decay small temperature fluctuations. During rainy weather, short-term temperature rises caused by sudden changes in cloud cover rate will be judged as invalid data to avoid triggering false alarms. At the same time, the dynamic temperature reference value is calculated through a time decay weight, reflecting the thermal inertia characteristics of the photovoltaic panel.

[0114] Finally, the drone scheduling module generates a dynamic flight path by constructing a fault propagation gradient field and combining the ambient light intensity attenuation rate. Traditional path planning only considers the shortest geometric distance. However, in this application, through the normalization of weighted light intensity and fault gradient parameters, high-risk areas are preferentially covered. When the comprehensive health index of a certain photovoltaic unit drops sharply due to the hot spot effect, the gradient field will strengthen the drone inspection density in this area. At the same time, the design of the dynamic statistical period enables large-inclination components to obtain a higher detection frequency during the high-temperature season.

[0115] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent substitutions on some of the technical features. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A photovoltaic power station inspection management system based on the Internet of Things, characterized in that, Including: Distributed sensing module, which collects real-time operation data of each photovoltaic unit through multiple types of sensors, including current value I i (t), voltage value U i (t), temperature T i (t) and environmental light intensity L(t); A dynamic decision-making module, which is used to calculate the comprehensive health index H i of the photovoltaic unit (t), and generate a dynamic operation and maintenance priority; A drone scheduling module that generates three-dimensional path planning parameters.

2. The photovoltaic power station inspection management system based on the Internet of Things according to claim 1, characterized in that In the dynamic decision-making module, the calculation of the cumulative historical temperature difference of the comprehensive health index adopts non-linear attenuation correction, and the expression is: ; where τ is the time step of historical data, the tanh function is used to suppress the temperature fluctuation interference under low light, and T avg is the dynamic temperature reference value, and L thre is the light-adaptive threshold; The dynamic temperature reference value T avg , and the calculation formula is: ； In the formula, ( ) is the time decay weight, τ is the time interval, and N is the statistical period. Different from the traditional static temperature threshold, the dynamic reference value can reflect the historical inertia and environmental adaptability of the thermal behavior of the photovoltaic panel.

3. The photovoltaic power station inspection management system based on the Internet of Things according to claim 2, characterized in that, The light-adaptive threshold L thre , which is the critical light intensity for distinguishing between normal operation and abnormal light states, and its value expression is: ； where μL(t) is the historical average light intensity of the current season, σL(t) is the standard deviation of the light intensity, S(t) is the cloud cover rate in the past 3 days, and S seasonal is the reference seasonal cloud cover rate.

4. A photovoltaic power station inspection management system based on the Internet of Things according to claim 1, characterized in that, When the UAV scheduling module performs three-dimensional path planning, it preferentially normalizes and weights the x-direction fault propagation gradient ∇ x P i (t) with the ambient light intensity attenuation rate, and automatically executes the calibration mode when the triggering times of the dynamic fault determination threshold P thre exceed the preset period; The value of the photovoltaic material attenuation factor ρ is determined in real time by a spectral analysis device for the light transmittance of the glass cover plate, and an exponential correlation mapping table is constructed in combination with the installation inclination angle θ for dynamic loading.

5. The photovoltaic power station inspection management system based on the Internet of Things according to claim 3, characterized in that, The dynamic temperature reference value T avg The value of the statistical period N is adjusted in segments according to the installation inclination angle θ of the photovoltaic module. When the inclination angle θ > 30°, N dynamically shortens the statistical window according to the seasonal light distribution; The light-adaptive threshold L thre with the reference seasonal cloud cover rate S seasonal is updated iteratively by moving average through the historical meteorological database, and the measured radiation value is introduced to perform feedback compensation on μL(t) in cloudy weather.

6. A photovoltaic power station inspection management method based on the Internet of Things, characterized in that, The method is implemented by using the Internet of Things-based photovoltaic power station inspection management system described in any one of claims 1-5, and includes the following steps: S1. Distributed data collection and dynamic reference calibration, where the sensing nodes deployed in the photovoltaic matrix periodically collect the operation parameters of each unit, including: Current value I i (t), voltage value U i (t), temperature T i (t) and ambient light intensity L(t); S2. Dynamic health assessment and operation and maintenance decision generation. First, the comprehensive health index is calculated, then the dynamic priority is generated through differential operation, and finally it is updated according to the cloud cover rate in the current season; S3. Perform three-dimensional path planning according to the operation and maintenance decision. At the same time, the drone is controlled by the drone scheduling module for adaptive inspection.

7. A photovoltaic power station inspection management method based on the Internet of Things according to claim 6, characterized in that, In step S1, the following process is executed: S11. Perform non-linear attenuation correction on the temperature data T i (t); S12. Update the photovoltaic material attenuation factor ρ according to the light transmittance of the glass cover plate measured in real time, and correct the weight coefficient α according to ρ·cosθ.

8. The method for photovoltaic power station inspection and management based on the Internet of Things according to claim 7, wherein, In step S2, the dynamic decision-making module is called to execute the following process: S21. Calculate the comprehensive health index; S22. Generate the dynamic priority through differential operation; S23. Update according to the cloud cover rate S(t) in the current season: ； where ΔS = |S(t) - S seasonal |, and S seasonal is updated by moving average of the meteorological database.

9. The method for photovoltaic power station inspection and management based on the Internet of Things according to claim 8, wherein, In step S3, the drone scheduling module executes the following process: S31. Construct gradient field parameters: ； In the formula, is the ambient light intensity attenuation rate, is the light intensity change rate in the x direction; S32. When the installation inclination angle θ > 30°, shorten the statistical period of the dynamic temperature reference T avg : ； S32. Trigger the calibration mode at a preset period: If the number of triggers within Δt thre thre > 3 times / period, then recalibrate the mapping table.

Images