Multi-parameter fusion photovoltaic module accumulated snow detection method and device, medium and equipment

Abstract

The invention discloses a multi-parameter fusion photovoltaic module accumulated snow detection method and device, a medium and equipment, and the method comprises the steps: obtaining the current temperature, brightness and electrical data of a photovoltaic module, and the current environment temperature, calculating the difference value between the temperature of the photovoltaic module and the current environment temperature, taking the difference value as a temperature difference, and carrying out the detection of the accumulated snow of the photovoltaic module based on the electrical data; and calculating the loss rate of the photoelectric conversion efficiency of the photovoltaic module through a photoelectric conversion efficiency loss model, and calculating the thickness value of the accumulated snow of the photovoltaic module through a multi-parameter fusion accumulated snow detection model based on the temperature difference, the brightness and the loss rate of the photoelectric conversion efficiency of the photovoltaic module. By constructing the multi-parameter fusion accumulated snow detection model, indirect detection of the accumulated snow thickness of the photovoltaic module is realized without the help of an expensive snow depth sensor, and the overall accumulated snow detection cost is reduced. In addition, detection of accumulated snow is realized through multi-dimensional correlation analysis, and cross validation and complementation of multi-source information are realized, so that the accuracy and reliability of accumulated snow detection are ensured.

Description

Technical Field

[0001] This application relates to the field of photovoltaic snow removal technology, specifically to a method, apparatus, medium, and equipment for detecting snow accumulation on photovoltaic modules using a multi-parameter fusion approach. Background Technology

[0002] Photovoltaic power generation is an energy technology that utilizes the photovoltaic effect of semiconductor materials to directly convert solar energy into electrical energy. Solar energy, as its energy source, is a fundamental requirement for photovoltaic power generation. When snow accumulates on the surface of photovoltaic modules, it hinders light transmission, weakens the panel's ability to absorb solar radiation, and thus affects the power generation efficiency of the photovoltaic modules. Therefore, to reduce the impact of snow accumulation on the power generation performance of photovoltaic modules, snow removal has become an indispensable part of the operation and maintenance process.

[0003] In related technologies, snow thickness detection typically relies on image recognition technology or dedicated external snow depth sensors. Image recognition methods suffer from high computational costs and deployment expenses, and lack intuitive representation of snow depth and precipitation. While direct snow depth detection using snow sensors offers advantages in accuracy, its application is costly for large-scale photovoltaic power plants. In short, existing snow detection technologies and snow removal methods cannot simultaneously balance cost and accuracy in snow detection.

[0004] Therefore, how to reduce the cost of snow accumulation detection while ensuring the accuracy of snow accumulation detection and achieving efficient snow removal is a problem that photovoltaic snow removal technology urgently needs to solve. Summary of the Invention

[0005] In view of this, embodiments of this application provide a multi-parameter fusion method, apparatus, medium, and equipment for detecting snow accumulation on photovoltaic modules. By constructing a multi-parameter fusion snow accumulation detection model, the method comprehensively analyzes the temperature difference between the surface of the photovoltaic module and the ambient temperature, the brightness of the photovoltaic module surface, and the loss of photoelectric conversion efficiency. Without the need for a snow depth sensor, it can indirectly and accurately estimate the snow accumulation on the photovoltaic module, thereby reducing the cost of snow accumulation detection while ensuring the accuracy of snow accumulation detection.

[0006] In a first aspect, embodiments of this application provide a multi-parameter fusion method for detecting snow accumulation on photovoltaic modules. The method includes: acquiring the current temperature, brightness, electrical data, and current ambient temperature of the photovoltaic module, and calculating the difference between the photovoltaic module's temperature and the current ambient temperature as the temperature difference, wherein the electrical data characterizes the current power generation status of the photovoltaic module; calculating the photoelectric conversion efficiency loss rate of the photovoltaic module based on the electrical data using a photoelectric conversion efficiency loss model, wherein the photoelectric conversion efficiency loss model calculates the ratio of the photovoltaic module's current actual photoelectric conversion efficiency to its expected photoelectric conversion efficiency under snow-free conditions; calculating the snow thickness value of the photovoltaic module based on the temperature difference, brightness, and photoelectric conversion efficiency loss rate using a multi-parameter fusion snow accumulation detection model, wherein the multi-parameter fusion snow accumulation detection model characterizes the mapping relationship between the photovoltaic module's temperature difference, brightness, photoelectric conversion efficiency loss rate, and snow thickness; and determining a snow removal strategy for the photovoltaic module based on the snow thickness value.

[0007] Secondly, embodiments of this application provide a multi-parameter fusion photovoltaic module snow accumulation detection device. The device includes: a data acquisition module configured to acquire the current temperature, brightness, electrical data of the photovoltaic module, and the current ambient temperature, and calculate the difference between the temperature of the photovoltaic module and the current ambient temperature as the temperature difference, wherein the electrical data is used to characterize the current power generation status of the photovoltaic module; and a data processing module configured to calculate the photoelectric conversion efficiency loss rate of the photovoltaic module based on the electrical data using a photoelectric conversion efficiency loss model, wherein the photoelectric conversion efficiency loss model is used to calculate the photovoltaic module's... The current actual photoelectric conversion efficiency of the photovoltaic module is compared with the expected photoelectric conversion efficiency of the photovoltaic module under snowless conditions. The snow thickness calculation module is configured to calculate the snow thickness value of the photovoltaic module based on the temperature difference, brightness, and photoelectric conversion efficiency loss rate of the photovoltaic module through a multi-parameter fusion snow detection model, wherein the multi-parameter fusion snow detection model is used to characterize the mapping relationship between the temperature difference, brightness, and photoelectric conversion efficiency loss rate of the photovoltaic module and the snow thickness. The snow removal strategy formulation module is configured to determine the snow removal strategy of the photovoltaic module based on the snow thickness value.

[0008] Thirdly, embodiments of this application provide an electronic device, including: a processor; and a memory for storing processor-executable instructions, wherein the processor is used to execute the multi-parameter fusion photovoltaic module snow accumulation detection method described in the first aspect above.

[0009] This application provides a multi-parameter fusion method, apparatus, medium, and device for detecting snow accumulation on photovoltaic modules. By constructing a multi-parameter fusion snow accumulation detection model, the snow thickness of the photovoltaic module is indirectly calculated based on the temperature, brightness, and photoelectric conversion efficiency loss rate of the photovoltaic module. This achieves snow thickness detection on photovoltaic modules without the need for expensive snow depth sensors, reducing the overall cost of snow accumulation detection. Furthermore, multi-dimensional correlation analysis is used to detect snow accumulation, enabling cross-validation and complementarity of multi-source information, improving the anti-interference capability of the snow accumulation detection model, ensuring the accuracy and reliability of snow accumulation detection, and reducing the overall cost of snow accumulation detection while maintaining accuracy. Attached Figure Description

[0010] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the embodiments of the present disclosure to explain the disclosure and do not constitute a limitation thereof. The above and other features and advantages will become more apparent to those skilled in the art from the description of detailed exemplary embodiments with reference to the accompanying drawings.

[0011] Figure 1 This is a schematic diagram of the structure of a multi-parameter fusion photovoltaic module snow accumulation detection system provided in some embodiments of this application.

[0012] Figure 2 This is a flowchart illustrating a multi-parameter fusion-based method for detecting snow accumulation on photovoltaic modules, provided in some embodiments of this application.

[0013] Figure 3 This is a flowchart illustrating a method for calculating the snow thickness value of a photovoltaic module using a multi-parameter fusion snow detection model, as provided in some embodiments of this application.

[0014] Figure 4 This is a schematic flowchart of a photovoltaic module snow removal method provided in some embodiments of this application.

[0015] Figure 5 This is a schematic diagram of the structure of a multi-parameter fusion photovoltaic module snow accumulation detection device provided in an exemplary embodiment of this application.

[0016] Figure 6 This is a block diagram of an electronic device for detecting snow accumulation on photovoltaic modules using multi-parameter fusion, provided in an exemplary embodiment of this application. Detailed Implementation

[0017] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] Application Overview In cold regions with frequent snowfall, snow accumulation on the surface of photovoltaic modules is one of the main factors affecting the power generation efficiency (photovoltaic conversion efficiency) of photovoltaic modules. Therefore, photovoltaic snow removal technology has become an indispensable part of photovoltaic operation and maintenance.

[0019] Snow thickness detection on photovoltaic (PV) panels is a prerequisite for snow removal operations. The accuracy of snow thickness detection directly affects the formulation and execution of subsequent snow removal strategies. Currently, snow thickness is typically detected using image recognition technology or dedicated external snow depth sensors. However, image recognition methods suffer from high computational complexity and deployment costs. Furthermore, their accuracy is easily affected by the selection of reference points, lighting conditions, and other environmental factors, making high-precision snow thickness detection difficult. While snow depth sensors offer advantages in accuracy, deploying them comprehensively for large-scale PV power plants is prohibitively expensive.

[0020] To address the aforementioned issues, this application provides a novel multi-parameter fusion snow accumulation detection method. This method innovatively constructs a multi-parameter fusion snow accumulation detection model to comprehensively analyze the temperature difference between the photovoltaic module surface and the ambient temperature, the brightness of the photovoltaic module surface, and the loss of photoelectric conversion efficiency. Without the need for a snow depth sensor, it achieves indirect and accurate estimation of snow accumulation on the photovoltaic module, thereby reducing the cost of snow accumulation detection while ensuring the accuracy of snow accumulation detection.

[0021] The following will refer to the appendix. Figures 1-6 The following describes various non-limiting embodiments of this application.

[0022] Exemplary Multi-parameter Fusion Snow Cover Detection System The multi-parameter fusion snow accumulation detection method provided in this application can be applied to a multi-parameter fusion snow accumulation detection system, which can detect snow thickness based on the triggering of the loss rate of photovoltaic module photoelectric conversion efficiency.

[0023] Figure 1 This is a schematic diagram of the structure of a multi-parameter fusion snow cover detection system provided in some embodiments of this application.

[0024] like Figure 1 As shown, the multi-parameter fusion snow cover detection system 100 in this application may include a photovoltaic panel array 110, a sensor assembly 120, a controller 130, a memory 140, an inverter 150, and a power grid 160. The photovoltaic panel array 110 may include multiple photovoltaic modules, and this application does not specify the number of photovoltaic modules 111.

[0025] In some embodiments, the sensor component 120 may be disposed on the photovoltaic array 110 for acquiring relevant parameter information of the photovoltaic module and environmental information.

[0026] For example, sensor assembly 120 may include a temperature sensor, a brightness sensor, a current sensor, and a voltage sensor. Specifically, the temperature sensor is disposed on the surface of the photovoltaic module and the backplane, respectively, to measure the temperature information of the photovoltaic module surface and the ambient temperature. The brightness sensor is disposed on the surface of the photovoltaic module to measure the brightness information of the photovoltaic module surface. The current sensor and the voltage sensor are disposed inside the photovoltaic module to measure the electrical data of the photovoltaic module.

[0027] In some embodiments, the controller 130 may be configured to be connected to the sensor assembly 120 and the inverter 150 respectively to control the power conversion process of the photovoltaic module 111 and realize the photovoltaic power generation process.

[0028] In some embodiments, the inverter 150 is connected between the power grid 160 and the photovoltaic panel array 110. The controller 130 can also change the output state of the current by controlling the inverter to be in energy storage state or inverter state, that is, the output is AC or DC.

[0029] Specifically, during the daytime sunrise, multiple photovoltaic units 111 in the photovoltaic panel array 110 absorb light energy. The light energy excites electrons in the photovoltaic units (also known as photovoltaic cells) to undergo transitions, generating electron-hole pairs and forming a current flowing from the P-type region to the N-type region, thereby generating direct current (DC). At this time, the controller 130 can control the inverter 150 to convert the DC generated by the photovoltaic panel array 110 into alternating current (AC) and output it to the power grid 160.

[0030] In some embodiments, the inverter 150 may be one or more of a grid-connected bidirectional inverter, a centralized inverter, and a string inverter, and may be flexibly configured according to the number of photovoltaic units included in the photovoltaic array 110, without being specifically limited here.

[0031] In some embodiments, the controller 130 can detect the thickness of snow on the photovoltaic module by using a multi-parameter fusion snow detection model stored in the memory 140, based on sensing data about the photovoltaic module 111 obtained from the sensor assembly 120 and sensing data about the environment.

[0032] In some embodiments, after receiving a snow removal signal, the controller 130 can control the inverter 150 to convert AC power to DC power output and apply a positive voltage across the photovoltaic module 111, so that the photovoltaic array 110 generates a certain amount of heat to melt the snow on the photovoltaic module 111.

[0033] In some embodiments, the multi-parameter fusion snow detection system 100 may further include a heating device, which, after the controller receives a snow removal signal, controls the heating device to generate heat to melt the snow on the photovoltaic module 111.

[0034] In some embodiments, memory 140 may be used to store data and / or instructions. Memory 140 may include one or more storage components, each of which may be a separate device or part of another device. In some embodiments, memory 140 includes random access memory (RAM), read-only memory (ROM), mass storage, and any combination thereof. Exemplary mass storage may include a hard disk, optical disk, solid-state drive, etc.

[0035] In some embodiments, memory 140 may be configured to store a computer program relating to the multi-parameter fusion photovoltaic module snow accumulation detection method shown in this application. When the computer program is executed (e.g., called by controller 130), the multi-parameter fusion photovoltaic module snow accumulation detection method shown in the embodiments of this application can be implemented.

[0036] Exemplary multi-parameter fusion snow detection method Corresponding to the above system, this application provides a method for detecting snow accumulation on photovoltaic modules using a multi-parameter fusion snow accumulation detection system. Figure 2 The diagram shown is a schematic flowchart of a multi-parameter fusion photovoltaic module snow detection method provided in some embodiments of this application.

[0037] In some embodiments, Figure 2 The exemplary process shown can be executed by controller 130.

[0038] like Figure 2 As shown, the method may include the following steps: S210. Obtain the current temperature, brightness, electrical data of the photovoltaic module and the current ambient temperature, and calculate the difference between the temperature of the photovoltaic module and the current ambient temperature as the temperature difference.

[0039] The current temperature of a photovoltaic module can refer to the temperature information of the surface of the photovoltaic module, the brightness can refer to the brightness information of the photovoltaic module, and the electrical data can include current data and voltage data, which are used to characterize the current power generation status of the photovoltaic module.

[0040] S220. Based on electrical data, calculate the photoelectric conversion efficiency loss rate of the photovoltaic module using a photoelectric conversion efficiency loss model.

[0041] Among them, the photoelectric conversion efficiency loss model is used to calculate the loss ratio between the current actual photoelectric conversion efficiency of the photovoltaic module and the expected photoelectric conversion efficiency of the photovoltaic module under the condition of no snow accumulation.

[0042] In some embodiments, the photoelectric conversion efficiency loss model can calculate the loss rate of the photovoltaic module's photoelectric conversion efficiency using its built-in photoelectric conversion efficiency function. For example, the photoelectric conversion efficiency function can be: in, The loss rate representing the photoelectric conversion efficiency of a photovoltaic module. This represents the current actual photoelectric conversion efficiency of photovoltaic modules. This represents the expected photoelectric conversion efficiency of photovoltaic modules under conditions of no snow accumulation. This represents the output power of a photovoltaic module at its maximum power point. The value represents the solar irradiance illuminating the surface of the photovoltaic module (unit: W / m²), and A represents the area of ​​the photovoltaic module (unit: m²).

[0043] In some embodiments, the maximum power point of a photovoltaic module can be calculated using a photovoltaic model. The photovoltaic model can be a mathematical model capable of accurately describing the nonlinear output characteristics (IV curve) of a photovoltaic module. For example, the photovoltaic model can be a single-diode model, and the current-voltage relationship (IV curve) described by a single diode can be achieved using the following formula: in, Represents the photocurrent source current. Represents the reverse saturation current of the diode. This represents the series resistance inside the photovoltaic module. Represents the parallel resistance inside the photovoltaic module. This represents the thermal voltage term related to the diode's ideality factor. Represents the output voltage of the photovoltaic module. This represents the output current of the photovoltaic module.

[0044] S230. Based on the temperature difference, brightness, and photoelectric conversion efficiency loss rate of the photovoltaic module, the snow thickness of the photovoltaic module is calculated by using a multi-parameter fusion snow detection model.

[0045] A multi-parameter fusion snow accumulation detection model is used to characterize the mapping relationship between the temperature difference, brightness, and photoelectric conversion efficiency loss rate of photovoltaic modules and the snow accumulation thickness.

[0046] Specifically, such as Figure 3 As shown, S230 may include the following sub-steps: S231. Perform feature mapping on the loss rate of temperature difference, brightness and photoelectric conversion efficiency to obtain the corresponding temperature difference characteristics, brightness characteristics and efficiency loss characteristics.

[0047] In some embodiments, the temperature difference, brightness, and photoelectric conversion efficiency loss rate of the photovoltaic module are first standardized to achieve feature mapping of the temperature difference, brightness, and photoelectric conversion efficiency loss rate, thereby obtaining the corresponding temperature difference characteristics, brightness characteristics, and efficiency loss characteristics, so as to facilitate the subsequent calculation of snow thickness by the model.

[0048] Considering the saturation characteristics of the snow insulation effect, even without snow accumulation, photovoltaic modules generate heat while converting solar energy into electricity through the photoelectric effect, resulting in a surface temperature 5°C-15°C higher than the ambient temperature. As snow accumulates, the temperature difference between the photovoltaic module and the ambient temperature gradually decreases. When the photovoltaic module is completely covered by snow, the temperature difference may even become negative. For example, the temperature difference can be standardized using the following temperature difference mapping formula to achieve temperature difference... The feature mapping yields the temperature difference characteristics. : i=1,2,3 in, This represents the mean of the i-th polynomial term representing the temperature difference. This represents the standard deviation of the i-th polynomial term representing the temperature difference. and It can be obtained through training samples. These are polynomial eigenvectors used to characterize the nonlinear relationship between temperature difference and snow thickness. For example... .

[0049] For example, considering the exponential decay of light in snow, the brightness can be mapped according to the following brightness mapping formula. Standardization is required to achieve brightness The feature mapping yields the brightness features. , in, The measured value representing brightness (the original brightness measurement value entered). It is a constant representing the offset. The representative is obtained through training on the training dataset. The mean, The representation is obtained through computation based on the training dataset. The standard deviation.

[0050] For example, the loss rate of photoelectric conversion efficiency can be represented by the following efficiency loss mapping formula. Standardize to achieve The feature mapping yields the efficiency loss features. : in, , The representative is obtained through training on the training dataset. The mean, The representative is obtained through training on the training dataset. standard deviation This represents the feature after the Logit transformation, used to map the interval [0,1] to the real number domain. Specifically, the loss rate of photoelectric conversion efficiency can be achieved using the following formula. The Logit transformation yields... .

[0051] in, Representatives passed on The values ​​obtained after boundary protection processing are used to achieve boundary protection, preventing errors in the input during model training or prediction. When the boundary value is 0 or 1, the program crashes or overflows. Specifically, ,in, For example, the boundary buffer constant. It can be 0.001; in this case, boundary protection will be used. Mapping from the [0,1] interval to [0.001,0.999] achieves boundary protection.

[0052] S232. Based on the attention mechanism, dynamically assign corresponding weight parameters to temperature features, brightness features, and efficiency loss features.

[0053] Considering that the reference value of temperature difference, brightness, and photoelectric conversion efficiency loss rate may vary depending on the snow thickness, in the snow thickness detection process, for example, when the snow does not completely cover the photovoltaic modules and the snow is relatively thin, the snow thickness detection may mainly rely on the photoelectric conversion efficiency loss rate, with temperature difference and brightness serving as auxiliary reference factors. When the snow completely covers the photovoltaic modules and the snow thickness is large, the photoelectric conversion efficiency of the photovoltaic modules may have dropped below 5%, approaching the boundary value. At this point, the photoelectric conversion efficiency loss rate will not change significantly with the increase of snow thickness and is no longer suitable as the main reference factor in the snow thickness detection process. Temperature or brightness can be used as the main reference factor in the snow thickness detection process. To address the above issues, some embodiments introduce an attention mechanism into the multi-parameter fusion snow detection model. This allows for adaptive allocation of different weights to the temperature difference feature, brightness feature, and photoelectric conversion efficiency loss rate feature based on the dynamic changes of temperature difference, brightness, and photoelectric conversion efficiency loss rate with snow thickness during the snow thickness detection process, enhancing the model's flexibility and detection accuracy in complex scenarios.

[0054] For example, the following formula can be used to assign corresponding weighting coefficients to the loss rates of temperature difference, brightness, and photoelectric conversion efficiency: , i=1,2,3.

[0055] Among them, attention score , where X is the feature vector set, X=[ ], The weight matrix obtained through training. This is the bias vector obtained through training. This can be represented by temperature difference characteristics. The assigned weights, This can be represented by brightness characteristics. The assigned weights, This can be represented as an efficiency loss characteristic. The assigned weights must satisfy the following conditions: .

[0056] S233. The temperature difference feature, brightness feature and efficiency loss feature are weighted and fused based on the assigned weight parameters.

[0057] In some embodiments, after assigning corresponding weights to the temperature difference feature, brightness feature, and efficiency loss feature in S232, the temperature difference feature, brightness feature, and efficiency loss feature are weighted and fused based on the corresponding weights to obtain the fused features. For example, the fused features can be obtained using the following formula. .

[0058] S234. Based on the weighted fusion features, the snow thickness of the photovoltaic module is calculated using a multi-parameter fusion snow detection model.

[0059] In some embodiments, the features obtained by weighted fusion of temperature difference features, brightness features, and efficiency loss features are further used to detect snow thickness through a multi-parameter fusion snow detection model, thereby improving the accuracy of the model in detecting snow thickness and effectively improving the accuracy and reliability of the model in snow detection and recognition.

[0060] In some embodiments, the multi-parameter fusion snow detection model can be a machine learning model, such as a random forest; or it can be a neural network model, such as a convolutional neural network (CNN) or a lightweight neural network (such as MobileNet or ShuffleNet). This application does not specifically limit the type of the multi-parameter fusion snow detection model.

[0061] In some embodiments, since the snow thickness on adjacent photovoltaic modules is generally the same and the difference is very small, in order to control the overall cost of snow accumulation detection, adjacent photovoltaic modules can be grouped together, and the temperature, brightness, and electrical data of the photovoltaic modules are measured in groups. That is, a temperature sensor, a brightness sensor, a current sensor, and a voltage sensor are set for each group of photovoltaic modules. For example, at least two photovoltaic modules can be divided into multiple photovoltaic strings, wherein each photovoltaic string includes at least one photovoltaic module. By measuring the temperature, brightness, and electrical data of each group of photovoltaic strings, the detection cost can be controlled while ensuring the effectiveness of snow accumulation detection.

[0062] As an example, the number of photovoltaic (PV) modules in each PV string can be determined based on the number of PV modules included in the PV array. For instance, if the PV array contains 12,000 PV modules, it can be divided into 4,000 groups of 3 PV modules each. That is, each PV string contains 3 PV modules.

[0063] It should be noted that this application does not specify the number of photovoltaic modules included in each photovoltaic string. However, in order to ensure the accuracy of the final snow accumulation detection results, the number of photovoltaic modules included in each photovoltaic string should preferably not exceed 5.

[0064] In some embodiments, considering that the main impact of snow accumulation on photovoltaic modules is the reduction in conversion efficiency, this application uses the loss rate of photovoltaic module photoelectric conversion efficiency as the trigger condition for snow detection using a multi-parameter fusion snow detection model. Snow detection is only performed using the multi-parameter fusion snow detection model when the loss rate of photoelectric conversion efficiency reaches the snow detection threshold, significantly reducing the computational overhead of the multi-parameter fusion snow detection model. Furthermore, it avoids frequent model calls for snow detection due to environmental noise in complex environments (e.g., environments with high amplitude and frequency of changes in light or temperature), enhancing the robustness of the snow detection system in complex environments.

[0065] In some embodiments, the snow accumulation detection threshold includes a first detection threshold and a second detection threshold, wherein the first detection threshold is greater than the second detection threshold. The first detection threshold is used to determine whether to enable snow accumulation detection, and the second detection threshold is used to determine whether to stop snow accumulation detection. Specifically, when the photoelectric conversion efficiency loss rate of the photovoltaic module is greater than or equal to the first detection threshold, the snow thickness of the photovoltaic module is calculated using a multi-parameter fusion snow accumulation detection model based on the temperature difference, brightness, and photoelectric conversion efficiency loss rate of the photovoltaic module obtained in S210 and S220. However, when the snow accumulation on the photovoltaic module reaches a certain thickness, the photoelectric conversion efficiency of the photovoltaic module will decrease linearly. When the photoelectric conversion efficiency has decreased to a very low level (e.g., below 3%), the loss rate of photoelectric conversion efficiency of the photovoltaic module will not fluctuate significantly with the continued increase in snow thickness, and the snow thickness detection has lost its reference value. At this time, the detection accuracy of the multi-parameter fusion snow accumulation detection model will also be affected to some extent. Therefore, when the photoelectric conversion efficiency of the photovoltaic module is greater than or equal to the second detection threshold, the process of estimating the snow accumulation of the photovoltaic module using the multi-parameter fusion snow accumulation detection model is stopped.

[0066] For example, assuming that the photovoltaic module has a photoelectric conversion efficiency of 20% under ideal conditions where it is not affected by snow or other factors, the first detection threshold can be 15% and the second detection threshold can be 5%.

[0067] S240. Determine the snow removal strategy for photovoltaic modules based on the snow thickness.

[0068] In some embodiments, to improve the accuracy of snow removal, a targeted snow removal strategy for the photovoltaic module can be formulated by combining two factors: the loss rate of the photovoltaic module's photoelectric conversion efficiency and the thickness of the snow accumulation. For details on the snow removal strategy formulation process, please refer to [link to relevant documentation]. Figure 4 And related descriptions of its corresponding embodiments.

[0069] Therefore, this application constructs a multi-parameter fusion snow accumulation detection model. Based on the temperature, brightness, and photoelectric conversion efficiency loss rate of the photovoltaic module, it indirectly calculates the snow thickness of the photovoltaic module. This achieves snow thickness detection of the photovoltaic module without the need for expensive snow depth sensors, reducing the overall cost of snow accumulation detection. Furthermore, multi-dimensional correlation analysis is used to detect snow accumulation, enabling cross-validation and complementarity of multi-source information. This improves the anti-interference capability of the snow accumulation detection model, ensuring the accuracy and reliability of snow accumulation detection, and ultimately reducing the overall cost of snow accumulation detection while maintaining accuracy.

[0070] Exemplary snow removal method for photovoltaic modules To further illustrate the process of formulating a snow removal strategy, this application provides a flowchart of a photovoltaic module snow removal method. Figure 4 ).

[0071] In some embodiments, Figure 4 The process shown can be executed by controller 130.

[0072] Considering that reducing the loss rate of photoelectric conversion efficiency is one of the main purposes of photovoltaic snow removal, and that when the snow accumulation on the photovoltaic modules is relatively thin, only a small amount of heating power is needed to remove the snow, while when the snow accumulation on the photovoltaic modules is relatively thick, a large amount of heating power is needed to melt the snow quickly. Otherwise, the snow melting time will also affect the overall photoelectric conversion efficiency of the photovoltaic modules. In some embodiments, snow removal strategies are specifically formulated for photovoltaic modules by combining the thickness of the snow accumulation and the loss rate of the photoelectric conversion efficiency of the photovoltaic modules.

[0073] Specifically, such as Figure 4 As shown, the method may include the following steps: S410. Determine the loss rate of the photovoltaic module and the thickness of the snow accumulation.

[0074] Specifically, the loss rate of the photovoltaic module and the snow thickness are determined through the aforementioned steps S220 and S230. For details, please refer to [link to relevant documentation]. Figure 2 and Figure 3 The relevant embodiments are not described in detail here.

[0075] S420. When the snow thickness is greater than or equal to the first snow threshold, less than the second snow threshold, and the loss rate is less than the second detection threshold, the first heating power is used for snow removal.

[0076] S430. When the snow thickness is greater than or equal to the second snow threshold or the loss rate is greater than or equal to the second detection threshold, the second heating power is used for snow removal.

[0077] The first snow accumulation threshold can be defined as the minimum snow thickness at which the photoelectric conversion efficiency of a photovoltaic (PV) module begins to decline. The second snow accumulation threshold can be defined as the snow accumulation thickness at which a 50% loss in PV module PV conversion efficiency is achieved, requiring higher heating power to accelerate snow melting and minimize the PV module's PV conversion efficiency loss caused by snow accumulation. The second snow accumulation threshold is greater than the first snow accumulation threshold.

[0078] Accordingly, the first heating power can be relatively low, used for snow removal when the snow depth of the photovoltaic module falls within the range of a first snow threshold and a second snow threshold (including the first snow threshold, excluding the second snow threshold) and the photoelectric conversion efficiency loss rate is less than a second detection threshold. The second heating power can be relatively high, used when the snow depth of the photovoltaic module is greater than or equal to the second snow threshold or the photoelectric conversion efficiency loss rate is greater than or equal to the second detection threshold, and the second heating power is greater than the first heating power. For details regarding the second detection threshold, please refer to [link to relevant documentation]. Figure 3 The description of the relevant embodiments is not specifically limited herein.

[0079] Therefore, by taking into account the different snow depths and photoelectric conversion efficiency loss rates of photovoltaic modules, different heating powers can be adopted for snow removal, thereby achieving refined snow removal management. This will improve the efficiency and accuracy of snow removal while controlling snow removal costs, thus achieving precise snow removal.

[0080] It should be noted that the first and second snow accumulation thresholds are merely examples. Three different heating powers can be determined using three different snow accumulation thresholds (e.g., the first, second, and third snow accumulation thresholds) to achieve the snow removal process for photovoltaic modules. This application does not specifically limit the first and second snow accumulation thresholds, the first heating power, and the second heating power; these can be flexibly set according to actual conditions.

[0081] In some embodiments, the first heating power and the second heating power can be determined by a snow removal cost model.

[0082] In some embodiments, the heating power (first heating power or second heating power) used for snow removal can be determined according to the above S420 or S430, the voltage required for snow removal can be determined, and the voltage can be applied in reverse to both ends of the photovoltaic module so that the photovoltaic module generates corresponding heat to melt the snow.

[0083] In some embodiments, a heating device may also be provided, which can be activated to generate heat for snow removal.

[0084] Exemplary multi-parameter fusion photovoltaic module snow accumulation detection device Figure 5This is a schematic diagram of the structure of a multi-parameter fusion photovoltaic module snow accumulation detection device 500 provided in an exemplary embodiment of this application. Figure 5 As shown, the multi-parameter integrated photovoltaic module snow detection device 500 includes: a data acquisition module 510, a data processing module 520, a snow thickness calculation module 530, and a snow removal strategy formulation module 540.

[0085] The data acquisition module 510 is configured to acquire the current temperature, brightness, electrical data of the photovoltaic module and the current ambient temperature, and calculate the difference between the temperature of the photovoltaic module and the current ambient temperature as the temperature difference, wherein the electrical data is used to characterize the current power generation status of the photovoltaic module.

[0086] The data processing module 520 is configured to calculate the loss rate of the photovoltaic module's photoelectric conversion efficiency based on the electrical data using a photoelectric conversion efficiency loss model, wherein the photoelectric conversion efficiency loss model is used to calculate the loss ratio of the photovoltaic module's current actual photoelectric conversion efficiency to the photovoltaic module's expected photoelectric conversion efficiency under snowless conditions.

[0087] The snow thickness calculation module 530 is configured to calculate the snow thickness value of the photovoltaic module based on the temperature difference, brightness and photoelectric conversion efficiency loss rate of the photovoltaic module through a multi-parameter fusion snow detection model, wherein the multi-parameter fusion snow detection model is used to characterize the mapping relationship between the temperature difference, brightness and photoelectric conversion efficiency loss rate of the photovoltaic module and the snow thickness.

[0088] The snow removal strategy formulation module 540 is configured to determine the snow removal strategy of the photovoltaic module based on the thickness value of the snow accumulation.

[0089] It should be understood that the specific working process and functions of the acquisition module 510 to the snow removal strategy formulation module 540 in the above embodiments can be referred to the above. Figures 1 to 4 The description of the multi-parameter fusion photovoltaic module snow accumulation detection method provided in the embodiments will not be repeated here to avoid repetition.

[0090] Exemplary electronic devices and computer-readable storage media Figure 6 This is a block diagram of an electronic device 600 for multi-parameter fusion photovoltaic module snow accumulation detection provided in an exemplary embodiment of this application.

[0091] Reference Figure 6The electronic device 600 includes a processing component 610, which further includes one or more processors, and memory resources represented by memory 620 for storing instructions, such as application programs, that can be executed by the processing component 610. The application programs stored in memory 620 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 610 is configured to execute instructions to perform the aforementioned multi-parameter fusion photovoltaic module snow accumulation detection method.

[0092] Electronic device 600 may also include a power supply component configured to perform power management of electronic device 600, a wired or wireless network interface configured to connect electronic device 600 to a network, and an input / output (I / O) interface. Electronic device 600 can be operated based on an operating system stored in memory 620, such as Windows Server. TM Mac OSX TM Unix TM Linux TM FreeBSD TM Or similar.

[0093] A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the aforementioned electronic device 600, enables the electronic device 600 to execute a multi-parameter fusion method for detecting snow accumulation on photovoltaic modules, comprising: acquiring the current temperature, brightness, electrical data of the photovoltaic module, and the current ambient temperature, and calculating the difference between the temperature of the photovoltaic module and the current ambient temperature as the temperature difference; calculating the photoelectric conversion efficiency loss rate of the photovoltaic module based on the electrical data using a photoelectric conversion efficiency loss model; calculating the snow thickness value of the photovoltaic module based on the temperature difference, brightness, and photoelectric conversion efficiency loss rate of the photovoltaic module using a multi-parameter fusion snow accumulation detection model; and determining a snow removal strategy for the photovoltaic module based on the snow thickness value.

[0094] All of the above-mentioned optional technical solutions can be combined in any way to form optional embodiments of this application, and will not be described in detail here.

[0095] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0096] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0097] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0098] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0099] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0100] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program verification codes, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0101] It should be noted that in the description of this application, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0102] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications or equivalent substitutions made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for detecting snow accumulation on photovoltaic modules using multi-parameter fusion, characterized in that, include: The current temperature, brightness, electrical data of the photovoltaic module and the current ambient temperature are obtained, and the difference between the temperature of the photovoltaic module and the current ambient temperature is calculated as the temperature difference. The electrical data is used to characterize the current power generation of the photovoltaic module. Based on the electrical data, the photoelectric conversion efficiency loss rate of the photovoltaic module is calculated using a photoelectric conversion efficiency loss model, wherein the photoelectric conversion efficiency loss model is used to calculate the loss ratio of the current actual photoelectric conversion efficiency of the photovoltaic module compared to the expected photoelectric conversion efficiency of the photovoltaic module under conditions without snow accumulation. Based on the temperature difference, brightness, and photoelectric conversion efficiency loss rate of the photovoltaic module, the snow thickness of the photovoltaic module is calculated by a multi-parameter fusion snow detection model. The multi-parameter fusion snow detection model is used to characterize the mapping relationship between the temperature difference, brightness, and photoelectric conversion efficiency loss rate of the photovoltaic module and the snow thickness. The snow removal strategy for the photovoltaic module is determined based on the thickness of the snow accumulation.

2. The multi-parameter fusion method for detecting snow accumulation on photovoltaic modules according to claim 1, characterized in that, The calculation of the snow thickness value of the photovoltaic module based on the temperature difference, brightness, and photoelectric conversion efficiency loss rate of the photovoltaic module, using a multi-parameter fusion snow detection model, includes: Feature mapping is performed on the temperature difference, the brightness, and the photoelectric conversion efficiency loss rate to obtain the corresponding temperature difference features, brightness features, and efficiency loss features; Based on the attention mechanism, corresponding weight parameters are dynamically assigned to the temperature difference feature, the brightness feature, and the efficiency loss feature; The temperature difference feature, the brightness feature, and the efficiency loss feature are weighted and fused based on the assigned weight parameters. Based on the weighted and fused features, the snow thickness of the photovoltaic module is calculated using the multi-parameter fused snow detection model.

3. The multi-parameter fusion method for detecting snow accumulation on photovoltaic modules according to claim 1, characterized in that, The calculation of the snow thickness value of the photovoltaic module based on the temperature difference, brightness, and photoelectric conversion efficiency loss rate of the photovoltaic module, using a multi-parameter fusion snow detection model, further includes: The loss rate of photoelectric conversion efficiency is used as the trigger condition for snow thickness detection. When the loss rate of photoelectric conversion efficiency meets the snow detection threshold, the snow thickness value of the photovoltaic module is calculated by a multi-parameter fusion snow detection model based on the temperature difference, brightness and the loss rate of photoelectric conversion efficiency of the photovoltaic module.

4. The multi-parameter fusion method for detecting snow accumulation on photovoltaic modules according to claim 3, characterized in that, When the loss rate of the photoelectric conversion efficiency meets the snow detection threshold, the snow thickness value of the photovoltaic module is calculated using a multi-parameter fusion snow detection model based on the temperature difference, brightness, and loss rate of the photoelectric conversion efficiency of the photovoltaic module. This includes: The snow accumulation detection threshold includes a first detection threshold and a second detection threshold, wherein the second detection threshold is less than the first detection threshold; When the loss rate of the photoelectric conversion efficiency of the photovoltaic module is greater than or equal to the first detection threshold, the thickness value of the snow on the photovoltaic module is calculated by a multi-parameter fusion snow detection model based on the temperature difference, brightness and the loss rate of the photoelectric conversion efficiency of the photovoltaic module. When the loss rate of the photovoltaic module's photoelectric conversion efficiency is greater than or equal to the second detection threshold, the snow thickness is not detected.

5. The multi-parameter fusion method for detecting snow accumulation on photovoltaic modules according to claim 4, characterized in that, The snow removal strategy for the photovoltaic module based on the snow thickness includes: When the photoelectric conversion efficiency loss rate of the photovoltaic module is greater than or equal to the first detection threshold, the heating power used for snow removal of the photovoltaic module is determined based on the loss rate and the snow thickness of the photovoltaic module.

6. The multi-parameter fusion method for detecting snow accumulation on photovoltaic modules according to claim 5, characterized in that, The step of determining the heating power used for snow removal from the photovoltaic modules based on the loss rate and the snow thickness of the photovoltaic modules includes: Determine the loss rate of the photovoltaic module and the thickness of the snow accumulation; When the thickness of the snow accumulation is greater than or equal to a first snow accumulation threshold, less than a second snow accumulation threshold, and the loss rate is less than the second detection threshold, the first heating power is used for snow removal, wherein the second snow accumulation threshold is greater than the first snow accumulation threshold. When the thickness of the snow accumulation is greater than or equal to the second snow accumulation threshold or the loss rate is greater than or equal to the second detection threshold, the second heating power is used for snow removal, wherein the second heating power is greater than the first heating power.

7. The multi-parameter fusion method for detecting snow accumulation on photovoltaic modules according to claim 5, characterized in that, The method further includes: Based on the heating power used for snow removal, determine the voltage required for snow removal; The voltage is applied in reverse to both ends of the photovoltaic module, causing the photovoltaic module to generate heat to melt the snow.

8. The multi-parameter fusion method for detecting snow accumulation on photovoltaic modules according to any one of claims 1 to 7, characterized in that, The photovoltaic module includes at least two photovoltaic modules, and the acquisition of the current temperature, brightness, and electrical data of the photovoltaic modules includes: The at least two photovoltaic modules are divided into multiple photovoltaic strings, wherein each photovoltaic string includes at least one photovoltaic module; The temperature, brightness, and electrical data of each photovoltaic string were measured.

9. A multi-parameter fusion photovoltaic module snow accumulation detection device, characterized in that, include: The data acquisition module is configured to acquire the current temperature, brightness, electrical data of the photovoltaic module and the current ambient temperature, and calculate the difference between the temperature of the photovoltaic module and the current ambient temperature as the temperature difference. The electrical data is used to characterize the current power generation status of the photovoltaic module. The data processing module is configured to calculate the loss rate of the photovoltaic module's photoelectric conversion efficiency based on the electrical data using a photoelectric conversion efficiency loss model, wherein the photoelectric conversion efficiency loss model is used to calculate the loss ratio of the photovoltaic module's current actual photoelectric conversion efficiency to the photovoltaic module's expected photoelectric conversion efficiency under snowless conditions. The snow thickness calculation module is configured to calculate the snow thickness value of the photovoltaic module based on the temperature difference, brightness and photoelectric conversion efficiency loss rate of the photovoltaic module through a multi-parameter fusion snow detection model. The multi-parameter fusion snow detection model is used to characterize the mapping relationship between the temperature difference, brightness and photoelectric conversion efficiency loss rate of the photovoltaic module and the snow thickness. The snow removal strategy formulation module is configured to determine the snow removal strategy for the photovoltaic module based on the thickness value of the accumulated snow.

10. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions. The processor is used to execute the multi-parameter fusion photovoltaic module snow accumulation detection method according to any one of claims 1 to 8.

Images