A method, system, equipment, and storage medium for detecting snow load on photovoltaic modules.

Abstract

This invention discloses a method, system, device, and storage medium for detecting snow load on photovoltaic modules. The photovoltaic module is uniformly divided into multiple test blocks. Using pressure sensors and laser snow depth sensors, pressure data and snow depth data corresponding to each test block are acquired after snow accumulation. Based on the pressure and snow depth data of each test block, first and second load data are determined for each test block. The target load data for each test block is determined based on the first and second load data and a preset weighting coefficient. This invention divides the photovoltaic module into multiple test blocks and collects pressure and snow depth data for each block. Based on these two types of data, the first and second load data are determined, and then the overall load data of the photovoltaic module is accurately determined according to the weighting coefficient. By utilizing two testing methods and taking into account the different snow loads at different locations on the module, the detection accuracy is greatly improved.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic power generation, and in particular to a method, system, computing device, and computer storage medium for detecting snow load on photovoltaic modules. Background Technology

[0002] Because traditional fossil fuels are non-renewable energy sources and cause various types of environmental pollution during their use, the use of various clean energy sources is increasing, with solar energy gaining popularity due to its numerous advantages. Photovoltaic power generation projects are the most important application of solar energy.

[0003] However, photovoltaic (PV) modules need to be installed outdoors to receive sunlight, so they will face different types of weather conditions throughout the year, all of which will have a certain impact on PV modules. In particular, winter snowfall will directly cover PV modules, not only blocking them but also creating loads that put stress on them.

[0004] Current patents in this field determine the load that photovoltaic modules can withstand by simulating the load conditions caused by rain and snow, but they do not accurately determine the load caused by actual snow accumulation. Therefore, it is impossible to understand the actual snow load conditions of photovoltaic modules and to provide prompts for clearing. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a method for detecting snow load on photovoltaic modules, along with a corresponding system, computing device, and computer storage medium for detecting snow load on photovoltaic modules.

[0006] According to one aspect of the present invention, a method for detecting snow load on photovoltaic modules is provided, the method comprising:

[0007] The photovoltaic module is evenly divided into multiple test blocks;

[0008] Using pressure sensors and laser snow depth sensors, pressure data and snow depth data for each test block are acquired after snow accumulation.

[0009] Based on the pressure data and snow depth data obtained for each test block, the first load data and the second load data for each test block are determined respectively.

[0010] The target load data for each test block is determined based on the first load data, the second load data, and the preset weighting coefficients.

[0011] In the above scheme, the step of uniformly dividing the photovoltaic module into multiple test blocks further includes:

[0012] The number of test blocks is determined based on the number of solar cells contained in the photovoltaic module; specifically, the number of solar cells in each test block and the number of test blocks are determined based on the number of solar cells in each row and each column of the photovoltaic module.

[0013] In the above scheme, the step of using pressure sensors and laser snow depth sensors to acquire pressure data and snow depth data corresponding to each test block after snow accumulation further includes:

[0014] Pressure sensors are installed on each test block to acquire pressure data for each test block;

[0015] Laser snow depth sensors are installed on photovoltaic modules to obtain snow depth data for each test block;

[0016] An additional pressure sensor is installed on the lower edge of the photovoltaic module to obtain pressure data at the lower edge; and a laser snow depth sensor is used to obtain snow depth data at the lower edge.

[0017] In the above scheme, the step of determining the first load data and the second load data corresponding to each test block based on the obtained pressure data and snow depth data of each test block further includes:

[0018] The first load data and the second load data for each test block were determined based on the pressure data and snow depth data, respectively; among them,

[0019] Based on the pressure data corresponding to each test block and the area of ​​the test block, calculate the first load data of the test block;

[0020] Based on the snow depth and snow density data corresponding to each test block, the second load data for that test block is calculated.

[0021] P = ρ × h × k

[0022] Where P is the second load data; ρ is the snow density; h is the snow depth data; and k is the non-uniformity coefficient.

[0023] In the above scheme, determining the target load data of each test block based on the first load data, the second load data, and the preset weighting coefficient further includes:

[0024] Determine the first coefficient corresponding to the first load data and the second coefficient corresponding to the second load data from the preset weight coefficients;

[0025] The target load data is calculated based on the first load data and its corresponding first coefficient, and the second load data and its corresponding second coefficient.

[0026] An alarm is triggered when the target load data exceeds a predetermined safe load threshold.

[0027] In the above scheme, the step of calculating the second load data of each test block based on the snow depth data and snow density corresponding to each test block further includes:

[0028] A snow cover type recognition model was constructed based on deep convolutional neural network technology;

[0029] An image training set is constructed based on historical image data acquired by a camera, and the snow type recognition model is trained to obtain the trained snow type recognition model.

[0030] The system acquires current snow image data using a camera and inputs it into a trained snow type recognition model to obtain snow type recognition results.

[0031] In the above scheme, after acquiring the current snow image data based on the camera and inputting it into the trained snow type recognition model to obtain the snow type recognition result, the method further includes:

[0032] The current snow type is determined based on the snow type identification results; the snow type includes fresh snow, compacted snow, and wet snow / ice mixture.

[0033] The corresponding snow density is determined based on the current snow cover type; where the snow density ρ corresponds to fresh snow. 新 ≈100kg / m 3 ; Snow density ρ corresponding to compacted snow 压实 ≈250kg / m 3 Snow density ρ corresponding to wet snow / ice mixture 混 ≈250kg / m 3 .

[0034] According to another aspect of the present invention, a photovoltaic module snow load detection system is provided, comprising: a division module, a data acquisition module, a calculation module, and a load determination module; wherein,

[0035] The partitioning module is used to uniformly divide the photovoltaic module into multiple test blocks;

[0036] The data acquisition module is used to acquire pressure data and snow depth data corresponding to each test block after snow accumulation occurs, using pressure sensors and laser snow depth sensors.

[0037] The calculation module is used to determine the first load data and the second load data corresponding to each test block based on the pressure data and snow depth data corresponding to each test block.

[0038] The load determination module is used to determine the target load data of each test block based on the first load data, the second load data, and the preset weighting coefficient.

[0039] According to another aspect of the present invention, a computing device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0040] The memory is used to store at least one executable instruction, which causes the processor to perform an operation corresponding to the above-described method for detecting snow load on a photovoltaic module.

[0041] According to another aspect of the present invention, a computer storage medium is provided, the storage medium storing at least one executable instruction, the executable instruction causing a processor to perform an operation corresponding to the above-described method for detecting snow load on a photovoltaic module.

[0042] According to the technical solution provided by the present invention, the photovoltaic module is uniformly divided into multiple test blocks; pressure sensors and laser snow depth sensors are used to acquire pressure data and snow depth data corresponding to each test block after snow accumulation; based on the acquired pressure data and snow depth data corresponding to each test block, the first load data and the second load data corresponding to each test block are determined respectively; the target load data of each test block is determined according to the first load data, the second load data and the preset weighting coefficient. Based on the technical solution provided by this invention, photovoltaic modules are divided into multiple test blocks. Pressure sensors and laser snow depth sensors are used to acquire pressure data and snow depth data for each test block. This allows for a more detailed understanding of the data for each area of ​​the entire photovoltaic module by acquiring data from each test block, thus addressing the problem of uneven snow load on the photovoltaic module. This helps to obtain more accurate load data after integration. Furthermore, by setting additional pressure sensors and laser snow depth sensors on the lower edge of the photovoltaic module, data at the lower edge, where the load may be increased due to snow sliding and frame obstruction, is acquired. This provides a better understanding of the overall state of the photovoltaic module and improves the accuracy of load data calculation. By collecting pressure data and snow depth data, corresponding load data are calculated based on these two different data types. These are then combined using preset weighting coefficients to further improve the accuracy of the final target load data. This helps staff understand the actual load data of the photovoltaic module under snow conditions, facilitating subsequent cleaning, repair, and maintenance work, as well as understanding the status and performance of the photovoltaic module. Furthermore, a snow type recognition model constructed using a deep convolutional neural network is used to analyze snow images on photovoltaic modules acquired by cameras after training. This model scientifically and accurately identifies the snow type and determines the corresponding snow density for different snow types. This makes the snow load data of photovoltaic modules more accurate, avoiding calculation errors caused by snow type identification bias. Consequently, it avoids damage and failure of modules due to incorrect load data, as well as various potential safety risks, thus reducing overall safety costs.

[0043] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0044] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0045] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0046] Figure 1 A schematic flowchart of a method for detecting snow load on photovoltaic modules according to an embodiment of the present invention is shown;

[0047] Figure 2 A flowchart illustrating a method for data acquisition of snow load on photovoltaic modules according to an embodiment of the present invention is shown.

[0048] Figure 3 A schematic flowchart of a method for calculating snow load on photovoltaic modules according to an embodiment of the present invention is shown.

[0049] Figure 4 A schematic flowchart of a method for identifying snow type and determining density according to an embodiment of the present invention is shown;

[0050] Figure 5 A structural block diagram of a photovoltaic module snow load detection system according to an embodiment of the present invention is shown;

[0051] Figure 6 A schematic diagram of the structure of a computing device according to an embodiment of the present invention is shown. Detailed Implementation

[0052] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0053] Figure 1 A flowchart illustrating a method for detecting snow load on photovoltaic modules according to an embodiment of the present invention is shown. The method includes the following steps:

[0054] Step S101: Divide the photovoltaic module into multiple test blocks evenly.

[0055] Specifically, the number of test blocks is determined based on the number of solar cells contained in the photovoltaic module; wherein, the number of solar cells in each test block and the number of test blocks are determined based on the number of solar cells in each row and each column of the photovoltaic module.

[0056] Preferably, the test blocks are divided according to the actual distribution of the solar cells. The number of solar cells in each row and column is divided in a relatively even manner to determine the number of solar cells in each test block, and the number of test blocks is determined accordingly. The specific allocation method is divided according to actual needs and is not limited here.

[0057] For example, if a photovoltaic module contains 72 solar cells, with 9 cells per row and 8 cells per column, and each row is divided into 3 equal parts and each column into 4 equal parts, then each test block contains 3 cells per row and 2 cells per column, for a total of 6 cells. The entire photovoltaic module is then divided into 12 test blocks.

[0058] Step S102: Using a pressure sensor and a laser snow depth sensor, pressure data and snow depth data corresponding to each test block are acquired after snow accumulation.

[0059] Step S103: Based on the pressure data and snow depth data corresponding to each test block obtained, determine the first load data and the second load data corresponding to each test block respectively.

[0060] Step S104: Determine the target load data for each test block based on the first load data, the second load data, and the preset weighting coefficient.

[0061] According to the photovoltaic module snow load detection method provided in this embodiment, the photovoltaic module is uniformly divided into multiple test blocks; pressure sensors and laser snow depth sensors are used to acquire pressure data and snow depth data corresponding to each test block after snow accumulation; based on the acquired pressure data and snow depth data corresponding to each test block, the first load data and the second load data corresponding to each test block are determined respectively; the target load data of each test block is determined according to the first load data, the second load data, and a preset weighting coefficient. The photovoltaic module snow load detection method provided in this embodiment divides the photovoltaic module into multiple test blocks. Pressure sensors and laser snow depth sensors are used to acquire pressure data and snow depth data for each test block. This allows for a more detailed understanding of the data for each area of ​​the entire photovoltaic module by acquiring data from each test block, thus addressing the problem of uneven snow load on the photovoltaic module. This helps to obtain more accurate load data after integration, improving the accuracy of load data calculation. By collecting the pressure data and snow depth data, corresponding load data are calculated based on these two different data types. These are then combined using preset weighting coefficients to further improve the accuracy of the final target load data. This helps staff understand the actual load data of the photovoltaic module under snow conditions, facilitating subsequent cleaning, repair, and maintenance work, as well as understanding the status and performance of the photovoltaic module.

[0062] Figure 2 A flowchart illustrating a method for data acquisition of snow load on photovoltaic modules according to an embodiment of the present invention is shown.

[0063] like Figure 2 As shown, the method includes the following steps:

[0064] Step S201: Set pressure sensors on each test block to acquire pressure data for each test block.

[0065] Preferably, the pressure sensor is a strain gauge pressure sensor.

[0066] Step S202: Install a laser snow depth sensor on the photovoltaic module to obtain snow depth data for each test block.

[0067] Preferably, the laser snow depth sensor can be a gimbal-mounted laser rangefinder to horizontally scan the snow thickness in different areas of the photovoltaic module.

[0068] In step S203, an additional pressure sensor is installed on the lower edge of the photovoltaic module to obtain lower edge pressure data; and a laser snow depth sensor is used to obtain lower edge snow depth data.

[0069] Preferably, for snow accumulation at the lower edge of photovoltaic modules caused by frame obstruction, a strain gauge pressure sensor is used to monitor the pressure peak area caused by snow sliding in real time, and a gimbaled laser rangefinder is used to measure the accumulation height caused by frame obstruction at the lower edge of the module. Simultaneously, an alarm can be triggered when the snow thickness exceeds a preset alarm thickness, which can be 15cm.

[0070] Based on the above method, by acquiring data from each test block, we can gain a more detailed understanding of the data for each area of ​​the entire photovoltaic module, in order to address the problem of uneven snow load on the photovoltaic module. This helps to obtain more accurate load data after integration. Furthermore, by setting additional pressure sensors and laser snow depth sensors on the lower edge of the photovoltaic module, we can focus on acquiring relevant data at the lower edge where the load may increase due to snow sliding and frame obstruction, thus gaining a better understanding of the overall state of the photovoltaic module and improving the accuracy of load data calculation.

[0071] Figure 3 A schematic flowchart of a method for calculating snow load on photovoltaic modules according to an embodiment of the present invention is shown.

[0072] like Figure 3 As shown, the method includes the following steps:

[0073] Step S301: Determine the first load data and the second load data corresponding to each test block based on the pressure data and snow depth data, respectively.

[0074] Specifically, based on the pressure data corresponding to each test block and the area of ​​the test block, the first load data of the test block is calculated;

[0075] Based on the snow depth and snow density data corresponding to each test block, the second load data for that test block is calculated.

[0076] P = ρ × h × k

[0077] Where P is the second load data; ρ is the snow density; h is the snow depth data; and k is the non-uniformity coefficient.

[0078] Preferably, for the tilt angle of the photovoltaic module, if the tilt angle is ≤30°, the stress concentration at the bottom is 1.5 to 2; if 30° < tilt angle ≤60°, the value of k is 1 to 1.5; if the tilt angle is >60°, k = 1.

[0079] Step S302: Determine the target load data for each test block based on the first load data, the second load data, and the preset weighting coefficient.

[0080] Specifically, the first coefficient corresponding to the first load data and the second coefficient corresponding to the second load data are determined from the preset weighting coefficients;

[0081] The target load data is calculated based on the first load data and its corresponding first coefficient, and the second load data and its corresponding second coefficient.

[0082] Preferably, the first average load data and the second average load data are calculated based on the first load data and the second load data corresponding to each test block, respectively.

[0083] Then, add the product of the first average load data and the first coefficient, and the product of the second average load data and the second coefficient, to obtain the target load data. That is, target load data = first average load data × first coefficient + second average load data × second coefficient.

[0084] Preferably, the first coefficient and the second coefficient can be 0.6 and 0.4, respectively.

[0085] Furthermore, the method also includes:

[0086] Step S303: Based on a predetermined safe load threshold, issue an alarm when the target load data exceeds the safe load threshold.

[0087] Preferably, after the photovoltaic modules leave the factory, a load test is conducted on the same model in advance to determine the safe load threshold.

[0088] Based on the above method, load data can be calculated from the collected pressure data and snow depth data, respectively, according to these two different data types. Based on the first and second load data of each test block, the overall first and second average load data of the photovoltaic module are calculated. These are then combined with preset weighting coefficients to further improve the accuracy of the final target load data. This helps staff understand the actual load data of the photovoltaic module under snow conditions, facilitating subsequent cleaning, repair, and maintenance work, as well as understanding the status and performance of the photovoltaic module. Simultaneously, based on a pre-determined safe load threshold, the current load data is assessed, and an alarm is triggered when it is exceeded, effectively prompting relevant staff to take action, further improving the safety and processing efficiency of the photovoltaic module under snow conditions.

[0089] Figure 4 A schematic flowchart of a method for identifying snow type and determining density according to an embodiment of the present invention is shown;

[0090] like Figure 4 As shown, the method includes the following steps:

[0091] Step S401: Construct a snow type recognition model based on deep convolutional neural network technology.

[0092] Preferably, the deep convolutional neural network can be a ResNet residual network to construct the snow type recognition model.

[0093] Step S402: Construct an image training set based on historical image data acquired by the camera, train the snow type recognition model, and obtain the trained snow type recognition model.

[0094] Step S403: Acquire current snow image data based on the camera and input it into the trained snow type recognition model to obtain the snow type recognition result.

[0095] Preferably, after acquiring current snow image data based on a camera and inputting it into a trained snow type recognition model to obtain a snow type recognition result, the method further includes:

[0096] The current snow type is determined based on the snow type identification results; the snow type includes fresh snow, compacted snow, and wet snow / ice mixture.

[0097] The corresponding snow density is determined based on the current snow cover type; where the snow density ρ corresponds to fresh snow. 新 ≈100kg / m 3 ; Snow density ρ corresponding to compacted snow 压实 ≈250kg / m 3Snow density ρ corresponding to wet snow / ice mixture 混 ≈250kg / m 3 .

[0098] Based on the above method, a snow type recognition model constructed by a deep convolutional neural network is used to analyze snow images on photovoltaic modules acquired by cameras after training. This scientifically and accurately identifies the snow type and determines the corresponding snow density for different snow types. This makes the snow load data of photovoltaic modules more accurate, avoids calculation errors caused by snow type identification bias, and thus avoids module damage and failure caused by incorrect load data, as well as various potential safety risks, thereby reducing the overall safety cost.

[0099] Figure 5 A structural block diagram of a photovoltaic module snow load detection system according to an embodiment of the present invention is shown;

[0100] like Figure 5 As shown, the system includes: a partitioning module 501, a data acquisition module 502, a calculation module 503, and a load determination module 504; wherein,

[0101] The dividing module 501 is used to uniformly divide the photovoltaic module into multiple test blocks.

[0102] Specifically, the partitioning module 501 is further used for:

[0103] The number of test blocks is determined based on the number of solar cells contained in the photovoltaic module; specifically, the number of solar cells in each test block and the number of test blocks are determined based on the number of solar cells in each row and each column of the photovoltaic module.

[0104] The data acquisition module 502 is used to acquire pressure data and snow depth data corresponding to each test block after snow accumulation, using a pressure sensor and a laser snow depth sensor.

[0105] Specifically, the data acquisition module 502 is further used for,

[0106] Pressure sensors are installed on each test block to acquire pressure data for each test block;

[0107] Laser snow depth sensors are installed on photovoltaic modules to obtain snow depth data for each test block;

[0108] An additional pressure sensor is installed on the lower edge of the photovoltaic module to obtain pressure data at the lower edge; and a laser snow depth sensor is used to obtain snow depth data at the lower edge.

[0109] The calculation module 503 is used to determine the first load data and the second load data corresponding to each test block based on the pressure data and snow depth data corresponding to each test block.

[0110] Specifically, the computing module 503 is further used for,

[0111] The first load data and the second load data for each test block were determined based on the pressure data and snow depth data, respectively; among them,

[0112] Based on the pressure data corresponding to each test block and the area of ​​the test block, calculate the first load data of the test block;

[0113] Based on the snow depth and snow density data corresponding to each test block, the second load data for that test block is calculated.

[0114] P = ρ × h × k

[0115] Where P is the second load data; ρ is the snow density; h is the snow depth data; and k is the non-uniformity coefficient.

[0116] Preferably, the calculation module 503 is further used for,

[0117] A snow cover type recognition model was constructed based on deep convolutional neural network technology;

[0118] An image training set is constructed based on historical image data acquired by a camera, and the snow type recognition model is trained to obtain the trained snow type recognition model.

[0119] The system acquires current snow image data using a camera and inputs it into a trained snow type recognition model to obtain snow type recognition results.

[0120] Preferably, the calculation module 503 is further used for,

[0121] The current snow type is determined based on the snow type identification results; the snow type includes fresh snow, compacted snow, and wet snow / ice mixture.

[0122] The corresponding snow density is determined based on the current snow cover type; where the snow density ρ corresponds to fresh snow. 新 ≈100kg / m 3 ; Snow density ρ corresponding to compacted snow 压实 ≈250kg / m 3 Snow density ρ corresponding to wet snow / ice mixture 混 ≈250kg / m 3 .

[0123] The load determination module 504 is used to determine the target load data of each test block based on the first load data, the second load data, and the preset weighting coefficient.

[0124] Specifically, the load determination module 504 is further used for,

[0125] Determine the first coefficient corresponding to the first load data and the second coefficient corresponding to the second load data from the preset weight coefficients;

[0126] The target load data is calculated based on the first load data and its corresponding first coefficient, and the second load data and its corresponding second coefficient.

[0127] An alarm is triggered when the target load data exceeds a predetermined safe load threshold.

[0128] The photovoltaic module snow load detection system provided in this embodiment includes: a division module, a data acquisition module, a calculation module, and a load determination module; wherein, the division module is used to uniformly divide the photovoltaic module into multiple test blocks; the data acquisition module is used to acquire pressure data and snow depth data corresponding to each test block after snow accumulation using a pressure sensor and a laser snow depth sensor; the calculation module is used to determine the first load data and the second load data corresponding to each test block based on the acquired pressure data and snow depth data corresponding to each test block; the load determination module is used to determine the target load data of each test block according to the first load data, the second load data, and a preset weighting coefficient. The photovoltaic module snow load detection system provided in this embodiment divides the photovoltaic module into multiple test blocks. Pressure sensors and laser snow depth sensors are used to acquire pressure and snow depth data for each test block. This allows for a more detailed understanding of the data for each area of ​​the entire photovoltaic module, addressing the issue of uneven snow load. This leads to more accurate load data after integration. Furthermore, by installing additional pressure and laser snow depth sensors on the lower edge of the photovoltaic module, data is specifically acquired at the lower edge where the load may be increased due to snow sliding and frame obstruction. This provides a better understanding of the overall photovoltaic module's condition and improves the accuracy of load data calculation. The system calculates corresponding load data based on the collected pressure and snow depth data, combining them with preset weighting coefficients to further improve the accuracy of the final target load data. This helps staff understand the actual load data of the photovoltaic module under snow conditions, facilitating subsequent cleaning, repair, and maintenance work, as well as understanding the condition and performance of the photovoltaic module. Furthermore, a snow type recognition model constructed using a deep convolutional neural network is used to analyze snow images on photovoltaic modules acquired by cameras after training. This model scientifically and accurately identifies the snow type and determines the corresponding snow density for different snow types. This makes the snow load data of photovoltaic modules more accurate, avoiding calculation errors caused by snow type identification bias. Consequently, it avoids damage and failure of modules due to incorrect load data, as well as various potential safety risks, thus reducing overall safety costs.

[0129] The present invention also provides a non-volatile computer storage medium storing at least one executable instruction that can execute a method for detecting snow load on a photovoltaic module in any of the above method embodiments.

[0130] Figure 6The diagram illustrates the structure of a computing device according to an embodiment of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the computing device.

[0131] like Figure 6 As shown, the computing device may include: a processor 602, a communications interface 604, a memory 606, and a communications bus 608.

[0132] in:

[0133] The processor 602, communication interface 604, and memory 606 communicate with each other via communication bus 608.

[0134] Communication interface 604 is used to communicate with other network elements such as clients or other servers.

[0135] The processor 602 is used to execute program 610, specifically to execute the relevant steps in the above embodiment of the method for detecting snow load on photovoltaic modules.

[0136] Specifically, program 610 may include program code, which includes computer operation instructions.

[0137] Processor 602 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The computing device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0138] Memory 606 is used to store program 610. Memory 606 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0139] Specifically, program 610 can be used to cause processor 602 to execute a photovoltaic module snow load detection method in any of the above method embodiments. The specific implementation of each step in program 610 can be found in the corresponding descriptions of the steps and units in the above embodiments of the photovoltaic module snow load detection method, and will not be repeated here. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the devices and modules described above can be referred to the corresponding process descriptions in the foregoing method embodiments, and will not be repeated here.

[0140] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, this invention is not directed to any particular programming language. It should be understood that the contents of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the invention.

[0141] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0142] Similarly, it should be understood that, in order to streamline this disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof. However, this method of disclosure should not be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0143] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0144] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments can be used in any combination.

[0145] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0146] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for detecting snow load on photovoltaic modules, characterized in that, The method comprises the following steps: dividing the photovoltaic module into multiple test blocks uniformly; acquiring pressure data and snow depth data of each test block after snowfall by using a pressure sensor and a laser snow depth sensor; calculating first load data of each test block based on the pressure data corresponding to the test block and the area of the test block; calculating second load data of each test block based on the snow depth data corresponding to the test block and the snow density; ； wherein, is a second load data; is a snow density; is a snow depth data; is a non-uniformity coefficient; for a module tilt angle of the photovoltaic module, if the module tilt angle ≤ 30°, the bottom stress concentration is the value range is 1.5 to 2; if 30° < the module tilt angle ≤ 60°, the value range is 1 to 1.5; if the module tilt angle > 60°, ; determining target load data of each test block according to the first load data, the second load data and a preset weight coefficient.

2. The method of claim 1, wherein, The step of dividing the photovoltaic module into multiple test blocks uniformly further comprises the following steps: determining the number of test blocks according to the number of cell pieces contained in the photovoltaic module; wherein the number of cell pieces contained in each test block and the number of test blocks are determined according to the number of cell pieces contained in each row and the number of cell pieces contained in each column of the photovoltaic module.

3. The method of claim 1, wherein, The step of acquiring pressure data and snow depth data of each test block after snowfall by using a pressure sensor and a laser snow depth sensor further comprises the following steps: setting a pressure sensor in each test block to acquire pressure data of each test block; setting a laser snow depth sensor on the photovoltaic module to acquire snow depth data of each test block; for the lower edge side of the photovoltaic module, additionally setting a pressure sensor to acquire lower edge pressure data, and using the laser snow depth sensor to acquire lower edge snow depth data.

4. The method of claim 1, wherein, The step of determining target load data of each test block according to the first load data, the second load data and a preset weight coefficient further comprises the following steps: determining a first coefficient corresponding to the first load data and a second coefficient corresponding to the second load data from the preset weight coefficient; calculating the target load data based on the first load data and the first coefficient corresponding thereto, and the second load data and the second coefficient corresponding thereto; performing an alarm when the target load data exceeds a predetermined safety load threshold.

5. The method of claim 1, wherein, The step of calculating second load data of each test block based on the snow depth data corresponding to the test block and the snow density further comprises the following steps: constructing a snow type recognition model based on a deep convolutional neural network technology; constructing an image training set based on historical image data acquired by a camera, training the snow type recognition model to obtain a trained snow type recognition model; inputting current snow image data acquired by the camera into the trained snow type recognition model to obtain a snow type recognition result.

6. The method of claim 5, wherein, After the step of inputting current snow image data acquired by the camera into the trained snow type recognition model to obtain a snow type recognition result, the method further comprises the following steps: determining a current snow type according to the snow type recognition result; wherein the snow type includes fresh snow, compacted snow and wet snow / ice mixture. According to the current snow type, the corresponding snow density is determined; wherein, the new snow corresponds to the snow density ; the compacted snow corresponds to the snow density ; the wet snow / ice mixture corresponds to the snow density .

7. A photovoltaic module snow load detection system characterized by, The method comprises the following steps: a dividing module, a data acquisition module, a calculation module and a load determination module; wherein the dividing module is configured to divide the photovoltaic module into multiple test blocks uniformly; the data acquisition module is configured to acquire pressure data and snow depth data of each test block after snowfall by using a pressure sensor and a laser snow depth sensor; The computing module is configured to calculate first load data of each test block based on pressure data corresponding to the test block and an area of the test block, and calculate second load data of the test block based on snow depth data corresponding to the test block and snow density, ； wherein, is a second load data; is a snow density; is a snow depth data; is a non-uniformity coefficient; for a module tilt angle of the photovoltaic module, if the module tilt angle ≤ 30°, the bottom stress concentration, the value range is 1.5 to 2; if 30° < the module tilt angle ≤ 60°, the value range is 1 to 1.5; if the module tilt angle > 60°, ; The load determining module is configured to determine target load data of each test block according to the first load data, the second load data, and a preset weight coefficient.

8. A computing device, comprising: Comprise: A processor, a memory, a communication interface, and a communication bus, the processor, the memory, and the communication interface complete communication with each other through the communication bus; The memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute operations corresponding to the photovoltaic module snow load detection method in any one of claims 1-6.

9. A computer storage medium, characterized in that The storage medium has at least one executable instruction stored therein, and the executable instruction causes the processor to execute operations corresponding to the photovoltaic module snow load detection method in any one of claims 1-6.

Images