Wind resistance early warning methods, devices, equipment and storage media for flexible photovoltaic systems

Abstract

The present application discloses a wind-resistance warning method, device, equipment and storage medium for a flexible photovoltaic support, and relates to the technical field of electrical digital data processing. The method simulates physical mechanical processes and uses Coulomb's law to simulate the tensile stress of the upper and lower chords from the wind. At the same time, the tensile stress under different wind forces can be further simulated by adjusting the charge amount of charged particles. The tensile stress of the upper and lower chords under future wind forces is then predicted through the probability distribution of future wind speeds. Then, corresponding warning signals are given according to the tensile stress under future wind forces, thereby eliminating the lag caused by manual inspections.

Description

Technical Field

[0001] The present application relates to the technical field of electrical digital data processing, and in particular to a wind-resistant warning method, device, equipment and storage medium for a flexible photovoltaic support. Background Art

[0002] ‌Flexible photovoltaic support is a large-span photovoltaic module support structure designed based on a tension structure system and formed by cables as component support members. ‌Compared with traditional rigid supports, it has the characteristics of "large span, high clearance, and long column distance", which enable flexible supports to adapt to more complex and diverse installation environments. ‌The structure of the flexible photovoltaic support adopts prestressed chords (wire ropes) between the two fixed points at both ends. The two fixed points at both ends adopt a rigid structure and an outer inclined steel strand to provide support. It can achieve a large span of 10~30 m and adapt to situations such as undulating mountains and increased vegetation. It only needs to set the foundation at a suitable location and tension the prestressed steel strand or wire rope. Under the condition that the water level remains unchanged, the construction of rigid columns, foundations and flexible supports can be realized in lakes and fish ponds.

[0003] The mainstream flexible photovoltaic brackets are single-layer cable suspension structure, double-layer cable truss structure, fish-belly cable truss structure, and string structure. Among them, the single-layer cable suspension structure is widely used due to its easy installation and easy subsequent maintenance. The single-layer cable suspension structure is generally composed of a main steel frame composed of beams and columns, cable bodies and other main components. The cable body is two cables parallel to the plane of the component. The cable body is used instead of a general tension member. After the component support cable is tensioned, it is fixed by the anchor at the end of the steel beam. The tensioning equipment makes the support cable obtain stress stiffness for supporting the component, and forms a self-balancing system by relying on the end of the cable.

[0004] Since flexible photovoltaic bracket technology only began to appear more than ten years ago, due to early technical and material limitations, the relevant technology of flexible photovoltaic bracket started late and the market development was relatively slow. At present, the research and development of flexible photovoltaic brackets is still in the hardware design and optimization stage, and the monitoring and early warning of flexible photovoltaic brackets are relatively lacking. The monitoring and operation and maintenance of flexible photovoltaic brackets are usually carried out through on-site manual monitoring methods such as manual inspections or drone inspections. Specifically, the flexible photovoltaic brackets are inspected on-site by staff or drones and human judgments are made, which leads to subjective factors and human errors. Moreover, the aforementioned monitoring method requires obvious external damage or damage to the flexible photovoltaic bracket before on-site confirmation of the failure of the flexible photovoltaic bracket can be made. Moreover, manual inspections often need to obtain inspection conclusions only after the damage or damage has occurred, and there is a lag. Summary of the invention

[0005] The main purpose of the present application is to provide a wind-resistant warning method, device, equipment and storage medium for a flexible photovoltaic bracket, so as to solve the problems in the prior art of the lack of monitoring means for flexible photovoltaic brackets and the subjective errors and lags in manual monitoring.

[0006] In order to achieve the above objectives, this application provides the following technical solutions:

[0007] A wind-resistant early warning method for a flexible photovoltaic support, the flexible photovoltaic support comprising at least two steel beams fixed to the ground, upper and lower chords erected on adjacent steel beams and in different planes, and a plurality of photovoltaic panels installed on the upper and lower chords, the wind-resistant early warning method comprising:

[0008] Step S1, constructing a physical model of the area where the flexible photovoltaic support is located in a virtual scene, and inputting the upper chord and the lower chord, as well as all steel beams and all photovoltaic panels into the physical model;

[0009] Step S2, in the physical model, each photovoltaic panel is equivalent to two first charged particles with preset electric quantity and the same polarity, one of the two first charged particles of the same photovoltaic panel is located at the upper chord and the other is located at the lower chord, and the interaction force between all the first charged particles is shielded;

[0010] Step S3, obtaining the future wind speed probability distribution of the area;

[0011] Step S4, converting the probability value of the future wind speed probability distribution into a charge amount according to a preset ratio, and defining the wind speed direction of the future wind speed probability distribution as an arrangement direction;

[0012] Step S5, arranging a plurality of columns of second charged particles in the arrangement direction, the number of columns of all second charged particles is the same as the number of all first charged particles, and the polarity of all second charged particles is the same as the polarity of all first charged particles, each column of second charged particles has a plurality of second charged particles arranged in a single linear manner, and at the same time, shielding the interaction force between all second charged particles;

[0013] Step S6, defining the wind speed of the future wind speed probability distribution as the speed of all second charged particles;

[0014] Step S7, driving all the second charged particles to move toward all the first charged particles based on the speeds of all the second charged particles, and obtaining the maximum first resultant force of the upper chord and the maximum second resultant force of the lower chord;

[0015] Step S8, respectively determining whether the first maximum value of the combined force and the second maximum value of the combined force exceed a preset maximum tensile stress, and if one of the first maximum value of the combined force and the second maximum value of the combined force exceeds the preset maximum tensile stress, executing step S9;

[0016] Step S9, generating an excessive wind warning signal and sending it to an external receiving end.

[0017] As a further improvement of the present application, step S3, obtaining the future wind speed probability distribution of the area, includes:

[0018] Step S31, obtaining a number of historical wind speed data of the area;

[0019] Step S32, normalizing all historical wind speed data and integrating them into a normalized data set;

[0020] Step S33, dividing the normalized data set into a training set and a validation set according to a preset ratio;

[0021] Step S34, defining a topological relationship of the neural network model, wherein the topological relationship includes an input layer, a hidden layer, and an output layer that are sequentially signal-connected;

[0022] Step S35, inputting the training set into the input layer, and iterating through the neural network model, obtaining a root mean square error between the validation set and the current training result based on each iteration;

[0023] Step S36, after the iteration is completed, obtaining the minimum value of all root mean square errors, and obtaining the training result corresponding to the minimum value as the prediction model;

[0024] Step S37, predicting future wind speed data of a preset number of steps by using the prediction model;

[0025] Step S38, substituting the future wind speed data into a two-parameter Weibull distribution function and solving the parameters of the two-parameter Weibull distribution function to obtain the future wind speed probability distribution.

[0026] As a further improvement of the present application, the neural network model is characterized by formula (1):

[0027] (1);

[0028] in, The preset neural network model; is the input layer and , is the first input nodes, each input node corresponds to a training set, is the first The first input node to the hidden layer The weights of the input nodes; is the first The bias of the input node; is the transfer function, and The numbers in the brackets of the superscripts are the number of layers.

[0029] As a further improvement of the present application, the root mean square error is characterized by formula (2):

[0030] (2);

[0031] in, is the root mean square error, is the number of all data in the training set, one data corresponds to one input node, For the The true value of the training set, For the The training results after the training of the training set is completed.

[0032] As a further improvement of the present application, step S38, substituting the future wind speed data into a two-parameter Weibull distribution function and solving the parameters of the two-parameter Weibull distribution function to obtain the future wind speed probability distribution, includes:

[0033] Step S381, defining the two-parameter Weibull distribution function according to formula (3):

[0034] (3);

[0035] in, is the two-parameter Weibull distribution function, and ; is the scale parameter of the Weibull distribution; is the shape parameter of the Weibull distribution; is the future wind speed data;

[0036] Step S382, defining the probability density function of the two-parameter Weibull distribution function according to formula (4):

[0037] (4);

[0038] in, is the probability density function;

[0039] Step S383: define the log-likelihood function of the scale parameter and the shape parameter according to equation (5):

[0040] (5);

[0041] in, is the log-likelihood function;

[0042] Step S384, solving the log-likelihood function to obtain a solution for the scale parameter and a solution for the shape parameter;

[0043] Step S385, substituting the solution of the scale parameter and the solution of the shape parameter into the two-parameter Weibull distribution function respectively to obtain the future wind speed probability distribution.

[0044] As a further improvement of the present application, step S7, based on the speed of all the second charged particles, drives all the second charged particles to move toward all the first charged particles, and obtains the maximum first resultant force of the upper chord and the maximum second resultant force of the lower chord, including:

[0045] Step S71, based on the current photovoltaic panel and according to Coulomb's law, calculate the forces acting on the two first charged particles and the second charged particles located within the projection range of the current photovoltaic panel;

[0046] Step S72, based on the current photovoltaic panel, defining the force on the upper chord as the upper chord force, and defining the force on the lower chord as the lower chord force;

[0047] Step S73, adding the upper chord forces of all photovoltaic panels to obtain the maximum value of the first resultant force;

[0048] Step S74, adding up the forces acting on the lower chords of all photovoltaic panels to obtain the maximum value of the second resultant force.

[0049] As a further improvement of the present application, step S9, generating an excessive wind warning signal and sending it to an external receiving end, includes:

[0050] Step S91, determining whether the maximum value of the first resultant force exceeds the preset maximum tensile stress, if so, executing step S92, if not, executing step S93;

[0051] Step S92, generating an upper string overload warning signal and sending it to an external receiving end;

[0052] Step S93, generating a lower chord overload warning signal and sending it to an external receiving end;

[0053] Step S94, sending an excessive wind warning signal to an external receiving end.

[0054] In order to achieve the above objectives, this application also provides the following technical solutions:

[0055] A wind-resistant warning device for a flexible photovoltaic support, the wind-resistant warning device is applied to the wind-resistant warning method as described above, and the wind-resistant warning device comprises:

[0056] A physical model building module, used to build a physical model of the area where the flexible photovoltaic support is located in a virtual scene, and input the upper chord and the lower chord, as well as all steel beams and all photovoltaic panels into the physical model;

[0057] A photovoltaic panel equivalent charged particle creation module is used to convert each photovoltaic panel into two first charged particles with preset electric charge and the same polarity, wherein one of the two first charged particles of the same photovoltaic panel is located at the upper chord and the other is located at the lower chord, and the interaction force between all the first charged particles is shielded;

[0058] A future wind speed probability distribution acquisition module is used to obtain the future wind speed probability distribution of the area;

[0059] A wind equivalent charged particle pre-creation module is used to convert the probability value of the future wind speed probability distribution into a charge amount through a preset ratio, and define the wind speed direction of the future wind speed probability distribution as an arrangement direction;

[0060] A wind-equivalent charged particle creation module, used to arrange a plurality of columns of second charged particles in the arrangement direction, the number of columns of all second charged particles is the same as the number of all first charged particles, and the polarity of all second charged particles is the same as the polarity of all first charged particles, each column of second charged particles has a plurality of second charged particles arranged in a single linear manner, and the interaction force between all second charged particles is shielded;

[0061] A wind equivalent charged particle definition module, used to define the wind speed of the future wind speed probability distribution as the speed of all second charged particles;

[0062] A charged particle simulation module, used for driving all second charged particles to move toward all first charged particles based on the speeds of all second charged particles, and obtaining a maximum first resultant force of the upper chord and a maximum second resultant force of the lower chord;

[0063] A preset maximum tensile stress judgment module is used to judge whether the maximum value of the first combined force and the maximum value of the second combined force exceed the preset maximum tensile stress;

[0064] The wind force excessive warning signal generating module is used to generate a wind force excessive warning signal and send it to an external receiving end if one of the first maximum value of the combined force and the second maximum value of the combined force exceeds the preset maximum tensile stress.

[0065] In order to achieve the above objectives, this application also provides the following technical solutions:

[0066] An electronic device includes a processor and a memory coupled to the processor, wherein the memory stores program instructions that can be executed by the processor; when the processor executes the program instructions stored in the memory, the wind resistance warning method for the flexible photovoltaic bracket as described above is implemented.

[0067] In order to achieve the above objectives, this application also provides the following technical solutions:

[0068] A storage medium stores program instructions, which, when executed by a processor, can implement the above-mentioned wind resistance warning method for a flexible photovoltaic support.

[0069] The present application constructs a physical model of the area where the flexible photovoltaic support is located in a virtual scene, and inputs the upper chord and the lower chord, as well as all steel beams and all photovoltaic panels into the physical model; in the physical model, each photovoltaic panel is equivalent to two first charged particles with preset electric charge and the same polarity, and one of the two first charged particles of the same photovoltaic panel is located at the upper chord and the other is located at the lower chord, while shielding the interaction force between all first charged particles; obtains the future wind speed probability distribution in the area; converts the probability value of the future wind speed probability distribution into the charge through a preset ratio, and defines the wind speed direction of the future wind speed probability distribution as the arrangement direction; arranges a number of columns of second charged particles in the arrangement direction, and the number of columns of all second charged particles is the same as that of all first charged particles. The number of second charged particles is the same, and the polarity of all second charged particles is the same as that of all first charged particles, each column of second charged particles has a number of second charged particles arranged in a single linear manner, and the interaction force between all second charged particles is shielded at the same time; the wind speed of the future wind speed probability distribution is defined as the speed of all second charged particles; based on the speed of all second charged particles, all second charged particles are driven to move toward all first charged particles, and the maximum first resultant force of the upper chord and the maximum second resultant force of the lower chord are obtained; it is determined whether the maximum first resultant force and the maximum second resultant force exceed the preset maximum tensile stress respectively, and if one of the maximum first resultant force and the maximum second resultant force exceeds the preset maximum tensile stress, an excessive wind warning signal is generated and sent to an external receiving end. The present application simulates the physical mechanical process and uses Coulomb's law to simulate the tensile stress of the upper and lower chords from the wind. At the same time, the charge of the charged particles can be adjusted to further simulate the tensile stress under different wind forces. The tensile stress of the upper and lower chords under future wind forces is then predicted through the probability distribution of future wind speeds. Then, corresponding early warning signals are given according to the tensile stress under future wind forces, thereby eliminating the lag caused by manual inspections. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 A schematic diagram of the structure of a flexible photovoltaic support according to an embodiment of the wind resistance warning method of the flexible photovoltaic support of the present application;

[0071] Figure 2 A schematic diagram of the steps of an embodiment of the wind resistance warning method of the flexible photovoltaic support of the present application;

[0072] Figure 3 This is a functional module diagram of an embodiment of a wind-resistant warning device for a flexible photovoltaic support of the present application;

[0073] Figure 4 This is a schematic diagram of the structure of an embodiment of the electronic device of the present application;

[0074] Figure 5 This is a schematic diagram of the structure of an embodiment of the storage medium of the present application. DETAILED DESCRIPTION

[0075] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0076] The terms "first", "second" and "third" in this application are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first", "second" and "third" can explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of this application are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0077] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0078] like Figure 1 As shown, this embodiment provides an embodiment of a wind-resistant warning method for a flexible photovoltaic support. In this embodiment, the flexible photovoltaic support includes at least two steel beams fixed to the ground, upper and lower chords erected on adjacent steel beams and on opposite planes from each other, and a plurality of photovoltaic panels installed on the upper and lower chords.

[0079] Preferably, the upper chord and the lower chord also require two anchor cables for fixation. One end of each anchor cable passes around the steel beam frame and is anchored to the ground, and the other end of each anchor cable is fixedly connected to the upper chord or the lower chord. The upper chord, the lower chord and the anchor cable all use steel strands with a diameter of 15.2 mm. The photovoltaic panels are then installed on the upper chord and the lower chord. The two steel beam frames form one span, and 16 photovoltaic panels are generally installed in each span. The interval between the photovoltaic panels is 30 mm, and the interval between the photovoltaic panels in the middle of the span is 300 mm. A single photovoltaic panel is 2278 mm long, 1134 mm wide, 30 mm thick, and has an inclination angle of 15°.

[0080] Specifically, see Figure 2 The wind-resistant early warning method specifically comprises the following steps:

[0081] Step S1, constructing a physical model of the area where the flexible photovoltaic support is located in the virtual scene, and inputting the upper chord and the lower chord, as well as all steel beams and all photovoltaic panels into the physical model.

[0082] Preferably, the physical model can be established by the finite element software Ansys to establish the finite element model of the flexible photovoltaic bracket, specifically, the modeling can be first performed by CAD, and the established CAD model can be imported into ANSYS18.0, and the ICEMCFD module of ANSYS18.0 can be used for meshing, the FLUENT module can be used for calculation, and the CFD-POST module and TECPLOT software can be used for post-processing to form the physical model of this embodiment.

[0083] Step S2, in the physical model, each photovoltaic panel is equivalent to two first charged particles with preset electric charge and the same polarity, one of the two first charged particles of the same photovoltaic panel is located at the upper chord and the other is located at the lower chord, and the interaction force between all the first charged particles is shielded.

[0084] Preferably, the charged particles of this embodiment use Coulomb's law, which is the interaction force between two stationary point charges in a vacuum, which is proportional to the product of the charges of the two stationary point charges and inversely proportional to the square of the distance between the two stationary point charges. The direction of the force is on their connecting line, and charges of the same name repel each other, and charges of different names attract each other. Since the polarity of each charge in this embodiment is the same, there is a repulsive force between adjacent nodes, and the repulsive force can be set in proportion to the preset charge. And the nodes in this embodiment are virtual points fitted by the software, which can be equivalent to "vacuum".

[0085] Step S3, obtaining the future wind speed probability distribution in the area.

[0086] Preferably, wind speed probability distribution is a statistical method to describe the law of wind speed change. It simulates the random change of wind speed through a probability model to help us understand and predict the changing trend of wind speed. As a random variable, the change of wind speed is difficult to observe and predict directly, but through probability distribution, we can better understand and analyze the statistical characteristics of wind speed. The study of wind speed probability distribution has important applications in many fields, including climate statistics, economic construction, and national defense construction. Through the analysis of wind speed data, researchers can use different probability distribution functions to fit wind speed data, such as Weibull distribution, Extreme Value distribution, Generalized Extreme Value distribution, Rayleigh distribution, tlocation-scale distribution, and Burr type Ⅻ distribution. These distribution functions can help us better understand and predict the change of wind speed and provide a basis for engineering design and climate prediction. In addition, the study of wind speed probability distribution also involves parameter estimation and confidence calculation, which helps us describe and predict the change of wind speed more accurately and provide a scientific basis for various applications.

[0087] Step S4, converting the probability value of the future wind speed probability distribution into a charge amount according to a preset ratio, and defining the wind speed direction of the future wind speed probability distribution as an arrangement direction.

[0088] Preferably, since the probability value is between [0, 1], a coefficient whose integer multiple is a preset ratio can be defined based on the charge amount of an elementary charge e, such as 10e, 100e, 1000e, etc.

[0089] For example, assuming that the probability value of a certain wind speed is 0.2, the probability value 0.2 can be converted into a charge amount 2e through the above coefficient by a coefficient of 10e.

[0090] Preferably, the elementary charge is also called the basic charge or elementary charge, which is the smallest unit of charge and is represented by the symbol e. The value of the elementary charge is approximately 1.6021766208×10 -19 coulomb.

[0091] Step S5, arranging several columns of second charged particles in the arrangement direction, the number of columns of all second charged particles is the same as the number of all first charged particles, and the polarity of all second charged particles is the same as the polarity of all first charged particles, each column of second charged particles has several single linearly arranged second charged particles, and at the same time shielding the interaction force between all second charged particles.

[0092] Preferably, since the wind is continuous, the number of second charged particles in each column is not limited and is theoretically infinite. According to Coulomb's law, the interaction force generated by second charged particles that are too far away is not sufficient to have an impact. During the software iteration process, the second charged particles that have crossed the physical model can be deleted and supplemented to the end of the queue that has not crossed the physical model based on the number of deletions to prevent software jams.

[0093] Step S6: define the wind speed of the future wind speed probability distribution as the speed of all second charged particles.

[0094] It is worth noting that speed is a vector unit, which includes rate and direction, and the same is true for wind speed.

[0095] Step S7, driving all the second charged particles to move toward all the first charged particles based on the speeds of all the second charged particles, and obtaining the maximum first resultant force of the upper chord and the maximum second resultant force of the lower chord.

[0096] Step S8, respectively determining whether the first maximum value of the combined force and the second maximum value of the combined force exceed the preset maximum tensile stress; if one of the first maximum value of the combined force and the second maximum value of the combined force exceeds the preset maximum tensile stress, executing step S9.

[0097] Preferably, in actual use, both the upper and lower chords need to obtain initial stiffness by applying pretension, which can offset the load of the upper structure and achieve a large span by controlling the cable force and the overall deformation of the structure. In prestressed steel structures, the range of tension control stress is obtained through analysis. This range is the existing technology in the industry, and the specific value needs to be formulated according to the actual project. This embodiment no longer limits it to a fixed value.

[0098] The preset maximum tensile stress is the maximum value of the above value range. Since this embodiment uses Coulomb's law, it is necessary to convert the preset maximum tensile stress into a force that meets the Coulomb force level at a certain ratio, and compare the resultant force received by the first charged particle with the converted force.

[0099] For example, the charge of a first charged particle is 10e, and the weight of a 2278mm×1134mm×30mm photovoltaic panel is 28kg, that is, 274.4N. Since a photovoltaic panel is equivalent to two first charged particles, the ratio is 20e:274.4. Here, e needs to be changed to dimensionless, using only 1.6021766208×10 -19 At this time, divide the preset maximum tensile stress by 274.4 and then multiply by 20e to get the converted force.

[0100] Step S9, generating an excessive wind warning signal and sending it to an external receiving end.

[0101] Furthermore, step S3, obtaining the future wind speed probability distribution in the area, includes:

[0102] Step S31, obtaining a number of historical wind speed data in the area.

[0103] Step S32, normalize all historical wind speed data and integrate them into a normalized data set.

[0104] Preferably, this embodiment prefers the normalization method of zero-mean normalization (Z-score normalization), which gives the mean and standard deviation of the original data to standardize the data, and the processed data conforms to the standard normal distribution, that is, the mean is 0 and the standard deviation is 1. For the normalization method, this embodiment can also use batch normalization. Compared with simple normalization, in the previous neural network training, only the input layer data is normalized, but not in the middle layer. Although the data set of the input node is normalized, the data distribution of the input data after matrix multiplication is likely to change greatly, and as the number of hidden layer network layers continues to deepen, the change in data distribution will become greater and greater. Therefore, the normalization processing performed by batch normalization in the middle layer of the neural network makes the training effect better.

[0105] Step S33, dividing the normalized data set into a training set and a validation set according to a preset ratio.

[0106] Preferably, the preset ratio is 8:2, so that the image data is divided into a training set and a sample set in a ratio of 8:2.

[0107] Preferably, in actual application, a certain proportion of validation sets are required to verify the accuracy of the model, that is, verification is required after training is completed, and the sample set prediction is started only after the verification is successful. Usually, the image data is divided into training set, validation set, and sample set in a ratio of 70%:15%:15%, that is, 70% of the data is the training set, 15% of the data is the validation set, and 15% of the data is the sample set.

[0108] Step S34, defining the topological relationship of the neural network model, the topological relationship includes an input layer, a hidden layer, and an output layer that are sequentially signal-connected.

[0109] Step S35, input the training set to the input layer, and iterate through the neural network model, and obtain the root mean square error between the verification set and the current training result based on each iteration.

[0110] Step S36, after the iteration is completed, obtain the minimum value of all root mean square errors, and obtain the training result corresponding to the minimum value as the prediction model.

[0111] Step S37, predicting future wind speed data for a preset number of steps through a prediction model.

[0112] Step S38, substituting the future wind speed data into the two-parameter Weibull distribution function and solving the parameters of the two-parameter Weibull distribution function to obtain the future wind speed probability distribution.

[0113] Preferably, the training model training a neural network usually requires providing a large amount of data, namely a data set; the data set is generally divided into three categories, namely the above-mentioned training set (training set), validation set (validation set) and test set (test set).

[0114] Among them, one epoch is the process of training once with all the samples in the training set. The so-called training once refers to one forward pass and one back pass. When the number of samples in an epoch (i.e., training set) is too large, training once may consume too much time, and it is not necessary to use all the data in the training set for each training. In this case, the entire training set needs to be divided into multiple small blocks, that is, divided into multiple batches for training. An epoch consists of one or more batches, where a batch is a part of the training set. Each training process only uses a part of the data, i.e., a batch. The process of training a batch is an iteration.

[0115] Preferably, the neural network training specifically includes a perceptron, which is composed of two layers of neurons. The input layer receives external input signals and transmits them to the output layer. The output layer is MP neurons, and the step function is .

[0116] Preferably, For the input nodes, given a training data set, the weight ( =1,2,...,n) and training bias It can be obtained through learning, It can be understood as the weight corresponding to a fixed value of -1,0. .

[0117] It should be noted that the step function here has no interchangeable symbolic meaning with other formulas in the embodiment. This step function is only used for principle explanation and does not participate in the calculation of other formulas.

[0118] Preferably, in this embodiment, the number of neural network training times can be set to 1000 times.

[0119] Preferably, the learning rate from the 1st to the 500th epoch can be set to 0.01, the learning rate from the 501st to the 750th epoch can be set to 0.001, and the learning rate from the 751st to the 1000th epoch can be set to 0.0001.

[0120] It can be understood that the neural network training of this embodiment mainly includes the following ideas:

[0121] ① Initialize the weights and bias items in the network.

[0122] Initializing parameter values ​​(output unit weights, bias terms and hidden unit weights, bias terms are all model parameters) is to activate forward propagation, obtain the output value of each layer element, and then obtain the value of the loss function.

[0123] ②Activate forward propagation to obtain the output value of each layer and the expected value of the loss function of each layer.

[0124] ③According to the loss function, calculate the error term of the output unit and the error term of the hidden unit.

[0125] Calculate various errors, calculate the gradient of the parameters with respect to the loss function, or calculate partial derivatives according to the chain rule of calculus. For partial derivatives of vectors or matrices in a composite function, the partial derivative of the function inside the composite function is always multiplied on the left; for partial derivatives of scalars in a composite function, the partial derivative of the function inside the composite function can be multiplied on the left or on the right.

[0126] ④Update the weights and bias items in the neural network.

[0127] ⑤ Repeat ②~④ until the loss function is less than the preset bias or the number of iterations is used up, and the output parameters at this time are the current optimal parameters.

[0128] Furthermore, the neural network model is represented by formula (1):

[0129] (1).

[0130] in, To preset the neural network model; is the input layer and , The input layer input nodes, each input node corresponds to a training set, The input layer The first input node to the hidden layer The weights of the input nodes; is connected to the hidden layer The bias of the input node; is the transfer function, and The numbers in the brackets of the superscripts are the number of layers.

[0131] Preferably, the numbers in the brackets of the symbol superscripts in formula (1) of this embodiment are the number of layers, for example, superscript (1) is the first layer, that is, the input layer, and superscript (1, 2) is from the first layer to the second layer, that is, the input layer to the hidden layer.

[0132] Furthermore, the root mean square error is expressed by formula (2):

[0133] (2).

[0134] in, is the root mean square error, is the number of all data in the training set, one data corresponds to one input node, For the The true value of the training set, For the The training results after the training of the training set is completed.

[0135] Further, in step S38, the future wind speed data is substituted into the two-parameter Weibull distribution function and the parameters of the two-parameter Weibull distribution function are solved to obtain the future wind speed probability distribution, including:

[0136] Step S381, define the two-parameter Weibull distribution function according to formula (3):

[0137] (3).

[0138] in, is the two-parameter Weibull distribution function, and ; is the scale parameter of the Weibull distribution; is the shape parameter of the Weibull distribution; For future wind speed data.

[0139] Step S382, define the probability density function of the two-parameter Weibull distribution function according to formula (4):

[0140] (4).

[0141] in, is the probability density function.

[0142] Step S383, define the log-likelihood function of the scale parameter and the shape parameter according to equation (5):

[0143] (5).

[0144] in, is the log-likelihood function.

[0145] Step S384, solving the log-likelihood function to obtain solutions for the scale parameter and the shape parameter.

[0146] Preferably, this embodiment provides a process for solving a log-likelihood function:

[0147] set up: as well as ,but:

[0148] .

[0149] Modify the above formula to get the matrix equation:

[0150] .

[0151] The above matrix equation is iterated by Jacobi iteration method until the spectral radius of the matrix equation is When , it is judged to be convergent.

[0152] After convergence, the scale parameter and shape parameter of the Weibull distribution can be obtained.

[0153] Step S385, substitute the solution of the scale parameter and the solution of the shape parameter into the two-parameter Weibull distribution function respectively to obtain the probability distribution of future wind speed.

[0154] Further, step S7, based on the speed of all the second charged particles, drives all the second charged particles to move toward all the first charged particles, and obtains the maximum first resultant force of the upper chord and the maximum second resultant force of the lower chord, including:

[0155] Step S71 , based on the current photovoltaic panel and according to Coulomb's law, calculate the forces acting between the two first charged particles and the second charged particles located within the projection range of the current photovoltaic panel.

[0156] Step S72, based on the current photovoltaic panel, the force on the upper chord is defined as the upper chord force, and the force on the lower chord is defined as the lower chord force.

[0157] Step S73, adding up the upper chord forces of all photovoltaic panels to obtain a first maximum resultant force.

[0158] Step S74, adding the forces acting on the lower chords of all photovoltaic panels to obtain the second maximum resultant force.

[0159] Furthermore, step S9, generating an excessive wind warning signal and sending it to an external receiving end, includes:

[0160] Step S91, determine whether the maximum value of the first resultant force exceeds the preset maximum tensile stress. If so, execute step S92; if not, execute step S93.

[0161] Step S92, generating an upper string overload warning signal and sending it to an external receiving end.

[0162] Step S93, generating a lower chord overload warning signal and sending it to an external receiving end.

[0163] Step S94, sending an excessive wind warning signal to an external receiving end.

[0164] In this embodiment, a physical model of the area where the flexible photovoltaic support is located is constructed in a virtual scene, and the upper chord and the lower chord, as well as all steel beams and all photovoltaic panels are input into the physical model; in the physical model, each photovoltaic panel is equivalent to two first charged particles with preset electric charge and the same polarity, and one of the two first charged particles of the same photovoltaic panel is located at the upper chord and the other is located at the lower chord, while shielding the interaction force between all first charged particles; the future wind speed probability distribution of the area is obtained; the probability value of the future wind speed probability distribution is converted into the electric charge through a preset ratio, and the wind speed direction of the future wind speed probability distribution is defined as the arrangement direction; a plurality of columns of second charged particles are arranged in the arrangement direction, and the number of columns of all second charged particles is the same as that of all first charged particles. The number of second charged particles is the same, and the polarity of all second charged particles is the same as that of all first charged particles, each column of second charged particles has a number of second charged particles arranged in a single linear manner, and the interaction force between all second charged particles is shielded at the same time; the wind speed of the future wind speed probability distribution is defined as the speed of all second charged particles; based on the speed of all second charged particles, all second charged particles are driven to move toward all first charged particles, and the maximum first resultant force of the upper chord and the maximum second resultant force of the lower chord are obtained; it is determined whether the maximum first resultant force and the maximum second resultant force exceed the preset maximum tensile stress respectively, and if one of the maximum first resultant force and the maximum second resultant force exceeds the preset maximum tensile stress, an excessive wind warning signal is generated and sent to an external receiving end. This embodiment simulates the physical mechanical process and uses Coulomb's law to simulate the tensile stress of the upper and lower chords from the wind. At the same time, the charge of the charged particles can be adjusted to further simulate the tensile stress under different wind forces. The tensile stress of the upper and lower chords under future wind forces is then predicted through the probability distribution of future wind speeds. Then, corresponding early warning signals are given according to the tensile stress under future wind forces, thereby eliminating the lag caused by manual inspections.

[0165] like Figure 2 As shown, this embodiment provides an embodiment of a wind-resistant warning device for a flexible photovoltaic support. In this embodiment, the wind-resistant warning device is applied to the wind-resistant warning method in the above-mentioned embodiment.

[0166] Specifically, the wind-resistant warning device includes a physical model construction module 1, a photovoltaic panel equivalent charged particle creation module 2, a future wind speed probability distribution acquisition module 3, a wind equivalent charged particle pre-creation module 4, a wind equivalent charged particle creation module 5, a wind equivalent charged particle definition module 6, a charged particle simulation module 7, a preset maximum tensile stress judgment module 8, and an excessive wind warning signal generation module 9, which are electrically connected in sequence.

[0167] Among them, the physical model construction module 1 is used to construct a physical model of the area where the flexible photovoltaic bracket is located in the virtual scene, and input the upper and lower chords, as well as all steel beams and all photovoltaic panels into the physical model; the photovoltaic panel equivalent charged particle creation module 2 is used to equate each photovoltaic panel to two first charged particles with preset power and the same polarity, and one of the two first charged particles of the same photovoltaic panel is located at the upper chord and the other is located at the lower chord, while shielding the interaction force between all first charged particles; the future wind speed probability distribution acquisition module 3 is used to obtain the future wind speed probability distribution in the area; the wind equivalent charged particle pre-creation module 4 is used to convert the probability value of the future wind speed probability distribution into the charge through a preset ratio, and define the wind speed direction of the future wind speed probability distribution as the arrangement direction; the wind equivalent charged particle creation module 5 is used to arrange a number of columns of second charged particles in the arrangement direction, and the number of columns of all second charged particles is the same as that of all first charged particles. The number of first charged particles is the same, and the polarity of all second charged particles is the same as that of all first charged particles, and each column of second charged particles has a number of second charged particles arranged in a single linear manner, while shielding the interaction force between all second charged particles; the wind equivalent charged particle definition module 6 is used to define the wind speed of the future wind speed probability distribution as the speed of all second charged particles; the charged particle simulation module 7 is used to drive all second charged particles to move toward all first charged particles based on the speed of all second charged particles, and obtain the maximum first resultant force of the upper chord and the maximum second resultant force of the lower chord; the preset maximum tensile stress judgment module 8 is used to respectively judge whether the maximum first resultant force and the maximum second resultant force exceed the preset maximum tensile stress; the excessive wind warning signal generation module 9 is used to generate an excessive wind warning signal and send it to an external receiving end if one of the maximum first resultant force and the maximum second resultant force exceeds the preset maximum tensile stress.

[0168] Furthermore, the future wind speed probability distribution acquisition module 3 specifically includes a first future wind speed probability distribution acquisition submodule, a second future wind speed probability distribution acquisition submodule, a third future wind speed probability distribution acquisition submodule, a fourth future wind speed probability distribution acquisition submodule, a fifth future wind speed probability distribution acquisition submodule, a sixth future wind speed probability distribution acquisition submodule, a seventh future wind speed probability distribution acquisition submodule, and an eighth future wind speed probability distribution acquisition submodule, which are electrically connected in sequence; the first future wind speed probability distribution acquisition submodule is electrically connected to the photovoltaic panel equivalent charged particle creation module 2, and the eighth future wind speed probability distribution acquisition submodule is electrically connected to the wind equivalent charged particle pre-creation module 4.

[0169] Among them, the first future wind speed probability distribution acquisition submodule is used to obtain several historical wind speed data in the area; the second future wind speed probability distribution acquisition submodule is used to normalize all historical wind speed data and integrate them into a normalized data set; the third future wind speed probability distribution acquisition submodule is used to divide the normalized data set into a training set and a verification set according to a preset ratio; the fourth future wind speed probability distribution acquisition submodule is used to define the topological relationship of the neural network model, and the topological relationship includes an input layer, a hidden layer, and an output layer that are sequentially connected by signals; the fifth future wind speed probability distribution acquisition submodule is used to input the training set into the input layer, And iterate through the neural network model, and obtain the root mean square error between the verification set and the current training result based on each iteration; the sixth future wind speed probability distribution acquisition submodule is used to obtain the minimum value of all root mean square errors after the iteration is completed, and obtain the training result corresponding to the minimum value as the prediction model; the seventh future wind speed probability distribution acquisition submodule is used to predict the future wind speed data of a preset number of steps through the prediction model; the eighth future wind speed probability distribution acquisition submodule is used to substitute the future wind speed data into the two-parameter Weibull distribution function and solve the parameters of the two-parameter Weibull distribution function to obtain the future wind speed probability distribution.

[0170] Furthermore, the fourth future wind speed probability distribution acquisition submodule is equipped with a neural network model represented by formula (1):

[0171] (1).

[0172] in, To preset the neural network model; is the input layer and , The input layer input nodes, each input node corresponds to a training set, The input layer The first input node to the hidden layer The weights of the input nodes; is connected to the hidden layer The bias of the input node; is the transfer function, and The numbers in the brackets of the superscripts are the number of layers.

[0173] Furthermore, the fifth future wind speed probability distribution acquisition submodule is equipped with a root mean square error represented by formula (2):

[0174] (2).

[0175] in, is the root mean square error, is the number of all data in the training set, one data corresponds to one input node, For the The true value of the training set, For the The training results after the training of the training set is completed.

[0176] Furthermore, the eighth future wind speed probability distribution acquisition submodule specifically includes a first future wind speed probability distribution acquisition unit, a second future wind speed probability distribution acquisition unit, a third future wind speed probability distribution acquisition unit, a fourth future wind speed probability distribution acquisition unit, and a fifth future wind speed probability distribution acquisition unit, which are electrically connected in sequence; the first future wind speed probability distribution acquisition unit is electrically connected to the seventh future wind speed probability distribution acquisition submodule, and the fifth future wind speed probability distribution acquisition unit is electrically connected to the wind equivalent charged particle pre-creation module 4.

[0177] The first future wind speed probability distribution acquisition unit is used to define a two-parameter Weibull distribution function according to formula (3):

[0178] (3).

[0179] in, is the two-parameter Weibull distribution function, and ; is the scale parameter of the Weibull distribution; is the shape parameter of the Weibull distribution; For future wind speed data.

[0180] The second future wind speed probability distribution acquisition unit is used to define the probability density function of the two-parameter Weibull distribution function according to formula (4):

[0181] (4).

[0182] in, is the probability density function.

[0183] The third future wind speed probability distribution acquisition unit is used to define the log-likelihood function of the scale parameter and the shape parameter according to formula (5):

[0184] (5).

[0185] in, is the log-likelihood function.

[0186] The fourth future wind speed probability distribution acquisition unit is used to solve the log-likelihood function to obtain the solution of the scale parameter and the solution of the shape parameter.

[0187] The fifth future wind speed probability distribution acquisition unit is used to substitute the solution of the scale parameter and the solution of the shape parameter into the two-parameter Weibull distribution function respectively to obtain the future wind speed probability distribution.

[0188] Furthermore, the charged particle simulation module 7 specifically includes a first charged particle simulation module, a second charged particle simulation module, a third charged particle simulation module, and a fourth charged particle simulation module that are electrically connected in sequence; the first charged particle simulation module is electrically connected to the wind equivalent charged particle definition module 6, and the fourth charged particle simulation module is electrically connected to the preset maximum tensile stress judgment module 8.

[0189] Among them, the first charged particle simulation module is used to calculate the forces between the two first charged particles and the second charged particles located within the projection range of the current photovoltaic panel according to Coulomb's law based on the current photovoltaic panel; the second charged particle simulation module is used to define the force located on the upper chord as the upper chord force and the force located on the lower chord as the lower chord force based on the current photovoltaic panel; the third charged particle simulation module is used to add the upper chord forces of all photovoltaic panels to obtain the maximum value of the first resultant force; the fourth charged particle simulation module is used to add the lower chord forces of all photovoltaic panels to obtain the maximum value of the second resultant force.

[0190] Furthermore, the excessive wind warning signal generation module 9 specifically includes a first excessive wind warning signal generation submodule, a second excessive wind warning signal generation submodule, a third excessive wind warning signal generation submodule, and a fourth excessive wind warning signal generation submodule, which are electrically connected in sequence; the first excessive wind warning signal generation submodule is electrically connected to the preset maximum tensile stress judgment module 8.

[0191] Among them, the first wind-force excessive warning signal generation submodule is used to determine whether the maximum value of the first resultant force exceeds the preset maximum tensile stress; the second wind-force excessive warning signal generation submodule is used to generate an upper chord overload warning signal if the maximum value of the first resultant force exceeds the preset maximum tensile stress, and send it to the external receiving end; the third wind-force excessive warning signal generation submodule is used to generate a lower chord overload warning signal and send it to the external receiving end if the maximum value of the first resultant force does not exceed the preset maximum tensile stress; the fourth wind-force excessive warning signal generation submodule is used to send the wind-force excessive warning signal to the external receiving end.

[0192] It should be noted that this embodiment is a functional module embodiment based on the above method embodiment. The preferred, expanded, limited and exemplary parts of this embodiment can refer to the above embodiment and will not be described in detail in this embodiment.

[0193] In this embodiment, a physical model of the area where the flexible photovoltaic support is located is constructed in a virtual scene, and the upper chord and the lower chord, as well as all steel beams and all photovoltaic panels are input into the physical model; in the physical model, each photovoltaic panel is equivalent to two first charged particles with preset electric charge and the same polarity, and one of the two first charged particles of the same photovoltaic panel is located at the upper chord and the other is located at the lower chord, while shielding the interaction force between all first charged particles; the future wind speed probability distribution of the area is obtained; the probability value of the future wind speed probability distribution is converted into the electric charge through a preset ratio, and the wind speed direction of the future wind speed probability distribution is defined as the arrangement direction; a plurality of columns of second charged particles are arranged in the arrangement direction, and the number of columns of all second charged particles is the same as that of all first charged particles. The number of second charged particles is the same, and the polarity of all second charged particles is the same as that of all first charged particles, each column of second charged particles has a number of second charged particles arranged in a single linear manner, and the interaction force between all second charged particles is shielded at the same time; the wind speed of the future wind speed probability distribution is defined as the speed of all second charged particles; based on the speed of all second charged particles, all second charged particles are driven to move toward all first charged particles, and the maximum first resultant force of the upper chord and the maximum second resultant force of the lower chord are obtained; it is determined whether the maximum first resultant force and the maximum second resultant force exceed the preset maximum tensile stress respectively, and if one of the maximum first resultant force and the maximum second resultant force exceeds the preset maximum tensile stress, an excessive wind warning signal is generated and sent to an external receiving end. This embodiment simulates the physical mechanical process and uses Coulomb's law to simulate the tensile stress of the upper and lower chords from the wind. At the same time, the charge of the charged particles can be adjusted to further simulate the tensile stress under different wind forces. The tensile stress of the upper and lower chords under future wind forces is then predicted through the probability distribution of future wind speeds. Then, corresponding early warning signals are given according to the tensile stress under future wind forces, thereby eliminating the lag caused by manual inspections.

[0194] like Figure 3 As shown, this embodiment provides an embodiment of an electronic device. In this embodiment, the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101 .

[0195] The memory 102 stores program instructions for implementing the wind resistance warning method for the flexible photovoltaic support of any of the above embodiments.

[0196] The processor 101 is used to execute the program instructions stored in the memory 102 to perform wind resistance warning for the flexible photovoltaic support.

[0197] The processor 101 may also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip having data processing capabilities. The processor 101 may also be a general-purpose processor, a digital data processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0198] Further, Figure 4 The schematic diagram of the structure of the storage medium of an embodiment of the present application is that the storage medium 11 of the embodiment of the present application stores program instructions 111 that can implement all the above methods, wherein the program instructions 111 can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0199] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0200] In addition, each functional unit in each embodiment of the present 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. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the specification and drawings of this application, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present application.

[0201] The specific implementation methods of the present application are described in detail above, but they are only examples, and the present application is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the present application is also within the scope of the present application, and therefore, the equalization, modification, and improvement made without departing from the spirit and principle of the present application should be included in the scope of the present application.

Claims

1. A wind warning method for a flexible photovoltaic support, wherein the flexible photovoltaic support comprises at least two steel beams fixed to the ground, upper and lower chords erected on adjacent steel beams and in different planes from each other, and a plurality of photovoltaic panels installed on the upper and lower chords, characterized in that: The wind resistance early warning method comprises: Step S1, constructing a physical model of the area where the flexible photovoltaic support is located in a virtual scene, and inputting the upper chord and the lower chord, as well as all steel beams and all photovoltaic panels into the physical model; Step S2, in the physical model, each photovoltaic panel is equivalent to two first charged particles with preset electric quantity and the same polarity, one of the two first charged particles of the same photovoltaic panel is located at the upper chord and the other is located at the lower chord, and the interaction force between all the first charged particles is shielded; Step S3, obtaining the future wind speed probability distribution of the area; Step S4, converting the probability value of the future wind speed probability distribution into a charge amount according to a preset ratio, and defining the wind speed direction of the future wind speed probability distribution as an arrangement direction; Step S5, arranging a plurality of columns of second charged particles in the arrangement direction, the number of columns of all second charged particles is the same as the number of all first charged particles, and the polarity of all second charged particles is the same as the polarity of all first charged particles, each column of second charged particles has a plurality of second charged particles arranged in a single linear manner, and at the same time, shielding the interaction force between all second charged particles; Step S6, defining the wind speed of the future wind speed probability distribution as the speed of all second charged particles; Step S7, driving all the second charged particles to move toward all the first charged particles based on the speeds of all the second charged particles, and obtaining the maximum first resultant force of the upper chord and the maximum second resultant force of the lower chord; Step S8, respectively determining whether the first maximum value of the combined force and the second maximum value of the combined force exceed a preset maximum tensile stress, and if one of the first maximum value of the combined force and the second maximum value of the combined force exceeds the preset maximum tensile stress, executing step S9; Step S9, generating an excessive wind warning signal and sending it to an external receiving end; Step S3, obtaining the future wind speed probability distribution of the area, including: Step S31, obtaining a number of historical wind speed data of the area; Step S32, normalizing all historical wind speed data and integrating them into a normalized data set; Step S33, dividing the normalized data set into a training set and a validation set according to a preset ratio; Step S34, defining a topological relationship of the neural network model, wherein the topological relationship includes an input layer, a hidden layer, and an output layer that are sequentially signal-connected; Step S35, inputting the training set into the input layer, and iterating through the neural network model, obtaining a root mean square error between the validation set and the current training result based on each iteration; Step S36, after the iteration is completed, obtaining the minimum value of all root mean square errors, and obtaining the training result corresponding to the minimum value as the prediction model; Step S37, predicting future wind speed data of a preset number of steps by using the prediction model; Step S38, substituting the future wind speed data into a two-parameter Weibull distribution function and solving the parameters of the two-parameter Weibull distribution function to obtain the future wind speed probability distribution; The neural network model is represented by formula (1): （1）； in, is the neural network model; is the input layer and , is the first input nodes, each input node corresponds to a training set, is the first The first input node to the hidden layer The weights of the input nodes; is the first The bias of the input node; is the transfer function, and The numbers in the brackets of the superscripts are the number of layers.

2. The wind-resistance early warning method according to claim 1, characterized in that: The root mean square error is represented by formula (2): （2）； in, is the root mean square error, is the number of all data in the training set, one data corresponds to one input node, For the The true value of the training set, For the The training results after the training of the training set is completed.

3. The wind-resistance early warning method according to claim 1, characterized in that: Step S38, substituting the future wind speed data into a two-parameter Weibull distribution function and solving the parameters of the two-parameter Weibull distribution function to obtain the future wind speed probability distribution, including: Step S381, defining the two-parameter Weibull distribution function according to formula (3): （3）； in, is the two-parameter Weibull distribution function, and ; is the scale parameter of the Weibull distribution; is the shape parameter of the Weibull distribution; is the future wind speed data; Step S382, defining the probability density function of the two-parameter Weibull distribution function according to formula (4): （4）； in, is the probability density function; Step S383: define the log-likelihood function of the scale parameter and the shape parameter according to equation (5): （5）； in, is the log-likelihood function; Step S384, solving the log-likelihood function to obtain a solution for the scale parameter and a solution for the shape parameter; Step S385, substituting the solution of the scale parameter and the solution of the shape parameter into the two-parameter Weibull distribution function respectively to obtain the future wind speed probability distribution.

4. The wind-resistance early warning method according to claim 1, characterized in that: Step S7, driving all the second charged particles to move toward all the first charged particles based on the speeds of all the second charged particles, and obtaining the maximum first resultant force of the upper chord and the maximum second resultant force of the lower chord, comprising: Step S71, based on the current photovoltaic panel and according to Coulomb's law, calculate the forces acting on the two first charged particles and the second charged particles located within the projection range of the current photovoltaic panel; Step S72, based on the current photovoltaic panel, defining the force on the upper chord as the upper chord force, and defining the force on the lower chord as the lower chord force; Step S73, adding the upper chord forces of all photovoltaic panels to obtain the maximum value of the first resultant force; Step S74, adding up the forces acting on the lower chords of all photovoltaic panels to obtain the maximum value of the second resultant force.

5. The wind-resistance early warning method according to claim 1, characterized in that: Step S9, generating an excessive wind warning signal and sending it to an external receiving end, includes: Step S91, determining whether the maximum value of the first resultant force exceeds the preset maximum tensile stress, if so, executing step S92, if not, executing step S93; Step S92, generating an upper string overload warning signal and sending it to an external receiving end; Step S93, generating a lower chord overload warning signal and sending it to an external receiving end; Step S94, sending an excessive wind warning signal to an external receiving end.

6. A wind-resistant warning device for a flexible photovoltaic support, the wind-resistant warning device being applied to the wind-resistant warning method according to any one of claims 1 to 5, characterized in that: The wind-resistant early warning device comprises: A physical model building module, used to build a physical model of the area where the flexible photovoltaic support is located in a virtual scene, and input the upper chord and the lower chord, as well as all steel beams and all photovoltaic panels into the physical model; A photovoltaic panel equivalent charged particle creation module is used to convert each photovoltaic panel into two first charged particles with preset electric charge and the same polarity, wherein one of the two first charged particles of the same photovoltaic panel is located at the upper chord and the other is located at the lower chord, and the interaction force between all the first charged particles is shielded; A future wind speed probability distribution acquisition module is used to obtain the future wind speed probability distribution of the area; A wind equivalent charged particle pre-creation module is used to convert the probability value of the future wind speed probability distribution into a charge amount through a preset ratio, and define the wind speed direction of the future wind speed probability distribution as an arrangement direction; A wind-equivalent charged particle creation module, used to arrange a plurality of columns of second charged particles in the arrangement direction, the number of columns of all second charged particles is the same as the number of all first charged particles, and the polarity of all second charged particles is the same as the polarity of all first charged particles, each column of second charged particles has a plurality of second charged particles arranged in a single linear manner, and the interaction force between all second charged particles is shielded; A wind equivalent charged particle definition module, used to define the wind speed of the future wind speed probability distribution as the speed of all second charged particles; A charged particle simulation module, used for driving all second charged particles to move toward all first charged particles based on the speeds of all second charged particles, and obtaining a maximum first resultant force of the upper chord and a maximum second resultant force of the lower chord; A preset maximum tensile stress judgment module is used to judge whether the maximum value of the first combined force and the maximum value of the second combined force exceed the preset maximum tensile stress; The wind force excessive warning signal generating module is used to generate a wind force excessive warning signal and send it to an external receiving end if one of the first maximum value of the combined force and the second maximum value of the combined force exceeds the preset maximum tensile stress.

7. An electronic device, characterized in that: It includes a processor and a memory coupled to the processor, wherein the memory stores program instructions that can be executed by the processor; when the processor executes the program instructions stored in the memory, the wind resistance warning method as described in any one of claims 1 to 5 is implemented.

8. A storage medium, characterized in that: The storage medium stores program instructions, and when the program instructions are executed by the processor, the wind resistance warning method according to any one of claims 1 to 5 can be implemented.

Images