A photovoltaic support design method and device, electronic equipment and storage medium

Abstract

The application provides a photovoltaic support design method and device, electronic equipment and storage medium, and belongs to the technical field of photovoltaic power generation. The method comprises the following steps: acquiring historical environmental load data monitored by each region of a photovoltaic field area; if the data is wind load data, classifying each region based on the wind load data to obtain a plurality of target regions; for each target region, performing a photovoltaic support design operation, which comprises the following steps: calling a target parameter set matched with the wind load data from a photovoltaic support parameter library to perform simulation analysis and obtain a first stress threshold set of a key stress position of the photovoltaic support; modifying the data in the first stress threshold set based on a dynamic effect compensation coefficient to obtain a second stress threshold set; optimizing the parameters in the target parameter set based on the second stress threshold set to determine an optimal design parameter set of the photovoltaic support in the target region, and performing the photovoltaic support design operation based on the optimal design parameter set. The application can improve the reliability and adaptability of photovoltaic support design.

Description

Technical Field

[0001] This application belongs to the field of photovoltaic power generation technology, specifically a photovoltaic support design method and device, electronic equipment, and storage medium. Background Technology

[0002] With the increasing global demand for clean energy, photovoltaic (PV) power generation has become a widely adopted sustainable energy solution. As a key structure supporting PV modules, the rationality and reliability of PV support structures directly affect the performance, safety, and lifespan of PV power generation systems. In practical applications, PV power plants operate in complex and diverse environments, and environmental loads significantly impact PV support structures. The vast differences in meteorological conditions across regions mean that if the PV support structure design fails to adequately consider these environmental loads, it may lead to deformation and damage of the support structure, resulting in PV module failure, reduced power generation efficiency, and even safety accidents.

[0003] Traditional photovoltaic (PV) support design methods often rely on experience and simplified calculation models, which do not take into account environmental loads in a comprehensive and accurate manner, resulting in many hidden dangers in the actual operation of the designed PV supports.

[0004] Relevant patent documents retrieved: This document, published in China (CN112733287A) on April 30, 2021, discloses a zoning method, design method, and photovoltaic support array for photovoltaic (PV) arrays. The technical solution includes obtaining extreme weather information of the PV array's location, calculating the dynamic amplification factor of the PV support's load-bearing components based on this information, calculating the total wind load by combining this with static wind load, and calculating the stress ratio while considering snow load and self-weight. Based on this stress ratio, the PV support is designed with differentiated layouts in inner and outer regions, thereby addressing the cost issue of the entire PV array design.

[0005] The prior art represented by the aforementioned documents has at least the following unresolved technical problems or defects: While the aforementioned patent documents involve the design and zoning of photovoltaic supports by combining extreme weather information with dynamic amplification coefficients, their technical concepts and actual scenarios for dealing with complex dynamic environments are fundamentally different from those of this invention.

[0006] Secondly, the specific design methods in the aforementioned patent documents rely too heavily on initial manual experience in selection, and for the different areas that are divided, the cost reduction design is only based on reducing the performance level of the load-bearing components in the inner area, which results in the photovoltaic brackets still having potential failure risks when facing real and variable future environmental loads.

[0007] Therefore, a more scientific and precise method for designing photovoltaic support systems is urgently needed. Summary of the Invention

[0008] In order to solve at least one of the above-mentioned technical problems in the prior art, the present invention provides a photovoltaic bracket design method and device, electronic device, and storage medium.

[0009] To achieve the above objectives, the technical solution of the present invention is as follows: In a first aspect, the present invention provides a photovoltaic support design method, comprising: acquiring historical environmental load data of each area monitored in the photovoltaic field, wherein the historical environmental load data is wind load data or snow load data; If the historical environmental load data is wind load data, then the regions are classified based on the historical environmental load data monitored in each region to obtain multiple target regions, and photovoltaic bracket design operations are performed on multiple target regions. If the historical environmental load data is snow load data, then the photovoltaic bracket design operation will be performed based on the preset photovoltaic bracket design specifications; For each target area, the photovoltaic support design process includes: Based on historical environmental load data of the target area, the matching target parameter set is called from the photovoltaic support parameter library to perform simulation analysis and obtain the first stress threshold set of key stress parts of the photovoltaic support. The photovoltaic support parameter library includes the structural geometric parameters and material performance parameters of the photovoltaic support. Environmental load data for future periods is obtained based on historical environmental load data and long short-term memory networks. The environmental load data for future periods is then decomposed into average load components and pulsating load components. The power spectral density function of the pulsating load is constructed based on the pulsating load component, and the resonance risk assessment factor is calculated based on the power spectral density function; the average load component and the pulsating load component are applied to the photovoltaic support, and the vibration response curves of the key stress parts of the photovoltaic support are obtained, and the vibration level is determined based on the vibration response curves. Calculate the dynamic effect compensation coefficient based on resonance risk assessment factors and vibration levels; The second set of stress thresholds is obtained by correcting the data in the first set of stress thresholds based on the dynamic effect compensation coefficient, and the long short-term memory network is a trained neural network model. The parameters in the target parameter set are optimized based on the second stress threshold set to determine the optimal design parameter set of the photovoltaic support in the target area, and the photovoltaic support design operation is performed based on the optimal design parameter set.

[0010] Furthermore, based on historical environmental load data of the target area, a matching set of target parameters is retrieved from the photovoltaic support parameter library, including: Extreme value statistical analysis is performed on historical environmental load data to determine the characteristic design values ​​of photovoltaic supports in the target area during their design life. The characteristic design values ​​include the basic wind pressure design value and the equivalent load spectrum used for fatigue analysis. The equivalent load spectrum includes the difference in the magnitude and number of load changes. Construct a multidimensional load matching vector based on feature design values; Calculate the fit score between the inherent structural characteristics and the multidimensional load matching vector of each candidate parameter set in the photovoltaic support parameter library, and take the candidate parameter set with the highest fit score as the target parameter set.

[0011] Furthermore, based on the target parameter set, simulation analysis yields the first stress threshold set for key stress-bearing components of the photovoltaic support, including: Static strength ultimate condition simulation analysis is performed on the target parameter set to calculate the maximum equivalent stress of the photovoltaic support under wind load and the maximum displacement of each key stress-bearing part; among them, the static strength ultimate condition represents the condition based on the basic wind pressure design value, and the fatigue damage accumulation condition represents the condition based on the equivalent load spectrum. Perform fatigue damage accumulation simulation analysis on the target parameter set to calculate the damage degree of each key stress-bearing part; Based on the maximum equivalent stress, the maximum displacement of each key stress-bearing part, and the degree of damage, the first stress threshold set of the key stress-bearing parts of the photovoltaic support is obtained.

[0012] Furthermore, the vibration level is determined based on the vibration response curve, including: Calculate the average displacement difference between the peak and trough points in the vibration response curve; The vibration level of the photovoltaic support is determined based on the ratio of the average displacement difference to the preset maximum static displacement of the key stress-bearing parts of the photovoltaic support.

[0013] Furthermore, based on the ratio of the average displacement difference to the preset maximum static displacement of the key stress-bearing parts of the photovoltaic support, the vibration level of the photovoltaic support is determined, including: The vibration level of the photovoltaic support is calculated based on the following formula:

[0014] In the formula, n This is the logarithm of the peak and valley points in the vibration response curve. Let be the displacement value of the i-th pair of peak points; This represents the displacement value of the i-th pair of valley points; x The preset maximum static displacement of the key stress-bearing parts of the photovoltaic support.

[0015] Furthermore, based on the resonance risk assessment factor and vibration level, the dynamic effect compensation coefficient is calculated, including: The dynamic effect compensation coefficient is calculated based on the following formula:

[0016] In the formula, K represents the dynamic effect compensation coefficient; The resonance risk weighting coefficient is determined based on the structural damping ratio of the photovoltaic support. Indicates the resonance risk assessment factor. The vibration level weighting coefficient is determined based on the installation tilt angle of the photovoltaic support. S represents the vibration level; The installation tilt angle of the photovoltaic bracket is determined based on the correlation between the power generation of the photovoltaic module and the installation tilt angle.

[0017] Furthermore, the resonance risk weighting coefficient is determined based on the structural damping ratio of the photovoltaic support, using the following formula:

[0018] In the formula, For resonance risk weighting coefficient; The preset maximum resonance risk weight coefficient; This is the preset minimum structural damping ratio; The current structural damping ratio of the photovoltaic support structure; The vibration level weighting coefficient is determined based on the installation tilt angle of the photovoltaic support, and the specific formula is as follows:

[0019] In the formula, This is the vibration level weighting coefficient; The preset maximum value of the vibration level weighting coefficient; This is the current installation tilt angle; This is the preset maximum installation tilt angle.

[0020] Secondly, this application also provides a photovoltaic bracket design device, comprising: The data acquisition module is used to acquire historical environmental load data of various areas of the photovoltaic field. The historical environmental load data is either wind load data or snow load data. The photovoltaic support design module is used to classify each region based on the historical environmental load data monitored in each region if the historical environmental load data is wind load data, and to perform photovoltaic support design operations on multiple target regions. If the historical environmental load data is snow load data, then the photovoltaic bracket design operation will be performed based on the preset photovoltaic bracket design specifications; Specifically, when performing photovoltaic support design operations on the target area, the photovoltaic support design module is used to: call the matching target parameter set from the photovoltaic support parameter library based on the historical environmental load data of the target area to perform simulation analysis and obtain the first stress threshold set of the key stress-bearing parts of the photovoltaic support. The photovoltaic support parameter library includes the structural geometric parameters and material performance parameters of the photovoltaic support. Environmental load data for future periods is obtained based on historical environmental load data and long short-term memory networks. The environmental load data for future periods is then decomposed into average load components and pulsating load components. The power spectral density function of the pulsating load is constructed based on the pulsating load component, and the resonance risk assessment factor is calculated based on the power spectral density function; the average load component and the pulsating load component are applied to the photovoltaic support, and the vibration response curves of the key stress parts of the photovoltaic support are obtained, and the vibration level is determined based on the vibration response curves. Calculate the dynamic effect compensation coefficient based on resonance risk assessment factors and vibration levels; The second set of stress thresholds is obtained by correcting the data in the first set of stress thresholds based on the dynamic effect compensation coefficient, and the long short-term memory network is a trained neural network model. The parameters in the target parameter set are optimized based on the second stress threshold set to determine the optimal design parameter set of the photovoltaic support in the target area, and the photovoltaic support design operation is performed based on the optimal design parameter set.

[0021] Thirdly, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the photovoltaic bracket design method described above.

[0022] Fourthly, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the photovoltaic support design method described above.

[0023] Compared with the prior art, this application has the following advantages: 1. This application provides a photovoltaic (PV) support design method, apparatus, electronic device, and storage medium. It acquires historical environmental load data from various areas of the PV field and processes it according to the data type. When the data is wind load, the design is performed after classifying the areas, fully considering the differences in wind load in different areas and accurately matching the actual needs of each area. When the data is snow load, the design is based on preset design specifications, ensuring the basic rationality and safety of the design. Furthermore, this embodiment uses historical wind load data to call a matching parameter set for simulation analysis, then combines future environmental load data to determine the dynamic effect compensation coefficient and correct the stress threshold. Finally, the optimal design parameter set is determined by optimizing the parameters. This design method closely follows actual environmental changes, greatly improving the adaptability of PV support design to different environmental conditions and ensuring the accuracy and reliability of the design results.

[0024] 2. This application provides a photovoltaic (PV) support design method and apparatus, electronic device, and storage medium. Utilizing a trained neural network model, it can quickly and accurately predict future environmental load data based on historical environmental load data, avoiding the tedious and time-consuming prediction process of traditional methods, thus saving significant time and manpower costs. Furthermore, by calling matching parameter sets from the PV support parameter library for simulation analysis and optimizing parameters based on stress threshold sets, it avoids blind design and repeated experiments, reducing design cycle time and material waste. While ensuring the performance and quality of the PV support, it achieves improved design efficiency and effective cost control. Attached Figure Description

[0025] Figure 1 A schematic flowchart illustrating a photovoltaic support design method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the area division of a photovoltaic field provided in an embodiment of this application; Figure 3 A schematic flowchart illustrating a photovoltaic support design method provided in another embodiment of this application; Figure 4 Vibration response curves of key stress-bearing parts of a photovoltaic support provided in an embodiment of this application; Figure 5 A structural block diagram of a photovoltaic bracket design device provided in an embodiment of this application; Figure 6 This is a schematic block diagram of an electronic device provided in an embodiment of this application.

[0026] Explanation of reference numerals in the attached figures: 20. Photovoltaic support design device; 21. Data acquisition module; 22. Photovoltaic support design module; 300. Electronic equipment; 301. Processor; 302. Input device; 303. Output device; 304. Memory; 305. Communication bus. Detailed Implementation

[0027] The technical solution of the present invention will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are not all embodiments of the present invention. All other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the present invention.

[0028] It should be noted that, unless otherwise specifically stated, the relative arrangement and numerical expressions of the components and steps described in these embodiments should not be construed as limiting the scope of the invention.

[0029] The following description of exemplary embodiments is merely illustrative and is not intended to limit the invention or its application or use in any way. Techniques, methods, and apparatus known to those skilled in the art may not be discussed in detail herein, but where applicable, such techniques, methods, and apparatus should be considered part of this specification.

[0030] Example 1 Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a photovoltaic support design method according to an embodiment of this application. This embodiment provides a photovoltaic support design method, which can be executed by an electronic device, and the specific steps include: S101: Obtain historical environmental load data for each area of ​​the photovoltaic field. The historical environmental load data is either wind load data or snow load data.

[0031] In this embodiment, a photovoltaic (PV) field area refers to a specific region where PV modules and supporting facilities, such as PV racks, inverters, and combiner boxes, are centrally installed. Examples include rooftops, deserts, Gobi deserts, and mountainous areas with abundant solar resources. Following preset spatial division rules (e.g., based on terrain elevation changes), the PV field area is divided into multiple sub-regions. Environmental load data is independently collected, recorded, and analyzed over a long period for each sub-region. The purpose of dividing the area into regions is to avoid local design redundancy or safety risks under extreme conditions caused by using a single average load value for the entire PV field area.

[0032] Historical environmental load data refers to environmental load data obtained during the site selection and design phase of photovoltaic (PV) sites, covering a continuous period of the past, through methods such as meteorological station monitoring or retrieval of historical meteorological records. Historical environmental load data is divided into wind load data and snow load data. Wind load data refers to data related to the pressure or suction that airflow may exert on the surface of PV supports and modules. Its core parameters include basic wind pressure, wind speed profile coefficient, wind load shape coefficient, and gust coefficient. Wind load has a decisive impact on the structural stability of PV supports; improper design can easily lead to support overturning or module damage.

[0033] Snow load data refers to quantitative data related to the weight of snow per unit area. Its core parameters include basic snow pressure, snow distribution coefficient, and roof snow slip coefficient. Snow load varies with latitude, altitude, and terrain. Excessive static load on the structure can lead to structural overload of photovoltaic brackets or microcracks in the modules.

[0034] S102: If the historical environmental load data is wind load data, then the regions are classified based on the historical environmental load data monitored in each region to obtain multiple target regions, and photovoltaic bracket design operations are performed on multiple target regions.

[0035] like Figure 2 As shown, Figure 2 This is a schematic diagram showing the regional division of the photovoltaic (PV) field. Assuming areas numbered ①-⑨ are the initial areas for collecting historical environmental load data, cluster analysis is performed on the historical wind load data of each area. Areas with similar wind strength and prevailing wind direction are merged, ultimately classifying the entire PV field into three target areas: the lined area, the grid area, and the blank area. Since the wind strength and direction vary for each target area, the PV support structures designed for each area are different, but the design logic and methods remain consistent. For each defined target area, refer to... Figure 3 The specific steps for performing photovoltaic bracket design operations include S201~S203: S201: Based on the historical environmental load data of the target area, the matching target parameter set is called from the photovoltaic support parameter library to perform simulation analysis and obtain the first stress threshold set of the key stress parts of the photovoltaic support.

[0036] The photovoltaic support system parameter library includes structural geometric parameters and material performance parameters. Structural geometric parameters include the cross-sectional dimensions of the support system, member lengths, support spacing, installation tilt angle, column embedment depth, and the dimensions and arrangement of connectors. Material performance parameters include the yield strength, tensile strength, elastic modulus, Poisson's ratio, and performance parameters of the anti-corrosion coating of the support material.

[0037] The target parameter set refers to a combination of geometric and material performance parameters of the photovoltaic support structure, selected from the photovoltaic support parameter library based on historical environmental load data characteristics of the target area and filtered according to preset matching rules, and adapted to the working conditions of the area. Preset matching rules can include load level-parameter correspondence rules, strength requirement-material selection rules, etc.

[0038] In this embodiment, after determining the target parameter set, a digital model of the photovoltaic support structure can be constructed using finite element analysis engineering simulation software. This model, along with environmental load data of the target area, serves as input to simulate the stress state and deformation of the support structure under wind loads. The simulation software used in this embodiment is ANSYS. Through simulation analysis, the core areas of the photovoltaic support structure under wind loads, where stress is concentrated or the stress is high, can be identified. These locations determine the structural safety of the support structure. Key stress-bearing areas include: the connection nodes between the columns and the foundation, the welds between the diagonal braces and the main beam, the connections between the main beam and the purlins, and areas where the steel sections are weakened.

[0039] The first stress threshold set refers to the set of maximum stress values ​​of each key stress-bearing part of the photovoltaic support under wind load in the target area, which are obtained through simulation analysis. Each stress value in this set corresponds to a key stress-bearing part and is the core basis for subsequent judgment on whether the strength of the support structure meets the standard.

[0040] S202: Obtain environmental load data for future periods based on historical environmental load data and long short-term memory network; determine dynamic effect compensation coefficients based on environmental load data for future periods; and correct the data in the first stress threshold set based on the dynamic effect compensation coefficients to obtain the second stress threshold set.

[0041] Among them, the Long Short-Term Memory Network is a trained neural network model.

[0042] In this embodiment, because different environments affect the data in the first stress threshold set, the data in the first stress threshold set can be corrected by predicting environmental load data for future periods to obtain a second stress threshold set. The environmental load data for future periods can be obtained based on historical environmental load data and a Long Short-Term Memory (LSTM) network. LSTM is an improved Recurrent Neural Network (RNN) that solves the gradient vanishing and gradient exploding problems of traditional RNNs through gating mechanisms (input gate, forget gate, and output gate), effectively capturing long-term dependencies in time-series data.

[0043] After historical environmental load data is input into the LSTM model, it is first converted into a time-series sample format that LSTM can process, represented in the form of a three-dimensional tensor [number of samples, time step, number of features]. For example, when the number of features is 1, it only contains load values; when the number of features is 3, it can contain load values, temperature, and humidity-related features. Then, the model performs calculations based on its internal gating mechanism. The core of LSTM is the memory unit and three gating structures (forget gate, input gate, and output gate). Each gating control uses a sigmoid activation function to control the transmission and filtering of information. The specific calculations are as follows: The forget gate retains or discards historical information from the memory cell based on the current input and the hidden state from the previous time step. In load prediction, the forget gate automatically retains long-term dependent features such as seasonal load fluctuations while discarding random noise. The input gate updates the information that needs updating by using the sigmoid activation function. The memory cell combines the historical information filtering result from the forget gate with the current information update result from the input gate to obtain the current memory cell state. The output gate generates the hidden state for the current time step based on the current memory cell state and the input information.

[0044] Finally, the model completes the mapping from features to predicted values ​​through the hidden states of LSTM in a fully connected layer, and restores them to the true environmental load values ​​through inverse normalization, thus obtaining the final environmental load data for the future time period and outputting the result.

[0045] In this embodiment, the dynamic effect compensation coefficient is a correction coefficient that considers the impact of dynamic changes in environmental loads (such as the instantaneous impact of gusts or the cumulative effect of load fluctuations) on the stress of the photovoltaic support, and its value is greater than or equal to 1. The dynamic effect compensation coefficient is positively correlated with the fluctuation frequency of the load in the future period, the duration of the peak load, and the rate of load change. After determining the dynamic effect compensation coefficient, it can be multiplied by the stress values ​​of each key stress-bearing part in the first stress threshold set to obtain the second stress threshold set. This set considers the effects of both static and dynamic loads, more closely resembling the actual stress state of the photovoltaic support under actual working conditions, thus making the subsequent photovoltaic support design more reliable.

[0046] In one embodiment, determining the dynamic effect compensation coefficient based on environmental load data for future time periods includes: The environmental load data for future time periods is decomposed into mean load components and fluctuating load components. The power spectral density function of the pulsating load is constructed based on the pulsating load components, and the resonance risk assessment factor is calculated based on the power spectral density function. The average load component and the pulsating load component are applied to the photovoltaic support to obtain the vibration response curves of the key stress-bearing parts of the photovoltaic support, and the vibration level is determined based on the vibration response curves. The dynamic effect compensation coefficient is calculated based on the resonance risk assessment factor and vibration level.

[0047] In this embodiment, the environmental load data for future periods is first decomposed into an average load component (the long-term stable mean of the load, corresponding to the static load part) and a pulsating load component (the random fluctuation part of the load around the mean, corresponding to the dynamic excitation part), thereby achieving the separation of the static and dynamic load components.

[0048] Secondly, for the pulsating load component, a power spectral density function is constructed using the Fourier transform method. This function can characterize the energy distribution characteristics of the pulsating load at different frequencies. Then, the power spectral density function is compared with the natural frequency spectrum of the photovoltaic support to calculate the resonance risk assessment factor. The higher the overlap between the frequency of the pulsating load and the natural frequency of the support, the larger the resonance risk assessment factor, which means that the probability of load pulsation causing structural resonance and amplifying stress response is higher.

[0049] Next, the decomposed average load component and pulsating load component are used as a joint excitation and applied to the finite element simulation model of the photovoltaic support. The displacement-time, i.e., the vibration response curve, of the key stress-bearing parts of the support is solved through transient dynamic analysis (see reference). Figure 4 Based on this curve, characteristic parameters such as vibration amplitude, vibration frequency, and stress fluctuation amplitude are extracted, and the vibration level is quantified.

[0050] Finally, the dynamic effect compensation coefficient is obtained by weighting the resonance risk assessment factor and the vibration level. The larger the resonance risk assessment factor and the vibration level, the larger the compensation coefficient, thereby enabling effective correction of the static stress threshold.

[0051] S203: Optimize the parameters in the target parameter set based on the second stress threshold set, determine the optimal design parameter set of the photovoltaic support in the target area, and perform the photovoltaic support design operation based on the optimal design parameter set.

[0052] In this embodiment, the stress values ​​of each key stress-bearing component in the second stress threshold set are first compared with the allowable stress of the material corresponding to the target parameter set to determine whether the initial parameter set meets the safety constraints. If the stress value of a key stress-bearing component exceeds the allowable stress of the material, the parameter set is deemed to have a structural failure risk, and relevant parameters need to be adjusted accordingly, such as increasing the cross-sectional size of the steel, replacing the main material with a higher strength grade, and optimizing the connection method of the support nodes to disperse stress concentration. If the stress value is lower than the allowable stress of the material, the parameter set is deemed to have an over-design problem, and the cross-sectional size needs to be appropriately reduced, the column burial depth shortened, or the support spacing increased to reduce material costs, while ensuring safety redundancy. After the above adjustments, the adjusted new parameter set can be input into the simulation model again to calculate a new second stress threshold set. The stress values ​​of each key stress-bearing component in the new second stress threshold set are compared with the allowable stress of the material corresponding to the target parameter set. This process is repeated iteratively until all parameters in the target parameter set meet the safety constraints, resulting in the optimal design parameter set for the photovoltaic support in the target area. The photovoltaic support design operation is then performed based on the optimal design parameter set.

[0053] The photovoltaic support design in this embodiment is suitable for the photovoltaic equipment installation needs in all regions, and can improve the design accuracy of photovoltaic support and reduce the replacement cost of photovoltaic support.

[0054] S103: If the historical environmental load data is snow load data, then the photovoltaic bracket design operation shall be performed based on the preset photovoltaic bracket design specifications.

[0055] In this embodiment, the pre-defined photovoltaic support design specifications refer to mandatory or recommended technical standards issued at the national, industry, or enterprise level, covering requirements for support structure strength verification, material selection principles, and safety redundancy coefficient settings. Common specifications include industry standards such as the "Technical Requirements for Photovoltaic Power Station Support Systems," which serve as the compliance basis for support design under snow load conditions.

[0056] As can be seen from the above, on the one hand, this embodiment acquires historical environmental load data from various areas of the photovoltaic field and processes it accordingly based on the data type. When the data is wind load, the design operation is carried out after classifying each area, fully considering the differences in wind load in different areas and accurately matching the actual needs of each area. When the data is snow load, the design is based on preset design specifications, ensuring the basic rationality and safety of the design. In addition, this embodiment uses historical wind load data to call matching parameter sets for simulation analysis, then combines future environmental load data to determine the dynamic effect compensation coefficient and correct the stress threshold. Finally, the optimal design parameter set is determined by optimizing the parameters. This design method conforms to actual environmental changes, greatly improving the adaptability of photovoltaic support design to different environmental conditions and ensuring the accuracy and reliability of the design results.

[0057] On the other hand, this embodiment utilizes a trained neural network model to quickly and accurately predict future environmental load data based on historical environmental load data, avoiding the tedious and time-consuming prediction process of traditional methods, thus saving significant time and manpower costs. Furthermore, by calling matching parameter sets from the photovoltaic support parameter library for simulation analysis and optimizing parameters based on stress threshold sets, it avoids blind design and repeated testing, reducing design cycles and material waste. While ensuring the performance and quality of the photovoltaic support, it achieves improved design efficiency and effective cost control.

[0058] In one embodiment of this application, retrieving a matching target parameter set from a photovoltaic support parameter library based on historical environmental load data of the target area includes: Extreme value statistical analysis is performed on historical environmental load data to determine the characteristic design values ​​of photovoltaic supports in the target area during their design life. The characteristic design values ​​include the basic wind pressure design value and the equivalent load spectrum used for fatigue analysis. The equivalent load spectrum includes the difference in the magnitude and number of load changes. Construct a multidimensional load matching vector based on feature design values; Calculate the fit score between the inherent structural characteristics and the multidimensional load matching vector of each candidate parameter set in the photovoltaic support parameter library, and take the candidate parameter set with the highest fit score as the target parameter set.

[0059] In this embodiment, the historical environmental load data includes many extreme values, such as wind speeds greater than level 10. By performing extreme value statistical analysis on the historical environmental load data, the maximum extreme load value that may occur within the design life of the photovoltaic support in the target area can be estimated, ensuring the safety of the support in the face of extreme working conditions. The design life refers to the preset safe service life of the photovoltaic support, which is the time benchmark for determining the characteristic design values. All load design values ​​must meet the safe use requirements within this life.

[0060] The characteristic design values ​​include two categories: basic wind pressure design values ​​and equivalent load spectra used for fatigue analysis. The basic wind pressure design value represents the maximum wind pressure value that may occur in the target area during the design life. The equivalent load spectra used for fatigue analysis are a set of load characteristics obtained by equivalently fitting the variation patterns of historical loads, including the amplitude difference and the number of load changes. The amplitude difference of load changes refers to the difference between the maximum and minimum loads during a single load cycle; the larger the amplitude difference, the faster the fatigue damage rate of the support structure. The number of load changes is the total number of alternating load cycles during the design life; the more cycles, the higher the risk of fatigue failure of the support structure.

[0061] Constructing a multidimensional load matching vector based on feature design values ​​can be understood as quantizing and encoding multiple core parameters of the feature design values ​​to build a multidimensional numerical vector. Normalization can eliminate the dimensional differences between different load parameters, ensuring the accuracy of subsequent fit calculations, and allowing the value of each dimension of the vector to directly participate in the fit scoring.

[0062] In this embodiment, the inherent structural characteristics of each candidate parameter set are the structural properties of the photovoltaic support itself, including strength characteristics, stiffness characteristics, and fatigue characteristics. To calculate the fit score between the inherent structural characteristics of each candidate parameter set in the photovoltaic support parameter library and the multidimensional load matching vector, firstly, the inherent structural characteristics corresponding to each candidate parameter set in the photovoltaic support parameter library need to be extracted and transformed into feature vectors corresponding to the dimensions of the multidimensional load matching vector. Secondly, a fit score model is constructed, and the matching degree between the feature vectors of the candidate parameter sets and the multidimensional load matching vector is calculated using vector similarity algorithms such as cosine similarity and Euclidean distance, thus obtaining the fit score for each candidate parameter set. Finally, the candidate parameter set with the highest score is determined as the target parameter set. This target parameter set can maximize the balance between the structural safety and material economy of the support while meeting the load requirements of the target area.

[0063] This embodiment determines characteristic design values ​​through extreme value statistical analysis of historical environmental load data, obtaining effective key indicators for the target area design and ensuring design reliability. By constructing a multi-dimensional load matching vector and calculating the fit score to select the target parameter set, the most matching parameters can be quickly screened from the parameter library, improving the accuracy and efficiency of parameter matching, making the photovoltaic support design more in line with actual needs, and effectively improving the design quality and performance.

[0064] In one embodiment of this application, a first set of stress thresholds for key stress-bearing components of a photovoltaic support is obtained through simulation analysis based on a target parameter set, including: Static strength ultimate condition simulation analysis is performed on the target parameter set to calculate the maximum equivalent stress of the photovoltaic support under wind load and the maximum displacement of each key stress-bearing part; among them, the static strength ultimate condition represents the condition based on the basic wind pressure design value, and the fatigue damage accumulation condition represents the condition based on the equivalent load spectrum. Perform fatigue damage accumulation simulation analysis on the target parameter set to calculate the damage degree of each key stress-bearing part; Based on the maximum equivalent stress, the maximum displacement of each key stress-bearing part, and the degree of damage, the first stress threshold set of the key stress-bearing parts of the photovoltaic support is obtained.

[0065] In this embodiment, the static strength limit condition represents the condition based on the basic wind pressure design value. The purpose of performing static strength limit condition simulation analysis on the target parameter set is to verify whether the strength and stiffness of the photovoltaic support under the ultimate static wind load meet the design requirements. The specific operation is as follows: First, a finite element model of the photovoltaic support structure is constructed in simulation software based on the target parameter set. Material properties such as the elastic modulus and yield strength of the main materials are defined. Then, the basic wind pressure design value is converted into a simulation load and uniformly applied to the windward surface of the photovoltaic modules and support structure as a surface load to simulate the effect of the ultimate static wind load. Finally, the stress distribution cloud map and displacement deformation cloud map of the photovoltaic support structure are calculated using the simulation solver. Key stress-bearing parts such as the connection nodes between the main beam and the column, and the connection points between the purlin and the main beam are located, and the maximum equivalent stress and maximum displacement of these parts are extracted.

[0066] In this embodiment, the fatigue damage cumulative condition represents the condition based on the equivalent load spectrum. A fatigue damage cumulative condition simulation analysis is performed on the target parameter set to evaluate the fatigue resistance of the photovoltaic support under alternating wind loads and predict the fatigue damage risk within the design life. The specific operation is as follows: First, a finite element model of the photovoltaic support is constructed in the simulation software based on the target parameter set. The load amplitude difference and cycle number in the equivalent load spectrum are used as input conditions, and the fatigue damage accumulation analysis condition is set in the simulation software. Miner's linear cumulative damage theory is used as the calculation basis. The alternating wind load is divided into different load levels, and the damage increment caused by a single cycle to the key stress parts under each load level is calculated. The damage increments under all load levels are accumulated to obtain the damage degree value of each key part, thereby determining whether the support will experience fatigue failure within its design life.

[0067] This embodiment obtains the maximum equivalent stress, maximum displacement, and damage degree of the photovoltaic support under wind load by performing static strength limit condition simulation analysis and fatigue damage accumulation condition simulation analysis based on the target parameter set. The combined results of these indicators provide a first stress threshold set, which can provide a reference for the design of photovoltaic supports and ensure the reliability of the design.

[0068] In one embodiment of this application, determining the vibration level based on the vibration response curve includes: Calculate the average displacement difference between the peak and trough points in the vibration response curve; The vibration level of the photovoltaic support is determined based on the ratio of the average displacement difference to the preset maximum static displacement of the key stress-bearing parts of the photovoltaic support.

[0069] In this embodiment, the vibration response curve has multiple peak points and valley points. All peak points and valley points in the curve are identified. The first peak point and valley point are taken as a group of data, and then grouped sequentially. The displacement difference between the peak point and valley point in each group is calculated. Finally, the average value of all displacement differences is calculated. This value reflects the average fluctuation amplitude of the vibration displacement. The larger the value, the more severe the vibration caused by the dynamic load.

[0070] The vibration level is obtained by calculating the ratio of the mean displacement difference to the preset maximum static displacement of the key stress-bearing parts of the photovoltaic support. This ratio is dimensionless. The larger the ratio, the more significant the fluctuation amplitude of the dynamic vibration displacement is relative to the static displacement, and the stronger the additional influence of the dynamic load on the stress of the support; conversely, it indicates that the dynamic influence is weaker.

[0071] In one embodiment, the vibration level of the photovoltaic support is determined based on the ratio of the average displacement difference to the preset maximum static displacement of the key stress-bearing parts of the photovoltaic support, including: The vibration level of the photovoltaic support is calculated based on the following formula:

[0072] In the formula, n This is the logarithm of the peak and valley points in the vibration response curve. Let be the displacement value of the i-th pair of peak points; This represents the displacement value of the i-th pair of valley points; x The preset maximum static displacement of the key stress-bearing parts of the photovoltaic support.

[0073] This embodiment calculates the average difference between the peak and valley displacements of the vibration response curve and determines the vibration level by combining it with the preset maximum static displacement. This allows for the quantification of the vibration degree of the photovoltaic support, which is beneficial for the subsequent calculation of the dynamic effect compensation coefficient.

[0074] In one embodiment of this application, the dynamic effect compensation coefficient is calculated based on the resonance risk assessment factor and the vibration level, including: The dynamic effect compensation coefficient is calculated based on the following formula:

[0075] In the formula, K represents the dynamic effect compensation coefficient; The resonance risk weighting coefficient is determined based on the structural damping ratio of the photovoltaic support. Indicates the resonance risk assessment factor. The vibration level weighting coefficient is determined based on the installation tilt angle of the photovoltaic support. S represents the vibration level; where the installation tilt angle of the photovoltaic bracket is determined based on the correlation between the power generation of the photovoltaic module and the installation tilt angle.

[0076] In this embodiment, the structural damping ratio is the inherent damping characteristic of the photovoltaic support structure, characterizing its ability to dissipate vibration energy and suppress resonance amplification. A larger structural damping ratio indicates stronger vibration reduction capability and a smaller resonance risk weighting coefficient; conversely, a smaller structural damping ratio indicates weaker vibration reduction capability and a larger resonance risk weighting coefficient. The formula for determining the resonance risk weighting coefficient based on the structural damping ratio of the photovoltaic support is as follows:

[0077] in, The maximum resonance risk weighting coefficient is, for example, 0.6. This represents the minimum structural damping ratio, for example, 0.005. The damping ratio of current photovoltaic support structures is as follows: for example, 0.005 for aluminum alloy photovoltaic supports, 0.15 for conventional steel supports, and 0.05 for heavy-duty seismic steel supports.

[0078] In this embodiment, the installation tilt angle range of the photovoltaic bracket is: The vibration level weighting coefficients are obtained according to the linear normalized mapping formula. The linear normalized mapping formula is:

[0079] in, This represents the maximum value of the vibration level weighting coefficient, for example, 0.4. For the current installation tilt angle, Let the maximum installation tilt angle be, for example, 45°. The vibration level weighting coefficient within the photovoltaic support at the current installation tilt angle can be obtained using the linear normalized mapping formula described above.

[0080] In this embodiment, when the installation tilt angle is equal to the latitude angle of the target area, sunlight can be perpendicularly incident on the module surface on the spring and autumn equinoxes, resulting in the maximum amount of light received per unit area and the maximum power generation. Considering the difference in irradiance between winter and summer, the tilt angle can be finely adjusted (e.g., latitude ±5°-10°) to balance the annual power generation. Therefore, the installation tilt angle of the photovoltaic support can be determined according to the power generation requirements of the photovoltaic modules in the target area.

[0081] As can be seen from the above, the embodiments of this application classify and design according to the historical environmental load data actually monitored in each area of ​​the photovoltaic field, which can match the wind load characteristics of different areas. Combined with simulation analysis and dynamic effect compensation, the actual working conditions are fully considered, making the designed photovoltaic support more suitable for the local environment and enhancing its adaptability to complex environments.

[0082] This application embodiment uses static strength limit condition and fatigue damage accumulation condition simulation analysis to consider the stress situation of photovoltaic support under different loads, obtain the first stress threshold set of key stress parts of photovoltaic support, and then perform dynamic effect compensation correction on the parameters in the above set to optimize the design parameters. This can effectively improve the structural strength and fatigue resistance of photovoltaic support and ensure operational reliability.

[0083] Example 2 Based on the same inventive concept, this application also provides a photovoltaic bracket design apparatus for implementing the photovoltaic bracket design method described above. The solution provided by this apparatus is similar to the solution described in the above method; therefore, the specific limitations in one or more photovoltaic bracket design apparatus embodiments provided below can be found in the limitations of the photovoltaic bracket design method described above, and will not be repeated here.

[0084] This application provides a photovoltaic bracket design device, such as... Figure 5 As shown, the photovoltaic bracket design device 20 includes a data acquisition module 21 and a photovoltaic bracket design module 22.

[0085] Data acquisition module 21 is used to acquire historical environmental load data of each area of ​​the photovoltaic field. The historical environmental load data is wind load data or snow load data. The photovoltaic support design module 22 is used to classify each region based on the historical environmental load data monitored in each region to obtain multiple target regions if the historical environmental load data is wind load data, and to perform photovoltaic support design operations on multiple target regions. If the historical environmental load data is snow load data, then the photovoltaic bracket design operation will be performed based on the preset photovoltaic bracket design specifications; Among them, when performing photovoltaic support design operation on the target area, the photovoltaic support design module 22 is specifically used to: call the matching target parameter set from the photovoltaic support parameter library based on the historical environmental load data of the target area to perform simulation analysis and obtain the first stress threshold set of the key stress parts of the photovoltaic support. The photovoltaic support parameter library includes the structural geometric parameters and material performance parameters of the photovoltaic support. Environmental load data for future periods is obtained based on historical environmental load data and a long short-term memory network. Dynamic effect compensation coefficients are determined based on the environmental load data for future periods. The data in the first set of stress thresholds are corrected based on the dynamic effect compensation coefficients to obtain a second set of stress thresholds. The long short-term memory network is a trained neural network model. The parameters in the target parameter set are optimized based on the second stress threshold set to determine the optimal design parameter set of the photovoltaic support in the target area, and the photovoltaic support design operation is performed based on the optimal design parameter set.

[0086] In one embodiment of this application, when the photovoltaic support design module 22 calls a matching target parameter set from the photovoltaic support parameter library based on historical environmental load data of the target area, it is specifically used for: Extreme value statistical analysis is performed on historical environmental load data to determine the characteristic design values ​​of photovoltaic supports in the target area during their design life. The characteristic design values ​​include the basic wind pressure design value and the equivalent load spectrum used for fatigue analysis. The equivalent load spectrum includes the difference in the magnitude and number of load changes. Construct a multidimensional load matching vector based on feature design values; Calculate the fit score between the inherent structural characteristics and the multidimensional load matching vector of each candidate parameter set in the photovoltaic support parameter library, and take the candidate parameter set with the highest fit score as the target parameter set.

[0087] In one embodiment of this application, when the photovoltaic support design module 22 obtains the first stress threshold set of key stress-bearing parts of the photovoltaic support through simulation analysis based on the target parameter set, it is specifically used for: Static strength ultimate condition simulation analysis is performed on the target parameter set to calculate the maximum equivalent stress of the photovoltaic support under wind load and the maximum displacement of each key stress-bearing part; among them, the static strength ultimate condition represents the condition based on the basic wind pressure design value, and the fatigue damage accumulation condition represents the condition based on the equivalent load spectrum. Perform fatigue damage accumulation simulation analysis on the target parameter set to calculate the damage degree of each key stress-bearing part; Based on the maximum equivalent stress, the maximum displacement of each key stress-bearing part, and the degree of damage, the first stress threshold set of the key stress-bearing parts of the photovoltaic support is obtained.

[0088] In one embodiment of this application, when determining the dynamic effect compensation coefficient based on environmental load data for future periods, the photovoltaic support design module 22 is specifically used for: The environmental load data for future time periods is decomposed into mean load components and fluctuating load components. The power spectral density function of the pulsating load is constructed based on the pulsating load components, and the resonance risk assessment factor is calculated based on the power spectral density function. The average load component and the pulsating load component are applied to the photovoltaic support to obtain the vibration response curves of the key stress-bearing parts of the photovoltaic support, and the vibration level is determined based on the vibration response curves. The dynamic effect compensation coefficient is calculated based on the resonance risk assessment factor and vibration level.

[0089] In one embodiment of this application, the photovoltaic support design module 22 is specifically used for: Calculate the average displacement difference between the peak and trough points in the vibration response curve; The vibration level of the photovoltaic support is determined based on the ratio of the average displacement difference to the preset maximum static displacement of the key stress-bearing parts of the photovoltaic support.

[0090] In one embodiment of this application, the photovoltaic support design module 22 is specifically used to: calculate the vibration level of the photovoltaic support based on the following formula:

[0091] In the formula, n This is the logarithm of the peak and valley points in the vibration response curve. Let be the displacement value of the i-th pair of peak points; This represents the displacement value of the i-th pair of valley points; x The preset maximum static displacement of the key stress-bearing parts of the photovoltaic support.

[0092] In one embodiment of this application, the photovoltaic support design module 22 is specifically used for: The dynamic effect compensation coefficient is calculated based on the following formula:

[0093] In the formula, K represents the dynamic effect compensation coefficient; The resonance risk weighting coefficient is determined based on the structural damping ratio of the photovoltaic support. Indicates the resonance risk assessment factor. The vibration level weighting coefficient is determined based on the installation tilt angle of the photovoltaic support. S represents the vibration level; The installation tilt angle of the photovoltaic bracket is determined based on the correlation between the power generation of the photovoltaic module and the installation tilt angle.

[0094] See Figure 6 , Figure 6 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 6 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of the modules in the aforementioned device embodiments, for example... Figure 5 The functions of the data acquisition module 21 and the photovoltaic bracket design module 22 are shown.

[0095] It should be understood that, in the embodiments of this application, the processor 301 may be a central processing unit, or it may be other general-purpose processors, digital signal processors, application-specific integrated circuits, field-programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0096] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0097] The memory 304 may include a read-only memory and a random access memory, and provides instructions and data to the processor 301. In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation methods described in the photovoltaic bracket design method provided in the embodiments of this application, or they can execute the implementation methods of the electronic devices described in the embodiments of this application, which will not be elaborated further here.

[0098] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to implement these processes. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0099] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, memory card, flash memory card, etc., provided on the electronic device. Furthermore, the computer-readable storage medium can include both internal storage units and external storage devices of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0100] Those skilled in the art will recognize that the modules / units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0101] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0102] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules, units, or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces or modules / units, or it may be an electrical, mechanical, or other form of connection.

[0103] The modules / units described as separate components may or may not be physically separate. Similarly, the components shown as modules / units may or may not be physical modules / units; they may be located in one place or distributed across multiple network modules / units. Some or all of the modules / units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0104] The above specific embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to examples, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the protection scope of the present invention.

Claims

1. A photovoltaic support design method, characterized in that, include: Acquire historical environmental load data for monitoring various areas of the photovoltaic field, wherein the historical environmental load data is wind load data or snow load data; If the historical environmental load data is wind load data, then based on the historical environmental load data monitored in each region, each region is classified to obtain multiple target regions, and photovoltaic bracket design operations are performed on the multiple target regions. If the historical environmental load data is snow load data, then the photovoltaic support design operation is performed based on the preset photovoltaic support design specifications; For each target area, the photovoltaic support design process includes: Based on historical environmental load data of the target area, the matching target parameter set is called from the photovoltaic support parameter library to perform simulation analysis and obtain the first stress threshold set of key stress-bearing parts of the photovoltaic support. The photovoltaic support parameter library includes the structural geometric parameters and material performance parameters of the photovoltaic support. Based on the historical environmental load data and the long short-term memory network, environmental load data for future periods is obtained, and the environmental load data for future periods is decomposed into average load components and pulsating load components. A power spectral density function of the pulsating load is constructed based on the pulsating load component, and a resonance risk assessment factor is calculated based on the power spectral density function; the average load component and the pulsating load component are applied to the photovoltaic support, and the vibration response curves of the key stress-bearing parts of the photovoltaic support are obtained; the vibration level is determined based on the vibration response curves. Calculate the dynamic effect compensation coefficient based on the resonance risk assessment factor and the vibration level; The second stress threshold set is obtained by correcting the data in the first stress threshold set based on the dynamic effect compensation coefficient, and the long short-term memory network is a trained neural network model. Based on the second set of stress thresholds, the parameters in the target parameter set are optimized to determine the optimal design parameter set for the photovoltaic support in the target area, and the photovoltaic support design operation is performed based on the optimal design parameter set.

2. The photovoltaic support design method as described in claim 1, characterized in that, The historical environmental load data based on the target area is used to retrieve a matching target parameter set from the photovoltaic support parameter library, including: Extreme value statistical analysis is performed on the historical environmental load data to determine the characteristic design values ​​of the photovoltaic support in the target area during its design life. The characteristic design values ​​include the basic wind pressure design value and the equivalent load spectrum for fatigue analysis. The equivalent load spectrum includes the amplitude difference and number of load changes. Construct a multidimensional load matching vector based on the aforementioned feature design values; Calculate the fit score between the inherent structural characteristics of each candidate parameter set in the photovoltaic support parameter library and the multidimensional load matching vector, and take the candidate parameter set with the highest fit score as the target parameter set.

3. The photovoltaic support design method as described in claim 1 or 2, characterized in that, Simulation analysis based on the target parameter set yields the first set of stress thresholds for key stress-bearing components of the photovoltaic support, including: A static strength limit condition simulation analysis is performed on the target parameter set to calculate the maximum equivalent stress of the photovoltaic support under wind load and the maximum displacement of each key stress-bearing part; wherein, the static strength limit condition represents the condition based on the basic wind pressure design value, and the fatigue damage accumulation condition represents the condition based on the equivalent load spectrum. Perform fatigue damage accumulation simulation analysis on the target parameter set to calculate the damage degree value of each key stress-bearing part; Based on the maximum equivalent stress, the maximum displacement of each key stress-bearing part, and the degree of damage, the first stress threshold set of the key stress-bearing parts of the photovoltaic support is obtained.

4. The photovoltaic support design method as described in claim 1, characterized in that, Determining the vibration level based on the vibration response curve includes: Calculate the average displacement difference between the peak and valley points in the vibration response curve; The vibration level of the photovoltaic support is determined based on the ratio of the average displacement difference to the preset maximum static displacement of the key stress-bearing parts of the photovoltaic support.

5. The photovoltaic support design method as described in claim 4, characterized in that, The determination of the vibration level of the photovoltaic support based on the ratio of the average displacement difference to the preset maximum static displacement of the key stress-bearing parts of the photovoltaic support includes: The vibration level of the photovoltaic support is calculated based on the following formula: In the formula, n This is the logarithm of the peak and valley points in the vibration response curve. Let be the displacement value of the i-th pair of peak points; This represents the displacement value of the i-th pair of valley points; x The preset maximum static displacement of the key stress-bearing parts of the photovoltaic support.

6. The photovoltaic support design method as described in claim 1, characterized in that, The dynamic effect compensation coefficient is calculated based on the resonance risk assessment factor and the vibration level, including: The dynamic effect compensation coefficient is calculated based on the following formula: In the formula, K represents the dynamic effect compensation coefficient; The resonance risk weighting coefficient is determined based on the structural damping ratio of the photovoltaic support. Indicates the resonance risk assessment factor. The vibration level weighting coefficient is determined based on the installation tilt angle of the photovoltaic support. S represents the vibration level; The installation tilt angle of the photovoltaic bracket is determined based on the correlation between the power generation of the photovoltaic module and the installation tilt angle.

7. The photovoltaic support design method as described in claim 6, characterized in that, The specific formula for determining the resonance risk weighting coefficient based on the structural damping ratio of the photovoltaic support is as follows: In the formula, This refers to the resonance risk weighting coefficient. The preset maximum resonance risk weight coefficient; This is the preset minimum structural damping ratio; The current structural damping ratio of the photovoltaic support structure; The vibration level weighting coefficient is determined based on the installation tilt angle of the photovoltaic bracket, and the specific formula is as follows: In the formula, This is the vibration level weighting coefficient; The preset maximum value of the vibration level weighting coefficient; This is the current installation tilt angle; This is the preset maximum installation tilt angle.

8. A photovoltaic support design device, characterized in that, include: The data acquisition module is used to acquire historical environmental load data of various areas of the photovoltaic field, wherein the historical environmental load data is wind load data or snow load data; The photovoltaic support design module is used to classify each region based on the historical environmental load data monitored in each region to obtain multiple target regions if the historical environmental load data is wind load data, and to perform photovoltaic support design operations on the multiple target regions. If the historical environmental load data is snow load data, then the photovoltaic support design operation is performed based on the preset photovoltaic support design specifications; Specifically, when performing photovoltaic support design operations on a target area, the photovoltaic support design module is used to: retrieve a matching target parameter set from the photovoltaic support parameter library based on the historical environmental load data of the target area for simulation analysis to obtain the first stress threshold set of key stress-bearing parts of the photovoltaic support; the photovoltaic support parameter library includes the structural geometric parameters and material performance parameters of the photovoltaic support. Based on the historical environmental load data and the long short-term memory network, environmental load data for future periods is obtained, and the environmental load data for future periods is decomposed into average load components and pulsating load components. A power spectral density function of the pulsating load is constructed based on the pulsating load component, and a resonance risk assessment factor is calculated based on the power spectral density function; the average load component and the pulsating load component are applied to the photovoltaic support, and the vibration response curves of the key stress-bearing parts of the photovoltaic support are obtained; the vibration level is determined based on the vibration response curves. Calculate the dynamic effect compensation coefficient based on the resonance risk assessment factor and the vibration level; The second stress threshold set is obtained by correcting the data in the first stress threshold set based on the dynamic effect compensation coefficient, and the long short-term memory network is a trained neural network model. Based on the second set of stress thresholds, the parameters in the target parameter set are optimized to determine the optimal design parameter set for the photovoltaic support in the target area, and the photovoltaic support design operation is performed based on the optimal design parameter set.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images