Photovoltaic support structural member strength analysis method and system based on wind load

Abstract

The invention discloses a photovoltaic support structural member strength analysis method and system based on a wind load, and relates to the technical field of photovoltaic equipment detection, the method improves the accuracy and economy of photovoltaic support wind resistance design through multi-modal data fusion and intelligent algorithm iteration, and improves the photovoltaic support structural member strength analysis efficiency. Firstly, wind speed / wind direction separation modeling based on machine learning breaks through the limitation of traditional static wind pressure calculation, and the extreme wind condition prediction accuracy is effectively improved; secondly, non-dominant dangerous working conditions such as a 52-degree inclination angle can be automatically positioned through linkage of a parameterized model and a global optimization algorithm, and the efficiency is obviously improved compared with manual trial calculation; and finally, a stress threshold dynamic early warning mechanism realizes conversion from passive checking calculation to active defense.

Description

Technical Field

[0001] The present application relates to the technical field of photovoltaic equipment detection, and in particular to a method and system for analyzing the strength of photovoltaic support structures based on wind loads. Background Art

[0002] A photovoltaic power station is a facility that harnesses solar energy to generate electricity. Using specialized materials like crystalline silicon panels and electronic components like inverters, the solar energy is converted into electricity, which is then connected to the power grid to be delivered. PV power stations are a green energy project encouraged by the government, characterized by cleanliness, environmental friendliness, and renewable energy. They are widely used in various applications, including providing power to areas without electricity, powering solar-powered consumer electronics (such as solar chargers and solar streetlights), and connecting to the grid. With technological advancements and policy support, photovoltaic power generation will play a crucial role in the future energy mix.

[0003] The installation of photovoltaic brackets for photovoltaic power stations usually follows a priori experience (for example, in areas near the equator with latitudes of 0° to 20°, an inclination angle of 15° to 25° is recommended; in mid-latitudes with latitudes of 20° to 40°, an inclination angle of 25°-35° is suitable; in high-latitude areas with latitudes above 40°, an inclination angle of 35° to 45° is recommended). Most photovoltaic brackets are not installed based on the changes in bracket stress caused by wind loads, which can cause the bracket to deform at best and even completely collapse at worst. Summary of the Invention

[0004] The main purpose of this application is to provide a method and system for analyzing the strength of photovoltaic bracket structures based on wind loads, so as to solve the problem in the prior art that the installation of photovoltaic brackets usually adopts prior experience, resulting in unsatisfactory subsequent operation and maintenance effects.

[0005] In order to achieve the above objectives, this application provides the following technical solutions: A photovoltaic support structure strength analysis method based on wind load is applied to photovoltaic supports that have been installed in a preset area. The photovoltaic support structure strength analysis method includes: Step S1, obtaining a plurality of ground wind speed data within the preset area based on a preset detection interval, each wind speed data including a wind speed and a wind direction; Step S2: training and learning all wind speeds and all wind directions by a machine learning machine to obtain a wind speed prediction model and a wind direction prediction model respectively; Step S3, predicting the future wind speed and future wind direction at the same future moment by using the wind speed prediction model and the wind direction prediction model, and combining them into the future wind speed at the same future moment; Step S4, obtaining structural data of the photovoltaic support and establishing a parameterized model in ANSYS; Step S5, inputting the future wind speeds at all future moments into the parameterized model in the ANSYS environment, and obtaining a set of stress data based on a future wind speed; Step S6, adjusting the photovoltaic panel inclination angle of the parameterized model with a preset step size in the ANSYS environment, and obtaining a set of adjusted stress data based on the photovoltaic panel inclination angle after each adjustment; Step S7, obtaining the optimal photovoltaic panel tilt angle of the parameterized model through a global optimization algorithm so that the corresponding adjusted stress data reaches the maximum stress value, and defining the optimal photovoltaic panel tilt angle as the most unfavorable working condition; Step S8, determining whether the adjusted stress data corresponding to the most unfavorable working condition exceeds the safety specification stress threshold, if so, executing step S9; Step S9: determining whether the photovoltaic bracket has a risk of irreversible deformation.

[0006] As a further improvement of the present application, step S9, determining whether the photovoltaic bracket has an irreversible deformation risk, then includes: Step S10, obtaining a future timestamp when the irreversible deformation risk first occurs, and defining it as a possible risk timestamp; Step S20, obtaining the future wind speed and the corresponding photovoltaic panel tilt angle corresponding to the possible risk timestamp, and packaging them into a risk data packet; Step S30: sending the risk data packet to an external monitoring terminal.

[0007] As a further improvement of the present application, step S9, determining whether the photovoltaic bracket has an irreversible deformation risk, then includes: Step S100, constructing a stress interval with a zero value as the minimum value of the stress interval and the maximum stress value as the maximum value of the stress interval; Step S200, dividing the stress interval into a plurality of sub-intervals; Step S300 , assigning a visible light color based on each subinterval, wherein the color temperature of each visible light color increases as the value of each subinterval increases; Step S400 , generating a visual animation of all parameterized models along the time course of all future moments; Step S500 , obtaining the stress data or the subinterval corresponding to the adjusted stress data of each parameterizable model, and the corresponding visible light color; Step S600, filling visible light color into each corresponding parameterizable model to obtain a dyeing visualization animation; Step S700: sending the dyeing visualization animation to an external visualization terminal.

[0008] As a further improvement of the present application, step S700, sending the dyeing visualization animation to an external visualization terminal, then includes: Step S1000, in response to a touch operation from an external visualization terminal, starting to display the visualization animation; Step S2000: identifying the operation type of the touch operation and enabling different demonstration effects based on different operation types.

[0009] As a further improvement of the present application, in step S2, all wind speeds and all wind directions are trained and learned by a machine learning machine to obtain a wind speed prediction model and a wind direction prediction model, respectively, including: Step S21, integrating all wind speeds into one data set; Step S22: Divide the data into a training set, a validation set, and a test set according to a preset ratio; Step S23, defining a neural network model; Step S24, training the training set through the neural network model, and updating the weights and biases of the neural network model through a back propagation algorithm based on the training results and the loss function of the validation set; Step S25, repeating step S24 several times until the loss function reaches a minimum value; Step S26, obtaining a neural network model corresponding to the minimum value of the loss function and defining it as the wind speed prediction model; In step S27, steps S21 to S26 are repeatedly executed with all wind directions as the execution subject to obtain a wind direction prediction model.

[0010] As a further improvement of the present application, step S3, predicting the future wind speed and future wind direction at the same future moment by the wind speed prediction model and the wind direction prediction model, and merging them into the future wind speed at the same future moment, includes: Step S31, inputting the test set corresponding to the wind speed into the wind speed prediction model; Step S32, obtaining the future wind speed at the next future moment through forward propagation of the wind speed prediction model; Step S33, using the future wind speed at the next future moment as an iteration subject to input the wind speed prediction model, and repeatedly executing step S32 to obtain a plurality of future wind speeds; Step S34, inputting the test set corresponding to the wind direction into the wind direction prediction model; Step S35, obtaining the future wind direction at the next future moment through forward propagation of the wind direction prediction model; Step S36, taking the future wind direction at the next future moment as the iteration subject and inputting the wind direction prediction model, and repeating step S35 to obtain a plurality of future wind directions; Step S37: Combine the future wind speed and future wind direction at the same future moment into the future wind speed.

[0011] As a further improvement of the present application, step S7, obtaining the optimal photovoltaic panel inclination angle of the parameterized model through a global optimization algorithm so that the corresponding adjusted stress data reaches the maximum stress value, and defining the optimal photovoltaic panel inclination angle as the most unfavorable working condition, includes: Step S71, randomly generating a plurality of random solutions based on the optimal photovoltaic panel tilt angle; Step S72, defining the optimization result of all random solutions as the corresponding adjusted stress data reaching the maximum stress value; Step S73, initializing the position of each random solution; Step S74, updating the current position and current speed of each random solution respectively; Step S75, obtaining the individual optimal solution and the global optimal solution of each random solution based on each update; Step S76, respectively determine whether the fitness value of each individual optimal solution and each global optimal solution no longer changes. If yes, proceed to step S77; Step S77: determining whether the optimal solution for the optimal photovoltaic panel tilt angle has been obtained.

[0012] In order to achieve the above objectives, this application also provides the following technical solutions: A photovoltaic support structure strength analysis system based on wind load, the photovoltaic support structure strength analysis system is applied to the photovoltaic support structure strength analysis method as described above, and the photovoltaic support structure strength analysis system includes: A ground wind speed data acquisition module, configured to acquire a plurality of ground wind speed data within the preset area based on a preset detection interval, each wind speed data including a wind speed and a wind direction; The ground wind speed data learning module is used to train and learn all wind speeds and all wind directions through a machine learning machine to obtain a wind speed prediction model and a wind direction prediction model respectively; A future wind speed data prediction module is used to predict the future wind speed and future wind direction at the same future moment by using the wind speed prediction model and the wind direction prediction model, and combine them into the future wind speed at the same future moment; A parameterized model building module, used to obtain structural data of the photovoltaic support and build a parameterized model in ANSYS; A stress data acquisition module is used to input the future wind speeds at all future moments into the parameterized model in an ANSYS environment, and obtain a set of stress data based on a future wind speed; A photovoltaic panel tilt adjustment module is used to adjust the photovoltaic panel tilt of the parameterized model with a preset step size in an ANSYS environment, and obtain a set of adjusted stress data based on the photovoltaic panel tilt after each adjustment; A photovoltaic panel tilt optimization module is used to obtain the optimal photovoltaic panel tilt of the parameterized model through a global optimization algorithm so that the corresponding adjusted stress data reaches the maximum stress value, and the optimal photovoltaic panel tilt is defined as the most unfavorable working condition; A most unfavorable working condition judgment module is used to judge whether the adjusted stress data corresponding to the most unfavorable working condition exceeds the safety specification stress threshold; The irreversible deformation risk determination module is used to determine whether the photovoltaic bracket has the risk of irreversible deformation if so.

[0013] In order to achieve the above objectives, this application also provides the following technical solutions: 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 photovoltaic support structure strength analysis method as described above is implemented.

[0014] In order to achieve the above objectives, this application also provides the following technical solutions: A storage medium stores program instructions, which, when executed by a processor, can implement the above-mentioned photovoltaic support structure strength analysis method.

[0015] The present application obtains a number of ground wind speed data in a preset area based on a preset detection interval, and each wind speed data includes a wind speed and a wind direction; all wind speeds and all wind directions are trained and learned separately by a machine learning machine to obtain a wind speed prediction model and a wind direction prediction model respectively; the future wind speed and future wind direction at the same future moment are predicted by the wind speed prediction model and the wind direction prediction model, and merged into the future wind speed at the same future moment; the structural data of the photovoltaic bracket is obtained and a parameterized model is established in ANSYS; the future wind speeds at all future moments are input into the parameterized model in the ANSYS environment, and a set of stress data is obtained based on a future wind speed; the photovoltaic panel inclination angle of the parameterized model is adjusted with a preset step size in the ANSYS environment, and a set of adjusted stress data is obtained based on the photovoltaic panel inclination angle after each adjustment; the optimal photovoltaic panel inclination angle of the parameterized model is obtained by a global optimization algorithm, so that the corresponding adjusted stress data reaches the maximum stress value, and the optimal photovoltaic panel inclination angle is defined as the most unfavorable working condition; it is judged whether the adjusted stress data corresponding to the most unfavorable working condition exceeds the safety specification stress threshold. If so, it is determined that the photovoltaic bracket has an irreversible deformation risk. This application improves the accuracy and economy of the wind-resistant design of photovoltaic brackets through multimodal data fusion and intelligent algorithm iteration. First, the wind speed / wind direction separation modeling based on machine learning breaks through the limitations of traditional static wind pressure calculations and effectively improves the accuracy of extreme wind condition predictions; second, the parameterized model is linked with the global optimization algorithm to automatically locate non-explicit dangerous working conditions such as a 52° inclination angle, which is significantly improved compared to manual calculation efficiency; finally, the stress threshold dynamic warning mechanism realizes the transition from passive verification to active defense. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a schematic diagram of the steps of an embodiment of a method for analyzing the strength of a photovoltaic support structure based on wind loads in this application; Figure 2 This is a functional module diagram of an embodiment of a photovoltaic support structure strength analysis system based on wind loads of the present application; Figure 3 This is a schematic structural diagram of an embodiment of the electronic device of the present application; Figure 4 This is a structural diagram of an embodiment of the storage medium of the present application. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0018] The terms "first," "second," and "third" in this application are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, features specified as "first," "second," or "third" may explicitly or implicitly include at least one of such features. In the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined. All directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this application are intended only to illustrate the relative positional relationships and movement of components in a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly. Furthermore, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements and may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to such process, method, product, or apparatus.

[0019] References to "embodiments" herein mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0020] like Figure 1 As shown, this embodiment provides an embodiment of a photovoltaic support structure strength analysis method based on wind load. In this embodiment, the photovoltaic support structure strength analysis method is applied to photovoltaic supports that have been installed in a preset area.

[0021] Preferably, the photovoltaic bracket of this embodiment is a conventional photovoltaic bracket in the prior art, including a support frame (columns, beams), connectors (bolts, clamps), a foundation (concrete or ground anchors) and photovoltaic panels.

[0022] Specifically, the photovoltaic support structure strength analysis method includes: Step S1 : acquiring a plurality of ground wind speed data within a preset area based on a preset detection interval, each wind speed data including a wind speed and a wind direction.

[0023] Preferably, the ground wind speed data refers to the wind speed within 10 m from the ground, and the preset detection interval can be set to 1 second.

[0024] Step S2: All wind speeds and all wind directions are trained and learned by a machine learning machine to obtain a wind speed prediction model and a wind direction prediction model respectively.

[0025] Preferably, an extreme learning machine can be used for training and learning the wind direction.

[0026] Step S3: predict the future wind speed and future wind direction at the same future moment using the wind speed prediction model and the wind direction prediction model, and combine them into the future wind speed at the same future moment.

[0027] Preferably, the step size of the future time can also be set to 1 second.

[0028] Step S4: Obtain the structural data of the photovoltaic bracket and establish a parameterized model in ANSYS.

[0029] Preferably, the photovoltaic bracket parametric model is established in ANSYS to achieve dynamic reconstruction of the model through parameter drive, see the following method: ① Parameter system construction: Geometric parameters: main beam cross-section (H-beam 200×200×8×12), column spacing (3.6m reference value), inclination angle variable (θ=15°~60°adjustable).

[0030] Material parameters: Q355B steel (elastic modulus 206GPa / Poisson's ratio 0.3), bolt connection stiffness (contact stiffness coefficient 0.8).

[0031] Load parameters: wind pressure distribution coefficient (according to IEC 61400-2 Class II), dynamic amplification factor (1.2).

[0032] ②APDL scripted modeling: #Key parameter settings *SET, L, 3600# Vertical spacing of columns (mm) *SET, W, 2000# Module width (mm) *SET, theta, 30# initial tilt angle (°) #Parametric geometry generation K,1,0,0,0#define key points K,2,L*COS(theta),0,L*SIN(theta) L,1,2#Generate inclined beam #Automatic mesh division ET,1,BEAM188# defines beam elements SECTYPE,1,BEAM,H #H-shaped steel section SECDATA,200,200,8,12 LESIZE,ALL,300#division size 300mm LMESH,ALL It is worth noting that the above pseudocode cannot end with punctuation.

[0033] ③ Parameterization of boundary conditions: Foundation fixed constraint: full degree of freedom constraint at the bottom of the column (UX=UY=UZ=ROTX=ROTY=ROTZ=0).

[0034] Simplified component connections: MPC184 rigid elements are used to simulate bolt connections.

[0035] Wind load mapping: non-uniform wind pressure loading is achieved through the SFGRAD command.

[0036] Step S5: inputting the future wind speeds at all future moments into the parameterized model in the ANSYS environment, and obtaining a set of stress data based on a future wind speed.

[0037] Preferably, based on the above steps ① to ③: ④Dynamic mapping of wind load: Pressure distribution based on CFD data: *DIM,PRESSURE,TABLE,6,3 #6 areas × 3 components PRESSURE(1,1)=0.8,1.2,0.5... #headwind / crosswind / leewind coefficient SFGRAD,PRES,0,X,0,0.5# Gradient loading along the X axis ⑤ Solver optimization configuration: Solving the equation: EQSLV,SPARSE#Sparse matrix solver TIME,1#1 second physical time AUTOTS,ON#Automatic time step Step S6: adjusting the photovoltaic panel inclination angle of the parameterized model with a preset step size in the ANSYS environment, and obtaining a set of adjusted stress data based on the photovoltaic panel inclination angle after each adjustment.

[0038] Preferably, the automatic tilt angle scanning with a step length of 0.5° can be achieved by using a loop statement in the batch mode of ANSYS.

[0039] Step S7, obtaining the optimal photovoltaic panel tilt angle of the parameterized model through a global optimization algorithm so that the corresponding adjusted stress data reaches the maximum stress value, and defining the optimal photovoltaic panel tilt angle as the most unfavorable working condition.

[0040] Step S8: determine whether the adjusted stress data corresponding to the most unfavorable working condition exceeds the safety specification stress threshold. If so, execute step S9.

[0041] Preferably, the safety specification stress threshold is set according to the material of the photovoltaic bracket. For example, a parametric model is established in ANSYS, the main beam adopts BEAM188 unit (E=206GPa), and the loading is carried out according to the combination of 1.2DL+1.4WL. The most unfavorable working condition (such as the 58° inclination wind suction condition) is screened, and the maximum stress of Q235 steel is verified to be ≤156MPa (0.66σs). Here, 156MPa (0.66σs) is the safety specification stress threshold.

[0042] Step S9: determining whether the photovoltaic bracket has a risk of irreversible deformation.

[0043] Furthermore, in step S9, it is determined whether the photovoltaic bracket has the risk of irreversible deformation, and then the following steps are also included: Step S10: Obtain a future timestamp when the irreversible deformation risk first occurs, and define it as a possible risk timestamp.

[0044] Step S20: Obtain the future wind speed and the corresponding photovoltaic panel tilt angle corresponding to the possible risk timestamp, and package them into a risk data packet.

[0045] Step S30: Send the risk data packet to an external monitoring terminal.

[0046] Furthermore, in step S9, it is determined whether the photovoltaic bracket has the risk of irreversible deformation, and then the following steps are also included: Step S100 , constructing a stress interval with a zero value as the minimum value of the stress interval and a maximum value of the stress interval as the maximum value of the stress interval.

[0047] Step S200: Divide the stress interval into several sub-intervals.

[0048] In step S300 , a visible light color is assigned based on each subinterval, and the color temperature of each visible light color increases as the value of each subinterval increases.

[0049] Preferably, the color temperature of the visible light may be increased from blue to red.

[0050] Step S400 : generating a visual animation of all parameterized models along the time course of all future moments.

[0051] Step S500 , obtaining the stress data or the subinterval corresponding to the adjusted stress data of each parameterizable model, and the corresponding visible light color.

[0052] Step S600 , filling visible light color into each corresponding parameterizable model to obtain a dyeing visualization animation.

[0053] Step S700: sending the dyeing visualization animation to an external visualization terminal.

[0054] Furthermore, in step S700, the dyeing visualization animation is sent to an external visualization terminal, and then the following steps are also included: Step S1000 : In response to a touch operation from an external visualization terminal, start displaying a visualization animation.

[0055] Step S2000: Identify the operation type of the touch operation and enable different demonstration effects based on different operation types.

[0056] Preferably, the demonstration effects include touch operations such as play, pause, fast forward, rewind, and touch. Play, pause, fast forward, and rewind can realize dynamic operations for visual animation, and touch can highlight the model components at different touch positions according to different touch positions. For example, if a photovoltaic panel is used, the photovoltaic panel will be highlighted and the corresponding parameters of the photovoltaic panel will be displayed.

[0057] Furthermore, step S2, all wind speeds and all wind directions are trained and learned by a machine learning machine to obtain a wind speed prediction model and a wind direction prediction model, respectively, which specifically includes the following steps: Step S21: All wind speeds are integrated into one data set.

[0058] Step S22: Divide the dataset into a training set, a validation set, and a test set according to a preset ratio.

[0059] Preferably, the preset ratio is 70:15:15, that is, 70% training set, 15% validation set, and 15% test set.

[0060] Step S23: defining a neural network model.

[0061] Preferably, two hidden layers may be used, that is, the input layer, the first hidden layer, the second hidden layer, and the output layer are sequentially signal-connected.

[0062] In step S24, the training set is trained using a neural network model, and the weights and biases of the neural network model are updated using a back propagation algorithm based on the training results and the loss function of the validation set.

[0063] Step S25, repeat step S24 several times until the loss function reaches a minimum value.

[0064] Step S26: Obtain a neural network model corresponding to the minimum value of the loss function and define it as a wind speed prediction model.

[0065] In step S27, steps S21 to S26 are repeatedly executed with all wind directions as the execution subject to obtain a wind direction prediction model.

[0066] It can be understood that the neural network training of this embodiment mainly includes the following ideas: ① Initialize the weights and bias items in the network.

[0067] Initializing the 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.

[0068] ②Activate forward propagation to obtain the output value of each layer and the expected value of the loss function of each layer.

[0069] ③ According to the loss function, calculate the error term of the output unit and the error term of the hidden unit.

[0070] Compute various errors, calculate the gradient of the parameters with respect to the loss function, or calculate partial derivatives using the chain rule of calculus. For partial derivatives of vectors or matrices within a composite function, always multiply the composite function's inner functions with the left derivative. For partial derivatives of scalars within a composite function, either multiply the composite function's inner functions with the right derivative can be used.

[0071] ④Update the weights and bias items in the neural network.

[0072] ⑤ Repeat ②~④ until the loss function is less than the preset bias or the number of iterations is exhausted, and the parameters output at this time are the current optimal parameters.

[0073] Furthermore, step S3 predicts the future wind speed and future wind direction at the same future moment using the wind speed prediction model and the wind direction prediction model, and combines them into the future wind speed at the same future moment, specifically including the following steps: Step S31: input the test set corresponding to the wind speed into the wind speed prediction model.

[0074] Step S32: Obtain the future wind speed at the next future moment through forward propagation of the wind speed prediction model.

[0075] Step S33: The future wind speed at the next future moment is used as the iteration subject to input the wind speed prediction model, and step S32 is repeatedly executed to obtain several future wind speeds.

[0076] In step S34, the test set corresponding to the wind direction is input into the wind direction prediction model.

[0077] Step S35, obtaining the future wind direction at the next future moment through forward propagation of the wind direction prediction model.

[0078] Step S36: The future wind direction at the next future moment is used as the iteration subject to input the wind direction prediction model, and step S35 is repeatedly executed to obtain several future wind directions.

[0079] Step S37: combining the future wind speed and the future wind direction at the same future moment into the future wind speed.

[0080] Furthermore, in step S7, the optimal photovoltaic panel tilt angle of the parameterized model is obtained by a global optimization algorithm so that the corresponding adjusted stress data reaches the maximum stress value, and the optimal photovoltaic panel tilt angle is defined as the most unfavorable working condition, including: Step S71 : randomly generating a number of random solutions based on the optimal photovoltaic panel tilt angle.

[0081] Step S72: defining the optimization result of all random solutions as the corresponding adjusted stress data reaching the maximum stress value.

[0082] Step S73: Initialize the position of each random solution.

[0083] Step S74: Update the current position and current speed of each random solution respectively.

[0084] Step S75: Obtain the individual optimal solution and the global optimal solution of each random solution based on each update.

[0085] Step S76: Determine whether the fitness value of each individual optimal solution and each global optimal solution no longer changes. If yes, execute step S77.

[0086] Step S77: determining whether the optimal solution for the optimal photovoltaic panel tilt angle has been obtained.

[0087] Preferably, the principles of steps S71 to S77 are as follows: ① Initialize the particle swarm: ‌Number of Particles‌: Sets the number of particles in the swarm (usually 20-50).

[0088] ‌Position and Velocity‌: Randomly initialize the position (solution) and velocity of each particle.

[0089] Individual Optimum (pBest): The initial position of each particle is the individual optimal solution.

[0090] ‌Global Best (gBest): Select the global best solution from all individual best solutions.

[0091] ②Assessing fitness: The fitness value of each particle (i.e., the quality of the solution) is calculated according to the objective function. The fitness value can be evaluated by one of the Griewank function, Rastrigin function, Schaffer function, Ackley function, and Rosenbrock function.

[0092] ③ Update individual optimality and global optimality: ‌Individual Best Update‌: If the fitness of the current particle is better than its individual best, update pBest.

[0093] ‌Global Best Update‌: If the fitness of a particle is better than the global best, update gBest.

[0094] ④‌ Update speed and location: Particle velocity updates.

[0095] Particle position updates.

[0096] ⑤ Check termination conditions: If the termination condition is met (such as reaching the maximum number of iterations, the fitness value is small enough or does not change much), the algorithm stops and outputs the global optimal solution; otherwise, return to ② and continue iterating.

[0097] ⑥ Output: Output the global optimal solution (gBest) as the final result.

[0098] This embodiment obtains a number of ground wind speed data in a preset area based on a preset detection interval, and each wind speed data includes a wind speed and a wind direction; all wind speeds and all wind directions are trained and learned separately by a machine learning machine to obtain a wind speed prediction model and a wind direction prediction model respectively; the future wind speed and future wind direction at the same future moment are predicted by the wind speed prediction model and the wind direction prediction model, and are merged into the future wind speed at the same future moment; the structural data of the photovoltaic bracket is obtained and a parameterized model is established in ANSYS; the future wind speeds at all future moments are input into the parameterized model in the ANSYS environment, and a set of stress data is obtained based on a future wind speed; the photovoltaic panel inclination angle of the parameterized model is adjusted with a preset step size in the ANSYS environment, and a set of adjusted stress data is obtained based on the photovoltaic panel inclination angle after each adjustment; the optimal photovoltaic panel inclination angle of the parameterized model is obtained by a global optimization algorithm, so that the corresponding adjusted stress data reaches the maximum stress value, and the optimal photovoltaic panel inclination angle is defined as the most unfavorable working condition; it is determined whether the adjusted stress data corresponding to the most unfavorable working condition exceeds the safety specification stress threshold, and if so, it is determined that the photovoltaic bracket has an irreversible deformation risk. This embodiment improves the accuracy and economy of the wind-resistant design of photovoltaic brackets through multimodal data fusion and intelligent algorithm iteration. First, the wind speed / wind direction separation modeling based on machine learning breaks through the limitations of traditional static wind pressure calculations and effectively improves the accuracy of extreme wind condition predictions; second, the parameterized model is linked with the global optimization algorithm to automatically locate non-explicit dangerous working conditions such as a 52° inclination angle, which is significantly more efficient than manual calculations; finally, the stress threshold dynamic warning mechanism realizes the transition from passive verification to active defense.

[0099] like Figure 2 As shown, this embodiment provides an embodiment of a photovoltaic support structure strength analysis system based on wind load. In this embodiment, the photovoltaic support structure strength analysis system is applied to the photovoltaic support structure strength analysis method of the above embodiment.

[0100] Specifically, the photovoltaic support structural member strength analysis system includes a ground wind speed data acquisition module 1, a ground wind speed data learning module 2, a future wind speed data prediction module 3, a parameterized model establishment module 4, a stress data acquisition module 5, a photovoltaic panel inclination adjustment module 6, a photovoltaic panel inclination optimization module 7, a most unfavorable working condition judgment module 8, and an irreversible deformation risk judgment module 9, which are electrically connected in sequence.

[0101] Among them, the ground wind speed data acquisition module 1 is used to obtain a number of ground wind speed data in a preset area based on a preset detection interval, and each wind speed data includes a wind speed rate and a wind direction; the ground wind speed data learning module 2 is used to train and learn all wind speeds and all wind directions respectively through a machine learning machine, and obtain a wind speed prediction model and a wind direction prediction model respectively; the future wind speed data prediction module 3 is used to predict the future wind speed and future wind direction at the same future moment through the wind speed prediction model and the wind direction prediction model, and merge them into the future wind speed at the same future moment; the parameterized model establishment module 4 is used to obtain the structural data of the photovoltaic bracket and establish a parameterized model in ANSYS; the stress data acquisition module 5 is used to The future wind speeds at all future moments are input into the parameterized model, and a set of stress data is obtained based on a future wind speed; the photovoltaic panel tilt angle adjustment module 6 is used to adjust the photovoltaic panel tilt angle of the parameterized model with a preset step size in the ANSYS environment, and a set of adjusted stress data is obtained based on the photovoltaic panel tilt angle after each adjustment; the photovoltaic panel tilt angle optimization module 7 is used to obtain the optimal photovoltaic panel tilt angle of the parameterized model through a global optimization algorithm, so that the corresponding adjusted stress data reaches the maximum stress value, and the optimal photovoltaic panel tilt angle is defined as the most unfavorable working condition; the most unfavorable working condition judgment module 8 is used to judge whether the adjusted stress data corresponding to the most unfavorable working condition exceeds the safety specification stress threshold; the irreversible deformation risk judgment module 9 is used to judge whether the photovoltaic bracket has the risk of irreversible deformation if so.

[0102] Furthermore, the photovoltaic support structural member strength analysis system includes a risk possible timestamp definition module, a risk data packet packaging module, and a risk data packet sending module that are electrically connected in sequence; the risk possible timestamp definition module is electrically connected to the irreversible deformation risk determination module 9.

[0103] Among them, the risk possible timestamp definition module is used to obtain the future timestamp when the irreversible deformation risk first occurs, and define it as the risk possible timestamp; the risk data packet packaging module is used to obtain the future wind speed corresponding to the risk possible timestamp and the corresponding photovoltaic panel inclination angle, and package them into a risk data packet; the risk data packet sending module is used to send the risk data packet to the external monitoring end.

[0104] Furthermore, the photovoltaic support structural member strength analysis system includes a stress interval construction module, a stress interval equalization module, a visible light color assignment module, a visualization animation generation module, a visible light color matching module, a visible light color filling module, and a dyeing visualization animation sending module, which are electrically connected in sequence; the stress interval construction module is electrically connected to the irreversible deformation risk judgment module 9.

[0105] Among them, the stress interval construction module is used to construct the stress interval with zero as the minimum value of the stress interval and the stress maximum value as the maximum value of the stress interval; the stress interval equalization module is used to divide the stress interval into several sub-intervals; the visible light color assignment module is used to assign a visible light color based on each sub-interval, and the color temperature of each visible light color increases as the value of each sub-interval increases; the visualization animation generation module is used to generate visualization animations for all parameterized models along the time process of all future moments; the visible light color matching module is used to obtain the stress data or the sub-interval corresponding to the adjusted stress data of each parameterizable model, as well as the corresponding visible light color; the visible light color filling module is used to fill the visible light color into each corresponding parameterizable model to obtain a dyed visualization animation; the dyed visualization animation sending module is used to send the dyed visualization animation to an external visualization terminal.

[0106] Furthermore, the photovoltaic support structural member strength analysis system includes a touch operation response module and a touch operation execution module that are electrically connected in sequence; the touch operation response module is electrically connected to the dyeing visualization animation sending module.

[0107] Among them, the touch operation response module is used to respond to the touch operation from the external visualization terminal and start displaying the visualization animation; the touch operation execution module is used to identify the operation type of the touch operation and start different demonstration effects based on different operation types.

[0108] Furthermore, the ground wind speed data learning module 2 specifically includes a first ground wind speed data learning unit, a second ground wind speed data learning unit, a third ground wind speed data learning unit, a fourth ground wind speed data learning unit, a fifth ground wind speed data learning unit, a sixth ground wind speed data learning unit, and a seventh ground wind speed data learning unit, which are electrically connected in sequence; the first ground wind speed data learning unit is electrically connected to the ground wind speed data acquisition module 1, and the seventh ground wind speed data learning unit is electrically connected to the future wind speed data prediction module 3.

[0109] Among them, the first ground wind speed data learning unit is used to integrate all wind speeds into a data set; the second ground wind speed data learning unit is used to divide the data into a training set, a validation set, and a test set according to a preset ratio; the third ground wind speed data learning unit is used to define a neural network model; the fourth ground wind speed data learning unit is used to train the training set through the neural network model, and update the weights and biases of the neural network model through the back propagation algorithm based on the training results and the loss function of the validation set; the fifth ground wind speed data learning unit is used to repeatedly execute the fourth ground wind speed data learning unit several times until the loss function reaches a minimum value; the sixth ground wind speed data learning unit is used to obtain the neural network model corresponding to the minimum value of the loss function and define it as a wind speed prediction model; the seventh ground wind speed data learning unit is used to repeatedly execute the first ground wind speed data learning unit to the sixth ground wind speed data learning unit with all wind directions as the execution body to obtain a wind direction prediction model.

[0110] Furthermore, the future wind speed data prediction module 3 specifically includes a first future wind speed data prediction unit, a second future wind speed data prediction unit, a third future wind speed data prediction unit, a fourth future wind speed data prediction unit, a fifth future wind speed data prediction unit, a sixth future wind speed data prediction unit, and a seventh future wind speed data prediction unit, which are electrically connected in sequence; the first future wind speed data prediction unit is electrically connected to the seventh ground wind speed data learning unit, and the seventh future wind speed data prediction unit is electrically connected to the parameterized model establishment module 4.

[0111] Among them, the first future wind speed data prediction unit is used to input the test set corresponding to the wind speed into the wind speed prediction model; the second future wind speed data prediction unit is used to obtain the future wind speed at the next future moment through forward propagation of the wind speed prediction model; the third future wind speed data prediction unit is used to input the future wind speed at the next future moment as the iterative body into the wind speed prediction model, repeatedly execute the second future wind speed data prediction unit, and obtain several future wind speeds; the fourth future wind speed data prediction unit is used to input the test set corresponding to the wind direction into the wind direction prediction model; the fifth future wind speed data prediction unit is used to obtain the future wind direction at the next future moment through forward propagation of the wind direction prediction model; the sixth future wind speed data prediction unit is used to input the future wind direction at the next future moment as the iterative body into the wind direction prediction model, repeatedly execute the fifth future wind speed data prediction unit, and obtain several future wind directions; the seventh future wind speed data prediction unit is used to merge the future wind speed and future wind direction at the same future moment into the future wind speed.

[0112] Furthermore, the photovoltaic panel tilt angle optimization module 7 specifically includes a first photovoltaic panel tilt angle optimization unit, a second photovoltaic panel tilt angle optimization unit, a third photovoltaic panel tilt angle optimization unit, a fourth photovoltaic panel tilt angle optimization unit, a fifth photovoltaic panel tilt angle optimization unit, a sixth photovoltaic panel tilt angle optimization unit, and a seventh photovoltaic panel tilt angle optimization unit, which are electrically connected in sequence; the first photovoltaic panel tilt angle optimization unit is electrically connected to the photovoltaic panel tilt angle adjustment module 6, and the seventh photovoltaic panel tilt angle optimization unit is electrically connected to the most unfavorable working condition judgment module 8.

[0113] Among them, the first photovoltaic panel tilt angle optimization unit is used to randomly generate a number of random solutions based on the optimal photovoltaic panel tilt angle; the second photovoltaic panel tilt angle optimization unit is used to define the optimization results of all random solutions as the corresponding adjusted stress data reaching the maximum stress value; the third photovoltaic panel tilt angle optimization unit is used to initialize the position of each random solution; the fourth photovoltaic panel tilt angle optimization unit is used to update the current position and current speed of each random solution respectively; the fifth photovoltaic panel tilt angle optimization unit is used to obtain the individual optimal solution and the global optimal solution of each random solution based on each update; the sixth photovoltaic panel tilt angle optimization unit is used to determine whether the fitness value of each individual optimal solution and each global optimal solution no longer changes; the seventh photovoltaic panel tilt angle optimization unit is used to determine that the optimal solution with the optimal photovoltaic panel tilt angle has been obtained if both are yes.

[0114] It should be noted that this embodiment is a functional module embodiment based on the above method embodiment. The optimization, expansion, limitation, example, and principle description of this embodiment can be referred to the above embodiment, and will not be repeated in this embodiment.

[0115] This embodiment obtains a number of ground wind speed data in a preset area based on a preset detection interval, and each wind speed data includes a wind speed and a wind direction; all wind speeds and all wind directions are trained and learned separately by a machine learning machine to obtain a wind speed prediction model and a wind direction prediction model respectively; the future wind speed and future wind direction at the same future moment are predicted by the wind speed prediction model and the wind direction prediction model, and are merged into the future wind speed at the same future moment; the structural data of the photovoltaic bracket is obtained and a parameterized model is established in ANSYS; the future wind speeds at all future moments are input into the parameterized model in the ANSYS environment, and a set of stress data is obtained based on a future wind speed; the photovoltaic panel inclination angle of the parameterized model is adjusted with a preset step size in the ANSYS environment, and a set of adjusted stress data is obtained based on the photovoltaic panel inclination angle after each adjustment; the optimal photovoltaic panel inclination angle of the parameterized model is obtained by a global optimization algorithm, so that the corresponding adjusted stress data reaches the maximum stress value, and the optimal photovoltaic panel inclination angle is defined as the most unfavorable working condition; it is determined whether the adjusted stress data corresponding to the most unfavorable working condition exceeds the safety specification stress threshold, and if so, it is determined that the photovoltaic bracket has an irreversible deformation risk. This embodiment improves the accuracy and economy of the wind-resistant design of photovoltaic brackets through multimodal data fusion and intelligent algorithm iteration. First, the wind speed / wind direction separation modeling based on machine learning breaks through the limitations of traditional static wind pressure calculations and effectively improves the accuracy of extreme wind condition predictions; second, the parameterized model is linked with the global optimization algorithm to automatically locate non-explicit dangerous working conditions such as a 52° inclination angle, which is significantly more efficient than manual calculations; finally, the stress threshold dynamic warning mechanism realizes the transition from passive verification to active defense.

[0116] 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.

[0117] The memory 102 stores program instructions for implementing the wind load-based photovoltaic support structure strength analysis method of any of the above embodiments.

[0118] The processor 101 is configured to execute program instructions stored in the memory 102 to perform a strength analysis of photovoltaic support structure components based on wind loads.

[0119] Processor 101 may also be referred to as a CPU (Central Processing Unit). Processor 101 may be an integrated circuit chip with data processing capabilities. 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 device, a discrete gate or transistor logic device, or a discrete hardware component. A general-purpose processor may be a microprocessor or any conventional processor.

[0120] Further, Figure 4 This is a schematic diagram of the structure of a storage medium in an embodiment of the present application. The storage medium 11 in the embodiment of the present application stores program instructions 111 that can implement all of the above methods, wherein the program instructions 111 can be stored in the above storage medium in the form of a software product, including a number of instructions for causing 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 method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program code, 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, server, mobile phone, and tablet.

[0121] In the several embodiments provided in this application, it should be understood that the disclosed systems, systems and methods can be implemented in other ways. For example, the system 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 through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0122] In addition, the functional units in the various embodiments 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-mentioned integrated units 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 description and drawings of this application, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

[0123] The above detailed description of the specific embodiments of the present application is intended only as an example, and the present application is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modifications or substitutions made to the present application are also within the scope of the present application. Therefore, equivalent changes, modifications, and improvements made without departing from the spirit and scope of the present application should be included within the scope of the present application.

Claims

1. A photovoltaic support structure strength analysis method based on wind load, wherein the photovoltaic support structure strength analysis method is applied to photovoltaic supports that have been installed in a preset area, and is characterized in that: The photovoltaic support structural member strength analysis method includes: Step S1, obtaining a plurality of ground wind speed data within the preset area based on a preset detection interval, each wind speed data including a wind speed and a wind direction; Step S2: training and learning all wind speeds and all wind directions by a machine learning machine to obtain a wind speed prediction model and a wind direction prediction model respectively; Step S3, predicting the future wind speed and future wind direction at the same future moment by using the wind speed prediction model and the wind direction prediction model, and combining them into the future wind speed at the same future moment; Step S4, obtaining structural data of the photovoltaic support and establishing a parameterized model in ANSYS; Step S5, inputting the future wind speeds at all future moments into the parameterized model in the ANSYS environment, and obtaining a set of stress data based on a future wind speed; Step S6, adjusting the photovoltaic panel inclination angle of the parameterized model with a preset step size in the ANSYS environment, and obtaining a set of adjusted stress data based on the photovoltaic panel inclination angle after each adjustment; Step S7, obtaining the optimal photovoltaic panel tilt angle of the parameterized model through a global optimization algorithm so that the corresponding adjusted stress data reaches the maximum stress value, and defining the optimal photovoltaic panel tilt angle as the most unfavorable working condition; Step S8, determining whether the adjusted stress data corresponding to the most unfavorable working condition exceeds the safety specification stress threshold, if so, executing step S9; Step S9: determining whether the photovoltaic bracket has a risk of irreversible deformation.

2. The photovoltaic support structure strength analysis method according to claim 1, characterized in that: Step S9, determining whether the photovoltaic bracket has irreversible deformation risk, then includes: Step S10, obtaining a future timestamp when the irreversible deformation risk first occurs, and defining it as a possible risk timestamp; Step S20, obtaining the future wind speed and the corresponding photovoltaic panel tilt angle corresponding to the possible risk timestamp, and packaging them into a risk data packet; Step S30: sending the risk data packet to an external monitoring terminal.

3. The photovoltaic support structure strength analysis method according to claim 1, characterized in that: Step S9, determining whether the photovoltaic bracket has irreversible deformation risk, then includes: Step S100, constructing a stress interval with a zero value as the minimum value of the stress interval and the maximum stress value as the maximum value of the stress interval; Step S200, dividing the stress interval into a plurality of sub-intervals; Step S300 , assigning a visible light color based on each subinterval, wherein the color temperature of each visible light color increases as the value of each subinterval increases; Step S400 , generating a visual animation of all parameterized models along the time course of all future moments; Step S500 , obtaining the stress data or the subinterval corresponding to the adjusted stress data of each parameterizable model, and the corresponding visible light color; Step S600, filling visible light color into each corresponding parameterizable model to obtain a dyeing visualization animation; Step S700: sending the dyeing visualization animation to an external visualization terminal.

4. The photovoltaic support structure strength analysis method according to claim 3, characterized in that: Step S700, sending the dyeing visualization animation to an external visualization terminal, then includes: Step S1000, in response to a touch operation from an external visualization terminal, starting to display the visualization animation; Step S2000: identifying the operation type of the touch operation and enabling different demonstration effects based on different operation types.

5. The photovoltaic support structure strength analysis method according to claim 1, characterized in that: Step S2: training and learning all wind speeds and all wind directions by a machine learning machine to obtain a wind speed prediction model and a wind direction prediction model, respectively, including: Step S21, integrating all wind speeds into one data set; Step S22: Divide the data into a training set, a validation set, and a test set according to a preset ratio; Step S23, defining a neural network model; Step S24, training the training set through the neural network model, and updating the weights and biases of the neural network model through a back propagation algorithm based on the training results and the loss function of the validation set; Step S25, repeating step S24 several times until the loss function reaches a minimum value; Step S26, obtaining a neural network model corresponding to the minimum value of the loss function and defining it as the wind speed prediction model; In step S27, steps S21 to S26 are repeatedly executed with all wind directions as the execution subject to obtain a wind direction prediction model.

6. The photovoltaic support structure strength analysis method according to claim 5, characterized in that: Step S3, predicting the future wind speed and future wind direction at the same future moment by using the wind speed prediction model and the wind direction prediction model, and merging them into the future wind speed at the same future moment, including: Step S31, inputting the test set corresponding to the wind speed into the wind speed prediction model; Step S32, obtaining the future wind speed at the next future moment through forward propagation of the wind speed prediction model; Step S33, using the future wind speed at the next future moment as an iteration subject to input the wind speed prediction model, and repeatedly executing step S32 to obtain a plurality of future wind speeds; Step S34, inputting the test set corresponding to the wind direction into the wind direction prediction model; Step S35, obtaining the future wind direction at the next future moment through forward propagation of the wind direction prediction model; Step S36, taking the future wind direction at the next future moment as the iteration subject and inputting the wind direction prediction model, and repeating step S35 to obtain a plurality of future wind directions; Step S37: Combine the future wind speed and future wind direction at the same future moment into the future wind speed.

7. The photovoltaic support structure strength analysis method according to claim 1, characterized in that: Step S7, obtaining the optimal photovoltaic panel tilt angle of the parameterized model through a global optimization algorithm so that the corresponding adjusted stress data reaches the maximum stress value, and defining the optimal photovoltaic panel tilt angle as the most unfavorable working condition, including: Step S71, randomly generating a plurality of random solutions based on the optimal photovoltaic panel tilt angle; Step S72, defining the optimization result of all random solutions as the corresponding adjusted stress data reaching the maximum stress value; Step S73, initializing the position of each random solution; Step S74, updating the current position and current speed of each random solution respectively; Step S75, obtaining the individual optimal solution and the global optimal solution of each random solution based on each update; Step S76, respectively determine whether the fitness value of each individual optimal solution and each global optimal solution no longer changes. If yes, proceed to step S77; Step S77: determining whether the optimal solution for the optimal photovoltaic panel tilt angle has been obtained.

8. A photovoltaic support structure strength analysis system based on wind load, wherein the photovoltaic support structure strength analysis system is applied to the photovoltaic support structure strength analysis method according to any one of claims 1 to 7, characterized in that: The photovoltaic support structure strength analysis system includes: A ground wind speed data acquisition module, configured to acquire a plurality of ground wind speed data within the preset area based on a preset detection interval, each wind speed data including a wind speed and a wind direction; The ground wind speed data learning module is used to train and learn all wind speeds and all wind directions through a machine learning machine to obtain a wind speed prediction model and a wind direction prediction model respectively; A future wind speed data prediction module is used to predict the future wind speed and future wind direction at the same future moment by using the wind speed prediction model and the wind direction prediction model, and combine them into the future wind speed at the same future moment; A parameterized model building module, used to obtain structural data of the photovoltaic support and build a parameterized model in ANSYS; A stress data acquisition module is used to input the future wind speeds at all future moments into the parameterized model in an ANSYS environment, and obtain a set of stress data based on a future wind speed; A photovoltaic panel tilt adjustment module is used to adjust the photovoltaic panel tilt of the parameterized model with a preset step size in an ANSYS environment, and obtain a set of adjusted stress data based on the photovoltaic panel tilt after each adjustment; A photovoltaic panel tilt optimization module is used to obtain the optimal photovoltaic panel tilt of the parameterized model through a global optimization algorithm so that the corresponding adjusted stress data reaches the maximum stress value, and the optimal photovoltaic panel tilt is defined as the most unfavorable working condition; A most unfavorable working condition judgment module is used to judge whether the adjusted stress data corresponding to the most unfavorable working condition exceeds the safety specification stress threshold; The irreversible deformation risk determination module is used to determine whether the photovoltaic bracket has the risk of irreversible deformation if so.

9. 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 photovoltaic support structure strength analysis method according to any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores program instructions, and when the program instructions are executed by the processor, the photovoltaic support structure component strength analysis method according to any one of claims 1 to 7 can be implemented.

Images