A photovoltaic array design simulation and optimization method

Abstract

The present invention discloses a photovoltaic array design simulation optimization method, which relates to the technical field of intelligent photovoltaic system optimization, including: designing a photovoltaic array in a herringbone shape and constructing a photovoltaic array three-dimensional model; performing multi-physics field coupling simulation settings based on the photovoltaic array three-dimensional model, computer domain and boundary conditions; training a machine learning model using historical data to predict the interaction between different physical fields, and identifying key areas that require higher grid density according to the conditions of the multi-physics field coupling simulation settings; dynamically adjusting the grid density according to the identified key areas; using the adjusted grid density to run a multi-physics field coupling simulation to evaluate the performance of the photovoltaic array; and adjusting the design of the photovoltaic array according to the evaluation results. The present invention uses herringbone design and multi-physics field simulation, combined with machine learning to optimize the grid, to comprehensively evaluate and improve the performance of the photovoltaic array, promote photovoltaic technology innovation, and effectively reduce costs.

Description

Technical Field

[0001] The invention relates to the technical field of intelligent photovoltaic system optimization, and in particular to a photovoltaic array design simulation optimization method. Background Art

[0002] In recent years, with the improvement of computing power and the advancement of multi-physics simulation technology, photovoltaic array design has entered a refined stage, and advanced numerical simulation methods such as CFD (computational fluid dynamics) and FEA (finite element analysis) have been widely used to accurately predict the performance of photovoltaic arrays in actual operating environments. Especially in the field of multi-physics coupling simulation, researchers are committed to building a comprehensive model that not only considers fluid dynamics, but also incorporates thermodynamics and structural mechanics. In addition, with the rise of big data and artificial intelligence technology, machine learning algorithms have been introduced into the field of photovoltaic array design to predict and optimize the performance of photovoltaic systems, further improving the efficiency and accuracy of the design.

[0003] Although existing technologies have made significant progress in photovoltaic array design, some limitations still exist. Traditional design methods are often based on static models and simplified assumptions, which cannot fully reflect the impact of dynamically changing environmental conditions on the performance of photovoltaic arrays. For example, fluctuations in wind speed and direction, periodic changes in temperature, seasonal differences in solar radiation intensity, etc., all of these factors will significantly affect the power generation efficiency and structural safety of photovoltaic arrays. In addition, when dealing with multi-physics field coupling problems, although existing technologies can simulate fluid dynamics, thermodynamics, and structural mechanics separately, they still face challenges in integrating these models to achieve efficient and accurate coupling analysis. In particular, how to reasonably allocate computing resources in a large-scale computing domain to ensure the simulation accuracy of key areas while controlling the overall computing cost is an urgent problem to be solved. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a photovoltaic array design simulation optimization method to solve the problem of inaccurate photovoltaic array performance prediction caused by dynamic environmental changes and low efficiency of multi-physical field coupling analysis in the prior art.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a photovoltaic array design simulation optimization method, which includes designing a photovoltaic array in a herringbone shape and constructing a three-dimensional model of the photovoltaic array; defining a computational domain according to the size of the photovoltaic array and the surrounding environment, and setting boundary conditions; performing a multi-physics field coupling simulation setting based on the three-dimensional model of the photovoltaic array, the computer domain, and the boundary conditions; using historical data to train a machine learning model to predict the interaction between different physical fields, and according to the conditions of the multi-physics field coupling simulation setting, identifying key areas that require a higher grid density; dynamically adjusting the grid density according to the identified key areas; using the adjusted grid density to run a multi-physics field coupling simulation to evaluate the performance of the photovoltaic array; and adjusting the design of the photovoltaic array according to the evaluation results.

[0008] As a preferred solution of the photovoltaic array design simulation optimization method of the present invention, wherein: the photovoltaic array is designed in a herringbone shape and a photovoltaic panel structure model diagram is constructed, and the specific steps are as follows:

[0009] Use SolidWorks to create the geometry of the photovoltaic panel, use a herringbone design for the photovoltaic panel structure, and design the array layout in the form of m×n, where m represents the number of rows and n represents the number of columns;

[0010] Define size parameters based on the specifications of the photovoltaic panels, power output requirements, and installation space limitations;

[0011] Define material properties according to industry standards and take into account the effects of temperature changes;

[0012] Assemble the completed individual photovoltaic panels into a complete photovoltaic array three-dimensional model;

[0013] As a preferred solution of the photovoltaic array design simulation optimization method of the present invention, wherein: a calculation domain is defined according to the size of the photovoltaic array and the surrounding environment, and boundary conditions are set, and the specific steps are as follows:

[0014] According to the size of the photovoltaic array, define a computational domain that is much larger than the boundary of the photovoltaic array to reduce the impact of boundary conditions on the simulation results;

[0015] Use an exponential wind profile to define velocity boundary conditions at the inlet boundary;

[0016] The outlet boundary adopts free outflow boundary condition, allowing the fluid to leave the computational domain freely;

[0017] No-slip wall boundary conditions are used at the bottom of the computational domain and on the surface of the photovoltaic array to simulate the interaction between the solid surface and the flowing medium;

[0018] As a preferred solution of the photovoltaic array design simulation optimization method of the present invention, wherein: the multi-physical field coupling simulation setting is performed based on the photovoltaic array three-dimensional model, computer domain and boundary conditions, and the specific steps are as follows:

[0019] The fluid mechanics simulation conditions are established according to the target fluid behavior, geometric structure characteristics and boundary conditions, and the SSTk-ω turbulence model is selected as the basis for simulating wind loads;

[0020] By integrating the heat conduction model, the heat absorbed by the solar panel and the surrounding temperature changes are considered to set the mechanical simulation conditions, and the solar radiation intensity and ambient temperature are defined at the same time;

[0021] The structural mechanics simulation conditions are set by considering the elastic modulus and density of the photovoltaic panel material and its property evolution with temperature;

[0022] Integrate the simulation conditions of fluid mechanics, thermodynamics and structural mechanics to ensure the interaction between the physical fields, and enhance the stability and accuracy of the simulation by setting up coupling algorithms;

[0023] Configure solver parameters to precisely define the time step, number of iterations, and convergence criteria.

[0024] As a preferred solution of the photovoltaic array design simulation optimization method of the present invention, the machine learning model is trained using historical data to predict the interaction between different physical fields, and the key areas requiring higher grid density are identified according to the conditions set by the multi-physical field coupling simulation. The specific steps are as follows:

[0025] Historical data include wind speed and direction, ambient temperature and humidity information, time series of solar radiation intensity, and actual output power of photovoltaic panels under different environmental conditions;

[0026] Preprocess the collected historical data using outlier detection and cleaning, data cleaning, and data standardization;

[0027] Select LSTM in the deep learning model as the grid density prediction model;

[0028] The historical data is defined as X = {x1, x2, ..., x T} as the input sequence to train the LSTM model;

[0029] Use the trained LSTM model to predict the interaction between different physical fields. The expression is:

[0030]

[0031] Among them, P g represents the mesh density requirement for a specific area, wi is the weight of the interaction of the ith physical field, f i (X i ) is the function of the ith physical field interaction, N is the number of physical field interactions, B is the regulation function, g j (X j ) is the jth physical field function that affects the mesh density, M is the number of physical fields that affect the mesh density, θ is the set of model parameters, i represents the type of physical field interaction, j represents the physical field that directly affects the mesh density, and X i It is the data closely related to the specific physical field interaction extracted from the total input data set X;

[0032] As a preferred solution of the photovoltaic array design simulation optimization method of the present invention, the grid density is dynamically adjusted according to the identified key areas, and the specific steps are as follows:

[0033] Define a critical density threshold R, and compare the density demand forecast value P g Dynamically adjust the grid density based on the relationship with the critical density threshold R;

[0034] When P g When ≥R, it means that the grid density needs to be increased, and the local grid refinement algorithm is applied to divide each grid unit that needs to be refined into smaller sub-units;

[0035] When P g When <R, it means that the mesh density is sufficient and no further refinement is required;

[0036] Add a transition zone between the refined area and the non-refined area to smoothly transition through gradually changing mesh density and reduce simulation errors caused by mutations;

[0037] Add the new nodes and units generated after the local area grid is refined into the grid data structure to update the grid data structure;

[0038] As a preferred solution of the photovoltaic array design simulation optimization method of the present invention, wherein: the adjusted grid density is used to run a multi-physics field coupling simulation to evaluate the photovoltaic array performance, and the specific steps are as follows:

[0039] Adjust simulation conditions for fluid dynamics, thermodynamics, and structural mechanics based on new mesh densities;

[0040] A comprehensive evaluation function Pe is defined, and an implicit coupling algorithm is used to simulate the interaction between fluid mechanics, thermodynamics and structural mechanics to evaluate the effective performance of the photovoltaic array. The expression is:

[0041]

[0042] Among them, P e is the effective performance of the photovoltaic array, F w is the wind load on the photovoltaic array, I s is the solar radiation intensity, E is the elastic modulus of the photovoltaic panel material, ρ is the density of the photovoltaic panel material, T e is the ambient temperature, and β is the influence coefficient of temperature change on material properties.

[0043] As a preferred solution of the photovoltaic array design simulation optimization method of the present invention, wherein: the design solution of the photovoltaic array is adjusted according to the evaluation results, the specific steps are as follows:

[0044] According to the effective performance P of the photovoltaic array e The value of is used to judge the effective performance of the photovoltaic array;

[0045] When P e When it is positive, it means that the photovoltaic array is in an effective working state, and its performance increases with F w and I s The current parameter settings are maintained;

[0046] When P e When it is equal to zero, it means that the performance of the photovoltaic array has reached the critical point. At this time, F w and I s The effects on performance cancel each other out;

[0047] In-depth analysis leads to F w and I s The reasons for the mutually offsetting effects on performance are analyzed, and the design parameters of the photovoltaic array are adjusted according to the results of the analysis, including changing the orientation and tilt angle of the array and replacing the materials;

[0048] When P e When it is a negative value, it means that the performance of the photovoltaic array is affected. w Reach high strength levels with T e Commonly caused by high temperature;

[0049] Immediately check the physical condition of the PV array, replace damaged and overheated components, re-evaluate the structural design and cooling system of the PV array, and enhance the wind resistance design of the array and add heat dissipation devices;

[0050] In a second aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the photovoltaic array design simulation optimization method as described in the first aspect of the present invention is implemented.

[0051] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the photovoltaic array design simulation optimization method as described in the first aspect of the present invention is implemented.

[0052] The beneficial effects of the present invention are as follows: through herringbone design and SolidWorks modeling, a photovoltaic array model with stable structure and strong wind resistance is constructed, and appropriate calculation domains and boundary conditions are defined to ensure the accuracy of the simulation environment and the minimization of boundary effects. Multi-physics field coupling simulation is used to combine fluid mechanics, thermodynamics and structural mechanics to comprehensively evaluate the performance of photovoltaic arrays under different conditions. Through machine learning models, the interaction between physical fields is predicted, and the grid density of key areas is intelligently identified and dynamically adjusted, which improves the simulation accuracy and calculation efficiency. The design of the photovoltaic array is adjusted according to the evaluation results to ensure that the photovoltaic array can maintain the best working state and energy conversion efficiency under various environmental conditions. The entire process integrates advanced simulation technology and data analysis methods, which greatly improves the scientificity and economy of photovoltaic array design, and is of great significance to promoting technological innovation in the photovoltaic industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0054] Figure 1 This is a flow chart of the photovoltaic array design simulation optimization method in Example 1.

[0055] Figure 2 This is a flow chart for dynamically adjusting the grid density in Example 1. DETAILED DESCRIPTION

[0056] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0057] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0058] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0059] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a photovoltaic array design simulation optimization method, comprising the following steps:

[0060] S1. Design a photovoltaic array in a herringbone shape and construct a three-dimensional model of the photovoltaic array.

[0061] Furthermore, SolidWorks was used to create the geometry of the photovoltaic panels, the photovoltaic panel structure was grouped in a herringbone design to improve wind resistance, and the array layout was designed in the form of m×n, where m represents the number of rows and n represents the number of columns;

[0062] Define the dimensional parameters (such as length, width, thickness, etc.) according to the specifications of the photovoltaic panels, power output requirements and installation space limitations, and ensure that the dimensional parameters meet industry standards and engineering design guidelines;

[0063] Define material properties (such as density, elastic modulus, thermal conductivity, etc.) according to industry standards and take into account the effects of temperature changes;

[0064] Assemble the completed individual photovoltaic panels into a complete photovoltaic array three-dimensional model;

[0065] It should also be explained that the dimensional parameter definition: the dimensional parameters of photovoltaic panels (such as length, width, thickness, etc.) are usually determined based on factors such as the specifications of the photovoltaic panels, power output requirements, and installation space limitations. These parameters need to comply with industry standards and engineering design guidelines to ensure that the photovoltaic panels can operate effectively in the intended environment.

[0066] Material property definition: The material properties used in PV panels (such as density, elastic modulus, thermal conductivity, etc.) should be defined according to the datasheets provided by the material suppliers or industry standards. These properties are crucial to simulate the behavior of PV panels under different environmental conditions, such as wind loads, temperature changes, etc.

[0067] SolidWorks is used to create photovoltaic panel geometry due to its excellent 3D modeling capabilities, precise dimensional control capabilities, intuitive user interface, and integrated engineering analysis tools. These features together ensure the accuracy, efficiency, and performance optimization of photovoltaic panel design, laying a solid foundation for subsequent simulation and manufacturing.

[0068] S2. Define a computational domain according to the size of the PV array and the surrounding environment, and set boundary conditions.

[0069] Furthermore, according to the size of the PV array, a computational domain much larger than the PV array boundary is defined to reduce the impact of boundary conditions on the simulation results;

[0070] For example, the size of the computational domain should be at least several times the maximum size of the PV array to ensure that boundary effects do not significantly affect the simulation results;

[0071] The velocity boundary condition at the inlet boundary is defined using an exponential wind profile, expressed as:

[0072]

[0073] Among them, U r is the reference score, z is the measured height, z r is the reference height, α is the ground roughness index, U(z) represents the wind speed at height z, and r represents the reference;

[0074] The outlet boundary adopts free outflow boundary condition, allowing the fluid to leave the computational domain freely;

[0075] No-slip wall boundary conditions are used at the bottom of the computational domain and on the surface of the photovoltaic array to simulate the interaction between the solid surface and the flowing medium;

[0076] It should also be noted that the no-slip wall boundary condition means that the velocity of the fluid at the solid wall must be equal to the velocity of the solid wall. In most cases, the solid wall is stationary, so the no-slip wall boundary condition means that the velocity of the fluid close to the wall is zero.

[0077] The free outflow boundary condition means that at the outlet boundary of the computational domain, the fluid can flow out freely without being affected by additional constraints or pressure. This boundary condition is usually used to simulate the situation of an open system, where the fluid flow at the outlet is not affected by the flow inside the computational domain, that is, the fluid flow state at the outlet is considered to be the same as the fluid state at an infinite distance outside. The free outflow boundary condition allows the fluid to leave the computational domain naturally without applying additional pressure or velocity boundary conditions.

[0078] S3. Based on the PV array three-dimensional model, computer domain and boundary conditions, multi-physics field coupling simulation settings are performed.

[0079] Furthermore, the fluid mechanics simulation conditions were established according to the target fluid behavior, geometric structure characteristics and boundary conditions, and the SSTk-ω turbulence model was selected as the basis for simulating wind loads, because the SSTk-ω model has good performance in the near-wall area and is suitable for the simulation of complex flow fields;

[0080] By integrating the heat conduction model, the heat absorbed by the solar panel and the surrounding temperature changes are considered to set the mechanical simulation conditions, and the solar radiation intensity and ambient temperature are defined at the same time;

[0081] The structural mechanics simulation conditions are set by considering the elastic modulus and density of the photovoltaic panel material and its property evolution with temperature;

[0082] Integrate the simulation conditions of fluid mechanics, thermodynamics and structural mechanics to ensure the interaction between the physical fields, and enhance the stability and accuracy of the simulation by setting up coupling algorithms;

[0083] Configure solver parameters to precisely define the time step, number of iterations, and convergence criteria.

[0084] It should also be noted that the integrated heat conduction model is an important component of the multi-physics coupling simulation. It takes into account the heat generated by the solar panel due to the absorption of sunlight in the working state, as well as the influence of the ambient temperature on the temperature distribution of the photovoltaic panel. The heat conduction model simulates the temperature distribution inside and on the surface of the photovoltaic panel, as well as how the heat is conducted from the panel to the surrounding environment by solving the heat conduction equation.

[0085] The definition of solar radiation intensity and ambient temperature is based on the location of the photovoltaic array, season, time and meteorological conditions. 2 The unit of temperature depends on the latitude of the geographical location, the solar altitude angle and the duration of sunshine, as well as the atmospheric transparency and cloud cover. The ambient temperature reflects the local climatic conditions, including seasonal changes, day and night temperature differences, and wind speed.

[0086] Setting up a coupling algorithm refers to the mathematical and computational methods used in multi-physics coupling simulations to ensure that different physical phenomena can interact with each other and correctly transmit information. In the context of photovoltaic array design simulation and optimization, the role of the coupling algorithm is to coordinate the interdependencies between different physical fields such as fluid mechanics, thermodynamics, and structural mechanics, and to ensure that the solutions of each physical field can be updated consistently and synchronously during the simulation process.

[0087] S4. Use historical data to train machine learning models to predict the interactions between different physical fields and identify key areas that require higher mesh density based on the conditions set up in the multi-physics coupled simulation.

[0088] Furthermore, historical data include wind speed and direction, ambient temperature and humidity information, time series of solar radiation intensity, and actual output power of photovoltaic panels under different environmental conditions, including date, time, and environmental parameters;

[0089] Preprocess the collected historical data using outlier detection and cleaning, data cleaning, and data standardization;

[0090] Select LSTM in the deep learning model as the grid density prediction model;

[0091] The historical data is defined as X = {x1, x2, ..., x T} as the input sequence, the physical field interaction result is defined as Y = {y1, y2, ..., y T} as the output sequence, train the LSTM model, the expression is:

[0092]

[0093] Where L is the overall error of the model prediction, T is the number of time steps, and y t represents the actual value predicted by the model at time t, h t Represents the prediction result generated by the model based on the input data at time t;

[0094] For the loss L at the tth time step t , the weights and biases are updated using the gradient descent principle, expressed as:

[0095]

[0096] Among them, W θ is the weight matrix of the model, θ is the set of parameters in the matrix, η is the learning rate, It represents the rate of change of a multivariate function with respect to one of the variables;

[0097] Use the trained LSTM model to predict the interaction between different physical fields. The expression is:

[0098]

[0099] Among them, P g represents the mesh density requirement for a specific area, w i is the weight of the interaction of the ith physical field, f i (X i ) is the function of the ith physical field interaction, N is the number of physical field interactions, B is the regulation function, g j (X j ) is the jth physical field function that affects the mesh density, M is the number of physical fields that affect the mesh density, θ is the set of model parameters, i represents the type of physical field interaction, j represents the physical field that directly affects the mesh density, and X i is the data related to a specific physical field interaction extracted from the total input data set X;

[0100] P g The value range of is [0,∞), where the smaller the value, the lower the mesh density requirement in the area; the larger the value, the higher the mesh density requirement in the area;

[0101] It should also be noted that outlier detection and cleaning uses the Z-Score method: the Z-Score of each data point is calculated, and those data points whose absolute value of the Z-Score exceeds 3 are removed;

[0102] Data cleaning is to fill missing values ​​of numerical features with the median;

[0103] Data normalization is to normalize each feature to have zero mean and unit variance;

[0104] The reason for choosing LSTM is that it can effectively process the time series characteristics of historical data and capture the trends and patterns of variables such as wind speed and temperature over time.

[0105] The LSTM (Long Short-Term Memory) model is trained using historical data X as input and the corresponding physical field interaction results Y as output. Here, X includes environmental data such as wind speed, wind direction, temperature, humidity, and solar radiation intensity, while Y reflects the impact of changes in these environmental conditions on physical fields (such as fluid dynamics, thermodynamics, and structural mechanics).

[0106] S5. Dynamically adjust the grid density based on the identified key areas.

[0107] Furthermore, based on the complexity of the physical phenomena covered, the limitations of the available computing resources, the required level of simulation accuracy, and the characteristics of the selected mesh refinement strategy, a critical density threshold R is defined, which is then compared with the density demand prediction value P g Dynamically adjust the grid density in relation to the critical density threshold R to ensure more accurate simulation results in these areas;

[0108] When P g When ≥R, it means that the grid density needs to be increased, and the local grid refinement algorithm is applied to divide each grid unit that needs to be refined into smaller sub-units;

[0109] When P g When <R, it means that the mesh density is sufficient and no further refinement is required;

[0110] Add a transition zone between the refined area and the non-refined area to smoothly transition through gradually changing mesh density and reduce simulation errors caused by mutations;

[0111] Add the new nodes and units generated after the local area grid is refined into the grid data structure to update the grid data structure;

[0112] It should also be noted that the lower limit of R is usually determined by the physical limitations of computing resources and the minimum mesh size. Too low an R value will result in an overly dense mesh in the entire computational domain, causing unnecessary computational burden and may even exceed the limits of computing resources. The upper limit of R is determined by the nature of the physical field and the minimum resolution required. If R is set too high, critical areas may not get enough mesh refinement, affecting the accuracy of the simulation results.

[0113] The local mesh refinement algorithm is an adaptive meshing technique that dynamically adjusts the resolution of the computational mesh based on local changes in physical quantities or pre-set indicators (such as the density demand prediction value Pg here). When the Pg value exceeds the preset critical density threshold R, it indicates that the physical process in the area is complex or changes dramatically, and a higher mesh density is required to capture details and improve simulation accuracy. Therefore, the algorithm will subdivide the mesh cells in these areas to produce a denser mesh; conversely, if Pg is less than R, the original mesh density remains unchanged. By adding a transition zone between the refined and non-refined areas, numerical errors introduced by sudden changes in mesh density can be avoided. This strategy can effectively balance computational efficiency and model accuracy because resources are mainly concentrated in the key areas that have the greatest impact on the results, rather than being evenly distributed in all spaces.

[0114] S6. Use the adjusted mesh density to run multiphysics coupled simulations to evaluate the performance of the PV array.

[0115] Furthermore, based on the new grid density, the simulation conditions of fluid mechanics, thermodynamics and structural mechanics are adjusted to ensure the accuracy and stability of the simulation;

[0116] Define a comprehensive evaluation function P e , using the implicit coupling algorithm to simulate the interaction between fluid mechanics, thermodynamics and structural mechanics, and evaluate the effective performance of the photovoltaic array, the expression is:

[0117]

[0118] Among them, P e is the effective performance of the photovoltaic array, F w is the wind load on the photovoltaic array, I s is the solar radiation intensity, E is the elastic modulus of the photovoltaic panel material, ρ is the density of the photovoltaic panel material, T e is the ambient temperature, and β is the influence coefficient of temperature change on material properties.

[0119] It should also be noted that Pe is defined based on multiple factors such as the wind load on the PV array, solar radiation intensity, PV panel material properties, ambient temperature, and the impact of temperature on material properties. It aims to comprehensively evaluate the effective performance of the PV array under specific environmental conditions.

[0120] The reason for using an implicit coupled algorithm is that it provides better stability and convergence, especially when dealing with strongly coupled physics. Implicit methods solve the equations for all the relevant physics simultaneously in each iteration, rather than solving them one by one as in explicit methods.

[0121] S7. Adjust the design of the photovoltaic array according to the evaluation results.

[0122] Furthermore, according to the effective performance P of the photovoltaic array e The value of is used to judge the effective performance of the photovoltaic array;

[0123] When P e When it is positive, it means that the photovoltaic array is in an effective working state, and its performance increases with F w and I s The current parameter settings are maintained;

[0124] When P e When it is equal to zero, it means that the performance of the photovoltaic array has reached the critical point. At this time, F w and I s The effects on performance cancel each other out;

[0125] In-depth analysis leads to F w and I s The reasons for the offsetting effects on performance are analyzed, and the design parameters of the photovoltaic array are adjusted according to the analysis results, including changing the orientation, tilt angle and material of the array to adapt to specific wind load and solar radiation conditions;

[0126] When P e When it is a negative value, it means that the performance of the photovoltaic array is affected. w Reach high strength levels with T e Commonly caused by high temperature;

[0127] Immediately check the physical condition of the PV array, replace damaged and overheated components, re-evaluate the structural design and cooling system of the PV array, and enhance the wind resistance design of the array and add heat dissipation devices;

[0128] It should also be noted that the design parameters of the photovoltaic array are adjusted specifically. First, based on the results of the multi-physics field coupling simulation, the designers will analyze the performance bottlenecks and stress conditions of the photovoltaic array under the current design. If it is found that the array is subjected to excessive stress under a specific wind load, it may be considered to adjust the orientation and tilt angle of the array to change the incident angle of the wind force, thereby reducing the impact of the wind load. Optimizing the orientation can ensure that the array better captures the sun's rays, while adjusting the tilt angle helps to maximize the area of ​​sunlight at different times of the year. Based on the thermodynamic and mechanical behavior revealed in the simulation, designers may choose more heat-resistant or tougher materials to improve the stability and efficiency of the photovoltaic array under high temperature or storm conditions. For example, the use of backplane materials with higher thermal conductivity can improve heat dissipation, and the use of lighter but stronger frame materials can reduce the weight of the array while enhancing structural rigidity.

[0129] In terms of enhancing the wind resistance design of the array, designers will use the principles of fluid mechanics to reduce the direct impact of wind on photovoltaic panels by optimizing the shape and layout of the array. This may include adopting streamlined contours, adjusting the arrangement and spacing of photovoltaic panels, and adding wind deflection structures such as wind wings or spoilers to guide the airflow smoothly through the array and reduce the vibration and stress caused by wind.

[0130] This embodiment also provides a computer device, which is suitable for the case of a photovoltaic array design simulation optimization method, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to implement the photovoltaic array design simulation optimization method proposed in the above embodiment.

[0131] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0132] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the photovoltaic array design simulation optimization method proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0133] In summary, the present invention constructs a three-dimensional model with a herringbone design to improve wind resistance, defines a wide computational domain and sets appropriate boundary conditions to reduce simulation errors, implements multi-physics field coupling simulation to examine the interaction between fluid mechanics, thermodynamics and structural mechanics, uses historical data to train a machine learning model to predict the interaction between physical fields and optimizes the grid density accordingly, and runs the adjusted multi-physics field simulation to evaluate performance. This comprehensive process not only enhances the stability and efficiency of photovoltaic arrays under various environmental conditions, but also provides a scientific and efficient strategy for design, which has a positive impact on the development and application of photovoltaic technology. With the continuous innovation of technology, the design optimization of photovoltaic arrays in the future will be more efficient and intelligent, further promoting sustainable development.

[0134] Example 2, referring to Table 1, is the second example of the present invention. To further verify the advancement of the present invention, experimental simulation data of the photovoltaic array design simulation optimization method are provided.

[0135] A test scenario covering different environmental variables, including wind load, solar radiation intensity and ambient temperature, was designed to fully evaluate the performance of the herringbone PV array under various conditions.

[0136] First, a three-dimensional model of the herringbone photovoltaic array was constructed using SolidWorks, and its geometric parameters and material properties were accurately set;

[0137] Secondly, the computational domain and boundary conditions were defined, and multi-physics coupling simulation technology was used to ensure that the model can accurately reflect the physical phenomena in the real environment;

[0138] Next, the LSTM model is used to predict the grid density in key areas and dynamically adjust it to optimize the simulation accuracy;

[0139] Finally, through the comprehensive evaluation function P e Evaluate the performance of the PV array and make necessary design adjustments based on the results to verify the effectiveness and superiority of the design.

[0140] The details are shown in Table 1:

[0141] Table 1 Experimental record table

[0142]

[0143] It can be seen from the above table that the control groups A and B represent the performance of the photovoltaic array of the prior art under different environmental conditions, while the experimental groups X and Y reflect the performance of the present invention under more severe environmental conditions. The wind load and solar radiation intensity of the experimental groups X and Y are significantly higher than those of the control group, but the comprehensive performance P e However, the P of experimental group Y is higher, especially under high wind load and high solar radiation conditions. e The value reached 1.2, which was 240% higher than that of the control group.

[0144] The present invention effectively improves the performance stability of photovoltaic arrays in extreme environments through the design of herringbone photovoltaic arrays, combined with dynamic grid density adjustment and multi-physics field coupling simulation. In particular, under high wind load conditions, the herringbone design enhances the wind resistance of the structure, and the LSTM prediction and adjustment of the grid density ensures the accuracy of the simulation results, allowing the photovoltaic array to better adapt to environmental changes and improve energy conversion efficiency.

[0145] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A photovoltaic array design simulation optimization method, characterized in that: include, Design the photovoltaic array in a herringbone shape and construct a three-dimensional model of the photovoltaic array; Define a computational domain according to the size of the PV array and the surrounding environment, and set boundary conditions; Based on the 3D model of photovoltaic array, computer domain and boundary conditions, multi-physics coupling simulation settings are performed; Use historical data to train machine learning models to predict the interactions between different physics and identify critical areas that require higher mesh density based on the conditions set up in a multiphysics coupled simulation. Dynamically adjust the grid density based on the identified critical areas; Using the adjusted mesh density, run multiphysics coupled simulations to evaluate the performance of the PV array. Adjust the design of the photovoltaic array based on the evaluation results; The calculation domain is defined according to the size of the photovoltaic array and the surrounding environment, and the boundary conditions are set. The specific steps are as follows: According to the size of the photovoltaic array, define a computational domain that is much larger than the boundary of the photovoltaic array to reduce the impact of boundary conditions on the simulation results; Use an exponential wind profile to define velocity boundary conditions at the inlet boundary; The outlet boundary adopts free outflow boundary condition, allowing the fluid to leave the computational domain freely; No-slip wall boundary conditions are used at the bottom of the computational domain and on the surface of the photovoltaic array to simulate the interaction between the solid surface and the flowing medium; The multi-physics field coupling simulation setting is performed based on the photovoltaic array three-dimensional model, computer domain and boundary conditions. The specific steps are as follows: The fluid mechanics simulation conditions are established according to the target fluid behavior, geometric structure characteristics and boundary conditions, and the SSTk-ω turbulence model is selected as the basis for simulating wind loads; By integrating the heat conduction model, the heat absorbed by the solar panel and the surrounding temperature changes are considered to set the mechanical simulation conditions, and the solar radiation intensity and ambient temperature are defined at the same time; The structural mechanics simulation conditions are set by considering the elastic modulus and density of the photovoltaic panel material and its property evolution with temperature; Integrate the simulation conditions of fluid mechanics, thermodynamics and structural mechanics to ensure the interaction between the physical fields, and enhance the stability and accuracy of the simulation by setting up coupling algorithms; Configure solver parameters to precisely define the time step, number of iterations, and convergence criteria.

2. The photovoltaic array design simulation optimization method according to claim 1, characterized in that: The specific steps of designing the photovoltaic array in a herringbone pattern and constructing a photovoltaic panel structure model diagram are as follows: Use SolidWorks to create the geometry of the photovoltaic panel, use a herringbone design for the photovoltaic panel structure, and design the array layout in the form of m×n, where m represents the number of rows and n represents the number of columns; Define size parameters based on the specifications of the photovoltaic panels, power output requirements, and installation space limitations; Define material properties according to industry standards and take into account the effects of temperature changes; After construction, the individual photovoltaic panels are assembled into a complete three-dimensional model of the photovoltaic array.

3. The photovoltaic array design simulation optimization method according to claim 2, characterized in that: The method of using historical data to train a machine learning model, predicting the interactions between different physical fields, and identifying key areas that require higher mesh density based on the conditions set for multi-physics coupling simulations is as follows: Historical data include wind speed and direction, ambient temperature and humidity information, time series of solar radiation intensity, and actual output power of photovoltaic panels under different environmental conditions; Preprocess the collected historical data using outlier detection and cleaning, data cleaning, and data standardization; Select LSTM in the deep learning model as the grid density prediction model; Define historical data as X={x1, x2, …, x T } as the input sequence to train the LSTM model; Use the trained LSTM model to predict the interaction between different physical fields. The expression is: ； Among them, P g represents the mesh density requirement for a specific area, w i is the weight of the interaction of the ith physical field, f i (X i ) is the function of the ith physical field interaction, N is the number of physical field interactions, B is the regulation function, and g j (X j ) is the jth physical field function that affects the mesh density, M is the number of physical fields that affect the mesh density, θ is the set of model parameters, i represents the type of physical field interaction, j represents the physical field that directly affects the mesh density, and X i is the data related to a specific physics interaction extracted from the total input data set X.

4. The photovoltaic array design simulation optimization method according to claim 3, characterized in that: The specific steps of dynamically adjusting the grid density according to the identified key areas are as follows: Define a critical density threshold R, and compare the density demand forecast value P g Dynamically adjust the grid density based on the relationship with the critical density threshold R; When P g When ≥R, it means that the grid density needs to be increased, and the local grid refinement algorithm is applied to divide each grid unit that needs to be refined into smaller sub-units; When P g When <R, it means that the mesh density is sufficient and no further refinement is required; Add a transition zone between the refined area and the non-refined area to smoothly transition through gradually changing mesh density and reduce simulation errors caused by mutations; The new nodes and units generated after the local area grid is refined are added to the grid data structure to update the grid data structure.

5. The photovoltaic array design simulation optimization method according to claim 4, characterized in that: The adjusted grid density is used to run a multi-physics coupling simulation to evaluate the performance of the photovoltaic array. The specific steps are as follows: Adjust simulation conditions for fluid dynamics, thermodynamics, and structural mechanics based on new mesh densities; Define a comprehensive evaluation function P e , using the implicit coupling algorithm to simulate the interaction between fluid mechanics, thermodynamics and structural mechanics, and evaluate the effective performance of the photovoltaic array, the expression is: ； Among them, P e is the effective performance of the photovoltaic array, F w is the wind load on the photovoltaic array, I s is the solar radiation intensity, E is the elastic modulus of the photovoltaic panel material, ρ is the density of the photovoltaic panel material, T e is the ambient temperature, and β is the influence coefficient of temperature change on material properties.

6. The photovoltaic array design simulation optimization method according to claim 5, characterized in that: The specific steps of adjusting the design of the photovoltaic array according to the evaluation results are as follows: According to the effective performance P of the photovoltaic array e The value of is used to judge the effective performance of the photovoltaic array; When P e When it is positive, it means that the photovoltaic array is in an effective working state, and its performance increases with F w and I s The current parameter settings are maintained; When P e When it is equal to zero, it means that the performance of the photovoltaic array has reached the critical point. At this time, F w and I s The effects on performance cancel each other out; In-depth analysis leads to F w and I s The reasons for the mutually offsetting effects on performance are analyzed, and the design parameters of the photovoltaic array are adjusted according to the results of the analysis, including changing the orientation and tilt angle of the array and replacing the materials; When P e When it is a negative value, it means that the performance of the photovoltaic array is affected. w Reach high strength levels with T e Commonly caused by high temperature; Immediately check the physical condition of the PV array, replace damaged and overheated components, re-evaluate the structural design and cooling system of the PV array, and enhance the wind resistance design of the array and add heat dissipation devices.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the photovoltaic array design simulation optimization method described in any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the photovoltaic array design simulation optimization method according to any one of claims 1 to 6 are implemented.

Images