Intelligent control method for crosslinking degree of EVA film suitable for photovoltaic module

Abstract

The application discloses an intelligent control method for the crosslinking degree of EVA film suitable for photovoltaic modules, and relates to the technical field of material processing. The method comprises the following steps: firstly, determining a parameter space containing a filling temperature interval and a crosslinking temperature interval based on the prior evolution experiment of the EVA film; secondly, constructing a multi-stage crosslinking simulation environment containing a filling simulation model and a heat preservation crosslinking simulation model in combination with a target lamination scene; then, combining the parameter space with the simulation environment to perform iterative lamination simulation optimization, and determining a film crosslinking parameter set containing a filling temperature-heat preservation time and a crosslinking temperature-heat preservation time; finally, implementing lamination crosslinking according to the parameter set. Through the combination of experiments and simulation, the application realizes accurate prediction of the crosslinking process of the EVA film and intelligent optimization of process parameters, overcomes the limitation of traditional methods which rely on experience and trial and error, and effectively improves the quality consistency and production efficiency of photovoltaic module packaging.

Description

Technical Field

[0001] This invention relates to the field of materials processing technology, and more specifically to a method for intelligent control of the crosslinking degree of EVA thin films applicable to photovoltaic modules. Background Technology

[0002] The long-term reliability of photovoltaic modules largely depends on the performance of the encapsulation materials, among which ethylene vinyl acetate copolymer (EVA) film is one of the most widely used encapsulation materials. Uncrosslinked ethylene vinyl acetate copolymer has a linear polymer structure, resulting in poor heat resistance and dimensional stability. It is prone to flow and deformation at high temperatures, failing to meet the long-term use requirements of photovoltaic modules in harsh outdoor environments. By adding a crosslinking agent to form a three-dimensional network structure, the heat resistance, mechanical strength, and dimensional stability of this material can be significantly improved.

[0003] Currently, differential scanning calorimetry (DSC) or solvent extraction methods are commonly used in the industry to evaluate the crosslinking process and the final degree of crosslinking. However, DSC is difficult to reflect the changes in the rheological properties of materials during the crosslinking process, while solvent extraction methods have inherent limitations such as long testing cycles, the use of toxic solvents, and the inability to characterize the evolution of material mechanical properties. In lamination packaging processes, a balance needs to be struck between sufficient material flow for filling and timely crosslinking and shaping. Insufficient material flowability during the filling stage can easily lead to defects such as bubbles and incomplete filling; improper control during the crosslinking stage can affect the mechanical properties and long-term durability of the final product. Summary of the Invention

[0004] This invention addresses the technical problems in the prior art, namely, the difficulty in simultaneously obtaining the rheological properties and crosslinking kinetic parameters of EVA films, and the inability to accurately model and optimize the crosslinking process during lamination. It provides an intelligent control method for the degree of crosslinking of EVA films suitable for photovoltaic modules.

[0005] The technical solution of the present invention to solve the above-mentioned technical problems is as follows:

[0006] This invention provides a method for intelligent control of the crosslinking degree of EVA thin films suitable for photovoltaic modules, comprising:

[0007] Based on a priori evolution experiments of EVA films, the parameter space affecting the degree of crosslinking is determined, wherein the parameter space includes at least the filling temperature range and the crosslinking temperature range.

[0008] Combining prior evolution experimental results with the target lamination scenario of EVA film, a multi-stage crosslinking simulation environment corresponding to the lamination process is constructed, wherein the multi-stage crosslinking simulation environment includes at least one filling simulation model and one thermal insulation crosslinking simulation model.

[0009] Iterative lamination simulation optimization is performed by combining the parameter space with the multi-stage crosslinking simulation environment, and the film crosslinking parameter set is determined based on the iterative lamination simulation optimization results. The film crosslinking parameter set includes at least the filling temperature-holding time and the crosslinking temperature-holding time.

[0010] Lamination crosslinking for photovoltaic modules is performed based on the aforementioned thin film crosslinking parameter set.

[0011] The beneficial effects of this invention are:

[0012] Compared to existing technologies, this invention first scientifically defines the feasible space of key process parameters through a priori evolutionary experiments, laying a reliable data foundation for subsequent optimization and avoiding blind parameter selection. Secondly, it innovatively constructs a multi-stage crosslinking simulation environment that matches the lamination process, simulating the filling flow process and the insulation crosslinking process with high fidelity, comprehensively reflecting the material's behavioral evolution at different stages. Thirdly, through an iterative optimization strategy combining the parameter space and the simulation environment, it can efficiently and accurately search for globally optimal or near-optimal combinations of process parameters, realizing a shift from experience-based trial and error to intelligent optimization. Finally, it outputs a set of thin-film crosslinking parameters that can directly guide production, ensuring the controllability and repeatability of the photovoltaic module lamination crosslinking process, and improving the consistency of product packaging quality and production efficiency. Attached Figure Description

[0013] Figure 1 A schematic flowchart of the intelligent control method for crosslinking degree of EVA thin film for photovoltaic modules provided by the present invention;

[0014] Figure 2 This is a schematic diagram of the intelligent control method for crosslinking degree of EVA thin film applicable to photovoltaic modules provided by the present invention. Detailed Implementation

[0015] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0016] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0017] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0018] Example 1, as Figure 1 , Figure 2 As shown, embodiments of the present invention provide a method for intelligent control of the crosslinking degree of EVA thin films suitable for photovoltaic modules, including:

[0019] S10: Based on the a priori evolution experiment of EVA film, determine the parameter space that affects the degree of crosslinking, wherein the parameter space includes at least the filling temperature range and the crosslinking temperature range;

[0020] First, the a priori evolution experiment is a series of fundamental material property tests and analyses conducted on the ethylene vinyl acetate copolymer film before implementing process parameter optimization. The aim is to systematically study the rheological behavior and structural evolution of the material under different thermal histories, providing data support and theoretical basis for the determination of subsequent process parameters.

[0021] Specifically, based on prior evolution experiments of EVA films, the parameter space affecting the degree of crosslinking is determined, wherein the parameter space includes at least the filling temperature range and the crosslinking temperature range, including:

[0022] Based on the prior evolution experiment on the EVA film, the corresponding rheological property-temperature evolution data are obtained, wherein the rheological properties include at least viscosity and modulus indicators.

[0023] The lower limit of the filling temperature is determined based on the rheological properties-temperature evolution data;

[0024] Based on the rheological properties-temperature evolution data, suspected gel points are obtained, and multiple temperature points near the suspected gel points are randomly selected for oscillation frequency scanning tests. Based on the oscillation frequency scanning test results, the temperature with the lowest correlation between the modulus index and the oscillation frequency is selected as the gel point.

[0025] The multidimensional critical temperatures of the EVA film are obtained, and the lowest one among the multidimensional critical temperatures is selected as the crosslinking critical temperature. The multidimensional critical temperatures include at least the decomposition critical temperature, the yellowing critical temperature, and the modulus critical temperature.

[0026] By combining the lower limit of the filling temperature, the gel point, and the critical crosslinking temperature, the filling temperature range and the crosslinking temperature range are defined to obtain the parameter space.

[0027] First, a priori evolution experiments were conducted on ethylene vinyl acetate copolymer films to obtain data on the evolution of their rheological properties with temperature. These rheological properties include at least two key indicators: complex viscosity and dynamic modulus. Complex viscosity reflects the material's flow resistance, while dynamic modulus characterizes the material's elastic and viscous responses. Specifically, in the a priori evolution experiments, programmed temperature rise tests were performed on the ethylene vinyl acetate copolymer films to fully record the changes in their dynamic rheological properties during the crosslinking process, simulating the thermal history experienced by the material during actual lamination, thereby revealing the complete transformation process of the material from its initial flow state to its final crosslinking and solidification.

[0028] Specifically, during the programmed temperature rise process, the rheological properties of the ethylene vinyl acetate copolymer film exhibit a regular evolution. In the initial stage, as the temperature increases, the mobility of molecular chain segments increases, the material's fluidity improves, and the complex viscosity continuously decreases. When the temperature reaches the crosslinking reaction initiation point, a three-dimensional network structure begins to form in the system, causing a turning point in the complex viscosity, which then gradually increases. As the crosslinking reaction continues, the material gradually loses its fluidity, the dynamic modulus relationship undergoes a fundamental change, and the storage modulus eventually surpasses the loss modulus, marking the material's transition from a viscous flow state to a gel state.

[0029] By collecting complex viscosity and dynamic modulus data at different temperatures, complete rheological property-temperature evolution data can be established, accurately reflecting the material's state characteristics in different temperature ranges: it mainly exhibits thermoplastic behavior in the low-temperature range and thermosetting characteristics in the high-temperature range. Specifically, the final obtained rheological property-temperature evolution data are complete curves of the continuous change of complex viscosity and dynamic modulus with temperature. This can characterize the entire structural evolution process of ethylene vinyl acetate copolymer from a viscous flow state to a gel state and finally to complete cross-linking during heating. It is used to accurately define the temperature window of the material in different physical states, providing key input parameters and theoretical basis for subsequent determination of the lower limit of the filling temperature, identification of the gel point, and establishment of multi-stage simulation models.

[0030] Secondly, the lower limit of the filling temperature is determined based on rheological properties-temperature evolution data. Specifically, in the initial stage of heating, the complex viscosity continuously decreases with increasing temperature, corresponding to an enhanced mobility of the ethylene vinyl acetate copolymer molecular chains. The lower limit of the filling temperature is the lowest temperature threshold that ensures sufficient flow and complete filling of the ethylene vinyl acetate copolymer film during lamination. Its selection principle is based on the essential law of material rheological properties changing with temperature: in the initial stage of heating, with the increase of heat input, the mobility of polymer molecular chain segments increases, and the intermolecular forces weaken, macroscopically manifested as a continuous decrease in complex viscosity. When the temperature reaches a certain critical point, the viscosity decrease trend slows down significantly, indicating that the molecular chains have acquired sufficient mobility to achieve effective flow. This critical point is the lower limit of the filling temperature, specifically corresponding to the starting position where the rate of decrease in the complex viscosity-temperature curve changes significantly. Setting this temperature as the minimum operating temperature of the filling stage can simultaneously consider energy efficiency and process reliability, ensuring complete filling of the material under lamination pressure while avoiding premature cross-linking reactions caused by excessively high temperatures, which would affect flow properties.

[0031] Furthermore, suspected gel points were identified by analyzing the dynamic modulus-temperature evolution curve. The gel point is the critical temperature at which the ethylene vinyl acetate copolymer film undergoes a liquid-solid transition during crosslinking. At this temperature, the material begins to form a continuous three-dimensional network structure and permanently loses its flowability. To accurately determine the gel point, multiple temperature points near the suspected gel points initially identified by the dynamic modulus-temperature evolution curve were selected for oscillation frequency scanning tests.

[0032] The preliminary identification of suspected gel points was achieved by analyzing the evolution of the dynamic modulus of the ethylene vinyl acetate copolymer film during programmed temperature rise. During the temperature rise test, the dynamic modulus, especially the relative relationship between storage modulus and loss modulus, exhibited a regular change. In the initial stage, due to the increased molecular chain motion caused by rising temperature, both storage modulus and loss modulus showed a decreasing trend. When the temperature rose to a certain range, although thermal motion continued to increase, the cross-linking reaction began to form a three-dimensional network structure, causing the decreasing trend of storage modulus to slow down, stabilize, and then increase.

[0033] Specifically, when the curves of storage modulus and loss modulus intersect, meaning the storage modulus first reaches and surpasses the loss modulus, the temperature region corresponding to this intersection point is preliminarily identified as a potential gel point. This intersection phenomenon signifies a shift in the material's dominant characteristic from viscous response to elastic response, indicating the formation and gradual dominance of a continuous network structure. This is an important macroscopic characterization of the material's transition from a viscous flow state to a gel state. This preliminary identification can define the temperature range requiring focused analysis for subsequent, more precise gel point determination.

[0034] Furthermore, near the suspected gel point, multiple temperature points were selected for oscillation frequency scanning tests. This test involved applying a series of small-amplitude oscillatory shears at different frequencies at each selected temperature point and recording the corresponding dynamic modulus response. According to Winter's gelation theory, at the actual gel point, the material's loss factor is independent of the test frequency, exhibiting a unique self-similarity. Therefore, by analyzing the dependence of dynamic modulus on frequency at different temperatures, the temperature point with the weakest correlation between dynamic modulus and oscillation frequency was selected as the final gel point. This gel point marks the beginning of polymer network penetration, providing a rigorous theoretical basis and experimental criterion for defining the process temperature boundary between the filling and crosslinking stages.

[0035] Furthermore, the multidimensional critical temperatures of the ethylene vinyl acetate copolymer film were obtained. The decomposition critical temperature at which mass loss reaches a preset threshold was determined by thermogravimetric analysis; the yellowing critical temperature was determined based on the yellowing index inflection point through a series of high-temperature isothermal experiments combined with color difference measurements; and the modulus plateau curve was obtained through high-temperature isothermal experiments, and the modulus transformation critical temperature with the lowest slope turning negative was selected. The lowest value among the three critical temperatures was selected as the final crosslinking critical temperature to ensure that the material crosslinks within a safe temperature range.

[0036] Specifically, the multidimensional critical temperatures of the EVA film are obtained, and the lowest one among the multidimensional critical temperatures is selected as the crosslinking critical temperature, including:

[0037] Thermogravimetric analysis was used to measure the change in mass of EVA film samples with temperature, determine the temperature at which the mass loss ratio reached a preset threshold, and obtain the critical decomposition temperature.

[0038] Through a series of high-temperature isothermal experiments, combined with colorimeter measurements of several yellowing index values ​​of EVA film after aging at several temperatures, and by using the elbow method to identify the temperature corresponding to the inflection point of the yellowing index value, the critical yellowing temperature is obtained.

[0039] Through a series of high-temperature isothermal experiments, several modulus plateau curves of EVA film samples at several temperatures were measured and obtained. The modulus plateau curve with a negative slope and the lowest isothermal temperature was selected as the modulus change critical temperature.

[0040] First, the decomposition critical temperature is determined through thermogravimetric analysis (TGA). This TGA method monitors the mass change trajectory of ethylene vinyl acetate copolymer film samples under programmed temperature rise. The temperature at which the sample mass loss ratio reaches a preset threshold is defined as the decomposition critical temperature. The preset threshold is the maximum allowable mass loss ratio for maintaining chemical structural stability under long-term use conditions, set based on industry standards and long-term aging test data, for example, a 5% mass loss rate. The decomposition critical temperature characterizes the boundary of the thermal stability of the ethylene vinyl acetate copolymer material; exceeding this critical temperature will trigger irreversible degradation of the polymer backbone.

[0041] Secondly, the critical temperature for yellowing was determined through a series of high-temperature isothermal experiments combined with color difference measurements. Yellowing refers to the phenomenon where ethylene vinyl acetate copolymer films undergo chemical structural changes under the influence of environmental factors such as heat, oxygen, or ultraviolet radiation, leading to a gradual shift in color towards yellow. The essence of this phenomenon is that the polymer molecular chains undergo oxidative degradation and other chemical reactions during aging, generating chromophores. Specifically, this manifests as decreased transparency, increased haze, and a yellowish hue. The degree of yellowing can be quantitatively measured using a colorimeter and characterized by the yellowing index. A higher yellowing index indicates a more severe degree of color degradation.

[0042] In photovoltaic (PV) module applications, yellowing directly leads to a decrease in light transmittance, affecting light transmission and causing a continuous decline in module power generation efficiency. Therefore, determining the critical temperature for yellowing is crucial for ensuring the long-term performance of PV modules.

[0043] Specifically, the series of high-temperature isothermal experiments involves placing ethylene vinyl acetate copolymer film samples under multiple different high-temperature conditions for isothermal aging. The holding time at each temperature point must ensure that the material reaches a stable state. After aging, a colorimeter is used to measure the sample surface and obtain the yellowing index value, which characterizes the degree of yellowing of the material. Specifically, in the data analysis stage, the yellowing index values ​​corresponding to each temperature point are plotted as a temperature-yellowing index curve. The elbow method is used to analyze this curve, and key inflection points are identified by calculating the curvature change. In the lower temperature range, the yellowing index increases slowly with increasing temperature; when the temperature reaches a certain critical value, the rate of increase of the yellowing index accelerates significantly, forming a clear inflection point. This inflection point is the curve inflection point, and the corresponding temperature is defined as the yellowing critical temperature. Below the inflection point temperature, yellowing is mainly caused by reversible physical changes; above the inflection point temperature, irreversible chemical degradation reactions become the dominant factor, leading to a sharp increase in the yellowing index and a rapid deterioration of the material's optical properties. Therefore, this yellowing critical temperature accurately defines the upper temperature limit for the material to maintain acceptable optical properties.

[0044] Furthermore, the modulus critical temperature was obtained through a series of high-temperature isothermal experiments. Specifically, ethylene vinyl acetate copolymer film samples were placed in a series of isothermal environments with temperature gradients, and the dynamic modulus of the samples was continuously monitored over time at fixed frequencies and strains using a rheometer. At each isothermal test point, when the modulus value no longer changed significantly over time, i.e., when it entered the so-called plateau period, the stable value of the modulus and its trend over time were recorded.

[0045] Furthermore, through mathematical analysis of the modulus plateau curves at all test temperatures, the slope characteristics of each curve during the plateau period were examined in detail. When the plateau curve exhibits a negative slope at a specific temperature, meaning that the modulus value begins to decline continuously after reaching the plateau, it indicates that under this temperature condition, the thermal degradation rate of the cross-linked network inside the material begins to exceed its formation rate, leading to irreversible damage to the three-dimensional network structure that serves as the rigid core support of the material.

[0046] Specifically, the modulus critical temperature is defined as the lowest isothermal temperature corresponding to all modulus plateau curves exhibiting a negative slope. It marks the minimum limit for a material to maintain its mechanical integrity under long-term heat exposure. Below this modulus critical temperature, the cross-linked structure of the material can remain stable or continue to strengthen; once this modulus critical temperature is exceeded, even for a short period, the material will begin to experience a fundamental degradation in its mechanical properties, and its load-bearing capacity and dimensional stability will continue to decline. Therefore, the modulus critical temperature is a key indicator for evaluating the long-term heat resistance of ethylene vinyl acetate copolymer films.

[0047] Finally, the lowest value among the above-mentioned critical temperatures for decomposition, yellowing, and modulus transformation is selected as the critical temperature for crosslinking to guide the process design. This ensures that the final determined upper limit of the crosslinking temperature is always within the safe boundaries of the material's various properties, thereby providing a reliable safety guarantee for the lamination process.

[0048] Finally, by combining the three key parameters—the lower limit of the filling temperature, the gel point, and the critical crosslinking temperature—and the performance parameters of the lamination equipment, the filling temperature range and the crosslinking temperature range are defined. The lower limit of the filling temperature range is the lower limit of the filling temperature, and the upper limit is the gel point minus the temperature control safety offset. The lower limit of the crosslinking temperature range is the gel point plus the temperature control safety offset, and the upper limit is the smaller value between the critical crosslinking temperature and the upper limit of the equipment temperature. The parameter space constructed in this way provides a scientific and reliable parameter boundary for subsequent process optimization.

[0049] Specifically, by combining the lower limit of the filling temperature, the gel point, and the critical crosslinking temperature, the filling temperature range and the crosslinking temperature range are defined to obtain the parameter space, including:

[0050] Obtain the operating performance data of the target laminator, and extract the temperature control accuracy and the upper limit of the laminator temperature based on the operating performance data;

[0051] Combining the temperature control accuracy with the preset temperature control safety factor N, the temperature control safety offset of the target laminator is calculated and determined, wherein the temperature control safety offset is N times the temperature control accuracy, and N is greater than 1;

[0052] Calculate the difference between the gel point and the temperature control safety offset to obtain the upper limit of the filling temperature, and calculate the sum of the gel point and the temperature control safety offset to obtain the lower limit of the crosslinking temperature;

[0053] The crosslinking critical temperature is compared with the upper limit of the laminator temperature, and the upper limit of the crosslinking temperature is determined based on the comparison results.

[0054] The filling temperature range is defined based on the lower limit of the filling temperature and the upper limit of the filling temperature, and the crosslinking temperature range is defined based on the lower limit of the crosslinking temperature and the upper limit of the crosslinking temperature.

[0055] First, obtain the operational performance data of the target laminator and extract two key parameters: the temperature control accuracy of the equipment and its maximum achievable operating temperature, i.e., the upper temperature limit of the laminator. The target laminator refers to a specific model or specification of laminating equipment planned for implementation of the ethylene-vinyl acetate copolymer film lamination process. The operational performance data of the target laminator is a set of parameters describing the core working capabilities of the equipment, obtained by consulting the equipment technical manual, factory test report, or conducting on-site equipment performance calibration tests. Temperature control accuracy reflects the fluctuation range of the actual temperature of its heating plate surface around the set temperature value during steady-state operation, and is an important indicator of the stability of the equipment's temperature control system. The upper temperature limit of the laminator reflects the highest safe operating temperature that the equipment's heating system can achieve and stably maintain in its design; this physical limit determines the upper limit of the selectable temperature range for the lamination process.

[0056] Secondly, by combining the temperature control accuracy with a preset temperature control safety factor N greater than 1, the temperature control safety offset is calculated. This temperature control safety offset is a temperature compensation value used for calculating the safety boundary of process parameters. Specifically, it is the product of the temperature control accuracy and the safety factor N. Its purpose is to add sufficient safety margin to the theoretical temperature boundary determined based on material properties, providing a reliable safety buffer for the process window. This operation aims to proactively offset the random fluctuations inherent in the temperature control system of the laminating equipment and the process risks caused by possible unexpected temperature deviations. It ensures that even in the face of brief temperature anomalies in the actual production environment, the process temperature can be reliably maintained within the critical range required by the material properties, thereby guaranteeing the process stability and product consistency of the lamination process.

[0057] Furthermore, using the calculated temperature control safety offset and the material's gel point, the boundaries of the two process stages are determined. The temperature value obtained by subtracting the temperature control safety offset from the gel point temperature serves as the upper limit of the filling temperature range, ensuring that the material temperature is strictly controlled below the gel point during the filling stage, preventing premature crosslinking. Simultaneously, the temperature control safety offset is added to the gel point temperature, resulting in the lower limit of the crosslinking temperature range, ensuring that the crosslinking reaction can be effectively initiated at a sufficiently high temperature above the gel point.

[0058] Furthermore, by comparing the critical crosslinking temperature of the material with the upper limit of the laminator temperature, the upper limit of the crosslinking temperature range is determined. If the critical crosslinking temperature is lower than the upper limit of the equipment, the upper limit of the crosslinking temperature is set to the critical crosslinking temperature minus the temperature control safety offset to ensure that the process temperature is always below the safe degradation temperature of the material; if the upper limit of the equipment temperature is even lower, then only the equipment limit can be used as the upper limit of the crosslinking temperature.

[0059] Specifically, the crosslinking critical temperature is compared with the upper limit of the laminator temperature, and the upper limit of the crosslinking temperature is determined based on the comparison result, including:

[0060] If the comparison result indicates that the critical crosslinking temperature is greater than the upper limit of the laminator temperature, then the upper limit of the laminator temperature shall be taken as the upper limit of the crosslinking temperature.

[0061] If the comparison result is that the crosslinking critical temperature is less than the upper limit of the laminator temperature, then the difference between the crosslinking critical temperature and the temperature control safety offset is calculated and output as the upper limit of the crosslinking temperature.

[0062] Specifically, when determining the upper limit of the crosslinking temperature, a comparative analysis of the critical crosslinking temperature and the upper limit of the laminator temperature is required. When the critical crosslinking temperature is higher than the upper limit of the laminator temperature, it indicates that the thermal stability boundary of the material exceeds the heating capacity limit of the equipment. In this case, the physical limitations of the equipment should be prioritized, and the upper limit of the crosslinking temperature should be directly set as the upper limit of the laminator temperature. While this setting ensures the feasibility of the process, it also means that the full potential of the material's temperature resistance cannot be fully realized.

[0063] When the crosslinking critical temperature is below the upper limit of the laminator temperature, it indicates that the equipment has sufficient heat treatment capacity. In this case, the thermal safety of the material is given priority. The pre-calculated temperature control safety offset is subtracted from the crosslinking critical temperature, and this difference is used as the final upper limit of the crosslinking temperature. This calculation process establishes a reliable protective buffer within the material's safety boundary, ensuring that even if unexpected positive temperature fluctuations occur, the actual process temperature can still be strictly controlled below the crosslinking critical temperature, thereby effectively preventing irreversible damage to the material caused by overheating, such as degradation, yellowing, and decline in mechanical properties.

[0064] Through the above decision-making mechanism, the final determined upper limit of crosslinking temperature can always meet the dual constraints of material safety and equipment feasibility, providing an important guarantee for achieving robust and reliable process manufacturing.

[0065] Finally, based on the determined lower and upper limits of the filling temperature, a filling temperature range is defined; based on the determined lower and upper limits of the crosslinking temperature, a crosslinking temperature range is defined. The resulting parameter space is a reliable range of process parameters that fully considers material properties and equipment capabilities, and incorporates safety redundancy for subsequent simulation optimization.

[0066] S20: Combining the prior evolution experimental results with the target lamination scenario of EVA film, a multi-stage crosslinking simulation environment corresponding to the lamination process is constructed, wherein the multi-stage crosslinking simulation environment includes at least one filling simulation model and one thermal insulation crosslinking simulation model.

[0067] The multi-stage crosslinking simulation environment is a digital computing framework built upon physical mechanisms and experimental data. This environment decouples the continuous lamination process into multiple stages with different dominant physical mechanisms and establishes high-fidelity computational models for each stage, thus forming a virtual platform capable of completely simulating and reflecting the entire actual lamination and crosslinking process. Through this digital virtual platform, accurate prediction and in-depth optimization of material flow, crosslinking reactions, and final packaging quality under different combinations of process parameters can be achieved before physical pilot production, thereby reducing R&D costs and improving the scientific rigor and reliability of process design.

[0068] Specifically, by combining prior evolution experimental results with the target lamination scenario of EVA films, a multi-stage crosslinking simulation environment corresponding to the lamination process is constructed, including:

[0069] Based on the target lamination scenario, a physical model of the target laminator is established;

[0070] Based on the physical model, and combining the prior thermofluid property equations with the finite element modeling method, the infill simulation model is constructed.

[0071] The input parameters of the filling simulation model include at least lamination pressure, lamination temperature, and material evolution viscosity indicators.

[0072] First, a physical model of the target laminator is established based on the target lamination scenario of ethylene vinyl acetate copolymer film. This physical model is a digital abstraction of the working chamber geometry, heating plate arrangement, and pressure application mechanism of the actual lamination equipment, providing an accurate physical basis for subsequent simulations.

[0073] Secondly, based on the established physical model, and combining prior thermofluid property equations with the finite element modeling method, a filling simulation model was constructed. This filling simulation model simulates the flow and filling behavior of the ethylene vinyl acetate copolymer melt between the glass and the backing plate during lamination by solving the governing equations of mass conservation, momentum conservation, and energy conservation. Among them, the material evolution viscosity index, as a key input parameter, reflects the dynamic characteristics of material viscosity changing with temperature and degree of crosslinking. This material evolution viscosity parameter is derived from the rheological property-temperature evolution data obtained from prior evolution experiments.

[0074] Specifically, the input parameters of the filling simulation model include at least lamination pressure, lamination temperature, and material evolution viscosity indicators. Lamination pressure drives melt flow, the lamination temperature field affects the melt viscosity distribution, and the material evolution viscosity indicators determine the flow resistance of the melt at different spatiotemporal points. Through the coupled calculation of these three types of parameters, the filling simulation model can accurately predict the advancement process of the melt front, the risk of bubble formation, and the uniformity of the final filling state, providing a quantitative basis for evaluating the filling quality.

[0075] In addition, by combining prior evolution experimental results with the target lamination scenario of EVA films, a multi-stage crosslinking simulation environment corresponding to the lamination process is constructed, which also includes:

[0076] Obtain historical lamination logs and extract corresponding sample crosslinking test data, wherein the sample crosslinking test data includes at least the measured temperature, measured heat preservation time and measured crosslinking degree;

[0077] Using the measured temperature and measured insulation time as sample inputs, and the measured crosslinking degree as supervision, a simulation model of insulation crosslinking based on regression analysis is constructed and trained.

[0078] The thermal insulation cross-linking simulation model includes either a machine learning regression model or a mathematical regression model.

[0079] The thermal insulation crosslinking simulation model is a data-driven predictive computational model designed to accurately predict the crosslinking kinetics of ethylene vinyl acetate copolymer films during the thermal insulation stage. The specific construction process of this thermal insulation crosslinking simulation model is as follows:

[0080] First, historical lamination logs are retrieved from the production history, and sample crosslinking measurement data is extracted from them. The historical lamination logs are process data archives automatically recorded and stored by the target laminator during production, comprehensively recording the actual process curves and corresponding process parameters executed by the lamination equipment in past production batches. The extracted sample crosslinking measurement data contains at least three key dimensions: the measured temperature during the lamination process, the corresponding measured holding time, and the final measured degree of crosslinking obtained through experiments. These clearly correlated data collectively constitute the sample basis for training and validating the insulation crosslinking simulation model.

[0081] Secondly, using measured temperature and measured holding time as model input features and measured crosslinking degree as a monitoring signal, a regression analysis method was employed to construct and train the thermal insulation crosslinking simulation model. During the training process, the thermal insulation crosslinking simulation model continuously adjusts its internal parameters to learn the complex nonlinear mapping relationship between the input temperature-time process conditions and the output crosslinking degree.

[0082] Specifically, the thermal insulation cross-linking simulation model can be implemented using two technical approaches: one is a mathematical regression model based on statistical learning, such as multinomial regression or nonlinear regression; the other is a more expressive machine learning regression model, such as support vector regression, random forest, or neural networks. The choice of model type depends on the available data scale and the required prediction accuracy.

[0083] For example, since there is a highly nonlinear and complex correlation between the degree of crosslinking of the ethylene vinyl acetate copolymer film and the process parameters during the heat preservation stage, and the neural network model has significant advantages in multi-level feature abstraction and complex pattern recognition, the neural network model is selected to construct the heat preservation crosslinking simulation model.

[0084] Specifically, the thermal insulation crosslinking simulation model mainly consists of an input layer, a feature abstraction layer, and a prediction output layer. The input layer receives a standardized vector of process parameters, which contains features in at least two dimensions: the set temperature and the planned thermal insulation time for the insulation stage. The feature abstraction layer employs a multi-layer fully connected neural network structure. The number of hidden layer neurons is adaptively configured according to the dimensions of the input features. Each neural network layer uses the ReLU activation function to introduce non-linear transformation capabilities, and Dropout layers are embedded between network layers with a dropout rate set between 0.2 and 0.4 to effectively suppress model overfitting and improve its generalization performance. The output layer uses a linear activation function to map the final abstract features to a continuous numerical value, which serves as the predicted degree of crosslinking.

[0085] During training, key hyperparameters included a learning rate of 0.001, 200 training epochs, and a batch size of 32. The learning rate was set to balance training stability and convergence speed; the number of training epochs ensured the model fully learned the complex mapping relationship between process parameters and crosslinking degree; and the batch size balanced training efficiency with memory resource consumption. Specifically, a supervised learning approach was used. Sample process parameter vectors were collected from historical lamination logs as the input sample set, and the corresponding measured crosslinking degree was simultaneously acquired to form a sample label set. The input sample set and the corresponding label sample set were divided into training, validation, and test sets in a 7:2:1 ratio.

[0086] Furthermore, the sample process parameter vectors in the training set are used as input, and the corresponding measured crosslinking degree is used as the supervision signal. The network weight parameters are iteratively optimized using the backpropagation algorithm and the Adam optimizer. The mean squared error loss function is used to measure the deviation between the predicted and measured crosslinking degrees. The training process is monitored using a validation set. When the validation set loss function value no longer decreases for several consecutive rounds and the prediction accuracy of the thermal insulation crosslinking simulation model reaches a predetermined threshold, such as 96%, training is terminated, resulting in a converged thermal insulation crosslinking simulation model. The final thermal insulation crosslinking simulation model can effectively capture the complex nonlinear relationship between process parameters and crosslinking degree results, achieving accurate crosslinking degree prediction.

[0087] S30: Combine the parameter space with the multi-stage crosslinking simulation environment to perform iterative lamination simulation optimization, and determine the film crosslinking parameter set based on the iterative lamination simulation optimization results, wherein the film crosslinking parameter set includes at least filling temperature-holding time and crosslinking temperature-holding time;

[0088] Since the parameter space determined in step S10 is essentially a safe and feasible region defined based on material properties and equipment performance, this feasible region can only ensure that process parameters will not cause fundamental problems such as material degradation or equipment exceeding limits, but it fails to reveal the quantitative relationship between specific parameter combinations within the region and the final process quality and efficiency. Therefore, it is still necessary to conduct systematic iterative simulation optimization in conjunction with a multi-stage crosslinking simulation environment.

[0089] Furthermore, since the photovoltaic module lamination process is essentially a multi-objective coupled optimization process, it needs to simultaneously satisfy multiple mutually restrictive process requirements. In the filling stage, the material must possess excellent flowability to achieve defect-free complete filling; in the crosslinking stage, a precise target crosslinking degree is required to ensure the long-term reliability of the module; simultaneously, the entire process cycle must be shortened as much as possible to achieve higher production efficiency. Traditional single experiments or simplified calculations are insufficient to effectively balance these complex objectives. By introducing an iterative optimization algorithm, which comprehensively considers the filling quality prediction output by the filling simulation model, the crosslinking degree prediction provided by the insulation crosslinking simulation model, and the production efficiency index measured by the lamination optimization function, the algorithm can automatically find the process parameter combination that simultaneously satisfies all constraints and achieves optimal overall performance.

[0090] Specifically, iterative lamination simulation optimization is performed by combining the parameter space with the multi-stage crosslinking simulation environment, and the film crosslinking parameter set is determined based on the iterative lamination simulation optimization results, including:

[0091] Based on the parameter space, parameters are randomly selected to generate a set of candidate lamination temperatures, wherein the set of candidate lamination temperatures includes multiple groups of candidate lamination temperature parameters, and the groups of candidate lamination temperature parameters include candidate filling temperature and candidate crosslinking temperature.

[0092] The candidate lamination temperature set is input into the filling simulation model, and the simulation is run in combination with the preset worst filling time. The filling quality value is calculated based on the preset filling quality evaluation function, wherein the filling quality evaluation function includes at least a bubble volume fraction factor and a maximum flow distance factor.

[0093] Based on the fill quality value, multiple candidate lamination temperature parameter groups that meet the fill quality threshold are filtered to obtain a second candidate lamination temperature set.

[0094] The second set of candidate lamination temperatures is input into the thermal insulation crosslinking simulation model, and the constraint solution is performed with the target crosslinking degree value as the objective to obtain multiple crosslinking thermal insulation time values.

[0095] Define a lamination optimization function, and combine the lamination optimization function, the crosslinking insulation time value, the second alternative lamination temperature set, and the most unfavorable filling time to calculate and obtain multiple lamination optimization function values;

[0096] The second candidate lamination temperature set is iteratively updated based on multiple lamination optimization function values, and the candidate lamination temperature parameter set corresponding to the best lamination optimization function value is selected as the target lamination temperature parameter set based on the iterative update results.

[0097] The target lamination temperature parameter set, the most unfavorable filling time, and the corresponding crosslinking and heat preservation time value are combined to obtain the filling temperature-heat preservation time and the crosslinking temperature-heat preservation time, and the output is the film crosslinking parameter set.

[0098] First, based on a predetermined parameter space, a set of candidate lamination temperatures is generated through random sampling. This set of candidate lamination temperatures contains multiple sets of candidate lamination temperature parameters, each set consisting of a candidate filling temperature and a candidate crosslinking temperature, serving as initial exploration points for subsequent simulation optimization.

[0099] Secondly, the entire set of candidate lamination temperatures is input into the filling simulation model for initial screening. To evaluate filling performance under the most demanding conditions, the filling simulation model is run using a preset, most unfavorable filling duration. This preset most unfavorable filling duration is set based on the longest sustainable pressurization time of the laminator within the process's allowable range. For example, based on equipment specifications and process safety regulations, the most unfavorable filling duration is set to 900 seconds. This setting aims to ensure that even within the longest allowable filling time, the selected process parameters still guarantee that the filling quality meets requirements.

[0100] For each temperature parameter group, the filling simulation model outputs key results of the filling process and calculates the filling quality value based on a preset filling quality evaluation function. This preset filling quality evaluation function comprehensively considers at least the bubble volume fraction factor and the maximum flow distance factor. The former assesses the risk of hermeticity defects in the encapsulation, while the latter assesses whether the filling is complete. The resulting filling quality value is a numerical index that comprehensively quantifies the filling effect, used to objectively compare the filling performance under different combinations of process parameters. The smaller the filling quality value, the better the filling quality. For example, the filling quality value can be calculated using the following function: Filling quality value = 0.6 × bubble volume fraction + 0.4 × normalized difference between maximum flow distance and target distance. Wherein, the bubble volume fraction is the ratio of bubble volume to total volume in the simulation area, and the normalized difference between the maximum flow distance and the target distance is the degree of difference between the actual flow distance and the theoretically required complete filling distance. When the bubble volume fraction is 0.05 and the normalized flow distance difference is 0.02, the corresponding filling quality value is calculated as 0.6 × 0.05 + 0.4 × 0.02 = 0.038. By setting a fill quality threshold, such as 0.05, the combination of process parameters that meets the fill performance requirements can be effectively screened out. Since the calculated result 0.038 is less than the preset fill quality threshold of 0.05, it indicates that the fill quality corresponding to this set of process parameters meets the qualification requirements. Therefore, this parameter combination will be retained and included in the second set of alternative lamination temperatures.

[0101] It is important to note that in this evaluation system, the numerical value of the fill quality value is negatively correlated with the fill quality; that is, the smaller the fill quality value, the better the fill quality. Setting a fill quality threshold of 0.05 signifies that only when the calculated fill quality value is less than or equal to this threshold is the set of process parameters considered to guarantee sufficient fill quality. This fill quality threshold is set based on the minimum requirements for bubble rate and fill integrity in photovoltaic module encapsulation industry standards. Specifically, the determination of this threshold requires comprehensive consideration of the module product's quality grade requirements, long-term reliability indicators, and the stability tolerance of the production process. By analyzing simulation results corresponding to qualified products in historical production data and combining them with the industry-standard acceptable upper limit for encapsulation defects, the final fill quality threshold value of 0.05 was determined. Any combination of process parameters with a fill quality value higher than 0.05 will be deemed unqualified due to the potential for excessive bubbles or incomplete filling.

[0102] Furthermore, after evaluation using the filling simulation model, only the temperature parameter group whose filling quality value is better than the preset quality threshold is retained. The parameter combinations selected in the initial screening constitute a second set of candidate lamination temperatures. The candidate parameters in this second set of candidate lamination temperatures provide a more reliable search space for subsequent crosslinking process optimization while ensuring filling quality.

[0103] Furthermore, for each temperature parameter group in the second set of alternative lamination temperatures, it is input into the thermal insulation crosslinking simulation model. This simulation model uses the target crosslinking degree as a constraint to perform a reverse solution, calculating the shortest crosslinking insulation time required at each specific alternative crosslinking temperature to achieve the target crosslinking degree. Thus, a corresponding insulation time is matched for each temperature parameter group.

[0104] Furthermore, a comprehensive lamination optimization function is defined. This function aims to balance process efficiency and energy consumption, and its mathematical expression comprehensively considers two key variables: total lamination time and lamination temperature. Specifically, the total lamination time is obtained by adding the preset worst-case filling time to the cross-linking insulation time value obtained through the insulation cross-linking simulation model; the lamination temperature is taken from the candidate cross-linking temperatures corresponding to each parameter group in the second set of candidate lamination temperatures.

[0105] For each parameter group in the second set of candidate lamination temperatures, its corresponding crosslinking and insulation time values ​​and the common worst-case filling time are substituted into the total lamination time calculation formula, and its candidate crosslinking temperature values ​​are obtained. Subsequently, these parameters are input into the lamination optimization function for calculation to obtain the corresponding lamination optimization function values.

[0106] For example, the lamination optimization function value = α × total lamination time + β × lamination temperature;

[0107] Here, α and β are weighting coefficients set according to production needs, representing the degree of importance attached to time efficiency and energy consumption costs, respectively. The specific values ​​of the weighting coefficients are determined based on the relative importance of process cycle and energy consumption in actual production.

[0108] For example, when the weighting coefficients α and β are 0.7 and β is 0.3, the total lamination time of a certain parameter group is 1200 seconds and the lamination temperature is 150℃, the lamination optimization function value is calculated as 0.7×1200+0.3×150=840+45=885.

[0109] Specifically, under this evaluation system, the smaller the lamination optimization function value, the shorter the process cycle and the lower the energy consumption level of the parameter set while ensuring product quality, indicating better overall performance. By comparing the magnitude of this lamination optimization function value, quantitative ranking and screening of multiple candidate process parameter combinations can be achieved.

[0110] Furthermore, for each parameter group in the second candidate lamination temperature set, a lamination optimization function value is calculated by combining its corresponding cross-linking and insulation time values ​​with the common worst-case filling time. Based on this, an intelligent algorithm iteratively updates the second candidate lamination temperature set. For example, using a genetic algorithm, each temperature parameter group in the current set is first encoded as a chromosome, and its lamination optimization function value serves as the fitness evaluation criterion. In each iteration, the algorithm performs selection, crossover, and mutation operations: selection retains superior individuals based on fitness; crossover generates new solutions by exchanging gene segments from different chromosomes; and mutation randomly perturbs individual genes to maintain population diversity. By continuously repeating this process, the genetic algorithm can gradually explore unevaluated regions in the parameter space and evolve towards lower lamination optimization function values, thereby continuously generating new temperature parameter groups with better overall performance.

[0111] After multiple rounds of iterative optimization, the combination of temperature parameters that makes the lamination optimization function value reach the global optimum is selected from the finally generated candidate lamination temperature parameter set and determined as the target lamination temperature parameter set.

[0112] Finally, the candidate filling temperatures in the target lamination temperature parameter set are paired with the preset most unfavorable filling time to form a filling temperature-holding time parameter pair characterizing the process conditions of the filling stage. Simultaneously, the candidate crosslinking temperatures in this parameter set are paired with their corresponding crosslinking holding time values ​​obtained through a crosslinking simulation model to form a crosslinking temperature-holding time parameter pair characterizing the process conditions of the crosslinking stage. These two core process parameter pairs together constitute a thin-film crosslinking parameter set that can be directly used to guide the lamination production of photovoltaic modules.

[0113] S40: Perform lamination crosslinking for photovoltaic modules according to the set of thin film crosslinking parameters.

[0114] Based on the thin-film crosslinking parameter set determined by the aforementioned optimization process, the photovoltaic module lamination crosslinking process is performed on the target laminator. This thin-film crosslinking parameter set clearly defines the key process conditions for the filling and crosslinking stages, including the filling temperature and its corresponding holding time, and the crosslinking temperature and its corresponding holding time.

[0115] During implementation, the photovoltaic modules to be laminated are first placed in the working chamber of the laminator. The first stage of operation is carried out according to the filling temperature and corresponding holding time set in the parameter set. In this stage, the laminator heating system precisely controls the chamber temperature at the target filling temperature and maintains this temperature condition for the preset holding time. At the same time, the specified lamination pressure is applied to ensure that the ethylene vinyl acetate copolymer film is fully melted and flows and fills completely.

[0116] Secondly, the process automatically switches to the second stage based on the crosslinking temperature and corresponding holding time set in the parameter set. The laminator adjusts its operating temperature to the target crosslinking temperature and maintains this state for the calculated holding time, allowing the ethylene vinyl acetate copolymer film to complete the construction of a three-dimensional network crosslinking structure under controlled conditions.

[0117] In summary, through this staged precise control based on an optimized parameter set, a photovoltaic module encapsulation structure with complete interface bonding, satisfactory cross-linking degree, and excellent weather resistance is ultimately obtained.

[0118] In summary, the embodiments of this application have at least the following technical effects:

[0119] Compared to existing technologies, this invention first scientifically determines the range of key parameters affecting the degree of crosslinking based on prior evolutionary experimental data, providing clear boundary conditions for process optimization and overcoming the limitations of traditional methods that rely on experience for parameter setting. Secondly, by constructing a multi-stage simulation environment integrating filling simulation and thermal insulation crosslinking simulation, a calculable description of the entire lamination process is achieved, enabling accurate prediction of material behavior evolution under different process conditions. Thirdly, an iterative optimization method combining parameter space and simulation environment solves the problem of multi-parameter coupled optimization, significantly improving the accuracy and efficiency of process parameter setting. Finally, by outputting an optimized and verified set of thin-film crosslinking parameters, reliable operational guidance is provided for the photovoltaic module lamination crosslinking process, effectively ensuring the consistency and stability of product encapsulation quality.

[0120] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0121] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0122] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. An intelligent control method for the crosslinking degree of EVA film suitable for photovoltaic modules, characterized in that, The method comprises the following steps: Based on the prior evolution experiment of EVA film, the parameter space affecting the crosslinking degree is determined, wherein the parameter space at least includes the filling temperature interval and the crosslinking temperature interval; Combine the prior evolution experiment results with the target lamination scene of EVA film to build a multi-stage crosslinking simulation environment corresponding to the lamination process, wherein the multi-stage crosslinking simulation environment at least includes one filling simulation model and one heat preservation crosslinking simulation model; Iterative lamination simulation optimization is carried out combining the parameter space and the multi-stage crosslinking simulation environment, and the film crosslinking parameter set is determined according to the iterative lamination simulation optimization results, wherein the film crosslinking parameter set at least includes filling temperature-heat preservation time and crosslinking temperature-heat preservation time; According to the film crosslinking parameter set, the lamination crosslinking of photovoltaic module is carried out; Wherein, combining the parameter space and the multi-stage crosslinking simulation environment to carry out iterative lamination simulation optimization, and determining the film crosslinking parameter set according to the iterative lamination simulation optimization results, comprising: Based on the parameter space, randomly select parameters to generate a set of alternative lamination temperatures, wherein the set of alternative lamination temperatures includes a plurality of alternative lamination temperature parameter groups, and the alternative lamination temperature parameter group includes an alternative filling temperature and an alternative crosslinking temperature; Input the set of alternative lamination temperatures into the filling simulation model, run the simulation combining the preset most unfavorable filling time, and calculate the filling quality value based on the preset filling quality evaluation function, wherein the filling quality evaluation function at least includes the bubble volume fraction factor and the maximum flow distance factor; According to the filling quality value, a plurality of alternative lamination temperature parameter groups meeting the filling quality threshold are screened to obtain a second set of alternative lamination temperatures; Input the second set of alternative lamination temperatures into the heat preservation crosslinking simulation model, and solve the constraint with the target crosslinking degree value to obtain a plurality of crosslinking heat preservation time values; Define a lamination optimization function, and calculate a plurality of lamination optimization function values by combining the lamination optimization function, the crosslinking heat preservation time value, the second set of alternative lamination temperatures, and the most unfavorable filling time; Based on a plurality of the lamination optimization function values, the second set of alternative lamination temperatures is iteratively updated, and the alternative lamination temperature parameter group corresponding to the optimal lamination optimization function value is selected as the target lamination temperature parameter group according to the iterative update result; Merge the target lamination temperature parameter group, the most unfavorable filling time, and the corresponding crosslinking heat preservation time value to obtain the filling temperature-heat preservation time and the crosslinking temperature-heat preservation time, and output as the film crosslinking parameter set. 2.The intelligent control method for crosslinking degree of EVA film applied to photovoltaic module according to claim 1, wherein, Based on the prior evolution experiment of EVA film, the parameter space affecting the crosslinking degree is determined, wherein the parameter space at least includes the filling temperature interval and the crosslinking temperature interval, comprising: Based on the prior evolution experiment of EVA film, the corresponding rheological property-temperature evolution data is obtained, wherein the rheological property at least includes viscosity index and modulus index; Determine the lower limit of the filling temperature according to the rheological property-temperature evolution data; According to the rheological property-temperature evolution data, a suspected gel point is obtained, and a plurality of temperature points near the suspected gel point are randomly selected for oscillation frequency scanning test, and according to the oscillation frequency scanning test result, a temperature with the lowest correlation between the modulus indicator and the oscillation frequency is selected as the gel point; A plurality of critical temperatures of the EVA film are obtained, and the lowest one of the plurality of critical temperatures is selected as the crosslinking critical temperature, wherein the plurality of critical temperatures at least include a decomposition critical temperature, a yellowing critical temperature and a modulus change critical temperature; The filling temperature interval and the crosslinking temperature interval are defined by combining the filling temperature lower limit, the gel point and the crosslinking critical temperature, and the parameter space is obtained. 3.The intelligent control method for crosslinking degree of EVA film applied to photovoltaic module according to claim 2, wherein, A plurality of critical temperatures of the EVA film are obtained, and the lowest one of the plurality of critical temperatures is selected as the crosslinking critical temperature, including: The decomposition critical temperature is obtained by measuring the change of the mass of the EVA film sample with temperature through thermogravimetric analysis, and determining the temperature corresponding to the preset threshold value of the mass loss ratio. The yellowing critical temperature is obtained by a series of high-temperature isothermal experiments, combining the measurement of a plurality of yellowing index values of the EVA film after aging at a plurality of temperatures by a color difference meter, and identifying the temperature corresponding to the inflection point of the yellowing index value by the elbow method. The modulus change critical temperature is obtained by a series of high-temperature isothermal experiments, and a plurality of modulus plateau period curves of the EVA film sample at a plurality of temperatures are measured and obtained, and the lowest one of the modulus plateau period curves with negative slope and isothermal temperature is selected as the modulus change critical temperature. 4.The intelligent control method for crosslinking degree of EVA film applied to photovoltaic module according to claim 2, wherein, The filling temperature interval and the crosslinking temperature interval are defined by combining the filling temperature lower limit, the gel point and the crosslinking critical temperature, and the parameter space is obtained, including: The operating performance data of the target laminator are obtained, and the temperature control precision and the laminator temperature upper limit are extracted according to the operating performance data; The temperature control safety offset of the target laminator is calculated and determined by combining the temperature control precision and the preset temperature control safety coefficient N, wherein the temperature control safety offset is N times of the temperature control precision, and N is greater than 1; The difference between the gel point and the temperature control safety offset is calculated to obtain the filling temperature upper limit, and the sum of the gel point and the temperature control safety offset is calculated to obtain the crosslinking temperature lower limit; The crosslinking critical temperature is compared with the laminator temperature upper limit, and the crosslinking temperature upper limit is determined correspondingly according to the comparison result; The filling temperature interval is defined based on the filling temperature lower limit and the filling temperature upper limit, and the crosslinking temperature interval is defined based on the crosslinking temperature lower limit and the crosslinking temperature upper limit. 5.The intelligent control method for crosslinking degree of EVA film applied to photovoltaic module according to claim 4, wherein, The crosslinking critical temperature is compared with the laminator temperature upper limit, and the crosslinking temperature upper limit is determined correspondingly according to the comparison result, including: If the comparison result is that the crosslinking critical temperature is greater than the laminator temperature upper limit, the laminator temperature upper limit is taken as the crosslinking temperature upper limit; If the comparison result is that the crosslinking critical temperature is less than the laminator temperature upper limit, the difference between the crosslinking critical temperature and the temperature control safety offset is calculated correspondingly, and the output is the crosslinking temperature upper limit. 6.The intelligent control method for crosslinking degree of EVA film applied to photovoltaic module according to claim 1, wherein, In combination with the prior evolution experiment result and the target lamination scenario of the EVA film, a multi-stage cross-linking simulation environment corresponding to a lamination process is constructed, including: Based on the target lamination scenario, a physical model of a target laminator is established; According to the physical model, in combination with a prior thermal fluid physical equation and a finite element modeling method, the filling simulation model is constructed; Wherein, the input parameters of the filling simulation model at least include lamination pressure, lamination temperature and material evolution viscosity indication. 7.The intelligent control method for crosslinking degree of EVA film applied to photovoltaic module according to claim 1, wherein, In combination with the prior evolution experiment result and the target lamination scenario of the EVA film, a multi-stage cross-linking simulation environment corresponding to a lamination process is constructed, further including: Obtain historical lamination logs and corresponding sample cross-linking measured data, wherein the sample cross-linking measured data at least includes measured temperature, measured holding time and measured cross-linking degree; Taking the measured temperature and the measured holding time as sample input, and taking the measured cross-linking degree as supervision, a holding cross-linking simulation model based on regression analysis is constructed and trained. 8.The intelligent control method for crosslinking degree of EVA film applied to photovoltaic module according to claim 7, wherein, The holding cross-linking simulation model includes any one of a machine learning regression model and a mathematical regression model.

Images