Decorative paper weather resistance evaluation method and system

Abstract

The invention discloses a decorative paper weather resistance evaluation method and system, and relates to the technical field of weather resistance evaluation, and the method comprises the steps: determining the structural composition information and target application space of target decorative paper; determining an aging influence factor of the decorative paper; determining a weather resistance evaluation index; performing relation analysis, and establishing a weather resistance evaluation model; establishing a closed bias feedback layer and an open bias feedback layer; and performing dynamic characteristic analysis, inputting a dynamic characteristic analysis result into the optimized weather resistance evaluation model for analysis, and generating a target weather resistance evaluation result corresponding to the weather resistance evaluation index. The technical problems that in the prior art, decorative paper weather resistance evaluation is difficult to consider different scenes and the accuracy is insufficient are solved, the effect of accurately evaluating the weather resistance of the decorative paper is achieved, and the technical effects of improving the accuracy and reliability of aging performance evaluation of the decorative paper in different application scenes are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of weather resistance evaluation, and in particular to a method and system for evaluating weather resistance of decorative paper. Background Art

[0002] In the current application field of decorative paper, as its usage scenarios become more and more extensive, from indoor home decoration to outdoor advertising display, building exterior wall covering, etc., the consideration of the weather resistance of decorative paper is becoming increasingly critical. Traditional decorative paper weather resistance evaluation technology has many limitations. On the one hand, in the setting of evaluation indicators, it often only focuses on a single or a few aspects, such as only focusing on color difference changes, ignoring the importance of comprehensive consideration of multi-dimensional indicators such as mechanical properties, surface damage and gloss, resulting in a one-sided evaluation of the actual aging state of decorative paper. On the other hand, in terms of the inclusion of environmental factors, it fails to fully cover the key factors affecting the aging of decorative paper, such as only considering temperature and humidity, while not paying enough attention to factors such as pollutant exposure, ultraviolet radiation, and especially complex and changeable wind speed, which makes the evaluation results deviate greatly from the actual aging conditions in outdoor or special indoor environments. Furthermore, most of the existing technologies lack different application scenarios, and cannot accurately reflect the actual weather resistance performance of decorative paper in different environments, making it difficult to meet the current diversified usage needs.

[0003] The existing technology has technical problems that the weather resistance evaluation of decorative paper is difficult to take into account different scenarios and the accuracy is insufficient. Summary of the invention

[0004] The present application provides a decorative paper weather resistance evaluation method and system, which are used to solve the technical problem in the prior art that the decorative paper weather resistance evaluation is difficult to take into account different scenarios and lacks accuracy.

[0005] In view of the above problems, the present application provides a method and system for evaluating the weather resistance of decorative paper.

[0006] In a first aspect of the present application, a method for evaluating weather resistance of decorative paper is provided, the method comprising: Determine the structural composition information and target application space of the target decorative paper; determine the decorative paper aging influencing factors, wherein the decorative paper aging influencing factors include at least temperature, humidity, pollutant exposure, ultraviolet radiation and wind speed; determine the weather resistance evaluation index, wherein the weather resistance evaluation index includes at least color difference, mechanical properties, surface damage and gloss; construct an aging evaluation sample based on the structural composition information, perform a relationship analysis between the decorative paper aging influencing factors and the weather resistance evaluation index, and establish a weather resistance evaluation model; perform a systematic bias analysis of closed scenes and open scenes based on the weather resistance evaluation model, establish a closed bias feedback layer and an open bias feedback layer, and optimize the weather resistance evaluation model; perform a dynamic characteristic analysis on any factor of the decorative paper aging influencing factors for the target application space, input the dynamic characteristic analysis results into the optimized weather resistance evaluation model for analysis, and generate a target weather resistance evaluation result corresponding to the weather resistance evaluation index.

[0007] A second aspect of the present application provides a decorative paper weatherability evaluation system, the system comprising: a structural composition information determination module, used to determine the structural composition information and target application space of the target decorative paper; an aging influence factor determination module, used to determine the aging influence factor of the decorative paper, wherein the aging influence factor of the decorative paper at least includes temperature, humidity, pollutant exposure, ultraviolet radiation and wind speed; a weather resistance evaluation index determination module, used to determine the weather resistance evaluation index, wherein the weather resistance evaluation index at least includes color difference, mechanical properties, surface damage and glossiness; a weather resistance evaluation model establishment module, which constructs an aging evaluation sample based on the structural composition information, and performs an aging evaluation on the aging influence factor of the decorative paper and the weather resistance evaluation index. The invention relates to a weather resistance evaluation index, and establishes a weather resistance evaluation model; a bias feedback layer establishment module, which performs a systematic bias analysis of closed scenarios and open scenarios based on the weather resistance evaluation model, establishes a closed bias feedback layer and an open bias feedback layer, and optimizes the weather resistance evaluation model; a weather resistance evaluation result generation module, which is used to perform a dynamic characteristic analysis on any factor of the decorative paper aging influencing factors for the target application space, input the dynamic characteristic analysis results into the optimized weather resistance evaluation model for analysis, and generate a target weather resistance evaluation result corresponding to the weather resistance evaluation index.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: Determine the structural composition information and target application space of the target decorative paper; determine the decorative paper aging influencing factors; determine the weather resistance evaluation index; construct an aging evaluation sample based on the structural composition information, analyze the relationship between the decorative paper aging influencing factors and the weather resistance evaluation index, and establish a weather resistance evaluation model; conduct a systematic bias analysis of closed scenes and open scenes based on the weather resistance evaluation model, establish a closed bias feedback layer and an open bias feedback layer, and optimize the weather resistance evaluation model; conduct a dynamic characteristic analysis of any factor in the decorative paper aging influencing factors for the target application space, input the dynamic characteristic analysis results into the optimized weather resistance evaluation model for analysis, and generate a target weather resistance evaluation result corresponding to the weather resistance evaluation index. The effect of achieving accurate evaluation of the weather resistance of decorative paper is achieved, and the accuracy and reliability of the aging performance evaluation of decorative paper in different application scenarios are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic flow chart of a method for evaluating weather resistance of decorative paper provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a decorative paper weather resistance evaluation system provided in an embodiment of the present application.

[0011] Explanation of the reference numerals: structural composition information determination module 10, aging influence factor determination module 20, weather resistance evaluation index determination module 30, weather resistance evaluation model establishment module 40, bias feedback layer establishment module 50, weather resistance evaluation result generation module 60. DETAILED DESCRIPTION

[0012] The present application provides a decorative paper weather resistance evaluation method and system, which are used to solve the technical problems in the prior art that the decorative paper weather resistance evaluation is difficult to take into account different scenarios and lacks accuracy.

[0013] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0014] Embodiment 1, as Figure 1 As shown, the present application provides a method for evaluating weather resistance of decorative paper, the method comprising: Step S100: determining the structural composition information and target application space of the target decorative paper.

[0015] Specifically, determining the structural composition information and target application space of the target decorative paper is the key link at the beginning of the entire weather resistance evaluation process. For structural composition information, the fiber structure of the decorative paper is observed under a microscope to understand its fiber type, thickness and interweaving method, which factors will affect the paper's ability to resist external environmental factors. With the help of a spectroscopic analyzer, the chemical composition of the surface coating of the decorative paper is determined to clarify which polymer materials, pigments or additives the coating is composed of, because the coating plays a key role in moisture resistance and UV protection. At the same time, X-ray diffraction technology is used to explore whether the paper contains mineral fillers and other ingredients that enhance toughness. In determining the target application space, many factors should be considered comprehensively. If it is an indoor application space, it is further subdivided, such as a home living room environment, and the daily light intensity needs to be considered. It is generally a mixture of indirect natural light and indoor light, and the lighting time depends on the owner's living habits; the temperature is relatively stable, usually 18-25℃, and the humidity is affected by the season and equipment such as air conditioning, roughly 40%-60%. If used in the kitchen, in addition to greater fluctuations in temperature and humidity, it also faces oil fume pollution, which contains pollutants such as grease particles and organic volatiles. For commercial places such as shopping malls and exhibition halls, the light intensity is high and lasts for a long time, and the frequent flow of people brings more dust and other pollutants. The temperature and humidity are controlled by central air conditioning but are relatively stable during business hours. If it is an outdoor application space, such as decorative paper on the exterior walls of buildings, the local climate zone characteristics must be considered. In tropical areas, there is high temperature, high humidity, strong ultraviolet radiation, and frequent rainstorms; in temperate areas, the four seasons are distinct, the temperature and humidity vary greatly, and there may be ice and snow erosion in winter; in arid areas, low humidity, strong winds and sand, and ultraviolet radiation should not be underestimated. Through careful investigation of these factors, the structural composition information and target application space of the target decorative paper can be accurately determined, laying a solid foundation for the subsequent accurate evaluation of its weather resistance.

[0016] Step S200: determining factors affecting aging of decorative paper, wherein the factors affecting aging of decorative paper at least include temperature, humidity, pollutant exposure, ultraviolet radiation and wind speed.

[0017] Specifically, it is crucial to determine the factors affecting the aging of decorative paper. For temperature, data from different regions are collected with the help of high-precision thermometers and temperature data acquisition systems. In tropical areas, the average summer temperature exceeds 30°C, which will cause the polymer chains in the decorative paper to break, the structure to loosen, and the mechanical properties to decline; in temperate areas, the temperature difference between winter and summer exceeds 30°C, which causes thermal expansion and contraction of the paper, stress concentration, and cracking of the paper. Humidity is monitored through a professional humidity sensor network. The humidity in coastal areas is 70%-90%, which is conducive to the growth of mold, and its secreted enzymes corrode the surface coating of decorative paper; the humidity of 20%-30% in arid areas causes the paper to lose water and become brittle, and its flexibility and tensile resistance deteriorate. In terms of pollutant exposure, samples from the central area of ​​the city are collected using atmospheric composition sampling and analysis equipment. Industrial and automobile exhaust contain acidic gases, which form acid rain when encountering moisture on the surface of paper to corrode the paper; indoor kitchens are monitored with grease particle detection devices. The attachment of oil fume and grease particles hinders air permeability and accelerates the aging of paper. Ultraviolet radiation is monitored by an ultraviolet radiation intensity detector. The intensity in plateaus is 30%-50% higher than that in plains, which can cause pigments to fade, destroy chemical bonds, and reduce paper strength. Long-term accumulated radiation near windows indoors can also cause damage. Wind speed is monitored by anemometers in coastal strong wind areas, mountain pass wind tunnels, etc. Strong winds carry sand and dust, which, according to the principle of wear, will wear the surface of decorative paper, make the paper thinner, damage the coating, and accelerate aging. The combination of these collections and analyses lays the foundation for weather resistance evaluation.

[0018] Step S300: determining weather resistance evaluation indicators, wherein the weather resistance evaluation indicators at least include color difference, mechanical properties, surface damage and glossiness.

[0019] Specifically, accurately determining the weather resistance evaluation index is a key link in evaluating the quality and durability of decorative paper. As a core index, color difference is measured using a professional colorimeter. By comparing the color changes of decorative paper before and after aging, the degree of color difference can be quantified. For example, under long-term ultraviolet radiation, high temperature or pollutant erosion, the molecular structure of the decorative paper pigment may change, causing the color to become lighter, darker or shift in hue. The color difference index can directly reflect the degree of visual deterioration and provide a basis for users to judge the appearance retention of decorative paper. Mechanical properties cover tensile strength, tear strength and other aspects. Using a universal material testing machine, mechanical tests such as stretching and tearing are performed on decorative paper samples before and after aging. When decorative paper is affected by humidity and temperature changes, the internal fiber structure may be damaged, and the performance of polymer materials changes. This is reflected in the mechanical properties as reduced tensile strength, easier to break paper, reduced tear strength, and easier to tear after a small crack. These data changes accurately show the changes in the physical durability of decorative paper. Surface damage indicators are determined by microscopic observation and image analysis technology. Under the influence of aging factors such as mold, sand erosion, and pollutant corrosion in high humidity environments, the decorative paper surface may be damaged by mildew, scratches, holes, etc. With the help of a high-power microscope, the surface of the decorative paper is imaged, and then the image analysis software is used to identify the damage type, quantity, area ratio and other parameters, which can intuitively present the surface damage condition, which is related to the beauty and protective function of the decorative paper. The glossiness is measured by a gloss meter, which emits light at a specific angle to illuminate the decorative paper and measures the intensity of the reflected light. If the decorative paper is eroded by acid rain, daily wiping and wear, etc., its surface microstructure changes, the smoothness decreases, and the glossiness decreases, which affects the decorative effect and texture of the decorative paper. Comprehensively considering the color difference, mechanical properties, surface damage and glossiness, these indicators can comprehensively and accurately evaluate the weather resistance of decorative paper in different environments.

[0020] Step S400: constructing an aging evaluation sample based on the structural composition information, performing relationship analysis on the decorative paper aging influencing factor and the weather resistance evaluation index, and establishing a weather resistance evaluation model.

[0021] Specifically, key operations are started based on the target decorative paper structure composition information obtained in the early stage. First, with this as a constraint, historical data in different environments and different time periods are widely collected, including the application time of historical decorative paper, such as recording the use cycle of a certain decorative paper outdoors for 3 years, and the service data of indoor wallpaper for 5 years, etc.; there are also historical influencing factor characteristic time series for the corresponding time period. For example, in the outdoor environment, temperature and humidity sensors, ultraviolet radiation monitors, air quality collectors, anemometers and other equipment are used to continuously record detailed information such as temperature fluctuations, humidity changes, ultraviolet radiation intensity, pollutant composition and concentration, wind speed, etc. every hour, every day, and even every month. In the indoor environment, the temperature and humidity in different areas such as the living room and the kitchen are also accurately collected with the seasons and usage scenarios; as well as the historical weather resistance evaluation index time series, using tools such as colorimeter, universal material testing machine, microscope combined with image analysis software, gloss meter, etc., to periodically detect the color difference evolution, mechanical property attenuation, surface damage, gloss reduction and other quantitative data during the aging process of decorative paper. These massive and orderly data are integrated to construct an aging evaluation sample. Next, for any influencing factor of the decorative paper aging, such as temperature, and the weather resistance evaluation index, we carried out an in-depth analysis of the influence of temporal variables, and observed how the color difference of the decorative paper changes with the temperature rise and fall when the temperature changes from season to season and from day to night, how the mechanical properties gradually decay, whether the surface damage is accelerated, and whether the glossiness is stable, so as to establish a single factor temporal evaluation channel. At the same time, we conducted a fusion effect analysis on each influencing factor, and combined different combinations of temperature and humidity, ultraviolet radiation and pollutant exposure, and paired any two, three or four of them, and analyzed the superimposed effects of them on the weather resistance evaluation index when they acted together on the decorative paper, such as how much faster the aging rate of decorative paper in a high temperature and high humidity environment is compared with that in a normal temperature and humidity environment, and the degree of deterioration of the mechanical properties of decorative paper when ultraviolet radiation and acid rain erode together, so as to construct an evaluation fusion layer. Finally, we cleverly combined the single factor temporal evaluation channel and the evaluation fusion layer to establish a set of accurate and comprehensive weather resistance evaluation models, which provided the core basis for the subsequent accurate evaluation of the weather resistance of decorative paper.

[0022] Step S500: performing systematic bias analysis of closed scenarios and open scenarios based on the weather resistance evaluation model, establishing a closed bias feedback layer and an open bias feedback layer, and optimizing the weather resistance evaluation model.

[0023] Specifically, in order to further improve the accuracy of the weather resistance evaluation model, a key optimization process was initiated. First, systematic bias analysis was carried out for closed scenes and open scenes respectively. For closed scenes, such as indoor exhibition halls, archives and other environments, the temperature and humidity sensors, light intensity detectors, air quality monitors and other equipment arranged therein are used to collect the characteristic values ​​of the actual decorative paper aging influencing factors, accurately record the application time of the decorative paper in the closed environment, and use colorimeter, mechanical performance testing equipment, etc. to obtain the actual weather resistance evaluation index values ​​and construct the first sample set. This sample set is input into the weather resistance evaluation model for testing. The model will output the corresponding prediction results, compare the actual values ​​with the predicted values, identify the deviation between the two, and eliminate discrete values ​​through data statistics and analysis methods. The relationship between the systematic test deviation and the characteristic value of the actual decorative paper aging influencing factors is deeply analyzed, and then the systematic deviation impact curve is generated to construct a closed bias feedback layer. Similarly, in open scenarios, such as outdoor building exterior walls and open-air billboards, various environmental monitoring instruments installed on site, including high-precision thermometers, wind speed and direction meters, ultraviolet radiation monitoring equipment, and atmospheric pollutant sampling and analysis devices, are used to collect the actual characteristic values ​​of decorative paper aging influencing factors, combined with the accurately recorded decorative paper application time and the actual weather resistance evaluation index values ​​obtained through professional testing methods to form the second sample set. The second sample set is input into the weather resistance evaluation model for testing, and the above deviation analysis process is repeated to construct an open bias feedback layer. Finally, the closed bias feedback layer and the open bias feedback layer are connected in parallel to the output end of the weather resistance evaluation model, so that the model can automatically call the corresponding feedback layer to optimize and adjust the output results according to the input scene information in subsequent operation, thereby greatly improving the accuracy and reliability of the weather resistance evaluation model for the weather resistance evaluation of decorative paper in different scenarios, and laying a solid foundation for accurately evaluating the durability of decorative paper in various practical applications.

[0024] Step 600: performing a dynamic characteristic analysis on any factor of the decorative paper aging influencing factors for the target application space, inputting the dynamic characteristic analysis result into the optimized weather resistance evaluation model for analysis, and generating a target weather resistance evaluation result corresponding to the weather resistance evaluation index.

[0025] Specifically, it is crucial to accurately grasp the characteristics of the target application space. First, conduct a dynamic characteristic analysis of any factor in the aging influencing factors of decorative paper for the target application space. If the target application space is an indoor smart office area, for the temperature factor, determine whether the space is equipped with an intelligent temperature control device. If so, connect the device to obtain the real-time adjustment target, such as setting the temperature to 26°C in summer and 22°C in winter. This is the dynamic characteristic analysis result of the temperature factor in this space; if there is no temperature control equipment, obtain the geographical location information of the office area, and use the local meteorological historical data to calculate the temperature change pattern of the area with the season and day and night in a year, such as the average daytime temperature of 30°C and 25°C at night in summer, and 10°C and 5°C at night in winter. Similarly, other factors such as humidity and ultraviolet radiation are also operated in the same way. After completing the dynamic characteristic analysis, the results are input into the optimized weather resistance evaluation model. The model is based on the single-factor temporal evaluation channel, evaluation fusion layer, and closed and open bias feedback layers constructed in the early stage, combined with the input dynamic characteristic analysis results, and predicts the future weather resistance performance of decorative paper for the preset evaluation time, and performs complex calculations and in-depth analysis. First, the aging process of decorative paper under the dynamic changes of various factors in different time periods is simulated, and then by matching the closed type of the target application space, such as the office area mentioned above is a closed space, the closed bias feedback layer is automatically called to optimize and calibrate the preliminary analysis results, and finally generate the target weather resistance evaluation results that accurately correspond to the weather resistance evaluation indicators, including the future color difference change range of decorative paper, the degree of mechanical property attenuation, the estimated surface damage status, and the gloss reduction range, etc., providing key basis for the actual application decision of decorative paper.

[0026] In a possible implementation, step S400 further includes: Step S410: Taking the structural composition information as a constraint, collecting the historical decorative paper application time, historical influencing factor feature time series and historical weather resistance evaluation index time series to construct the aging evaluation sample.

[0027] Step S420: Based on the aging evaluation sample, a temporal variable impact analysis is performed on any influencing factor of the decorative paper aging influencing factor and the weather resistance evaluation index to establish a single factor temporal evaluation channel.

[0028] Step S430: Based on the aging evaluation sample, a fusion effect analysis is performed on each influencing factor of the decorative paper aging influencing factor to construct an evaluation fusion layer.

[0029] Step S440: combining the single factor temporal evaluation channel and the evaluation fusion layer to establish the weather resistance evaluation model.

[0030] Specifically, the structural composition information of the target decorative paper is used as the core constraint to start comprehensive data collection. The historical data of decorative paper in different application scenarios in the past are deeply excavated, and the application time of historical decorative paper is accurately recorded. For example, the decorative paper in a museum has been used for 8 years, and the decorative paper of an outdoor billboard has gone through 5 seasons. At the same time, a series of professional monitoring equipment, such as temperature and humidity sensors, ultraviolet radiation detectors, air quality collectors, etc., are used to continuously collect the characteristic time series of historical influencing factors at fixed time intervals (such as every hour, every day). For example, in the outdoor environment, the temperature fluctuations, humidity increase and decrease trends, day and night fluctuations of ultraviolet radiation intensity, and time period changes of pollutant concentrations in a year are recorded in detail; in the indoor environment, the temperature and humidity in areas such as living rooms and bedrooms are also accurately monitored with the seasons, usage scenarios, and possible light and pollutant conditions. In addition, with the help of tools such as colorimeter, universal material testing machine, microscope combined with image analysis software, gloss meter, etc., the historical weather resistance evaluation index time series of the decorative paper aging process is periodically detected to quantify its color difference evolution, mechanical property attenuation, surface damage, gloss reduction and other data. These rich and orderly data are integrated and aggregated to carefully construct an aging assessment sample.

[0031] Based on the carefully constructed aging evaluation samples, an in-depth analysis of the temporal variables between the aging influencing factors of decorative paper and the weather resistance evaluation indicators is carried out to establish a single factor temporal evaluation channel. Taking temperature as an example, the key influencing factor, long-term temperature data is first accurately extracted from the aging evaluation samples, covering the specific temperature values ​​of different years, seasons, and day and night periods, as well as the corresponding decorative paper application time information. These data are organized into a structured data set, in which temperature data and application time are used as independent variables, and weather resistance evaluation indicators such as color difference, mechanical properties, surface damage, and glossiness are used as dependent variables. Subsequently, a multivariate linear regression algorithm is used to try to construct a mathematical model between independent variables and dependent variables. Through the learning of a large number of data samples by the algorithm, the influence coefficient of each independent variable on the dependent variable is calculated, so as to clearly quantify the degree of influence of temperature changes and time on various weather resistance indicators of decorative paper. For example, the model may reveal that for every 5°C increase in temperature, the color difference of decorative paper will increase by 2 units and the tensile strength will decrease by 10% when the application time increases by 1 year. At the same time, the ARIMA model in time series analysis is introduced to fully consider the autocorrelation and seasonal fluctuation characteristics of temperature data over time, and further optimize the prediction of the changing trend of weather resistance indicators. With the help of this model, not only can the immediate impact of the current temperature change on the decorative paper be accurately captured, but also, based on the historical temperature fluctuation law, it can be predicted that in the future, as the temperature continues to change, the weather resistance indicators of decorative paper, such as surface damage, may gradually deteriorate. By comprehensively using these advanced machine algorithms, the temporal relationship between temperature factors and weather resistance evaluation indicators is analyzed in all aspects, and a single-factor temporal evaluation channel for temperature is established. Similar operations are then repeated for other influencing factors such as humidity and ultraviolet radiation, ultimately providing key support for the accurate construction of a weather resistance evaluation model.

[0032] Based on the existing aging evaluation samples, the key fusion effect analysis is started. First, look at the combination of two influencing factors. Take temperature and humidity as an example. Detailed data in different time periods and application scenarios, as well as the corresponding weather resistance evaluation index values, are accurately screened from the aging evaluation samples. By comparing the changes in decorative paper under high temperature and high humidity and normal temperature and humidity environments, data analysis tools are used to explore whether the color difference increases, whether the mechanical properties decline faster, whether the surface damage is more serious, and the magnitude of the change in gloss. For example, it is found that in the hot and humid summer outdoor environment, the color difference of decorative paper may increase by 5 units in just a few months compared to the normal temperature and humidity environment, and the tensile strength decreases by 15%. Then focus on the combination of ultraviolet radiation and pollutant exposure, extract relevant information from the sample data. When ultraviolet radiation is strong and accompanied by pollutants such as industrial waste gas and automobile exhaust, the surface of the decorative paper is observed with the help of professional analysis methods. It is found that its chemical bond breakage is accelerated, the surface damage quickly develops from fine scratches to obvious corrosion spots, and the glossiness also drops sharply. For multiple factor combinations, such as the synergistic effects of temperature, humidity, and ultraviolet radiation, data modeling technology is used to build a model that reflects their complex interactive relationships based on the historical data of these factors and the corresponding weather resistance evaluation indicators. This model can accurately predict how the mechanical properties of decorative paper decay over time and at what rate the surface damage deteriorates under specific temperature, humidity, and ultraviolet conditions. By integrating the analysis results of these different combinations of influencing factors, an evaluation fusion layer was successfully constructed, which fully demonstrates the comprehensive effect of the fusion of multiple factors on the weather resistance of decorative paper.

[0033] Using the weighted fusion strategy, the weights of the single-factor dynamic model and the evaluation fusion layer model are initialized, and the sum is 1. Based on the validation data set, the prediction accuracy indicators of the two models, such as the root mean square error (RMSE), are calculated in different actual scenarios, such as indoor stable environment (single factor dominant) and outdoor complex climate (multiple factors interact significantly). If the RMSE of the single-factor model is smaller in the indoor scene, indicating that the prediction is more accurate, it is increased by a certain step size (such as 0.05) and reduced accordingly; conversely, if the RMSE of the evaluation fusion layer model is dominant in the outdoor scene, the weight is adjusted to tilt towards it. By repeatedly iterating and optimizing this process on the training set and the validation set, the two are closely combined to build an accurate and reliable weather resistance evaluation model. Once the structural composition of the decorative paper, the environmental parameters of the target application scenario and the expected use time are input, the model can quickly output the detailed evolution of various weather resistance indicators of the decorative paper in the future with the built-in algorithm and the previous massive data learning results, providing strong technical support for the durability evaluation of decorative paper.

[0034] In a possible implementation, step S430 further includes: Step S431: combining any two factors of the decorative paper aging influencing factors, and performing a joint action superposition relationship analysis based on the aging evaluation sample and the weather resistance evaluation index to generate a first superposition relationship.

[0035] Step S432: combining any three factors of the decorative paper aging influencing factors, and performing a joint action superposition relationship analysis based on the aging evaluation sample and the weather resistance evaluation index to generate a second superposition relationship.

[0036] Step S433: combining any four factors of the decorative paper aging influencing factors, and performing a joint action superposition relationship analysis based on the aging evaluation sample and the weather resistance evaluation index to generate a third superposition relationship.

[0037] Step S434: generating the evaluation fusion layer based on the first superposition relationship, the second superposition relationship and the third superposition relationship.

[0038] Specifically, when analyzing the combined effect of any two factors in the factors affecting the aging of decorative paper to generate the first superposition relationship, the common combination of temperature and humidity is taken as an example. First, from the rich aging evaluation sample database, the detailed continuous data of temperature and humidity in various historical periods and covering various application scenarios (such as indoor office areas, outdoor billboards, home bedrooms, etc.) and the corresponding precise quantitative values ​​of weather resistance evaluation indicators are accurately retrieved. Then, the variance analysis algorithm is used to take different temperature and humidity combination scenarios (normal temperature and humidity, high temperature and high humidity, low temperature and high humidity, low temperature and low humidity, etc.) as grouping variables, and the color difference, mechanical properties (tensile strength, tear strength, etc.), surface damage, gloss and other weather resistance evaluation indicators as dependent variables. The algorithm is used to calculate the inter-group variance and the intra-group variance to measure the significant difference in the impact of different temperature and humidity combinations on various weather resistance indicators. For example, in the comparative analysis of the high temperature and high humidity group and the normal temperature and humidity group, the variance analysis results show that for the color difference index, the inter-group variance is significantly greater than the intra-group variance, indicating that the combined change of temperature and humidity has a significant effect on color difference. At the same time, a linear regression algorithm is introduced, and a multivariate linear regression model with each weather resistance index is constructed with temperature and humidity values ​​as independent variables. Based on the principle of least squares method, the regression coefficient is determined through iterative training of a large amount of sample data. For example, the relationship model between the color difference change of decorative paper and temperature and humidity in a specific application scenario is obtained: color difference = a×temperature+b×humidity+c (a, b, c are regression coefficients), which accurately quantifies the superposition effect of the two on color difference when they work together. The results of the comprehensive variance analysis to determine the significance of the impact and the specific relationship quantified by linear regression clearly show the first superposition relationship of various weather resistance indicators when the two factors of temperature and humidity act together on the decorative paper, providing key basic data for the subsequent construction of a comprehensive evaluation fusion layer.

[0039] Taking any three factors affecting the aging of decorative paper as an example, we selected three typical combinations of factors affecting the aging of decorative paper, namely, ultraviolet radiation, temperature and pollutant exposure. First, we extracted their detailed data in different periods and environments from the aging evaluation samples, including ultraviolet radiation intensity values, temperature values, pollutant composition and concentration data, and obtained the corresponding weather resistance evaluation index data, such as color difference, tensile strength, surface damage degree, gloss and other quantitative values. Then, we used the principal component analysis (PCA) algorithm to reduce the dimensionality of the original high-dimensional data, highlight key information, and reduce the amount of subsequent calculations. Then, we used the partial least squares regression (PLSR) method to construct a regression model with the reduced dimensionality ultraviolet radiation, temperature, and pollutant-related data as independent variables and the weather resistance evaluation index as the dependent variable. Through multiple iterative optimizations and solving the regression coefficients, we obtain relationship expressions such as “Tensile strength attenuation = a×UV radiation intensity + b×temperature + c×pollutant concentration + d×UV radiation intensity × temperature + e×UV radiation intensity × pollutant concentration + f×temperature × pollutant concentration + g” (ag is the regression coefficient). This accurately quantifies the superimposed effects of the three on weather resistance indicators such as tensile strength, and then generates a second superposition relationship.

[0040] Using a recursive algorithm, we select from the existing set of at least four aging influencing factors, such as temperature, humidity, pollutant exposure, and ultraviolet radiation, step by step. First, we select one factor, then select from the remaining ones, and repeat this process until we have four, such as temperature, humidity, ultraviolet radiation, and pollutant exposure as a group, or temperature, wind speed, ultraviolet radiation, and pollutant exposure in different combinations, and clearly list all the combinations. We establish a close connection with the aging assessment sample data, which are generally stored in the database. At this time, we use a method similar to writing query statements to accurately extract the information of the corresponding time period from the database table based on the specific identification of the combination. For example, for a certain combination, the query statement clearly tells the database to find the application time of each time period under this combination, the temperature, humidity, ultraviolet radiation value, and pollutant exposure value at that time, as well as the corresponding weather resistance evaluation indicators, such as color difference, mechanical properties, surface damage, and gloss values, to quickly obtain the required data set. Finally, a multivariate linear regression model was built, with the four aging influencing factors as independent variables and the weather resistance evaluation index as the dependent variable. By continuously substituting data and using the gradient descent method and other means to adjust the coefficients in the model, the linear relationship between the factors and the index was initially explored. On the other hand, a neural network model was constructed, with the input layer corresponding to the four factors, two hidden layers in the middle, and a suitable activation function. During training, the data obtained earlier was input in batches, allowing the model to learn more complex and deep nonlinear relationships, and finally accurately excavating the intrinsic connection between the four factors and the weather resistance evaluation index when they work together, generating a reliable third superposition relationship.

[0041] When generating an evaluation fusion layer based on the existing first superposition relationship, second superposition relationship and third superposition relationship, a weighted fusion algorithm is used, that is, the frequency ratio of the prediction of the final weather resistance evaluation result corresponding to the feature vector groups based on the first superposition relationship, the second superposition relationship and the third superposition relationship in the historical sample data is first counted respectively, and this is used as the weight W1, W2, and W3, and then the three feature vector groups are weighted and summed according to their respective weights to obtain a fused feature vector group, thereby constructing an evaluation fusion layer that can comprehensively reflect the synergistic effect of all aging influencing factors on the weather resistance of decorative paper.

[0042] In a possible implementation, step S500 further includes: Step S510: collecting aging evaluation samples, wherein the aging evaluation samples include a first sample set and a second sample set, the first sample set is the characteristic values ​​of actual decorative paper aging influencing factors, decorative paper application time, and actual weather resistance evaluation index values ​​collected in a closed scene, and the second sample set is the characteristic values ​​of actual decorative paper aging influencing factors, decorative paper application time, and actual weather resistance evaluation index values ​​collected in an open scene.

[0043] Step S520: testing the first sample set using the weather resistance evaluation model, identifying systematic bias in a closed scenario based on the test results, and constructing the closed bias feedback layer.

[0044] Step S530: testing the second sample set using the weather resistance evaluation model, identifying the systematic bias in an open scenario based on the test results, and constructing the open bias feedback layer.

[0045] Step S540: connecting the closed bias feedback layer and the open bias feedback layer in parallel to the output end of the weather resistance evaluation model to complete the optimization of the weather resistance evaluation model.

[0046] Specifically, we collect aging evaluation samples through various pre-built high-precision sensor networks and data collection programs. For closed scenarios, temperature sensors, humidity sensors, UV sensors (used to detect trace UV rays that may penetrate windows or lighting equipment), pollutant monitors, and anemometers deployed in closed environments such as indoor exhibition halls and constant temperature and humidity storage rooms transmit the aging influencing factor characteristic values ​​of the actual decorative paper environment to me in real time, including temperature values ​​accurate to one decimal place, such as 22.5℃, humidity maintained at 49.8%, and the extremely small values ​​corresponding to the wind speed of nearly zero, as well as detailed quantitative pollutant composition and concentration, weak UV radiation intensity; at the same time, relying on the built-in clock to accurately record the application time of the decorative paper from the moment it is installed and activated, accumulated in milliseconds, and through professional image acquisition and analysis equipment, mechanical properties testing equipment, the corresponding actual weather resistance evaluation index values ​​are measured, and the color difference is accurately quantified to 0.1 unit changes, specific parameters of subtle changes in mechanical properties, surface damage degree scratch depth or damaged area ratio in millimeters, gloss attenuation percentage values ​​and other information are fully collected to form the first sample set. When facing open scenes, the enhanced sensor combination distributed in outdoor billboards, building exterior walls and other areas begins to operate. The temperature sensor can adapt to a wide range of fluctuations from -20℃ to 40℃, the humidity sensor can sensitively capture the sudden change of humidity caused by rain, fog and other weather conditions, the high-sensitivity ultraviolet radiation sensor can accurately measure the intensity of strong and long-lasting ultraviolet rays under direct sunlight, the comprehensive air pollutant monitor can analyze the complex and diverse pollutant components and concentrations in real time, and the wind speed and direction meter can dynamically track the wind speed changes and directions, and quickly feedback the characteristic values ​​of the aging influencing factors faced by the actual decorative paper in the open scene, such as the temperature can reach 35.2℃ during the high temperature period in summer, the humidity can instantly soar to more than 90% after heavy rain, the wind speed can exceed 10 meters / second during strong winds, and the ultraviolet radiation reaches its peak in the afternoon on sunny days; combined with the precise time synchronization module to record the duration of the decorative paper being tested in the complex outdoor environment, subdivided into hours based on days; then use the outdoor special weather resistance testing equipment to obtain the corresponding actual weather resistance evaluation index values, accurately record the real-time changes of color difference, mechanical properties, surface damage and gloss under variable outdoor conditions, and gather them into the second sample set.

[0047] For the first sample set, the characteristic values ​​of the actual decorative paper aging influencing factors in the closed scene, including accurate temperature, humidity, ultraviolet radiation intensity, pollutant concentration data, and application time down to milliseconds, are strictly arranged and input according to the established format of the weather resistance evaluation model. The hybrid algorithm of the built-in multiple linear regression and neural network is quickly operated. The multiple linear regression initially builds a linear prediction framework, and gives basic predictions with aging factors as independent variables and weather resistance evaluation indicators as dependent variables. The neural network uses nonlinear fitting capabilities to dig deep into complex relationships for optimization and outputs the predicted weather resistance evaluation index values. Then, the clustering algorithm is used to compare the predicted values ​​with the actual values, and similar deviation sample subsets are found by grouping according to the deviation size, direction, and trend. Subsequently, the Pearson correlation coefficient algorithm is used to analyze the correlation between the deviation and the characteristic value of the aging factor in each subset, such as the change law of the color difference prediction deviation when the indoor temperature fluctuates, and the deviation distribution model is constructed to complete the identification of the systematic bias of the closed scene, convert the relationship between the deviation and the factor function into a digital adjustment parameter, integrate it into the algorithm architecture, and finally construct a closed bias feedback layer.

[0048] Similarly, for the second sample set, the processing flow is similar. The characteristic values ​​of aging influencing factors in open scenarios, such as variable outdoor temperature, unstable humidity, strong ultraviolet rays, complex pollutants, and uncertain wind speed, are accurately entered into the model together with the application time. After the model calculates and outputs the predicted value, it is compared with the actual value. At this time, considering the complex and variable nature of the outdoor environment, adaptive algorithms such as chaos theory analysis and wavelet transform are used to mine deviation characteristics. Because factors such as outdoor temperature and wind speed often change nonlinearly, these algorithms are used to identify complex fluctuation patterns such as mechanical performance deviations during high temperature and strong wind periods, and an open scenario deviation distribution model is constructed to complete systematic bias identification. The relevant rules are then converted into adjustment parameters to construct an open bias feedback layer, laying the foundation for subsequent model optimization.

[0049] To optimize the weather resistance evaluation model, the closed bias feedback layer runs based on the built-in high-precision algorithm and rich local database. When the model outputs the weather resistance prediction results of the decorative paper under the set environmental parameters, such as the values ​​of various indicators after being placed in a certain temperature, humidity, and ultraviolet intensity scene for a certain period of time, it quickly retrieves the historical data of similar conditions, uses algorithms such as mean square error to compare the deviation, and generates a digital coded feedback signal according to the correction rule when the threshold is exceeded. At the same time, the open bias feedback layer builds a multi-element acquisition fusion system, relying on the outdoor sensor network to capture the state of the decorative paper in the natural climate in real time, using image recognition and MEMS sensors to quantify damage and monitor the environment; the machine learning algorithms used include Bayesian networks and decision tree algorithms to generate optimization instructions. Finally, through the parallel interface and synchronization mechanism, the two are connected in parallel to the model output for collaborative optimization.

[0050] In a possible implementation, step S520 further includes: Step S521: testing the first sample set using the weather resistance evaluation model to establish a systematic test deviation set.

[0051] Step S522: after removing discrete values ​​from the systematic test deviation set, analyzing the relationship between the systematic test deviation and the characteristic value of the actual decorative paper aging influencing factor, and generating a systematic deviation influence curve.

[0052] Step S523: constructing the closed bias feedback layer using the systematic deviation influence curve.

[0053] Specifically, first, the multi-dimensional data corresponding to each sample in the first sample set, including the material category of the decorative paper (different paper, plastic materials, etc. are identified by specific codes), the environmental parameters (temperature and humidity are recorded by precise sensor measurements, ultraviolet radiation intensity is quantified by professional radiation meters, and pollutant concentration is based on chemical analysis instrument data), and the preset usage time and other information, are organized into vector forms that are suitable for the model input format. Then, these vectors are input into the weather resistance evaluation model in turn. The model is based on an internal deep learning architecture, such as a multi-layer perceptron (MLP), whose neuron nodes perform complex calculations based on the aging laws of decorative paper learned from massive training data in the past. For each input sample, the model outputs the corresponding predicted values ​​of various weather resistance indicators, including color difference prediction values ​​(quantified values ​​of color changes in simulated environments are obtained based on color space conversion algorithms), mechanical property attenuation prediction (tensile strength, tear strength, etc. are calculated through stress-strain simulation algorithms), surface damage degree estimation (quantified scratches, wear, etc. are determined by combining image recognition and texture analysis algorithms), and gloss change inference (the reduction value of gloss units is calculated using light reflection models). At the same time, the difference between each predicted value output by the model and the actual weather resistance index value that was accurately measured and stored in the sample set in advance was calculated pair by pair according to the mean square error (MSE) algorithm. The obtained deviation values ​​were arranged in order according to the sample numbers, and finally a systematic test deviation set was successfully established, which accurately reflected the overall deviation of the model's current test on the first sample set.

[0054] The box plot method in statistics is used to identify and eliminate discrete values. The deviation values ​​of each weather resistance index are used as the data basis to draw a box plot. The normal data interval is determined based on the position of the upper and lower edges of the box and the upper and lower lines. The data points outside the interval are discrete values. These abnormal points are removed from the deviation set to ensure the reliability of the subsequent analysis data. After the discrete values ​​are eliminated, for each actual decorative paper aging influencing factor, such as temperature, the corresponding weather resistance index deviation data under different temperature conditions are extracted from the deviation set, and the linear regression analysis method is used to explore the potential linear relationship between the two. When the temperature rises, whether the deviations of color difference, mechanical properties, etc. show a linear increase or a more complex change trend; the same operation is performed for factors such as humidity and ultraviolet radiation. After a comprehensive analysis of the relationship between each factor and the deviation, a suitable data fitting algorithm is selected. If it is found that most relationships are close to the form of a quadratic function, a quadratic polynomial fitting is adopted. The values ​​of each factor are taken as the independent variable, and the corresponding systematic deviation of the weather resistance index is taken as the dependent variable. The polynomial coefficients are accurately determined through a large number of calculations, and then a systematic deviation influence curve is generated that can intuitively show the dynamic changes of the systematic test deviation with the characteristic value of the actual aging influencing factor, providing key guidance for subsequent model optimization.

[0055] When constructing a closed bias feedback layer, first extract key information from the systematic deviation impact curve. According to the deviation change trend of weather resistance index corresponding to different aging influencing factors (such as temperature, humidity, ultraviolet radiation, etc.) presented by the curve, determine the initial weight distribution within the feedback layer. For example, if it is found that the color difference deviation of decorative paper increases sharply when the temperature rises, a higher initial weight is set for the adjustment module corresponding to the temperature factor in the closed bias feedback layer, so that it is more sensitive to the color difference problem caused by temperature in the subsequent feedback adjustment process. At the same time, according to the deviation changes caused by the synergy between the factors reflected by the curve, a complex internal correlation structure is constructed. For example, when ultraviolet radiation and temperature increase at the same time, resulting in a nonlinear increase in the deviation of mechanical properties, a special synergistic adjustment link is set in the feedback layer to accurately respond to this compound impact.

[0056] When constructing the open bias feedback layer, the second sample set, that is, the data carefully collected in the open scene, covering the characteristic values ​​of the actual decorative paper aging influencing factors, the decorative paper application time, and the actual weather resistance evaluation index values, is input into the weather resistance evaluation model for testing. The model outputs the prediction results according to the built-in algorithm, and by comparing the predicted values ​​with the actual weather resistance evaluation index values ​​in the sample set, the deviation is calculated and a systematic test deviation set is established. Subsequently, in view of the complexity of the open scene data, methods such as the box plot method combined with data smoothing are used to accurately eliminate discrete values ​​caused by environmental mutations, accidental measurement errors, etc. in the systematic test deviation set to ensure the reliability of the data. Then, the data value is deeply explored to analyze the relationship between the systematic test deviation and the characteristic values ​​of the actual decorative paper aging influencing factors. At this time, since the second sample set comes from a real open scene, such as outdoor billboards affected by complex factors such as strong winds, heavy rains, and long-term sun exposure, the relationship between these dynamic and sudden conditions and the deviation of weather resistance indicators can be comprehensively considered during the analysis, and the law under the synergistic effect of multiple factors can be explored by using multivariate linear regression or random forest algorithm in machine learning. Based on these in-depth analysis results, the systematic deviation impact curve is generated using data fitting technology. The curve faithfully reflects the deviation change trend under the interweaving of various factors in the real open scene. Finally, an open bias feedback layer is constructed based on this systematic deviation impact curve rich in real information, and the key nodes and change trends of the impact of different environmental factors on the deviation are extracted from the curve, and converted into dynamic weight settings and adaptive adjustment rules within the feedback layer.

[0057] In a possible implementation, step S600 further includes: Step S610: Determine whether the target application space includes a device for adjusting any of the factors.

[0058] Step S620: If yes, connect the device to obtain an adjustment target, and determine the dynamic characteristic analysis result according to the adjustment target.

[0059] Step S630: If not, obtain the geographical location of the target application space, and perform historical dynamic statistics on any factor of the decorative paper aging influencing factors based on the geographical location to generate the dynamic characteristic analysis result.

[0060] Specifically, a comprehensive and detailed investigation is conducted on the target application space to determine whether there is any equipment that can adjust any of the factors affecting the aging of decorative paper. The target application space mentioned here covers a wide range, including indoor areas such as museum exhibition halls and libraries that have high requirements for environmental control, as well as outdoor places such as bus station advertising columns and building exterior wall decoration areas that are exposed to the natural environment. For each factor that may affect the aging of decorative paper, such as temperature, humidity, ultraviolet radiation, pollutant concentration, etc., check one by one whether there are corresponding adjustment facilities. For example, in the museum exhibition hall, check whether it is equipped with a temperature and humidity adjustment system, air purification and filtration devices to regulate temperature and humidity and reduce harmful pollutants.

[0061] Once it is determined that the target application space does contain such adjustment equipment, quickly establish a connection channel with these devices to obtain the adjustment target information. Taking the indoor office space as an example, if it is connected to the central air-conditioning control system, it is found that the temperature adjustment target is set to be maintained between 22-26°C all year round, and the humidity is stable in the range of 40%-60%. This shows that the space has a clear control demand for the two key aging factors of temperature and humidity. Based on these obtained adjustment targets, combined with the existing knowledge system related to the aging of decorative paper and the data models accumulated in the early stage, the dynamic characteristics under such precise control are deeply analyzed, and the dynamic characteristics analysis results such as the change in the aging rate of decorative paper over time in this environment and the evolution trend of various weather resistance indicators are accurately determined, providing strong support for the accurate estimation of the life and performance changes of decorative paper.

[0062] If the judgment result is no, that is, the target application space is not equipped with equipment to adjust any aging influencing factors, the geographical location of the target application space is locked at the first time. This geographical location information covers a wealth of environmental connotations. For example, being located in a low-latitude tropical area means high temperatures, strong ultraviolet radiation and high humidity all year round; being located in a high-latitude cold zone means facing cold and low temperatures, large seasonal differences in sunshine time and other environmental characteristics. Relying on the geographic information system (GIS) and a large amount of historical environmental data resources, in-depth historical dynamic statistics are carried out for any factor influencing the aging of decorative paper. For example, for outdoor decorative paper application scenarios located in coastal areas, the humidity factor is historically traced back, and the humidity change curves in different seasons and different periods over the past few years or even decades, as well as the corresponding records of the actual aging of the decorative paper in the area, are statistically analyzed through data analysis and fitting technology, to generate dynamic characteristic analysis results covering how humidity fluctuations affect the aging process of decorative paper, the decline law of the weather resistance index of decorative paper under different humidity extremes, etc., which also provide key basis for the subsequent maintenance and replacement strategy formulation of decorative paper.

[0063] In a possible implementation, step S600 further includes: Step S640: Identify the closed type of the target application space.

[0064] Step S650: matching a target feedback layer in the closed bias feedback layer and the open bias feedback layer based on the closed type.

[0065] Step S660: After analyzing the dynamic characteristic analysis result and the preset evaluation time with the weather resistance evaluation model, output feedback optimization is performed through the target feedback layer to generate the target weather resistance evaluation result corresponding to the preset evaluation time.

[0066] Specifically, identifying the closed type of the target application space has become a key task. The target application space has different forms, and the closed types cover a wide range, from a completely closed indoor precision laboratory environment, where the surrounding walls, ceilings and floors are specially sealed, and air exchange relies on a professional purification and ventilation system, which can isolate the interference of external temperature, humidity and pollutants to the greatest extent; to a relatively closed ordinary office space, although there are doors and windows for ventilation, but the temperature and humidity are basically in a stable state of artificially controlled daily; to semi-open shopping mall entrances, street shop windows and other areas, such spaces are directly connected to the open environment on one or more sides, and the temperature, humidity, light and air composition fluctuate greatly with changes in the outside world; to the fully open outdoor building exterior walls, large open-air billboards, exposed to the natural climate and various environmental factors without any cover. Through field surveys, sensor monitoring, and combined with multi-faceted means such as space design drawings, it is precisely determined what type of closed type the target application space belongs to.

[0067] Accurately matching the target feedback layer is a key link in optimizing weather resistance evaluation. Once the closure type of the target application space is clear, it is necessary to choose between a closed bias feedback layer and an open bias feedback layer. If the target application space is fully enclosed, for example, a dust-free production workshop, which is tightly sealed on all sides, the temperature and humidity are constantly controlled by precision air conditioning, the air purification level is extremely high, and it is almost completely isolated from the outside environment. In this case, the closed bias feedback layer is undoubtedly the best match. It relies on an internally solidified high-precision model, and the model parameters are derived from a large number of rigorous experimental data on the aging of decorative paper in a similar closed environment. It can make detailed adjustments to the preliminary results output by the weather resistance evaluation model in a stable and accurate way. For example, when the evaluation model predicts the color difference change of the decorative paper in the workshop in the future, the closed feedback layer corrects the possible minor deviations based on the internally stored aging trajectory of the decorative paper in the same temperature and humidity and low pollution environment, so that the results are more realistic. On the contrary, if the target application space is open, such as a large outdoor bus station advertising display area, it is directly exposed to natural factors such as sunlight, wind, rain, and dust without any shelter, and the environment changes dramatically and is difficult to predict. At this time, an open bias feedback layer is selected. By deploying multifunctional environmental sensors in the surrounding area, real-time data such as sudden temperature changes, soaring humidity, and peak ultraviolet intensity are collected in real time, so that the final feedback results can fully reflect the rapid and changeable aging trend of decorative paper in a real open environment, ensuring that the matching target feedback layer and the closed type complement each other, providing a guarantee for the subsequent generation of accurate weather resistance evaluation results.

[0068] The weatherability evaluation model begins to receive dynamic characteristic analysis results, covering all-round environmental information of the target application space, from daily temperature fluctuations, seasonal changes in humidity, to day and night differences in ultraviolet radiation, and environmental responses to pollutant concentrations, all presented in precise data. At the same time, combined with the preset evaluation time, the model quickly starts with a complex algorithm trained based on massive aging data, deeply analyzes the aging trajectory of decorative paper within a given time span, and predicts the trend of key weatherability indicators such as the color difference gradient range, tensile strength attenuation amplitude, and surface damage development. Immediately afterwards, the target feedback layer plays a key role. If it is a closed bias feedback layer, the model output is checked one by one against the closed space standard aging mode. Once a color difference deviation caused by humidity is found, it is accurately corrected according to internal rules to ensure that it fits the closed environment characteristics; if it is an open bias feedback layer, it immediately captures outdoor sudden rainstorms, strong winds and other environmental time-varying data, and flexibly optimizes the model results accordingly, so that it keeps up with the changes in the open environment, and finally generates a target weatherability evaluation result that accurately corresponds to the preset evaluation time, providing a solid decision-making foundation for the full life cycle management of decorative paper.

[0069] Embodiment 2 is based on the same inventive concept as the method for evaluating weather resistance of decorative paper in the above embodiment. Figure 2As shown, the present application provides a decorative paper weather resistance evaluation system, and the system and method embodiments in the present application are based on the same inventive concept. The system includes: The structural composition information determination module 10 is used to determine the structural composition information and target application space of the target decorative paper.

[0070] The aging influence factor determination module 20 is used to determine the aging influence factors of the decorative paper, wherein the aging influence factors of the decorative paper at least include temperature, humidity, pollutant exposure, ultraviolet radiation and wind speed.

[0071] The weather resistance evaluation index determination module 30 is used to determine the weather resistance evaluation index, wherein the weather resistance evaluation index at least includes color difference, mechanical properties, surface damage and glossiness.

[0072] The weather resistance evaluation model building module 40 builds an aging evaluation sample based on the structural composition information, performs a relationship analysis between the decorative paper aging influencing factor and the weather resistance evaluation index, and builds a weather resistance evaluation model.

[0073] The bias feedback layer establishment module 50 performs systematic bias analysis of closed scenarios and open scenarios based on the weather resistance evaluation model, establishes a closed bias feedback layer and an open bias feedback layer, and optimizes the weather resistance evaluation model.

[0074] The weather resistance evaluation result generating module 60 is used to perform dynamic characteristic analysis on any factor of the decorative paper aging influencing factors for the target application space, input the dynamic characteristic analysis result into the optimized weather resistance evaluation model for analysis, and generate a target weather resistance evaluation result corresponding to the weather resistance evaluation index.

[0075] Furthermore, the weather resistance evaluation model building module 40 also includes: The aging evaluation sample construction unit is used to collect the historical decorative paper application time, the historical influencing factor characteristic time series and the historical weather resistance evaluation index time series based on the structural composition information as a constraint to construct the aging evaluation sample.

[0076] The single factor temporal evaluation channel establishing unit performs temporal variable impact analysis on any influencing factor of the decorative paper aging influencing factor and the weather resistance evaluation index based on the aging evaluation sample, and establishes a single factor temporal evaluation channel.

[0077] The evaluation fusion layer construction unit performs fusion effect analysis on each influencing factor of the decorative paper aging influencing factor based on the aging evaluation sample to construct an evaluation fusion layer.

[0078] The weather resistance evaluation model building unit is used to combine the single factor temporal evaluation channel and the evaluation fusion layer to build the weather resistance evaluation model.

[0079] Furthermore, the evaluation fusion layer construction unit also includes: The first superposition relationship generating unit is used to combine any two factors of the decorative paper aging influencing factors, perform a joint superposition relationship analysis based on the aging evaluation sample and the weather resistance evaluation index, and generate a first superposition relationship.

[0080] The second superposition relationship generating unit is used to combine any three factors of the decorative paper aging influencing factors, perform a joint superposition relationship analysis based on the aging evaluation sample and the weather resistance evaluation index, and generate a second superposition relationship.

[0081] The third superposition relationship generating unit is used to combine any four factors of the decorative paper aging influencing factors, perform a joint superposition relationship analysis based on the aging evaluation sample and the weather resistance evaluation index, and generate a third superposition relationship.

[0082] The evaluation fusion layer generation unit generates the evaluation fusion layer based on the first superposition relationship, the second superposition relationship and the third superposition relationship.

[0083] Furthermore, the bias feedback layer establishing module 50 further includes: An aging evaluation sample collection unit is used to collect aging evaluation samples, wherein the aging evaluation samples include a first sample set and a second sample set, the first sample set is the actual decorative paper aging influence factor characteristic value, decorative paper application time and actual weather resistance evaluation index value collected in a closed scene, and the second sample set is the actual decorative paper aging influence factor characteristic value, decorative paper application time and actual weather resistance evaluation index value collected in an open scene.

[0084] A closed bias feedback layer construction unit is used to test the first sample set through the weather resistance evaluation model, perform systematic bias identification in a closed scenario according to the test results, and construct the closed bias feedback layer.

[0085] An open bias feedback layer construction unit is used to test the second sample set through the weather resistance evaluation model, identify the systematic bias in the open scenario according to the test results, and construct the open bias feedback layer.

[0086] The weather resistance evaluation model optimization unit is used to connect the closed bias feedback layer and the open bias feedback layer in parallel to the output end of the weather resistance evaluation model to complete the optimization of the weather resistance evaluation model.

[0087] Furthermore, the closed bias feedback layer construction unit also includes: The systematic test deviation set establishing unit is used to test the first sample set through the weather resistance evaluation model to establish a systematic test deviation set.

[0088] The systematic deviation influence curve generating unit is used to analyze the relationship between the systematic test deviation and the characteristic value of the actual decorative paper aging influence factor after removing discrete values ​​from the systematic test deviation set, and generate the systematic deviation influence curve.

[0089] The closed bias feedback layer establishing unit is used to construct the closed bias feedback layer with the systematic deviation influence curve.

[0090] Furthermore, the weather resistance evaluation result generating module 60 further includes: The device determination unit is used to determine whether the target application space contains a device for adjusting any of the factors.

[0091] The dynamic characteristic analysis result determining unit is used to connect to the device to obtain an adjustment target, and determine the dynamic characteristic analysis result according to the adjustment target.

[0092] The dynamic characteristic analysis result generating unit is used for, if not, obtaining the geographical location of the target application space, and performing historical dynamic statistics on any factor of the decorative paper aging influencing factors based on the geographical location to generate the dynamic characteristic analysis result.

[0093] Furthermore, the weather resistance evaluation result generating module 60 further includes: The closed type identification unit is used to identify the closed type of the target application space.

[0094] The target feedback layer matching unit matches the target feedback layer in the closed bias feedback layer and the open bias feedback layer based on the closed type.

[0095] A feedback optimization output unit is used to analyze the dynamic characteristic analysis result and the preset evaluation time with the weather resistance evaluation model, and then perform output feedback optimization through the target feedback layer to generate the target weather resistance evaluation result corresponding to the preset evaluation time.

[0096] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0097] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0098] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for evaluating weather resistance of decorative paper, characterized in that: include: Determine the structural composition information and target application space of the target decorative paper; Determining factors affecting aging of the decorative paper, wherein the factors affecting aging of the decorative paper include at least temperature, humidity, pollutant exposure, ultraviolet radiation, and wind speed; Determining weather resistance evaluation indicators, wherein the weather resistance evaluation indicators at least include color difference, mechanical properties, surface damage and glossiness; constructing an aging evaluation sample based on the structural composition information, performing a relationship analysis on the decorative paper aging influencing factor and the weather resistance evaluation index, and establishing a weather resistance evaluation model; Based on the weather resistance evaluation model, a systematic bias analysis of closed scenarios and open scenarios is performed, a closed bias feedback layer and an open bias feedback layer are established, and the weather resistance evaluation model is optimized; A dynamic characteristic analysis is performed on any factor of the decorative paper aging influencing factors for the target application space, and the dynamic characteristic analysis result is input into the optimized weather resistance evaluation model for analysis to generate a target weather resistance evaluation result corresponding to the weather resistance evaluation index.

2. A method for evaluating weather resistance of decorative paper according to claim 1, characterized in that: An aging evaluation sample is constructed based on the structural composition information, a relationship analysis is performed on the decorative paper aging influencing factor and the weather resistance evaluation index, and a weather resistance evaluation model is established, including: Taking the structural composition information as a constraint, collecting the historical decorative paper application time, historical influencing factor characteristic time series and historical weather resistance evaluation index time series to construct the aging evaluation sample; Based on the aging evaluation sample, a temporal variable impact analysis is performed on any influencing factor of the decorative paper aging influencing factor and the weather resistance evaluation index to establish a single factor temporal evaluation channel; Based on the aging evaluation sample, performing fusion effect analysis on each influencing factor of the decorative paper aging influencing factor to construct an evaluation fusion layer; The weather resistance evaluation model is established by combining the single factor temporal evaluation channel and the evaluation fusion layer.

3. A method for evaluating weather resistance of decorative paper according to claim 2, characterized in that: Based on the aging evaluation sample, a fusion effect analysis is performed on each influencing factor of the decorative paper aging influencing factor to construct an evaluation fusion layer, including: Combining any two factors of the decorative paper aging influencing factors, and performing a joint action superposition relationship analysis based on the aging evaluation sample and the weather resistance evaluation index to generate a first superposition relationship; Combining any three factors among the decorative paper aging influencing factors, and performing a joint action superposition relationship analysis based on the aging evaluation sample and the weather resistance evaluation index to generate a second superposition relationship; Combining any four factors of the decorative paper aging influencing factors, and performing a joint action superposition relationship analysis based on the aging evaluation sample and the weather resistance evaluation index to generate a third superposition relationship; The evaluation fusion layer is generated based on the first superposition relationship, the second superposition relationship and the third superposition relationship.

4. A method for evaluating weather resistance of decorative paper according to claim 1, characterized in that: Based on the weather resistance evaluation model, a systematic bias analysis of closed scenarios and open scenarios is performed, a closed bias feedback layer and an open bias feedback layer are established, and the weather resistance evaluation model is optimized, including: Collecting aging evaluation samples, wherein the aging evaluation samples include a first sample set and a second sample set, wherein the first sample set is the characteristic values ​​of actual decorative paper aging influencing factors, decorative paper application time, and actual weather resistance evaluation index values ​​collected in a closed scene, and the second sample set is the characteristic values ​​of actual decorative paper aging influencing factors, decorative paper application time, and actual weather resistance evaluation index values ​​collected in an open scene; Testing the first sample set by using the weather resistance evaluation model, identifying the systematic bias in a closed scenario according to the test results, and constructing the closed bias feedback layer; Testing the second sample set by using the weather resistance evaluation model, identifying the systematic bias in the open scene according to the test results, and constructing the open bias feedback layer; The closed bias feedback layer and the open bias feedback layer are connected in parallel to the output end of the weather resistance evaluation model to complete the optimization of the weather resistance evaluation model.

5. A method for evaluating weather resistance of decorative paper according to claim 4, characterized in that: The first sample set is tested by the weather resistance evaluation model, and systematic bias identification is performed in a closed scenario according to the test results, so as to construct the closed bias feedback layer, including: Testing the first sample set using the weather resistance evaluation model to establish a systematic test deviation set; After removing discrete values ​​from the systematic test deviation set, the relationship between the systematic test deviation and the characteristic value of the actual decorative paper aging influencing factor is analyzed to generate a systematic deviation influence curve; The closed bias feedback layer is constructed with the systematic deviation influence curve.

6. A method for evaluating weather resistance of decorative paper according to claim 1, characterized in that: Performing a dynamic characteristic analysis on any factor of the decorative paper aging influencing factors for the target application space includes: Determining whether the target application space includes a device for adjusting any of the factors; If yes, connect the device to obtain the adjustment target, and determine the dynamic characteristic analysis result according to the adjustment target; If not, the geographical location of the target application space is obtained, and based on the geographical location, historical dynamic statistics are performed on any factor of the decorative paper aging influencing factors to generate the dynamic characteristic analysis result.

7. A method for evaluating weather resistance of decorative paper according to claim 1, characterized in that: The dynamic characteristic analysis results are input into the optimized weather resistance evaluation model for analysis to generate target weather resistance evaluation results corresponding to the weather resistance evaluation index, including: Identifying the closure type of the target application space; matching a target feedback layer in the closed bias feedback layer and the open bias feedback layer based on the closed type; After analyzing the dynamic characteristic analysis result and the preset evaluation time by the weather resistance evaluation model, the output feedback optimization is performed through the target feedback layer to generate the target weather resistance evaluation result corresponding to the preset evaluation time.

8. A decorative paper weather resistance evaluation system, characterized in that: The system is used to implement a decorative paper weather resistance evaluation method according to any one of claims 1 to 7, and the system comprises: A structural composition information determination module, used to determine the structural composition information and target application space of the target decorative paper; An aging influence factor determination module, used to determine the aging influence factors of the decorative paper, wherein the aging influence factors of the decorative paper at least include temperature, humidity, pollutant exposure, ultraviolet radiation and wind speed; A weather resistance evaluation index determination module, used to determine the weather resistance evaluation index, wherein the weather resistance evaluation index at least includes color difference, mechanical properties, surface damage and glossiness; A weather resistance evaluation model establishment module is used to construct an aging evaluation sample based on the structural composition information, analyze the relationship between the decorative paper aging influencing factor and the weather resistance evaluation index, and establish a weather resistance evaluation model; A bias feedback layer establishment module performs a systematic bias analysis of closed scenarios and open scenarios based on the weather resistance evaluation model, establishes a closed bias feedback layer and an open bias feedback layer, and optimizes the weather resistance evaluation model; The weather resistance evaluation result generation module is used to perform dynamic characteristic analysis on any factor of the decorative paper aging influencing factors for the target application space, input the dynamic characteristic analysis result into the optimized weather resistance evaluation model for analysis, and generate a target weather resistance evaluation result corresponding to the weather resistance evaluation index.

Images