Intelligent monitoring method and system for performance of radiation refrigeration coating

Abstract

The invention relates to the technical field of analysis and testing, in particular to a radiation refrigeration coating performance intelligent monitoring method and system.The radiation refrigeration coating performance intelligent monitoring method comprises the steps that multi-source monitoring data, coating preparation parameters and climate zone parameters of a radiation refrigeration coating are obtained; polarization optical analysis is carried out on data related to optics in the multi-source monitoring data, and a coating performance measured value of the radiation refrigeration coating is calculated based on a polarization optical analysis result. Inputting the multi-source monitoring data, the coating preparation parameters, the polarization optical analysis result, the coating performance measured value and the climate zone parameters into a pre-trained physical constraint deep neural network model to obtain a coating performance predicted value; correcting the climate zone parameters to obtain climate zone correction parameters, constructing a multi-climate zone differential degradation dynamic model according to the climate zone correction parameters, and inputting the coating performance measured value into the multi-climate zone differential degradation dynamic model to obtain the coating performance attenuation trend and the remaining service life. And generating a radiation refrigeration coating performance monitoring report.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of analytical testing technology, in particular to a radiation refrigeration coating performance intelligent monitoring method and system. BACKGROUND

[0002] The radiation refrigeration coating is a key passive cooling material to cope with climate crisis and refrigeration energy consumption crisis. It does not need external energy input and realizes sustainable cooling by natural law. It precisely utilizes the 8-13 micrometer infrared transparent window of the earth's atmosphere to dissipate the heat on the surface of the object to the deep space in the form of thermal radiation. At the same time, it maintains a very high reflectivity to the 0.3-2.5 micrometer band of solar radiation. Even in the daytime when the sun is shining directly, the surface temperature of the object can be lower than the ambient temperature, achieving zero energy consumption, zero emission, zero noise and zero refrigerant cooling effect. As an important industrialization carrier of radiation refrigeration technology, the material system of the radiation refrigeration coating presents diversified development. The polymer-based composite material is the mainstream. By matching titanium dioxide, barium sulfate and other efficient solar scatterers with high infrared emission polymer matrix, parameters such as particle size and dispersion stability are continuously optimized to pursue higher solar reflectivity and infrared emissivity.

[0003] During the preparation and use of the radiation refrigeration coating, its performance needs to be monitored in real time. However, in the existing radiation refrigeration coating performance monitoring method, there are the following problems: (1) offline or semi-real-time monitoring is carried out by using temperature sensors and thermocouples, which lacks synchronous online collection of optical performance and refrigeration performance, and cannot monitor coating microstructure parameters; (2) meteorological parameters and coating performance are not associated, and the quantitative relationship between environmental factors and coating performance is not established, and the influence of environmental parameter differences in different climate zones on performance decay is not considered; (3) there is no quantitative prediction method for long-term stability of the coating, and the service life and maintenance period of the coating cannot be evaluated in advance. The above problems will lead to that the performance monitoring result of the radiation refrigeration coating is not comprehensive and accurate.

[0004] Therefore, how to improve the comprehensiveness and accuracy of the performance monitoring result of the radiation refrigeration coating is a problem to be solved at present. SUMMARY

[0005] Therefore, the purpose of the present application is to provide a radiation refrigeration coating performance intelligent monitoring method and system to solve the above technical problems.

[0006] In order to achieve the above purpose, the present application adopts the following technical scheme:

[0007] The radiation refrigeration coating performance intelligent monitoring method of the present application comprises:

[0008] obtaining multi-source monitoring data of the radiation refrigeration coating, coating preparation parameters and climate zone parameters;

[0009] performing polarized optical analysis on data related to optics in the multi-source monitoring data to obtain a polarized optical analysis result, calculating a measured value of coating performance of the radiative cooling coating based on the polarized optical analysis result, and inputting the multi-source monitoring data, the coating preparation parameters, the polarized optical analysis result, the measured value of coating performance, and the climate zone parameters into a pre-trained physical constraint deep neural network model to obtain a predicted value of coating performance;

[0010] correcting the climate zone parameters to obtain climate zone corrected parameters, constructing a multi-climate zone differentiated degradation dynamics model according to the climate zone corrected parameters, and inputting the measured value of coating performance into the multi-climate zone differentiated degradation dynamics model to obtain a coating performance attenuation trend and a remaining service life;

[0011] generating a radiative cooling coating performance monitoring report according to the measured value of coating performance, the predicted value of coating performance, the coating performance attenuation trend, and the remaining service life.

[0012] The application also provides a radiative cooling coating performance intelligent monitoring system, comprising:

[0013] a obtaining unit configured to obtain multi-source monitoring data of a radiative cooling coating, coating preparation parameters, and climate zone parameters;

[0014] an analysis unit configured to perform polarized optical analysis on data related to optics in the multi-source monitoring data to obtain a polarized optical analysis result, calculate a measured value of coating performance of the radiative cooling coating based on the polarized optical analysis result, and input the multi-source monitoring data, the coating preparation parameters, the polarized optical analysis result, the measured value of coating performance, and the climate zone parameters into a pre-trained physical constraint deep neural network model to obtain a predicted value of coating performance;

[0015] a correction unit configured to correct the climate zone parameters to obtain climate zone corrected parameters, construct a multi-climate zone differentiated degradation dynamics model according to the climate zone corrected parameters, and input the measured value of coating performance into the multi-climate zone differentiated degradation dynamics model to obtain a coating performance attenuation trend and a remaining service life;

[0016] a report generating unit configured to generate a radiative cooling coating performance monitoring report according to the measured value of coating performance, the predicted value of coating performance, the coating performance attenuation trend, and the remaining service life.

[0017] The present application has the following beneficial effects: the radiation cooling coating performance intelligent monitoring method and system of the present application comprehensively acquires multi-dimensional data, accurately calculates through polarization optical analysis combined with a physically constrained deep neural network model, differentiates performance attenuation prediction in multiple climate zones, and generates standardized monitoring reports, optimizing the whole process from data acquisition, performance calculation, trend prediction to result presentation, effectively improving the comprehensiveness and accuracy of the radiation cooling coating performance monitoring results. First, instead of being limited to single temperature monitoring data, multi-source monitoring data, coating preparation parameters, and climate zone parameters are synchronously acquired, covering multiple dimensions such as coating optics, temperature meteorology, microstructure, preparation process, and deployment climate environment, ensuring the comprehensiveness of monitoring from the data source, and avoiding the one-sidedness of monitoring results caused by missing data dimensions. Second, polarization optical analysis is performed on the optical related data, and the coating performance measured value is calculated based on the results, and the multi-dimensional data is input into the pre-trained physically constrained deep neural network model to obtain the performance predicted value, which realizes the correlation and quantification of coating microstructure and macro optical performance through polarization optical analysis, makes the performance measured value calculation more in line with the actual characteristics of the coating, and uses the physically constrained deep neural network model to combine the advantages of physical laws and data-driven, reducing the prediction deviation of pure data models and improving the accuracy of performance numerical calculation. Then, a differentiated degradation dynamics model for multiple climate zones is constructed by correcting the climate zone parameters, and the coating performance measured value is substituted into the model to obtain the attenuation trend and remaining service life, fully considering the influence of environmental parameter differences in different climate zones on the performance of the coating, solving the problem of lack of regional pertinence in performance attenuation prediction in the prior art, making the performance trend prediction results more in line with the environmental characteristics of the actual use of the coating, and improving the accuracy of the prediction monitoring results. Finally, the monitoring report is generated by integrating the coating performance measured value, predicted value, attenuation trend, and remaining service life, and the scattered monitoring data and analysis results are systematically integrated and presented, which not only ensures that the monitoring results cover the current performance, future prediction, and long-term attenuation of the coating, but also makes the presentation of the monitoring results more systematic and comprehensive, and the multi-dimensional data support and accurate calculation of the whole process also make the results presented in the final monitoring report more accurate. BRIEF DESCRIPTION OF DRAWINGS

[0018] The present application will be further described below in conjunction with the drawings and examples:

[0019] Figure 1 The flowchart of the radiation cooling coating performance intelligent monitoring method in an embodiment of the present application;

[0020] Figure 2 The structure diagram of the radiation cooling coating performance intelligent monitoring system in an embodiment of the present application. DETAILED DESCRIPTION

[0021] Figure 1 The flow chart of the intelligent monitoring method for the performance of the radiant cooling coating in an embodiment of the present application is shown in FIG. 1. Figure 1 The intelligent monitoring method for the performance of the radiant cooling coating in the present application includes the following steps.

[0022] S110, acquiring multi-source monitoring data of the radiant cooling coating, coating preparation parameters, and climate zone parameters.

[0023] S120, performing polarized optical analysis on the optical-related data in the multi-source monitoring data to obtain a polarized optical analysis result, calculating a measured value of the coating performance of the radiant cooling coating based on the polarized optical analysis result, and inputting the multi-source monitoring data, the coating preparation parameters, the polarized optical analysis result, the measured value of the coating performance, and the climate zone parameters into a pre-trained physically constrained deep neural network model to obtain a predicted value of the coating performance.

[0024] S130, correcting the climate zone parameters to obtain climate zone correction parameters, constructing a multi-climate zone differentiated degradation dynamics model according to the climate zone correction parameters, and inputting the measured value of the coating performance into the multi-climate zone differentiated degradation dynamics model to obtain a coating performance attenuation trend and a remaining service life.

[0025] S140, generating a radiant cooling coating performance monitoring report according to the measured value of the coating performance, the predicted value of the coating performance, the coating performance attenuation trend, and the remaining service life.

[0026] The multi-source monitoring data refers to the collective term of various types of monitoring data that can reflect the optical properties of the radiant cooling coating, the ambient temperature and weather conditions, and the state of the microstructure of the coating surface. The data specifically includes polarized reflectance spectra, infrared radiation spectra, and other optical-related data, coating surface temperature, ambient temperature, relative humidity, solar radiation intensity, wind speed, and other temperature and weather-related data, as well as the state of particle dispersion on the coating surface, pore distribution, and interface bonding state, covering the performance of the coating itself and external environmental factors, and providing comprehensive data support for subsequent analysis.

[0027] The coating preparation parameters refer to the key process and structure parameters that affect the final performance of the radiant cooling coating during the preparation process. The parameters specifically include Zeta potential, bubble volume fraction, and interface bonding energy difference. These parameters directly affect the core cooling performance of the coating, such as solar reflectivity and infrared emissivity, and are the key basis for analyzing the performance characteristics of the coating.

[0028] Among them, climate zone parameters refer to quantitative data related to the climate characteristics of the area where the coating is deployed and used. Climate zone parameters are important environmental indicators for evaluating the stability and lifespan of materials in outdoor use. Environmental conditions in different climate zones will have different effects on the degradation of material performance. Specifically, these parameters include Köppen climate type codes, annual average total ultraviolet radiation, annual average relative humidity, and annual extreme maximum temperature data for the target climate zone. Climate zone parameters based on the Köppen climate classification system can accurately characterize the environmental characteristics of different regions and provide a basis for subsequent differential degradation prediction.

[0029] Among them, polarization optics analysis refers to the use of the basic principles of polarization optics to process and calculate optical data such as the polarization reflection spectrum of materials in order to obtain characteristic parameters that can characterize the microstructure and optical properties of the material surface. This analysis is carried out on optical related data in multi-source monitoring data, and finally obtains analytical results such as linear polarization degree and biaxial reflection function, realizing the transformation of vector parameters of coating microstructure changes, and providing microscopic basis for coating performance calculation.

[0030] Among them, the measured value of coating performance refers to the actual measured and calculated value of the core cooling performance of the radiation cooling coating based on the results of polarization optical analysis and in combination with relevant physical laws and calculation formulas. The value specifically includes the average solar reflectivity, average infrared emissivity, and net cooling power. These three parameters are the core characterization indicators of the cooling performance of the radiation cooling coating and can directly reflect the actual cooling capacity of the coating.

[0031] Among them, the physical constraint deep neural network model refers to a deep neural network model that integrates relevant physical laws and regulations as constraints. This model is pre-built and trained based on the measured values ​​of coating performance in different climate zones. It introduces physical constraint terms related to radiation cooling. After inputting multi-source monitoring data, coating preparation parameters and other multi-dimensional data, it can output accurate coating performance prediction values.

[0032] Among them, the coating performance prediction value refers to the prediction result of the core cooling performance of the coating obtained after inputting multi-dimensional data into a pre-trained physical constraint deep neural network model. This prediction value corresponds to the measured value of the coating performance, including the predicted values ​​of solar reflectivity, infrared emissivity and net cooling power, which can reflect the performance change trend of the coating in subsequent use.

[0033] Among them, the climate zone correction parameter refers to the parameter obtained after quantitatively correcting the original climate zone parameter, which can accurately characterize the accelerated decay effect of different climate zones on the performance of radiation-cooled coatings. This parameter is calculated based on data such as the annual average total ultraviolet radiation, annual average relative humidity, and annual extreme maximum temperature of the target climate zone. The value is positively correlated with the performance decay rate of the coating in that climate zone.

[0034] Among them, the multi-climate zone differentiated degradation dynamic model refers to a dynamic model based on climate zone correction parameters that can reflect the performance degradation law of radiation cooling coating under different climate zone environmental conditions. This model combines climate zone correction parameters with degradation rate constants dominated by ultraviolet radiation, humidity, and temperature, and can characterize the degradation rate of solar reflectivity and infrared emissivity respectively, so as to achieve accurate prediction of coating performance degradation in different climate zones.

[0035] Among them, the coating performance degradation trend refers to the change law of the core cooling performance of the coating over time after the measured value of the coating performance is input into the multi-climate zone differentiated degradation kinetic model. This trend is mainly reflected in the decrease curve of solar reflectivity and infrared emissivity with the service time, which can clearly show the deterioration process of the coating cooling performance.

[0036] The remaining service life refers to the usable time of the radiation-cooling coating from the current moment until its performance reaches the failure threshold, calculated based on the measured value of the coating performance and the differential degradation kinetic model of multiple climate zones. This service life is determined by the solar reflectivity failure threshold, and the calculation result can be converted into commonly used time units such as days and years, which is convenient for practical engineering applications.

[0037] The radiation cooling coating performance monitoring report integrates various monitoring and analysis results, including measured values, predicted values, performance degradation trends, and remaining service life of the coating. This report is generated based on the radiation cooling coating application technology standards and includes index tables, structural analysis charts, performance degradation trend graphs, etc., to achieve a systematic and standardized presentation of monitoring results.

[0038] For example, when conducting intelligent performance monitoring of a rare-earth-doped radiation-cooling coating used on the exterior wall of a building, a multi-parameter real-time monitoring system integrating hyperspectral sensors, infrared thermal imagers, humidity sensors, and flow potential measurement equipment is first used to acquire multi-source monitoring data such as the polarization reflectance spectrum, infrared radiation spectrum, coating surface temperature, ambient relative humidity, solar radiation intensity, and particle dispersion state on the coating surface. Simultaneously, coating preparation parameters including Zeta potential, bubble volume fraction, and interfacial binding energy difference are extracted from the coating preparation process file. Furthermore, the climate zone parameters for the area where the building is located (subtropical humid climate) are obtained, including the annual average total ultraviolet radiation, annual average relative humidity, and annual extreme maximum temperature. Next, polarization optical analysis is performed on the polarization reflectance spectrum to calculate the linear polarization degree and biaxial reflectance function. The average solar reflectance is calculated based on Kirchhoff's laws combined with the linear polarization degree, and the average infrared emissivity is calculated based on Stefan-Boltzmann's laws combined with the bubble volume fraction. Finally, the measured value of the coating performance, representing the net cooling power, is calculated using temperature and meteorological data. Subsequently, the... Multi-source monitoring data, coating preparation parameters, polarization optics analysis results, measured coating performance values, and climate zone parameters are input into a pre-trained physically constrained deep neural network model to obtain predicted coating performance values ​​for average solar reflectance, average infrared emissivity, and net cooling power. Then, climate zone correction parameters are calculated based on the climate zone parameters. These parameters, along with degradation rate constants dominated by ultraviolet radiation, humidity, and temperature, are substituted into a multi-factor coupled degradation model to construct a differentiated degradation dynamics model for the subtropical humid climate zone. Measured coating performance values ​​are input into this model to fit the annual decrease in solar reflectance and infrared emissivity, and the remaining service life of the coating is calculated. Finally, according to preset standards, the measured values, predicted values, degradation trends, and remaining service life are standardized, dimensionally unified, and data fused to generate a radiation-cooling coating performance monitoring report containing a table of core performance indicators, a curve showing the change in linear polarization degree with wavelength, a graph showing the degradation trends of solar reflectance and infrared emissivity, and a predicted remaining service life curve, thus completing the intelligent monitoring of the coating's performance.

[0039] By converting changes in the coating's microstructure into quantitative parameters through polarization optics analysis and combining them with physical laws to calculate measured values ​​of coating performance, and by utilizing a physically constrained deep neural network model to integrate physical laws and data-driven advantages to obtain accurate performance predictions, the correlation between the coating's microstructure and macroscopic performance is quantified, improving the accuracy of coating performance calculations and solving the problems of insufficient microscopic basis and large deviations in prediction results in existing technology performance calculations. Based on climatic zone parameters, a multi-climatic zone differentiated degradation kinetic model is constructed, fully considering the impact of different environmental parameters in different climatic zones on coating performance degradation. This achieves accurate and differentiated prediction of coating performance degradation trends and remaining service life, compensating for the lack of regional specificity in existing technology performance degradation predictions and providing scientific advance guidance for coating maintenance and replacement. Furthermore, by integrating multiple monitoring and analysis results to generate standardized radiation-cooling coating performance monitoring reports, the scattered data analysis results are presented systematically and in a standardized manner. This not only covers multiple aspects such as the coating's current performance, future predictions, and long-term degradation, but also enhances the engineering application value of the monitoring results, providing comprehensive and accurate scientific basis for material optimization, process improvement, and engineering applications of radiation-cooling coatings, effectively solving the core problem of insufficient comprehensiveness and accuracy in existing technology monitoring results.

[0040] As can be seen from the above, the solution in this application optimizes the entire process from data acquisition, performance calculation, trend prediction to result presentation by comprehensively acquiring multi-dimensional data, accurately calculating by combining polarization optical analysis with a physically constrained deep neural network model, predicting performance degradation in different climate zones, and generating standardized monitoring reports. This effectively improves the comprehensiveness and accuracy of the performance monitoring results of radiation cooling coatings. First, it moves beyond simple temperature monitoring data, simultaneously acquiring multi-source monitoring data, coating preparation parameters, and climate zone parameters. This covers multiple dimensions, including coating optics, temperature and meteorology, microstructure, preparation process, and deployment climate environment, ensuring comprehensive monitoring from the data source and avoiding biased results due to missing data dimensions. Second, it performs polarization optics analysis on optical-related data and calculates measured coating performance values ​​based on these results. Simultaneously, it inputs multi-dimensional data into a pre-trained physically constrained deep neural network model to obtain performance predictions. This approach quantifies the correlation between coating microstructure and macroscopic optical performance through polarization optics analysis, making the calculated performance values ​​more closely reflect the actual characteristics of the coating. Furthermore, the physically constrained deep neural network model combines the advantages of physical laws and data-driven approaches, reducing prediction biases inherent in pure data models and improving the accuracy of performance numerical calculations. Then… By modifying climate zone parameters to construct a multi-climate zone differentiated degradation kinetic model, the measured values ​​of coating performance are substituted into the model to obtain the degradation trend and remaining service life. This fully considers the impact of different environmental parameters in different climate zones on coating performance, solving the problem of lack of regional specificity in performance degradation prediction in existing technologies. This makes the performance trend prediction results more consistent with the environmental characteristics of actual coating use, improving the accuracy of predictive monitoring results. Finally, the measured values, predicted values, degradation trends, and remaining service life of coating performance are integrated to generate a monitoring report. This systematically integrates and presents the scattered monitoring data and analysis results, ensuring that the monitoring results cover multiple aspects such as the current performance, future predictions, and long-term degradation of the coating. It also makes the presentation of monitoring results more systematic and comprehensive. At the same time, the multi-dimensional data support and precise calculations throughout the process also make the results presented in the final monitoring report more accurate.

[0041] In some embodiments, the multi-source monitoring data includes data related to optics, temperature and meteorology, and surface microstructure. The optics-related data includes polarization reflection spectrum and infrared radiation spectrum. The temperature and meteorology-related data includes coating surface temperature, ambient temperature, relative humidity, solar radiation intensity, and wind speed. The surface microstructure-related data includes the particle dispersion state, pore distribution, and interface bonding state of the coating surface.

[0042] The coating preparation parameters include Zeta potential, bubble volume fraction, and interfacial binding energy difference.

[0043] The climate zone parameters include the Köppen climate type code, the annual average total ultraviolet radiation, the annual average relative humidity, and the annual extreme maximum temperature data for the target climate zone.

[0044] Among them, polarization reflection spectrum refers to the reflection spectrum of incident light with different polarization directions by the radiation cooling coating. This spectrum is a core component of optical related data and is the raw data for carrying out polarization optical analysis, calculating linear polarization degree and bidirectional reflection function. Its detection wavelength range covers the 0.3-2.5μm band of solar radiation.

[0045] Among them, infrared radiation spectrum refers to the radiation spectrum emitted by the radiation-cooling coating in the infrared band. The detection wavelength range of this spectrum covers the 8-13μm band of the atmospheric window and is an important original basis for calculating the infrared emissivity of the coating, which can accurately reflect the infrared radiation-cooling characteristics of the coating.

[0046] Among them, the surface temperature of the coating refers to the surface thermodynamic temperature of the radiation cooling coating during actual use. This temperature is collected by a high-precision infrared thermal imager or thermocouple array with a sampling frequency of ≥1Hz. It is a key temperature meteorological parameter for calculating core performance indicators such as net cooling power.

[0047] The ambient temperature refers to the thermodynamic temperature of the surrounding air in the area where the radiation cooling coating is deployed. This temperature is collected by a temperature sensor with an accuracy of ±0.1°C, providing accurate ambient temperature data for calculating net cooling power and heat transfer coefficient.

[0048] Relative humidity refers to the percentage of actual water vapor pressure in the air in the environment where the radiation cooling coating is used compared to the saturated water vapor pressure at the same temperature. This parameter is collected by a humidity sensor with an accuracy of ±2%RH. It is not only the core data for calculating climate zone correction parameters, but also an important basis for analyzing the humidity-related degradation of the coating.

[0049] Among them, solar radiation intensity refers to the solar radiation energy incident on a unit area of ​​the radiation cooling coating per unit time. This parameter is collected by a solar radiation sensor with an accuracy of ±5W / m², and is one of the core parameters for calculating net cooling power.

[0050] Among them, wind speed refers to the air flow speed in the environment where the radiation cooling coating is used. This parameter is collected by an ultrasonic anemometer with a sampling frequency of ≥1Hz and is a key data for calculating the total heat transfer coefficient between the coating surface and the ambient air.

[0051] Among them, the particle dispersion state of the coating surface refers to the uniformity of the distribution and agglomeration of functional particles in the matrix of the radiation cooling coating. This state is characterized by the Zeta potential. The higher the absolute value of the Zeta potential, the better the particle dispersion stability, which is an important indicator for evaluating the microstructure stability of the coating.

[0052] Among them, pore distribution refers to the size, number and spatial distribution characteristics of pores inside the radiation cooling coating. This state is quantitatively characterized by the bubble volume fraction with an accuracy of ±0.01, and is an important microstructure parameter for calculating infrared emissivity and heat transfer coefficient.

[0053] Among them, the interfacial bonding state refers to the degree of interfacial bonding between the rare earth functional phase and the polymer matrix in the radiation cooling coating. This state is characterized by the difference in interfacial bonding energy with an accuracy of ±0.1eV. The larger the difference in interfacial bonding energy, the better the interfacial bonding state. It is the core parameter for evaluating the microstructure and long-term stability of the coating.

[0054] Among them, the Köppen climate type coding refers to the feature coding of different climate zones based on the Köppen climate classification system. This coding is the core identifier of climate zone parameters and provides a standardized climate zone classification basis for the subsequent construction of multi-climate zone differentiated degradation dynamics models.

[0055] Among them, the annual average total ultraviolet radiation of the target climate zone refers to the total energy of ultraviolet radiation in the area where the radiation cooling coating is deployed and used within one year. This parameter is the core data for calculating the climate zone correction parameter. The higher the value, the more significant the accelerated ultraviolet degradation effect of the climate zone on the coating.

[0056] Among them, the annual average relative humidity refers to the average relative humidity in the area where the radiation cooling coating is deployed and used within one year. This parameter is the key data for calculating the climate zone correction parameter and is used to quantify the degree of influence of humidity in different climate zones on the performance degradation of the coating.

[0057] Among them, the annual extreme maximum temperature refers to the highest ambient temperature that occurs in the area where the radiation cooling coating is deployed within a year. This parameter is an important data for calculating the climate zone correction parameter and is used to quantitatively characterize the accelerating effect of extreme temperatures in different climate zones on the performance degradation of the coating.

[0058] In this embodiment, multi-source monitoring data is subdivided into optical, temperature and meteorological, and surface microstructure-related data, and specific indicators for each subcategory are clearly defined. This achieves full coverage of coating macroscopic performance, external environment, and microstructure data, overcoming the shortcomings of existing technologies that only monitor macroscopic temperature parameters and lack core microstructure and optical data. This allows the monitoring data to more comprehensively reflect the actual state of the coating. The coating preparation parameters are clearly defined as three key parameters directly related to the coating's core cooling performance: Zeta potential, bubble volume fraction, and interfacial binding energy difference. This avoids interference from irrelevant preparation parameters, making the correlation analysis between preparation parameters and coating performance more accurate and improving the accuracy of performance measurement and prediction. Based on the Köppen climate classification system... The system clearly defines the specific components of climate zone parameters, quantifying them into calculable indicators such as Köppen climate type codes and annual average total ultraviolet radiation. This provides standardized and quantifiable basic data for subsequent climate zone parameter correction and the construction of multi-climate zone differentiated degradation dynamic models, solving the problem of the inability to quantify the influence of climate zones in existing technologies and further improving the accuracy of coating performance degradation prediction. By clearly defining various parameters, the data source of the entire monitoring method becomes more standardized and unified, which not only facilitates subsequent data processing, model training and analysis, but also improves the comparability and engineering application value of monitoring results, laying a data foundation for the standardized and engineering implementation of radiation-cooled coating performance monitoring.

[0059] In some embodiments, the polarization optical analysis results include linear polarization degree and biaxial reflection function. Polarization optical analysis is performed on the optically related data in the multi-source monitoring data to obtain polarization optical analysis results, including:

[0060] The degree of linear polarization is calculated based on the intensity of reflected light in orthogonally polarized directions at the same wavelength and incident angle. The degree of linear polarization is expressed as follows:

[0061] in, For linear polarization degree, To the maximum reflected light intensity, Minimum reflected light intensity;

[0062] Based on the reflectance of the radiation-cooled coated sample and the reflectance of an ideal Lambertian reflector, the bidirectional reflection function is calculated, and the bidirectional reflection function is expressed as follows:

[0063]

[0064] in, It is a bidirectional reflection function. The reflectance radiance of the radiation-cooled coating sample. Let be the reflectance of an ideal Lambertian reflector. For wavelength, Angle of incidence The angle of reflection.

[0065] Among them, the same wavelength and the same incident angle refer to the standardized test conditions followed when carrying out polarization optical analysis. These conditions are the core test requirements for polarization optical analysis. During the analysis, for each characteristic wavelength in the 0.3-2.5μm solar radiation band, the intensity of polarized reflected light is detected at a preset fixed incident angle to ensure the accuracy of the linear polarization degree calculation.

[0066] Among them, the orthogonal polarization direction refers to the vibration direction of two mutually perpendicular polarized light in polarization optics. The reflection spectrum of four polarization directions (0°, 45°, 90°, and 135°) is detected by a CMOS sensor with an integrated micro polarizer array, and the intensity of reflected light in the orthogonal polarization direction is selected to calculate the degree of linear polarization, so as to achieve accurate quantification of the polarization characteristics of the coating.

[0067] The maximum reflected light intensity refers to the maximum value of the reflected light intensity of the coating in the orthogonal polarization direction under test conditions of the same wavelength and the same incident angle. This value is collected and extracted by the sensor in real time, and the unit is consistent with the sensor's light intensity detection unit, providing accurate data support for the quantitative calculation of linear polarization degree.

[0068] The minimum reflected light intensity refers to the minimum value of the reflected light intensity of the coating in the orthogonal polarization direction under test conditions of the same wavelength and the same incident angle. This value is collected synchronously with the maximum reflected light intensity, and the ratio of the difference between the two to the sum directly determines the magnitude of the linear polarization degree, intuitively reflecting the polarization control capability of the coating.

[0069] Among them, the reflected radiance refers to the reflected light radiant flux emitted by the radiation-cooled coating sample per unit solid angle and per unit projected area under specified wavelength, incident angle and reflection angle. This value is obtained by actual measurement by a hyperspectral sensor and is the core molecular parameter for calculating the bidirectional reflection function. Its value change can directly reflect the influence of the coating surface microstructure on light reflection.

[0070] An ideal Lambertian reflector is an ideal reflector in the field of optics that can uniformly diffusely reflect incident light in all spatial directions. Its reflectance does not change with the observation angle (reflection angle). Using the reflectance of the ideal Lambertian reflector as a reference, the bidirectional reflection function is obtained by comparing it with the reflectance of the coating sample. This achieves the relative quantification of the anisotropic reflection characteristics of the coating. Furthermore, a standard white board with a reflectance ≥0.99 is used to approximate the ideal Lambertian reflector for actual testing.

[0071] Among them, wavelength refers to the spatial length between two adjacent identical vibration phase points during the propagation of light vibration. It is a core physical quantity characterizing the spectral characteristics of light. The wavelength covers the 0.3-2.5μm band of solar radiation and is a core dimensional parameter for polarization optics analysis. The degree of linear polarization and the biaxial reflection function are both calculation results under specific wavelengths, which can reflect the polarization and reflection characteristics of the coating in different solar radiation bands.

[0072] The incident angle refers to the angle between the direction of incident light propagation and the normal to the surface of the radiation-cooled coating. The incident angle is a preset fixed parameter for polarization optics analysis and is one of the core variables for calculating the biaxial reflection function. Its value matches the actual light-receiving angle of the coating, ensuring that the analysis results are consistent with the actual application scenarios of the coating.

[0073] The reflection angle refers to the angle between the direction of reflected light propagation and the normal to the surface of the radiation-cooled coating. The reflection angle is the core variable of the bidirectional reflection function. By detecting the reflection radiance of the coating under different reflection angles, the reflection characteristics of the coating surface in different directions can be accurately characterized, reflecting the spatial distribution characteristics of the coating's microstructure.

[0074] In this embodiment, the test conditions are limited to the same wavelength and the same incident angle, effectively eliminating the interference of external variables such as wavelength and incident angle on the polarization analysis results. This ensures the objectivity and uniqueness of the linear polarization degree calculation results, allowing the polarization optical analysis results to truly reflect the coating's own polarization control capability. By calculating the bidirectional reflection function based on an ideal Lambertian reflector, the relative quantification of the coating's anisotropic reflection characteristics is achieved. This accurately characterizes the reflection capability of the coating surface in different directions, intuitively reflecting the spatial distribution characteristics of the coating's microstructure. It provides accurate and effective parameter support for subsequent calculation of the coating's measured performance values ​​based on the polarization optical analysis results, further improving the accuracy of the measured coating performance values. From an optical analysis perspective, this ensures the comprehensiveness and accuracy of the radiation-cooled coating performance monitoring results.

[0075] In some embodiments, the measured values ​​of the radiation-cooled coating performance are calculated based on the polarization optical analysis results, including:

[0076] The average solar reflectivity is calculated based on Kirchhoff's laws and the aforementioned degree of linear polarization.

[0077] The average infrared emissivity is calculated based on the Stefan-Boltzmann law and the bubble volume fraction.

[0078] Based on the energy balance theory, and combined with the average solar reflectivity, average infrared emissivity, linear polarization degree, and temperature-related meteorological data, the net cooling power is calculated. The net cooling power is expressed as follows:

[0079] in, Net cooling power, The average infrared emissivity, The Stefan-Boltzmann constant is... The thermodynamic temperature of the coating surface is from the temperature and meteorological data. This refers to the ambient air thermodynamic temperature in temperature-meteorological data. The average solar reflectance, The intensity of solar radiation incident on the coating surface. The degree of linear polarization, It is the total heat transfer coefficient between the surface of the layer and the ambient air.

[0080] Kirchhoff's laws state that under thermal equilibrium, the emissivity and absorptivity of any object are numerically equal, and the sum of the reflectivity and absorptivity of an object is 1. Based on these laws, a calculation logic relating solar reflectivity and polarization optical properties is established. By combining the influence of linear polarization on solar reflectivity, the accurate calculation of average solar reflectivity is achieved.

[0081] The Stefan-Boltzmann law is a fundamental law of thermal radiation in which the total radiative emissivity of a blackbody is proportional to the fourth power of its thermodynamic temperature. This law quantitatively describes the relationship between an object's temperature and its radiative capacity. By combining this law to construct a relationship between infrared emissivity and the microstructure parameters of the coating, and incorporating the influence of bubble volume fraction on infrared radiation into the calculation, the average infrared emissivity can be accurately measured.

[0082] Among them, the energy balance theory refers to the physical theory that in a closed system, energy can neither be created out of thin air nor disappear out of thin air, but can only be transformed from one form to another or transferred from one object to another, and the total energy of the system remains unchanged. Based on this theory, the energy balance relationship between the infrared radiation heat dissipation of the coating, the solar radiation absorption heat loss, and the convective heat loss is analyzed, and the calculation formula for net cooling power is derived.

[0083] The average solar reflectance refers to the average overall reflectance of the radiation-cooling coating within the solar radiation band (0.3-2.5μm). It is a core indicator characterizing the coating's ability to reflect solar radiation. A higher value indicates that the coating reflects solar radiation better and absorbs less solar heat. This indicator is calculated in combination with the degree of linear polarization and can comprehensively reflect the coating's polarization optical characteristics and macroscopic solar reflectance. It is a key parameter for evaluating the coating's basic cooling performance.

[0084] Among them, the average infrared emissivity refers to the average overall emissivity of the radiation cooling coating in the infrared band (8-13μm) of the atmospheric window. It is the core indicator characterizing the coating's ability to emit infrared radiation to the outside world. The higher the value, the better the infrared radiation heat dissipation effect of the coating. This indicator is calculated in combination with the bubble volume fraction and can reflect the influence of the coating's micro-pore structure on its infrared emission capability. It is an important parameter for evaluating the coating's core cooling performance.

[0085] The Stefan-Boltzmann constant is a universal physical constant in the field of thermal radiation, which characterizes the ratio of blackbody radiative emissivity to the fourth power of temperature. This constant can be directly substituted into the net cooling power calculation formula to provide accurate physical constant support for the calculation of infrared radiation heat dissipation.

[0086] Among them, the thermodynamic temperature of the coating surface refers to the absolute temperature of the surface of the radiation-cooled coating. It is the core physical quantity characterizing the thermal state of the coating surface. This temperature is obtained by converting the coating surface temperature and is a key temperature parameter for calculating infrared radiation heat dissipation and convective heat loss.

[0087] Among them, the ambient air thermodynamic temperature refers to the absolute temperature of the ambient air in which the coating is located. It is the benchmark thermal state parameter for evaluating the cooling effect of the coating. This temperature is converted from the ambient temperature and together with the coating surface thermodynamic temperature, it constitutes the core temperature-related variables in the calculation of net cooling power.

[0088] The overall heat transfer coefficient is a physical quantity that characterizes the convective heat transfer capacity between the surface of the radiative cooling coating and the surrounding ambient air. The larger the value, the higher the convective heat transfer efficiency between the coating and the environment, and the more significant the convective heat loss. This coefficient is calculated by comprehensively considering factors such as wind speed, coating thickness, and bubble volume fraction. It is the core parameter for accurately calculating convective heat loss and directly affects the calculation results of net cooling power.

[0089] In this embodiment, the net cooling power is quantitatively calculated using a standardized formula, comprehensively considering the three core energy expenditure items: infrared radiation heat dissipation, solar radiation absorption heat loss, and convective heat loss. The influence of key parameters such as linear polarization degree and overall heat transfer coefficient is also incorporated, achieving refined and accurate calculation of net cooling power that truly reflects the actual cooling capacity of the coating. The specific calculation methods and steps for the measured values ​​of coating performance are clarified, establishing standardized and replicable implementation specifications for the calculation of measured performance values. This ensures the comparability of measured performance values ​​for different scenarios and coatings, enhancing the engineering application value of the monitoring method. Simultaneously, the accurate measured performance values ​​lay a high-quality data foundation for subsequent predictions using physically constrained deep neural network models and the analysis of differentiated degradation dynamic models across multiple climate zones. Furthermore, from the performance measurement perspective, this ensures the comprehensiveness and accuracy of the radiation-cooling coating performance monitoring results.

[0090] In some embodiments, before inputting the multi-source monitoring data, the coating preparation parameters, the polarization optical analysis results, the measured values ​​of the coating performance, and the climate zone parameters into a pre-trained physically constrained deep neural network model, the method further includes:

[0091] A dataset was constructed based on measured coating performance values ​​from different climate zones. Physical constraints corresponding to solar reflectivity, infrared emissivity, and net cooling power were designed, and the model was trained using a total loss function. The physical constraint deep neural network model is represented as follows:

[0092] in, The net cooling power predicted by the model. The solar reflectance predicted by the model. The infrared emissivity predicted by the model. A deep neural network mapping function for predicting net cooling power. This is a deep neural network mapping function for solar reflectivity. For infrared emissivity, a deep neural network mapping function is used. Input feature vectors to the model, , , These are learnable weight parameters. For the physical constraints used to predict net cooling power, For the physical constraint term of solar reflectivity, This is a physical constraint term for infrared emissivity;

[0093] The total loss function is expressed as follows:

[0094]

[0095] in, For the total loss function, The mean square error between the predicted and measured values. These are the weighting coefficients for the physical constraint terms. This represents the deviation between the predicted value and the physical theoretical value.

[0096] Among them, physical constraints refer to mathematical expressions constructed based on classical physical laws and theoretical formulas in the field of radiative cooling, which are used to constrain the prediction results of deep neural networks. Physical constraints are divided into three categories: solar reflectivity, infrared emissivity, and net cooling power, which correspond to the core physical laws of radiative cooling and are the core components of constructing a physically constrained deep neural network model.

[0097] Among them, the deep neural network mapping function refers to the mathematical function in the deep neural network that realizes the nonlinear mapping from the input feature vector to the target predicted value. Independent deep neural network mapping functions are designed for net cooling power, solar reflectivity and infrared emissivity to achieve accurate and independent prediction of different performance indicators.

[0098] Learnable weight parameters refer to numerical parameters that can be continuously adjusted and optimized through the backpropagation algorithm during model training. , , The weights of the physical constraints corresponding to net cooling power, solar reflectivity, and infrared emissivity are adaptively adjusted according to the features of the dataset during training.

[0099] The mean squared error (MSE) is the average value obtained by squaring the difference between the model's predicted value and the actual measured value. The MSE serves as the basis for calculating the data-driven loss term and is used to measure the fitting accuracy of the deep neural network to the measured data.

[0100] Among them, the weight coefficient of the physical constraint term is a constant parameter used to adjust the contribution ratio of the physical constraint loss term in the total loss function. The value of this coefficient is adapted according to the prediction bias and physical rationality of the model during the training process to ensure that the model fits the measured data and conforms to the physical laws.

[0101] The deviation between the predicted value and the physical theoretical value refers to the result obtained by quantifying the difference between the performance index value predicted by the model and the theoretical value calculated by the corresponding physical constraint term. This deviation is calculated by a preset quantification formula, and the smaller the value, the stronger the physical rationality of the model prediction result.

[0102] In this embodiment, a comprehensive and diverse dataset is constructed based on measured coating performance values ​​from different climate zones. This allows the trained model to possess stronger generalization capabilities, enabling it to adapt to coating performance prediction scenarios in various climate zones. This overcomes the shortcomings of existing models, which rely on limited training data and are only applicable to specific scenarios, thus improving the comprehensiveness of performance prediction. Dedicated physical constraint terms are designed for the three core performance indicators, and learnable weight parameters are introduced. This achieves an organic integration of physical laws and data-driven approaches. It utilizes deep neural networks to uncover complex nonlinear relationships between multi-dimensional data, while the physical constraint terms ensure that the prediction results conform to the objective physical laws of radiative cooling, solving the problem of purely numerical methods. This paper addresses the issues of physical paradoxes and large prediction biases inherent in traditional data-driven models, significantly improving the accuracy of coating performance predictions. By integrating data-driven loss terms and physical constraint loss terms through a total loss function and setting weight coefficients for the physical constraint terms to achieve a dynamic balance between the two, the model can simultaneously consider data fitting accuracy and physical rationality during training. The performance predictions output by the trained model can more realistically and accurately reflect the actual performance change trend of the coating, providing high-quality prediction data support for subsequent coating performance degradation trend analysis and remaining service life prediction. This further ensures the comprehensiveness and accuracy of radiation-cooled coating performance monitoring results from the performance prediction perspective.

[0103] In some implementations, the climate zone parameters are corrected to obtain climate zone correction parameters, including:

[0104] The annual average total ultraviolet radiation, annual average relative humidity, and annual extreme maximum temperature data of the target climate zone are corrected to obtain the climate zone correction parameters, which are expressed as follows:

[0105] in, Correcting parameters for climate zones, The target climate zone's average annual ultraviolet radiation. For reference to total ultraviolet radiation, Humidity sensitivity coefficient The average annual relative humidity. For reference relative humidity, For temperature sensitivity coefficient, This is the highest extreme temperature of the year. For reference temperature, It is a natural exponential function.

[0106] Among them, the reference total ultraviolet radiation refers to the preset benchmark value of total ultraviolet radiation in the coating performance degradation study. It is a fixed reference benchmark for the ultraviolet radiation dimension when calculating the climate zone correction parameters, and is used to characterize the strength of ultraviolet radiation in the target climate zone relative to the benchmark level.

[0107] Among them, the humidity sensitivity coefficient is a constant parameter obtained by experimental fitting, which is used to quantify the degree of influence of annual average relative humidity on the accelerated degradation effect of coating performance. It is an empirical value obtained by fitting a large number of accelerated aging experiments and is used to accurately calculate the contribution of the humidity dimension to the climate zone correction parameter.

[0108] Among them, reference relative humidity refers to the preset relative humidity benchmark value in the climate zone parameter correction. It is a fixed reference benchmark for the humidity dimension when calculating the climate zone correction parameters and is used to characterize the difference in relative humidity benchmark level of the target climate zone.

[0109] Among them, the temperature sensitivity coefficient is a constant parameter obtained by experimental fitting, which is used to quantify the degree of influence of the annual extreme maximum temperature on the accelerated degradation effect of coating performance. It is an empirical value obtained by fitting multiple sets of accelerated aging experiments in climate zones, and is used to accurately calculate the contribution of the temperature dimension to the climate zone correction parameter.

[0110] The reference temperature refers to the preset extreme temperature benchmark value in the climate zone parameter correction. It is a fixed reference benchmark for the temperature dimension when calculating the climate zone correction parameters, and is used to characterize the level of the extreme temperature of the target climate zone relative to the benchmark level.

[0111] In this embodiment, for the three core climatic factors affecting coating performance degradation—ultraviolet radiation, humidity, and temperature—relative ratio, linear correction, and exponential correction calculation methods were designed to align with the different effects of each climatic factor on coating degradation. Ultraviolet radiation is directly quantified using a ratio method to quantify its relative intensity; humidity is corrected using a linear method to reflect its linear effect; and temperature is represented by an exponential function to characterize its nonlinear accelerating effect. This ensures that the climatic zone correction parameters accurately reflect the comprehensive degradation acceleration characteristics of the target climatic zone. By introducing reference values ​​such as total ultraviolet radiation, reference relative humidity, and reference temperature, the calculation dimensions of various climatic parameters across different climatic zones are unified, making the parameters from different types of climatic zones, such as tropical, arid, and temperate zones, comparable and verifiable. The computational approach addresses the issue of different dimensions of environmental parameters in different climate zones, which prevent direct calculation. By incorporating empirical parameters such as humidity and temperature sensitivity coefficients from experimental fitting, the research results from numerous accelerated aging experiments are integrated into the calculation of climate zone correction parameters. This makes the calculation results more consistent with the actual aging patterns of coatings, enhancing the practical reference value of the climate zone correction parameters. The obtained climate zone correction parameters provide core quantitative basis for the subsequent construction of multi-climate zone differentiated degradation kinetic models, enabling the models to accurately distinguish the degradation characteristics of coatings in different climate zones. From the perspective of climate zone quantitative correction, the accuracy of coating performance degradation trends and remaining service life prediction is improved, further ensuring the comprehensiveness and accuracy of radiation-cooled coating performance monitoring results.

[0112] In some implementations, a multi-climate zone differentiated degradation kinetic model is constructed based on the climate zone correction parameters, and the measured values ​​of the coating performance are input into the multi-climate zone differentiated degradation kinetic model to obtain the coating performance degradation trend and remaining service life, including:

[0113] Substituting the climate zone correction parameters and the degradation rate constants dominated by ultraviolet radiation, humidity, and temperature into the multi-factor coupled degradation model, we obtain the multi-climate zone differentiated degradation dynamics model.

[0114] The multi-factor coupled degradation model includes the solar reflectivity degradation rate and the infrared emissivity degradation rate, wherein the solar reflectivity degradation rate is expressed as follows:

[0115] in, The rate of solar reflectivity degradation. Correcting parameters for climate zones, The degradation rate constant is dominated by ultraviolet radiation. The degradation rate constant is dominated by humidity. The temperature-dominant degradation rate constant. The average solar reflectance;

[0116] The infrared emissivity degradation rate is expressed as follows:

[0117]

[0118] in, The rate of infrared emissivity degradation. Correcting parameters for climate zones, The average infrared emissivity, The relative humidity is the real-time ambient temperature, and T is the real-time ambient thermodynamic temperature.

[0119] Among them, the ultraviolet-dominated degradation rate constant refers to a quantitative parameter characterizing the rate at which ultraviolet radiation affects the performance degradation of the radiation-cooled coating. This constant is obtained by fitting accelerated aging experiments and, together with climate zone correction parameters, determines the contribution of the ultraviolet dimension to the degradation of the coating's solar reflectivity and infrared emissivity.

[0120] Among them, the humidity-dominated degradation rate constant is a quantitative parameter that characterizes the rate at which ambient humidity affects the performance degradation of the radiation-cooling coating. This constant is determined through experimental fitting and is an important parameter for calculating the degradation rate of coating performance. Furthermore, in the calculation of infrared emissivity degradation, it needs to be further quantified in combination with real-time ambient relative humidity.

[0121] Among them, the temperature-dominated degradation rate constant is a quantitative parameter that characterizes the rate at which ambient temperature affects the performance degradation of the radiation-cooled coating. This constant is obtained by fitting accelerated aging experiments and needs to be quantified in conjunction with real-time ambient thermodynamic temperature in the infrared emissivity degradation calculation to reflect the dynamic influence of temperature on coating degradation.

[0122] Among them, the multi-factor coupled degradation model refers to a mathematical model that comprehensively considers the combined effects of multiple environmental factors such as ultraviolet radiation, humidity, and temperature, and is used to quantify the degradation rate of the core performance indicators of radiation-cooled coatings. The model is divided into two independent degradation rate calculation modules: solar reflectivity and infrared emissivity, which respectively quantify the multi-factor coupled degradation law of different performance indicators.

[0123] Among them, the solar reflectance degradation rate refers to the rate of change of the average solar reflectance of the radiation-cooled coating over time. This rate is calculated by coupling the climate zone correction parameters with the degradation rate constant dominated by ultraviolet radiation, humidity, and temperature. It can accurately reflect the deterioration trend of the coating's solar reflectance under the influence of multiple factors in the target climate zone.

[0124] Among them, the infrared emissivity degradation rate refers to the rate of change of the average infrared emissivity of the radiation-cooled coating over time. The calculation of this rate not only combines climate zone correction parameters and three types of degradation rate constants, but also incorporates real-time environmental relative humidity and thermodynamic temperature, which can dynamically reflect the influence of environmental parameter changes on the degradation of the coating's infrared emissivity.

[0125] Among them, the real-time ambient relative humidity refers to the real-time relative humidity of the air in the environment during the use of the radiation cooling coating. This parameter is collected in real time by a humidity sensor and substituted into the infrared emissivity degradation rate calculation formula to realize the dynamic quantitative calculation of infrared emissivity degradation.

[0126] Among them, the real-time ambient thermodynamic temperature refers to the real-time absolute air temperature in the environment in which the radiation-cooling coating is used. This parameter is collected and calculated in real time by an ambient temperature sensor. It is a dynamic parameter for calculating the infrared emissivity degradation rate, making the degradation rate calculation more consistent with the actual use environment of the coating.

[0127] In this embodiment, the constructed multi-factor coupled degradation model comprehensively considers the coupled influence of three core environmental factors—ultraviolet radiation, humidity, and temperature—on coating performance. This overcomes the shortcomings of existing single-factor degradation models, which cannot reflect the synergistic effects of multiple factors in real-world environments. This makes the calculation of coating performance degradation trends and remaining service life more closely aligned with actual application scenarios. By using climate zone correction parameters to regionally modify the multi-factor coupled degradation model, the model achieves differentiated quantification of coating degradation rates in different climate zones. This accurately reflects the accelerating effect of environmental characteristics in different climate zones, such as tropical, arid, and temperate zones, on coating performance degradation. This solves the problem of existing technologies failing to consider climate zone differences in performance degradation prediction and resulting in large prediction deviations. The clearly defined degradation kinetic model construction method and degradation rate calculation formula provide a standardized and quantifiable basis for calculating coating performance degradation trends and remaining service life. This ensures a unified calculation standard for coating degradation analysis in different scenarios, enhancing the engineering application value of the monitoring method. Simultaneously, the accurate degradation rate calculation lays a core data foundation for subsequent coating performance degradation trend fitting and remaining service life prediction, further guaranteeing the comprehensiveness and accuracy of radiation-cooled coating performance monitoring results from the perspective of performance degradation analysis.

[0128] In some embodiments, the measured values ​​of the coating performance are input into the multi-climate zone differentiated degradation kinetic model to obtain the coating performance degradation trend and remaining service life, including:

[0129] The measured values ​​of the coating performance are input into the multi-climate zone differentiated degradation kinetic model to obtain the remaining service life, and the coating performance degradation trend is fitted. The remaining service life is expressed as follows:

[0130] in, For the remaining service life, The total degradation rate constant of the coating in the target climate zone. The initial solar reflectance of the coating. The threshold for solar reflectivity failure. For usage time Instantaneous measured solar reflectance of the coating It is the natural logarithm function.

[0131] Among them, the total degradation rate constant of the coating in the target climate zone refers to the quantitative parameter that characterizes the rate of degradation of the overall performance of the coating in the target climate zone after combining the degradation rate constants of three environmental factors, namely ultraviolet radiation, humidity, and temperature, with the climate zone correction parameters. This constant is calculated by superimposing the climate zone correction parameters with the degradation rate constants dominated by ultraviolet radiation, humidity, and temperature, and is the core parameter for quantitatively calculating the remaining service life of the coating.

[0132] Among them, the initial solar reflectance of the coating refers to the initial value of solar reflectance measured under standard test conditions after the radiation cooling coating is prepared. It is a benchmark index characterizing the solar radiation reflectance capability of the coating in its brand-new state. This value is the measured solar reflectance of the coating at the initial stage of production or deployment. It is the basic benchmark data for calculating the remaining service life, and its value directly affects the initial reference dimension for life prediction.

[0133] Among them, the solar reflectivity failure threshold refers to the pre-set critical value of solar reflectivity that determines the loss of effective cooling capacity of the radiation cooling coating. It is a critical value determined by combining the engineering application requirements and cooling performance requirements of the radiation cooling coating, and provides a clear basis for the calculation of the remaining service life.

[0134] Among them, the instantaneous measured solar reflectance of the coating at usage time t refers to the solar reflectance value obtained by the real-time monitoring system after the coating has been used for an actual duration of t. It is a dynamic indicator that characterizes the actual solar reflectance capability of the coating at a certain moment during its use. This value is obtained by the optical performance monitoring module of the multi-parameter real-time monitoring system and is the core dynamic data for calculating the remaining service life. The difference between it and the failure threshold determines the remaining performance degradation space of the coating.

[0135] In this embodiment, the multi-factor coupled degradation effects of the target climate zone are integrated by the total degradation rate constant. The synergistic effect of the climate zone correction parameter and the single-factor degradation rate constant is incorporated into the lifetime calculation, so that the calculation result of the remaining lifetime can accurately reflect the degradation characteristics of the coating in the actual climate environment. This makes up for the shortcomings of the existing technology in lifetime prediction that does not consider regional climate differences and has large deviations from actual use, and significantly improves the accuracy of the remaining lifetime prediction. The instantaneous measured solar reflectance at the usage time t is used as the basis for dynamic calculation. Combined with the initial solar reflectance of the coating and the failure threshold, a dynamic assessment of the remaining lifetime of the coating is realized. The prediction result can be updated in real time according to the performance degradation of the coating in actual use. This solves the problem that traditional static lifetime prediction cannot reflect the actual use status of the coating and improves the real-time performance and accuracy of lifetime prediction.

[0136] In some embodiments, a radiation cooling coating performance monitoring report is generated based on the measured coating performance values, the predicted coating performance values, the coating performance degradation trend, and the remaining service life, including:

[0137] Based on the preset radiation cooling coating application technology standard, the measured value of the coating performance, the predicted value of the coating performance, the coating performance degradation trend, and the remaining service life are standardized, dimensionally unified, and data fused to obtain the processed data.

[0138] The radiation-cooling coating performance monitoring report is generated based on the processed data. The radiation-cooling coating performance monitoring report includes an index table, a structural analysis chart, and a performance degradation trend chart. The index table includes solar reflectivity, infrared emissivity, net cooling power, Zeta potential, bubble volume fraction, and interfacial binding energy difference. The structural analysis chart includes a curve of linear polarization degree as a function of wavelength and a biaxial reflection function distribution chart. The performance degradation trend chart includes time decay curves of solar reflectivity and infrared emissivity and a remaining service life prediction curve.

[0139] The pre-defined radiation cooling coating application technology standard refers to the industry specifications or national standards formulated in the field of radiation cooling for coating performance testing, evaluation, and report generation. Specifically, the standard is T / CECS10378-2024 or GB / T25261, which is the unified execution basis for generating radiation cooling coating performance monitoring reports.

[0140] Standardized labeling refers to the processing method of adding unified labels, units, test condition descriptions, and other labeling information to various data such as measured and predicted values ​​of coating performance in accordance with the requirements of preset technical standards. Standardized labeling requires labeling various performance parameters with information such as test band, unit, and test environment, and labeling the calculation basis and time dimension for attenuation trend and lifespan, so as to achieve standardized presentation of data.

[0141] Among them, data fusion processing refers to the processing method of integrating, associating and sorting out different types and dimensions of monitoring and analysis data such as measured values, predicted values, decay trends and remaining service life of coating performance according to preset rules. Data fusion processing needs to associate performance parameters with microstructure parameters, compare measured values ​​with predicted values, and match decay trends with remaining service life, so that the processed data can form a complete performance monitoring system.

[0142] The indicator table is a report component that systematically presents the core performance parameters and microstructure parameters of the radiation-cooling coating in tabular form. The indicator table should centrally present the measured values, predicted values, and standard thresholds of core performance indicators such as solar reflectivity and infrared emissivity, as well as microstructure parameters such as zeta potential.

[0143] Among them, the structural analysis charts refer to the report components that present the microstructure analysis data related to the polarization optics of the coating in a visual form such as curves and distribution diagrams. Specifically, the structural analysis charts are curves of linear polarization degree as a function of wavelength and distribution diagrams of biaxial reflection functions, which intuitively reflect the relationship between the microstructure of the coating and its polarization optics properties.

[0144] The performance degradation trend chart is a report component that visualizes the decay patterns of the coating's core performance indicators and the predicted remaining service life in the form of curves. This chart includes time decay curves for solar reflectivity and infrared emissivity, as well as a predicted remaining service life curve, thus enabling a visual display of coating performance degradation and lifespan.

[0145] Among them, the solar reflectance index is a quantitative indicator that comprehensively characterizes the solar reflectance capability of the coating. This index is an optional core parameter in the index table and is used to comprehensively evaluate the solar radiation reflectance performance of the coating.

[0146] Among them, the curve of linear polarization degree versus wavelength refers to the curve of the trend of the linear polarization degree of the coating in the solar radiation band (0.3-2.5μm) plotted with wavelength as the abscissa and linear polarization degree as the ordinate. This curve is the core component of the structural analysis chart and provides a visual basis for the analysis of changes in the microstructure of the coating.

[0147] Among them, the biaxial reflection function distribution map refers to the spatial distribution graph of the coating's reflection characteristics, which is drawn with the incident angle and reflection angle as the horizontal and vertical axes and the biaxial reflection function value as the color or height dimension. This distribution map is an important component of the structural analysis chart and accurately characterizes the influence of the coating's microstructure on light reflection.

[0148] Among them, the time decay curves of solar reflectivity and infrared emissivity refer to the curves of the degradation trend of the core performance indicators of the coating over time, plotted with the usage time as the horizontal axis and solar reflectivity / infrared emissivity as the vertical axis. These curves are obtained by fitting a multi-climate zone differentiated degradation kinetic model, accurately reflecting the performance degradation characteristics of the coating in the target climate zone.

[0149] Among them, the remaining service life prediction curve refers to the curve showing the trend of the coating's remaining service life as a function of service time, plotted with service time as the horizontal axis and remaining service life as the vertical axis. This curve is associated with the performance degradation curve, enabling simultaneous visualization of performance degradation and service life consumption.

[0150] In this embodiment, by standardizing, unifying, and fusion-processing various monitoring and analysis data, the differences in units and interpretation biases between different data are eliminated. The inherent correlations between data from different dimensions are uncovered, allowing scattered measured values, predicted values, and degradation trends to form a systematic whole. This solves the shortcomings of existing technologies where monitoring data is fragmented and cannot form a complete performance evaluation system, improving the systematicness and comprehensiveness of monitoring results. The monitoring results are presented in diverse forms such as indicator tables, structural analysis charts, and performance degradation trend graphs, achieving intuitive core data, visualized microstructure analysis, and trend display of performance degradation and lifespan. This allows technicians to quickly and accurately interpret the current performance, microstructure characteristics, and future degradation trends of the coating. The monitoring report integrates the core performance parameters, microstructure parameters, performance predictions, degradation trends, and remaining service life of the coating, addressing the issues of single-dimensional and difficult-to-interpret monitoring results in existing technologies. This improves the readability and practicality of the monitoring results. The monitoring report integrates comprehensive monitoring and analysis results from all dimensions, including core performance parameters, microstructure parameters, performance predictions, degradation trends, and remaining service life of the coating. All data is processed and presented based on standardized procedures, providing a comprehensive, accurate, and scientific basis for material optimization, process improvement, engineering application selection, and refined operation and maintenance of radiation-cooled coatings. This not only further enhances the comprehensiveness and accuracy of radiation-cooled coating performance monitoring results from the perspective of result presentation but also significantly improves the engineering application value of the entire monitoring method, laying a standardized technical foundation for the large-scale engineering application of radiation-cooled coatings.

[0151] like Figure 2 As shown, this application also provides an intelligent monitoring system for the performance of radiation-cooled coatings, comprising:

[0152] The acquisition unit is used to acquire multi-source monitoring data of the radiation-cooled coating, coating preparation parameters, and climate zone parameters.

[0153] The analysis unit is used to perform polarization optical analysis on the optical-related data in the multi-source monitoring data to obtain polarization optical analysis results, calculate the measured value of the coating performance of the radiation-cooling coating based on the polarization optical analysis results, and input the multi-source monitoring data, the coating preparation parameters, the polarization optical analysis results, the measured value of the coating performance and the climate zone parameters into a pre-trained physical constraint deep neural network model to obtain the predicted value of the coating performance.

[0154] The correction unit is used to correct the climate zone parameters to obtain climate zone correction parameters, construct a multi-climate zone differentiated degradation dynamic model based on the climate zone correction parameters, and input the measured value of the coating performance into the multi-climate zone differentiated degradation dynamic model to obtain the coating performance degradation trend and remaining service life.

[0155] The report generation unit is used to generate a radiation cooling coating performance monitoring report based on the measured value of the coating performance, the predicted value of the coating performance, the coating performance degradation trend, and the remaining service life.

[0156] The present invention provides an intelligent monitoring system for the performance of radiation-cooled coatings. By comprehensively acquiring multi-dimensional data, accurately calculating the performance using polarization optics analysis combined with a physically constrained deep neural network model, predicting performance degradation in different climate zones, and generating standardized monitoring reports, the entire process from data acquisition, performance calculation, trend prediction to result presentation is optimized, effectively improving the comprehensiveness and accuracy of the performance monitoring results for radiation-cooled coatings. First, it moves beyond simple temperature monitoring data, simultaneously acquiring multi-source monitoring data, coating preparation parameters, and climate zone parameters. This covers multiple dimensions, including coating optics, temperature and meteorology, microstructure, preparation process, and deployment climate environment, ensuring comprehensive monitoring from the data source and avoiding biased results due to missing data dimensions. Second, it performs polarization optics analysis on optical-related data and calculates measured coating performance values ​​based on these results. Simultaneously, it inputs multi-dimensional data into a pre-trained physically constrained deep neural network model to obtain performance predictions. This approach quantifies the correlation between coating microstructure and macroscopic optical performance through polarization optics analysis, making the calculated performance values ​​more closely reflect the actual characteristics of the coating. Furthermore, the physically constrained deep neural network model combines the advantages of physical laws and data-driven approaches, reducing prediction biases inherent in pure data models and improving the accuracy of performance numerical calculations. Then… By modifying climate zone parameters to construct a multi-climate zone differentiated degradation kinetic model, the measured values ​​of coating performance are substituted into the model to obtain the degradation trend and remaining service life. This fully considers the impact of different environmental parameters in different climate zones on coating performance, solving the problem of lack of regional specificity in performance degradation prediction in existing technologies. This makes the performance trend prediction results more consistent with the environmental characteristics of actual coating use, improving the accuracy of predictive monitoring results. Finally, the measured values, predicted values, degradation trends, and remaining service life of coating performance are integrated to generate a monitoring report. This systematically integrates and presents the scattered monitoring data and analysis results, ensuring that the monitoring results cover multiple aspects such as the current performance, future predictions, and long-term degradation of the coating. It also makes the presentation of monitoring results more systematic and comprehensive. At the same time, the multi-dimensional data support and precise calculations throughout the process also make the results presented in the final monitoring report more accurate.

Claims

1. A method for intelligent monitoring of the performance of a radiation-cooled coating, characterized in that, include: Acquire multi-source monitoring data, coating preparation parameters, and climate zone parameters for the radiation-cooling coating; Polarization optical analysis is performed on the optical-related data in the multi-source monitoring data to obtain polarization optical analysis results. Based on the polarization optical analysis results, the measured value of the coating performance of the radiation-cooling coating is calculated. The multi-source monitoring data, the coating preparation parameters, the polarization optical analysis results, the measured value of the coating performance, and the climate zone parameters are input into a pre-trained physical constraint deep neural network model to obtain the predicted value of the coating performance. The climate zone parameters are corrected to obtain climate zone correction parameters. A multi-climate zone differentiated degradation kinetic model is constructed based on the climate zone correction parameters. The measured values ​​of the coating performance are input into the multi-climate zone differentiated degradation kinetic model to obtain the coating performance degradation trend and remaining service life. A performance monitoring report for the radiation cooling coating is generated based on the measured values ​​of the coating performance, the predicted values ​​of the coating performance, the coating performance degradation trend, and the remaining service life.

2. The intelligent monitoring method for the performance of radiation-cooled coatings as described in claim 1, characterized in that: The multi-source monitoring data includes data related to optics, temperature and meteorology, and surface microstructure. Among them, the optical data includes polarization reflection spectrum and infrared radiation spectrum; the temperature and meteorology data includes coating surface temperature, ambient temperature, relative humidity, solar radiation intensity, and wind speed; and the surface microstructure data includes the particle dispersion state, pore distribution, and interface bonding state of the coating surface. The coating preparation parameters include Zeta potential, bubble volume fraction, and interfacial binding energy difference. The climate zone parameters include the Köppen climate type code, the annual average total ultraviolet radiation, the annual average relative humidity, and the annual extreme maximum temperature data for the target climate zone.

3. The intelligent monitoring method for the performance of radiation-cooled coatings as described in claim 2, characterized in that, The polarization optical analysis results include linear polarization degree and bidirectional reflection function. Polarization optical analysis is performed on the optically related data in the multi-source monitoring data to obtain the polarization optical analysis results, including: The degree of linear polarization is calculated based on the intensity of reflected light in orthogonally polarized directions at the same wavelength and incident angle. The degree of linear polarization is expressed as follows: in, For linear polarization degree, To the maximum reflected light intensity, Minimum reflected light intensity; Based on the reflectance of the radiation-cooled coated sample and the reflectance of an ideal Lambertian reflector, the bidirectional reflection function is calculated, and the bidirectional reflection function is expressed as follows: in, It is a bidirectional reflection function. The reflectance radiance of the radiation-cooled coating sample. Let be the reflectance of an ideal Lambertian reflector. For wavelength, Angle of incidence The angle of reflection.

4. The intelligent monitoring method for the performance of radiation-cooled coatings as described in claim 3, characterized in that, The measured values ​​of the radiation-cooled coating performance were calculated based on the polarization optical analysis results, including: The average solar reflectivity is calculated based on Kirchhoff's laws and the aforementioned degree of linear polarization. The average infrared emissivity is calculated based on the Stefan-Boltzmann law and the bubble volume fraction. Based on the energy balance theory, and combined with the average solar reflectivity, average infrared emissivity, linear polarization degree, and temperature-related meteorological data, the net cooling power is calculated. The net cooling power is expressed as follows: in, Net cooling power, The average infrared emissivity, The Stefan-Boltzmann constant is... The thermodynamic temperature of the coating surface is from the temperature and meteorological data. This refers to the ambient air thermodynamic temperature in temperature-meteorological data. The average solar reflectance, The intensity of solar radiation incident on the coating surface. The degree of linear polarization, It is the total heat transfer coefficient between the surface of the layer and the ambient air.

5. The intelligent monitoring method for the performance of radiation-cooled coatings as described in claim 1, characterized in that, Before inputting the multi-source monitoring data, the coating preparation parameters, the polarization optical analysis results, the measured values ​​of the coating performance, and the climate zone parameters into the pre-trained physically constrained deep neural network model, the following steps are also included: A dataset was constructed based on measured coating performance values ​​from different climate zones. Physical constraints corresponding to solar reflectivity, infrared emissivity, and net cooling power were designed, and the model was trained using a total loss function. The physical constraint deep neural network model is represented as follows: in, The net cooling power predicted by the model. The solar reflectance predicted by the model. The infrared emissivity predicted by the model. A deep neural network mapping function for predicting net cooling power. This is a deep neural network mapping function for solar reflectivity. For infrared emissivity, a deep neural network mapping function is used. Input feature vectors to the model, , , These are learnable weight parameters. For the physical constraints used to predict net cooling power, For the physical constraint term of solar reflectivity, This is a physical constraint term for infrared emissivity; The total loss function is expressed as follows: in, For the total loss function, The mean square error between the predicted and measured values. These are the weighting coefficients for the physical constraint terms. This represents the deviation between the predicted value and the physical theoretical value.

6. The intelligent monitoring method for the performance of radiation-cooled coatings as described in claim 2, characterized in that, The climate zone parameters are corrected to obtain climate zone correction parameters, including: The annual average total ultraviolet radiation, annual average relative humidity, and annual extreme maximum temperature data of the target climate zone are corrected to obtain the climate zone correction parameters, which are expressed as follows: in, Correcting parameters for climate zones, The target climate zone's average annual ultraviolet radiation. For reference to total ultraviolet radiation, Humidity sensitivity coefficient The average annual relative humidity. For reference relative humidity, For temperature sensitivity coefficient, This is the highest extreme temperature of the year. For reference temperature, It is a natural exponential function.

7. The intelligent monitoring method for the performance of radiation-cooled coatings as described in claim 1, characterized in that, A multi-climate zone differentiated degradation kinetic model is constructed based on the climate zone correction parameters, and the measured coating performance values ​​are input into the multi-climate zone differentiated degradation kinetic model to obtain the coating performance degradation trend and remaining service life, including: Substituting the climate zone correction parameters and the degradation rate constants dominated by ultraviolet radiation, humidity, and temperature into the multi-factor coupled degradation model, we obtain the multi-climate zone differentiated degradation dynamics model. The multi-factor coupled degradation model includes the solar reflectivity degradation rate and the infrared emissivity degradation rate, wherein the solar reflectivity degradation rate is expressed as follows: in, The rate of solar reflectivity degradation. Correcting parameters for climate zones, The degradation rate constant is dominated by ultraviolet radiation. The degradation rate constant is dominated by humidity. The temperature-dominant degradation rate constant. The average solar reflectance; The infrared emissivity degradation rate is expressed as follows: in, The rate of infrared emissivity degradation. Correcting parameters for climate zones, The average infrared emissivity, The relative humidity is the real-time ambient temperature, and T is the real-time ambient thermodynamic temperature.

8. The intelligent monitoring method for the performance of radiation-cooled coatings as described in claim 7, characterized in that, The measured values ​​of the coating performance are input into the multi-climate zone differentiated degradation kinetic model to obtain the coating performance degradation trend and remaining service life, including: The measured values ​​of the coating performance are input into the multi-climate zone differentiated degradation kinetic model to obtain the remaining service life, and the coating performance degradation trend is fitted. The remaining service life is expressed as follows: in, For the remaining service life, The total degradation rate constant of the coating in the target climate zone. The initial solar reflectance of the coating. The threshold for solar reflectivity failure. For usage time Instantaneous measured solar reflectance of the coating It is the natural logarithm function.

9. The intelligent monitoring method for the performance of radiation-cooled coatings as described in claim 1, characterized in that, Based on the measured values ​​of the coating performance, the predicted values ​​of the coating performance, the coating performance degradation trend, and the remaining service life, a radiation cooling coating performance monitoring report is generated, including: Based on the preset radiation cooling coating application technology standard, the measured value of the coating performance, the predicted value of the coating performance, the coating performance degradation trend, and the remaining service life are standardized, dimensionally unified, and data fused to obtain the processed data. The radiation-cooling coating performance monitoring report is generated based on the processed data. The radiation-cooling coating performance monitoring report includes an index table, a structural analysis chart, and a performance degradation trend chart. The index table includes solar reflectivity, infrared emissivity, net cooling power, Zeta potential, bubble volume fraction, and interfacial binding energy difference. The structural analysis chart includes a curve of linear polarization degree as a function of wavelength and a biaxial reflection function distribution chart. The performance degradation trend chart includes time decay curves of solar reflectivity and infrared emissivity and a remaining service life prediction curve.

10. A smart monitoring system for the performance of a radiation-cooled coating, characterized in that, include: The acquisition unit is used to acquire multi-source monitoring data of the radiation-cooled coating, coating preparation parameters, and climate zone parameters. The analysis unit is used to perform polarization optical analysis on the optical-related data in the multi-source monitoring data to obtain polarization optical analysis results, calculate the measured value of the coating performance of the radiation-cooling coating based on the polarization optical analysis results, and input the multi-source monitoring data, the coating preparation parameters, the polarization optical analysis results, the measured value of the coating performance and the climate zone parameters into a pre-trained physical constraint deep neural network model to obtain the predicted value of the coating performance. The correction unit is used to correct the climate zone parameters to obtain climate zone correction parameters, construct a multi-climate zone differentiated degradation dynamic model based on the climate zone correction parameters, and input the measured value of the coating performance into the multi-climate zone differentiated degradation dynamic model to obtain the coating performance degradation trend and remaining service life. The report generation unit is used to generate a radiation cooling coating performance monitoring report based on the measured value of the coating performance, the predicted value of the coating performance, the coating performance degradation trend, and the remaining service life.

Images