An automated magnesium oxide coating analysis system and method

Abstract

The application relates to an automatic magnesium oxide coating analysis system and method, and belongs to the technical field of coating quality analysis. The method comprises the following steps: acquiring the properties, infrared spectrum and environmental temperature and humidity data of the magnesium oxide coating, and constructing a multi-source feature set; analyzing the distribution dispersion and local enrichment risk of free water based on a dynamic migration model, and analyzing the bond weakening degree and dissociation risk of combined water based on a chemical stability model; generating free water treatment process parameters for inhibiting structural damage and combined water treatment process parameters for preventing performance attenuation according to abnormal analysis results and coating properties; and through coupling influence analysis on the two types of process parameters, the balance requirements of coating structural integrity and chemical stability are coordinated, an optimized process scheme is generated, and synergistic regulation and control are realized. The application realizes accurate identification, independent analysis and synergistic control of free water and combined water, and improves the accuracy, reliability and quality consistency of coating moisture treatment.

Description

Technical Field

[0001] This application relates to the field of coating quality analysis technology, and in particular to a method and system for analyzing the moisture state of magnesium oxide coatings and controlling the process. Background Technology

[0002] Magnesium oxide coatings, as important functional materials, play a crucial role in high-temperature protection, electronic insulation, and corrosion resistance. The long-term stability of the coating directly determines the service life and reliability of related products. It is noteworthy that moisture in the coating exists in two distinct physicochemical forms—free water molecules and bound water molecules. These two forms have completely different mechanisms of influence on coating performance: free water mainly induces swelling and deformation of the coating through capillary forces and undergoes local enrichment under temperature gradients, leading to micro-cracks and interfacial delamination; while bound water alters the crystal structure stability of magnesium oxide through chemical bonding with the lattice, potentially causing lattice distortion and deterioration of protective performance during thermal cycling.

[0003] Currently, the main technical bottlenecks in the field of moisture analysis for magnesium oxide coatings are as follows: First, most existing detection methods rely on single infrared spectroscopy analysis or environmental parameter monitoring, lacking effective fusion of multi-source information and failing to establish a correlation model between moisture state and process conditions. Second, traditional analytical methods generally treat moisture as a whole, failing to fully consider the essential differences between free water and bound water in terms of migration characteristics, location, and their impact on coating performance. Third, existing technical systems mainly rely on offline sampling and detection, making it impossible to achieve real-time monitoring and early warning of moisture state during production. Fourth, due to the lack of a synergistic analytical framework for free water migration kinetics and bound water chemical stability, it is difficult to construct accurate process parameter optimization models.

[0004] These technical deficiencies result in a significant lag in existing coating quality control methods, frequently leading to the following quality problems in actual industrial production: cracking due to uneven moisture distribution, bubble formation caused by localized moisture accumulation, and deteriorated adhesion due to decreased interfacial bonding. Particularly in high-end manufacturing, with increasingly stringent product reliability requirements, higher standards are being placed on the consistency and stability of coating quality. The shortcomings of existing technologies in real-time moisture monitoring, early warning of anomalies, and adaptive optimization of process parameters have become a technical bottleneck restricting further improvements in coating quality. Summary of the Invention

[0005] To overcome the technical shortcomings of existing magnesium oxide coating moisture analysis, such as the single monitoring index, inability to distinguish moisture state, and lack of adaptive process control, this application provides an automated magnesium oxide coating analysis system and method. By constructing a separate monitoring system for free water and bound water and establishing a multi-source data fusion analysis mechanism, it can achieve accurate diagnosis of coating moisture state and intelligent optimization of process parameters.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] In a first aspect, this application provides an automated method for analyzing magnesium oxide coatings, comprising the following steps:

[0008] S1: Obtain magnesium oxide coating properties, infrared spectral data, and environmental temperature and humidity data, and after analysis and processing, construct the coating property characteristics, infrared spectral feature vectors of free water and bound water, and environmental temperature and humidity feature set;

[0009] S2: Combine the infrared spectral feature vector of free water with the environmental temperature and humidity feature set to perform anomaly analysis of the free water state of the coating; based on the results of the anomaly analysis of the free water in the coating and the coating property characteristics, assess the risk of coating morphological damage caused by the free water treatment process, and generate free water treatment process parameters to suppress coating structural damage accordingly.

[0010] S3: Perform anomaly analysis of the bound water state of the coating by combining the infrared spectral feature vector of the bound water with the environmental temperature and humidity feature set; based on the results of the anomaly analysis of the bound water and the coating property characteristics, assess the risk of coating performance damage caused by the bound water treatment process, and generate bound water treatment process parameters to prevent coating performance degradation accordingly.

[0011] S4: Analyze the impact of water treatment process on coating integrity on the treatment process parameters of free water and bound water, and generate a balanced process scheme for the treatment of free water and bound water by coordinating the process requirements of coating structural integrity and chemical stability.

[0012] S5: Based on the aforementioned balanced process scheme, the treatment processes for free water and bound water are synergistically regulated.

[0013] According to the above technical solution, the steps of obtaining magnesium oxide coating properties, infrared spectral data, and environmental temperature and humidity data, and then analyzing and processing them to construct coating property characteristics, infrared spectral feature vectors of free water and bound water, and environmental temperature and humidity feature sets include:

[0014] The coating property characteristics are constructed, including basic parameters and microstructure parameters. The basic parameters are coating thickness and substrate type. The microstructure parameters include average particle size of magnesium oxide particles, coefficient of thermal expansion, elastic modulus, porosity and pore size distribution, crystallinity and surface hydroxyl density. The property characteristic set is constructed through system integration.

[0015] Infrared spectral feature vectors were constructed, and a differentiated parameter extraction strategy was adopted: for free water, the absorbance and half-peak width of the characteristic peaks of free water were extracted; for bound water, the absorbance and peak position shift of the characteristic peaks of bound water were extracted. This strategy can characterize the state changes of physically adsorbed and chemically bonded water, respectively.

[0016] An environmental temperature and humidity feature set is constructed, including time-series data of temperature and relative humidity, as well as derived indicators such as temperature gradient, humidity change rate, absolute humidity and dew point temperature.

[0017] According to the above technical solution, the steps for analyzing the abnormal state of the free water in the coating include:

[0018] S210: The absorbance and half-width at half-maximum (WHM) parameters of the free water characteristic peak in the infrared spectral feature vector are spatiotemporally coupled with the temperature gradient data and humidity change rate data in the environmental temperature and humidity feature set. The spatiotemporally coupled data is then used as input data to a dynamic migration model to calculate the distribution dispersion and local enrichment risk coefficient of free water. A spatiotemporal coupling between environmental driving forces and water response is established. Through time alignment and data fusion, the absorbance and WHM parameters of the free water characteristic peak are dynamically correlated with the environmental temperature gradient and humidity change rate data. This coupling mechanism quantifies the driving effect of temperature gradient on water content and the degree of influence of humidity change rate on the state of water molecules.

[0019] A dynamic migration model is constructed to achieve a quantitative analysis of the water transport mechanism. The model is based on the unsteady diffusion theory and couples Darcy's law and Fick's law to describe the macroscopic convection migration driven by the temperature gradient and the microscopic diffusion process dominated by the concentration gradient, respectively. The model achieves a mathematical representation of the entire water transport path by solving the macroscopic migration rate and the microscopic diffusion rate in parallel.

[0020] During the model analysis phase, the dominant mechanism of water transport is dynamically identified by calculating the real-time ratio of macroscopic migration rate to microscopic diffusion rate (migration-diffusion ratio). The macroscopic migration dominance threshold is a critical value set based on coating structure parameters, and the mechanism failure judgment threshold is a stability boundary set based on statistical fluctuation characteristics. When the migration-diffusion ratio is consistently higher than the macroscopic migration dominance threshold, it indicates that environmental stress has become the main driving force, and the output is a local enrichment risk coefficient that is positively correlated with the ratio. When the ratio fluctuates drastically and exceeds the mechanism failure judgment threshold, it indicates that the transport balance has been broken, and the output is a distribution dispersion that is positively correlated with the fluctuation amplitude.

[0021] S220: The distribution dispersion and local enrichment risk coefficient are compared in parallel with preset distribution dispersion safety threshold and local enrichment risk threshold, respectively. If the distribution dispersion exceeds the distribution dispersion safety threshold, it is determined that the free water distribution is abnormal; otherwise, it is determined that the free water distribution is normal. If the local enrichment risk coefficient exceeds the local enrichment risk threshold, it is determined that the local enrichment of free water is abnormal; otherwise, it is determined that the local distribution concentration of free water is normal. Thresholds are set based on the inherent properties of the coating and abnormal state judgment is performed. The distribution dispersion safety threshold is calculated by combining porosity and interface bonding strength through a pore structure stability model. The local enrichment risk threshold is determined by combining material yield strength and thermal stress resistance through thermo-mechanical coupling simulation. Through the dual threshold parallel comparison mechanism, the accurate identification and classification judgment of the abnormal state of free water is achieved.

[0022] Based on the above technical solution, the steps of assessing the risk of coating morphological damage caused by the free water treatment process and generating free water treatment process parameters to inhibit coating structural damage, according to the analysis results of the coating free water anomaly and the coating property characteristics, include:

[0023] S230: Establish a pore strength function model for coating porosity, pore size distribution parameters, and coating pore expansion resistance to characterize the influence of pore structure on capillary forces of water; combine the pore strength function model with the dispersion of free water distribution to determine the maximum allowable rate of humidity change to prevent swelling deformation; conduct a correlation analysis between pore structure and water transport; accurately quantify the expansion resistance corresponding to different pore sizes by constructing a pore strength function model based on elastoplastic mechanics theory and combined with nanoindentation experimental data; and determine the maximum allowable rate of humidity change to prevent coating swelling deformation by combining free water distribution dispersion data.

[0024] S240: Establish a particle size-crack correlation model between the average particle size of magnesium oxide particles and the driving force of crack propagation to reflect the influence mechanism of particle size on stress concentration inside the coating; combine the particle size-crack correlation model with the local enrichment risk coefficient to determine the safe threshold of temperature gradient for inhibiting crack propagation; establish a quantitative relationship between the average particle size of magnesium oxide particles and the driving force of crack propagation, and characterize the influence mechanism of particle size change on crack initiation based on fracture mechanics theory; combine the local enrichment risk coefficient to determine the safe threshold of temperature gradient for inhibiting microcrack propagation.

[0025] S250: Based on the coating thickness, the elastic modulus parameters of the substrate and the coating, and the difference in their coefficients of thermal expansion, the interfacial thermal stress distribution between the substrate and the coating is calculated to characterize the deformation compatibility of the substrate and the coating during heat treatment. Combining the interfacial thermal stress distribution with the coating crystallinity, the drying temperature control range and ventilation rate adjustment range for suppressing structural damage are determined. Interfacial thermodynamic compatibility optimization analysis is conducted. Based on the coating thickness, elastic modulus, and the difference in their coefficients of thermal expansion, the interfacial thermal stress distribution is calculated using the thermoelastic theory of multilayer structures. Combining the coating crystallinity parameter with its stress buffering capacity, the drying temperature control range and ventilation rate adjustment range for suppressing structural damage are determined.

[0026] S260: Integrate the above-mentioned maximum allowable humidity change rate, temperature gradient safety threshold, drying temperature control range, and ventilation rate adjustment range to generate free water treatment process parameters that suppress coating structure damage; by systematically integrating the above parameters, construct a complete free water treatment process parameter optimization system to form a process control scheme that matches the microstructure characteristics of the coating.

[0027] According to the above technical solution, the steps for analyzing the abnormal state of the coating bound water include:

[0028] S310: The absorbance and peak position shift parameters of the bound water characteristic peak in the infrared spectral feature vector of the bound water are chemically coupled with the absolute humidity and dew point temperature data in the environmental temperature and humidity feature set. The data after chemical potential field coupling is input into the chemical steady state model to calculate the degree of bond weakening and the dissociation risk coefficient. A bonding state monitoring mechanism based on chemical potential field coupling is established. The absolute humidity data of the environment is converted into the chemical potential of environmental water molecules through thermodynamic analysis, and the peak position shift of the bound water characteristic peak is analyzed as the change of hydrogen bond interaction energy. An energy balance equation is constructed to realize the dynamic correlation between the external environment and the internal bonding state.

[0029] A chemical stability model for bound water was constructed for quantitative evaluation. The model calculates the adsorption potential of environmental water molecules based on absolute humidity and dew point temperature data, and inverses the current bonding strength based on the absorbance and peak position shift of the characteristic peak of bound water. By calculating the real-time ratio of bonding strength to the adsorption potential of environmental water molecules, dynamic monitoring of the stability of bound water is achieved.

[0030] When the ratio is lower than the preset bonding weakening threshold, the bonding weakening degree is output as negatively correlated with the real-time ratio; when the ratio is further lower than the dissociation risk threshold, the dissociation risk coefficient is output as negatively correlated with the real-time ratio. These two parameters quantify the degree of bonding structure stability decay and the risk of bound water detachment, respectively.

[0031] S320: The bond weakening degree and dissociation risk coefficient are compared in parallel with preset bond weakening degree safety threshold and dissociation risk threshold, respectively: if the bond weakening degree exceeds the bond weakening degree safety threshold, it is determined to be an abnormality of unstable bound water bonding; otherwise, it is determined to be a stable bonding state. If the dissociation risk coefficient exceeds the dissociation risk threshold, it is determined to be an abnormality of excessive dissociation of bound water; otherwise, it is determined to be a normal dissociation state. The abnormal state is determined based on the intrinsic characteristics of the coating material. The bond weakening degree safety threshold is determined by analyzing the supporting ability of hydroxyl density on the hydrogen bond network and the contribution of crystallinity to structural stability. The dissociation risk threshold is obtained statistically through accelerated aging tests. Through the dual threshold determination mechanism, it is ensured that the abnormal diagnosis results reflect both the immediate risk state and conform to the material durability characteristics.

[0032] Based on the above technical solution, the steps of assessing the risk of coating performance degradation caused by the bound water treatment process, and generating bound water treatment process parameters to prevent coating performance degradation, according to the abnormal analysis results of the bound water in the coating and the coating property characteristics, include:

[0033] S330: Establish a surface hydroxyl-bond stability correlation model between the hydroxyl density of the coating surface and the bonding stability of bound water to characterize the influence of the number of active sites per unit area on chemical bonding stability; combine the surface hydroxyl-bond stability correlation model with the degree of bond weakening to determine the curing atmosphere humidity control range required to maintain bonding stability; establish a quantitative relationship between surface hydroxyl density and bound water bonding strength to characterize the influence of the number of active sites per unit area on chemical bonding energy based on interfacial chemistry theory; combine bond weakening data to analyze the influence of hydrogen bond network stability decay on interfacial chemical properties and determine the curing atmosphere humidity control range required to maintain bonding stability.

[0034] S340: Establish a crystallinity-thermal stability correlation model between coating crystallinity parameters and lattice thermal stability to reflect the mechanism by which crystal structure integrity affects resistance to thermal disturbances; combine the crystallinity-thermal stability correlation model with the dissociation risk coefficient to determine the maximum heating rate threshold to prevent excessive dissociation; establish a mapping relationship between coating crystallinity parameters and lattice structure stability to reflect the mechanism by which crystal structure integrity affects resistance to thermal disturbances based on crystal field theory; combine the dissociation risk coefficient to assess the degree of influence of lattice defects on the stability of bound water and determine the maximum heating rate threshold to prevent excessive dissociation.

[0035] S350: Based on the difference in thermal expansion coefficients, elastic modulus, and coating thickness parameters between the substrate and the coating, the thermal stress distribution at the coating-substrate interface is calculated to characterize the deformation compatibility of heterogeneous materials in a temperature field. Combining the interface thermal stress distribution with bond weakening, a staged heat preservation time parameter is determined to ensure the stability of the interface chemical structure. Based on the thermal expansion coefficients, elastic modulus, and coating thickness parameters of the substrate and the coating, the thermal stress distribution at the coating-substrate interface is calculated using multilayer thermoelastic theory to characterize the deformation compatibility of heterogeneous materials in a temperature field. Combining the thermal stress distribution with the coating's porosity and pore size distribution parameters, the influence of porous structures on interface stress concentration is analyzed, and a staged heat preservation time parameter to ensure structural integrity is determined.

[0036] S360: By combining the curing atmosphere humidity control range, maximum heating rate threshold, and staged heat preservation time parameters, the bound water treatment process parameters are generated to prevent coating performance degradation; by integrating the above parameters, a complete bound water treatment process parameter protection system is constructed to ensure that the chemical stability of the coating is protected to the maximum extent while regulating the bound water state.

[0037] Based on the above technical solution, the influence of water treatment process parameters on coating integrity is analyzed, including:

[0038] S410: Establish a comprehensive risk quantification model for coating loss. Using the process parameters obtained from S2 and S3 as inputs, calculate two types of risks in parallel: structural damage and performance degradation, generating two independent risk quantification values: a structural damage risk value based on the dispersion and local enrichment risk coefficient of free water distribution, combined with coating microstructure parameters; and a performance degradation risk value based on the bonding weakening degree and dissociation risk coefficient, combined with coating chemical property parameters. Construct two independent risk assessment channels: in the structural damage risk assessment channel, a structural damage risk value is established based on the dispersion and local enrichment risk coefficient of free water distribution, combined with coating microstructure parameters; in the performance degradation risk assessment channel, a performance degradation risk value is established based on the bonding weakening degree and dissociation risk coefficient, combined with coating chemical property parameters.

[0039] S420: Based on structural damage risk values ​​and performance degradation risk values, an experimental design method is used to change the parameter combinations of drying temperature, ventilation rate, curing humidity, and heating rate. The risk response value under each parameter combination is calculated using the risk quantification model, establishing a quantitative mapping relationship between process parameters and dual risks, and forming a process parameter-dual risk response relationship graph. This graph characterizes the impact of process parameter changes on structural integrity and chemical stability, while also reflecting the coupling effect between various process parameters. Based on the dual risk values, an experimental design method is used to systematically change the combination of process parameters, and the risk response value under each parameter combination is calculated using the risk quantification model. A quantitative mapping relationship between process parameters and dual risks is established, forming a process parameter-dual risk response relationship graph, accurately characterizing the impact of process parameter changes on coating integrity.

[0040] Based on the above technical solution, by coordinating the process requirements of coating structural integrity and chemical stability, a balanced process scheme for the treatment of free water and bound water is generated, including:

[0041] S430: Based on the real-time proportional relationship and absolute magnitude of the coating structure damage risk value and performance degradation risk value, the coating moisture treatment process is dynamically divided into three process stages: when the ratio of the structural damage risk value to the performance degradation risk value exceeds the structural dominant proportional coefficient and exceeds the structural damage risk safety threshold, the main free water removal stage is entered; when the two risk values ​​are in a preset equilibrium range and neither exceeds their respective safety thresholds, the equilibrium transition stage is entered; when the ratio of the performance degradation risk value to the structural damage risk value exceeds the performance dominant proportional coefficient and exceeds the performance degradation risk safety threshold, the performance stabilization stage is entered; a dynamic process control mechanism based on risk status identification is established; according to the real-time proportional relationship and absolute magnitude of the coating structure damage risk value and performance degradation risk value, the treatment process is divided into three strategy stages: the main free water removal stage, the equilibrium transition stage, and the performance stabilization stage.

[0042] S440: Based on the identified process stages, in the process parameter-dual-risk response relationship graph, a specific optimization model is established for each stage and the optimal combination of process parameters is solved. The specific solution process is as follows:

[0043] In the main stage of removing free water, a dewatering optimization model is established with the objective function of minimizing the structural damage risk value and the condition that the performance degradation risk value does not exceed the performance degradation warning threshold. Macroscopic process parameters, including drying temperature, ventilation rate and dehumidification rate, are obtained by solving the dewatering optimization model.

[0044] During the equilibrium transition phase, a dual-water balance optimization model is established with the goal of minimizing the weighted sum of structural damage risk and performance degradation risk. By adjusting the weight coefficients to coordinate the rate of decrease of the two risks, the Pareto optimal solution set of the process parameters is obtained. This solution set defines the steady-state process parameters for this phase, including the isothermal holding value, equilibrium ventilation volume, and humidity stability range.

[0045] In the performance stabilization stage, a performance optimization model is established with the objective function of minimizing the performance degradation risk value and the constraint that the structural damage risk value does not exceed the structural damage safety threshold. By solving the performance optimization model, fine process parameters are obtained, including the heating rate, curing humidity window, and stage holding time. A staged multi-objective optimization system is constructed. In the main free water removal stage, the objective is to minimize the structural damage risk, and the enhanced mass transfer process parameters are solved. In the equilibrium transition stage, the objective is to minimize the weighted sum of the two risks, and the Pareto optimal solution set of the process parameters is solved. In the performance stabilization stage, the objective is to minimize the performance degradation risk, and the protective process parameters are solved.

[0046] S450: By integrating the above optimal process parameter combinations, a balanced process scheme is formed for the treatment of free water and bound water; by systematically integrating the optimal process parameter combinations of the three stages, a complete balanced process scheme is constructed to achieve the best balance between treatment effect and coating protection.

[0047] Based on the above technical solution, the treatment processes for free water and bound water are synergistically controlled, including:

[0048] S510: Extract the balanced process scheme of free water and bound water treatment process; convert the balanced process scheme into specific control commands and issue them to the execution equipment; monitor the process execution status and coating response characteristics in real time, and dynamically calculate the water balance state deviation index based on the real-time collected infrared spectral characteristic data and environmental temperature and humidity parameters.

[0049] S520: Based on the balanced process scheme of free water and bound water treatment, the treatment process parameters of free water and bound water are coordinated and controlled; when the deviation exceeds the tolerance range, the process parameter correction amount is calculated by reverse optimization algorithm based on the process parameter-dual risk response relationship spectrum, and the control command is dynamically adjusted; an adaptive control mechanism based on state feedback is established to realize intelligent closed-loop control and continuous optimization of the treatment process.

[0050] Secondly, this application provides an automated magnesium oxide coating analysis system, comprising:

[0051] The data acquisition and feature construction module is used to acquire the property data, infrared spectral data and environmental temperature and humidity data of the magnesium oxide coating, and construct the coating property features, infrared spectral feature vectors of free water and bound water and environmental temperature and humidity feature set through parsing and processing.

[0052] The free water analysis module is used to perform anomaly analysis of the free water state in the coating based on the free water infrared spectral feature vector and the environmental temperature and humidity feature set, and to generate free water treatment process parameters to suppress coating structural damage by combining the coating property characteristics. This module establishes a dynamic migration model to quantitatively analyze the distribution characteristics and migration law of free water in the coating, accurately assess the risk of structural damage caused by uneven moisture, and provide a scientific basis for optimizing process parameters.

[0053] The bound water analysis module is used to perform anomaly analysis of the bound water state of the coating based on the infrared spectral feature vector of the bound water and the set of environmental temperature and humidity features, and to generate bound water treatment process parameters to prevent coating performance degradation based on the coating property features. This module monitors the changes in the bonding state of bound water by constructing a chemical stability model, assesses the risk of performance degradation caused by chemical bond dissociation, and ensures the effective maintenance of the chemical stability of the coating.

[0054] The balanced process analysis module is used to analyze the impact of water treatment processes on the integrity of the coating by examining the treatment parameters of free water and bound water. By coordinating the process requirements of coating structural integrity and chemical stability, it generates a balanced process scheme for the treatment of free water and bound water. This module establishes a dual-risk assessment mechanism to identify the critical conditions for structural damage and performance degradation, and uses a multi-objective optimization algorithm to solve for the optimal balance point of process parameters, achieving the best balance between treatment effect and coating protection.

[0055] The collaborative control execution module is used to control the execution process of the free water and bound water treatment processes based on the balanced process scheme.

[0056] Thirdly, this application provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the automated magnesium oxide coating analysis method as described in the first aspect by calling the computer program stored in the memory.

[0057] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform an automated magnesium oxide coating analysis method as described in the first aspect.

[0058] Compared with the prior art, this application has the following advantages and beneficial effects:

[0059] This application achieves accurate identification and independent analysis of moisture in different states by constructing a separation and monitoring system for free water and bound water; it establishes an accurate assessment model of coating moisture state through a multi-source data fusion analysis mechanism; it innovatively proposes a dynamic process control strategy based on risk state identification, and achieves a process balance between efficient removal of free water and stable retention of bound water through a staged multi-objective optimization algorithm; this solution effectively solves the technical problem that traditional analysis methods cannot simultaneously take into account the integrity of coating structure and chemical stability, significantly improves the accuracy and reliability of coating moisture treatment process, and provides a complete technical solution for coating quality control. Attached Figure Description

[0060] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0061] Figure 1 This is a schematic diagram of the overall process of an automated magnesium oxide coating analysis method provided in an embodiment of this application;

[0062] Figure 2 This is a schematic diagram of the structure for analyzing the abnormal state of free water in the coating provided in this application embodiment;

[0063] Figure 3 This is a schematic diagram of the structure for analyzing the abnormal state of the coating bound water provided in the embodiments of this application;

[0064] Figure 4 This is a schematic diagram illustrating the impact of the water treatment process provided in this application embodiment on the integrity of the coating.

[0065] Figure 5 This is a schematic diagram of the balanced process scheme for the treatment of free water and bound water provided in the embodiments of this application;

[0066] Figure 6 This is a schematic diagram of the structure of an automated magnesium oxide coating analysis system provided in an embodiment of this application;

[0067] Figure 7 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0068] The technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments and specific features in the embodiments are detailed descriptions of the technical solution of this application, rather than limitations thereof. In the absence of conflict, the embodiments and technical features in the embodiments can be combined with each other.

[0069] Please see Figure 1 , Figure 1 This is a schematic diagram of the overall process of an automated magnesium oxide coating analysis method provided in this application embodiment, which specifically includes the following steps:

[0070] S1: Obtain the properties of the magnesium oxide coating, infrared spectral data, and environmental temperature and humidity data, and after analysis and processing, construct the coating property characteristics, infrared spectral feature vectors of free water and bound water, and environmental temperature and humidity feature set.

[0071] The steps for acquiring magnesium oxide coating properties, infrared spectral data, and ambient temperature and humidity data include:

[0072] The coating properties were obtained using appropriate testing equipment: coating thickness was measured using a scanning electron microscope; the average particle size and crystallinity of magnesium oxide particles were analyzed using an X-ray diffractometer; the coefficient of thermal expansion and elastic modulus were measured using a thermomechanical analyzer and a nanoindenter; porosity and pore size distribution were determined using a mercury porosimeter; and the surface hydroxyl density was analyzed using X-ray photoelectron spectroscopy.

[0073] Infrared spectral feature vectors were acquired using a Fourier transform infrared spectrometer at 1640 cm⁻¹. -1 In the vicinity of the free water characteristic region, the absorbance and full width at half maximum (FWHM) of the characteristic peaks were extracted; at 3300 cm⁻¹ -1 The absorbance and peak position shift of the characteristic peaks in the nearby bound water characteristic region are extracted.

[0074] The environmental temperature and humidity feature set is collected through a network of temperature and humidity sensors, and derived features such as temperature gradient, humidity change rate, absolute humidity and dew point temperature are calculated based on the original time series data.

[0075] S2: Combine the infrared spectral feature vector of free water with the environmental temperature and humidity feature set to perform anomaly analysis of the free water state of the coating; based on the results of the anomaly analysis of the free water in the coating and the coating property characteristics, assess the risk of coating morphological damage caused by the free water treatment process, and generate free water treatment process parameters to suppress coating structural damage accordingly.

[0076] S210: The absorbance and full width at half maximum (FWHM) parameters of the free water characteristic peaks in the infrared spectral feature vector are spatiotemporally coupled with the temperature gradient data and humidity change rate data in the environmental temperature and humidity feature set. The spatiotemporally coupled data is then used as input to the dynamic migration model to calculate the distribution dispersion and local enrichment risk coefficient of free water. The model also spatiotemporally couples the spectral characteristics of free water with the environmental temperature and humidity characteristics and inputs this data into the dynamic migration model. This model couples macroscopic migration driven by temperature gradients with microscopic diffusion dominated by concentration gradients. By calculating the real-time ratio of these two factors, i.e., the migration-diffusion ratio, it dynamically outputs the distribution dispersion and local enrichment risk coefficient.

[0077] S220: The distribution dispersion and local enrichment risk coefficient are compared in parallel with the preset distribution dispersion safety threshold and local enrichment risk threshold, respectively; if the distribution dispersion exceeds the distribution dispersion safety threshold, it is determined that the free water distribution is abnormally uneven, otherwise it is determined that the free water distribution is normal; if the local enrichment risk coefficient exceeds the local enrichment risk threshold, it is determined that the local enrichment of free water is abnormal, otherwise it is determined that the local distribution concentration of free water is normal.

[0078] The risk coefficients mentioned above are compared with the safety thresholds set based on coating properties (such as porosity, interfacial bonding strength, and material yield strength) to determine whether the free water distribution is uneven or the local enrichment is abnormal.

[0079] S230: Establish a pore strength function model of coating porosity, pore size distribution parameters and coating pore expansion resistance to characterize the influence of pore structure on water capillary force; combine the pore strength function model with the dispersion of free water distribution to determine the maximum allowable humidity change rate to prevent swelling deformation.

[0080] S240: Establish a particle size-crack correlation model between the average particle size of magnesium oxide particles and the driving force of crack propagation to reflect the influence mechanism of particle size on stress concentration inside the coating; combine the particle size-crack correlation model with the local enrichment risk coefficient to determine the safe threshold of temperature gradient to suppress crack propagation.

[0081] S250: Based on the coating thickness, the elastic modulus parameters of the substrate and the coating, and the difference in their coefficients of thermal expansion, the interfacial thermal stress distribution between the substrate and the coating is calculated to characterize the deformation coordination characteristics of the substrate and the coating during heat treatment; combined with the interfacial thermal stress distribution and the coating crystallinity, the drying temperature control range and ventilation rate adjustment range for suppressing structural damage are determined.

[0082] S260: Integrating the above-mentioned maximum allowable humidity change rate, temperature gradient safety threshold, drying temperature control range, and ventilation rate adjustment range, free water treatment process parameters to suppress coating structural damage are generated; based on the anomaly analysis results, the structural damage risk is assessed in conjunction with coating properties: a pore strength function model is established to determine the maximum allowable humidity change rate; a particle size-crack correlation model is established to determine the temperature gradient safety threshold; through interfacial thermal stress analysis, the drying temperature control range and ventilation rate adjustment range are determined; integrating the above parameters, free water treatment process parameters to suppress structural damage are generated.

[0083] S3: Perform anomaly analysis of the bound water state of the coating by combining the infrared spectral feature vector of bound water with the environmental temperature and humidity feature set; based on the results of the anomaly analysis of the bound water and the coating property characteristics, assess the risk of coating performance damage caused by the bound water treatment process, and generate bound water treatment process parameters to prevent coating performance degradation accordingly.

[0084] S310: The absorbance and peak position shift parameters of the bound water characteristic peak in the infrared spectral feature vector of the bound water are chemically coupled with the absolute humidity and dew point temperature data in the environmental temperature and humidity feature set, and the data after chemical potential coupling is input into the chemical steady-state model to calculate the bonding weakening degree and dissociation risk coefficient; the spectral features of bound water are chemically coupled with the environmental temperature and humidity features and input into the chemical steady-state model; the model dynamically outputs the bonding weakening degree and dissociation risk coefficient by calculating the real-time ratio of the bonding strength inside the coating to the adsorption potential of environmental water molecules.

[0085] S320: The bonding weakening degree and dissociation risk coefficient are compared in parallel with the preset bonding weakening degree safety threshold and dissociation risk threshold, respectively: if the bonding weakening degree exceeds the bonding weakening degree safety threshold, it is determined that the bound water bonding is unstable and abnormal; otherwise, it is determined that the bonding state is stable. If the dissociation risk coefficient exceeds the dissociation risk threshold, it is determined that the bound water is excessively dissociated and abnormal; otherwise, it is determined that the dissociation state is normal. The above risk coefficient is compared with the safety threshold set based on the coating properties to determine whether the bound water bonding is unstable or excessively dissociated and abnormal.

[0086] S330: Establish a surface hydroxyl-bonding stability correlation model between the hydroxyl density of the coating surface and the bonding stability of bound water, to characterize the influence of the number of active sites per unit area on chemical bonding stability; combine the surface hydroxyl-bonding stability correlation model with the degree of bonding weakening to determine the curing atmosphere humidity control range required to maintain bonding stability.

[0087] S340: Establish a crystallinity-thermal stability correlation model between coating crystallinity parameters and lattice thermal stability to reflect the mechanism by which crystal structure integrity affects the resistance to thermal disturbances; combine the crystallinity-thermal stability correlation model with the dissociation risk coefficient to determine the maximum heating rate threshold to prevent excessive dissociation.

[0088] S350: Based on the difference in thermal expansion coefficients, elastic modulus and coating thickness parameters between the substrate and the coating, the thermal stress distribution at the interface between the coating and the substrate is calculated to characterize the deformation compatibility of heterogeneous materials in the temperature field; combined with the interface thermal stress distribution and bonding weakening degree, the staged heat preservation time parameters to ensure the stability of the interface chemical structure are determined.

[0089] S360: Combining the curing atmosphere humidity control range, maximum heating rate threshold, and staged holding time parameters, generate bound water treatment process parameters to prevent coating performance degradation; based on anomaly analysis results, assess the risk of performance degradation by combining coating properties: establish a surface hydroxyl-bond stability correlation model to determine the curing atmosphere humidity control range; establish a crystallinity-thermal stability correlation model to determine the maximum heating rate threshold; determine the staged holding time parameters through interfacial thermal stress distribution analysis; integrate the above parameters to generate bound water treatment process parameters to prevent performance degradation.

[0090] S4: Analyze the impact of water treatment process parameters on coating integrity on the treatment parameters of free water and bound water, and generate a balanced process scheme for the treatment of free water and bound water by coordinating the process requirements of coating structural integrity and chemical stability.

[0091] S410: Establish a comprehensive risk quantification model for coating loss. Using the process parameters obtained from S2 and S3 as inputs, calculate two types of risks in parallel: structural damage and performance degradation, and generate two independent risk quantification values ​​for structural damage and performance degradation: Based on the dispersion of free water distribution and the risk coefficient of local enrichment, combined with the microstructure parameters of the coating, establish the risk value of structural damage; based on the bonding weakening degree and the risk coefficient of dissociation, combined with the chemical property parameters of the coating, establish the risk value of performance degradation.

[0092] S420: Based on structural damage risk values ​​and performance degradation risk values, an experimental design method is used to change the parameter combinations of drying temperature, ventilation rate, curing humidity, and heating rate. The risk response values ​​under each parameter combination are calculated through the risk quantification model, establishing a quantitative mapping relationship between process parameters and dual risks, and forming a process parameter-dual risk response relationship spectrum to characterize the influence of process parameter changes on structural integrity and chemical stability, while reflecting the coupling effect between various process parameters. A comprehensive coating loss risk quantification model is established to calculate structural damage risk values ​​and performance degradation risk values ​​in parallel, forming a process parameter-dual risk response relationship spectrum to characterize the comprehensive impact of process adjustments on coating integrity.

[0093] S430: Based on the real-time proportional relationship and absolute magnitude of the coating structure damage risk value and the performance degradation risk value, the coating moisture treatment process is dynamically divided into three process stages: when the ratio of the structure damage risk value to the performance degradation risk value exceeds the structural dominant proportional coefficient and exceeds the structural damage risk safety threshold, the process enters the main free water removal stage; when the two risk values ​​are in a preset equilibrium range and neither exceeds their respective safety thresholds, the process enters the equilibrium transition stage; when the ratio of the performance degradation risk value to the structure damage risk value exceeds the performance dominant proportional coefficient and exceeds the performance degradation risk safety threshold, the process enters the performance stabilization stage.

[0094] S440: Based on the identified process stages, in the process parameter-dual-risk response relationship graph, a specific optimization model is established for each stage and the optimal combination of process parameters is solved. The specific solution process is as follows:

[0095] In the main stage of removing free water, a dewatering optimization model is established with the objective function of minimizing the structural damage risk value and the condition that the performance degradation risk value does not exceed the performance degradation warning threshold. Macroscopic process parameters, including drying temperature, ventilation rate and dehumidification rate, are obtained by solving the dewatering optimization model.

[0096] During the equilibrium transition phase, a dual-water balance optimization model is established with the goal of minimizing the weighted sum of structural damage risk and performance degradation risk. By adjusting the weight coefficients to coordinate the rate of decrease of the two risks, the Pareto optimal solution set of the process parameters is obtained. This solution set defines the steady-state process parameters for this phase, including the isothermal holding value, equilibrium ventilation volume, and humidity stability range.

[0097] During the performance stabilization phase, a performance optimization model is established with the objective function of minimizing the performance degradation risk value and the constraint that the structural damage risk value does not exceed the structural damage safety threshold. By solving the performance optimization model, fine process parameters are obtained, including heating rate, curing humidity window and stage holding time.

[0098] Based on the real-time ratio and absolute level of the dual risk values, the processing is dynamically divided into three stages:

[0099] Primary stage for removing free water: When the risk of structural damage is dominant, the goal is to rapidly remove free water and generate enhanced mass transfer process parameters;

[0100] Balanced transition phase: When both risks are within the safe range and their proportions are balanced, steady-state process parameters are generated with the goal of synergistic optimization.

[0101] Performance stabilization phase: When the risk of performance degradation is dominant, fine protective process parameters are generated with the goal of protecting bound water and chemical stability.

[0102] S450: By integrating the above optimal process parameter combinations, a balanced process scheme for the treatment of free water and bound water is generated; through phased multi-objective optimization, the above parameter combinations are integrated to finally generate a balanced process scheme that takes into account both structural integrity and chemical stability.

[0103] S5: Based on the balanced process scheme, the treatment process of free water and bound water is synergistically controlled;

[0104] S510: A balanced process scheme for the extraction of free water and bound water; based on the generated balanced process scheme, the execution equipment is driven to perform coordinated control. During process execution, the infrared spectrum of the coating and environmental parameters are monitored in real time, and the overall deviation of key state indicators from the target values ​​is calculated.

[0105] S520: Based on the balanced process scheme of free water and bound water treatment, the treatment process parameters of free water and bound water are coordinated and controlled; when the deviation exceeds the preset tolerance, the correction amount of the process parameters is dynamically solved in reverse according to the established process parameter-risk response relationship map, and the execution command is adjusted in real time.

[0106] This closed-loop control mechanism ensures that the coating structure integrity and chemical stability are maintained at the best level throughout the process, achieving adaptive synergistic regulation.

[0107] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure for analyzing the anomaly of the free water state in the coating provided in this application embodiment. This embodiment demonstrates the complete process of analyzing the anomaly state from the basic characteristic data of free water and finally outputting the adaptation process, including:

[0108] The steps for analyzing the anomalies in the free water state of the coating include: firstly, establishing a dynamic relationship between environmental driving forces and the water state through spatiotemporal correlation coupling; specifically, synchronizing and interpolating the infrared characteristics of free water with environmental parameters to form a continuous time series; then calculating the sliding window correlation coefficients of temperature gradient-absorbance and humidity change rate-half-peak width to quantify the intensity of the thermal driving force on the water content and the degree of influence of humidity fluctuations on the distribution uniformity.

[0109] Based on the environmental driving intensity revealed by the above correlation analysis, a dynamic migration mathematical model is constructed to achieve accurate analysis of the transport mechanism. The model abstracts the coating as a porous medium and couples two parallel mechanisms: macroscopic migration driven by temperature gradient and microscopic diffusion dominated by concentration gradient, thus fully characterizing the transport behavior of moisture in the coating.

[0110] The macroscopic migration model is based on Darcy's law and incorporates the ambient temperature gradient. As the primary driving force, its governing equations are as follows:

[0111] ;

[0112] in, The output is the macroscopic migration rate. The permeability tensor is determined by the coating porosity and pore size distribution. The dynamic viscosity of water, This is the thermal osmotic pressure gradient derived from the temperature gradient.

[0113] The micro-diffusion model is based on the unsteady Fick second law, which considers the water concentration gradient. As the main driving force, the moisture concentration gradient The inversion calculation is based on the half-peak width parameter of the free water characteristic peak obtained from the aforementioned dynamic correlation analysis. The governing equations of the micro-diffusion model are as follows:

[0114] ;

[0115] By discretizing and solving the partial differential equation, the microscopic diffusion flux of water molecules is obtained, and then it is converted into an equivalent microscopic diffusion rate. ;in, The effective diffusion coefficient is a function of the coating crystallinity and hydroxyl density.

[0116] This dynamic migration model uses a coupled solver to perform parallel computation and data exchange on the two governing equations, thereby outputting synchronous results. and These two key physical quantities;

[0117] Output-based and The distribution dispersion is calculated using the following core equation. With the risk coefficient of local enrichment :

[0118] Local enrichment risk coefficient equation: when the migration-diffusion ratio Persistently above the macro migration-dominant threshold When the enrichment risk coefficient is calculated, it is given by the following formula:

[0119] ;

[0120] in, This is a risk accumulation weighting factor used to adjust the model's sensitivity to risk accumulation. The time frame for risk accumulation is defined as the length of time for retrospective risk calculation. At a historical moment The instantaneous value of the migration-diffusion ratio; It is the positive operator; The characteristic migration rate, whose value is related to the coating material and structure, is used to normalize the macroscopic migration rate in order to eliminate dimensions and establish a unified evaluation benchmark. As the time variable for integration, from Changes within the window, This indicates the time Integral elements.

[0121] Distribution dispersion equation: When the fluctuation amplitude of the migration-diffusion ratio exceeds the threshold for determining mechanism discrepancy ( > Only when the time condition is met will the distribution dispersion be calculated and output; at this time, the distribution dispersion is calculated by the following formula:

[0122] ;

[0123] in, The dispersion coefficient is used to adjust the model's sensitivity to uneven distribution. Migration-Diffusion Ratio within the Sliding Time Window The standard deviation is used to quantify the fluctuation range of water transport mechanisms; This represents the average microscopic diffusion rate within the time window, and its value reflects the overall intensity of spontaneous diffusion of water molecules.

[0124] The two key threshold settings involved in this embodiment are as follows:

[0125] Macro migration dominant threshold Its setting is derived from the inherent mass transfer characteristics of the coating, namely the ratio of macroscopic permeability to microscopic effective diffusion coefficient, which reflects the inherent resistance characteristics of the coating material itself to the water migration path.

[0126] Threshold for determining mechanism failure Its setting is derived from historical data under stable system conditions, namely the inherent standard deviation of the migration-diffusion ratio under normal operating conditions, which represents the stability benchmark of the synergistic effect of the water transport mechanism.

[0127] Ultimately, based on the migration-diffusion ratio The distribution dispersion obtained by derivation calculation With the risk coefficient of local enrichment The system performs an anomaly detection for the free water state; this detection process is implemented through a dual threshold comparison mechanism.

[0128] Distribution anomaly detection: Determine the distribution dispersion Compared with the preset distribution dispersion safety threshold Perform a comparison; this threshold The stability of the coating pore structure was determined through a model, and it is a function of the coating porosity and the interfacial bonding strength, with the specific relationship as follows:

[0129] ;

[0130] in, The proportionality coefficient was obtained through calibration using a coating pore structure stability model; The density of the coating is characterized by its lower porosity, which indicates a denser structure and a higher tolerance for uneven moisture distribution. The interfacial bonding strength is the bonding force between the coating and the substrate. The higher this value, the stronger the coating's ability to resist stress caused by uneven moisture distribution.

[0131] when > At that time, it was determined that the coating had an abnormal uneven distribution of moisture.

[0132] Enrichment anomaly detection: This involves determining the risk coefficient of local enrichment. Compared with the preset local enrichment risk threshold Perform a comparison; this threshold The thermo-mechanical coupling simulation model determined that the coefficient of performance (COP) is a function of the coating material's yield strength and thermal stress tolerance, with the specific relationship as follows:

[0133] ;

[0134] in, The proportionality coefficient is obtained through calibration using a thermo-mechanical coupling simulation model; the yield strength is the critical stress at which the coating material undergoes plastic deformation. The higher the value, the stronger the material's ability to resist local plastic deformation caused by moisture accumulation; the thermal stress is the thermal mismatch stress generated inside the coating under the process temperature field. The larger this value, the higher the risk of damage caused by the combined effect of moisture accumulation.

[0135] when > At that time, it was determined that there was an abnormal local accumulation of moisture in the coating.

[0136] This parallel decision-making process enables the identification and classification of abnormal free water states in the coating. The distribution dispersion calculated during the decision-making process... With the risk coefficient of local enrichment These two continuous quantitative indicators will serve as key input parameters, directly passed to the subsequent structural damage risk assessment module, providing a quantitative diagnostic basis for process parameter optimization.

[0137] The steps for assessing the risk of coating morphological damage caused by the free water treatment process, and accordingly generating free water treatment process parameters to suppress coating structural damage, include:

[0138] Pore ​​structure and swelling risk analysis: This step aims to determine the critical humidity condition to prevent coating swelling and deformation. This embodiment establishes a pore strength function model based on elastoplastic mechanics, characterizes the pore structure using a Weiber distribution, and sets the free water distribution dispersion... As input parameters, the additional stress on the pore wall caused by uneven moisture distribution is analyzed; the function parameters are determined through nanoindentation experimental data, and a quantitative relationship model between the uneven distribution and the critical fracture stress is established. This relationship can be characterized as follows:

[0139] ;

[0140] in, The intrinsic critical stress of the coating was measured by nanoindentation experiments; The solid phase ratio and porosity of the coating are given. The lower the value, the denser the structure, and the greater the contribution of the matrix strength. The porosity sensitivity index is obtained by fitting the strength test data of samples with different porosities, and reflects the degree of nonlinear influence of porosity changes on strength. The moisture distribution attenuation coefficient is determined through a combination of coupled fluid-mechanical simulation and acoustic emission experiments, and is used to quantify the distribution dispersion. The model exhibits an exponential decay effect on critical stress and achieves dynamic assessment of coating swelling and deformation risk by coupling the dual effects of porosity and moisture distribution.

[0141] Based on this model, the maximum allowable rate of humidity change to prevent swelling and deformation of the coating is obtained by inversion calculation through the capillary force-humidity balance relationship. This parameter serves as the precise critical value for humidity control in the drying process.

[0142] Particle size and crack propagation analysis: This step aims to determine the safe temperature boundary for suppressing microcracks. This embodiment constructs a particle size-crack correlation model based on fracture mechanics, establishes a quantitative relationship between the average particle size of magnesium oxide and the stress concentration factor, and includes a local enrichment risk factor. As a key input, the weakening effect of moisture enrichment on interfacial strength is assessed; by analyzing the driving effect of particle size on cracks, a mathematical relationship between enrichment risk and crack propagation force is established. Based on linear elastic fracture mechanics, the relationship between the critical stress intensity factor and enrichment risk can be expressed as:

[0143] ;

[0144] in, Apparent fracture toughness characterizes the coating’s actual ability to resist crack propagation under the risk of localized moisture accumulation in real time. This represents the intrinsic fracture toughness of the coating material in a dry state; a higher value indicates a stronger ability of the material to resist crack propagation. The coupling coefficient is obtained through fracture mechanics simulation and experimental data calibration, and is used to quantify the degree of weakening of fracture toughness by local water enrichment.

[0145] By combining the fracture toughness parameters of the coating, the safety threshold of the temperature gradient for inhibiting the initiation and propagation of microcracks was finally determined, which serves as the safety boundary for the rate of temperature change during the heat treatment process.

[0146] Interfacial thermodynamic compatibility analysis: This step aims to determine the macroscopic process window that ensures the stability of the substrate-coating system structure. A thermal stress analysis model is established using multilayer thermoelastic theory. The interfacial thermal stress distribution is calculated based on the coating thickness, elastic modulus, and the difference in thermal expansion coefficients, with corrections made considering the stress buffering capacity of crystallinity. The specific formula for interfacial thermal stress is as follows:

[0147] ;

[0148] in, Interfacial thermal stress, representing the stress caused by temperature changes. The in-plane tensile stress generated near the interface between the coating and the substrate is the main driving force for coating wrinkling, cracking or interface delamination. The elastic modulus of the coating characterizes the material's ability to resist elastic deformation. The difference between the coefficients of thermal expansion between the coating and the substrate is the largest in absolute value, and the more severe the deformation incompatibility caused by temperature changes. This refers to the temperature change during the process. The Poisson's ratio of the coating; the denominator term ( This demonstrates the amplification effect of lateral shrinkage of the material on axial stress under plane stress conditions;

[0149] Based on theoretical estimation using thermal stress formulas and accurate stress cloud maps obtained through finite element simulation, the interface stress concentration under different combinations of drying temperature and ventilation rate is analyzed to identify a safe process window for controlling thermal stress below the yield strength of the coating material.

[0150] This step aims to integrate all critical process parameters to form a complete and executable solution. By establishing a multi-parameter collaborative optimization model, the maximum allowable humidity change rate, temperature gradient safety threshold, drying temperature control range, and ventilation rate adjustment range are all incorporated into the decision box.

[0151] The core objective of this optimization process is to solve the problem using a sequential quadratic programming algorithm, while strictly adhering to the safety boundaries defined by the aforementioned parameters. This algorithm iteratively constructs and solves quadratic programming subproblems, gradually approximating the optimal parameter combination that satisfies all process constraints and minimizes the risk of structural damage.

[0152] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure for analyzing the abnormal state of bound water in the coating provided in this embodiment. This embodiment demonstrates the complete process of analyzing abnormal states from basic bound water characteristic data and finally outputting an adapted process, including:

[0153] First, a chemical potential field coupling between environmental driving forces and bonding state responses is established. Through data alignment and interpolation, the infrared spectral characteristics of bound water and environmental parameters are fused into a synchronous time series. Based on this, using thermodynamic relationships and spectral-energy mapping, the changes in the chemical potential of environmental water molecules and the hydrogen bonding energy within the coating are calculated to quantify the external desorption driving force and the internal bonding strength. Finally, by analyzing the dynamic correlation between the two within a sliding time window, a normalized coupling strength coefficient is generated, completing the construction of the chemical potential field.

[0154] Subsequently, the aforementioned coupling parameters are input into the chemical steady-state model for precise quantitative evaluation, enabling dynamic monitoring and risk assessment of bound water stability. The quantification process of the chemical steady-state model is as follows:

[0155] This model, based on the principle of thermodynamic equilibrium, aims to quantify the chemical stability of bound water within the coating; its core lies in calculating a key dimensionless ratio—the real-time bonding stability ratio. This ratio is used to dynamically characterize the balance between bonding strength and environmental desorption driving force. The ratio is calculated as follows:

[0156] ;

[0157] in: The adsorption potential of environmental water molecules is obtained by taking the absolute value of the chemical potential of environmental water molecules, and is used to directly characterize the strength of the driving force of environmental desorption. The current bond strength is determined by the change in hydrogen bond interaction energy mentioned above. After normalization, the calculation formula is:

[0158] ;

[0159] in, This is a proportionality coefficient related to the intrinsic bonding energy of the coating.

[0160] This model is based on real-time bonding stability ratio. Perform status checks and parameter output:

[0161] Bond weakening state determination and quantification: This embodiment presets a safe threshold for bond weakening degree. This threshold is determined by the hydroxyl density and crystallinity of the coating surface; the lower the hydroxyl density and the worse the crystallinity, the lower the crystallinity. The value increases accordingly.

[0162] like If the bonding stability decreases, the model is determined to have entered a state of decreased bonding stability; at this time, the model outputs the bonding weakening degree. Its value is calculated by the following formula:

[0163] );

[0164] in, The weakening factor is a conversion factor that transforms the theoretical ratio into the actual level of risk. Value and ( The difference between the two values ​​is positively correlated, which quantifies the degree of decay in the stability of the bonded structure.

[0165] Dissociation risk status determination and quantification: This embodiment presets a more stringent dissociation risk threshold. < This threshold, determined through accelerated aging tests, is the critical condition for irreversible dissociation of bound water. If... < If the risk of bound water separation increases, this embodiment is determined to have entered a state of increased risk; at this time, the model outputs a dissociation risk coefficient. Its value is calculated by the following formula:

[0166] ;

[0167] in, This is the risk coefficient, whose value is determined using historical dissociation data; Value and ( The difference is positively correlated and used to warn of the risk level of bound water chemically detaching from the coating surface.

[0168] Steady state confirmation: If ≥ If the water-bound state is stable, the model outputs stable parameters that represent normal behavior.

[0169] Through the above quantification process, the chemical stable state model accurately transforms the coupled characteristic parameters into evaluation indicators with clear physical meaning, namely, the degree of bond weakening. With dissociation risk coefficient .

[0170] Bond weakening degree quantified by chemical stability model With dissociation risk coefficient The process involves determining anomalies in the bound water state; this determination is achieved through a dual threshold comparison mechanism.

[0171] Bond anomaly detection: Determine the bond weakening degree With the preset bond weakening safety threshold A comparison was performed; this threshold was determined using a chemical stability model of the coating, and is a function of the hydroxyl density and crystallinity of the coating surface, specifically:

[0172] ;

[0173] in, The chemical stability coefficient is determined by calibrating the intrinsic bonding energy and macroscopic durability test results of the coating material system. This function indicates that the bonding stability of the coating is jointly determined by its hydroxyl density and crystallinity; the higher the product of the two, the stronger the intrinsic bonding ability of the coating, and the higher its allowable safe threshold for bond weakening.

[0174] when At that time, it was determined that the coating had an abnormality of unstable bonding of bound water.

[0175] Dissociation anomaly determination: The dissociation risk coefficient is used to determine the dissociation risk factor. With respect to the preset dissociation risk threshold Perform a comparison; this threshold Accelerated aging tests simulating actual service environments were conducted to statistically determine the critical conditions for irreversible dissociation of bound water; when At that time, it was determined that the coating had an abnormality of excessive dissociation of bound water.

[0176] This parallel decision-making process enables accurate identification and classification of abnormal chemical states of the coating's bound water; the resulting bond weakening degree... With dissociation risk coefficient This will serve as a core evaluation parameter, directly used in subsequent assessments of the risk of coating performance degradation caused by water treatment processes, and will generate corresponding protective process parameters.

[0177] The specific steps for assessing the risk of coating performance degradation due to the combined water treatment process, and accordingly generating combined water treatment process parameters to prevent coating performance degradation, include:

[0178] Surface chemical bond stability analysis aims to determine the critical humidity boundary for maintaining the chemical bond stability of the coating. This embodiment establishes a surface hydroxyl-bond stability correlation model based on risk state mapping. This model uses the bond weakening degree W as the core input to quantify the sensitivity of bond stability decay to process conditions. Its core relationship is as follows:

[0179] ;

[0180] in, The current dissociation energy barrier characterizes the energy barrier that bound water molecules need to overcome to detach from the active sites on the coating surface under the current weakened bonding state of the coating. The intrinsic dissociation barrier under ideal lattice conditions; Surface hydroxyl density; The hydroxyl group synergistic effect coefficient; This is the stability reference constant; For bond weakening degree; The model is a sensitivity coefficient for weakening; it quantifies the decay law of chemical bonding stability as environmental conditions change by characterizing the competition mechanism between hydroxyl density and bonding weakening degree.

[0181] This equation quantifies the critical dissociation barrier. intrinsic bonding energy Hydroxyl density Correlation of bond weakening The maximum allowable humidity fluctuation range can be obtained by solving in reverse.

[0182] Crystal structure stability analysis: This step aims to determine the safe temperature rise boundary to prevent excessive dissociation of bound water due to thermal disturbance. This embodiment constructs a crystallinity-thermal stability correlation model based on crystal field theory, establishes a quantitative relationship between coating crystallinity and the activation energy of bound water dissociation, and assigns a dissociation risk coefficient... As a key input, the impact of lattice defects on the stability of bound water is evaluated. By analyzing the supporting effect of crystal structure integrity on the hydrogen bond network, a functional relationship between crystallinity and dissociation energy barrier is established, with the core equation being:

[0183] ;

[0184] in: is the rate constant for the dissociation reaction of bound water; Pre-exponential factors; The initial dissociation activation energy when unaffected by water accumulation; The coupling coefficient is used to quantify the risk of local enrichment. The degree to which the activation energy is weakened; This is the generalized gas constant applicable to this dissociation reaction; Let be the absolute temperature of the process. This equation introduces a risk factor. By dynamically modifying the activation energy, the intrinsic relationship between crystallinity degradation and accelerated bound water dissociation rate was quantitatively described.

[0185] This equation introduces a risk coefficient. The activation energy was dynamically corrected, and the intrinsic relationship between crystallinity degradation and the accelerated dissociation rate of bound water was quantitatively described. The maximum temperature rise rate can be solved by combining the safe rate threshold.

[0186] Interfacial thermo-chemical compatibility analysis aims to determine a phased insulation strategy to ensure the stability of the chemical structure at the substrate-coating interface. This embodiment constructs an interfacial bonding stability model based on stress-assisted dissociation theory. This model couples the mechanical effect of interfacial thermal stress on chemical bonds with the chemical instability of bond weakening to quantify the risk of instability of water bound to the interface. Its core equation is:

[0187] ;

[0188] in: Let be the apparent dissociation reaction rate constant of interfacial bound water; It is the pre-exponential factor for interfacial reactions; It is the intrinsic dissociation activation energy under stress-free and bond-stable conditions; This is the stress coupling coefficient, used to quantify interfacial thermal stress. The weakening effect on the dissociation activation energy; The chemically weakening coupling coefficient is used to quantify the degree of bond weakening. The weakening effect on the dissociation activation energy; Boltzmann's constant; This refers to absolute temperature.

[0189] Based on this model, by setting the maximum allowable interface dissociation rate threshold, the staged holding time parameter necessary to ensure the stability of the interface chemical structure can be determined by inverse solution.

[0190] In the process parameter integration and optimization stage, a multi-parameter collaborative optimization model is established to integrate key parameters such as humidity fluctuation range, temperature rise rate threshold, and temperature control range, so as to minimize the risk of performance degradation while meeting all constraints.

[0191] Based on chemical sensitivity analysis and multi-objective optimization algorithms, a complete process scheme including curing curves, temperature programs, and humidity control strategies is constructed, and a process parameter file with clear setpoints, control accuracy, and anomaly handling strategies is output.

[0192] Please see Figure 4 , Figure 4 This is a schematic diagram illustrating the structural analysis of the impact of the water treatment process provided in this application on the integrity of the coating. This embodiment demonstrates the analysis of coating integrity using adapted process parameters for free water and bound water, specifically including:

[0193] The steps for analyzing the impact of water treatment processes on coating integrity, combining the treatment process parameters for both free and bound water, include:

[0194] The impact of water treatment process parameters on coating integrity was analyzed to examine the effects of water treatment processes on free and bound water. This was achieved by establishing a dual-channel risk assessment mechanism, the core of which lies in using precise mathematical models to quantify the two types of risks in parallel.

[0195] Structural damage risk value The calculation is performed using the following comprehensive model:

[0196] ;

[0197] in, and These represent the distribution dispersion and local enrichment risk coefficient output by the free water analysis module, respectively. The safety threshold for the distribution dispersion. This represents the safety threshold for local enrichment risk. Induced stress refers to the localized stress that is generated and amplified at microscopic defects inside the coating due to the combined effects of moisture and process thermal stress. This represents the critical failure stress of the coating. The normalized weighting coefficients for structural damage risk values ​​are determined through sensitivity analysis of coating microstructure parameters. This model quantifies the comprehensive risk of structural failures such as swelling deformation, interface peeling, or microcracks in the coating under current process parameters.

[0198] Performance degradation risk value The calculation is performed using the following comprehensive model:

[0199] ;

[0200] in, and These are the bonding weakening degree and dissociation risk coefficient output by the water analysis module, respectively. As a safety threshold for bond weakening, To dissociate the risk safety threshold; This refers to the amount of energy reduction in the activation energy of bound water dissociation. This is the initial activation energy; The normalized weighting coefficients for the performance degradation risk value are determined through sensitivity analysis of the coating's chemical properties; this model quantifies the comprehensive risk of coating performance degradation due to chemical bond breakage under current process parameters.

[0201] A systematic experimental design approach was adopted, and multiple process combinations were formed by adjusting four key process parameters: drying temperature, ventilation rate, curing humidity, and heating rate. Each set of parameters was input into a risk assessment system to obtain corresponding structural integrity risk and chemical performance risk data. Based on these data, the correspondence between process parameters and risk levels was established, and a visualized risk response map was generated.

[0202] This graph visually illustrates the changing patterns of the two types of risks under different process conditions, and can accurately identify the optimal process range that keeps both structural and performance risks at a low level.

[0203] Please see Figure 5 , Figure 5 This is a schematic diagram of the balanced process scheme for generating free water and bound water treatment provided in this application embodiment; this embodiment demonstrates the generation of a balanced process scheme using a comprehensive risk analysis of the coating, specifically including:

[0204] The balanced process scheme is generated by establishing a dynamic control mechanism based on real-time risk status. This mechanism divides the entire process into three adaptive stages with distinct technical characteristics based on the real-time proportional relationship and absolute magnitude of the structural damage risk value and the performance degradation risk value.

[0205] When the risk of structural damage is significantly higher than the risk of performance degradation and exceeds the safety threshold, the system enters the main free water removal stage. In this stage, an enhanced mass transfer mechanism is adopted to establish an efficient moisture discharge channel by increasing the drying temperature and ventilation rate. At the same time, a piecewise linear temperature rise curve and a controlled humidity reduction strategy are established to maximize the moisture migration efficiency while ensuring structural safety.

[0206] When both types of risk values ​​are within the safe threshold and their proportions are balanced, the system switches to the equilibrium transition stage. In this stage, a dual-risk collaborative optimization strategy is adopted to achieve the best balance between structural integrity and chemical stability through dynamic weight adjustment, maintain the constant temperature operating range and coordinate with balanced ventilation to establish a stable humidity control window, and provide a smooth transition for process conversion.

[0207] When the risk of performance degradation significantly outweighs the risk of structural damage, the system enters the performance stabilization stage. This stage adopts a "low temperature - gradual change - precise control" process route, implements a gradual heating program and is combined with a narrow humidity control range, and sets staged lattice holding time to maximize the protection of the bound water bonded structure, suppress excessive dissociation of bound water, and promote the stable reconstruction of the coating's chemical structure.

[0208] Ultimately, by integrating the optimal parameter combinations of the three stages, a complete balanced process scheme is formed, including segmented temperature control curves, dynamic ventilation strategies, progressive humidity control curves, and staged heat preservation times, to achieve synergistic protection of the coating structure integrity and chemical stability throughout the entire process.

[0209] Please see Figure 6 , Figure 6 This is a schematic diagram of an automated magnesium oxide coating analysis system provided in an embodiment of this application. The automated magnesium oxide coating analysis system includes:

[0210] The data acquisition and feature construction module 210 is used to acquire the attribute data, infrared spectral data and environmental temperature and humidity data of the magnesium oxide coating, and construct the coating attribute features, infrared spectral feature vectors of free water and bound water and environmental temperature and humidity feature set through parsing and processing.

[0211] The free water analysis module 220 is used to perform abnormal analysis of the free water state of the coating based on the free water infrared spectral feature vector and the environmental temperature and humidity feature set, and to generate free water treatment process parameters to suppress coating structural damage by combining the coating property features.

[0212] The bound water analysis module 230 is used to perform anomaly analysis of the bound water state of the coating based on the infrared spectral feature vector of bound water and the set of environmental temperature and humidity features, and to generate bound water treatment process parameters to prevent coating performance degradation based on the coating property features.

[0213] The balanced process analysis module 240 is used to analyze the impact of water treatment process parameters on the integrity of the coating on the treatment process parameters of free water and bound water, and to generate a balanced process scheme for the treatment process of free water and bound water by coordinating the process requirements of coating structural integrity and chemical stability.

[0214] The coordinated control execution module 250 is used to control the execution process of the free water and bound water treatment process based on the balanced process scheme.

[0215] The parameters and steps for implementing the corresponding functions of each unit module in the automated magnesium oxide coating analysis system of this application can be referred to the parameters and steps in the embodiments of the automated magnesium oxide coating analysis method above, and will not be repeated here.

[0216] Please see Figure 7 The present invention also provides an electronic device 300, including a memory 310, a processor 320, and a communication bus 330; the memory 310 and the processor 320 are connected via the communication bus 330. The memory 310 stores an automated magnesium oxide coating analysis method as provided in the above embodiments, which can be loaded and executed by the processor 320.

[0217] The memory 310 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 310 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing an automated magnesium oxide coating analysis method provided in the above embodiments, etc. The data storage area may store data involved in the automated magnesium oxide coating analysis method provided in the above embodiments, etc.

[0218] Processor 320 may include one or more processing cores. Processor 320 executes instructions, programs, code sets, or instruction sets stored in memory 310, and calls data stored in memory 310 to perform various functions and process data as described in this application. Processor 320 may be at least one of the following: Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), Controller, Microcontroller, and Microprocessor. It is understood that, for different devices, the electronic devices used to implement the functions of processor 320 may also be other types, and this application embodiment does not specifically limit the specific devices used.

[0219] The communication bus 330 may include a path for transmitting information between the aforementioned components. The communication bus 330 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 330 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 The symbol is represented by a single double arrow, but this does not mean that there is only one bus or one type of bus.

[0220] This application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as described in the above embodiments, an automated magnesium oxide coating analysis method.

[0221] In this embodiment, a computer-readable storage medium can be a tangible device that holds and stores instructions used by an instruction execution device. The computer-readable storage medium can be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, the computer-readable storage medium can be a portable computer disk, a hard disk, a USB flash drive, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical encoding device, or any combination thereof.

[0222] The terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0223] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing application concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions claimed in this application.

Claims

1. An automated magnesium oxide coating analysis method characterized by, The method comprises the following steps: S1: Obtain magnesium oxide coating properties, infrared spectrum data and environmental temperature and humidity data, and perform analysis processing to construct coating property characteristics, infrared spectrum characteristic vectors of free water and bound water, and environmental temperature and humidity characteristic sets; S2: Perform coating free water state anomaly analysis on the free water infrared spectrum characteristic vector and the environmental temperature and humidity characteristic set; based on the coating free water anomaly analysis result and the coating property characteristics, evaluate the coating morphology damage risk caused by the free water treatment process, and generate free water treatment process parameters for inhibiting coating structure damage accordingly; S3: Perform coating bound water state anomaly analysis on the bound water infrared spectrum characteristic vector and the environmental temperature and humidity characteristic set; based on the coating bound water anomaly analysis result and the coating property characteristics, evaluate the coating performance damage risk caused by the bound water treatment process, and generate bound water treatment process parameters for preventing coating performance degradation accordingly; S4: Analyze the influence of the free water and bound water treatment process parameters on the coating integrity, and generate a balanced process scheme for the free water and bound water treatment processes by coordinating the process requirements of coating structure integrity and chemical stability; S5: Based on the balanced process scheme, coordinate and control the free water and bound water treatment processes.

2. The automated magnesium oxide coating analysis method of claim 1, wherein, Obtain magnesium oxide coating properties, infrared spectrum data and environmental temperature and humidity data, and perform analysis processing to construct coating property characteristics, infrared spectrum characteristic vectors of free water and bound water, and environmental temperature and humidity characteristic sets, which comprise: The coating property characteristics are composed of basic parameters and microstructure parameters; the basic parameters include coating thickness and substrate type; the microstructure parameters include magnesium oxide particle average particle size, thermal expansion coefficient of the substrate and the coating, elastic modulus of the substrate and the coating, porosity and pore size distribution of the coating, crystallinity of the coating, and hydroxyl density on the surface of the coating; The infrared spectrum characteristic vectors are composed of characteristic peak core parameters extracted from free water and bound water characteristic spectral intervals, wherein the free water infrared spectrum characteristic vector contains free water characteristic peak absorbance and half-peak width parameters, and the bound water infrared spectrum characteristic vector contains bound water characteristic peak absorbance and peak shift amount parameters; The environmental temperature and humidity characteristic set is calculated based on the time series data of the environment where the coating is located, which is collected by a temperature and humidity sensing device in real time, and specifically includes temperature gradient data, humidity change rate data, absolute humidity and dew point temperature data.

3. The automated magnesium oxide coating analysis method of claim 2, wherein, In step S2, the coating free water state anomaly analysis is performed, and the specific steps include: S210: Spatially and temporally correlate and couple the free water characteristic peak absorbance and half-peak width parameters in the free water infrared spectrum characteristic vector with the temperature gradient data and humidity change rate data in the environmental temperature and humidity characteristic set, and input the data after spatial and temporal correlation and coupling as input data into a dynamic migration model to calculate the distribution dispersion degree and local enrichment risk coefficient of the free water; S220: The distribution dispersion and local enrichment risk coefficient are compared with the preset distribution dispersion safety threshold and local enrichment risk threshold respectively; if the distribution dispersion exceeds the distribution dispersion safety threshold, it is determined that the free water distribution is abnormal, otherwise it is determined that the free water distribution state is normal; if the local enrichment risk coefficient exceeds the local enrichment risk threshold, it is determined that the free water is locally enriched, otherwise it is determined that the free water distribution concentration is normal.

4. The automated magnesium oxide coating analysis method of claim 3, wherein, In step S2, based on the coating free water abnormal analysis result and the coating attribute feature, the risk of coating morphology damage caused by free water treatment process is evaluated, and the free water treatment process parameters for inhibiting coating structure damage are generated accordingly. The specific steps include: S230: Establish a pore strength function model of coating porosity, pore size distribution parameters and coating pore anti-expansion strength, which is used to characterize the influence law of pore structure on water capillary force; combined with the pore strength function model and the free water distribution dispersion, the maximum allowed humidity change rate to prevent swelling deformation is determined; S240: Establish a particle size-crack correlation model of magnesium oxide particle average particle size and crack propagation driving force, which is used to reflect the influence mechanism of particle size on the stress concentration in the coating; combined with the particle size-crack correlation model and the local enrichment risk coefficient, the temperature gradient safety threshold for inhibiting crack propagation is determined; S250: Based on the coating thickness, the elastic modulus parameters of the substrate and the coating, and the difference of the thermal expansion coefficients of the two, the interface thermal stress distribution of the substrate and the coating is calculated, which is used to characterize the deformation coordination characteristics of the substrate and the coating in the heat treatment process; combined with the interface thermal stress distribution and the coating crystallinity, the drying temperature control interval and the ventilation rate adjustment range for inhibiting structure damage are determined; S260: The maximum allowed humidity change rate, the temperature gradient safety threshold, the drying temperature control interval and the ventilation rate adjustment range are integrated to generate the free water treatment process parameters for inhibiting coating structure damage.

5. The automated magnesium oxide coating analysis method of claim 3, wherein, In step S3, the coating bound water state abnormality analysis is performed, and the specific steps include: S310: The bound water feature peak absorbance and peak shift parameter in the bound water infrared spectrum feature vector are coupled with the absolute humidity and dew point temperature data in the environmental temperature and humidity feature set in the chemical potential field, and the data after the chemical potential field coupling is input into the chemical stability model to calculate the bond weakening degree and dissociation risk coefficient; S320: The bond weakening degree and dissociation risk coefficient are compared with the preset bond weakening degree safety threshold and dissociation risk threshold respectively; if the bond weakening degree exceeds the bond weakening degree safety threshold, it is determined that the bound water bond is unstable, otherwise it is determined that the bond state is stable; if the dissociation risk coefficient exceeds the dissociation risk threshold, it is determined that the bound water is excessively dissociated, otherwise it is determined that the dissociation state is normal.

6. The automated magnesium oxide coating analysis method of claim 5, wherein, Based on the coating bound water abnormal analysis result and the coating attribute feature, the risk of coating performance damage caused by bound water treatment process is evaluated, and the bound water treatment process parameters for preventing coating performance degradation are generated accordingly. The specific steps include: S330: Establishing a surface hydroxyl-bonding stability correlation model of the coating surface hydroxyl density and the bonding water bonding stability, for characterizing the influence law of the number of active sites per unit area on the chemical bonding stability; combining the surface hydroxyl-bonding stability correlation model with the bonding weakening degree, determining the solidification atmosphere humidity control range required to maintain the bonding stability; S340: Establishing a crystallinity-thermal stability correlation model of the coating crystallinity parameter and the lattice thermal stability, for reflecting the action mechanism of the crystal structure integrity on the thermal disturbance resistance; combining the crystallinity-thermal stability correlation model with the dissociation risk coefficient, determining the maximum heating rate threshold for preventing excessive dissociation; S350: Based on the difference between the thermal expansion coefficients of the substrate and the coating, the elastic modulus, and the coating thickness parameters, calculating the thermal stress distribution of the coating and substrate interface, for characterizing the deformation coordination characteristics of heterogeneous materials in the temperature field; combining the interface thermal stress distribution with the bonding weakening degree, determining the phased holding time parameters to ensure the stability of the interface chemical structure; S360: Integrating the solidification atmosphere humidity control range, the maximum heating rate threshold, and the phased holding time parameters, generating the combined water treatment process parameters to prevent performance degradation of the coating.

7. The automated magnesium oxide coating analysis method of claim 6, wherein, In step S4, the influence of the water treatment process parameters on the coating integrity is analyzed, specifically including: S410: Establishing a coating comprehensive loss risk quantification model, taking the process parameters obtained in S2 and S3 as input, and calculating the structure damage and performance degradation risks in parallel, generating two independent risk quantification values of structure damage and performance degradation: based on the free water distribution dispersion degree and the local enrichment risk coefficient, combining the coating microstructure parameters, establishing the structure damage risk value; based on the bonding weakening degree and the dissociation risk coefficient, combining the coating chemical property parameters, establishing the performance degradation risk value; S420: Based on the structure damage risk value and the performance degradation risk value, using experimental design method to change the parameter combinations of drying temperature, ventilation rate, solidification humidity and heating rate, calculating the risk response values under each parameter combination through the risk quantification model, establishing the quantitative mapping relationship between process parameters and double risks, forming the process parameter-double risk response relationship map, for characterizing the influence law of process parameter changes on structure integrity and chemical stability, and reflecting the coupling effect between each process parameter.

8. The automated magnesium oxide coating analysis method of claim 7, wherein, In step S4, the process requirements of coordinating the structure integrity and chemical stability of the coating are generated, and the balance process scheme of the free water and combined water treatment process is generated, specifically including: S430: Based on the real-time proportional relationship and absolute size of the coating structure damage risk value and the performance degradation risk value, the coating moisture treatment process is dynamically divided into three process stages: when the ratio of the structure damage risk value to the performance degradation risk value exceeds the structure dominant proportion coefficient and exceeds the structure damage risk safety threshold, the main free water removal stage is entered; when the two risk values are in the preset balance interval and neither exceeds the respective safety threshold, the balance transition stage is entered; when the ratio of the performance degradation risk value to the structure damage risk value exceeds the performance dominant proportion coefficient and exceeds the performance degradation risk safety threshold, the performance stable stage is entered; S440: Based on the identified process stage, a specific optimization model is established for each stage in the process parameter-double risk response relationship graph, and the optimal process parameter combination is solved, and the specific solving process is as follows: In the main free water removal stage, a water removal optimization model is established with the minimization of the structure damage risk value as the objective function and the performance degradation risk value not exceeding the performance degradation warning threshold as the condition, and the macro process parameters including drying temperature, ventilation rate and dehumidification rate are obtained by solving the water removal optimization model; In the balance transition stage, a double balance optimization model is established with the minimization of the weighted sum of the structure damage risk value and the performance degradation risk value as the objective, and the Pareto optimal solution set of the process parameters is obtained by adjusting the weight coefficient to coordinate the descending rate of the two risks; the solution set defines the steady-state process parameters of this stage, including constant temperature holding value, balance ventilation amount and humidity stability range; In the performance stable stage, a performance optimization model is established with the minimization of the performance degradation risk value as the objective function and the structure damage risk value not exceeding the structure damage safety threshold as the constraint condition, and the fine process parameters including temperature rising rate, solidification humidity window and stage holding time are obtained by solving the performance optimization model; S450: The optimal process parameter combination is integrated as the balance process scheme of the free water and bound water treatment process.

9. The automated magnesium oxide coating analysis method of claim 8, wherein, In step S5, the treatment process of free water and bound water is synergistically controlled, and the specific steps include: S510: Extract the balance process scheme of the free water and bound water treatment process; S520: Based on the balance process scheme of the free water and bound water treatment process, the treatment process parameters of free water and bound water are synergistically controlled.

10. An automated magnesium oxide coating analysis system, characterized by, The system comprises: A data acquisition and feature construction module for acquiring attribute data, infrared spectrum data and environmental temperature and humidity data of the magnesium oxide coating, and constructing coating attribute features, free water and bound water infrared spectrum feature vectors and environmental temperature and humidity feature sets through analysis and processing; A free water analysis module for analyzing the free water state anomaly of the coating based on the free water infrared spectrum feature vector and the environmental temperature and humidity feature set, and generating free water treatment process parameters for inhibiting coating structure damage in combination with the coating attribute features; A bound water analysis module for analyzing the bound water state anomaly of the coating based on the bound water infrared spectrum feature vector and the environmental temperature and humidity feature set, and generating bound water treatment process parameters for preventing coating performance degradation in combination with the coating attribute features; A balance process analysis module is configured to analyze the influence of the treatment process parameters of the free water and the bound water on the coating integrity, and to generate a balance process scheme of the free water and the bound water treatment process by coordinating the process requirements of the coating structural integrity and the chemical stability; A synergistic regulation execution module is configured to regulate the execution process of the free water and the bound water treatment process based on the balance process scheme.

Images