Construction engineering material detection method and system

Abstract

The invention relates to the technical field of material detection, in particular to a building engineering material detection method and system. The method comprises the following steps: performing multi-area scanning on a building decoration wall coating through an ultrasonic scanner to obtain a wall coating sound wave data set, identifying non-uniform distribution of coating texture, then calculating density distribution difference of an inner coating and an outer coating between layers according to the coating texture data, and further performing quantitative simulation on water resistance permeation loss to obtain the water resistance permeation loss of the building decoration wall coating. The method comprises the following steps: acquiring water-resistant permeation loss data, then inferring a permeation mechanism periodic aging process of the coating on the basis of the water-resistant permeation loss data, detecting the tolerance performance of a coating material in combination with permeation mechanism aging data, acquiring material tolerance performance data, and comprehensively evaluating the quality and durability of the coating. According to the invention, the detection technology is optimized, so that the detection technology is more perfect.

Description

Technical Field

[0001] The present invention relates to the technical field of material detection, and in particular to a construction engineering material detection method and system. Background Art

[0002] With the development of construction projects, the quality and performance requirements of building materials are getting higher and higher, especially in coating materials. Durability and long-term performance have become one of the important criteria for evaluating building quality. As an indispensable part of construction projects, coatings are widely used in walls, floors, roofs and other parts. They not only play a decorative role, but also play a key role in waterproofing, anti-corrosion, and anti-aging. Therefore, how to scientifically and accurately detect the quality and performance of coating materials, especially their water resistance, durability and aging, has become an important topic in the quality control of construction projects. However, a traditional construction material testing method has the problem of inaccurate analysis of the waterproof performance of coatings, resulting in large errors in the detection of coating material aging. Summary of the invention

[0003] Based on this, it is necessary to provide a construction material detection method and system to solve at least one of the above technical problems.

[0004] To achieve the above object, a construction material detection method is provided, the method comprising the following steps: Step S1: Scanning a multi-region wall coating of a building decoration by an ultrasonic scanner to obtain a wall coating acoustic wave data set; identifying the coating texture non-uniform distribution based on the wall coating acoustic wave data set to obtain coating texture non-uniform distribution data; Step S2: Calculate the density distribution difference between inner and outer coatings according to the coating texture non-uniformity distribution data to obtain the density distribution difference data between inner and outer coatings; perform quantitative simulation of water resistance penetration loss according to the interlayer adhesion density difference data to obtain the quantitative data of water resistance penetration loss; Step S3: Perform periodic aging inference on the water resistance penetration loss quantification data to obtain periodic aging data on the penetration mechanism; perform coating material tolerance performance testing based on the periodic aging data on the penetration mechanism to obtain coating material tolerance performance data.

[0005] Preferably, step S1 comprises the following steps: Step S11: Scanning the wall coating of the building decoration in multiple regions by using an ultrasonic scanner to obtain a wall coating acoustic wave data set; Step S12: performing noise reduction processing on the wall coating sound wave dataset to obtain a wall coating noise reduction sound wave dataset; Step S13: performing microscopic morphology analysis of the inside and outside of the coating based on the wall coating noise reduction wave data set to obtain the inside and outside morphology data of the coating; Step S14: Identify the coating texture non-uniformity distribution based on the coating internal and external appearance structure data to obtain the coating texture non-uniformity distribution data.

[0006] Preferably, step S2 comprises the following steps: Step S21: Acquire coating raw material property data; perform coating inner and outer layer structure analysis on the coating inner and outer surface structure data according to the wall coating acoustic wave data set to obtain coating inner and outer layer structure data; Step S22: Calculate the density distribution difference between the inner and outer coatings according to the coating texture non-uniformity distribution data and the wall coating acoustic wave data set, and obtain the density distribution difference data between the inner and outer coatings; Step S23: performing interlayer adhesion density difference analysis based on the inner and outer coating density distribution difference data and the inner and outer layer structure data of the coating to obtain interlayer adhesion density difference data; Step S24: performing a sunlight crack depth extension prediction simulation on the interlayer adhesion density difference data to obtain crack depth extension prediction data; Step S25: Perform a quantitative simulation of water resistance penetration loss based on the interlayer adhesion density difference data, crack depth extension prediction data and coating material property data to obtain water resistance penetration loss quantitative data.

[0007] Preferably, step S24 comprises the following steps: Step S241: Acquire all-weather sunshine data; evaluate the ultraviolet thermal radiation intensity of the all-weather sunshine data to obtain ultraviolet thermal radiation intensity data; Step S242: Analyze the critical range of heat decomposition resistance of the coating raw material property data to obtain the critical range of heat decomposition resistance of the raw material; Step S243: fitting the nonlinear relationship of thermal expansion of the interlayer adhesion density difference data and the critical range of heat-resistant decomposition of the raw material according to the ultraviolet thermal radiation intensity data to obtain the nonlinear relationship of thermal expansion of the coating layer; Step S244: performing thermal expansion stress distribution difference decomposition processing based on the nonlinear relationship of thermal expansion between coating layers and the interlayer adhesion density difference data to obtain thermal expansion stress distribution difference data; Step S245: Perform a sunlight crack depth propagation prediction simulation based on the nonlinear relationship of thermal expansion between coating layers and the thermal expansion stress distribution difference data to obtain crack depth propagation prediction data.

[0008] Preferably, step S25 comprises the following steps: Step S251: performing an expansion morphology trend analysis on the crack depth extension prediction data to obtain crack extension morphology trend data; estimating the vertical depth variance between the trend differences of the crack depth extension prediction data based on the crack extension morphology trend data to obtain the vertical depth variance of the trend difference; Step S252: performing interlayer adhesion density weakening estimation on the interlayer adhesion density difference data according to the vertical depth variance of the strike difference to obtain interlayer adhesion density weakening data; Step S253: quantifying the coating density structure loss of the coating raw material property data based on the vertical depth variance of the strike difference and the interlayer adhesion density weakening data to obtain the coating density structure loss data; Step S254: estimating the water vapor penetration barrier loss strength according to the vertical depth variance of the strike difference, the interlayer adhesion density weakening data and the coating density structure loss data, and obtaining the water vapor penetration barrier loss strength data; Step S255: Perform a quantitative simulation of water penetration resistance loss based on the water vapor penetration barrier loss strength data to obtain quantitative data of water penetration resistance loss.

[0009] Preferably, step S3 comprises the following steps: Step S31: normalizing the quantified data of water resistance penetration loss to obtain normalized data of water resistance penetration loss; Step S32: performing permeation mechanism periodic aging inference on the normalized data of water resistance permeation loss to obtain permeation mechanism periodic aging data; Step S33: Perform coating material tolerance performance testing based on the penetration mechanism periodic aging data to obtain coating material tolerance performance data.

[0010] Preferably, step S32 includes the following steps: Step S321: performing a permeation time series progressive aggravation evaluation on the normalized water resistance permeation loss data to obtain permeation time series progressive aggravation data; Step S322: performing iterative fitting on the penetration time series progressive intensification data to obtain penetration time series intensification iterative data; Step S323: performing nonlinear regression analysis on the infiltration time series intensified iteration data to obtain infiltration iterative intensified regression data; Step S324: inferring the periodic aging of the permeability mechanism according to the permeability iterative aggravation regression data to obtain the periodic aging data of the permeability mechanism.

[0011] Preferably, for executing the construction material detection method as described above, the construction material detection system comprises: The texture non-uniform distribution recognition module is used to perform multi-area scanning of the building decoration wall coating through an ultrasonic scanner to obtain a wall coating acoustic wave data set; based on the wall coating acoustic wave data set, the coating texture non-uniform distribution is recognized to obtain coating texture non-uniform distribution data; The water resistance penetration loss quantification module is used to calculate the density distribution difference between the inner and outer coatings between the layers according to the coating texture non-uniformity distribution data, and obtain the density distribution difference data of the inner and outer coatings; and to perform a quantitative simulation of the water resistance penetration loss according to the interlayer adhesion density difference data, and obtain the water resistance penetration loss quantification data; The tolerance performance detection module is used to infer the periodic aging of the penetration mechanism based on the quantitative data of water resistance penetration loss to obtain the periodic aging data of the penetration mechanism; based on the periodic aging data of the penetration mechanism, the tolerance performance of the coating material is detected to obtain the tolerance performance data of the coating material.

[0012] The beneficial effect of the present invention is that by performing multi-region scanning on the wall coating of building decoration through an ultrasonic scanner, an acoustic wave data set of the wall coating can be obtained. This process can accurately reflect the texture non-uniformity distribution of the coating and provide detailed basic data for subsequent analysis. This multi-region scanning technology can identify the differences in texture and thickness of each area of ​​the coating, thereby providing a scientific basis for the repair and maintenance of the building coating, especially when detecting coating aging and potential problems, it helps to find coating defects early and improve maintenance efficiency and quality. After obtaining the data on the non-uniformity distribution of the coating texture, the density distribution difference between the inner and outer coatings between the layers is further calculated, and the difference in density between the inner and outer coatings can be clearly distinguished. This calculation is crucial for evaluating the overall structure and layer stability of the coating, especially in terms of waterproofing and heat insulation. Through density difference analysis, the adhesion and density differences of the coating can be quantified, and the simulation of water resistance penetration loss can be further guided, thereby providing important data support for the water tightness and anti-seepage performance of the building, ensuring the durability and service life of the coating. The analysis of the difference in interlayer adhesion density in the step provides accurate basic data for the quantitative simulation of water resistance penetration loss. Through this simulation, the water resistance performance of the coating in different environments can be quantified, especially the protective effect under special conditions such as moisture or heavy rain. This process provides quantitative performance data for coating design and material selection, and can predict and optimize the use effect of building coatings. Through scientific simulation, the shortcomings of previous empirical judgments are avoided, unnecessary waste of resources is reduced, and the safety and comfort of buildings are improved. Finally, based on the quantitative data of water resistance penetration loss, the periodic aging inference of the penetration mechanism is carried out to study the performance degradation law of the coating in long-term use. By systematically inferring the aging process of the coating, the durability of the coating material under different service years and climatic conditions can be predicted. This aging inference can not only guide the selection and maintenance cycle of coating materials, but also provide data support for the research and development of coating materials, improve the overall performance of coating materials, and ensure that the building maintains good protective performance for a long time. Therefore, the present invention is an optimization treatment of a traditional construction material testing method, which solves the problem that the traditional construction material testing method has inaccurate analysis of the coating waterproof performance, thereby causing large errors in the detection of coating material aging, improves the accuracy of the coating waterproof performance analysis, and reduces the error in the detection of coating material aging. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A schematic diagram of the steps of a construction material testing method; Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart; Figure 3 for Figure 1Detailed implementation steps of step S3 in FIG. DETAILED DESCRIPTION

[0014] See also Figures 1 to 3 , a construction material detection method, the method comprising the following steps: Step S1: Scanning a multi-region wall coating of a building decoration by an ultrasonic scanner to obtain a wall coating acoustic wave data set; identifying the coating texture non-uniform distribution based on the wall coating acoustic wave data set to obtain coating texture non-uniform distribution data; Step S2: Calculate the density distribution difference between inner and outer coatings according to the coating texture non-uniformity distribution data to obtain the density distribution difference data between inner and outer coatings; perform quantitative simulation of water resistance penetration loss according to the interlayer adhesion density difference data to obtain the quantitative data of water resistance penetration loss; Step S3: Perform periodic aging inference on the water resistance penetration loss quantification data to obtain periodic aging data on the penetration mechanism; perform coating material tolerance performance testing based on the periodic aging data on the penetration mechanism to obtain coating material tolerance performance data.

[0015] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a construction material detection method of the present invention. In this example, the construction material detection method includes the following steps: Step S1: Scanning a multi-region wall coating of a building decoration by an ultrasonic scanner to obtain a wall coating acoustic wave data set; identifying the coating texture non-uniform distribution based on the wall coating acoustic wave data set to obtain coating texture non-uniform distribution data; In an embodiment of the present invention, when a multi-region scanning is performed on a wall coating of a building decoration by an ultrasonic scanner, the scanner emits an ultrasonic signal at a fixed frequency, so that it penetrates the coating and generates reflections at the interfaces of different materials. By receiving the reflected signal and measuring the time difference of signal propagation and the amplitude attenuation, the structural information inside the coating is obtained. During the scanning process, the frequency of the ultrasonic wave should be controlled between 1MHz and 10MHz to adapt to coating materials of different thicknesses and densities, and to avoid excessive attenuation of high-frequency signals or insufficient resolution of low-frequency signals. By scanning multiple regions, a complete acoustic wave data set of the wall coating is obtained. When the data set is subjected to feature extraction, the wavelet transform method is used to decompose the signal into different frequency bands to identify the texture change characteristics therein, and the threshold-based method is used to remove noise and enhance the effective information of the signal. Subsequently, the texture feature extraction is performed on the de-noised signal, and the gray level co-occurrence matrix analysis method is used to calculate parameters such as energy, contrast, and correlation to quantify the non-uniform distribution characteristics of the coating surface and interior, thereby obtaining the coating texture non-uniform distribution data.

[0016] Step S2: Calculate the density distribution difference between inner and outer coatings according to the coating texture non-uniformity distribution data to obtain the density distribution difference data between inner and outer coatings; perform quantitative simulation of water resistance penetration loss according to the interlayer adhesion density difference data to obtain the quantitative data of water resistance penetration loss; In an embodiment of the present invention, based on the obtained coating texture non-uniformity distribution data, a statistical analysis method is used to calculate the density distribution difference between the inner and outer layers of the coating. By measuring the attenuation of ultrasonic signals in different areas and comparing the reference data of the same type of standard materials, the variation range of the coating density is calculated. When calculating the difference in interlayer adhesion density, the echo amplitude comparison analysis method is used to compare the reflectivity of ultrasonic signals at different interfaces, analyze the coating interface bonding, and combine the density distribution data to evaluate the variation trend of the adhesion density. In order to quantify the water resistance penetration loss, based on the adhesion density difference data, the water penetration rate is determined by a penetration experiment, and the corresponding relationship between the penetration depth and time is established. The interpolation fitting is combined with multiple measurement results to obtain the quantitative data of water penetration loss.

[0017] Step S3: Perform periodic aging inference on the water resistance penetration loss quantification data to obtain periodic aging data on the penetration mechanism; perform coating material tolerance performance testing based on the periodic aging data on the penetration mechanism to obtain coating material tolerance performance data.

[0018] In the embodiment of the present invention, for the quantitative data of water resistance penetration loss, based on the data records of long-term exposure environment, the variation trend of penetration amount over time is analyzed, and the aging model of penetration mechanism is established by time series analysis method. By measuring the change of penetration rate at different time points, the long-term aging effect is predicted by curve fitting method, and the periodic aging data of penetration mechanism is obtained. Combined with the aging data, the tolerance performance of coating material is tested, and the durability of material under different penetration depth conditions is evaluated by material fatigue test method. By applying periodic stress, recording the durability limit value of the material, and analyzing its variation trend, the tolerance performance data of coating material is finally obtained.

[0019] Preferably, step S1 comprises the following steps: Step S11: Scanning the wall coating of the building decoration in multiple regions by using an ultrasonic scanner to obtain a wall coating acoustic wave data set; Step S12: performing noise reduction processing on the wall coating sound wave dataset to obtain a wall coating noise reduction sound wave dataset; Step S13: performing microscopic morphology analysis of the inside and outside of the coating based on the wall coating noise reduction wave data set to obtain the inside and outside morphology data of the coating; Step S14: Identify the coating texture non-uniformity distribution based on the coating internal and external appearance structure data to obtain the coating texture non-uniformity distribution data.

[0020] In the embodiment of the present invention, during the multi-area scanning process of the wall coating of the building decoration, the ultrasonic scanner first needs to set a suitable scanning frequency range so that the ultrasonic wave can effectively penetrate the coating and form a reflection signal at the material interface. In general, the frequency of the ultrasonic probe is selected between 1MHz and 10MHz, where the low frequency is suitable for thicker or denser coatings, and the high frequency is suitable for thinner or finer surface structures. When the probe contacts the wall coating, a coupling agent should be used to fill the gap between the probe and the coating to reduce the energy loss of the sound wave and improve the signal transmission efficiency. The scanning is carried out in a grid-like manner, and a fixed step size (such as 1mm to 5mm) is set to cover the wall surface in turn to ensure data integrity. During the scanning process, after the ultrasonic emission signal enters the coating, it will be reflected when encountering internal defects, interfaces or changes in material density of the coating. The receiving probe captures the reflected signal and records its propagation time, amplitude attenuation and frequency change to generate a wall coating acoustic wave data set. The acquired wall coating acoustic wave data set contains useful signals and environmental noise, and the data needs to be denoised to ensure the accuracy of the signal. The denoising process first performs bandpass filtering on the collected acoustic wave signals, sets the filtering frequency band, and suppresses the noise interference components (such as mechanical vibration, environmental noise, etc.). Subsequently, the wavelet transform method is applied to the filtered signal to decompose it into sub-signals of different frequency bands, and the threshold denoising method is used to remove high-frequency noise interference. After signal reconstruction, the denoised data is analyzed in the time domain and frequency domain, and the power spectrum density of the signal is calculated using Fourier transform to detect whether there is still mutation noise or discrete noise points. If there is still interference signal, the adaptive filtering method is used to further optimize the data. After the denoising process is completed, the wall coating denoised acoustic wave data set is obtained to provide a clear signal input for subsequent analysis. The microscopic morphology structure inside and outside the coating is analyzed using the denoised acoustic wave data set. First, the thickness distribution of the coating is calculated based on the time delay and attenuation of the reflected signal, and the uniformity of the coating thickness is judged by comparing the data of multiple scanning areas. Subsequently, the ultrasonic echo spectrum analysis method is used to analyze the spectral characteristics of the signal and extract the microstructural information of the coating material. If there are holes, cracks or delamination inside the coating, the frequency spectrum of its echo signal will show characteristic distortion, which can be distinguished by comparing with the reference signal of the normal coating. In order to further analyze the bonding of the inner and outer layers of the coating, the ultrasonic phase difference method is used to measure the phase change of the echo signal at different depths, calculate the bonding strength of the coating interface, and obtain the internal and external morphological structure data of the coating. Based on the internal and external morphological structure data of the coating, the non-uniform distribution of the coating texture is identified. First, the texture features of the ultrasonic reflection signals in different scanning areas are extracted, and the grayscale co-occurrence matrix analysis method is used to calculate parameters such as energy, contrast, and correlation, and the coating texture feature map is drawn in two-dimensional space. Subsequently, the edge detection algorithm is used to segment the texture structure on the surface and inside of the coating, and identify local areas of uneven density, microcracks or particle accumulation.If the coating material has uneven particle distribution, the entropy value will increase significantly in the calculation of texture feature parameters, and if there are local cracks on the coating surface, the contrast parameter will fluctuate abnormally. Finally, by comprehensively analyzing the texture parameters, the non-uniform distribution data of the coating texture is obtained, and other physical detection methods can be further combined to verify the true structural characteristics of the non-uniform distribution area.

[0021] Preferably, step S2 comprises the following steps: Step S21: Acquire coating raw material property data; perform coating inner and outer layer structure analysis on the coating inner and outer surface structure data according to the wall coating acoustic wave data set to obtain coating inner and outer layer structure data; Step S22: Calculate the density distribution difference between the inner and outer coatings according to the coating texture non-uniformity distribution data and the wall coating acoustic wave data set, and obtain the density distribution difference data between the inner and outer coatings; Step S23: performing interlayer adhesion density difference analysis based on the inner and outer coating density distribution difference data and the inner and outer layer structure data of the coating to obtain interlayer adhesion density difference data; Step S24: performing a sunlight crack depth extension prediction simulation on the interlayer adhesion density difference data to obtain crack depth extension prediction data; Step S25: Perform a quantitative simulation of water resistance penetration loss based on the interlayer adhesion density difference data, crack depth extension prediction data and coating material property data to obtain water resistance penetration loss quantitative data.

[0022] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S21: Acquire coating raw material property data; perform coating inner and outer layer structure analysis on the coating inner and outer surface structure data according to the wall coating acoustic wave data set to obtain coating inner and outer layer structure data; In the embodiment of the present invention, when obtaining the coating raw material property data, firstly, the raw material samples of the wall coating are collected, and the representative coating area is selected for analysis. Professional equipment such as scanning electron microscope (SEM) is used to collect high-resolution images to observe the microscopic morphology of the coating. At the same time, an X-ray diffraction (XRD) instrument is used to perform qualitative and quantitative analysis on the physical phase of the coating raw material to obtain the mineral composition and relative content of the coating material. Then, the thermal stability of the coating raw material is measured by thermogravimetric analysis (TGA), and thermal performance analysis is performed in combination with differential scanning calorimetry (DSC), so as to obtain the thermal expansion coefficient, melting point and other physical performance data of the coating raw material. These data provide basic data for the subsequent interlayer structure analysis. At the same time, by comparing the raw material characteristics of different coatings, it is possible to In order to obtain the performance and reliability differences of each coating under environmental changes and conduct structural data analysis between the inner and outer layers of the coating, multi-point acoustic wave sensors are installed to conduct acoustic wave propagation tests on the wall coating at different locations to obtain the time and frequency data of acoustic wave propagation. Through these acoustic wave data, the acoustic wave reflection method is used to analyze the interface structure between the inner and outer layers of the coating. Combined with parameters such as the thickness, density and elastic modulus of the coating, the structural distribution of the inner and outer layers of the coating is inferred by using the change in the acoustic wave propagation speed, and then the interlayer structural differences of the coating are obtained. Combined with the texture distribution of the coating, the interface conditions of the inner and outer layers of the coating can be further refined. For example, by comparing the acoustic wave propagation delays in different areas, it is possible to analyze whether there are defects at the interface between the inner and outer layers of the coating, or differences in physical properties due to uneven coating.

[0023] Step S22: Calculate the density distribution difference between the inner and outer coatings according to the coating texture non-uniformity distribution data and the wall coating acoustic wave data set, and obtain the density distribution difference data between the inner and outer coatings; In an embodiment of the present invention, based on the coating texture non-uniformity distribution data and the wall coating acoustic wave data set, the structural data between the inner and outer layers of the coating is analyzed to calculate the density distribution difference of each layer of the coating. First, the wall coating acoustic wave data is subjected to time-frequency analysis to extract the ultrasonic reflection signals at different positions, and the acoustic impedance of each layer of the coating is calculated in combination with the thickness data of each layer of the coating. Subsequently, the density distribution of different regions of the coating is calculated based on the acoustic impedance. If the density of a certain region is significantly lower than that of other regions, it indicates that there are microcracks or pores in the region. In order to further accurately calculate the density distribution difference between the inner and outer coatings between the layers, the chemical composition of the coating surface is determined by X-ray photoelectron spectroscopy analysis to determine whether there is material composition segregation caused by uneven density. Finally, the density variation amplitude between the inner and outer layers of the coating is calculated based on the above experimental data, and the results are stored in the database for subsequent analysis.

[0024] In another embodiment, the density distribution difference between the inner and outer layers of the coating is calculated based on the coating texture non-uniformity distribution data and the wall coating acoustic wave data set. First, the acoustic impedance of different areas of the coating is calculated using the echo intensity and propagation time in the ultrasonic scanning data. The change in acoustic impedance reflects the distribution difference of the coating density. The acoustic impedance calculation is based on the relationship between the material density and the ultrasonic propagation velocity, extracts the signal attenuation rate at different depths, and combines the ultrasonic tomography (UTI) technology to reconstruct the coating density distribution map. The coating is divided into multiple regions using the image segmentation method, and the density mean and standard deviation of each region are calculated to evaluate the uniformity of the density. Combined with X-ray transmission imaging, the density inside the coating is analyzed, and the gray value gradient is used to calculate the change trend of the coating density distribution. Through three-dimensional reconstruction technology, a coating density distribution model is established, the density gradient and change rate between different layers are calculated, and the density distribution difference data of the inner and outer coatings are obtained.

[0025] Step S23: performing interlayer adhesion density difference analysis based on the inner and outer coating density distribution difference data and the inner and outer layer structure data of the coating to obtain interlayer adhesion density difference data; In an embodiment of the present invention, based on the coating density distribution difference data and the inner and outer interlayer structure data of the coating, the interlayer adhesion density is analyzed. First, the hardness and elastic modulus of each layer of the coating are determined by the nanoindentation test method, and the hardness gradient change is analyzed to judge the bonding strength of the coating interface. Subsequently, an interface shear experiment is used to load the coating in different regions with shear stress, and the failure mode of the coating interface is recorded. If brittle fracture occurs at the interface, it indicates that the adhesion density is low. Combined with X-ray tomography technology, the micro cracks inside the coating are three-dimensionally reconstructed, and the relationship between the crack expansion path and the interlayer bonding strength is calculated. Finally, by comprehensive analysis of the experimental data, the interlayer adhesion density difference of the coating is calculated, and the adhesion strength distribution of each region is recorded in the database.

[0026] In another embodiment, based on the difference data of the density distribution of the inner and outer coatings and the data of the structure between the inner and outer layers of the coating, the difference analysis of the interlayer adhesion density is performed. The nanoindentation test technology is used to perform mechanical property tests in the coating area at different depths, measure the hardness and elastic modulus of the coating, and evaluate the difference in mechanical properties inside the coating. The scanning electron microscope (SEM) is combined with the energy spectrum analysis (EDS) to observe the bonding state of the coating interface, analyze the chemical composition distribution at the interface, and determine whether there are interface defects or unevenly distributed adhesives. The ultrasonic shear wave test method is used to measure the shear wave propagation velocity of the coating interface, and calculate the changes in the shear modulus and adhesion strength. Through micro-tensile testing, the adhesion between different layers is measured, and the peeling energy of the interface layer is calculated. Combined with thermomechanical analysis (TMA), the expansion coefficient of the coating at different temperatures is measured, and the influence of temperature on the interlayer adhesion density is analyzed. The finite element analysis method is used to simulate the stress distribution of the coating under the action of external force, identify the weak area of ​​adhesion density, and obtain the difference data of interlayer adhesion density.

[0027] Step S24: performing a sunlight crack depth extension prediction simulation on the interlayer adhesion density difference data to obtain crack depth extension prediction data; In an embodiment of the present invention, the depth expansion of sunlight cracks is predicted based on the interlayer adhesion density difference data. First, the climate data of the building area is obtained, including the sunlight intensity, temperature variation range and humidity fluctuation, and the temperature stress distribution of the coating is calculated in combination with the thermal expansion coefficient of the coating. Subsequently, the thermal stress model of the coating is established using the finite element analysis method, and the temperature load under actual climatic conditions is applied to simulate the expansion trend of cracks under long-term sunlight. Combined with the laboratory ultraviolet aging test data, the effect of ultraviolet rays on the degradation rate of the coating surface is analyzed, and the aging parameters in the crack extension model are adjusted. Finally, the crack depth change curve of the coating is obtained by simulation calculation, and the periodic change law of crack extension is recorded for subsequent analysis.

[0028] In another embodiment, the interlayer adhesion density difference data is used to predict the depth extension of sunlight cracks. First, the annual sunshine data of the area where the building is located is obtained, including parameters such as solar radiation intensity, ultraviolet index, and daily maximum and minimum temperatures. The ultraviolet thermal radiation intensity assessment model is used to calculate the thermal load changes of the coating in different time periods, and the degradation trend of the coating under long-term sunlight is analyzed in combination with the critical interval data of the thermal decomposition of the coating. The thermal expansion nonlinear relationship fitting method is used to analyze the expansion behavior of the coating under different temperature conditions, and the interlayer stress changes are calculated. The microcrack growth rate of the coating interface is simulated using the thermal expansion stress distribution difference data, and the fracture mechanics method is used to calculate the crack expansion path and depth changes under different stress states. Combined with the accelerated aging experimental data, a time-dependent model of crack growth is established to predict the depth change trend of the cracks in the coating during long-term use, and obtain crack depth growth prediction data.

[0029] Step S25: Perform a quantitative simulation of water resistance penetration loss based on the interlayer adhesion density difference data, crack depth extension prediction data and coating material property data to obtain water resistance penetration loss quantitative data.

[0030] In an embodiment of the present invention, the water resistance permeation loss is quantified based on the interlayer adhesion density difference data, the crack depth extension prediction data and the coating raw material property data. First, the water vapor barrier performance of the coating is determined by a water vapor permeation experiment, and the water vapor permeation rate is calculated in combination with the porosity of the coating. Subsequently, based on the crack extension data, the effect of the crack on the water vapor permeability is calculated. If the crack extends to the coating interface, the water vapor permeation rate will increase significantly. Combined with the water absorption data of the coating, the diffusion rate of water inside the coating is calculated, and the water resistance change trend of the coating under a long-term humidity environment is simulated. Finally, the experimental data and simulation results are used to quantify the water resistance permeation loss of the coating, and a complete water resistance performance database is formed for subsequent testing and analysis.

[0031] In another embodiment, a quantitative simulation of water resistance permeation loss is performed based on the interlayer adhesion density difference data, crack depth extension prediction data and coating raw material property data. First, based on the crack extension morphology trend data, the spatial distribution characteristics of the cracks are analyzed, and the crack uniformity distribution index is calculated using the statistical analysis method of the crack extension direction. The vertical depth variance between the crack depth extension prediction data is estimated, and the depth variation of the cracks in different areas is calculated. Combined with the crack extension data, the interlayer adhesion density weakening is estimated for the interlayer adhesion density difference data, and the strength change of the coating under long-term penetration is analyzed. The porosity change and water vapor permeability inside the coating are calculated by the coating density structure loss quantification method. Based on the water vapor permeation barrier loss strength estimation method, the water vapor diffusion coefficient of the coating is calculated, and combined with the accelerated water resistance experimental data, a water resistance permeation loss quantification model is established to obtain water resistance permeation loss quantification data.

[0032] Preferably, step S24 comprises the following steps: Step S241: Acquire all-weather sunshine data; evaluate the ultraviolet thermal radiation intensity of the all-weather sunshine data to obtain ultraviolet thermal radiation intensity data; Step S242: Analyze the critical range of heat decomposition resistance of the coating raw material property data to obtain the critical range of heat decomposition resistance of the raw material; Step S243: fitting the nonlinear relationship of thermal expansion of the interlayer adhesion density difference data and the critical range of heat-resistant decomposition of the raw material according to the ultraviolet thermal radiation intensity data to obtain the nonlinear relationship of thermal expansion of the coating layer; Step S244: performing thermal expansion stress distribution difference decomposition processing based on the nonlinear relationship of thermal expansion between coating layers and the interlayer adhesion density difference data to obtain thermal expansion stress distribution difference data; Step S245: Perform a sunlight crack depth propagation prediction simulation based on the nonlinear relationship of thermal expansion between coating layers and the thermal expansion stress distribution difference data to obtain crack depth propagation prediction data.

[0033] In an embodiment of the present invention, all-weather sunshine data of the area where the building is located is obtained by a meteorological data acquisition device, including parameters such as total solar radiation, ultraviolet index, daily maximum and minimum temperature, change of solar altitude angle, cloud cover, etc. A spectroradiometer is used to measure the ultraviolet radiation intensity, collect ultraviolet radiation data in the 280nm-400nm band, and record the change of radiation intensity in different time periods. Using the time series analysis method, a long-term trend analysis of the sunshine data is performed to determine the change law of ultraviolet radiation in different seasons. Based on the Fourier transform technology, the data is periodically analyzed, the main frequency characteristics of the sunshine intensity are extracted, and the radiation intensity change mode of the annual cycle and the daily cycle is identified. The all-weather ultraviolet radiation data is accumulated and calculated by the numerical integration method to obtain the daily, monthly and annual cumulative ultraviolet radiation intensity. Combined with the surface orientation and tilt angle of the building, the effective radiation received by the coating surface is calculated, and the actual radiation intensity is adjusted using the angle correction coefficient. Based on the above analysis results, an ultraviolet radiation intensity database is established to provide basic data for subsequent coating aging analysis. The thermal stability of the coating raw materials was tested by thermogravimetric analyzer (TGA). The samples were heated at a heating rate of 10°C / min in a nitrogen atmosphere, and the mass loss was recorded. The decomposition starting temperature, maximum decomposition rate temperature and residual mass of the coating materials were analyzed. The glass transition temperature (Tg), melting temperature (Tm) and thermal decomposition temperature (Td) of the coating materials were determined by differential scanning calorimeter (DSC), and the thermal properties of the coatings under different temperature conditions were analyzed. Combined with Fourier transform infrared spectroscopy (FTIR) testing, the functional group changes of the coatings at different temperatures were monitored, the chemical bond breaking was identified, and its thermal degradation mechanism was determined. X-ray photoelectron spectroscopy (XPS) was used to analyze the surface elemental composition of the coating materials after high temperature treatment to determine whether there was element loss caused by oxidation or thermal decomposition. Based on the above experimental data, the critical range of thermal decomposition resistance of the coating materials, that is, the maximum temperature range that the materials can withstand in a stable state, was determined, and the decomposition rate and mass loss rate in different temperature ranges were recorded. The linear expansion coefficient of the coating sample at different temperatures was measured based on a thermomechanical analyzer (TMA), the thermal expansion rate in different temperature ranges was recorded, and the thermal expansion coefficient of the coating material was calculated. The storage modulus, loss modulus and loss factor of the coating at different temperatures were measured using a dynamic thermomechanical analyzer (DMA), and the effect of thermal expansion on the mechanical properties of the coating was analyzed. Combined with the ultraviolet thermal radiation intensity data, the surface temperature change of the coating under actual sunlight conditions was calculated, and a curve of the coating temperature change over time was established. The nonlinear regression method was used to fit the thermal expansion coefficient of the coating with the temperature change data to obtain the nonlinear relationship of thermal expansion between the coating layers. The finite element analysis method was used to simulate the effect of temperature change on the stress distribution between the coating layers, calculate the thermal stress changes under different temperature gradients, and identify the stress concentration area generated at the coating interface.Combined with the data of interlayer adhesion density difference, the strain distribution at the interface of the coating during thermal expansion was analyzed, and the nonlinear relationship of thermal expansion between the coating layers was obtained. According to the nonlinear relationship of thermal expansion between the coating layers, the thermal stress distribution of the coating material under different temperature conditions was calculated. The finite element method was used to mesh the coating structure, define the material properties of different layers, and apply temperature loads to simulate the thermal expansion behavior of the coating under sunlight changes. The thermal stress distribution of the coating under different temperature gradients was calculated using the thermal stress analysis method, and the stress distribution difference was decomposed to extract the stress concentration in the key area. The thermal stress concentration factor at the coating interface was calculated using the fracture mechanics method to analyze the crack growth trend caused by thermal expansion. Combined with the data of interlayer adhesion density difference, the stress transfer mechanism between different layers of the coating during thermal expansion was analyzed to determine the location of stress relaxation or stress concentration between layers. Based on the above analysis, a database of thermal expansion stress distribution differences was constructed to provide data support for the subsequent prediction of crack depth extension. The surface strain of the coating samples heated by sunlight was measured using digital image correlation (DIC) technology to record the crack growth rate and direction. Infrared thermal imaging technology is used to monitor the temperature field on the coating surface, analyze the temperature gradient changes around the cracks, and determine the area of ​​thermal stress concentration. Combined with the difference data of thermal expansion stress distribution, the crack extension depth and extension rate under different temperature cycles are calculated. The energy release rate of crack extension is calculated by fracture mechanics method, and the crack extension trend under different stress states is analyzed. Through fatigue tests, high and low temperature cycle tests are carried out on coating samples, the time dependence of crack extension is recorded, and a time evolution model of crack extension is established. Based on long-term meteorological data, the crack extension rate of the coating in different seasons is simulated, and the cumulative extension depth of the crack under long-term exposure conditions is calculated. Combining experimental data and numerical calculation results, a crack extension prediction database is established to obtain crack depth extension prediction data.

[0034] Preferably, step S25 comprises the following steps: Step S251: performing an expansion morphology trend analysis on the crack depth extension prediction data to obtain crack extension morphology trend data; estimating the vertical depth variance between the trend differences of the crack depth extension prediction data based on the crack extension morphology trend data to obtain the vertical depth variance of the trend difference; Step S252: performing interlayer adhesion density weakening estimation on the interlayer adhesion density difference data according to the vertical depth variance of the strike difference to obtain interlayer adhesion density weakening data; Step S253: quantifying the coating density structure loss of the coating raw material property data based on the vertical depth variance of the strike difference and the interlayer adhesion density weakening data to obtain the coating density structure loss data; Step S254: estimating the water vapor penetration barrier loss strength according to the vertical depth variance of the strike difference, the interlayer adhesion density weakening data and the coating density structure loss data, and obtaining the water vapor penetration barrier loss strength data; Step S255: Perform a quantitative simulation of water penetration resistance loss based on the water vapor penetration barrier loss strength data to obtain quantitative data of water penetration resistance loss.

[0035] In the embodiment of the present invention, the crack depth extension prediction data is obtained by step S24, and includes information such as the depth, position and extension direction of the crack inside the coating. In order to further analyze the extension morphology trend of the crack, the crack depth extension prediction data is processed by image processing technology. First, the crack depth extension prediction data is converted into a two-dimensional image form, in which the position and depth of the crack are represented by different gray levels of pixel values. The image is processed using an edge detection algorithm (such as a Canny operator) to extract the edge contour of the crack. Then, the crack direction is analyzed by a morphological analysis method (such as a skeleton extraction algorithm) to obtain the main direction and branch direction of the crack. For example, assuming that the crack extends from the coating surface to the inside, the main direction is vertically downward, and the branch direction is the oblique extension on the left and right sides. The main direction and branch direction information of these cracks are the crack extension morphology trend data. Next, based on the crack extension morphology trend data, the vertical depth variance between the trend differences is estimated for the crack depth extension prediction data. Specifically, the crack is divided into multiple sub-areas according to its extension direction, and each sub-area corresponds to a specific crack direction. In each sub-region, the variance of the crack depth is calculated to evaluate the degree of change of the crack depth in different directions. For example, for cracks with a main direction of vertical downward, the depth variance in the vertical direction is calculated; for cracks with an oblique branch direction, the depth variance in the oblique direction is calculated. By comparing the crack depth variances of different directions, the vertical depth variance of the strike difference is obtained. This parameter reflects the difference in the depth change of the crack in different directions, and provides an important basis for subsequent analysis. The vertical depth variance of the strike difference obtained in step S251 is an important feature of the crack depth change, which is closely related to the interlayer adhesion density inside the coating. The interlayer adhesion density difference data is obtained through step S23, which includes the distribution of the adhesion density between the inner and outer layers of the coating. In order to estimate the degree of weakening of the interlayer adhesion density, a method based on weight distribution is adopted. First, the vertical depth variance of the strike difference is spatially aligned with the interlayer adhesion density difference data to ensure that the corresponding positions of the two inside the coating are consistent. Then, according to the size of the vertical depth variance of the strike difference, a weight value is assigned to the interlayer adhesion density at each location. The calculation of the weight value is based on the empirical relationship between the crack depth variance and the adhesion density. For example, assuming that the larger the crack depth variance is, the more drastic the crack depth change at that location is, and the more easily the interlayer adhesion density is damaged, so the assigned weight value is also larger. Specifically, for each tiny area inside the coating, the corresponding vertical depth variance value of the strike difference is calculated, and the weight value is calculated according to the preset empirical formula. Then, the weight value is multiplied by the original interlayer adhesion density value of the area to obtain the estimated value of the weakened interlayer adhesion density of the area. By weakening the interlayer adhesion density of all areas inside the coating, the interlayer adhesion density weakening data is obtained.This data reflects the decrease in interlayer adhesion density caused by crack expansion inside the coating, and provides an important basis for subsequent analysis. The coating raw material property data is obtained through step S21, which contains information such as the chemical composition, molecular structure and physical properties of the coating raw material. These data are the basis for evaluating the loss of coating density structure. The vertical depth variance of the strike difference and the weakening data of the interlayer adhesion density provide specific information on the changes in the internal structure of the coating. In order to quantify the loss of coating density structure, a method based on multi-parameter fusion is adopted. First, the vertical depth variance of the strike difference and the weakening data of the interlayer adhesion density are normalized so that their value range is between 0 and 1, so as to facilitate comparison and fusion with the coating raw material property data. Then, a quantitative model is established based on the correlation between the key parameters (such as porosity, elastic modulus, etc.) in the coating raw material property data and the vertical depth variance of the strike difference and the weakening data of the interlayer adhesion density. Specifically, for each tiny area inside the coating, the corresponding normalized vertical depth variance value of the difference in strike and the weakening value of the interlayer adhesion density are calculated, and the coating density structure loss value of the area is calculated by a preset quantitative formula in combination with the coating raw material property parameters (such as porosity) in the area. For example, assuming that the higher the porosity, the larger the vertical depth variance of the difference in strike, the more serious the weakening of the interlayer adhesion density, and the larger the coating density structure loss value. By calculating and summarizing the coating density structure loss of all areas inside the coating, the coating density structure loss data is obtained. This data reflects the density structure loss caused by crack propagation and decreased interlayer adhesion density inside the coating, providing an important basis for subsequent analysis. Water vapor permeation barrier loss strength is an important indicator for evaluating the water resistance of coatings. The vertical depth variance of the difference in strike, the weakening data of interlayer adhesion density, and the coating density structure loss data are all closely related to the water vapor permeation barrier performance. In order to estimate the water vapor permeation barrier loss strength, a physical model-based analysis method is used. First, based on the vertical depth variance of the strike difference and the interlayer adhesion density weakening data, the changes in the water vapor permeation path inside the coating are calculated. The larger the crack depth variance, the weaker the interlayer adhesion density, the more complex the water vapor permeation path, and the smaller the permeation resistance. Then, combined with the coating density structure loss data, the changes in the porosity and pore connectivity inside the coating are evaluated. The greater the density structure loss, the higher the porosity, the better the pore connectivity, and the easier it is for water vapor to penetrate. Specifically, by establishing a water vapor permeation model, the vertical depth variance of the strike difference, the interlayer adhesion density weakening data, and the coating density structure loss data are used as input parameters. Based on Fick's diffusion law, the model considers the porosity, pore connectivity, and crack distribution inside the coating to calculate the permeation flux of water vapor inside the coating.For example, assuming that the porosity inside the coating increases from 0.1 to 0.2, the crack depth variance increases from 0.01 to 0.05, and the interlayer adhesion density decreases from 0.9 to 0.7, the water vapor permeation flux will increase significantly. By calculating and summarizing the water vapor permeation flux in different areas inside the coating, the water vapor permeation barrier loss strength data is obtained. This data reflects the changes in the water vapor permeability performance of the coating under crack expansion and structural loss, and provides an important basis for subsequent analysis. Quantitative simulation of water resistance permeation loss is a key step in evaluating the water resistance of the coating. The water vapor permeation barrier loss strength data is obtained through step S254, which includes the changes in the water vapor permeability performance inside the coating. In order to perform quantitative simulation of water resistance permeation loss, a method based on time series analysis is adopted. First, a water resistance permeation model of the coating is established based on the water vapor permeation barrier loss strength data. The model assumes that the water vapor permeation process is a dynamic process that changes with time, and the permeation loss strength gradually increases with time. Then, the model is solved by a numerical simulation method to calculate the water resistance permeation loss of the coating at different time points. Specifically, the coating is divided into multiple tiny areas, and the water vapor permeation barrier loss strength of each area is used as the initial condition. During the simulation process, the water vapor permeation of each area is calculated step by step according to the preset time step (such as every day). For example, assuming that the water vapor permeation barrier loss strength of the coating is 0.1 at the initial moment, as time goes by, the cracks expand and the structural loss intensifies, and the water vapor permeation barrier loss strength gradually increases to 0.3. Through simulation calculations, the water vapor permeation of the coating at different time points is recorded, and finally the quantitative data of water resistance permeation loss is obtained. This data reflects the decrease in water resistance of the coating due to crack expansion and structural loss during actual use, and provides an important basis for the quality evaluation and improvement of construction materials.

[0036] Preferably, step S254 includes the following steps: According to the vertical depth variance of the strike difference, the interlayer adhesion density weakening data and the coating density structure loss data, the sparse structure strengthening analysis inside the coating was carried out to obtain the sparse structure strengthening data inside the coating; The internal sparse structure strengthening data of the coating, the interlayer adhesion density weakening data and the coating compact structure loss data are numerically integrated to obtain the internal and external cross-linking and curing weakening values ​​of the coating; Based on the sparse structure strengthening data inside the coating and the cross-linking and curing weakening values ​​inside and outside the coating, the water vapor interface diffusion density increment simulation is performed to obtain the water vapor interface diffusion density increment data; The water vapor penetration barrier loss strength is estimated based on the water vapor interface diffusion density increment data to obtain the water vapor penetration barrier loss strength data.

[0037] In the embodiment of the present invention, first, in the initial stage of step S254, the sparse structure strengthening analysis inside the coating is performed. Specifically, based on the acoustic wave data set of the wall coating (the data set reflects information such as the thickness, material density and surface morphology of the coating), the sparse structure of the coating can be evaluated by calculating the vertical depth variance of the orientation difference of the coating and the interlayer adhesion density weakening data. The vertical depth variance of the orientation difference can be inferred by the difference in the propagation velocity of the acoustic wave in different areas of the coating, wherein the change in the propagation velocity of the acoustic wave reflects the density and structural uniformity of the coating material. Based on this difference, the sparse structure strengthening data inside the coating is obtained by algorithm analysis. Next, the sparse structure strengthening data inside the coating, the interlayer adhesion density weakening data and the coating compactness structure loss data are numerically integrated for cross-linking and curing weakening inside and outside the coating. In this process, it is first necessary to pre-process the data, weightedly fuse the interlayer adhesion density weakening data and the coating compactness structure loss data, and calculate the comprehensive influence of various parameters by the weighted average method. This processing is intended to reveal the microstructural weakening inside the coating, especially due to aging or external load caused by long-term use. On this basis, the cross-linking and curing weakening values ​​inside and outside the coating are calculated by numerical integration method, so as to obtain the overall structural weakening trend of the coating under different environments. Based on the sparse structure strengthening data inside the coating and the cross-linking and curing weakening values ​​inside and outside the coating, the water vapor interface diffusion density increment simulation is further performed. The core task of this step is to simulate the diffusion behavior of water vapor in the coating. Using the water vapor diffusion model, the diffusion process of water vapor molecules at the coating interface is simulated based on the previously derived structural data. The diffusion model takes into account factors such as the porosity, interfacial tension and the compactness of the interlayer structure of the coating, which will affect the permeability of water vapor in the coating. Through repeated iterations, the water vapor interface diffusion density increment data is finally obtained, which indicates the degree of water vapor diffusion on the coating surface and its underlying structure within a given time. Finally, the water vapor permeation barrier loss strength is estimated based on the water vapor interface diffusion density increment data. The water vapor permeation barrier loss strength is closely related to the waterproof performance of the coating. Therefore, the waterproof ability of the coating can be evaluated based on the simulation results of water vapor diffusion. This process estimates the loss strength of the water vapor penetration barrier under specific conditions by analyzing the water vapor diffusion density increment data and combining it with the penetration resistance characteristics of the coating material. This loss strength can reflect the aging or performance degradation of the coating caused by water vapor penetration during actual use. Ultimately, this loss strength data provides a key reference for evaluating the waterproof effect and maintenance cycle of the coating. The implementation process specifically and meticulously explains how to derive the microstructural characteristics of the coating based on the acoustic wave data set, infer structural weakening through data integration, and then simulate water vapor diffusion and its impact on coating performance.

[0038] Preferably, step S3 comprises the following steps: Step S31: normalizing the quantified data of water resistance penetration loss to obtain normalized data of water resistance penetration loss; Step S32: performing permeation mechanism periodic aging inference on the normalized data of water resistance permeation loss to obtain permeation mechanism periodic aging data; Step S33: Perform coating material tolerance performance testing based on the penetration mechanism periodic aging data to obtain coating material tolerance performance data.

[0039] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes: Step S31: normalizing the quantified data of water resistance penetration loss to obtain normalized data of water resistance penetration loss; In the embodiment of the present invention, the quantitative data of water penetration loss resistance is normalized. First, based on the water vapor penetration barrier loss strength data, the data is normalized according to the maximum and minimum normalization method. The water penetration loss resistance data is linearly transformed by the extreme value normalization method, and all data are mapped to between 0 and 1 to avoid the influence of different data scales on subsequent analysis. After obtaining the maximum and minimum values ​​of the data, the difference between each data point and the minimum value is calculated and divided by the difference between the maximum and minimum values ​​to obtain a normalized data set. The range of the normalized data is limited to between 0 and 1, so that the test data of different batches are comparable, ensuring the accuracy of subsequent analysis. In the normalization process, outliers are removed, and the box plot (Box Plot, box and line plot) method is used to detect outliers. The data is screened according to the quartile distribution, and the outlier points exceeding 1.5 times the interquartile range (Interquartile Range) are removed to improve the reliability of the data. At the same time, the kernel density estimation (Kernel Density Estimation) is used to estimate the value of the data. The kernel density estimation (KE) method was used to analyze the distribution of the data to ensure the uniformity of the normalized data and finally obtain the normalized data of water resistance penetration loss.

[0040] Step S32: performing permeation mechanism periodic aging inference on the normalized data of water resistance permeation loss to obtain permeation mechanism periodic aging data; In the embodiment of the present invention, the normalized data of water resistance penetration loss is used to infer the periodic aging of the penetration mechanism. First, based on the normalized data, according to the time series analysis method, the trend analysis of the data of water resistance penetration loss changing with time is performed, and the autoregressive integrated moving average model (ARIMA model) is used to predict the future penetration loss trend. The sliding window technology is used to smooth the data to eliminate the influence of short-term fluctuations and improve the stability of the prediction. By calculating the change rate of water resistance penetration loss in different time periods, combined with the periodic aging experimental data, the durability change of the coating under the action of long-term water vapor erosion is analyzed. The penetration loss data is analyzed in the frequency domain by using the Fourier transform (Fourier transform) method to extract the periodic change characteristics and calculate the main aging cycle. According to the change cycle of the data, a periodic aging prediction model is established, and the aging trend is fitted by using the exponential decay function. The penetration loss rate at different time nodes is calculated, and the coating damage rate at different aging stages is obtained by data regression analysis. Based on the multiple regression method (Multiple Regression Analysis, multivariate regression analysis) was used to establish the coating penetration mechanism aging equation, and the model was optimized based on the experimental data, and finally the penetration mechanism periodic aging data was obtained.

[0041] Step S33: Perform coating material tolerance performance testing based on the penetration mechanism periodic aging data to obtain coating material tolerance performance data.

[0042] In the embodiment of the present invention, the tolerance performance of the coating material is tested based on the periodic aging data of the penetration mechanism. First, according to the periodic aging data, a stress accelerated aging test (Stress Accelerated Aging Test) is used to simulate the aging process of the coating under a long-term use environment. By controlling the environmental humidity, temperature and ultraviolet irradiation intensity, the durability change of the coating under different aging cycles is detected. The adsorption capacity of the coating surface to water vapor is measured by a dynamic contact angle tester (Dynamic Contact Angle Tester), and the change of the coating tolerance with the aging degree is analyzed. The gas permeation test (Gas Permeation Test) is used to measure the water vapor permeation rate of the coating at different aging stages. The change of the microstructure of the coating is analyzed in combination with a scanning electron microscope (Scanning Electron Microscope). The change of the chemical composition of the coating during the aging process is detected by an energy spectrum analysis (Energy Dispersive Spectroscopy) technology to obtain the loss rate of the main components of the coating. The infrared spectrum analysis (Fourier Transform Fourier transform infrared spectroscopy (FTIR) is used to detect the changes in coating functional groups and analyze the chemical bond breakage. Nanoindentation test (Nanoindentation Test) is used to determine the changes in coating hardness with aging time. The coating tolerance attenuation rate is calculated based on the periodic aging data, and finally the coating material tolerance performance data is obtained.

[0043] Preferably, step S32 includes the following steps: Step S321: performing a permeation time series progressive aggravation evaluation on the normalized water resistance permeation loss data to obtain permeation time series progressive aggravation data; Step S322: performing iterative fitting on the penetration time series progressive intensification data to obtain penetration time series intensification iterative data; Step S323: performing nonlinear regression analysis on the infiltration time series intensified iteration data to obtain infiltration iterative intensified regression data; Step S324: inferring the periodic aging of the permeability mechanism according to the permeability iterative aggravation regression data to obtain the periodic aging data of the permeability mechanism.

[0044] In an embodiment of the present invention, the normalized data of water resistance seepage loss is evaluated for the gradual intensification of seepage time series. First, based on the time series analysis method, the normalized water resistance seepage loss data is sorted according to the time axis to construct a time series data set. The moving average (Moving Average) method is used to smooth the data to reduce the impact of short-term fluctuations on long-term trends. The seepage loss increments in different time windows are calculated. The growth trend of the seepage loss is obtained by the cumulative increment analysis method. The difference (Differencing) method is used to eliminate the trend influence and improve the data stability. Based on the growth rate of the data, the exponential smoothing (Exponential Smoothing) method is used to predict the seepage loss trend at future time points. Combined with the growth curve of the seepage rate, the data segmented regression analysis method is used to calculate the change rate of the seepage rate at different stages. The local regression weighted scatter point smoothing (LOESS) method is used to further optimize the seepage time series trend curve to obtain the seepage time series gradual intensification data. The seepage time series gradual intensification data is iteratively fitted. First, based on the obtained seepage time series gradual intensification data, the least squares method (Least Squares) is used. The data were preliminarily fitted using the least squares method (LSM) to calculate the residual of the fitting curve and determine the degree of data fitting. If the fitting error was large, the gradient descent method was used to optimize the fitting parameters and adjust the shape of the fitting curve to make it more consistent with the actual data change trend. During the optimization process, the loss function of each iteration was calculated to ensure that the loss value gradually decreased. The polynomial regression method was used to perform high-order fitting on the data to improve the fitting accuracy. The best fitting curve was found by adjusting the polynomial order. If the data had large nonlinear characteristics, the spline interpolation method was used to optimize the fitting results. The piecewise function was used to construct a smoother fitting curve to ensure the continuity and differentiability of the data. Finally, the infiltration time series intensified iterative data was obtained. The infiltration time series intensified iterative data was subjected to nonlinear regression analysis. First, based on the fitted data, the nonlinear least squares method (Nonlinear Least Squares) was used to solve the optimal regression parameters. The power function (Power The data were fitted with a curve using power function and exponential function, and the coefficient of determination (R²) of the regression curve was calculated to measure the regression effect. If the R² value was low, the regression model was adjusted and logarithmic regression was tried.Logistic regression or logistic regression is used for data fitting, and the regression parameters are iteratively optimized to minimize the data fitting error. In the process of regression analysis, the Bayesian Information Criterion and Akaike Information Criterion are used for model optimization to screen out the regression model that best fits the data trend. The Monte Carlo Simulation method is used to evaluate the robustness of the regression model to ensure that the model can accurately predict the penetration loss trend in different time periods. Finally, the iterative infiltration regression data is obtained, and the periodic aging of the penetration mechanism is inferred based on the iterative infiltration regression data. First, based on the regression data, the growth rate of the penetration loss in different time periods is calculated, and the spectral characteristics of the data are analyzed by Fourier Transform to identify the main periodic components of the penetration loss. The autoregressive moving average model (ARMA) is used. AverageModel, Autoregressive Moving Average Model) is used to predict future penetration trends and calculate the penetration loss rates at different cycle stages. Combined with long-term aging test data, the penetration loss data is decomposed into three parts: long-term trend, seasonal fluctuations, and random disturbances using the time series decomposition method. The three parts are analyzed separately. The penetration loss rate is fitted with the Exponential Decay Model to obtain the long-term aging trend. Based on the staged regression method, the loss rate change rate at each aging stage is calculated. Combined with the coating microstructure change data, the physical and chemical change characteristics of the material during the aging process are analyzed, and finally the periodic aging data of the penetration mechanism are obtained.

[0045] Preferably, the present invention further provides a construction material detection system for executing the construction material detection method as described above, the construction material detection system comprising: The texture non-uniform distribution recognition module is used to perform multi-area scanning of the building decoration wall coating through an ultrasonic scanner to obtain a wall coating acoustic wave data set; based on the wall coating acoustic wave data set, the coating texture non-uniform distribution is recognized to obtain coating texture non-uniform distribution data; The water resistance penetration loss quantification module is used to calculate the density distribution difference between the inner and outer coatings between the layers according to the coating texture non-uniformity distribution data, and obtain the density distribution difference data of the inner and outer coatings; and to perform a quantitative simulation of the water resistance penetration loss according to the interlayer adhesion density difference data, and obtain the water resistance penetration loss quantification data; The tolerance performance detection module is used to infer the periodic aging of the penetration mechanism based on the quantitative data of water resistance penetration loss to obtain the periodic aging data of the penetration mechanism; based on the periodic aging data of the penetration mechanism, the tolerance performance of the coating material is detected to obtain the tolerance performance data of the coating material.

[0046] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A construction material detection method, characterized in that: The following steps are involved: Step S1: Scanning a multi-region wall coating of a building decoration by an ultrasonic scanner to obtain a wall coating acoustic wave data set; Based on the wall coating acoustic wave data set, the coating texture non-uniform distribution is identified to obtain the coating texture non-uniform distribution data; Step S2: Calculate the density distribution difference between inner and outer coatings according to the coating texture non-uniformity distribution data to obtain the density distribution difference data between inner and outer coatings; perform quantitative simulation of water resistance penetration loss according to the interlayer adhesion density difference data to obtain the quantitative data of water resistance penetration loss; Step S3: performing permeation mechanism periodic aging inference on the water resistance permeation loss quantification data to obtain permeation mechanism periodic aging data; Based on the periodic aging data of the penetration mechanism, the coating material tolerance performance is tested to obtain the coating material tolerance performance data.

2. The construction material detection method according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Scanning the wall coating of the building decoration in multiple regions by using an ultrasonic scanner to obtain a wall coating acoustic wave data set; Step S12: performing noise reduction processing on the wall coating sound wave dataset to obtain a wall coating noise reduction sound wave dataset; Step S13: performing microscopic morphology analysis of the inside and outside of the coating based on the wall coating noise reduction wave data set to obtain the inside and outside morphology data of the coating; Step S14: Identify the coating texture non-uniformity distribution based on the coating internal and external appearance structure data to obtain the coating texture non-uniformity distribution data.

3. The construction material detection method according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: Acquire coating raw material property data; perform coating inner and outer layer structure analysis on the coating inner and outer surface structure data according to the wall coating acoustic wave data set to obtain coating inner and outer layer structure data; Step S22: Calculate the density distribution difference between the inner and outer coatings according to the coating texture non-uniformity distribution data and the wall coating acoustic wave data set, and obtain the density distribution difference data between the inner and outer coatings; Step S23: performing interlayer adhesion density difference analysis based on the inner and outer coating density distribution difference data and the inner and outer layer structure data of the coating to obtain interlayer adhesion density difference data; Step S24: performing a sunlight crack depth extension prediction simulation on the interlayer adhesion density difference data to obtain crack depth extension prediction data; Step S25: Perform a quantitative simulation of water resistance penetration loss based on the interlayer adhesion density difference data, crack depth extension prediction data and coating material property data to obtain water resistance penetration loss quantitative data.

4. The construction material detection method according to claim 3, characterized in that: Step S24 includes the following steps: Step S241: Acquire all-weather sunshine data; evaluate the ultraviolet thermal radiation intensity of the all-weather sunshine data to obtain ultraviolet thermal radiation intensity data; Step S242: Analyze the critical range of heat decomposition resistance of the coating raw material property data to obtain the critical range of heat decomposition resistance of the raw material; Step S243: fitting the nonlinear relationship of thermal expansion of the interlayer adhesion density difference data and the critical range of heat-resistant decomposition of the raw material according to the ultraviolet thermal radiation intensity data to obtain the nonlinear relationship of thermal expansion of the coating layer; Step S244: performing thermal expansion stress distribution difference decomposition processing based on the nonlinear relationship of thermal expansion between coating layers and the interlayer adhesion density difference data to obtain thermal expansion stress distribution difference data; Step S245: Perform a sunlight crack depth propagation prediction simulation based on the nonlinear relationship of thermal expansion between coating layers and the thermal expansion stress distribution difference data to obtain crack depth propagation prediction data.

5. The construction material detection method according to claim 3, characterized in that: Step S25 includes the following steps: Step S251: performing an expansion morphology trend analysis on the crack depth extension prediction data to obtain crack extension morphology trend data; estimating the vertical depth variance between the trend differences of the crack depth extension prediction data based on the crack extension morphology trend data to obtain the vertical depth variance of the trend difference; Step S252: performing interlayer adhesion density weakening estimation on the interlayer adhesion density difference data according to the vertical depth variance of the strike difference to obtain interlayer adhesion density weakening data; Step S253: quantifying the coating density structure loss of the coating raw material property data based on the vertical depth variance of the strike difference and the interlayer adhesion density weakening data to obtain the coating density structure loss data; Step S254: estimating the water vapor penetration barrier loss strength according to the vertical depth variance of the strike difference, the interlayer adhesion density weakening data and the coating density structure loss data, and obtaining the water vapor penetration barrier loss strength data; Step S255: Perform a quantitative simulation of water penetration resistance loss based on the water vapor penetration barrier loss strength data to obtain quantitative data of water penetration resistance loss.

6. The construction material detection method according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: normalizing the quantified data of water resistance penetration loss to obtain normalized data of water resistance penetration loss; Step S32: performing permeation mechanism periodic aging inference on the normalized data of water resistance permeation loss to obtain permeation mechanism periodic aging data; Step S33: Perform coating material tolerance performance testing based on the penetration mechanism periodic aging data to obtain coating material tolerance performance data.

7. The construction material detection method according to claim 6, characterized in that: Step S32 includes the following steps: Step S321: performing a permeation time series progressive aggravation evaluation on the normalized water resistance permeation loss data to obtain permeation time series progressive aggravation data; Step S322: performing iterative fitting on the penetration time series progressive intensification data to obtain penetration time series intensification iterative data; Step S323: performing nonlinear regression analysis on the infiltration time series intensified iteration data to obtain infiltration iterative intensified regression data; Step S324: inferring the periodic aging of the permeability mechanism according to the permeability iterative aggravation regression data to obtain the periodic aging data of the permeability mechanism.

8. A construction material detection system, characterized in that: Used to perform the construction material detection method according to claim 1, the construction material detection system comprises: The texture non-uniform distribution recognition module is used to perform multi-area scanning of the building decoration wall coating through an ultrasonic scanner to obtain a wall coating acoustic wave data set; based on the wall coating acoustic wave data set, the coating texture non-uniform distribution is recognized to obtain coating texture non-uniform distribution data; The water resistance penetration loss quantification module is used to calculate the density distribution difference between the inner and outer coatings between the layers according to the coating texture non-uniformity distribution data, and obtain the density distribution difference data of the inner and outer coatings; and to perform a quantitative simulation of the water resistance penetration loss according to the interlayer adhesion density difference data, and obtain the water resistance penetration loss quantification data; The tolerance performance detection module is used to infer the periodic aging of the penetration mechanism based on the quantitative data of water resistance penetration loss to obtain the periodic aging data of the penetration mechanism; based on the periodic aging data of the penetration mechanism, the tolerance performance of the coating material is detected to obtain the tolerance performance data of the coating material.

Images