TG and IRE-2 Based Coating Base Emissivity Testing Method and System

Abstract

The present invention belongs to the technical field of material inspection, and specifically relates to a method and system for measuring the emissivity of a coating base material based on TG and IRE-2. First, a TG emissivity measuring instrument collects the full-band emissivity data of the target area of the coating base material and generates a curve, and marks the sensitive band. After determining that the sensitive band is within the measurable range of the IRE-2 measuring instrument, the dual-band emissivity data collected by it is obtained. Linear regression analysis is performed on the full-band and dual-band data to obtain a mapping relationship model, and an SVM neural network model is established with this as the kernel function. Finally, the data collected in real time by IRE-2 is input into the model to output the full-band emissivity of the coating base material. This method can accurately determine the sensitive band, and combines dual-band measurement with model prediction of the full-band emissivity to improve the measurement efficiency and accuracy.

Description

Technical Field

[0001] The present invention belongs to the technical field of material inspection, and particularly relates to a method and system for testing the emissivity of a coating base material based on TG and IRE-2. Background Art

[0002] The emissivity of a coating base material is an important parameter to measure its thermal radiation performance, which directly affects its application effects in scenarios such as high temperature and infrared stealth. There are many existing testing methods for coating base materials, such as the full-spectrum emissivity measurement method, the dual-band emissivity measurement method, the Fourier transform infrared spectroscopy method, the variable-temperature emissivity test method, etc. These methods can accurately test the emissivity of the coating base material. However, in the actual industrial testing environment, when testing the emissivity of the coating base material, it is often necessary to consider both the full-spectrum accuracy and real-time performance at the same time. However, the existing testing methods can only meet the testing requirements in one aspect. For example, although the full-spectrum emissivity test method can obtain the full-spectrum emissivity of the coating base material, it is difficult to meet the on-site rapid detection requirements. The dual-band emissivity measurement method is suitable for on-site use, but it can only obtain the emissivity data of specific bands and cannot directly reflect the full-band emissivity characteristics. Summary of the Invention

[0003] The technical problem to be solved by the present invention is that the existing emissivity test methods cannot consider both the full-spectrum accuracy and real-time performance at the same time.

[0004] To solve the above technical problem, the present invention is realized through the following technical solutions:

[0005] In a first aspect, a method for testing the emissivity of a coating base material based on TG and IRE-2 is proposed, including the following steps: S1: Obtain the full-band emissivity data of the target area on the coating base material collected by the TG emissivity measuring instrument under laboratory conditions; S2: Generate a corresponding full-band emissivity curve using the full-band emissivity data; S3: Mark the sensitive band corresponding to the absorption peak of the full-band emissivity curve; S4: Determine whether the sensitive band is within the measurable band range of the IRE-2 dual-band emissivity measuring instrument; if so, execute S5; if not, re-determine the target area on the coating base material and return to S1; S5: Obtain the first-band emissivity data and the second-band emissivity data of the target area collected by the IRE-2 dual-band emissivity measuring instrument under the laboratory conditions; S6: Perform linear regression analysis on the full-band emissivity data, the first-band emissivity data, and the second-band emissivity data to obtain a mapping relationship model; S7: Establish an SVM neural network model with the mapping relationship model as the kernel function; S8: Obtain the first-band emissivity field data and the second-band emissivity field data collected in real time by the IRE-2 dual-band emissivity measuring instrument; S9: Input the first-band emissivity field data and the second-band emissivity field data into the trained SVM neural network model and output the full-band emissivity of the coating base material.

[0006] Second aspect, a coating base material emissivity test system based on TG and IRE-2 is proposed, including: a first data acquisition module, configured to acquire the full-band emissivity data of a target area on the coating base material collected by a TG emissivity measuring instrument under laboratory conditions; a curve generation module, configured to generate a corresponding full-band emissivity curve by using the full-band emissivity data; a band marking module, configured to mark the sensitive band corresponding to the absorption peak of the full-band emissivity curve; a first analysis and control module, configured to determine whether the sensitive band is within the measurable band range of an IRE-2 dual-band emissivity measuring instrument; if so, control the second data acquisition module to work; if not, re-determine the target area on the coating base material and control the first data acquisition module to work; a second data acquisition module, configured to acquire the first-band emissivity data and the second-band emissivity data of the target area collected by the IRE-2 dual-band emissivity measuring instrument under the laboratory conditions; a linear regression analysis module, configured to perform linear regression analysis on the full-band emissivity data, the first-band emissivity data, and the second-band emissivity data to obtain a mapping relationship model; a model establishment module, configured to establish an SVM neural network model with the mapping relationship model as a kernel function; a third data acquisition module, configured to acquire the first-band emissivity on-site data and the second-band emissivity on-site data collected in real time by the IRE-2 dual-band emissivity measuring instrument; a result acquisition module, configured to input the first-band emissivity on-site data and the second-band emissivity on-site data into the trained SVM neural network model and output the full-band emissivity of the coating base material.

[0007] Third aspect, a computer device is proposed, including a memory, a processor, and a transceiver that are communicatively connected in sequence, where the memory is used to store a computer program, the transceiver is used to send and receive data, and the processor is used to read the computer program and execute a coating base material emissivity test method based on TG and IRE-2 as described in the first aspect.

[0008] Fourth aspect, a computer-readable storage medium is proposed, where an instruction is stored on the computer-readable storage medium, and when the instruction runs on a computer, it executes a coating base material emissivity test method based on TG and IRE-2 as described in any one of the first aspect.

[0009] Fifth aspect, a computer program product including an instruction is proposed, and when the instruction runs on a computer, it causes the computer to execute a coating base material emissivity test method based on TG and IRE-2 as described in the first aspect; the computer includes: a general computer, a special computer, or a programmable device.

[0010] Compared with the prior art, the present invention has the following advantages and beneficial effects: By combining the TG emissivity measuring instrument with the IRE-2 dual-band emissivity measuring instrument, rapid inversion of the emissivity in the key band and improvement of the overall accuracy are achieved, meeting the requirements of full-spectrum accuracy and real-time performance for dynamic monitoring in industrial fields. Specifically, the present invention uses the high-precision full-spectrum emissivity data provided by the TG emissivity measuring instrument as a reference, and at the same time uses the IRE-2 dual-band emissivity measuring instrument to measure the emissivity in real time and quickly. Through sensitive band screening, the dual-band realizes the collaborative optimization of reference data and real-time data; further, through linear regression analysis and the establishment of an SVM neural network model with a mapping relationship model as the kernel function, a complete test chain of "data acquisition - feature screening - model construction - real-time prediction" is formed, realizing the rapid inversion of the full-band emissivity of the coating base material using on-site emissivity data, thus taking into account both full-spectrum accuracy and real-time performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, form a part of this application, and do not constitute a limitation to the embodiments of the present invention. In the drawings:

[0012] Figure 1 It is a schematic flow chart of a method for testing the emissivity of a coating base material based on TG and IRE-2 provided in Embodiment 1 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the embodiments. The illustrative embodiments and descriptions thereof of the present invention are only used to explain the present invention and do not constitute a limitation to the present invention. The following described embodiments are a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0014] In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that: These specific details do not have to be employed to practice the present invention. In other embodiments, well-known structures, materials, or methods are not specifically described in order to avoid obscuring the present invention. The materials, instruments, and reagents used in the following embodiments, unless otherwise specified, can all be obtained from commercial sources. The technical means used in the embodiments, unless otherwise specified, are all conventional means well-known to those skilled in the art.

[0015] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of this application, "a plurality of" means two or more, unless otherwise specifically defined.

[0016] Embodiment 1: Provide a method for testing the emissivity of a coating base material based on TG and IRE-2. This method includes Figure 1 the following steps shown:

[0017] S1: Obtain the full-band emissivity data of the target area on the coating base material collected by the TG emissivity measuring instrument under laboratory conditions.

[0018] The TG emissivity measuring instrument is an instrument used to measure the emissivity of the coating base material. It works based on the thermogravimetric principle and can collect the full-band emissivity data of the target area on the coating base material under laboratory conditions. These data can reflect the emission ability of the material at different wavelengths. By analyzing and processing the full-band emissivity data, such as generating a full-band emissivity curve and marking the sensitive bands corresponding to the absorption peaks, the emission characteristics of the coating base material can be further understood, providing important basic data for subsequent research and applications.

[0019] S2: Generate a corresponding full-band emissivity curve using the full-band emissivity data.

[0020] First, organize and screen the full-band emissivity data, including removing outliers and processing duplicate data. Among them, removing outliers is to preliminarily check the full-band emissivity data collected by the TG emissivity measuring instrument. By setting reasonable data range thresholds, identify and remove data points that deviate significantly from the normal range. For example, when it is known that the theoretical range of the emissivity of the coating base material under specific experimental conditions is between 0.3 and 0.9, data points significantly lower than 0.3 or higher than 0.9 can be regarded as outliers. At the same time, observe the data distribution and remove isolated data points as abnormal data from the dataset. Further, processing duplicate data is for duplicate collected data points and needs to be processed. The average value of the duplicate data can be calculated and used to replace the duplicate data points to ensure the uniqueness and accuracy of the data, while reducing the impact of data redundancy on subsequent analysis.

[0021] Then, determine the abscissa and ordinate of the full-band emissivity curve. Use the abscissa to represent the wavelength, and determine the value range of the abscissa according to the wavelength range covered by the experiment. For example, if the wavelength range measured in the experiment is 0.2μm - 20μm, then the abscissa range is set from 0.2μm to 20μm. The unit uses micrometers in the International System of Units to ensure the universality and comparability of the data. Use the ordinate to represent the emissivity, and its value range is determined according to the actual measurement data, generally between 0 and 1. Emissivity is a dimensionless physical quantity, so the unit does not need to be marked on the ordinate.

[0022] Next, draw a scatter plot. Professional drawing software such as Origin, Matlab, etc. can be used, or the drawing function in office software such as Excel can also be used. This embodiment will be described by taking Origin software as an example. Import the sorted and filtered data into Origin software in the order of wavelength (abscissa data) and emissivity (ordinate data). During the import process, ensure that the data format is correct, and each column of data corresponds to the corresponding variable. In Origin software, select the imported data columns, click the "Plot" menu, and select the "Scatter Plot" option. The software will draw a scatter plot based on the imported data. At this time, each data point represents the emissivity of the coating substrate at a specific wavelength.

[0023] Finally, curve fitting. This embodiment selects multi-similar fitting as the curve fitting method. In Origin software, click the "Analysis" menu, select the "Fitting" sub-menu, and then select "Polynomial Fitting". In the polynomial fitting settings window, determine the order of the polynomial according to the complexity of the data. First, select a lower order (such as second order or third order) for fitting and observe the fitting effect. If the deviation between the fitting curve and the data points of the scatter plot is large, the order can be increased, but overfitting should be avoided. At the same time, set the confidence interval of the fitting to 95% to ensure the reliability of the fitting result. After completing the parameter settings, click the "OK" button, and the software will perform polynomial fitting on the scatter plot and generate a fitting curve.

[0024] By performing this step, on the one hand, the emissivity characteristics can be visually presented - the full-band emissivity curve can show the change of the emissivity of the coating substrate within the entire measurement wavelength range in an intuitive graphical form. Through the curve trend, the high and low fluctuations of the emissivity at different wavelengths can be seen. For example, the emissivity remains at a relatively high level in some wavelength intervals, while it is relatively low in others. Compared with simply listing the data, it can enable people to more quickly and comprehensively grasp the overall characteristics of the material's emissivity change with wavelength, providing an intuitive basis for subsequent analysis; on the other hand, it helps to identify absorption peaks - the absorption peaks appear as obvious trough shapes on the curve. By observing the curve and using mathematical means such as the first derivative method and the second derivative method (these methods all rely on the complete emissivity curve data), the positions of the absorption peaks can be accurately located.

[0025] S3: Mark the sensitive band corresponding to the absorption peak of the full-band emissivity curve.

[0026] The sensitive band corresponding to the absorption peak of the full-band emissivity curve refers to a wavelength range near the absorption peak position in the full-band emissivity curve, which has special indicative significance for the emission characteristics of the material. The absorption peak is the trough where the emissivity curve dips downward, representing that the material has a strong absorption ability for specific energy at this wavelength, thereby affecting its emissivity. The sensitive band is a wavelength interval determined around the absorption peak, and its boundaries are defined by the full-width at half-maximum method or the threshold-based method.

[0027] The premise of marking the sensitive band corresponding to the absorption peak is to identify the absorption peak. The method for identifying the absorption peak is as follows:

[0028] First, use mathematical analysis software (such as Origin, Matlab) to perform the first derivative on the full-band emissivity curve. After taking the derivative of the emissivity curve function, a first derivative function is obtained. Since the slope of the curve at the absorption peak changes significantly, it appears as a zero-crossing point where the value changes from negative to positive on the first derivative curve. By searching for these zero-crossing points, the position of the absorption peak can be preliminarily determined. For example, when the first derivative changes from -0.03 through the zero point to 0.05, the vicinity of the corresponding abscissa value is the position of the absorption peak. Further, perform the second derivative on the first derivative curve to obtain the second derivative function. Since at the absorption peak, the second derivative is negative and its absolute value reaches the local maximum. By searching for these local maximum negative value points in the second derivative curve, the absorption peak can be more accurately located. Compared with the first derivative, the second derivative is more sensitive to the curvature change of the curve and can capture the characteristics of the absorption peak more accurately. For example, within a certain wavelength range, the local maximum negative value of the second derivative appears at 5 μm, indicating that this position is an absorption peak.

[0029] It should be noted that the sensitive band described in this embodiment is the band in the full-band emissivity curve where the emissivity decrease amount > 0.1 and the full-width at half-maximum < 1 μm. After identifying the absorption peak, mark the band corresponding to the absorption peak to obtain the sensitive band.

[0030] After marking out the sensitive band, the boundaries of the absorption peak can also be defined based on the full width at half maximum method or the threshold method. The purpose of identifying the absorption peak boundaries is as follows: First, the sensitive range can be accurately defined. The absorption peak boundaries clarify the starting and ending positions of the absorption peak on the wavelength axis, and the sensitive band determined based on this is more accurate. By identifying the boundaries of the absorption peak, the wavelength range that truly has a significant impact on the emission characteristics of the material can be accurately delineated, avoiding the sensitive band range being too large or too small, so that subsequent research and applications can focus on the key area. Second, it is beneficial for characteristic analysis. Accurate absorption peak boundaries and sensitive bands can provide a more reliable basis for in-depth analysis of the optical, thermal, and other characteristics of the material. Third, the reliability of testing and application can be improved. In this embodiment, by clarifying the absorption peak boundaries, it helps to determine whether the IRE-2 dual-band emissivity measuring instrument can effectively cover the key measurement area, thereby improving the accuracy of emissivity testing and ensuring that in practical applications, the decisions and designs based on the sensitive band data are more reliable.

[0031] This embodiment supplements the specific implementation method for identifying the boundaries of the absorption peak based on the threshold method: Set a threshold related to the change in emissivity. For example, use the change rate of emissivity on both sides of the absorption peak reaching a certain set value (such as the emissivity change being greater than 0.05 per micrometer) as the boundary judgment condition. Starting from the absorption peak position, scan the curve data to both sides. When the change rate of emissivity first exceeds the set threshold, the corresponding abscissa value is the boundary of the absorption peak. Assume that on the right side of the absorption peak, start scanning from 5 μm. When the change rate of emissivity first becomes greater than 0.05 at 5.3 μm, the right boundary of the absorption peak is 5.3 μm. Similarly, determine the left boundary. This method is applicable to situations where the accuracy requirement for the absorption peak boundary is not particularly high but a rough range needs to be determined quickly.

[0032] S4: Determine whether the sensitive band is within the measurable band range of the IRE-2 dual-band emissivity measuring instrument; if so, execute S5; if not, re-determine the target area on the coating base material and return to S1.

[0033] Since the IRE-2 dual-band emissivity measuring instrument has its specific measurable band range, only when the sensitive band is within this range can the measuring instrument effectively measure the sensitive band. By judging whether the sensitive band is within the measurable range, the situation of unable to measure due to band mismatch can be excluded in advance, ensuring the smooth progress of the measurement work. On the contrary, if the sensitive band is not within the measurable band range of the measuring instrument, accurate emissivity data of the sensitive band cannot be obtained using this measuring instrument. And the sensitive band is crucial for studying the emissivity characteristics of the coating substrate. The lack of data in this band will make the measurement results incomplete and unable to accurately reflect the true emissivity characteristics of the material. Therefore, judging whether the sensitive band is within the measurable range is to ensure that the obtained data can effectively reflect the emissivity characteristics of the coating substrate and provide reliable data support for subsequent analysis and research. Through this step, a suitable measurement area can be screened out, enabling the measurement data to meet the requirements for model establishment, thereby improving the accuracy and reliability of the entire test method.

[0034] S5: Obtain the first-band emissivity data and the second-band emissivity data of the target area collected by the IRE-2 dual-band emissivity measuring instrument under laboratory conditions.

[0035] The first-band emissivity data and the second-band emissivity data collected by the IRE-2 dual-band emissivity measuring instrument are the key data sources for subsequent analysis and model establishment. By using the dual-band emissivity data to predict the full-band emissivity, rapid and accurate measurement of the emissivity of the coating substrate can be achieved.

[0036] In addition, after obtaining the first-band emissivity data and the second-band emissivity data in this embodiment, the first data deviation between the full-band emissivity data and the first-band emissivity data in the same band range, and the second data deviation between the full-band emissivity data and the second-band emissivity data in the same band range are also obtained. On the one hand, by calculating the first data deviation and the second data deviation, the difference degree between the first-band and second-band emissivity data collected by the IRE-2 dual-band emissivity measuring instrument and the full-band emissivity data in the same band range can be intuitively understood. The smaller the deviation, the higher the coincidence degree between the dual-band measurement data and the full-band data, and the higher the measurement accuracy of the measuring instrument; on the contrary, a larger deviation indicates that there may be errors in the measurement, such as calibration problems of the measuring instrument, influence of the measurement environment, etc., so as to take corresponding measures to improve the measurement accuracy. On the other hand, when establishing the mapping relationship model or SVM neural network model between the full-band emissivity and the dual-band emissivity, the data deviation is an important reference index. By analyzing the data deviation, the contribution degree of data in different bands to the model and the potential relationship between the data can be understood, so as to reasonably select model parameters, optimize the model structure, and improve the fitting degree and prediction accuracy of the model.

[0037] The method for calculating the data deviation is as follows:

[0038] First, determine the same wavelength range. It is necessary to clarify the same wavelength range of the full-band emissivity data and the emissivity data of the first and second bands. This can be determined according to the specifications of the measuring instrument and the settings of data acquisition. For example, if the measurement range of the full-band emissivity data is 0.1 - 20 μm, and the first band of the IRE-2 dual-band emissivity measuring instrument is 3 - 5 μm, and the second band is 8 - 14 μm, then the corresponding same wavelength ranges for the full-band data are 3 - 5 μm and 8 - 14 μm.

[0039] Then, perform data matching and alignment. After determining the same wavelength range, the full-band emissivity data needs to be matched and aligned with the emissivity data of the first and second bands within this range. For example, if the wavelength point interval of the full-band emissivity data within the range of 3 - 5 μm is 0.1 μm, and the wavelength point interval of the first-band emissivity data is 0.2 μm, then interpolation processing needs to be performed on the first-band data to make its wavelength points consistent with those of the full-band data for subsequent calculations.

[0040] Finally, calculate the data deviation. In this embodiment, the absolute deviation of the data is calculated. For the emissivity data at each same wavelength point, calculate the absolute value of the difference between the full-band emissivity value and the emissivity value of the first or second band, that is, the absolute deviation.

[0041] When the first data deviation > the threshold or the second data deviation > the threshold, it indicates that there may be an error in the measurement. At this time, a warning is issued and the process returns to S1 for re-measurement.

[0042] S6: Perform linear regression analysis on the full-band emissivity data, the first-band emissivity data, and the second-band emissivity data to obtain a mapping relationship model.

[0043] The purpose of this method is to obtain the full-band emissivity through inversion. Therefore, by constructing a mapping relationship model, the quantitative relationship between the full-band emissivity data and the emissivity data of the first and second bands is clarified. Given the emissivity data of the first and second bands, the full-band emissivity can be accurately predicted.

[0044] In addition, in actual situations, there is a certain linear correlation between the emissivities of the coating base materials in different bands. From a physical perspective, the microstructure and optical properties of materials to a certain extent determine their emissivity characteristics, and these characteristics may have a relatively stable variation relationship between different bands, which can be approximately described by a linear function within a certain range. Therefore, in this embodiment, linear regression analysis is performed on the full-band emissivity data, the first-band emissivity data, and the second-band emissivity data to obtain a mapping relationship model. The dependent variable of the mapping relationship model is the full-band emissivity, and the independent variables of the mapping relationship model are the first-band emissivity, the second-band emissivity, and the ambient temperature, and its expression is: ; where E represents the predicted value of the full-band emissivity, λ 1 is one of the measurable bands of the IRE-2 dual-band emissivity measuring instrument, λ 2 is the other measurable band of the IRE-2 dual-band emissivity measuring instrument, is the measured emissivity of the IRE-2 dual-band emissivity measuring instrument in the band λ 1, is the measured emissivity of the IRE-2 dual-band emissivity measuring instrument in the band λ 2, T represents the ambient temperature, a is the weight coefficient of the measured emissivity of the IRE-2 dual-band emissivity measuring instrument in the band λ 1, b is the weight coefficient of the measured emissivity of the IRE-2 dual-band emissivity measuring instrument in the band λ 2, c is the temperature compensation coefficient, d is the constant offset term.

[0045] S7: Establish an SVM neural network model with the mapping relationship model as the kernel function.

[0046] It should be noted that:

[0047] First, the mapping relationship model reflects the internal relationship between the full-band emissivity data and the first- and second-band emissivity data. Introducing it as the kernel function into the SVM neural network model can utilize this prior knowledge to better perform feature extraction and non-linear mapping on the data, thereby improving the model's fitting and prediction capabilities for emissivity data, enabling it to more accurately handle complex emissivity data relationships, and enhancing the model's accuracy and generalization ability.

[0048] Second, in practice, the relationship between emissivity data may not be a simple linear relationship. The SVM itself has good processing ability for non-linear problems. By using the kernel function based on the mapping relationship model, the original data can be mapped to a higher-dimensional feature space, where it is easier to find the linearly separable boundary of the data, thus effectively solving the non-linear problems in emissivity data and more accurately describing the complex non-linear relationship between emissivities in different bands.

[0049] Third, the kernel function established based on the mapping relationship model can enable the SVM neural network model to better adapt to different data sets and noise interference. Since the mapping relationship model is obtained through the analysis of actual emissivity data, it contains the inherent characteristics and laws of the data, can suppress the influence of noise and abnormal data to a certain extent, and make the model have stronger robustness, that is, the model can still maintain good performance and stability when facing different measurement errors, data missing or other interference factors.

[0050] Fourth, using the mapping relationship model as the kernel function can simplify the structure of the SVM neural network model. Compared with directly using a complex neural network structure to fit emissivity data, the SVM model based on a specific kernel function usually has fewer parameters, thus reducing the complexity and training time of the model, avoiding the occurrence of overfitting phenomenon, and at the same time improving the interpretability of the model, facilitating the understanding and application of the model.

[0051] Furthermore, the specific method for establishing the SVM neural network model with the mapping relationship model as the kernel function:

[0052] First, according to the mapping relationship model , define the kernel function K ( x i , x j ). The expression of the kernel function is: .

[0053] In the expression of the kernel function, represents the measured emissivity of the i th sample in band λ 1 of the IRE-2 dual-band emissivity measuring instrument, represents the measured emissivity of the j th sample in band λ 1 of the IRE-2 dual-band emissivity measuring instrument, represents the measured emissivity of the i th sample in band λ 2 of the IRE-2 dual-band emissivity measuring instrument, represents the measured emissivity of the jThe measured emissivity of a sample in the band of the IRE-2 dual-band emissivity measuring instrument λ in band 2, T i denote the i environmental temperature corresponding to the T j th sample, j and the environmental temperature corresponding to the

[0054] Then, select support vector regression SVR as the type of support vector machine SVM.

[0055] Next, set the SVM neural network model parameters. The model parameters include the penalty parameter C and the kernel function coefficient. Among them, the penalty parameter C is used to control the complexity and error tolerance of the model; the larger C is, the higher the requirement for the fitting degree of the model to the training data, but it may lead to overfitting; the smaller C is, the simpler the model is, but it may result in underfitting. Specifically, the penalty parameter needs to be determined according to the actual number of training samples. When the number of training samples is small, in order to prevent the model from being too complex and overfitting, a smaller C value can be selected; on the contrary, if the number of samples is sufficient and the model has enough data for learning, the C value can be appropriately increased to better fit the data and improve the accuracy of the model. For example, the penalty parameter C can be selected from [0.01, 10]. The kernel function coefficient corresponds to the above weight coefficient a , b , c , d .

[0056] Finally, input the training samples into the SVM model and use the kernel function K ( x i , x j ) and the set penalty parameter and kernel function coefficient for training. The goal of the training process is to find a set of optimal model parameters to minimize the loss function of the model on the training dataset.

[0057] S8: Obtain the on-site data of the emissivity in the first band and the on-site data of the emissivity in the second band collected in real time by the IRE-2 dual-band emissivity measuring instrument.

[0058] S9: Input the on-site data of the emissivity in the first band and the on-site data of the emissivity in the second band into the trained SVM neural network model, and output the full-band emissivity of the coating base material.

[0059] Embodiment 2: Corresponding to Embodiment 1, this embodiment provides a coating base material emissivity testing system based on TG and IRE-2, including:

[0060] The first data acquisition module is used to acquire the full-band emissivity data of the target area on the coating base material collected by the TG emissivity measuring instrument under laboratory conditions.

[0061] The curve generation module is used to generate a corresponding full-band emissivity curve by using the full-band emissivity data.

[0062] The band marking module is used to mark the sensitive bands corresponding to the absorption peaks of the full-band emissivity curve.

[0063] The first analysis and control module is used to determine whether the sensitive band is within the measurable band range of the IRE-2 dual-band emissivity measuring instrument; if so, it controls the second data acquisition module to work; if not, it re-determines the target area on the coating base material and controls the first data acquisition module to work.

[0064] The second data acquisition module is used to acquire the first-band emissivity data and the second-band emissivity data of the target area collected by the IRE-2 dual-band emissivity measuring instrument under the laboratory conditions.

[0065] The linear regression analysis module is used to perform linear regression analysis on the full-band emissivity data, the first-band emissivity data, and the second-band emissivity data to obtain a mapping relationship model.

[0066] The model establishment module is used to establish an SVM neural network model with the mapping relationship model as the kernel function.

[0067] The third data acquisition module is used to acquire the first-band emissivity field data and the second-band emissivity field data collected by the IRE-2 dual-band emissivity measuring instrument in real time.

[0068] The result acquisition module is used to input the first-band emissivity field data and the second-band emissivity field data into the trained SVM neural network model and output the full-band emissivity of the coating base material.

[0069] The boundary recognition module is used to recognize the boundaries of the absorption peaks based on the threshold method.

[0070] The data cleaning module is used to perform moving average filtering on the full-band emissivity data, the first-band emissivity data, and the second-band emissivity data.

[0071] The data deviation acquisition module is used to acquire the first data deviation of the full-band emissivity data and the first-band emissivity data in the same band range, and acquire the second data deviation of the full-band emissivity data and the second-band emissivity data in the same band range.

[0072] A data compensation module, configured to compensate the first-band emissivity field data by using the first data deviation, and compensate the second-band emissivity field data by using the second data deviation.

[0073] A second analysis and control module, configured to control the warning module and the first data acquisition module to work when the first data deviation > the threshold or the second data deviation > the threshold.

[0074] Embodiment 3: Based on the method provided in Embodiment 1 and the system provided in Embodiment 2 above, this embodiment provides a computer device that executes the method described in Embodiment 1 or any method that may be related to the method described in Embodiment 1, including a memory, a processor, and a transceiver that are communicatively connected in sequence. Among them, the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the method described in Embodiment 1 or any method that may be related to the method described in Embodiment 1. Specifically, the memory may, but is not limited to, include a random access memory (RAM), a read-only memory (ROM), a flash memory, a first-in first-out memory (FIFO), and / or a first-in last-out memory (FILO), etc.; the processor may, but is not limited to, adopt a microprocessor of the STM32F105 series. In addition, the computer device may, but is not limited to, further include a power module, a display screen, and other necessary components.

[0075] For the working process, working details, and technical effects of the computer device provided in this embodiment, reference may be made to the method described in Embodiment 1 or any method that may be related to the method described in Embodiment 1, and details are not described herein again.

[0076] Embodiment 4: This embodiment provides a computer-readable storage medium storing a method including the method described in Embodiment 1 or any method that may be related to the method described in Embodiment 1, that is, instructions are stored on the computer-readable storage medium, and when the instructions are run on a computer, the method described in Embodiment 1 or any method that may be related to the method described in Embodiment 1 is executed. Among them, the computer-readable storage medium refers to a carrier for storing data, and may, but is not limited to, include computer-readable storage media such as floppy disks, optical discs, hard disks, flash memories, USB flash drives, and / or memory sticks. The computer may be a general-purpose computer, a dedicated computer, a computer network, or other programmable devices.

[0077] For the working process, working details and technical effects of the aforementioned computer-readable storage medium provided in this embodiment, reference may be made to the method described in Embodiment 1 or any method that may be related to the method described in Embodiment 1, which will not be elaborated herein.

[0078] Embodiment 5: This embodiment provides a computer program product containing instructions that, when run on a computer, cause the computer to execute the method described in Embodiment 1 or any method that may be related to the method described in Embodiment 1. Among them, the computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices.

[0079] It should be understood that the "system", "device", "unit" and / or "module" used in this specification are a way to distinguish different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the said words can be replaced by other expressions.

[0080] As shown in this specification and the claims, unless the context clearly indicates an exception, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list, and the method or device may also include other steps or elements.

[0081] The specific embodiments described above further elaborate on the purpose, technical solution and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0082] It should be noted that the structures, proportions, sizes, etc. shown in the drawings of this specification are only used to cooperate with the content disclosed in the specification for those familiar with this technology to understand and read, and are not used to limit the limiting conditions under which the present invention can be implemented. Therefore, they do not have technical essence. Any modification of the structure, change of the proportional relationship or adjustment of the size, without affecting the effects that the present invention can produce and the purposes that can be achieved, should still fall within the scope covered by the technical content disclosed in the present invention. At the same time, the terms such as "upper", "lower", "left", "right", "middle" and the like cited in this specification are only for the convenience of clear narration and are not used to limit the scope under which the present invention can be implemented. The change or adjustment of their relative relationship, without substantial change in the technical content, should also be regarded as the scope within which the present invention can be implemented.

Claims

1. A method for testing the emissivity of a coating base material based on TG and IRE-2, characterized in that, It includes the following steps: S1: Obtain the full-band emissivity data of the target area on the coating base material collected by the TG emissivity measuring instrument under laboratory conditions; S2: Generate a corresponding full-band emissivity curve using the full-band emissivity data; S3: Mark the sensitive band corresponding to the absorption peak of the full-band emissivity curve; S4: Determine whether the sensitive band is within the measurable band range of the IRE-2 dual-band emissivity measuring instrument; if so, execute S5; if not, re-determine the target area on the coating base material and return to S1; S5: Obtain the first-band emissivity data and the second-band emissivity data of the target area collected by the IRE-2 dual-band emissivity measuring instrument under the laboratory conditions; S6: Conduct a linear regression analysis on the full-band emissivity data, the first-band emissivity data, and the second-band emissivity data to obtain a mapping relationship model; S7: Establish an SVM neural network model with the mapping relationship model as the kernel function; S8: Obtain the on-site first-band emissivity data and the on-site second-band emissivity data collected by the IRE-2 dual-band emissivity measuring instrument in real time; S9: Input the on-site first-band emissivity data and the on-site second-band emissivity data into the trained SVM neural network model and output the full-band emissivity of the coating base material.

2. The method for testing the emissivity of a coating base material based on TG and IRE-2 according to claim 1, wherein The sensitive band is the band in the full-band emissivity curve where the emissivity decrease amount > 0.1 and the full width at half maximum < 1 μm; After marking the sensitive band, it further includes the following steps: Identify the boundary of the absorption peak based on the threshold method.

3. A method for testing the emissivity of a coating base material based on TG and IRE-2 according to claim 1 or 2, characterized in that, Before S6, it further includes the following steps: Conduct a moving average filtering on the full-band emissivity data, the first-band emissivity data, and the second-band emissivity data.

4. A method for testing the emissivity of a coating base material based on TG and IRE-2 according to claim 1 or 2, characterized in that, After S5, it further includes the following steps: Obtain the first data deviation of the full-band emissivity data and the first-band emissivity data in the same band range, and obtain the second data deviation of the full-band emissivity data and the second-band emissivity data in the same band range; After S8, it further includes the following steps: Compensate the on-site first-band emissivity data using the first data deviation, and compensate the on-site second-band emissivity data using the second data deviation.

5. A method for testing the emissivity of a coating base material based on TG and IRE-2 according to claim 4, characterized in that, After S5, it further includes the following steps: When the first data deviation > the threshold or the second data deviation > the threshold, issue a warning and return to S1.

6. A method for testing the emissivity of a coating base material based on TG and IRE-2 according to claim 1 or 2, characterized in that, The dependent variable of the mapping relationship model is the full-band emissivity, and the independent variables of the mapping relationship model are the first-band emissivity, the second-band emissivity, and the ambient temperature; The expression of the mapping relationship model is as follows: ; where E represents the predicted value of the full-band emissivity, λ 1 is one of the measurable bands of the IRE-2 dual-band emissivity measuring instrument, λ 2 is the other measurable band of the IRE-2 dual-band emissivity measuring instrument, is the measured emissivity of the IRE-2 dual-band emissivity measuring instrument in the band λ 1, is the measured emissivity of the IRE-2 dual-band emissivity measuring instrument in the band λ 2, T represents the ambient temperature, a is the weight coefficient of the measured emissivity of the IRE-2 dual-band emissivity measuring instrument in the band λ 1, b is the weight coefficient of the measured emissivity of the IRE-2 dual-band emissivity measuring instrument in the band λ 2, c is the temperature compensation coefficient, d is the constant offset term.

7. A coating base emissivity testing system based on TG and IRE-2, characterized in that It includes: A first data acquisition module for obtaining the full-band emissivity data of the target area on the coating base material collected by the TG emissivity measuring instrument under laboratory conditions; A curve generation module for generating a corresponding full-band emissivity curve using the full-band emissivity data; A band marking module for marking the sensitive band corresponding to the absorption peak of the full-band emissivity curve; The first analysis control module is used to determine whether the sensitive band is within the measurable band range of the IRE-2 dual-band emissivity measuring instrument; if so, it controls the second data acquisition module to work; if not, it re-determines the target area on the coating base material and controls the first data acquisition module to work; The second data acquisition module is used to acquire the first-band emissivity data and the second-band emissivity data of the target area collected by the IRE-2 dual-band emissivity measuring instrument under the laboratory conditions; The linear regression analysis module is used to perform linear regression analysis on the full-band emissivity data, the first-band emissivity data, and the second-band emissivity data to obtain a mapping relationship model; The model establishment module is used to establish an SVM neural network model with the mapping relationship model as the kernel function; The third data acquisition module is used to acquire the first-band emissivity field data and the second-band emissivity field data collected by the IRE-2 dual-band emissivity measuring instrument in real time; The result acquisition module is used to input the first-band emissivity field data and the second-band emissivity field data into the trained SVM neural network model and output the full-band emissivity of the coating base material; 8. A coating base emissivity testing system based on TG and IRE-2 according to claim 7, characterized in that The sensitive band is the band in the full-band emissivity curve where the emissivity decrease amount > 0.1 and the full width at half maximum < 1 μm; The system further includes: a boundary recognition module, which is used to recognize the boundary of the absorption peak based on the threshold method.

9. A coating base emissivity test system based on TG and IRE-2 according to claim 7 or 8, characterized in that, It further includes: The data cleaning module is used to perform moving average filtering on the full-band emissivity data, the first-band emissivity data, and the second-band emissivity data.

10. A coating base emissivity test system based on TG and IRE-2 according to claim 7 or 8, characterized in that, It further includes: The data deviation acquisition module is used to acquire the first data deviation of the full-band emissivity data and the first-band emissivity data in the same band range, and acquire the second data deviation of the full-band emissivity data and the second-band emissivity data in the same band range; The data compensation module is used to compensate the first-band emissivity field data with the first data deviation and compensate the second-band emissivity field data with the second data deviation; The second analysis control module is used to control the warning module and the first data acquisition module to work when the first data deviation > the threshold or the second data deviation > the threshold.

Images