Heating surface aging grade evaluation method based on feature migration

Abstract

The invention relates to a heating surface aging grade evaluation method based on feature migration. The heated surface aging grade evaluation method based on feature migration comprises the following steps: S10, setting a sample assembly; s20, respectively placing the plurality of sample assemblies in equipment to be detected; s30, obtaining a sample data set; s40, respectively obtaining first sample data and first in-service data at the moment; s50, obtaining a correction value; and S60, correcting the sample data set through the correction value to obtain a corrected data set. The heated surface aging grade evaluation method based on feature migration has the advantage of being convenient to evaluate.

Description

Technical Field

[0001] The present application relates to the technical field of nondestructive testing, and in particular to a method for evaluating the aging grade of a heated surface based on feature migration. Background Art

[0002] With the advancement of industrialization, more high-temperature pressure-bearing equipment is widely used in the power, metallurgy, power machinery, petrochemical and other industries. The safe and stable operation of equipment is closely related to production life safety and economic development. Therefore, service status monitoring and risk assessment of high-temperature pressure-bearing equipment materials are important means to ensure production safety and economic benefits. For the thermal power generation industry, under the background of energy conservation and emission reduction requirements, more large-scale and high-parameter power station units are put into operation, which puts higher requirements on the performance of heat-bearing pressure materials.

[0003] At present, the service status monitoring of high-temperature pressure-bearing materials is mainly carried out through preventive planned maintenance (major repairs, minor repairs, regular maintenance, and temporary repairs). The failure status of the material is evaluated by inspecting the surface status, geometric dimensions, metallographic structure, and mechanical properties of the monitored components during service. However, the current failure detection methods for high-temperature pressure-bearing materials have defects to varying degrees. The destructive evaluation method requires cutting the pipe for sampling, which affects the continuous operation of the equipment, has a long detection cycle, and the representativeness of the sampling needs to be improved. Traditional non-destructive testing has the disadvantages of radiation risks, can only detect macroscopic defects, or has limited detection depth.

[0004] Based on this, it is necessary to develop a new generation of non-destructive testing methods that can quickly / in-situ predict and analyze the failure trend of metal materials. Laser-Induced Breakdown Spectroscopy (LIBS) is a technical means that can meet the above needs. By micro-ablating the test object, the breakdown spectrum information characterizing the characteristics of the material matrix is ​​obtained, and the characteristic detection can be achieved with almost no damage to the test object. In addition, the measuring devices that constitute this technology can be integrated into portable measuring equipment or remote measuring devices, so as to meet the needs of online monitoring of the service process of in-service materials or convenient manual detection during maintenance, and ensure the safe operation of high-temperature and pressure-bearing major equipment. However, this technical means needs to be carried out when the system is shut down or under maintenance.

[0005] The working environment of high-temperature pressure steel in service is often very harsh. The main reasons for the failure and aging of the steel are the changes in the metallographic structure of the steel, the precipitation and growth of carbides, and the changes in the micro-area distribution of related elements under high-temperature service. The spectrum of steel with different aging degrees can reflect the current aging characteristics of the steel. However, the cycle of updating and replacing high-temperature pressure equipment in power plants is long, and the aging level of the replaced heated surface metal samples is relatively single. In addition, to obtain the actual steel samples, the replaced steel needs to be cut and polished, and the acquisition process is complicated. Therefore, in actual research, it is difficult to obtain a sufficient number of high-temperature pressure steel samples with a wide range of aging levels under actual service conditions. This makes it difficult to obtain sufficient data support for data comparison, spectral feature analysis, and model establishment during the research process. Summary of the invention

[0006] Based on this, the purpose of this application is to provide a method for evaluating the aging grade of a heated surface based on feature migration, which has the advantage of being able to be tested at any time, thereby facilitating the acquisition of test results.

[0007] In one aspect of the present application, a method for evaluating the aging grade of a heating surface based on feature migration is provided, comprising the steps of:

[0008] S10, setting a sample assembly;

[0009] S20, placing a plurality of the sample assemblies in the devices to be tested respectively;

[0010] S30, taking out the sample assembly at fixed time intervals and performing aging detection to obtain a sample data set;

[0011] S40, in a shutdown state, respectively detecting the aging conditions of the sample assembly and the in-service equipment, and respectively obtaining the first sample data and the first in-service data at that moment;

[0012] S50, comparing the first sample data with the first in-service data, and correcting the first sample data using the first in-service data to obtain a corrected value;

[0013] S60, correcting the sample data set by using the correction value to obtain a corrected data set.

[0014] The method for evaluating the aging grade of a heated surface based on feature migration described in this application is to set up a sample assembly, then place the sample assembly together with the pressure-bearing equipment and run them simultaneously; after a set time interval, take out the sample assembly, and then detect the surface condition of the sample assembly by means of LIBS, and record and store the detected data. The sample assembly is tested and recorded multiple times at the same time interval until the system is shut down. When the system is shut down, the aging conditions of the sample assembly and the in-service equipment are detected separately, also by LIBS.

[0015] The two sets of data are then compared, their deviations are analyzed, and corrections are made based on the deviations so that the data values ​​of the sample components are consistent with those of the in-service equipment.

[0016] After the data set is corrected, a corrected data set is obtained, and the in-service equipment is evaluated through the corrected data set.

[0017] Therefore, the heating surface aging grade evaluation method based on feature migration of the present application can not only easily obtain more data, but also more accurately reflect the actual situation through the corrected data, so as to make a more accurate evaluation; because the amount of data is larger and richer, it can also make a more accurate prediction of the subsequent heating surface aging situation. In other words, the technical solution of the present application is not only more convenient for detection, but also can make a prediction of the same situation.

[0018] Furthermore, the method further comprises the steps of:

[0019] S70, repeating steps S30-S50 to obtain a plurality of correction values ​​at a plurality of time intervals, and obtaining a correction curve according to the plurality of correction values.

[0020] Furthermore, the method further comprises the steps of:

[0021] S80. Establish an aging grade model based on the correction curve.

[0022] Furthermore, the sample assembly includes a main pipe, a pressure-bearing end cover, a mounting cover, and a sample pipe;

[0023] A plurality of mounting holes are formed on the pressure-bearing end cover, and one end of the sample tube is mounted on the mounting hole of the pressure-bearing end cover;

[0024] The other end of the sample tube passes through and is sleeved on the mounting cover;

[0025] A plurality of branch through holes are formed in the pressure-bearing end cover, and a main through hole is formed, and the main through hole is respectively connected with the plurality of branch through holes; the plurality of branch through holes are respectively connected with the corresponding mounting holes one by one;

[0026] The main pipe is connected to the pressure-bearing end cover, and the main pipe is communicated with the main through hole;

[0027] An inner cavity is formed in the sample tube;

[0028] The main through hole is communicated with one end of a plurality of branch through holes respectively, and the other end of each branch through hole is communicated with the inner cavity of the sample tube.

[0029] Furthermore, the sample assembly further comprises a first fixing column and a second fixing column, wherein the first fixing column is installed in the middle of the pressure-bearing end cover, and the second fixing column is installed in the middle of the mounting cover; one end of the second fixing column is sleeved on the first fixing column;

[0030] A boss is formed at the end of the sample tube, and the boss abuts against the surface of the mounting cover to prevent the sample tube from being loosened from the mounting cover;

[0031] A sealing ring is provided at the connection between the sample tube and the mounting hole.

[0032] Furthermore, the sample assembly further comprises a mounting seat, and the mounting seat is mounted on the mounting cover;

[0033] Alternatively, the mounting seat is mounted on the mounting cover and the pressure-bearing end cover.

[0034] Furthermore, in step S30, aging detection is performed, including detecting the aging condition of the heated surface by LIBS.

[0035] Furthermore, the method further includes step S90 of evaluating the aging grade of the test sample according to the aging grade model.

[0036] Furthermore, in step S80, the aging grade model is generated according to the correction curve by means of feature migration.

[0037] For better understanding and implementation, the present application is described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a flowchart of a method for evaluating the aging grade of a heated surface based on feature migration, which is an example of the present application;

[0039] Figure 2 This is a flowchart of another exemplary method for evaluating the aging grade of a heated surface based on feature migration according to the present application;

[0040] Figure 3 A schematic diagram of the three-dimensional structure of an exemplary sample assembly of the present application;

[0041] Figure 4A schematic diagram of a three-dimensional structure of an exemplary sample assembly of the present application from another perspective;

[0042] Figure 5 A cross-sectional view of an exemplary sample assembly of the present application;

[0043] Figure 6 A schematic diagram of the three-dimensional structure of another exemplary sample assembly of the present application;

[0044] Figure 7 A cross-sectional view of another exemplary sample assembly of the present application;

[0045] Figure 8 A side view of an exemplary pressure-bearing end cover of the present application;

[0046] Fig. 9 A cross-sectional view of half of the BB surface of an exemplary pressure-bearing end cover of the present application;

[0047] Fig.10 This is a cross-sectional view of the other half of the exemplary pressure-bearing end cover of the present application after being cut along the BB surface. DETAILED DESCRIPTION

[0048] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. In the description of the present application, unless otherwise specified, "multiple" means two or more.

[0049] In order to obtain steel samples with different aging degrees and enrich the spectral data of steel samples, the study of the aging characteristics of high-temperature pressure-bearing steel can be first carried out around the artificially set sample tube 30. The artificially set sample tube 30 can simulate the real samples of in-service equipment to a certain extent, and it also has certain similarities with the real samples of in-service equipment in terms of metallographic structure, aging characteristics and LIBS spectral information. After studying the spectrum of the artificially set sample tube 30, the analyzed and summarized steel sample aging spectral characteristics are extended to the actual steel samples, and verified in combination with spectral correction, so as to solve the problem of difficulty in obtaining actual steel samples and single aging level in the research.

[0050] See also Figure 1-Figure 10 , an exemplary method for evaluating the aging grade of a heated surface based on feature migration in the present application comprises the following steps:

[0051] S10. Set up the sample assembly.

[0052] See also Figure 3-Figure 10 In some preferred embodiments, the sample assembly includes a main pipe 10, a pressure-bearing end cover 20, a mounting cover 40, and a sample pipe 30;

[0053] The pressure-bearing end cover 20 is formed with a plurality of mounting holes C, and one end of the sample tube 30 is mounted on the mounting hole C of the pressure-bearing end cover 20;

[0054] The other end of the sample tube 30 passes through and is sleeved on the mounting cover 40;

[0055] The pressure-bearing end cover 20 is formed with a plurality of branch through holes A and a main through hole, and the main through hole is connected with the plurality of branch through holes A respectively; the plurality of branch through holes A are connected with the corresponding mounting holes C one by one respectively;

[0056] The main pipe 10 is connected to the pressure-bearing end cover 20, and the main pipe 10 is in communication with the main through hole;

[0057] The sample tube 30 has an inner cavity formed therein;

[0058] The main through hole is communicated with one end of each of the branch through holes A, and the other end of each of the branch through holes A is communicated with the inner cavity of the sample tube 30 .

[0059] In some preferred embodiments, the sample assembly further includes a first fixing column 51 and a second fixing column 52, wherein the first fixing column 51 is installed in the middle of the pressure-bearing end cover 20, and the second fixing column 52 is installed in the middle of the mounting cover 40; one end of the second fixing column 52 is sleeved on the first fixing column 51;

[0060] A boss 31 is formed at the end of the sample tube 30, and the boss 31 abuts against the surface of the mounting cover 40 to prevent the sample tube 30 from being loosened from the mounting cover 40;

[0061] A sealing ring is provided at the connection between the sample tube 30 and the mounting hole C.

[0062] Compared with the prior art, the sample assembly of the present application is more suitable for the detection of high-temperature pressure-bearing equipment.

[0063] In some preferred embodiments, the sample assembly further includes a mounting seat 60, and the mounting seat 60 is mounted on the mounting cover 40;

[0064] Alternatively, the mounting seat 60 is mounted on the mounting cover 40 and the pressure-bearing end cover 20 .

[0065] Further, the mounting base 60 has two structures, one for horizontal placement, such as Figure 3 and4 As shown, at this time, the mounting seat 60 is installed on the mounting cover 40 and the pressure-bearing end cover 20, one is used for vertical placement, such as Figure 6 As shown, at this time, the mounting seat 60 is installed on the bottom surface of the mounting cover 40.

[0066] S20, placing a plurality of the sample assemblies in the devices to be tested respectively;

[0067] S30, taking out the sample assembly at fixed time intervals and performing aging detection to obtain a sample data set;

[0068] After the samples were pre-treated by grinding and polishing, LIBS detection was performed to obtain the spectrum data of continuous laser pulses at 30 different measuring points of each sample tube.

[0069] Different mechanical properties of metal surfaces, such as hardness, will cause differences in laser ablation samples. Also, factors such as slightly different curvatures on the surface of metal pipes and different surface layer structures will affect the interaction between the laser and the sample, thereby interfering with the correlation between LIBS data and heat-resistant steel properties. Therefore, the collected LIBS data needs to be preprocessed to eliminate error interference.

[0070] The standard normal transformation (SNV) can be used to eliminate the influence of surface roughness, different sizes of solid particles and surface scattering of the test sample.

[0071] At the same time, multivariate scatter correction (MSC) can be used to correct the baseline drift and eliminate the scattering effect caused by the uneven metal surface.

[0072] In some preferred embodiments, in step S30, aging detection is performed, including detecting the aging condition of the heated surface by LIBS.

[0073] S40, in a shutdown state, respectively detecting the aging conditions of the sample assembly and the in-service equipment, and respectively obtaining the first sample data and the first in-service data at that moment;

[0074] Since there are certain characteristic differences between the artificially set sample tube 30 and the real sample of the in-service equipment, the artificially set sample tube 30 cannot completely simulate the metal characteristics of the real sample of the in-service equipment. The spectra of the two have certain similarities and correlations, but there are still some characteristic differences. Therefore, it is necessary to perform characteristic analysis on the spectral data of the two samples.

[0075] Specifically, the Pearson correlation coefficient was used to calculate the correlation between the spectra of two types of samples.

[0076] Analyze the intensity difference of characteristic spectral lines and correct the intensity difference. Randomly sample the spectrum data of different aging levels of the artificially set sample tube 30 and the real sample data of the in-service equipment, and compare and analyze the spectrum intensity ratio of the LIBS data of the artificially set sample tube 30 and the real sample data of the in-service equipment at each wavelength point under the same aging level. The closer the spectrum intensity ratio of the uncorrected artificially set sample tube 30 and the real sample data of the in-service equipment at each wavelength point is to 1, the closer the spectrum intensity of the uncorrected artificially set sample tube 30 and the real sample of the in-service equipment at this wavelength point is, and the artificially set sample tube 30 can better characterize the spectrum characteristic information in the real sample of the in-service equipment.

[0077] The spectral data of random sampling is calculated according to the above formula, and the average spectral intensity ratio under the sampling data can be calculated for different aging levels, which is called the spectral intensity correction curve of the artificially set sample tube 30 under different aging levels.

[0078] S50, comparing the first sample data with the first in-service data, and correcting the first sample data using the first in-service data to obtain a corrected value;

[0079] S60, correcting the sample data set by using the correction value to obtain a corrected data set.

[0080] The method for evaluating the aging grade of a heated surface based on feature migration described in this application is to set up a sample assembly, then place the sample assembly together with the pressure-bearing equipment and run them simultaneously; after a set time interval, take out the sample assembly, and then detect the surface condition of the sample assembly by means of LIBS, and record and store the detected data. The sample assembly is tested and recorded multiple times at the same time interval until the system is shut down. When the system is shut down, the aging conditions of the sample assembly and the in-service equipment are detected separately, also by LIBS.

[0081] The two sets of data are then compared, their deviations are analyzed, and corrections are made based on the deviations so that the data values ​​of the sample components are consistent with those of the in-service equipment.

[0082] After the data set is corrected, a corrected data set is obtained, and the in-service equipment is evaluated through the corrected data set.

[0083] Therefore, the heating surface aging grade evaluation method based on feature migration of the present application can not only easily obtain more data, but also more accurately reflect the actual situation through the corrected data, so as to make a more accurate evaluation; because the amount of data is larger and richer, it can also make a more accurate prediction of the subsequent heating surface aging situation. In other words, the technical solution of the present application is not only more convenient for detection, but also can make a prediction of the same situation.

[0084] In some preferred embodiments, the steps are further included:

[0085] S70, repeating steps S30-S50 to obtain a plurality of correction values ​​at a plurality of time intervals, and obtaining a correction curve according to the plurality of correction values.

[0086] In some preferred embodiments, the steps are further included:

[0087] S80. Establish an aging grade model based on the correction curve.

[0088] In some preferred embodiments, in step S80, the aging grade model is generated according to the correction curve by means of feature migration.

[0089] For the spectrum β (source domain data) of the artificially set sample tube 30 and the spectrum α (target domain data) of the real sample of the in-service equipment, the correlation will be greatly improved after the intensity correction. Then, the polynomial kernel function is used to perform spatial mapping φ to further achieve the goal of feature migration, so that the source domain data and the target domain data after mapping migration have the same or quite close distribution, that is, P(φ(β))≈P(φ(α)). The specific algorithm flow is as follows:

[0090] (1) Introduce the function D that describes the domain distance. For two one-dimensional vector sets X and Y of the same length, we have the following formula:

[0091]

[0092] Where n and m represent the number of vectors. D(X,Y) is the distance between the average vectors of the two vector sets.

[0093] (2) Use polynomial kernel function to perform high-dimensional space mapping, as shown in formula (9).

[0094] κ(x,y)=(αx T y+c) d

[0095] Where x and y are spectral data in two different domains, α is the slope, c is the constant term, and d is the polynomial order.

[0096] (3) Calculate the domain distance between the spectral data of the artificially set sample tube 30 and the spectral data of the real sample of the in-service equipment with the same aging level after mapping.

[0097] D n =D(φ(α n ),φ(β n )), where n represents the aging level

[0098] By changing the parameters of the kernel function and performing iterative calculations, the Dn are as small as possible, and determine the optimal parameters of the multi-form kernel function mapping.

[0099] (4) The optimal kernel mapping function is obtained by solving the optimal parameters, and new spectral data after high-dimensional space mapping is obtained.

[0100] α * =φ(α),β * =φ(β)

[0101] In some preferred embodiments, the method further includes step S90 of evaluating the aging grade of the test sample according to the aging grade model.

[0102] The model building process is the process of establishing the relationship between the spectrum and the aging level. The basic process is to build a model based on the spectrum data of multiple samples with known aging levels, and then use the model to evaluate the aging level of the test object samples. The modeling data source uses the spectrum that has been processed as above.

[0103] Models with good prediction performance often require a large amount of data for training, but it is difficult to obtain LIBS data of real samples of heat-resistant steel in-service equipment. Therefore, there is less spectral data of real samples of in-service equipment, and a small amount of training data will lead to poor training effect of the model. Based on the above spectral correction method, after feature migration of the artificially set sample tube 30 data, the corrected LIBS data of the artificially set sample tube 30 is used as the training set for model training, and the real sample LIBS data of in-service equipment is used as the verification set to debug the model parameters.

[0104] This method uses support vector machine (SVM) to establish a feature analysis model, selects only the characteristic variables of some sample points as support vectors, and maps the training sample data points to a higher dimensional space through the kernel function.

[0105] In addition, because LIBS spectral data contains rich spectral features, it is easy to cause the curse of dimensionality, that is, the number of feature variables is much larger than the number of samples, resulting in sparse sample data in high-dimensional space. Due to the sparsity of samples, the classification model can easily find a complex hyperplane in high-dimensional space, leading to overfitting problems.

[0106] Therefore, in order to improve the prediction and generalization ability of the classification model and better understand the contribution of each variable to the classification model, it is necessary to perform feature selection on the spectral feature variables. Based on recursive feature elimination (RFE), the weight vector coefficients of the learner are used to represent the contribution of the variable to the model, thereby eliminating invalid and redundant variables.

[0107] In the present application, in order to ensure the accuracy of the detected data, each sample tube 30 is numbered, and the placement position and angle of each sample tube 30 are recorded.

[0108] Compared with the existing technology and equipment, the technology of the present invention has the following advantages and beneficial effects:

[0109] (1) In view of interference factors such as surface differences and environmental fluctuations, targeted spectral preprocessing methods are used to reduce the impact of surface scattering, baseline drift, and surface pits on the quality and stability of spectral data, thereby ensuring the stability and effectiveness of spectral characterization of matrix characteristics.

[0110] (2) Through spectral correlation analysis and feature analysis, the LIBS data of the artificially set sample tube 30 of heat-resistant steel is spectrally corrected and data dimension reduced to eliminate redundant feature information and improve the correlation between the spectral data of the artificially set sample tube 30 and the real sample of the in-service equipment.

[0111] (3) The feature mapping matrix is ​​used to map the LIBS data of the artificially set sample tube 30 (source domain data) and the real sample LIBS data of the in-service equipment (target domain data) into a new high-dimensional space. After mapping, the two have the same distribution and retain the original feature information.

[0112] (4) Combining spectral correction and feature mapping, the artificially set sample tube 30 data after feature migration is used as a training set for modeling, and a heat-resistant steel aging grade prediction model based on feature transfer learning is constructed to accurately predict the aging characteristics of real samples of in-service equipment.

[0113] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent application. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application.

Claims

1. A method for evaluating the aging grade of a heated surface based on feature migration, characterized in that: Includes steps: S10, setting a sample assembly; S20, placing a plurality of the sample assemblies in the devices to be tested respectively; S30, taking out the sample assembly at fixed time intervals and performing aging detection to obtain a sample data set; S40, in a shutdown state, respectively detecting the aging conditions of the sample assembly and the in-service equipment, and respectively obtaining the first sample data and the first in-service data at that moment; S50, comparing the first sample data with the first in-service data, and correcting the first sample data using the first in-service data to obtain a corrected value; S60, correcting the sample data set by using the correction value to obtain a corrected data set.

2. The method for evaluating the aging grade of a heated surface based on feature migration according to claim 1, characterized in that: Also includes the steps: S70, repeating steps S30-S50 to obtain a plurality of correction values ​​at a plurality of time intervals, and obtaining a correction curve according to the plurality of correction values.

3. The method for evaluating the aging grade of a heated surface based on feature migration according to claim 2, characterized in that: Also includes the steps: S80. Establish an aging grade model based on the correction curve.

4. The method for evaluating the aging grade of a heated surface based on feature migration according to claim 3 is characterized in that: The sample assembly includes a main pipe, a pressure-bearing end cover, a mounting cover, and a sample pipe; A plurality of mounting holes are formed on the pressure-bearing end cover, and one end of the sample tube is mounted on the mounting hole of the pressure-bearing end cover; The other end of the sample tube passes through and is sleeved on the mounting cover; A plurality of branch through holes are formed in the pressure-bearing end cover, and a main through hole is formed, and the main through hole is respectively connected with the plurality of branch through holes; the plurality of branch through holes are respectively connected with the corresponding mounting holes one by one; The main pipe is connected to the pressure-bearing end cover, and the main pipe is communicated with the main through hole; An inner cavity is formed in the sample tube; The main through hole is communicated with one end of a plurality of branch through holes respectively, and the other end of each branch through hole is communicated with the inner cavity of the sample tube.

5. The method for evaluating the aging grade of a heated surface based on feature migration according to claim 4 is characterized in that: The sample assembly further includes a first fixing column and a second fixing column, wherein the first fixing column is installed in the middle of the pressure-bearing end cover, and the second fixing column is installed in the middle of the mounting cover; one end of the second fixing column is sleeved on the first fixing column; A boss is formed at the end of the sample tube, and the boss abuts against the surface of the mounting cover to prevent the sample tube from being loosened from the mounting cover; A sealing ring is provided at the connection between the sample tube and the mounting hole.

6. The method for evaluating the aging grade of a heated surface based on feature migration according to claim 4 is characterized in that: The sample assembly also includes a mounting seat, and the mounting seat is mounted on the mounting cover; Alternatively, the mounting seat is mounted on the mounting cover and the pressure-bearing end cover.

7. The method for evaluating the aging grade of a heated surface based on feature migration according to any one of claims 1 to 6, characterized in that: In step S30, an aging condition detection is performed, including detecting the aging condition of the heated surface by using LIBS.

8. The method for evaluating the aging grade of a heated surface based on feature migration according to claim 3 is characterized in that: The method further includes step S90 of evaluating the aging grade of the test sample according to the aging grade model.

9. The method for evaluating the aging grade of a heated surface based on feature migration according to claim 3 is characterized in that: In step S80, the aging grade model is generated according to the correction curve by means of feature migration.

Images