SBS modified asphalt performance rapid evaluation method based on phase state structure

Abstract

The invention relates to the field of asphalt performance evaluation, in particular to a rapid evaluation method for SBS modified asphalt performance based on a phase state structure. Aiming at the problem of long asphalt performance evaluation time consumption caused by the existing SBS modified asphalt performance evaluation method, the invention provides the SBS modified asphalt performance rapid evaluation method based on the phase state structure. Constructing an SBS modified asphalt performance evaluation model; obtaining a trained SBS modified asphalt performance evaluation model; acquiring a to-be-evaluated SBS modified asphalt phase structure picture, and inputting the to-be-evaluated SBS modified asphalt phase structure picture into the trained SBS modified asphalt performance evaluation model to obtain a performance result of the to-be-evaluated SBS modified asphalt; test instruments are few in types, test time is short, and asphalt consumption is low. According to the method, rapid evaluation of the high and low temperature performance and the storage stability of the SBS modified asphalt can be realized by only one test, and the problem of long asphalt performance evaluation time consumption caused by an existing SBS modified asphalt performance evaluation method is solved.

Description

Technical Field

[0001] The invention relates to the field of asphalt performance evaluation, and in particular to a method for quickly evaluating the performance of SBS modified asphalt based on phase structure. Background Art

[0002] Asphalt is a temperature-sensitive material, and its performance will change with the change of temperature, so it is easy to deform at high temperature and brittle at low temperature. By adding modifiers, the temperature sensitivity of asphalt can be effectively improved, and its performance can be improved.

[0003] Among many modifiers, SBS (styrene-butadiene-styrene block copolymer) has become one of the most widely used modifiers because it can improve the high and low temperature performance of asphalt at the same time. However, it is found that SBS modified asphalt is prone to segregation during use, resulting in unstable performance. Therefore, in order to ensure the quality and service life of asphalt pavement, the high and low temperature performance and storage stability of SBS modified asphalt should be evaluated. The current test methods are temperature scanning test based on DSR, bending creep stiffness test based on BBR, and polymer modified asphalt segregation test.

[0004] The above-mentioned existing asphalt performance evaluation methods require many types of test instruments, long test time, and a large amount of asphalt. Therefore, it is urgent to propose a method suitable for the rapid evaluation of the high and low temperature performance and storage stability of SBS modified asphalt. Existing studies have shown that the phase structure of SBS modified asphalt can be observed by fluorescence microscopy, and it has a certain relationship with the performance of SBS modified asphalt. Therefore, the performance of SBS modified asphalt can be evaluated based on its phase structure. Previous studies have mostly evaluated its high temperature performance based on the area and particle size of SBS particles in the phase structure, but the morphological characteristics of SBS used are all size characteristics, and the performance studied is relatively single. The distribution characteristics of the phase structure of SBS modified asphalt are not characterized, and the relationship between the phase structure of SBS modified asphalt and its low temperature performance is not considered.

[0005] In summary, the existing SBS modified asphalt performance evaluation methods have the problems of requiring many types of test instruments, long test time, and large asphalt consumption, which often leads to a lag in the performance evaluation of SBS modified asphalt on site. Summary of the invention

[0006] The purpose of the present invention is to solve the problem of long time in the existing SBS modified asphalt performance evaluation method, and propose a SBS modified asphalt performance rapid evaluation method based on phase structure.

[0007] 1. Construct an SBS modified asphalt performance evaluation model; obtain a trained SBS modified asphalt performance evaluation model;

[0008] 2. Collect the phase structure picture of the SBS modified asphalt to be evaluated, input the phase structure picture of the SBS modified asphalt to be evaluated into the trained SBS modified asphalt performance evaluation model, and obtain the performance result of the SBS modified asphalt to be evaluated;

[0009] The performance result data of the SBS modified asphalt include: softening point difference, critical temperature, creep stiffness, and creep rate; the performance results of the SBS modified asphalt applicable to the present invention are not limited to these four, and only some basic performance indicators are listed. Other performance results are also within the protection scope of the present invention.

[0010] The first step is to construct an SBS modified asphalt performance evaluation model; obtain a trained SBS modified asphalt performance evaluation model; the specific process is:

[0011] Step 1: Get the training set;

[0012] Step 2: Construct an SBS modified asphalt performance evaluation model, train the SBS modified asphalt performance evaluation model according to the training set, and obtain a trained SBS modified asphalt performance evaluation model.

[0013] The specific process of obtaining the training set in step 1 is:

[0014] Step 11: Obtain the SBS modified asphalt performance experimental data set;

[0015] Step 1 and 2: Obtain the SBS modified asphalt phase structure diagram data set;

[0016] Step 13: Use the SBS modified asphalt performance experimental data set and the SBS modified asphalt phase structure characteristic parameter data set as training sets;

[0017] The SBS modified asphalt performance evaluation model in step 2 includes: an image preprocessing module, a recognition and quantification module, and a random forest module;

[0018] The specific process of training the SBS modified asphalt performance evaluation model according to the training set to obtain the trained SBS modified asphalt performance evaluation model is as follows:

[0019] S1: Input the SBS modified asphalt phase structure diagram dataset in the training set into the image preprocessing module for image preprocessing to obtain the preprocessed SBS modified asphalt phase structure diagram;

[0020] S2: Input the pre-processed SBS modified asphalt phase structure atlas into the recognition and quantification module to obtain the SBS modified asphalt phase structure characteristic parameter data set;

[0021] S3: The random forest module is trained according to the SBS modified asphalt phase structure characteristic parameter data set and the SBS modified asphalt performance experimental data set to obtain a trained SBS modified asphalt performance evaluation model.

[0022] The random forest module is an existing well-known random forest learning algorithm; the training process is also a conventional training process, the SBS modified asphalt phase structure characteristic parameter data set of the present invention is the input sample, the performance experiment data set is equivalent to the sample label, the trained random forest module inputs the SBS modified asphalt phase structure characteristic parameter data, and outputs the SBS modified asphalt performance data.

[0023] The beneficial effects of the present invention are:

[0024] The SBS modified asphalt evaluation system of the present invention has fewer types of test instruments, a short test time, and a small amount of asphalt. The present invention can achieve a rapid evaluation of the high and low temperature performance and storage stability of SBS modified asphalt with only one test. Compared with conventional asphalt performance evaluation tests, this method requires a small amount of asphalt (<5g), and the test content only requires placing the sample under a fluorescent microscope and photographing the phase structure of the SBS modified asphalt. The rest is automatically processed and calculated by the model, which is simple to operate, short in time, and highly accurate. At the same time, the present invention also provides a film-making method that can stably obtain the real SBS modified asphalt phase structure. This method is different from the traditional hot drop method, as follows:

[0025] After dropping asphalt onto the glass slide, the present invention does not rush to add a cover glass; under the action of the heating table, the asphalt is first made to flow evenly and smoothly, and after the asphalt forms a smooth asphalt film, the cover glass is added. When the cover glass is stable, the sample is removed; although the sample prepared in this way still has an unreal phase structure in which the SBS modifier moves with the cover glass around the sample, the original phase structure of the SBS modified asphalt is still retained in the center of the sample. Therefore, under a fluorescent microscope, the SBS modified asphalt in the center of the sample can be photographed to obtain a real and effective SBS modified asphalt phase structure. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 Schematic diagram of fluorescent images of different positions of the SBS modified asphalt test piece of the present invention;

[0027] Figure 2 The present invention is a flow chart of the performance evaluation of SBS modified asphalt based on phase structure;

[0028] Figure 3 This is a schematic diagram of the image preprocessing, recognition and quantification process of the present invention;

[0029] Figure 4 This is a schematic diagram of the correlation coefficient of characteristic parameters before collinearity screening of the present invention;

[0030] Figure 5 This is a schematic diagram of the correlation coefficient of characteristic parameters after collinearity screening of the present invention;

[0031] Figure 6 It is a schematic diagram of the correlation between the characteristic parameters and the critical temperature of the present invention;

[0032] Figure 7 It is a schematic diagram of the correlation between characteristic parameters and creep stiffness of the present invention;

[0033] Figure 8 It is a schematic diagram of the correlation between characteristic parameters and creep rate of the present invention;

[0034] Fig. 9 It is a schematic diagram of the correlation between the characteristic parameters of the present invention and the softening point difference. DETAILED DESCRIPTION

[0035] Specific implementation method 1: Combination Figure 1 The invention is described, comprising:

[0036] 1. Construct an SBS modified asphalt performance evaluation model; obtain a trained SBS modified asphalt performance evaluation model;

[0037] 2. Collect the phase structure picture of the SBS modified asphalt to be evaluated, input the phase structure picture of the SBS modified asphalt to be evaluated into the trained SBS modified asphalt performance evaluation model, and obtain the performance result of the SBS modified asphalt to be evaluated;

[0038] The performance result data of the SBS modified asphalt include: softening point difference, critical temperature, creep stiffness, and creep rate; the performance results of the SBS modified asphalt applicable to the present invention are not limited to these four, and only some basic performance indicators are listed. Other performance results are also within the protection scope of the present invention.

[0039] The first step is to construct an SBS modified asphalt performance evaluation model; obtain a trained SBS modified asphalt performance evaluation model; the specific process is:

[0040] Step 1: Get the training set;

[0041] Step 2: Construct an SBS modified asphalt performance evaluation model, train the SBS modified asphalt performance evaluation model according to the training set, and obtain a trained SBS modified asphalt performance evaluation model.

[0042] Specific implementation method 2: The difference between this implementation method and specific implementation method 1 is that:

[0043] The specific process of obtaining the training set in step 1 is:

[0044] Step 11: Obtain the SBS modified asphalt performance experimental data set;

[0045] Step 1 and 2: Obtain the SBS modified asphalt phase structure diagram data set;

[0046] Step 13: Use the SBS modified asphalt performance experimental data set and the SBS modified asphalt phase structure characteristic parameter data set as training sets;

[0047] The SBS modified asphalt performance evaluation model in step 2 includes: an image preprocessing module, a recognition and quantification module, and a random forest module;

[0048] The specific process of training the SBS modified asphalt performance evaluation model according to the training set to obtain the trained SBS modified asphalt performance evaluation model is as follows:

[0049] S1: Input the SBS modified asphalt phase structure diagram dataset in the training set into the image preprocessing module for image preprocessing to obtain the preprocessed SBS modified asphalt phase structure diagram;

[0050] S2: Input the pre-processed SBS modified asphalt phase structure atlas into the recognition and quantification module to obtain the SBS modified asphalt phase structure characteristic parameter data set;

[0051] S3: The random forest module is trained according to the SBS modified asphalt phase structure characteristic parameter data set and the SBS modified asphalt performance experimental data set to obtain a trained SBS modified asphalt performance evaluation model.

[0052] The random forest module is an existing well-known random forest learning algorithm; the training process is also a conventional training process, the SBS modified asphalt phase structure characteristic parameter data set of the present invention is the input sample, the performance experiment data set is equivalent to the sample label, the trained random forest module inputs the SBS modified asphalt phase structure characteristic parameter data, and outputs the SBS modified asphalt performance data.

[0053] The other steps and parameters are the same as those in the first specific implementation.

[0054] Specific implementation method three: This implementation method is different from the specific implementation method one in that:

[0055] The SBS modified asphalt performance experimental data set in step 11 includes: SBS modified asphalt high temperature performance data, SBS modified asphalt low temperature performance data and SBS modified asphalt storage stability data;

[0056] The performance data of the SBS modified asphalt include: softening point difference, critical temperature, creep stiffness, creep rate;

[0057] The softening point difference represents storage stability, the critical temperature represents high temperature performance, the creep stiffness and creep rate represent low temperature performance. These are the performance data, which are all very traditional tests for characterizing performance.

[0058] The specific process of obtaining the SBS modified asphalt phase structure diagram data set in steps 1 and 2 is as follows:

[0059] Step 121: Prepare X types of SBS modified asphalt, and prepare an SBS modified asphalt sample preparation for each type of SBS modified asphalt; X is a positive integer; the SBS content in the X types of SBS modified asphalt is different;

[0060] Step 122: extracting N SBS modified asphalt phase structure diagrams from each SBS modified asphalt sample; N is a positive integer, and the value range of N is 5 to 10;

[0061] The other steps and parameters are the same as those in the first to second embodiments.

[0062] Specific implementation method 4: This implementation method is different from specific implementation methods 1 to 4 in that:

[0063] The specific process of making an SBS modified asphalt sample film for one of the SBS modified asphalts in step 121 is as follows: drip the SBS modified asphalt onto a glass slide; under the action of a heating platform, first make the asphalt flow evenly and smoothly, and then cover the asphalt with a cover glass after it forms a smooth asphalt film. When the cover glass is stable, remove the sample; and obtain an SBS modified asphalt sample film;

[0064] The specific process of extracting N SBS modified asphalt phase structure diagrams from one of the SBS modified asphalt samples in step 122 is as follows:

[0065] Step 1221: Place the SBS modified asphalt sample on a fluorescence microscope, and then adjust the fluorescence microscope objective magnification to 10x.

[0066] Step 1222: Turn on the bright light of the fluorescence microscope to focus, turn off the bright light and turn on the fluorescence after a clear field of view is obtained; the excitation wavelength of the fluorescence is set to 488 mm, and the emission wavelength of the fluorescence is 507 mm;

[0067] Step 1223: Use a fluorescence microscope to take a fluorescence picture to obtain a phase structure diagram of SBS modified asphalt, repeat steps 1221 to 1223 N times; obtain N phase structure diagrams of SBS modified asphalt;

[0068] The other steps and parameters are the same as those in the first to third embodiments.

[0069] Specific implementation method 5: This implementation method is different from specific implementation methods 1 to 4 in that:

[0070] In S1, a phase structure diagram of SBS modified asphalt in the training set is input into the image preprocessing module for image preprocessing to obtain a preprocessed phase structure diagram of SBS modified asphalt as follows:

[0071] An SBS modified asphalt phase structure diagram input to the image preprocessing module is filtered, denoised, grayed and binarized in sequence to obtain a preprocessed SBS modified asphalt phase structure diagram.

[0072] The other steps and parameters are the same as those in Specific Embodiments 1 to 4.

[0073] Specific implementation method 6: This implementation method is different from specific implementation methods 1 to 5 in that:

[0074] In S2, the pre-processed SBS modified asphalt phase structure atlas is input into the identification and quantification module to obtain the SBS modified asphalt phase structure characteristic parameter data set; the specific process is:

[0075] S2.1: performing image recognition processing on all pre-processed SBS modified asphalt phase structure images to obtain SBS particle pixels in each pre-processed SBS modified asphalt phase structure image;

[0076] S2.2: Calculate the characteristic values ​​of Y initial characteristic parameters of the SBS particles in each pre-processed SBS modified asphalt phase structure diagram according to the SBS particle pixels in each pre-processed SBS modified asphalt phase structure diagram; Y is a positive integer;

[0077] S2.3: According to the characteristic values ​​of Y initial characteristic parameters of SBS particles in each pre-treated SBS modified asphalt phase structure diagram, the Y initial characteristic parameters are screened to obtain Z screening characteristic parameters; Z is a positive integer;

[0078] S2.4: The characteristic values ​​of the Z screening characteristic parameters of the SBS particles in each pre-processed SBS modified asphalt phase structure diagram are used as the SBS modified asphalt phase structure characteristic parameter data set;

[0079] The other steps and parameters are the same as those in the first to fifth embodiments.

[0080] Specific implementation method 7: This implementation method is different from specific implementation methods 1 to 6 in that:

[0081] In the step S2.2, the characteristic values ​​of Y initial characteristic parameters of the SBS particles in each pre-processed SBS modified asphalt phase structure diagram are calculated according to the SBS particle pixels in each pre-processed SBS modified asphalt phase structure diagram; the specific process is:

[0082] S2.2.1: Based on the SBS particle pixels identified in S2.1, obtain the basic parameters of all SBS particles;

[0083] The basic parameters of the SBS particles include: area, center of mass, position, bounding box, roundness, eccentricity, ellipse major axis, minor axis and perimeter; the pixel size of each SBS particle represents the area of ​​the particle, and other parameters can also be further obtained according to the pixel position, which belongs to conventional image processing technology means;

[0084] S2.2.2: Calculate the characteristic values ​​of the initial characteristic parameters of all SBS particles based on the basic parameters of all SBS particles;

[0085] The Y initial characteristic parameters in S2.2 include:

[0086] Mean of isometric axis ratio, median of isometric axis ratio, standard deviation of isometric axis ratio, coefficient of variation of isometric axis ratio, area-weighted isometric axis ratio, mean of isometric eccentricity, median of isometric eccentricity, standard deviation of isometric eccentricity, coefficient of variation of isometric eccentricity, area-weighted isometric eccentricity, area-weighted isoplanar axis ratio, area-weighted isoplanar eccentricity, mean of isoplanar axis ratio, median of isoplanar axis ratio, standard deviation of isoplanar axis ratio, coefficient of variation of isoplanar axis ratio, mean of isoplanar eccentricity, median of isoplanar eccentricity, standard deviation of isoplanar eccentricity, coefficient of variation of isoplanar eccentricity, number of particles, area-weighted mean axis ratio, standard deviation of area-weighted axis ratio, coefficient of variation of area-weighted axis ratio, total particle area, particle area ratio, mean particle area , median particle area, standard deviation of particle area, coefficient of variation of particle area, average roundness, median roundness, standard deviation of roundness, coefficient of variation of roundness, area-weighted roundness, average diameter of equal-surface circles, median diameter of equal-surface circles, standard deviation of equal-surface circle diameters, coefficient of variation of equal-surface circle diameters, area-weighted diameter of equal-surface circles, average rectangularity, median rectangularity, standard deviation of rectangularity, coefficient of variation of rectangularity, area-weighted rectangularity, average angularity, median angularity, standard deviation of angularity, coefficient of variation of angularity, area-weighted angularity, average area of ​​each unit cell, median area of ​​each unit cell, standard deviation of each unit cell, coefficient of variation of each unit cell area, representative value of the maximum area of ​​the polymer, difference box dimension;

[0087] The initial characteristic parameters of the present invention are actually not limited to these. Any parameter that can characterize the characteristics of the particles is the initial characteristic parameter. The subsequent steps will screen these parameters according to the correlation and other directions.

[0088] The general process of calculating the characteristic value of the characteristic parameter of the SBS particle in one of the pre-processed SBS modified asphalt phase structure diagrams according to the SBS particle pixels in one of the pre-processed SBS modified asphalt phase structure diagrams in S2.2 is:

[0089] According to the relationship between the pixel position, pixel size and actual size of the identified SBS particles, the built-in eigenvalue calculator in MATLAB is input for calculation.

[0090] For example, a pixel represents an actual size of 0.4um; the SBS particle size is the pixel area, and the SBS particle shape is the pixel axis ratio (when it is identified as an ellipse, it is the ratio of the major axis to the minor axis). The SBS particle distribution is to divide the image into 16 identical grids, and then calculate the coefficient of variation of the SBS particle area in each grid. The SBS particle texture is calculated by the difference box dimension. These eigenvalues ​​and the calculation method of eigenvalues ​​are well known to those skilled in the art.

[0091] The other steps and parameters are the same as those in Specific Embodiments 1 to 6.

[0092] Specific implementation eight: This implementation differs from specific implementations one to seven in that:

[0093] In S2.3, according to the characteristic values ​​of Y initial characteristic parameters of SBS particles in each pre-treated SBS modified asphalt phase structure diagram, Y initial characteristic parameters are screened to obtain Z screened initial characteristic parameters; the specific process is:

[0094] S2.3.1: Perform differential screening on Y initial characteristic parameters according to the characteristic values ​​of Y initial characteristic parameters of SBS particles in each phase structure diagram of pretreated SBS modified asphalt to obtain Y1 differentially screened characteristic parameters;

[0095] S2.3.2: Perform collinearity screening on Y1 types of differentially screened characteristic parameters according to the characteristic values ​​of Y1 types of differentially screened characteristic parameters of SBS particles in each pre-treated SBS modified asphalt phase structure diagram, and obtain Y2 types of collinearly screened characteristic parameters;

[0096] S2.3.3: According to the characteristic values ​​of Y2 kinds of collinearly screened characteristic parameters of SBS particles in each pretreated SBS modified asphalt phase structure diagram and the SBS modified asphalt performance experimental data set, correlation screening is performed on Y2 kinds of collinearly screened characteristic parameters to obtain Z kinds of screened characteristic parameters; other steps and parameters are the same as those in specific implementation methods one to seven.

[0097] Specific implementation method 9: This implementation method is different from specific implementation methods 1 to 8 in that:

[0098] In S2.3.1, Y initial characteristic parameters are differentially screened according to the characteristic values ​​of Y initial characteristic parameters of SBS particles in each pre-treated SBS modified asphalt phase structure diagram to obtain Y1 differentially screened characteristic parameters; the specific process is:

[0099] S2.3.1.1: Calculate the coefficient of variation of each initial characteristic parameter, where the coefficient of variation is the coefficient of variation in different SBS modified asphalt conditions.

[0100] Among them, the coefficient of variation Cv of the yth initial characteristic parameter y The calculation formula is expressed as:

[0101] Cv y =S y / M y

[0102] In the formula, S y represents the standard deviation of the y-th initial characteristic parameter, M y represents the average value of the y-th initial characteristic parameter;

[0103] S y and M y They are all calculated based on the eigenvalue of the yth initial characteristic parameter, and the calculation process of the standard deviation and the average value is well known.

[0104] S2.3.1.2: Set a difference threshold, retain the initial feature parameters with a coefficient of variation higher than the difference threshold, and obtain Y1 feature parameters after difference screening;

[0105] The difference threshold is set artificially;

[0106] In S2.3.2, Y1 kinds of differentially screened characteristic parameters are collinearly screened according to the characteristic values ​​of Y1 kinds of differentially screened characteristic parameters of SBS particles in each pre-treated SBS modified asphalt phase structure diagram, to obtain Y2 kinds of collinearly screened characteristic parameters; the specific process is:

[0107] S2.3.2.1: Calculate the collinearity value between each feature parameter after differential screening and the feature parameters after other differential screening;

[0108] Among them, the calculation formula of the collinearity value Vz of the characteristic parameter after the z-th difference screening is:

[0109] When the Pearson correlation coefficients between the characteristic parameters after the z-th difference screening and the characteristic parameters after other difference screening are both less than 0.7, and the VIF indexes between the characteristic parameters after the z-th difference screening and the characteristic parameters after other difference screening are both less than 10, the collinearity value Vz=1, otherwise the collinearity value Vz=0;

[0110] The Pearson correlation coefficient and VIF index are calculated based on the characteristic values ​​of the characteristic parameters after difference screening;

[0111] The calculation formula is well known in the art.

[0112] S2.3.2.2: Remove the feature parameters after difference screening whose collinearity value is 0, and obtain Y2 types of feature parameters after collinearity screening;

[0113] The characteristic values ​​of the characteristic parameters of the SBS particles after Y2 kinds of collinear screening in each pre-treated SBS modified asphalt phase structure diagram in S2.3.3 and the SBS modified asphalt performance experimental data set are used to perform correlation screening on the characteristic parameters after Y2 kinds of collinear screening to obtain Z kinds of initial characteristic parameters after screening. The specific process is as follows:

[0114] S2.3.3.1: The characteristic values ​​of the Y2 collinearity-screened characteristic parameters of the SBS particles in each pre-treated SBS modified asphalt phase structure diagram and the SBS modified asphalt performance experimental data set are plotted, and a scatter plot of the collinearity-screened characteristic parameters and asphalt performance is drawn.

[0115] S2.3.3.2: Fit the scatter plot of the characteristic parameters after collinearity screening and the asphalt performance, and obtain the correlation R between the characteristic parameters after collinearity screening and the asphalt performance 2 ;

[0116] S2.3.3.3: Set correlation threshold; retain correlation R 2 Feature parameters above the correlation threshold, Z types of screening feature parameters;

[0117] The other steps and parameters are the same as those in Specific Embodiments 1 to 8.

[0118] Specific implementation method 10: This implementation method is different from specific implementation methods 1 to 9 in that:

[0119] The specific process of collecting the phase structure picture of the SBS modified asphalt to be evaluated in the second step is:

[0120] 21: Prepare the sample preparation of SBS modified asphalt to be evaluated, place the sample preparation of SBS modified asphalt to be evaluated on a fluorescence microscope, and then adjust the objective lens magnification of the fluorescence microscope to 10x.

[0121] 22: Turn on the bright light of the fluorescence microscope to focus, turn off the bright light and turn on the fluorescence after a clear field of view is obtained; the excitation wavelength of the fluorescence is set to 488 mm, and the emission wavelength of the fluorescence is 507 mm;

[0122] Step 23: Use a fluorescence microscope to take a fluorescence picture to obtain a phase structure diagram of the SBS modified asphalt to be evaluated, repeat steps 1221 to 1223 M times; obtain M phase structure diagrams of the SBS modified asphalt to be evaluated. Other steps and parameters are the same as those in the specific embodiments 1 to 9.

[0123] Combining the simulation analysis of specific implementation methods one to ten

[0124] As shown in Table 1, the present invention provides a method for rapid evaluation of asphalt performance based on the phase structure of SBS modified asphalt. 27 types of SBS modified asphalt were prepared based on different SBS dosages, shearing times and development times, and the phase structure images of SBS modified asphalt were obtained by fluorescence microscopy; the images were substituted into the SBS modified asphalt performance rapid evaluation model to obtain the high and low temperature performance and storage stability of SBS modified asphalt. The present invention accurately characterizes the high temperature performance and storage stability based on the phase structure of SBS modified asphalt, R 2 are 0.987 and 0.952 respectively, which have a good characterization effect on the creep rate m of the low temperature performance index of SBS modified asphalt. 2 is 0.94, but the characterization effect of creep stiffness S of SBS modified asphalt at low temperature is poor. 2 Only 0.81. Among them, the 9th group of SBS modified asphalt has excellent comprehensive performance, with both high and low temperature performance and good storage stability.

[0125]

[0126] Table 1

[0127] The above only describes the preferred embodiments of the present invention. It should be understood that the present invention is not limited to the above specific implementation methods. Although the present invention has been disclosed as above in the preferred embodiments, it is not used to limit the present invention. Any technician familiar with the profession can make some changes or modify the technical contents disclosed above into equivalent embodiments with equivalent changes without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent replacement and improvement made to the above embodiments without departing from the content of the technical solution of the present invention, based on the technical essence of the present invention, within the spirit and principles of the present invention, still fall within the protection scope of the technical solution of the present invention.

Claims

1. A rapid evaluation method for SBS modified asphalt performance based on phase structure, characterized in that: The following steps are involved:

1. Construct an SBS modified asphalt performance evaluation model; obtain a trained SBS modified asphalt performance evaluation model; 2. Collect the phase structure picture of the SBS modified asphalt to be evaluated, input the phase structure picture of the SBS modified asphalt to be evaluated into the trained SBS modified asphalt performance evaluation model, and obtain the performance result of the SBS modified asphalt to be evaluated; The first step is to construct an SBS modified asphalt performance evaluation model; obtain a trained SBS modified asphalt performance evaluation model; the specific process is: Step 1: Get the training set; Step 2: Construct an SBS modified asphalt performance evaluation model, train the SBS modified asphalt performance evaluation model according to the training set, and obtain a trained SBS modified asphalt performance evaluation model.

2. The method for rapid evaluation of SBS modified asphalt performance based on phase structure according to claim 1, characterized in that: The specific process of obtaining the training set in step 1 is: Step 11: Obtain the SBS modified asphalt performance experimental data set; Step 1 and 2: Obtain the SBS modified asphalt phase structure diagram data set; Step 13: Use the SBS modified asphalt performance experimental data set and the SBS modified asphalt phase structure characteristic parameter data set as training sets; The SBS modified asphalt performance evaluation model in step 2 includes: an image preprocessing module, a recognition and quantification module, and a random forest module; The specific process of training the SBS modified asphalt performance evaluation model according to the training set to obtain the trained SBS modified asphalt performance evaluation model is as follows: S1: Input the SBS modified asphalt phase structure diagram dataset in the training set into the image preprocessing module for image preprocessing to obtain the preprocessed SBS modified asphalt phase structure diagram; S2: Input the pre-processed SBS modified asphalt phase structure atlas into the recognition and quantification module to obtain the SBS modified asphalt phase structure characteristic parameter data set; S3: The random forest module is trained according to the SBS modified asphalt phase structure characteristic parameter data set and the SBS modified asphalt performance experimental data set to obtain a trained SBS modified asphalt performance evaluation model.

3. The method for rapid evaluation of SBS modified asphalt performance based on phase structure according to claim 2, characterized in that: The specific process of obtaining the SBS modified asphalt phase structure diagram data set in steps 1 and 2 is as follows: Step 121: Prepare X types of SBS modified asphalt, and prepare an SBS modified asphalt sample preparation for each type of SBS modified asphalt; X is a positive integer; the SBS content in the X types of SBS modified asphalt is different; Step 122: Extract N SBS modified asphalt phase structure diagrams for each SBS modified asphalt sample preparation; N is a positive integer, and the value range of N is 5 to 10.

4. The method for rapid evaluation of SBS modified asphalt performance based on phase structure according to claim 3 is characterized in that: The specific process of extracting N SBS modified asphalt phase structure diagrams from one of the SBS modified asphalt samples in step 122 is as follows: Step 1221: Place the SBS modified asphalt sample on a fluorescence microscope, and then adjust the fluorescence microscope objective magnification to 10x. Step 1222: turning on the bright light of the fluorescence microscope for focusing, and after focusing, turning off the bright light and turning on the fluorescence; the excitation wavelength of the fluorescence is set to 488 mm, and the emission wavelength of the fluorescence is 507 mm; Step 1223: Use a fluorescence microscope to take a fluorescence picture to obtain a phase structure diagram of SBS modified asphalt, repeat steps 1221 to 1223 N times; obtain N phase structure diagrams of SBS modified asphalt.

5. The method for rapid evaluation of SBS modified asphalt performance based on phase structure according to claim 4 is characterized in that: In S1, a phase structure diagram of SBS modified asphalt in the training set is input into the image preprocessing module for image preprocessing to obtain a preprocessed phase structure diagram of SBS modified asphalt as follows: An SBS modified asphalt phase structure diagram input to the image preprocessing module is filtered, denoised, grayed and binarized in sequence to obtain a preprocessed SBS modified asphalt phase structure diagram.

6. The method for rapid evaluation of SBS modified asphalt performance based on phase structure according to claim 5, characterized in that: In said S2, the pre-processed SBS modified asphalt phase structure atlas is input into the identification and quantification module to obtain a SBS modified asphalt phase structure characteristic parameter data set; The specific process is: S2.1: performing image recognition processing on all pre-processed SBS modified asphalt phase structure images to obtain SBS particle pixels in each pre-processed SBS modified asphalt phase structure image; S2.2: Calculate the characteristic values ​​of Y initial characteristic parameters of the SBS particles in each pre-processed SBS modified asphalt phase structure diagram according to the SBS particle pixels in each pre-processed SBS modified asphalt phase structure diagram; Y is a positive integer; S2.3: According to the characteristic values ​​of Y initial characteristic parameters of SBS particles in each pre-treated SBS modified asphalt phase structure diagram, the Y initial characteristic parameters are screened to obtain Z screening characteristic parameters; Z is a positive integer; S2.4: The characteristic values ​​of the Z screening characteristic parameters of the SBS particles in each pre-processed SBS modified asphalt phase structure diagram are used as the SBS modified asphalt phase structure characteristic parameter data set.

7. A method for rapid evaluation of SBS modified asphalt performance based on phase structure according to claim 6, characterized in that: In said S2.2, according to the SBS particle pixels in each pre-processed SBS modified asphalt phase structure diagram, characteristic values ​​of Y initial characteristic parameters of the SBS particles in each pre-processed SBS modified asphalt phase structure diagram are calculated; The specific process is: S2.2.1: Based on the SBS particle pixels identified in S2.1, obtain the basic parameters of all SBS particles; S2.2.2: Calculate the characteristic values ​​of the initial characteristic parameters of all SBS particles based on the basic parameters of all SBS particles.

8. The method for rapid evaluation of SBS modified asphalt performance based on phase structure according to claim 7, characterized in that: In said S2.3, according to the characteristic values ​​of Y initial characteristic parameters of SBS particles in each pre-treated SBS modified asphalt phase structure diagram, Y initial characteristic parameters are screened to obtain Z screened initial characteristic parameters; The specific process is: S2.3.1: Perform differential screening on Y initial characteristic parameters according to the characteristic values ​​of Y initial characteristic parameters of SBS particles in each phase structure diagram of pretreated SBS modified asphalt to obtain Y1 differentially screened characteristic parameters; S2.3.2: Perform collinearity screening on Y1 types of differentially screened characteristic parameters according to the characteristic values ​​of Y1 types of differentially screened characteristic parameters of SBS particles in each pre-treated SBS modified asphalt phase structure diagram, and obtain Y2 types of collinearly screened characteristic parameters; S2.3.3: According to the characteristic values ​​of Y2 collinearly screened characteristic parameters of SBS particles in each pre-treated SBS modified asphalt phase structure diagram and the SBS modified asphalt performance experimental data set, correlation screening is performed on Y2 collinearly screened characteristic parameters to obtain Z screened characteristic parameters.

9. The method for rapid evaluation of SBS modified asphalt performance based on phase structure according to claim 8, characterized in that: In S2.3.1, Y initial characteristic parameters are differentially screened according to the characteristic values ​​of Y initial characteristic parameters of SBS particles in each pre-treated SBS modified asphalt phase structure diagram to obtain Y1 differentially screened characteristic parameters; the specific process is: S2.3.1.1: Calculate the coefficient of variation of each initial characteristic parameter, where the coefficient of variation is the coefficient of variation in different SBS modified asphalt conditions. Among them, the coefficient of variation Cv of the yth initial characteristic parameter y The calculation formula is expressed as: Cv y =S y / M y In the formula, S y represents the standard deviation of the y-th initial characteristic parameter, M y represents the average value of the y-th initial characteristic parameter; S y and M y are calculated based on the eigenvalues ​​of the yth initial characteristic parameters. S2.3.1.2: Set a difference threshold, retain the initial feature parameters with a coefficient of variation higher than the difference threshold, and obtain Y1 feature parameters after difference screening; In S2.3.2, Y1 kinds of differentially screened characteristic parameters are collinearly screened according to the characteristic values ​​of Y1 kinds of differentially screened characteristic parameters of SBS particles in each pre-treated SBS modified asphalt phase structure diagram, to obtain Y2 kinds of collinearly screened characteristic parameters; the specific process is: S2.3.2.1: Calculate the collinearity value between each feature parameter after differential screening and the feature parameters after other differential screening; Among them, the calculation formula of the collinearity value Vz of the characteristic parameter after the z-th difference screening is: When the Pearson correlation coefficients between the characteristic parameters after the z-th difference screening and the characteristic parameters after other difference screening are both less than 0.7, and the VIF indexes between the characteristic parameters after the z-th difference screening and the characteristic parameters after other difference screening are both less than 10, the collinearity value Vz=1, otherwise the collinearity value Vz=0; The Pearson correlation coefficient and VIF index are calculated based on the characteristic values ​​of the characteristic parameters after difference screening; S2.3.2.2: Remove the feature parameters after difference screening whose collinearity value is 0, and obtain Y2 types of feature parameters after collinearity screening; The characteristic values ​​of the characteristic parameters of the SBS particles after Y2 kinds of collinear screening in each pre-treated SBS modified asphalt phase structure diagram in S2.3.3 and the SBS modified asphalt performance experimental data set are used to perform correlation screening on the characteristic parameters after Y2 kinds of collinear screening to obtain Z kinds of initial characteristic parameters after screening. The specific process is as follows: S2.3.3.1: The characteristic values ​​of the characteristic parameters of the SBS particles after Y2 kinds of collinear screening in each phase structure diagram of the pre-treated SBS modified asphalt and the experimental data set of the performance of the SBS modified asphalt are plotted, and the scatter plot of the characteristic parameters after collinear screening and the asphalt performance is drawn; S2.3.3.2: Fit the scatter plot of the characteristic parameters after collinearity screening and the asphalt performance, and obtain the correlation R between the characteristic parameters after collinearity screening and the asphalt performance 2 ; S2.3.3.3: Set correlation threshold; retain correlation R 2 Feature parameters above the correlation threshold are Z screening feature parameters.

10. A method for rapid evaluation of SBS modified asphalt performance based on phase structure according to claim 9, characterized in that: The specific process of collecting the phase structure picture of the SBS modified asphalt to be evaluated in the second step is: 21: Prepare a sample preparation of the SBS modified asphalt to be evaluated, place the sample preparation of the SBS modified asphalt to be evaluated on a fluorescence microscope, and then adjust the objective lens magnification of the fluorescence microscope to 10x; 22: Turn on the bright light of the fluorescence microscope to focus, turn off the bright light after focusing and turn on the fluorescence; the excitation wavelength of the fluorescence is set to 488mm, and the emission wavelength of the fluorescence is 507mm; 23: Use a fluorescence microscope to take a fluorescence picture to obtain a phase structure diagram of the SBS modified asphalt to be evaluated, and repeat steps 1221 to 1223 M times; M phase structure diagrams of SBS modified asphalt to be evaluated are obtained.

Images