Method and device for predicting the adhesion of an aggregate to bitumen

Abstract

This invention provides a method and apparatus for predicting the adhesion of aggregate-asphalt interfaces. The method includes: acquiring multiple sets of sample data of the aggregate-asphalt interface; each set of sample data contains multiple independent variables and corresponding dependent variables. The independent variables include the wetting work of high-temperature molten asphalt-aggregate during the spreading process of high-temperature molten asphalt on the aggregate surface, the adhesion work of room-temperature solid asphalt-aggregate during the contact process between room-temperature solid asphalt and aggregate, and the depth of asphalt filling the aggregate pores during the interlocking-anchoring process of room-temperature solid asphalt and aggregate; the dependent variable is the pull-out strength of the aggregate-asphalt interface; determining an interface adhesion prediction model based on gene expression programming, multiple independent variables, and dependent variables; and predicting the adhesion of the aggregate-asphalt interface based on the interface adhesion prediction model. This invention improves the accuracy of aggregate-asphalt interface adhesion prediction.

Description

Technical Field

[0001] This invention relates to the field of road engineering technology, and specifically to a method and apparatus for predicting the adhesion of aggregates to asphalt interfaces. Background Technology

[0002] Asphalt pavement, due to its advantages such as driving comfort, low noise, short construction period, and good mechanical properties, has become the most common structural form for highways. However, with the rapid development of my country's economy and the dramatic increase in traffic volume, asphalt pavements are constantly subjected to speeding and overloading, making them highly susceptible to early-stage defects such as loosening, spalling, and potholes. Asphalt mixtures can be considered as non-homogeneous three-phase composite materials composed of an asphalt phase, an aggregate phase, and an interfacial phase between the aggregate and asphalt. The interfacial phase, as the weakest part of the asphalt mixture structure, directly affects the stability of the asphalt mixture structure. Therefore, accurately evaluating the interfacial adhesion between aggregates and asphalt is of great significance for constructing long-life asphalt pavements.

[0003] Currently, researchers both domestically and internationally have conducted extensive studies, resulting in the development of several theories from a microscopic perspective, including micromechanical theory, chemical reaction theory, molecular orientation theory, electrostatic theory, surface energy theory, and mechanical interlocking theory. While these theories—micromechanical, chemical reaction, molecular orientation, and electrostatic—can explain the causes of aggregate-asphalt interfacial adhesion from different angles, in practical research, they are more suitable for qualitative analysis of the adhesion mechanism and are less effective at quantitatively describing aggregate-asphalt adhesion using a single evaluation parameter. Although surface energy and mechanical interlocking theories can quantitatively describe aggregate-asphalt interfacial adhesion, they each only partially consider the bonding capacity generated by asphalt-aggregate contact and wetting, and the mechanical interlocking force generated by the interlocking-anchoring structure, thus failing to comprehensively evaluate aggregate-asphalt interfacial adhesion.

[0004] Therefore, there is an urgent need to provide a method and apparatus for predicting the adhesion of aggregates to asphalt interfaces to solve the above-mentioned technical problems. Summary of the Invention

[0005] In view of this, it is necessary to provide a method and apparatus for predicting the adhesion of aggregates to asphalt interfaces, so as to solve the technical problem that the existing technology cannot accurately predict the adhesion of aggregates to asphalt interfaces.

[0006] On one hand, this invention provides a method for predicting the adhesion of aggregates to asphalt interfaces. The formation process of the adhesion of aggregates to asphalt interfaces includes the spreading process of high-temperature molten asphalt on the aggregate surface, the contact process between room-temperature solid asphalt and aggregates, and the interlocking-anchoring process between room-temperature solid asphalt and aggregates. The method for predicting the adhesion of aggregates to asphalt interfaces includes:

[0007] Multiple sets of sample data of the aggregate-asphalt interface are obtained, and each set of sample data contains multiple independent variables and a dependent variable corresponding to the multiple independent variables. The multiple independent variables include the high-temperature molten asphalt-aggregate wetting work during the spreading process of the high-temperature molten asphalt on the aggregate surface, the room-temperature solid asphalt-aggregate adhesion work during the contact process between the room-temperature solid asphalt and the aggregate, and the asphalt filling depth of the aggregate pores during the interlocking-anchoring process of the room-temperature solid asphalt and the aggregate. The dependent variable is the pull-out strength of the aggregate-asphalt interface.

[0008] A predictive model for interface adhesion is determined based on gene expression programming, the multiple independent variables, and the dependent variable.

[0009] The adhesion between aggregate and asphalt is predicted based on the aforementioned interfacial adhesion prediction model.

[0010] In some possible implementations, obtaining multiple sets of sample data of the aggregate-asphalt interface includes:

[0011] Multiple types of asphalt, multiple types of aggregates, and multiple contact temperatures are obtained, and multiple test schemes are determined based on the multiple types of asphalt, the multiple types of aggregates, and the multiple contact temperatures;

[0012] Determine the high-temperature molten asphalt-aggregate wetting work during the spreading process of high-temperature molten asphalt on the aggregate surface in each group of test schemes;

[0013] Determine the adhesion work of room temperature solid asphalt-aggregate during the contact process between room temperature solid asphalt and aggregate in each group of test schemes;

[0014] Determine the depth of asphalt filling aggregate pores during the interlocking-anchoring process of room temperature solid asphalt and aggregate in the test schemes described in each group;

[0015] The pull-out strength of the aggregate-asphalt interface in each test scheme was determined based on mechanical tensile tests.

[0016] In some possible implementations, determining the high-temperature molten asphalt-aggregate wetting work during the spreading process of the high-temperature molten asphalt on the aggregate surface in each group of the test schemes includes:

[0017] The surface energy of the high-temperature molten asphalt during the spreading process on the aggregate surface in each group of test schemes was obtained, and the contact angle between the high-temperature molten asphalt and the aggregate was obtained;

[0018] The wetting work of the high-temperature molten asphalt-aggregate is determined based on the surface energy and the contact angle.

[0019] In some possible implementations, determining the work of adhesion between room-temperature solid asphalt and aggregate during the contact process in each group of test schemes includes:

[0020] Obtain the total surface energy of the asphalt and the total surface energy of the aggregate during the process from molten asphalt to solid asphalt at room temperature in each group of test schemes;

[0021] The adhesion work of the asphalt-aggregate solid at room temperature is determined based on the total surface energy of the asphalt and the total surface energy of the aggregate.

[0022] In some possible implementations, determining the depth of asphalt filling the aggregate pores during the interlocking-anchoring process of room-temperature solid asphalt and aggregate in each group of the test schemes includes:

[0023] The surface tension of the high-temperature molten asphalt, the contact angle between the high-temperature molten asphalt and the aggregate, and the average pore size of the aggregate within the pore size range of the adsorbed asphalt were obtained in each group of test schemes.

[0024] The depth of the asphalt-filled aggregate pores is determined based on the surface tension, the contact angle, and the average pore size of the aggregate.

[0025] In some possible implementations, the method of determining the interface adhesion prediction model based on gene expression programming, the multiple independent variables, and the dependent variable includes:

[0026] Step 1: Determine the operator, gene header length, number of genes, and population size;

[0027] Step 2: Create an initial population based on the operator, the gene head length, the number of genes, the population size, and the multiple independent variables; the initial population includes multiple chromosomes, each chromosome being composed of genes;

[0028] Step 3: Convert the multiple chromosomes into expression trees, and determine the initial interface adhesion prediction model based on the expression trees;

[0029] Step 4: Decode each chromosome to obtain a decoded expression, and determine the fitness value of each chromosome based on the decoded expression, the fitness function, and the dependent variable;

[0030] Step 5: Determine whether the fitness value is greater than the fitness threshold;

[0031] Step 6: When the fitness value is greater than or equal to the fitness threshold, the initial interface adhesion prediction model is the interface adhesion prediction model.

[0032] Step 7: When the fitness value is less than the fitness threshold, perform selection, mutation, transposition and recombination operations on the multiple chromosomes to obtain multiple evolutionary chromosomes, and return to step 3 to execute steps 3 to 7.

[0033] In some possible implementations, the fitness function is:

[0034]

[0035] In the formula, f i C represents the fitness value. i For multiple sets of sample data; T j C represents the dependent variable value in the j-th sample data; (i,j) M represents the predicted value of the dependent variable determined based on the initial interface adhesion prediction model; M is a selection range constant.

[0036] In some possible implementations, the interface adhesion prediction model is as follows:

[0037] POST=x2(x1+x3+0.5007)+0.7448x3-0.0548

[0038] In the formula, POST is the pull-out strength; x1 is the wetting work of the high-temperature molten asphalt-aggregate; x2 is the adhesion work of the room-temperature solid asphalt-aggregate; and x3 is the depth of asphalt filling the aggregate pores.

[0039] In some possible implementations, prior to the determination of the interface adhesion prediction model based on the gene expression programming method, the multiple independent variables, and the dependent variable, the following additional steps are included:

[0040] Determine multiple correlation coefficients among the multiple independent variables;

[0041] The significance of the multiple correlation coefficients was verified, and multiple significant values ​​were obtained.

[0042] The correlation between the multiple independent variables is determined based on the multiple significant values.

[0043] On the other hand, the present invention also provides an aggregate-asphalt interface adhesion prediction device. The formation process of aggregate-asphalt interface adhesion includes a high-temperature molten asphalt spreading process on the aggregate surface, a room-temperature solid asphalt contact process with the aggregate, and a room-temperature solid asphalt interlocking-anchoring process with the aggregate. The aggregate-asphalt interface adhesion prediction device includes:

[0044] The sample data acquisition unit is used to acquire multiple sets of sample data of the aggregate-asphalt interface, each set of sample data having multiple independent variables and a dependent variable corresponding to the multiple independent variables; the multiple independent variables include the high-temperature molten asphalt-aggregate wetting work during the spreading process of the high-temperature molten asphalt on the aggregate surface, the room-temperature solid asphalt-aggregate adhesion work during the contact process between the room-temperature solid asphalt and the aggregate, and the asphalt filling depth of the aggregate pores during the interlocking-anchoring process of the room-temperature solid asphalt and the aggregate; the dependent variable is the pull-out strength of the aggregate-asphalt interface.

[0045] A prediction model determination unit is used to determine an interface adhesion prediction model based on gene expression programming, the multiple independent variables, and the dependent variable.

[0046] The adhesion prediction unit is used to predict the adhesion between aggregate and asphalt interface based on the interface adhesion prediction model.

[0047] The beneficial effects of adopting the above implementation method are as follows: The aggregate-aggregate interface adhesion prediction method provided by this invention, by setting independent variables in the sample data including the high-temperature molten asphalt-aggregate wetting work during the spreading of high-temperature molten asphalt on the aggregate surface, the room-temperature solid asphalt-aggregate adhesion work during the contact process between room-temperature solid asphalt and aggregate, and the asphalt filling depth of aggregate pores during the interlocking-anchoring process of room-temperature solid asphalt and aggregate, considers the entire process of asphalt-aggregate interface adhesion formation, namely: high-temperature mixing and wetting, room-temperature contact bonding, and interlocking-anchoring process, thereby improving the comprehensiveness and rationality of the sample data and thus improving the accuracy of aggregate-aggregate interface adhesion prediction. Furthermore, by using the high-temperature molten asphalt-aggregate wetting work under the surface energy theory, the room-temperature solid asphalt-aggregate adhesion work, and the asphalt filling depth of aggregate pores under the mechanical interlocking theory as microscopic evaluation parameters characterizing the adhesion of the asphalt-aggregate interface, the inherent biases of the two theories can be eliminated, thereby further improving the accuracy of aggregate-aggregate interface adhesion prediction.

[0048] Furthermore, this invention uses pull-out strength as the dependent variable, that is, it uses pull-out strength as a macroscopic performance index characterizing the adhesion between aggregate and asphalt interface, which intuitively reflects the interface adhesion strength, takes into account the role of asphalt filling the pore depth of aggregate, and ensures the rationality of the prediction of the adhesion between aggregate and asphalt interface.

[0049] Furthermore, this invention uses gene expression programming, multiple independent variables, and dependent variables to determine the interface adhesion prediction model. It can obtain a highly accurate interface adhesion prediction model without requiring a large amount of data, and it does not require the assumption of a relational model. At the same time, it does not require the independent variables to be independent of each other, which can improve the determination efficiency and accuracy of the interface adhesion prediction model. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 A schematic flowchart of an embodiment of the method for predicting the adhesion of aggregates to asphalt interfaces provided by the present invention;

[0052] Figure 2 For the present invention Figure 1 A schematic diagram of an embodiment of S101;

[0053] Figure 3 For the present invention Figure 1 A schematic diagram of an embodiment of S102;

[0054] Figure 4 This is a schematic flowchart of an embodiment of the present invention for verifying the correlation and significance of multiple independent variables;

[0055] Figure 5 A schematic diagram of an embodiment of the aggregate-asphalt interface adhesion prediction device provided by the present invention;

[0056] Figure 6 A schematic diagram of an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0057] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0058] It should be understood that the illustrative drawings are not drawn to scale. The flowcharts used in this invention illustrate operations implemented according to some embodiments of the invention. It should be understood that the operations in the flowcharts may be implemented out of order, and steps without logical contextual relationships may be reversed or performed simultaneously. Furthermore, those skilled in the art, guided by the content of this invention, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor systems and / or microcontroller systems.

[0059] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0060] This invention provides a method and apparatus for predicting the adhesion of aggregates to asphalt interfaces, which will be described below.

[0061] First, it should be noted that the formation process of the adhesion between aggregate and asphalt includes the process of high-temperature molten asphalt spreading on the surface of aggregate, the process of contact between room-temperature solid asphalt and aggregate, and the process of interlocking and anchoring room-temperature solid asphalt and aggregate.

[0062] Figure 1 A schematic flowchart of an embodiment of the aggregate-asphalt interface adhesion prediction method provided by the present invention is shown below. Figure 1 As shown, the methods for predicting the adhesion between aggregates and asphalt interfaces include:

[0063] S101. Obtain multiple sets of sample data of the aggregate-asphalt interface; each set of sample data has multiple independent variables and dependent variables corresponding to the multiple independent variables. The multiple independent variables include the high-temperature molten asphalt-aggregate wetting work during the high-temperature molten asphalt spreading process on the aggregate surface, the normal temperature solid asphalt-aggregate adhesion work during the normal temperature solid asphalt-aggregate contact process, and the asphalt filling aggregate pore depth during the normal temperature solid asphalt-aggregate interlocking-anchoring process. The dependent variable is the pull-out strength of the aggregate-asphalt interface.

[0064] S102. A prediction model for interface adhesion based on gene expression programming method, multiple independent variables and dependent variables;

[0065] S103. Predict the adhesion between aggregate and asphalt interface based on the interfacial adhesion prediction model.

[0066] Compared with existing technologies, the aggregate-aggregate interface adhesion prediction method provided in this invention, by setting independent variables in the sample data including the high-temperature molten asphalt-aggregate wetting work during the spreading of high-temperature molten asphalt on the aggregate surface, the room-temperature solid asphalt-aggregate adhesion work during the contact process between room-temperature solid asphalt and aggregate, and the asphalt filling depth of aggregate pores during the interlocking-anchoring process of room-temperature solid asphalt and aggregate, considers the entire process of asphalt-aggregate interface adhesion formation, namely: high-temperature mixing and wetting, room-temperature contact bonding, and interlocking-anchoring process. This improves the comprehensiveness and rationality of the sample data, thereby improving the accuracy of aggregate-aggregate interface adhesion prediction. Furthermore, by using the high-temperature molten asphalt-aggregate wetting work under the surface energy theory, the room-temperature solid asphalt-aggregate adhesion work, and the asphalt filling depth of aggregate pores under the mechanical interlocking theory as microscopic evaluation parameters characterizing the adhesion of the asphalt-aggregate interface, the inherent biases of the two theories can be eliminated, thereby further improving the accuracy of aggregate-aggregate interface adhesion prediction.

[0067] Furthermore, in this embodiment of the invention, pull-out strength is used as the dependent variable, that is, pull-out strength is used as a macroscopic performance index characterizing the adhesion between aggregate and asphalt interface, which intuitively reflects the interface adhesion strength, takes into account the role of asphalt filling the pore depth of aggregate, and ensures the rationality of the prediction of the adhesion between aggregate and asphalt interface.

[0068] Furthermore, the embodiments of the present invention determine the interface adhesion prediction model based on gene expression programming, multiple independent variables and dependent variables. It can obtain a highly accurate interface adhesion prediction model without a large amount of data, and does not require the assumption of a relational model. At the same time, it does not require the independent variables to be independent of each other, which can improve the determination efficiency and accuracy of the interface adhesion prediction model.

[0069] In some embodiments of the present invention, such as Figure 2 As shown, step S101 includes:

[0070] S201. Obtain multiple types of asphalt, multiple types of aggregates, and multiple contact temperatures, and determine multiple test schemes based on multiple types of asphalt, multiple types of aggregates, and multiple contact temperatures;

[0071] S202. Determine the high-temperature molten asphalt-aggregate wetting work during the spreading process of high-temperature molten asphalt on the aggregate surface in each group of test schemes;

[0072] S203. Determine the adhesion work of room temperature solid asphalt-aggregate during the contact process between room temperature solid asphalt and aggregate in each group of test schemes.

[0073] S204. Determine the depth of asphalt filling aggregate pores during the interlocking-anchoring process of room temperature solid asphalt and aggregate in each group of test schemes.

[0074] S205. Determine the pull-out strength of the aggregate-asphalt interface in each test scheme based on mechanical tensile tests.

[0075] That is, each test scheme serves as a set of sample data, and each set of sample data includes the high-temperature molten asphalt-aggregate impregnation work, the room-temperature solid asphalt-aggregate adhesion work, the depth of asphalt filling aggregate pores, and the pull-out strength.

[0076] In specific embodiments of the present invention, the asphalt types include, but are not limited to, 70# base asphalt and SBS modified asphalt, the aggregate types include, but are not limited to, limestone, diabase, granite and andesite, and the contact temperatures include, but are not limited to, 130°C, 150°C and 170°C.

[0077] In some embodiments of the present invention, step S202 includes:

[0078] The surface energy of high-temperature molten asphalt during the spreading process on the aggregate surface in each test scheme was obtained, and the contact angle between high-temperature molten asphalt and aggregate was obtained;

[0079] The wetting work of high-temperature molten asphalt-aggregate is determined based on surface energy and contact angle.

[0080] In a specific embodiment of the present invention, the high-temperature molten asphalt-aggregate impregnation work is shown in Table 1:

[0081] Table 1. High-Temperature Melting Asphalt – Aggregate Impregnation Energy

[0082]

[0083]

[0084] In some embodiments of the present invention, step S203 includes:

[0085] Obtain the total surface energy of asphalt and the total surface energy of aggregates during the process from molten asphalt to solid asphalt at room temperature in each test scheme.

[0086] The adhesion work of solid asphalt-aggregate at room temperature is determined based on the total surface energy of asphalt and the total surface energy of aggregate.

[0087] In a specific embodiment of the present invention, the adhesion work of solid asphalt-aggregate at room temperature is shown in Table 2:

[0088] Table 2. Adhesion work of solid asphalt at room temperature and aggregates

[0089]

[0090] In some embodiments of the present invention, step S204 includes:

[0091] The surface tension of the high-temperature molten asphalt, the contact angle between the high-temperature molten asphalt and the aggregate, and the average pore size of the aggregate within the pore size range of the adsorbed asphalt were obtained in each group of test schemes.

[0092] The pore depth of asphalt-filled aggregates is determined based on surface tension, contact angle, and average pore size of the aggregates. In a specific embodiment of the present invention, the pore depth of asphalt-filled aggregates is shown in Table 3:

[0093] Table 3 Pore Depth of Asphalt-Filled Aggregates

[0094]

[0095] In a specific embodiment of the present invention, the pull-out strength in step S205 is shown in Table 4:

[0096] Table 4 Pull-out Strength

[0097]

[0098]

[0099] In some embodiments of the present invention, such as Figure 3 As shown, step S102 includes:

[0100] S301, Determine the operator, gene header length, number of genes, and population size;

[0101] S302. Create an initial population based on operators, gene head length, number of genes, population size, and multiple independent variables; the initial population includes multiple chromosomes, each chromosome being composed of genes;

[0102] S303. Transform multiple chromosomes into expression trees and determine an initial interface adhesion prediction model based on the expression trees;

[0103] S304. Decode each chromosome to obtain the decoded expression, and determine the fitness value of each chromosome based on the decoded expression, fitness function, and dependent variable.

[0104] S305. Determine whether the fitness value is greater than the fitness threshold.

[0105] S306. When the fitness value is greater than or equal to the fitness threshold, the initial interface adhesion prediction model is the interface adhesion prediction model.

[0106] S307. When the fitness value is less than the fitness threshold, perform selection, mutation, transposition and recombination operations on multiple chromosomes to obtain multiple evolved chromosomes, and return to S303 to execute S303 to S307.

[0107] It should be understood that, in order to avoid the training being unable to end in case the fitness threshold is set too high or other situations, in some embodiments of the present invention, training is also terminated when the number of chromosome evolutions exceeds the maximum number of iterations, and the prediction model corresponding to the last generation of chromosomes is an interface adhesion prediction model.

[0108] It should be understood that a gene consists of a head and a tail. When generating a gene, the gene head should be randomly generated using operators and terminal symbols, and the gene tail should be randomly generated using terminal symbols. The length of the gene head and the length of the gene tail need to satisfy the following relationship in order to legally decode the chromosome.

[0109] N 尾部 =N 头部 ×(n-1)+1

[0110] In the formula, N 尾部 N represents the length of the gene tail. 头部 is the length of the gene header; n is the maximum number of operators.

[0111] Terminal symbols include both numerical values ​​of the independent variable and the constant value. Operators include, but are not limited to, +, -, ×, / , ln, sqrt, etc.

[0112] In a specific embodiment of the present invention, the selection operation in step S307 is any one of the selection algorithms such as betting pool selection, deterministic selection, tournament selection, etc.

[0113] The mutation operation involves randomly selecting a chromosome from the population, then randomly selecting a gene from the chromosome, and finally randomly selecting a location from the gene to mutate.

[0114] Transposition operations include, but are not limited to, IS transposition, RIS transposition, and gene transposition. IS transposition involves randomly selecting a chromosome from the population, randomly selecting an IS length from the IS transposition length, selecting a gene segment of that IS length on the chromosome, and randomly selecting a gene to insert into the head portion of the chromosome, excluding the first element. RIS transposition involves randomly selecting a point in the head portion of the chromosome and searching backwards along the gene until a function is found. This function becomes the starting position of the RIS element. If no function is found, the transposition does not perform any operation. Gene transposition only changes the position of the gene within the same chromosome.

[0115] In a specific embodiment of the present invention, the parameter settings in the gene expression programming method in step S102 are shown in Table 5:

[0116] Table 5. Parameter settings in gene expression programming.

[0117]

[0118]

[0119] Considering the significant differences in the magnitudes of different variables in the sample data of this embodiment, the fitness function is a relative error fitness function, specifically expressed as:

[0120]

[0121] In the formula, f i C represents the fitness value. i For multiple sets of sample data; T j C represents the dependent variable value in the j-th sample data; (i,j) is the predicted value of the dependent variable determined based on the initial interface adhesion prediction model; M is the selection range constant.

[0122] The interface adhesion prediction model determined based on the above process is as follows:

[0123] POST=x2(x1+x3+0.5007)+0.7448x3-0.0548

[0124] In the formula, POST is the pull-out strength; x1 is the high-temperature molten asphalt-aggregate impregnation work; x2 is the room-temperature solid asphalt-aggregate adhesion work; and x3 is the depth of asphalt filling the aggregate pores.

[0125] Since the prerequisite for gene expression programming is that there cannot be a significant correlation between independent variables, therefore, as Figure 4 As shown, before step S102, the procedure further includes:

[0126] S401. Determine multiple correlation coefficients among multiple independent variables;

[0127] S402. Perform significance testing on multiple correlation coefficients to obtain multiple significance values ​​(P-values);

[0128] S403. Determine the correlation between multiple independent variables based on multiple significant values.

[0129] Specifically: when the correlation between multiple independent variables is not significant, step S102 is then performed to ensure the accuracy of the determined interface adhesion prediction model.

[0130] It should be noted that the correlation coefficient can be the Pearson correlation coefficient and / or the Spearman correlation coefficient.

[0131] In a specific embodiment of the present invention, the Pearson correlation coefficient and significance test results are shown in Table 6, and the Spearman correlation coefficient and significance test results are shown in Table 7.

[0132] Table 6. Pearson correlation coefficient and significance test results.

[0133]

[0134] Table 7. Spearman correlation coefficient and significance test results.

[0135]

[0136] With a significance level of 0.05, Tables 6 and 7 show that both the Pearson correlation coefficient and the Spearman correlation coefficient have a significance P-value greater than 0.05, indicating that the null hypothesis is valid and there is no statistical correlation between any two of the three evaluation parameters, meeting the conditions for using the gene expression programming method. In other words, the interfacial adhesion prediction model determined by the gene expression programming method has high reliability and can be used to predict the adhesion between aggregates and asphalt.

[0137] To verify the effectiveness of the aggregate-asphalt interfacial adhesion prediction method proposed in this invention, in some embodiments of this invention, the pull-out strength of the first test scheme (70# base asphalt and limestone combination at 130℃) and the twelfth test scheme (SBS modified asphalt and andesite combination at 170℃) and the pull-out predicted strength obtained by the interfacial adhesion prediction model were obtained, and the relative error between the two was determined. The pull-out strength and relative error are shown in Table 8.

[0138] Table 8 Pull-out strength and relative error

[0139]

[0140] As can be seen from Table 8: 3. The relative errors are all within the range. The relative errors of the two schemes involved in the verification are 3.512% and 0.688%, respectively. The model expression can well describe the influence of the three aggregate-asphalt interface adhesion parameters on the pull-out strength, and provide a theoretical basis for selecting appropriate asphalt, aggregate and mixing temperature in engineering.

[0141] To better implement the aggregate-asphalt interface adhesion prediction method in this invention embodiment, based on the aggregate-asphalt interface adhesion prediction method, this invention embodiment also provides an aggregate-asphalt interface adhesion prediction device. The formation process of aggregate-asphalt interface adhesion includes the process of high-temperature molten asphalt spreading on the aggregate surface, the process of room-temperature solid asphalt contacting the aggregate, and the process of room-temperature solid asphalt interlocking and anchoring with the aggregate; such as Figure 5 As shown, the aggregate-asphalt interface adhesion prediction device 500 includes:

[0142] The sample data acquisition unit 501 is used to acquire multiple sets of sample data of the aggregate-asphalt interface. Each set of sample data has multiple independent variables and a dependent variable corresponding to the multiple independent variables. The multiple independent variables include the high-temperature molten asphalt-aggregate wetting work during the high-temperature molten asphalt spreading process on the aggregate surface, the normal temperature solid asphalt-aggregate adhesion work during the normal temperature solid asphalt-aggregate contact process, and the asphalt filling aggregate pore depth during the normal temperature solid asphalt-aggregate interlocking-anchoring process. The dependent variable is the pull-out strength of the aggregate-asphalt interface.

[0143] The prediction model determination unit 502 is used to determine the interface adhesion prediction model based on gene expression programming, multiple independent variables and dependent variables;

[0144] Adhesion prediction unit 503 is used to predict the adhesion between aggregate and asphalt interface based on interface adhesion prediction model.

[0145] The aggregate-asphalt interface adhesion prediction device 500 provided in the above embodiments can realize the technical solutions described in the above aggregate-asphalt interface adhesion prediction method embodiments. The specific implementation principles of each module or unit can be found in the corresponding content in the above aggregate-asphalt interface adhesion prediction method embodiments, and will not be repeated here.

[0146] like Figure 6 As shown, the present invention also provides an electronic device 600. The electronic device 600 includes a processor 601, a memory 602, and a display 603. Figure 6 Only some components of the electronic device 600 are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0147] In some embodiments, processor 601 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 602 or process data, such as the aggregate-asphalt interface adhesion prediction method of the present invention.

[0148] In some embodiments, processor 601 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 601 may be local or remote. In some embodiments, processor 601 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, intranet, multi-cloud, etc., or any combination thereof.

[0149] In some embodiments, memory 602 may be an internal storage unit of electronic device 600, such as a hard disk or memory of electronic device 600. In other embodiments, memory 602 may also be an external storage device of electronic device 600, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 600.

[0150] Furthermore, the memory 602 may include both internal storage units of the electronic device 600 and external storage devices. The memory 602 is used to store application software and various types of data installed on the electronic device 600.

[0151] In some embodiments, display 603 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 603 is used to display information from electronic device 600 and to display a visual user interface. Components 601-603 of electronic device 600 communicate with each other via a system bus.

[0152] In one embodiment, when processor 601 executes the aggregate-asphalt interface adhesion prediction program in memory 602, the following steps can be implemented:

[0153] Multiple sets of sample data of the aggregate-asphalt interface were obtained; each set of sample data had multiple independent variables and a dependent variable corresponding to the multiple independent variables. The multiple independent variables included the high-temperature molten asphalt-aggregate wetting work during the high-temperature molten asphalt spreading on the aggregate surface, the normal-temperature solid asphalt-aggregate adhesion work during the contact between normal-temperature solid asphalt and aggregate, and the asphalt filling aggregate pore depth during the interlocking-anchoring process of normal-temperature solid asphalt and aggregate. The dependent variable was the pull-out strength of the aggregate-asphalt interface.

[0154] A model for predicting interface adhesion is determined based on gene expression programming, multiple independent variables, and dependent variables.

[0155] The adhesion between aggregate and asphalt is predicted based on the interfacial adhesion prediction model.

[0156] It should be understood that when the processor 601 executes the aggregate-asphalt interface adhesion prediction program in the memory 602, in addition to the functions mentioned above, it can also perform other functions, as detailed in the description of the corresponding method embodiments above.

[0157] Furthermore, this embodiment of the invention does not specifically limit the type of electronic device 600 mentioned. Electronic device 600 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the invention, electronic device 600 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0158] Accordingly, this application also provides a computer-readable storage medium for storing computer-readable programs or instructions. When the programs or instructions are executed by a processor, they can implement the steps or functions of the aggregate-asphalt interface adhesion prediction method provided in the above-described method embodiments.

[0159] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0160] The above provides a detailed description of the method and apparatus for predicting the adhesion of aggregates to asphalt interfaces provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for predicting the adhesion of aggregate to asphalt interface, characterized in that, The formation process of the adhesion between aggregate and asphalt interface includes the process of high-temperature molten asphalt spreading on the surface of aggregate, the process of contact between room-temperature solid asphalt and aggregate, and the process of interlocking and anchoring room-temperature solid asphalt and aggregate. The method for predicting the adhesion between aggregates and asphalt includes: Multiple sets of sample data of the aggregate-asphalt interface are obtained; each set of sample data includes multiple independent variables and a dependent variable corresponding to the multiple independent variables. The multiple independent variables include the high-temperature molten asphalt-aggregate wetting work during the spreading process of the high-temperature molten asphalt on the aggregate surface, the room-temperature solid asphalt-aggregate adhesion work during the contact process between the room-temperature solid asphalt and the aggregate, and the asphalt filling depth of the aggregate pores during the interlocking-anchoring process of the room-temperature solid asphalt and the aggregate. The dependent variable is the pull-out strength of the aggregate-asphalt interface. A predictive model for interface adhesion is determined based on gene expression programming, the multiple independent variables, and the dependent variable. The adhesion between aggregate and asphalt is predicted based on the aforementioned interfacial adhesion prediction model.

2. The method for predicting the adhesion of aggregate to asphalt interface according to claim 1, characterized in that, The acquisition of multiple sets of sample data at the aggregate-asphalt interface includes: Multiple types of asphalt, multiple types of aggregates, and multiple contact temperatures are obtained, and multiple test schemes are determined based on the multiple types of asphalt, the multiple types of aggregates, and the multiple contact temperatures; Determine the high-temperature molten asphalt-aggregate wetting work during the spreading process of high-temperature molten asphalt on the aggregate surface in each group of test schemes; Determine the adhesion work of room temperature solid asphalt-aggregate during the contact process between room temperature solid asphalt and aggregate in each group of test schemes; Determine the depth of asphalt filling aggregate pores during the interlocking-anchoring process of room temperature solid asphalt and aggregate in the test schemes described in each group; The pull-out strength of the aggregate-asphalt interface in each test scheme was determined based on mechanical tensile tests.

3. The method for predicting the adhesion of aggregate to asphalt interface according to claim 2, characterized in that, The determination of the high-temperature molten asphalt-aggregate wetting work during the spreading process of the high-temperature molten asphalt on the aggregate surface in each group of test schemes includes: The surface energy of the high-temperature molten asphalt during the spreading process on the aggregate surface in each group of test schemes was obtained, and the contact angle between the high-temperature molten asphalt and the aggregate was obtained; The wetting work of the high-temperature molten asphalt-aggregate is determined based on the surface energy and the contact angle.

4. The method for predicting the adhesion of aggregate to asphalt interface according to claim 2, characterized in that, The determination of the adhesion work of room-temperature solid asphalt-aggregate during the contact process between room-temperature solid asphalt and aggregate in each group of test schemes includes: Obtain the total surface energy of asphalt during the process from molten asphalt to solid asphalt at room temperature in each group of test schemes, as well as the total surface energy of the aggregate. The adhesion work of the room temperature solid asphalt-aggregate is determined based on the total surface energy of the asphalt and the total surface energy of the aggregate.

5. The method for predicting the adhesion of aggregate to asphalt interface according to claim 2, characterized in that, Determining the depth of asphalt filling aggregate pores during the interlocking-anchoring process of room-temperature solid asphalt and aggregate in each group of test schemes includes: The surface tension of the high-temperature molten asphalt, the contact angle between the high-temperature molten asphalt and the aggregate, and the average pore size of the aggregate within the pore size range of the adsorbed asphalt were obtained in each group of test schemes. The depth of the asphalt-filled aggregate pores is determined based on the surface tension, the contact angle, and the average pore size of the aggregate.

6. The method for predicting the adhesion of aggregate to asphalt interface according to claim 1, characterized in that, The interface adhesion prediction model based on gene expression programming, the multiple independent variables, and the dependent variable includes: Step 1: Determine the operator, gene header length, number of genes, and population size; Step 2: Create an initial population based on the operator, the gene head length, the number of genes, the population size, and the multiple independent variables; the initial population includes multiple chromosomes, each chromosome being composed of genes; Step 3: Convert the multiple chromosomes into expression trees, and determine the initial interface adhesion prediction model based on the expression trees; Step 4: Decode each chromosome to obtain a decoded expression, and determine the fitness value of each chromosome based on the decoded expression, the fitness function, and the dependent variable; Step 5: Determine whether the fitness value is greater than or equal to the fitness threshold; Step 6: When the fitness value is greater than or equal to the fitness threshold, the initial interface adhesion prediction model is the interface adhesion prediction model. Step 7: When the fitness value is less than the fitness threshold, select, mutate, transpose and recombine the multiple chromosomes to obtain multiple evolutionary chromosomes, and return to step 3 to execute steps 3 to 7.

7. The method for predicting the adhesion of aggregate to asphalt interface according to claim 6, characterized in that, The fitness function is: In the formula, This is the fitness value; Multiple sets of sample data; For the first The value of the dependent variable in the group sample data; The predicted value of the dependent variable is determined based on the initial interface adhesion prediction model; To select a range constant.

8. The method for predicting the adhesion of aggregate to asphalt interface according to claim 1, characterized in that, The interface adhesion prediction model is as follows: In the formula, For tensile strength; The work done by the high-temperature molten asphalt-aggregate impregnation. The adhesion work of the solid asphalt-aggregate at room temperature; The depth of the asphalt-filled aggregate pores.

9. The method for predicting the adhesion of aggregate to asphalt interface according to claim 1, characterized in that, Before the gene expression programming method, the multiple independent variables, and the dependent variable determine the interface adhesion prediction model, the following is also included: Determine multiple correlation coefficients among the multiple independent variables; The significance of the multiple correlation coefficients was verified, and multiple significant values ​​were obtained. The correlation between the multiple independent variables is determined based on the multiple significant values.

10. A device for predicting the adhesion of aggregates to asphalt interfaces, characterized in that, The formation process of the adhesion between aggregate and asphalt interface includes the process of high-temperature molten asphalt spreading on the surface of aggregate, the process of contact between room-temperature solid asphalt and aggregate, and the process of interlocking and anchoring room-temperature solid asphalt and aggregate. The aggregate-asphalt interface adhesion prediction device includes: The sample data acquisition unit is used to acquire multiple sets of sample data of the aggregate-asphalt interface. Each set of sample data includes multiple independent variables and a dependent variable corresponding to the multiple independent variables. The multiple independent variables include the high-temperature molten asphalt-aggregate wetting work during the spreading process of the high-temperature molten asphalt on the aggregate surface, the room-temperature solid asphalt-aggregate adhesion work during the contact process between the room-temperature solid asphalt and the aggregate, and the asphalt filling depth of the aggregate pores during the interlocking-anchoring process of the room-temperature solid asphalt and the aggregate. The dependent variable is the pull-out strength of the aggregate-asphalt interface. A prediction model determination unit is used to determine an interface adhesion prediction model based on gene expression programming, the multiple independent variables, and the dependent variable. The adhesion prediction unit is used to predict the adhesion between aggregate and asphalt interface based on the interface adhesion prediction model.

Images