A high-strength asphalt concrete

Abstract

The application provides a high-strength asphalt concrete proportioning design method and an asphalt concrete pavement material, belongs to the field of asphalt concrete, and prepares a plurality of proportioning samples and detects actual compressive strength data of each sample; each influence factor affecting the compressive strength of the asphalt concrete is determined, and an asphalt concrete proportioning prediction model is established according to the actual compressive strength data of each sample and in combination with the influence factor data; the asphalt concrete optimal proportioning under the required compressive strength of the asphalt concrete is obtained according to the asphalt concrete proportioning prediction model and in combination with an optimization algorithm; the influence factors affecting the compressive strength of the concrete are determined, and a concrete proportioning prediction model is established according to the actual compressive strength data of each sample and in combination with the influence factor data; the concrete proportioning design is obtained according to the prediction model and by substituting the required compressive strength data, and iteration optimization is performed according to the comparison between the actual compressive strength of the proportioning sample and the required compressive strength to meet the required accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of asphalt concrete, in particular to a high-strength asphalt concrete. BACKGROUND

[0002] More than 90% of the asphalt pavement that has been built is designed according to the principle of dense gradation, which belongs to dense gradation asphalt concrete pavement with small design air void. However, in the prior art, the proportioning of high-strength asphalt concrete pavement material is mostly obtained from documents, and there is no clear understanding and analysis in the design, and unreasonable design scheme will lead to defects in material performance, so that the product cannot meet the actual needs of the use environment.

[0003] At present, the proportioning design of high-performance concrete mainly adopts a semi-empirical method, that is, the relationship between the compressive strength of asphalt concrete and the oil-stone ratio, component dosage and other factors is fitted to obtain the optimal proportioning design. However, the above method still has some imperfections, that is, there is a large difference between the actual strength of the product made of the concrete proportioning designed by the above method and its theoretical strength, which leads to insufficient compressive strength of the actual product to meet the needs of the use scene. SUMMARY

[0004] Therefore, the present application provides a high-strength asphalt concrete to solve the problem that the actual strength of the product made of the concrete proportioning designed by the prior art method is often quite different from its theoretical strength, which leads to insufficient compressive strength of the actual product to meet the needs of the use scene.

[0005] The technical scheme of the present application is as follows: The present application provides a high-strength asphalt concrete proportioning design method, which comprises the following steps: S1 preparing a plurality of proportioning samples with asphalt, filler, fine aggregate, coarse aggregate, fiber stabilizer and steel fiber as components and detecting the actual compressive strength data of each sample; S2 determining each influencing factor affecting the compressive strength of asphalt concrete, and establishing an asphalt concrete proportioning prediction model according to the actual compressive strength data of each sample combined with the data of each influencing factor; S3 presetting the required compressive strength data of asphalt concrete, and obtaining the optimal proportioning of asphalt concrete under the required compressive strength of asphalt concrete according to the asphalt concrete proportioning prediction model combined with an optimization algorithm.

[0006] On the basis of the above technical scheme, preferably, step S2 comprises the following steps: S21 taking the obtained actual compressive strength data of the sample as the dependent variable Y1, and taking the data of at least one asphalt concrete compressive strength influencing factor as the independent variables X1, X2, X3……X n, wherein n≥1; S22 uses the continuous data of the asphalt concrete component ratio of the sample with the same actual compressive strength under the same preparation condition as continuous data, and uses the continuous data to make a prediction of the asphalt concrete component ratio requirement; S23 combines the sample actual compressive strength data and the continuous data of each related influencing factor into an item set {compressive strength, influencing parameter 1, influencing parameter 2, influencing parameter 3…influencing parameter n}, i.e. {Y1, X1, X2, X3…X n}, wherein the influence of each independent variable on the dependent variable is linear; S24 proportionally calculates the continuous data of the sample component ratio, and makes the dependent variable change with the independent variable, to obtain a regression equation Y1=α0+α1X1+α2X2+α3X3+…+α n X n +β, wherein α0, α1, α2, α3…α n are regression parameters, and β is an error compensation parameter; S25 uses the least square method to obtain the multiple regression equation and the regression coefficient, so as to obtain the values of α0, α1, α2, α3…α n , and thus obtain the regression equation Y1 as a reference of the asphalt concrete component ratio prediction model.

[0007] Further preferably, step S3 comprises the following steps, S31 presets the asphalt concrete requirement compressive strength data according to the asphalt concrete use scene, substitutes the requirement compressive strength data into the regression equation obtained in step S25 as Y1, and converts one kind of asphalt concrete component ratio data; S32 prepares a sample according to the asphalt concrete component ratio data obtained in step S31 and detects the actual compressive strength data thereof; S33 compares the sample actual compressive strength data with the requirement compressive strength data and calculates the relative error value, the relative error value=|actual compressive strength data-requirement compressive strength data| / requirement compressive strength data, and if the relative error value is less than 5%, it represents that the design precision of the asphalt concrete component ratio meets the requirement.

[0008] Further preferably, step S3 further comprises the following steps, S34 if the relative error value is not less than 5%, it represents that the design precision of the asphalt concrete component ratio does not meet the requirement, and an optimization algorithm is used to optimize the asphalt concrete component ratio data, and steps S32 and S33 are repeated for iteration until the design precision of the asphalt concrete component ratio data meets the requirement.

[0009] Further preferably, the optimization algorithm is a genetic algorithm.

[0010] Further preferably, the factors affecting the compressive strength of the asphalt concrete in step S21 are porosity, oil aggregate ratio, fiber stabilizer content and steel fiber content; the porosity, oil aggregate ratio, fiber stabilizer content and steel fiber content are taken as independent variables X1, X2, X3 and X4 respectively, and a regression equation Y1 = a0 + a1X1 + a2X2 + a3X3 + a4X4 + b is obtained; the regression equation is taken as the objective function of the genetic algorithm, and the porosity, oil aggregate ratio, fiber stabilizer content and steel fiber content are taken as the constraint range parameters, and the method for obtaining the asphalt concrete component ratio that meets the design precision requirement through the genetic algorithm includes the following steps: step one, randomly obtaining a plurality of concrete ratios as the initial population P0 based on the objective function and the constraint range parameters; step two, calculating the fitness of each ratio in the population P n based on the objective function, wherein n is an integer greater than or equal to 1; step three, performing genetic operations on the population P n based on the genetic algorithm to generate the next generation population P n+1 = P n +1; step four, setting the maximum evolution number N, and when n = N, the evolution is terminated, and the concrete ratio with the maximum fitness obtained is output as the optimal solution, and the concrete ratio data output by the optimal solution is used to prepare a sample.

[0011] Further preferably, the range of the constraint range parameters is determined, wherein the porosity is obtained by calculating the gradation of coarse and fine aggregates through the MAA accumulation model, and then being converted, and the proportion of the size of sand and gravel in the coarse and fine aggregates can be calculated by the following formula, P(D) = (D q -D q min ) / (D q max -D q min ), wherein P(D) is the percentage of sand and gravel with a particle size less than D in the total amount of selected sand and gravel; D is the particle size of sand and gravel; D min is the minimum particle size of sand and gravel; D max is the maximum particle size of sand and gravel; q is the distribution modulus, and q takes a value in the range of 0.22 to 0.25; the oil aggregate ratio is 4.1% to 5%, the fiber stabilizer content is 2.5% to 3.0%, and the steel fiber volume content is not greater than 5%.

[0012] In another aspect, the present application also provides an asphalt concrete pavement material, which is obtained by using the high-strength asphalt concrete proportioning design method according to any one of claims 1 to 7, and which comprises asphalt, filler, fine aggregate, coarse aggregate, fiber stabilizer and steel fiber, wherein the mass content of each component is as follows: asphalt 2% to 5%, filler 5% to 7%, fine aggregate 35% to 43%, coarse aggregate 50% to 60%, fiber stabilizer 2.5% to 3.0%, and the volume content of steel fiber is not more than 5%.

[0013] Preferably, in the above technical solution, the asphalt is high-viscosity modified asphalt, and the filler comprises silica fume, fly ash and ultra-fine mineral powder.

[0014] Preferably, in the above technical solution, the aspect ratio of the steel fiber is 60 to 70.

[0015] The high-strength asphalt concrete of the present application has the following beneficial effects compared with the prior art:

[0016] (1) The present application determines multiple influencing factors affecting the compressive strength of concrete, and establishes a concrete proportioning prediction model according to the actual compressive strength data of each sample combined with the data of each influencing factor, and then obtains the concrete proportioning design by substituting the required compressive strength data into the prediction model, and iteratively optimizes the proportioning design according to the comparison between the actual compressive strength of the proportioning sample and the required compressive strength, so that the compressive strength of the product obtained under the final optimized proportioning design meets the required accuracy.

[0017] (2) The influencing factors determined by the present application include porosity, oil-stone ratio, fiber stabilizer content and steel fiber content, which cover all factors that can affect the compressive strength of asphalt concrete, and a concrete proportioning prediction model is established through a regression equation, so that the proportioning design can be predicted according to requirements. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0019] The application discloses a high-strength asphalt concrete proportioning design method, and has the technical scheme that the application is based on the application of the asphalt concrete proportioning design of the application person according to technical documents, and the application person finds that there is a great difference between the actual compressive strength of the asphalt concrete product and the theoretical compressive strength of the proportioning obtained according to the technical documents through the Marshall test method.

[0020] Firstly, the porosity has a great influence on the strength of the asphalt concrete. In theory, the porosity can be greatly improved by adjusting the component proportioning of the fine aggregate, the coarse aggregate and the filler, so that the compactness of the asphalt concrete is improved, and the strength and modulus of the product are greatly improved. However, under the same component proportioning, the material types of the aggregate, the coarse aggregate and the filler are changed, so that the grading of the aggregate, the coarse aggregate and the filler is changed, and the porosity of the product is actually influenced, and the strength of the product is influenced.

[0021] Secondly, the asphalt-aggregate ratio is one of important factors influencing the strength of the asphalt concrete. According to the existing research, the asphalt-aggregate ratio under the same grading scheme is very close, and can be consistent with the previous theoretical design experience. Under the same porosity, the asphalt-aggregate ratio under different grading schemes has a great difference, so that the asphalt amount is greatly changed. Under different grading schemes, in order to make the product reach the same compactness, the porosity needs to be reduced and the actual amount of asphalt needs to be increased, but the asphalt-aggregate ratio is increased, so that the strength of the product is influenced.

[0022] Thirdly, the mixing amount of the fiber stabilizer, the additive and the steel fiber in the product components also influences the strength of the product, and the influencing mechanism is relatively complex. According to the present research, it is generally considered that the fiber stabilizer or the additive and other components can gradually increase the strength of the product with the increase of the mixing amount, but the influence of the fiber stabilizer or the additive and other components on the strength of the product tends to be stable or slowly decreases after reaching a certain peak value. The mixing of the steel fiber can greatly improve the mechanical properties of the asphalt concrete. The aspect ratio of the steel fiber has a significant influence on the bending performance, the tensile performance and the like of the product component, and has a relatively weak influence on the compressive strength of the product, but still has a certain degree of influence.

[0023] Based on the above reasons, the application person finds through the test that the porosity, the asphalt-aggregate ratio, the mixing amount of the fiber stabilizer and the mixing amount of the steel fiber are main factors influencing the strength of the product, so that there is a great difference between the theoretical compressive strength of the product design proportioning and the actual compressive strength of the product. In order to reduce the influence and eliminate the difference as much as possible, the design method mainly comprises the following steps.

[0024] S1 several samples are prepared with asphalt, filler, fine aggregate, coarse aggregate, fiber stabilizer and steel fiber as components, and actual compressive strength data of each sample is detected.

[0025] S2 each influencing factor affecting the compressive strength of asphalt concrete is determined, and an asphalt concrete proportioning prediction model is established according to the actual compressive strength data of each sample combined with the data of each influencing factor.

[0026] S3 presetting the required compressive strength data of asphalt concrete, the optimal proportioning of asphalt concrete under the required compressive strength of asphalt concrete is obtained according to the asphalt concrete proportioning prediction model combined with the optimization algorithm.

[0027] The principle of the method is essentially that the actual compressive strength data of samples produced by a large number of proportions and the proportioning data of each sample form a data set, the influencing factors of the product compressive strength are determined, and the relationship between these influencing factors and the data set is obtained through an algorithm to obtain a prediction model for the proportioning design of asphalt concrete. Finally, the target compressive strength data is substituted into the model to obtain the design proportioning under the target compressive strength. The actual compressive strength data of the actual product is obtained by preparing the actual product through the design proportioning, and the design proportioning data is iteratively optimized through the optimization algorithm, so that the actual compressive strength data of the final product can be as close as possible to the target data to meet the requirements.

[0028] On the basis of the previous embodiment, in order to establish the concrete proportioning prediction model, specifically, step S2 includes the following steps.

[0029] S21 the obtained sample actual compressive strength data is taken as the dependent variable Y1, and the data of at least one asphalt concrete compressive strength influencing factor is taken as the independent variables X1, X2, X3……X n , wherein n≥1.

[0030] S22 under the same preparation conditions, the asphalt concrete component proportioning data of samples with the same actual compressive strength is taken as continuous data for asphalt concrete proportioning requirement prediction.

[0031] S23 the sample actual compressive strength data and the continuous data of each related influencing factor are combined into an item set {compressive strength, influencing parameter 1, influencing parameter 2, influencing parameter 3……influencing parameter n}, that is, {Y1, X1, X2, X3……X n} wherein the influence of each independent variable on the dependent variable is linear. It should be noted that the influence of the proportion of each component of the asphalt concrete on the product strength is not essentially continuously improved as the proportion increases, but the method can limit the improvement of the product strength as the proportion of the component increases within a certain range, so that the influence of each independent variable on the dependent variable can be considered linear within the limited range.

[0032] S24 performs proportional calculation on the continuous data of the sample component proportion, and changes the dependent variable with the change of the independent variable, to obtain a regression equation,

[0033] Y1 = a0 + a1X1 + a2X2 + a3X3 + … + a n X n + β,

[0034] wherein a0, a1, a2, a3, …, a n are regression parameters, and β is an error compensation parameter.

[0035] S25 obtains the multiple regression equation and the regression coefficient by using the least square method, so as to obtain the values of a0, a1, a2, a3, …, a n , and thus obtains the regression equation Y1 as a reference of the asphalt concrete proportion prediction model.

[0036] In the previous embodiment, although the concrete proportion prediction model is established, there are still more than one solution for the design proportion of the same product to obtain the actual compressive strength, which makes it difficult for the designer to determine the direction of screening and improving the obtained multiple design proportions, and the present application provides a solution, specifically, step S3 comprises the following steps.

[0037] S31 substitutes the demand compressive strength data of the asphalt concrete as Y1 into the regression equation obtained in step S25 according to the demand compressive strength data of the asphalt concrete preset according to the use scene of the asphalt concrete, to convert the proportion data of one kind of asphalt concrete component.

[0038] S32 prepares a sample according to the asphalt concrete proportion data obtained in step S31 and detects the actual compressive strength data of the sample.

[0039] S33 compares the actual compressive strength data of the sample with the demand compressive strength data and calculates the relative error value, the relative error value = | actual compressive strength data - demand compressive strength data | / demand compressive strength data, if the relative error value is less than the design precision requirement, it represents that the design precision of the proportion of the asphalt concrete component meets the demand.

[0040] After the product design ratio is selected according to the required compressive strength, the actual compressive strength data of the sample is obtained by detecting the sample made based on the design ratio, and the actual compressive strength data is compared with the required compressive strength to determine whether the difference meets the accuracy requirement, so as to determine whether the selected product design ratio meets the requirement and provide a thought for designers to screen and determine the design ratio meeting the requirement.

[0041] Further, on the basis of the above embodiments, the designers can also iteratively optimize and improve the selected design ratio, and step S3 further includes the following step S34: if the relative error value is not less than the design accuracy requirement, it means that the design accuracy of the component ratio of the asphalt concrete does not meet the requirement, the optimization algorithm is used to optimize the component ratio data of the asphalt concrete, and steps S32 and S33 are repeated for iteration until the design accuracy of the component ratio data of the asphalt concrete meets the requirement.

[0042] In the above embodiments, according to most technical documents, the design accuracy requirement is usually 5%. For some scenarios with higher accuracy requirements, the design accuracy requirement will also increase accordingly.

[0043] The optimization algorithm in the previous embodiment adopts a genetic algorithm. The genetic algorithm (GA) is a computational model simulating the natural selection and genetic mechanism of Darwin's biological evolution process, which is a method of searching for an optimal solution by simulating the natural evolution process. It starts from a population representing the potential solution set of the problem, and a population is composed of a certain number of individuals coded by genes. In this application, the individual refers to the concrete ratio.

[0044] Specifically, in step S21, the compressive strength influencing factors of the asphalt concrete are porosity, oil-stone ratio, fiber stabilizer dosage and steel fiber dosage; the porosity, oil-stone ratio, fiber stabilizer dosage and steel fiber dosage are taken as independent variables X1, X2, X3 and X4, respectively, and the regression equation obtained in this case is

[0045] Y1=α0+α1X1+α2X2+α3X3+α4X4+β.

[0046] According to the principle of genetic algorithm, the regression equation is taken as the objective function of the genetic algorithm, and the porosity, oil-stone ratio, fiber stabilizer dosage and steel fiber dosage are taken as the constraint range parameters. The method for obtaining the component ratio of the asphalt concrete meeting the design accuracy requirement by the genetic algorithm includes the following steps:

[0047] Step one, randomly obtain several concrete mixtures as initial population P0 based on objective function and constraint range parameters. Specifically, when preparing asphalt concrete, a reasonable amount of each raw material is determined according to relevant specifications and actual engineering requirements, and a value range is preset for each raw material, which is used as the constraint condition for concrete mixture design.

[0048] Step two, calculate the fitness of each mixture in population P n based on the objective function, where n is an integer greater than or equal to 1.

[0049] Step three, perform genetic operations on population P n based on the genetic algorithm to generate the next generation population P n+1 = P n +1. Genetic operations include selection, crossover and mutation. The purpose of selection is to directly inherit the optimized individuals to the next generation or produce new individuals through paired crossover and then inherit them to the next generation; selection operation is based on the fitness evaluation of individuals in the population. The crossover operator is applied to the population and plays a key role in the genetic algorithm. The mutation operator is applied to the population, which changes the gene value at some loci of the individual string in the population. Specifically, selection can be performed by random sampling first, then a crossover probability is set, and the crossover operator is used for crossover operation under the crossover probability, then a mutation probability is set and the mutation feature information is randomly selected for mutation operation, and finally the next generation population is generated.

[0050] Step four, set the maximum evolution number N, when n=N, the evolution is terminated, and the concrete mixture with the maximum fitness obtained is output as the optimal solution. The concrete mixture data output with the optimal solution is used to prepare samples.

[0051] In the previous embodiment, the range of each constraint range parameter needs to be limited. The porosity is calculated by the MAA accumulation model after the grading of coarse and fine aggregates is obtained, and then it is converted to know. Specifically, the proportion of sand and gravel particle size in coarse and fine aggregates can be calculated by the following formula,

[0052] P(D) = (D q -D q min ) / (D q max -D q min ,

[0053] where P(D) is the percentage of sand and gravel with a particle size less than D in the total amount of selected sand and gravel; D is the sand and gravel particle size; D min is the minimum particle size of sand and gravel; D maxD is the maximum particle size in the sand and gravel; q is the distribution modulus, and when q is usually 0.22 to 0.25, the closest packing of aggregates of different particle sizes is calculated. The particle size of each sand and gravel in the gradation of coarse and fine aggregates can be calculated by the above formula, and the porosity is converted.

[0054] Meanwhile, as mentioned above, since the present method needs to limit the allocation ratio of each component within a certain range, the improvement of the component ratio can affect the improvement of the product strength, and thus within the limited range, the influence of each independent variable on the dependent variable is linear. According to the existing technical documents, the preferred range of oilstone ratio is 4.1% to 5%, the preferred range of fiber stabilizer content is 2.5% to 3.0%, and the preferred range of steel fiber volume content is not more than 5%.

[0055] The present application also provides a kind of asphalt concrete pavement material, and the component allocation ratio of the asphalt concrete pavement material is obtained by using the high-strength asphalt concrete proportioning design method of any one of the above embodiments, and the components include asphalt, filler, fine aggregate, coarse aggregate, fiber stabilizer and steel fiber;Wherein, the mass content of each component is that asphalt is 2% to 5%, filler is 5% to 7%, fine aggregate is 35% to 43%, coarse aggregate is 50% to 60%, fiber stabilizer is 2.5% to 3.0%, and the volume content of steel fiber is not more than 5%. Wherein, the asphalt is high-viscosity modified asphalt, and the filler includes silica fume, fly ash and ultra-fine mineral powder. The aspect ratio of steel fiber is 60-70.

[0056] The present application is verified by the present design method, and the result analysis is as follows:

[0057] The present application is verified by the present design method, and the result analysis is as follows:

[0058] Y1=α0+α1X1+α2X2+α3X3+α4X4+β,

[0059] According to the above concrete proportioning prediction model, the asphalt concrete design proportion is selected as follows: asphalt, wherein the asphalt is high-viscosity modified asphalt;Filler, wherein the filler includes silica fume, fly ash and ultra-fine mineral powder;Fine aggregate;Coarse aggregate;Fiber stabilizer;Steel fiber volume content, and the aspect ratio of steel fiber is 65.

[0060] According to the above design proportion, the sample is made and detected, and the actual compressive strength is MPa, and the error is

[0061] After optimization by optimization algorithm, the design proportion is obtained as follows: asphalt;Silica fume, fly ash and ultra-fine mineral powder;Fine aggregate;Coarse aggregate;Fiber stabilizer;Steel fiber volume content.

[0062] According to the improved design ratio iteration sample is made and detection is known that the actual compressive strength is MPa, the error is, meets the accuracy requirement.

[0063] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A high strength asphalt concrete, characterized by: The components include asphalt, filler, fine aggregate, coarse aggregate, fiber stabilizer and steel fiber; The mass content of each component is, Asphalt 2% to 5%, the asphalt is high viscosity modified asphalt; Filler 5% to 7%, the filler includes silica ash, fly ash and superfine mineral powder; Fine aggregate 35% to 43%, Coarse aggregate 50% to 60%, Fiber stabilizer 2.5% to 3.0%, The volume content of steel fiber is not more than 5%, and the aspect ratio of the steel fiber is 60-70; The design method of the component ratio of each component includes the following steps, S1, a plurality of samples with different component ratios are prepared with asphalt, filler, fine aggregate, coarse aggregate, fiber stabilizer and steel fiber as components, and the actual compressive strength data of each sample is detected; S2, each influencing factor affecting the compressive strength of asphalt concrete is determined, and an asphalt concrete proportioning prediction model is established according to the actual compressive strength data of each sample combined with the data of each influencing factor; S21, the obtained sample actual compressive strength data is taken as the dependent variable Y1, the influencing factors of the compressive strength of asphalt concrete are determined as porosity, oil stone ratio, fiber stabilizer content and steel fiber content, and the porosity, oil stone ratio, fiber stabilizer content and steel fiber content are taken as independent variables X1, X2, X3 and X4 respectively; S22, under the same preparation conditions, the component ratio data of the asphalt concrete of the sample with the same actual compressive strength is taken as continuous data, and the continuous data is used for asphalt concrete proportioning demand prediction; S23, the sample actual compressive strength data is combined with the continuous data of each related influencing factor as an item set {compressive strength, influencing parameter 1, influencing parameter 2, influencing parameter 3, influencing parameter 4}, that is, {Y1, X1, X2, X3, X4}, wherein it is preset that the influence of each independent variable on the dependent variable is linear; The range of each of the influencing factors of the compressive strength of asphalt concrete is determined, wherein the porosity is calculated by the MAA accumulation model after the grading of the coarse and fine aggregates is known, and the proportion of the size of the sand and stone in the coarse and fine aggregates can be calculated by the following formula, P(D) = (D q - D q min ) / (D q max - D q min ), wherein P(D) is the percentage of the total amount of sand and gravel selected whose particle size is less than D; D is the particle size of the sand and gravel; D min is the minimum particle size in the sand and gravel; D max is the maximum particle size in the sand and gravel; q is the distribution modulus, q has a value range of 0.22 to 0.25; The oil stone ratio is 4.1% to 5%, the fiber stabilizer content is 2.5% to 3.0%, and the volume content of steel fiber is not more than 5%; S24, the continuous data of the component ratio of the sample is proportionally calculated, and the dependent variable changes with the change of the independent variable, and the regression equation is obtained as, Y1=α0+α1X1+α2X2+α3X3+α4X4+β, Wherein, α0, α1, α2, α3 and α4 are regression parameters, and β is an error compensation parameter; S25, the least square method is used to obtain the multiple regression equation and the regression coefficient, so as to obtain the values of α0, α1, α2, α3 and α4, and thus the regression equation Y1 is obtained as the reference of the asphalt concrete proportioning prediction model; S3, presetting the demand compressive strength data of asphalt concrete, obtaining the optimal component ratio of asphalt concrete under the demand compressive strength of asphalt concrete according to the asphalt concrete proportioning prediction model combined with the optimization algorithm; the optimization algorithm is genetic algorithm.

2. The high strength asphalt concrete of claim 1, wherein: The step S3 includes the following steps, S31 presetting the asphalt concrete demand compressive strength data according to the asphalt concrete use scene, substituting the demand compressive strength data as Y1 into the regression equation obtained in step S25, and converting the asphalt concrete component proportioning data of one kind; S32 preparing a sample according to the asphalt concrete proportioning data obtained in step S31 and detecting the actual compressive strength data thereof; S33 comparing the sample actual compressive strength data with the demand compressive strength data and calculating the relative error value thereof, the relative error value = | actual compressive strength data - demand compressive strength data | / demand compressive strength data, and if the relative error value is less than 5%, it represents that the design precision of the asphalt concrete component proportioning meets the demand.

3. The high strength asphalt concrete of claim 2, wherein: The step S3 further comprises the following steps, S34 if the relative error value is not less than 5%, it represents that the design precision of the asphalt concrete component proportioning does not meet the demand, the optimization algorithm is used to optimize the asphalt concrete component proportioning data, and steps S32 and S33 are repeated for iteration until the design precision of the asphalt concrete component proportioning data meets the demand.

4. The high strength asphalt concrete of claim 3, wherein: The regression equation in the step S21 is taken as the objective function of the genetic algorithm, and the porosity, oil-stone ratio, fiber stabilizer content and steel fiber content are taken as the constraint range parameters, and the method for obtaining the asphalt concrete component proportioning with design precision meeting the demand through the genetic algorithm comprises the following steps, Step one, randomly obtaining a plurality of concrete proportions based on the objective function and the constraint range parameters as the initial population P0; Step two, calculate the population P according to the objective function n the fitness of each combination, where n is an integer greater than or equal to 1. Step three, according to the genetic algorithm to the population P n Genetic operation, generate the next generation of population P n+1 = P n +1; Step four, setting the maximum evolution number N, when n=N, the evolution is terminated, the concrete proportion with the maximum fitness obtained is taken as the optimal solution output, and the concrete proportion data of the optimal solution output is used to prepare a sample.