Bituminous mixture mix proportion design method based on machine vision

Abstract

The invention discloses an asphalt mixture mix proportion design method based on machine vision, and the method comprises the following steps: obtaining a target asphalt mixture raw material component type, the asphalt mixture raw material components comprise aggregate, asphalt and filler; determining the covering thickness of the corresponding asphalt on the aggregate according to the target asphalt mixture; acquiring three-dimensional image data of the aggregate according to the scanning equipment, establishing a surface model of the aggregate according to the three-dimensional image data, and determining the asphalt volume required by the aggregate in the target asphalt mixture according to the surface model of the aggregate and the covering thickness on the aggregate; obtaining the asphalt volume required by the filler in the target asphalt mixture according to the critical filler concentration; and adding the asphalt volume required by the aggregate in the target asphalt mixture and the asphalt volume required by the filler in the target asphalt mixture to obtain the total volume dosage of the asphalt in the target asphalt mixture. The invention aims to realize high-efficiency determination of the mix proportion of each component in the target asphalt mixture.

Description

Technical Field

[0001] The present invention relates to the technical field of asphalt mixtures, and particularly to a method for designing the mix proportion of asphalt mixtures based on machine vision. Background Technique

[0002] At present, during the process of highway construction and maintenance, asphalt mixtures account for a large proportion. Analyzing the performance and road performance of asphalt mixtures has very detailed analysis steps, and a large number of Marshall specimens need to be made to analyze their performance, which requires a large amount of manpower and material resources for asphalt mixture performance testing. In order to optimize the design of asphalt mixtures, defining the optimal asphalt film thickness is the basis for achieving high-performance asphalt mixture levels.

[0003] The existing invention patent with the publication number CN115081058A discloses a method for predicting the optimal asphalt content in Marshall mix proportion design. According to the type of asphalt mixture, nominal maximum particle size, and gradation, it determines the design technical requirements of volume index values and calculates the basic parameters of the asphalt mixture, preliminarily determines the asphalt content range, groups the asphalt content and void ratio within the range at certain intervals respectively, calculates the volume index values of different asphalt contents at different void ratios, determines the intersection of the asphalt content ranges that meet the design requirements for each volume index value under each void ratio condition according to the graphical method, then calculates the range of the optimal asphalt content based on the end values of the intersection, and then calculates the optimal asphalt content in combination with the key sieve hole and maximum particle size parameters. Although this method solves the problem of inaccurate prediction caused by only being able to estimate through engineering experience before the previous mix proportion design, there are still certain limitations in determining the volume index values only based on the void ratio. Summary of the Invention

[0004] The main purpose of the present invention is to provide a method, system, and storage medium for designing the mix proportion of asphalt mixtures based on machine vision, aiming to solve the technical problem of low efficiency in the existing design of asphalt mixture mix proportions.

[0005] To achieve the above object, the present invention provides a method for designing the mix proportion of asphalt mixtures based on machine vision, and the method includes the following steps:

[0006] Step 1, obtaining the types of raw material components of the target asphalt mixture, where the raw material components of the asphalt mixture include aggregate, asphalt, and filler, the particle size of the filler is less than 0.075 mm, and the aggregate has multiple particle size distributions and each particle size aggregate has a corresponding mass percentage;

[0007] Step 2, determining the covering thickness of the corresponding asphalt on the aggregate according to the target asphalt mixture;

[0008] Step 3: Obtain the three-dimensional image data of the aggregate according to the scanning device, establish the surface model of the aggregate based on the three-dimensional image data, and determine the asphalt volume required for the aggregate in the target asphalt mixture according to the surface model of the aggregate and the covering thickness on the aggregate;

[0009] Step 4: Obtain the asphalt volume required for the filler in the target asphalt mixture according to the critical filler concentration;

[0010] Step 5: Add the asphalt volume required for the aggregate in the target asphalt mixture to the asphalt volume required for the filler in the target asphalt mixture to obtain the total asphalt volume used in the target asphalt mixture, so as to determine the mix ratio of each component in the target asphalt mixture.

[0011] Optionally, in Step 2, the covering thickness range of the asphalt on the aggregate is 5-15 μm.

[0012] Optionally, in Step 3, the scanning device is a FARO ARM PLATINIUM laser scanner or a CT scanner.

[0013] Optionally, in Step 3, the steps of establishing the surface model of the aggregate according to the three-dimensional image data include:

[0014] Calculate the surface area factor of each particle size aggregate according to the three-dimensional image data;

[0015] Obtain the total surface area of the aggregate according to the mass percentage of each particle size aggregate and the surface area factor of each particle size aggregate, so as to determine the surface model of the aggregate.

[0016] Optionally, the calculation formula for calculating the surface area factor of each particle size aggregate according to the three-dimensional image data is:

[0017] Calculate the volume V of 1 kg of aggregate i1kg , where ρ a is the aggregate density, with the unit of kg / m 3 ;

[0018] Calculate the number of particles N of 1 kg of aggregate i1kg , where ν i is the volume of the average particle, with the unit of m 3 ;

[0019] Calculate the specific surface area factor α i , α i = N i1kg .s i where s i is the surface area of the average particle, with the unit of m 2 .

[0020] Optionally, the specific calculation formula for obtaining the total surface area of the aggregate based on the mass percentage of each particle size aggregate and the surface area factor of each particle size aggregate is as follows:

[0021] SSA agg = ∑α i ·(P i+1 - P i ), where SSA agg is the total surface area of the aggregate, Ρ i represents the cumulative passing rate at particle size i, Ρ i+1 represents the cumulative passing rate at particle size i + 1, and the passing rate is in mass percentage.

[0022] Optionally, the specific formula for determining the volume of asphalt required for the aggregate in the target asphalt mixture based on the surface model of the aggregate and the covering thickness on the aggregate is as follows:

[0023] V bit-agg = t opt-agg ·SSA agg , where t opt-agg is the covering thickness on the aggregate, and V bit-agg is the volume of asphalt required for the aggregate.

[0024] Optionally, the specific formula for obtaining the volume of asphalt required for the filler in the target asphalt mixture based on the critical filler concentration is as follows:

[0025] V filler represents the filler volume, in m3, and V bit-filler represents the volume of asphalt used for coating the filler, in m 3 , and φ c represents the critical filler concentration, in %.

[0026] In addition, to achieve the above object, the present invention also provides a machine vision-based asphalt mixture proportion design system, which includes a memory, a processor, and a machine vision-based asphalt mixture proportion design program stored on the memory and executable on the processor. When the machine vision-based asphalt mixture proportion design program is executed by the processor, it implements the steps of the machine vision-based asphalt mixture proportion design method as described in any one of the above.

[0027] In addition, to achieve the above object, the present invention also provides a computer storage medium, on which a machine vision-based asphalt mixture proportion design program is stored. When the machine vision-based asphalt mixture proportion design program is executed by a processor, it implements the steps of the machine vision-based asphalt mixture proportion design method as described in any one of the above.

[0028] Beneficial effects:

[0029] The method for designing the mix proportion of asphalt mixture based on machine vision proposed by the present invention scans the true shape of the aggregate with a laser scanning instrument and allows obtaining a 3D image, providing information about the number of faces and vertices of the aggregate, as well as their volume and surface area. Then, the surface area of the aggregate is calculated through the corresponding formula, and the asphalt dosage of the aggregate is calculated according to the conventional asphalt film thickness of the aggregate and the calculated surface area of the aggregate. At the same time, according to the mass and density of the filler, and using the critical filler concentration to calculate the minimum amount of asphalt required to maintain the diluted state of the asphalt mortar. The asphalt dosages required for the aggregate and the filler are added together to determine the asphalt dosage of the asphalt mixture. Furthermore, through a specific calculation method, the optimal asphalt dosage required for the aggregate and the filler under the selected gradation can be quickly evaluated, providing technical support for saving time and improving experimental efficiency in the performance evaluation of asphalt mixtures. Description of the drawings

[0030] Figure 1 It is a schematic flow chart of an embodiment of the method for designing the mix proportion of asphalt mixture based on machine vision of the present invention.

[0031] Figure 2 It is the gradation curve of AC-B16 type asphalt mixture in Example 1;

[0032] Figure 3 It is the three-dimensional images of aggregates with different sizes obtained in Example 1;

[0033] Figure 4 It is a broken line graph of the asphalt dosage and the specimen density of AC-B16 type asphalt mixture in Example 1;

[0034] Figure 5 It is a broken line graph of the asphalt dosage and the stability of AC-B16 type asphalt mixture in Example 1;

[0035] Figure 6 It is a broken line graph of the asphalt dosage and the void ratio of AC-B16 type asphalt mixture in Example 1;

[0036] Figure 7 It is a broken line graph of the asphalt dosage and the air voids of AC-B16 type asphalt mixture in Example 1;

[0037] Figure 8 It is a broken line graph of the asphalt dosage and the asphalt saturation of AC-B16 type asphalt mixture in Example 1;

[0038] Figure 9 It is a broken line graph of the asphalt dosage and the flow value of AC-B16 type asphalt mixture in Example 1;

[0039] Figure 10It is a broken line graph after summarizing the asphalt content and physical and mechanical indexes of Marshall test for AC-B16 type asphalt mixture in Example 1;

[0040] Figure 11 It is the three-dimensional images of aggregates with different sizes obtained in Example 2;

[0041] Figure 12 It is a broken line graph of asphalt content and stability for AC-B20 type asphalt mixture in Example 2;

[0042] Figure 13 It is a broken line graph of asphalt content and void ratio for AC-B20 type asphalt mixture in Example 2;

[0043] Figure 14 It is a broken line graph of asphalt content and asphalt saturation for AC-B20 type asphalt mixture in Example 2;

[0044] Figure 15 It is a broken line graph of asphalt content and flow value for AC-B20 type asphalt mixture in Example 2;

[0045] Figure 16 It is a broken line graph of asphalt content and gap ratio for AC-B20 type asphalt mixture in Example 2;

[0046] Figure 17 It is a broken line graph of asphalt content and specimen density for AC-B20 type asphalt mixture in Example 2;

[0047] Figure 18 It is a broken line graph after summarizing the asphalt content and physical and mechanical indexes of Marshall test for AC-B20 type asphalt mixture in Example 2.

[0048] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed implementation manners

[0049] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0050] As Figure 1 shown, the present invention provides a method for designing the mix proportion of asphalt mixture based on machine vision, and the method includes the following steps:

[0051] Step 1: Obtain the types of raw material components of the target asphalt mixture. Specifically, select the raw material components and gradation types of the asphalt mixture. Among them, the raw material components of the asphalt mixture include aggregate, asphalt, and filler, and the particle size of the filler is less than 0.075 mm. The aggregate has various particle size distributions, and each particle size aggregate has a corresponding mass percentage. And determine the technical indicators of the asphalt used. At the same time, according to the "Test Regulations for Aggregates in Highway Engineering" (JTGE42—2005), measure the physical properties and mechanical properties of the aggregate and filler respectively. Determine the mineral aggregate gradation for the test according to the relevant specification requirements and the existing gradation theory research results.

[0052] Step 2: Determine the covering thickness of the corresponding asphalt on the aggregate according to the target asphalt mixture. Specifically, the covering thickness of the asphalt on the aggregate is denoted as the asphalt film thickness. Currently, the covering thickness range of the asphalt on the aggregate is 5 - 15 μm. Preferably, the covering thickness on the aggregate in the AC gradation is 10 μm.

[0053] Step 3: Obtain the three-dimensional image data of the aggregate according to the scanning device, establish the surface model of the aggregate based on the three-dimensional image data, and determine the asphalt volume required for the aggregate in the target asphalt mixture according to the surface model of the aggregate and the covering thickness on the aggregate.

[0054] That is, adopt laser scanning technology or computer tomography (CT) technology to obtain the three-dimensional image of the aggregate and generate a high-resolution surface model of the aggregate; use image processing software to process the three-dimensional image, extract the surface area, volume and geometric features of the aggregate; based on the actual shape of the aggregate, calculate the surface area factor α of aggregates with different particle sizes through proportional scaling i and correct it through the relative position and surface roughness with other particles to obtain a more accurate surface area factor; weight-average the surface area factors α of aggregates with different particle sizes i by mass percentage (P) to calculate the total surface area SSA of the aggregate agg and use it to calculate the asphalt film thickness.

[0055] Among them, the scanning device includes a) a laser scanning module: used to scan the aggregate and obtain its three-dimensional shape and surface area;

[0056] b) an image processing module: used to analyze the three-dimensional image of the aggregate and calculate its surface area and volume;

[0057] c) a particle size analysis module: used to measure the particle size distribution (PSD) of the filler and calculate its specific surface area (BET);

[0058] d) a calculation module: used to calculate the total asphalt consumption based on the aggregate surface area factor and the critical concentration of the filler;

[0059] e) Performance verification module: used to verify the performance of the optimized asphalt mixture through experimental tests (such as Marshall test, gyratory compactor test, indirect tensile strength test, splitting tensile strength test) to ensure that it meets the standard requirements.

[0060] Further, the calculation module includes:

[0061] a) Aggregate surface area calculation module: used to calculate the surface area factor α of the aggregate through laser scanning images i ;

[0062] b) Filler calculation module: used to calculate the critical concentration φ of the filler through particle size analysis and specific surface area measurement c and obtain the asphalt demand;

[0063] c) Total asphalt dosage calculation module: used to calculate the total asphalt dosage of the aggregate and the filler and output the optimized asphalt ratio.

[0064] Preferably, laser scanning technology (such as FARO ARM PLATINIUM laser scanner) is used to determine the true shape of the aggregate. Also, using a FARO ARM PLATINIUM laser scanner with high precision (0.03 mm), combined with a LINEPROBE III scanning head, the 3D shape of the object can be accurately captured. Calculate the surface area and volume of each piece of aggregate based on these images to obtain a more accurate mineral aggregate surface area.

[0065] Further, use 3D modeling and surface analysis tools such as Meshlab, Geomagic, CloudCompare or similar to analyze these 3D images to obtain the true surface area and volume of the aggregate particles.

[0066] Specifically, when calculating the average particle surface area and volume in each particle size range, the "average particle" surface area and volume in each particle size level are the average values of all particles in that particle size range. By calculating the average surface area and volume of the particles in each classification level, the surface area factor α of each classification level is finally obtained. i . The total specific surface area of the aggregate is directly obtained according to the following formula, thereby obtaining the asphalt dosage.

[0067] Calculate the proportional factor and total surface area in the required asphalt dosage.

[0068] ① Calculate how many particles of a certain size exist in one kilogram of these aggregates, and multiply the number of particles with the "average" particle area by the obtained surface area factor α i , the calculation is as follows:

[0069] Calculate the volume V of 1 kg of aggregate i1kg , where ρ a is the aggregate density, with the unit of kg / m 3 ;

[0070] Calculate the number of particles N of 1 kg of aggregate i1kg , where ν i is the volume of the average particle, with the unit of m 3 ;

[0071] Calculate the specific surface area factor α i , α i = N i1kg .s i , where s i is the surface area of the average particle, with the unit of m 2 .

[0072] ② Multiply the specific surface area factor α i by the mass percentage P for each aggregate component belonging to the grading curve, and sum all the contributions to calculate the total specific surface area SSA of the mineral aggregate covered by the original asphalt agg :

[0073] SSA agg = ∑α i ·(P i+1 - P i ), where Ρ i represents the cumulative passing rate at particle size i, and Ρ i+1 represents the cumulative passing rate at particle size i + 1.

[0074] ③ Use the optimum film thickness t opt-agg to calculate the asphalt volume V required for the aggregate bit-agg .

[0075] V bit-agg = t opt-agg ·SSA agg , where t opt-agg is 10 μm.

[0076] Step 4, calculation of the asphalt dosage required for the filler

[0077] The calculation method of the asphalt amount for filling with the critical filling concentration overcomes the limitation that the specific surface area is difficult to directly measure. That is, when the filler reaches a certain concentration in the asphalt mixture, the stiffness of the asphalt changes significantly, marking the transition from the dilution zone (where the filler particles are separated by the free asphalt volume) to the concentration zone (where the free asphalt begins to decrease and the bonding ability of the asphalt decreases). The determination of the critical filling concentration helps to calculate the minimum asphalt volume required to ensure that the asphalt has appropriate stiffness and fluidity during production. The specific calculation formula is based on the volume and weight of the filler, the density of the filler, and the critical filling concentration to determine the required asphalt volume. The calculated asphalt volume needs to be multiplied by the density of the asphalt to obtain the actual required asphalt mass.

[0078] Calculate the critical filling concentration of the filler and the minimum amount of asphalt required to keep the adhesive in the dilution stage after producing the asphalt mixture according to the critical filling concentration. Preferably, use a laser diffractometer or an optical particle size analyzer to measure the particle size distribution (PSD) of the filler; use the BET method to measure the specific surface area of the filler and calculate its effective specific surface area according to different filler types (such as limestone, slaked lime, mineral powder, etc.); use the following formula to calculate the critical concentration φ of the filler c :

[0079] φ c = 83.2RV(%) + 4.79MBV, where RV(%) is the Rigden porosity and MBV is the methylene blue value.

[0080] The critical filling concentration is used to calculate the minimum amount of asphalt required to keep the adhesive in the dilution stage after producing the asphalt mixture.

[0081]

[0082]

[0083] Where: ρ f represents the filler density, unit kg / m 3 W filler represents the filler mass, unit kg, V filler represents the filler volume, unit m3, V bit-filler represents the asphalt volume used for coating the filler, unit m 3 φ c represents the critical filling concentration, unit %.

[0084] Step 5, calculate the total asphalt dosage.

[0085] Specifically, add the asphalt dosage required for the aggregate and the asphalt dosage required for the filler to obtain the total asphalt dosage. Calculate the total asphalt dosage: V bit-tot = V bit-agg + Vbit-filler ;

[0086]

[0087] Furthermore, these theoretical results are also verified through the design of asphalt mixtures in practical applications to ensure that the calculated asphalt quantity and ratio meet the requirements of actual production. Specifically, first, based on the calculated asphalt dosage, hot mix asphalt (HMA) is prepared, that is, standard specimens are prepared according to the calculated asphalt content, and mixture specimens are made according to the target ratio respectively.

[0088] Secondly, the performance of the asphalt mixture is verified through a series of tests (such as Marshall test, gyratory compactor test, indirect tensile strength test, splitting tensile strength test, fatigue test, etc.) to ensure that it meets the design requirements.

[0089] Specifically, specimens are made using a Marshall compactor according to different asphalt contents. Four groups of specimens are made for each asphalt content to ensure the reliability of the experimental data. The stability, flow value, asphalt saturation, and void ratio of the asphalt mixture specimens are measured by Marshall tests.

[0090] According to the stability and flow value, etc., a relationship diagram of the physical and mechanical indexes of the Marshall test under different asphalt contents is drawn to determine the optimal asphalt content. And specimens are made according to the obtained optimal asphalt dosage for performance testing. The high and low temperature stability is evaluated through indirect tensile tests. The fatigue performance of the asphalt mixture under long-term loads is tested through fatigue tests to simulate the impact of high-load traffic on the road. Evaluate whether the performance of the specimens made from the calculated optimal asphalt content meets the specification requirements. At the same time, evaluate whether the error between the calculated asphalt content and the result of the optimal asphalt dosage in the experiment is reasonable and whether it can prove the rationality of the above calculation process.

[0091] The present invention relates the asphalt dosage to the asphalt film thickness and the asphalt dosage parameters required for aggregates and fillers, and establishes a correlation evaluation method, which is more accurate than calculating the asphalt dosage based on volume parameters. Through the evaluation method provided by the present invention, the asphalt dosage can be evaluated quickly and accurately, and the optimal asphalt dosage range can be determined, greatly saving resources.

[0092] In addition, to achieve the above object, the present invention also provides an asphalt mixture mix design system based on machine vision. The system includes a memory, a processor, and a machine vision-based asphalt mixture mix design program stored on the memory and executable on the processor. When the machine vision-based asphalt mixture mix design program is executed by the processor, it realizes the steps of the machine vision-based asphalt mixture mix design method as described in any one of the above.

[0093] In addition, to achieve the above object, the present invention further provides a computer storage medium, on which a machine vision-based asphalt mixture mix design program is stored. When the machine vision-based asphalt mixture mix design program is executed by a processor, the steps of the machine vision-based asphalt mixture mix design method described in any one of the above are implemented.

[0094] Furthermore, to better illustrate the effects of the present invention, the following takes AC asphalt mixture as an example to conduct machine vision-based asphalt mixture mix design.

[0095] Example 1:

[0096] 1. Prepare raw materials.

[0097] In this experimental material, the aggregate is AC-B16 and the aggregate needs to be screened according to the target gradation curve. The gradation curve graph can be seen in the appendix Figure 1 and the filler part selects limestone.

[0098] Aggregate quality parameters: 2741 kg / m 3 The quality parameters of limestone include: density: 2705 kg / m 3 . Ridgen void ratio: 32%, methylene blue value 4. Conventional asphalt is used, with a penetration of 82 (10 -1 mm), a softening point of 47.8 °C, and a penetration index (PI) of -0.6, meeting the requirements of AC-B16.

[0099] 2. Calculate the specific surface area factor of the aggregate, the total specific surface area of the aggregate, and the asphalt dosage of the aggregate.

[0100] Use a FARO ARMPLATINIUM laser scanner to scan 16 - 19 mm aggregate particles to obtain a three-dimensional image with an accuracy of 0.03 mm. Use the three-dimensional scan data to establish a surface model of the aggregate. The three-dimensional images of aggregates of different sizes are as Figure 3 shown. Use software such as Meshlab and Geomagic to process the three-dimensional images of the aggregates to accurately calculate the surface area and volume of the aggregates.

[0101] Calculate how many particles of a certain size exist in one kilogram of these aggregates, and multiply the number of particles with the "average" particle area to obtain the specific surface area factor α i , and the calculation is as follows:

[0102] Calculate the volume V of 1 kg of aggregate i1kg , where ρ a is the aggregate density, with the unit of kg / m 3 ;

[0103] Calculate the number of particles N of 1 kg of aggregatei1kg , where ν i is the volume of the average particle, with the unit of m 3 ;

[0104] Calculate the specific surface area factor α i , α i = N i1kg .s i

[0105] where s i is the surface area of the average particle, with the unit of m 2 .

[0106] The following is a calculation example for the particle size range of 19 / 16 mm:

[0107] Aggregate density: ρ a = 2741 kg / m 3 ;

[0108] Average particle surface area: s i = 3.56×10 -3 m 2 ;

[0109] Average particle volume: ν i = 1.3×10 -5 m 3 ;

[0110] The number of particles per 1 kg of aggregate:

[0111] Specific surface area factor α i = N i1kg .s i = 28.06×3.56×10 -3 = 0.09989 m 2 / kg;

[0112] Obtained by similar calculations for all particle size ranges, the specific surface area factors for each particle size are shown in Table 1.

[0113] Table 1 Specific surface area factors for particle sizes

[0114]

[0115] Table 2 Mass-weighted surface areas for particle sizes

[0116]

[0117]

[0118] Calculate the total specific surface area:

[0119] The specific surface area factor α for each particle size range i is weighted and summed according to the particle size distribution (Ρ i+1 -Ρ i ), where Table 2 is the mass-weighted surface area of the particle size, and the total specific surface area of the aggregate is expressed as:

[0120] SSA agg = ∑α i ·(P i+1 -P i ) = 2.544 m 2 / kg.

[0121] Using the optimal coating thickness t opt-agg = 10 μm to calculate the asphalt volume required for the aggregate:

[0122] V bit-agg = t opt-agg ·SSA agg = 2.544×10 -5 m 3 / kg.

[0123] 3. Calculate the asphalt dosage for the filler

[0124] Key parameters:

[0125] Filler passing rate: 7%; Ridgen void ratio: 32%; Methylene blue value 4.

[0126] Calculated by the following equation below the critical filler concentration:

[0127] φ c = 83.2RV(%) + 4.79MBV = 46%;

[0128] Filler density: 2705 kg / m 3 .

[0129] Filler volume V filler :

[0130]

[0131] The asphalt volume V bit-filler required for the filler:

[0132]

[0133] 4. Calculate the total asphalt volume and asphalt content.

[0134] V bit-tot = V bit-agg + V bit-filler = 5.582×10 -5 m 3 / kg.

[0135] Known asphalt density: 1030 kg / m 3 , the asphalt mass percentage is calculated to be 5.75%, and the final asphalt content is: 5.43%.

[0136] 5. Performance testing and performance verification.

[0137] Specimens are made using a Marshall compactor at different asphalt contents (4.5%, 5.0%, 5.5%, 6.0%). Standard specimens are prepared according to the calculated asphalt content, and mixture specimens are made according to the target ratio. Specimens are made using a Marshall compactor at different asphalt contents. Four groups of specimens are made for each asphalt content to ensure the reliability of the experimental data. The specific test results are shown in Table 3.

[0138] Table 3 Summary of volume parameters, stability and flow value of Marshall specimens of AC - B16 type asphalt mixture

[0139]

[0140] The stability, flow value, asphalt saturation, and void ratio of the asphalt mixture specimens are measured by the Marshall test. Based on the stability and flow value, etc., a relationship diagram of the physical and mechanical indexes of the Marshall test at different asphalt contents is drawn (as shown in the appendix Figures 4 - 10 ), and the optimal asphalt content is determined.

[0141] The optimal asphalt dosage is obtained as 5.52% from the relationship diagram of mechanical indexes. At an asphalt content of 5.52%, the density value is 2.472 g / cm 3 , and this value indicates that the mixture has reached good density. At an asphalt content of 5.52%, the stability reaches 8.3 kN, which is higher than the requirements of many road standards, indicating that the mixture under this asphalt dosage has good anti - deformation ability under high - load environments and can effectively resist the permanent deformation caused by traffic loads. Flow value: The flow value is 3.0 mm, indicating that this asphalt content can ensure that the mixture has good anti - deformation ability and appropriate fluidity, meeting the design requirements; Void ratio: The void ratio is 5.9%, which meets the target range (3% - 6%), indicating that this asphalt content ensures appropriate density.

[0142] In the indirect tensile test, the specimens are loaded to failure at three different temperatures (-10°C, 15°C, and 40°C), and the tensile strength is calculated. Tensile strength is an important index for the crack resistance of the mixture, especially under low - temperature and high - temperature conditions. This test mainly examines the low - temperature crack resistance and fatigue resistance of the asphalt mixture. In the indirect tensile strength test, specimens with four different asphalt contents (4.5%, 5.0%, 5.5%, 6.0%) are tested at three temperatures (-10°C, 15°C, 40°C), and the test results are shown in Table 4.

[0143] Table 4 - Indirect Tensile Strength of Four Different Asphalt Contents

[0144]

[0145] The mixture with 5.52% asphalt content shows good mechanical properties at different temperatures, meeting the usage requirements under various climate conditions. The tensile strength at normal temperature is 1.8 MPa, far higher than the critical value of 1.0 MPa, indicating good tensile strength under normal temperature conditions and being able to effectively resist the tensile force of the road surface during daily use.

[0146] The tensile strength at high temperature is 0.8 MPa. Although it is lower than that at normal temperature, it is still greater than the critical value of 0.5 MPa, proving that this mix proportion still has good tensile properties under high temperature conditions.

[0147] In the fatigue resistance test, the fatigue performance of the asphalt mixture under long-term load is simulated to evaluate its durability. Intermittent loading is carried out, with each loading of 0.3 MPa, a loading frequency of 10 Hz, and 100,000 loadings. The fatigue life reaches 100,000 times, significantly higher than the critical fatigue life of 90,000 times, indicating that this asphalt mixture has good fatigue resistance during long-term use.

[0148] The error between the optimal asphalt dosage of 5.52% in the experiment and the asphalt content of 5.43% calculated by the formula is only 0.09%. This embodiment proves that the asphalt mix proportion design method based on the true surface area of the aggregate and the critical concentration of the filler has high accuracy and applicability. The asphalt dosage estimated by this method can not only significantly reduce the experimental workload but also optimize the durability and performance of HMA.

[0149] Example 2:

[0150] 1. Prepare raw materials.

[0151] In this experimental material, the aggregate selects aggregates with different particle size ranges according to AC - B20: 19 - 26.5 mm, 16 - 19 mm, 13.2 - 16 mm, 9.5 - 13.2 mm, 4.75 - 9.5 mm, 2.36 - 4.75 mm, 1.18 - 2.36 mm, 0.6 - 1.18 mm, 0.3 - 0.6 mm, 0.15 - 0.3 mm, 0.075 - 0.15 mm.

[0152] The filler part selects hydrated lime.

[0153] Aggregate mass parameter: 2800 kg / m 3 . The hydrated lime mass parameters include: density: 2249 kg / m 3. Ridgen void ratio: 40%. Methylene blue value 4. Using conventional road asphalt, the penetration is 88 (10 -1 mm), the softening point is 50.4 °C, and the penetration index (PI) is -0.5, meeting the requirements of AC-B-20.

[0154] 2. Calculate the aggregate specific surface area factor, the total specific surface area of the aggregate, and the aggregate asphalt dosage.

[0155] Use a FARO ARMPLATINIUM laser scanner to scan 19 - 26.5 mm aggregate particles to obtain a three-dimensional image with an accuracy of 0.03 mm. Establish a surface model of the aggregate using the three-dimensional scan data. The three-dimensional images of aggregates of different sizes are as Figure 11 shown. Use software such as Meshlab and Geomagic to process the three-dimensional images of the aggregates to accurately calculate the surface area and volume of the aggregates.

[0156] Calculate the specific surface area factor for each aggregate particle size and weighted average according to its mass percentage to obtain the total specific surface area factor of the aggregate. The following are the specific surface area factors for aggregates of different particle sizes:

[0157] Obtained by similar calculations for all particle size ranges. The specific surface area factor for each particle size is shown in Table 5, and the mass-weighted surface area of the particle size is shown in Table 6.

[0158] Table 5 Specific surface area factor of particle size

[0159]

[0160] Table 6 Mass-weighted surface area of particle size

[0161]

[0162] Calculate the total specific surface area:

[0163] Multiply the specific surface area factor α of each particle size range i by the particle size distribution (Ρ i+1 -Ρ i ) and sum them up to obtain the total specific surface area of the aggregate: SSA agg = ∑α i ·(P i+1 -P i ) = 3.210 m 2 / kg.

[0164] Use the optimal coating thickness t opt-agg = 10 μm to calculate the asphalt volume required for the aggregate:

[0165] V bit-agg = t opt-agg ·SSA agg= 3.210×10 -5 m 3 / kg。

[0166] 3. Calculate the asphalt dosage for the filler

[0167] Key parameters:

[0168] Filler passing rate: 7%; Ridgen void ratio: 40%; Methylene blue value 4.

[0169] Below the critical filler concentration, it is calculated by the following equation:

[0170] φ c = 83.2RV(%) + 4.79MBV = 52.4%.

[0171] Filler density: 2249 kg / m 3 .

[0172] The volume of asphalt required for the filler V bit-filler :

[0173]

[0174] 4. Calculate the total asphalt volume and asphalt content.

[0175] V bit-tot = V bit-agg + V bit-filler = 6.032×10 -5 m 3 / kg。

[0176] Given asphalt density: 1030 kg / m 3 , the calculated asphalt mass percentage is 6.21%, and the final asphalt content is 5.85%

[0177] 5. Performance testing and performance verification

[0178] Prepare specimens using a Marshall compactor at different asphalt contents (4.5%, 5.0%, 5.5%, 6.0%). Prepare standard specimens according to the calculated asphalt content and make mixture specimens according to the target mix ratio. Prepare specimens using a Marshall compactor at different asphalt contents. Make 4 groups of specimens for each asphalt content to ensure the reliability of the experimental data. The test results are shown in Table 7 below.

[0179] Table 7 is a summary of the volume parameters, stability, and flow value of Marshall specimens of AC-B-20 type asphalt mixture

[0180]

[0181] The stability, flow value, asphalt saturation, void ratio, stability and flow value of asphalt mixture specimens are measured by the Marshall test. The relationship diagram of physical and mechanical indexes of the Marshall test under different asphalt contents is drawn (attached Figures 12 - 18 as shown), and the optimum asphalt content is determined. Based on these data, the optimum asphalt dosage is 5.9%. When the optimum asphalt dosage is 5.9%, the stability is 8.7 KN, indicating that this mix ratio has good anti-deformation ability and is suitable for high-strength traffic roads. The flow value is 3.0 mm, and the flow value is moderate, indicating that the asphalt mixture has good fluidity and can obtain good compactness during construction. The void ratio is 5.2%, which is in the ideal range, indicating that this asphalt mixture is relatively dense and can effectively enhance durability and water damage resistance.

[0182] The ITST test measures the tensile strength of the mixture at different temperatures to evaluate its low-temperature crack resistance and high-temperature stability. The test conditions are -10°C, 15°C and 40°C, and the results are shown in Table 8 below.

[0183] Table 8 Indirect tensile strength test data of AC-B20 type asphalt mixture

[0184]

[0185] Among them, the tensile strength of the optimum asphalt dosage of 5.9% at normal temperature is 2.8 MPa, which is significantly higher than the critical value of 1.0 MPa, indicating that this asphalt mixture has strong tensile properties at normal temperature. The tensile strength at high temperature is 1.2 MPa. Although it is lower than that at normal temperature, it is still higher than the critical value of 0.5 MPa, indicating that this mixture shows good tensile strength at high temperature.

[0186] In the fatigue test, the fatigue performance of the asphalt mixture under long-term load is simulated to evaluate its durability. Intermittent loading, 0.3 MPa for each load, loading frequency 10 Hz, and loading 100,000 times. The fatigue life reaches 105,000 times, which is significantly higher than the critical fatigue life of 95,000 times, indicating that this asphalt mixture has good fatigue resistance and is suitable for roads with long-term high-strength loads.

[0187] The error between the optimum asphalt dosage of 5.9% in the experiment and the asphalt content of 5.85% calculated by the formula is only 0.05%. That is, the asphalt content calculated by the formula meets the standard.

[0188] It should be noted that in this document, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article or system comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, article or system comprising such element.

[0189] The serial numbers of the embodiments of the present invention above are for description only and do not represent the superiority or inferiority of the embodiments.

[0190] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for designing the mix proportion of asphalt mixture based on machine vision, characterized in that, The method includes the following steps: Step 1: Obtain the types of raw material components of the target asphalt mixture. The raw material components of the asphalt mixture include aggregates, asphalt, and fillers, and the particle size of the fillers is less than 0.075 mm. The aggregates have various particle size distributions and each particle size of the aggregates has a corresponding mass percentage; Step 2: Determine the covering thickness of the corresponding asphalt on the aggregates according to the target asphalt mixture; Step 3: Obtain the three-dimensional image data of the aggregates by a scanning device, establish a surface model of the aggregates based on the three-dimensional image data, and determine the asphalt volume required for the aggregates in the target asphalt mixture according to the surface model of the aggregates and the covering thickness on the aggregates; Step 4: Obtain the asphalt volume required for the fillers in the target asphalt mixture according to the critical filler concentration; Step 5: Add the asphalt volume required for the aggregates in the target asphalt mixture to the asphalt volume required for the fillers in the target asphalt mixture to obtain the total asphalt volume used in the target asphalt mixture, so as to determine the mix ratio of each component in the target asphalt mixture.

2. The method for designing the mix proportion of asphalt mixture based on machine vision according to claim 1, characterized in that In Step 2, the covering thickness range of the asphalt on the aggregates is 5 - 15 μm.

3. The method for designing the mix proportion of asphalt mixture based on machine vision according to claim 1, characterized in that, In Step 3, the scanning device is a FARO ARM PLATINIUM laser scanner or a CT scanner.

4. The method for designing the mix proportion of asphalt mixture based on machine vision according to claim 1, characterized in that, In Step 3, the steps of establishing a surface model of the aggregates based on the three-dimensional image data include: Calculate the surface area factor of each particle size of the aggregates according to the three-dimensional image data; Obtain the total surface area of the aggregates according to the mass percentage of each particle size of the aggregates and the surface area factor of each particle size of the aggregates to determine the surface model of the aggregates.

5. The method for designing the mix proportion of asphalt mixture based on machine vision according to claim 4, characterized in that, The specific calculation formula for calculating the surface area factor of each particle size of the aggregates according to the three-dimensional image data is: Calculate the volume V of 1 kg of aggregate i1kg , where ρ a is the aggregate density, in kg / m 3 ; Calculate the number of particles N in 1 kg of aggregate i1kg , where ν i is the volume of the average particle, in m 3 ; Calculate the specific surface area factor α i , α i = N i1kg .s i , where s i is the surface area of the average particle in m 2 .

6. The method for designing the mix proportion of asphalt mixture based on machine vision according to claim 5, wherein, The specific calculation formula for obtaining the total surface area of the aggregates according to the mass percentage of each particle size of the aggregates and the surface area factor of each particle size of the aggregates is: SSA agg = ∑α i ·(P i+1 - P i ), where SSA agg is the total surface area of the aggregate, Ρ i represents the cumulative passing rate at particle size i, Ρ i+1 represents the cumulative passing rate at particle size i + 1, and the passing rate is in mass percentage.

7. The method for designing the mix proportion of asphalt mixture based on machine vision according to claim 6, wherein The specific formula for determining the asphalt volume required for the aggregates in the target asphalt mixture according to the surface model of the aggregates and the covering thickness on the aggregates is: V bit-agg = t opt-agg ·SSA agg , where t opt-agg is the covering thickness on the aggregate, and V bit-agg is the asphalt volume required for the aggregate.

8. The method for designing the mix proportion of asphalt mixture based on machine vision according to claim 1, characterized in that, The specific formula for obtaining the asphalt volume required for the fillers in the target asphalt mixture according to the critical filler concentration is: V filler represents the packing volume, with the unit of m 3 , V bit-filler represents the asphalt volume used for coating the packing, with the unit of m 3 , φ c represents the critical packing concentration, with the unit of %.

9. An asphalt mixture mix design system based on machine vision, characterized in that, The system includes a memory, a processor, and a machine vision-based asphalt mixture mix ratio design program stored on the memory and operable on the processor. When the machine vision-based asphalt mixture mix ratio design program is executed by the processor, it realizes the steps of the machine vision-based asphalt mixture mix ratio design method as described in any one of claims 1 to 8.

10. A computer storage medium, characterized in that, A machine vision-based asphalt mixture mix ratio design program is stored on the computer storage medium. When the machine vision-based asphalt mixture mix ratio design program is executed by the processor, it realizes the steps of the machine vision-based asphalt mixture mix ratio design method as described in any one of claims 1 to 8.

Images