Method and system for predicting tensile strength of asphalt mixture on basis of cohesive strength of asphalt mortar, and electronic device
By establishing a prediction model based on the cohesive strength of asphalt mortar and the splitting tensile strength of asphalt mixture, the problems of long test cycle and high instrument accuracy of asphalt mixture tensile strength were solved, achieving efficient and accurate tensile strength prediction and optimizing the mix proportion and construction process of asphalt mixture.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- SOUTH CHINA UNIV OF TECH
- Filing Date
- 2025-10-17
- Publication Date
- 2026-07-23
AI Technical Summary
Existing tensile strength tests for asphalt mixtures have long testing cycles and require highly accurate testing instruments, making it difficult to obtain tensile strength data efficiently and cost-effectively.
By acquiring datasets of splitting tensile strength of asphalt mixtures and cohesive strength of asphalt mortar, and dividing them into training and testing sets, a prediction model for the tensile strength of asphalt mixtures was established. The cohesive strength of asphalt mortar was used as the independent variable, and the natural logarithm of the splitting tensile strength of asphalt mixtures was used as the dependent variable. Data fitting and iteration were performed to generate the prediction model.
It enables rapid and efficient prediction of the tensile strength of asphalt mixtures, reduces testing costs and time, improves evaluation efficiency, lowers the accuracy requirements of testing instruments, and enhances the accuracy and adaptability of the prediction model.
Smart Images
Figure CN2025128561_23072026_PF_FP_ABST
Abstract
Description
A method, system, and electronic equipment for predicting the tensile strength of asphalt mixtures based on the cohesive strength of asphalt mortar. Technical Field
[0001] This application relates to a method, system, and electronic equipment for predicting the tensile strength of asphalt mixtures based on the cohesive strength of asphalt mortar, belonging to the technical field of materials testing or analysis. Background Technology
[0002] To ensure the superior performance of asphalt pavements, asphalt mixtures must meet certain road performance requirements before they can be used in engineering projects. Common mechanical properties of asphalt mixtures include shear strength, flexural strength, tensile strength, and compressive strength. Among these, tensile strength plays a particularly important role in asphalt mixtures, especially in directly affecting the low-temperature crack resistance and durability of asphalt pavements. Higher tensile strength allows asphalt mixtures to better withstand external tensile stresses, reducing crack formation and thus extending the service life of asphalt pavements.
[0003] Bending beam tests, direct tensile tests, and indirect tensile tests are all used to evaluate the tensile properties of asphalt mixtures. Among these, the indirect tensile test, also known as the splitting tensile test, is widely used for asphalt mixture performance evaluation and asphalt pavement analysis. During the splitting test, as the load increases, the stress state in the middle of the specimen is quite similar to the stress state of the pavement subbase when the load is applied. It plays an important role in the performance evaluation and engineering applications of asphalt mixtures, especially in low-temperature crack resistance, fatigue resistance, and durability. It not only provides data support for asphalt mixture mix design but also ensures the stability and safety of asphalt pavements during long-term use.
[0004] To address the problem of cracking in asphalt mixtures, it is necessary to evaluate them. Existing tests for evaluating the tensile strength of asphalt mixtures require pre-formed specimens, have long testing cycles, and demand high-precision testing equipment. Therefore, obtaining the tensile strength of asphalt mixtures more efficiently and cost-effectively has become an urgent problem to be solved. Summary of the Invention
[0005] The purpose of this application is to provide a method, system, and electronic equipment for predicting the tensile strength of asphalt mixtures based on the cohesive strength of asphalt mortar, which addresses the shortcomings of existing technologies such as long testing cycles and high precision requirements for testing instruments.
[0006] The embodiments of this application provide the following solutions:
[0007] A method for predicting the tensile strength of asphalt mixtures based on the cohesive strength of asphalt mortar, applied to the generation of a prediction model for the tensile strength of asphalt mixtures, includes:
[0008] To obtain the splitting tensile strength of asphalt mixtures and the cohesive strength of asphalt mortars;
[0009] The datasets of splitting tensile strength of asphalt mixture and cohesive strength of asphalt mortar are divided into training set and test set. The training set is subjected to data fitting processing to obtain the training model of tensile strength of asphalt mixture. The training model of tensile strength of asphalt mixture includes: the independent variable is the cohesive strength of asphalt mortar, the dependent variable is the splitting tensile strength of asphalt mixture, and the dependent variable is the natural logarithm of the independent variable.
[0010] The training model for the tensile strength of asphalt mixtures is tested using a test set. The relative error between the test values and the actual experimental values is detected. If the relative error is less than a preset threshold, a prediction model for the tensile strength of asphalt mixtures is generated.
[0011] Furthermore, obtaining the splitting tensile strength of the asphalt mixture and the cohesive strength of the asphalt mortar further includes:
[0012] Asphalt mixture specimens were prepared, and splitting tensile strength of asphalt mixtures was obtained by conducting splitting tensile tests at different temperatures.
[0013] Asphalt mortar was prepared, and a pull-out test was conducted at the corresponding temperature to obtain the cohesive strength of the asphalt mortar. Specifically, the content of each aggregate and the asphalt content in the mortar were kept consistent with the original mixture. Asphalt mortar was prepared, and the cohesive strength of the asphalt mortar at different temperatures was obtained by pull-out test.
[0014] The conditions for the splitting test of asphalt mixtures and the pull-out test of asphalt mortar were matched, and both tests used water bath insulation and uniform loading.
[0015] Based on the obtained splitting tensile strength of asphalt mixture and cohesive strength of asphalt mortar, training set and test set are formed. The tensile strength prediction model of asphalt mixture is obtained by fitting the training set.
[0016] Furthermore, in the process of preparing asphalt mortar, the aggregate distribution of the mortar is converted according to the asphalt mixture gradation, and the amount of asphalt is determined by the specific surface area method.
[0017] Set the size of the slab, the pull rate, and the diameter of the pull head required for the pull test. Heat the pull head and the slab. Apply the same mass of asphalt mortar to the groove of the pull head. Press the pull head against the slab until it contacts the slab. Let it stand and cool to room temperature.
[0018] After water bath temperature control, a pull-out test was conducted to read the maximum tensile force when the asphalt mortar was damaged, and the average value was taken as the experimental result.
[0019] Furthermore, the process of dividing the datasets of splitting tensile strength of asphalt mixtures and cohesive strength of asphalt mortar into training and testing sets, and performing data fitting processing on the training set to obtain a training model for the tensile strength of asphalt mixtures, further includes:
[0020] The independent variable in the asphalt mixture tensile strength training model is the asphalt mortar cohesive strength, and the dependent variable is the asphalt mixture splitting tensile strength. The dependent variable is the natural logarithm of the independent variable, satisfying the following formula:
[0021]
[0022] In this context, the cohesive strength of asphalt mortar is the independent variable x, the splitting tensile strength of asphalt mixture is the dependent variable y, C is a constant, and A is the coefficient of the dependent variable.
[0023] Furthermore, during the data fitting process of the training set, different functions are fitted, and the corresponding model parameters are adjusted.
[0024] The tensile strength training model of asphalt mixture was iterated multiple times, and the model parameters were adjusted until the model reached fitting convergence under the logarithmic function. The tensile strength training model of asphalt mixture was then used to predict the test set to obtain the corresponding predicted values.
[0025] The relative error between the predicted value and the actual test value is calculated until the tensile strength training model of asphalt mixture meets the error threshold, and then the tensile strength prediction model of asphalt mixture is generated.
[0026] Further preferred options include:
[0027] One or more asphalt mixtures are input into the asphalt mixture tensile strength prediction model, the prediction temperature range is set, the model fitting effect is obtained, and the tensile strength of the asphalt mixture is obtained.
[0028] Further preferred methods include: acquiring asphalt mixture samples, generating corresponding asphalt mixture images and performing corresponding binarization processing, selecting thresholds to distinguish asphalt mortar and aggregate areas, and acquiring rectangular slice color images of asphalt mixture samples using sample slicing method and digital image scanning technology.
[0029] The asphalt mortar region and the aggregate region are separated by a connected component labeling algorithm to form different region labels. The distribution of the asphalt mortar region is analyzed by calculating the pixel value histogram of the asphalt mortar region in the image.
[0030] The rectangular slice color image is cropped at the image center, and a representative volume element is set as a sliding window to obtain the processed rectangular slice color image. Calculations are then performed based on the inherent and relative uniformity of the asphalt mixture sample.
[0031] The normal distribution curves of different asphalt mixtures are fitted, and the normal distribution curve of the asphalt mixture is selected as the benchmark for calculation to obtain the KLD divergence value of different asphalt mixtures. The uniformity of the asphalt mixture sample is determined based on the KLD divergence value.
[0032] More preferably, the step of acquiring asphalt mixture samples, generating corresponding asphalt mixture images and performing corresponding binarization processing, and acquiring rectangular slice color images of asphalt mixture samples using sample slicing method and digital image scanning technology, further includes:
[0033] The rectangular slice color image is preprocessed by using image enhancement technology and median filtering algorithm to eliminate brightness unevenness and image noise, and by using image binarization algorithm to define different colors for mortar area and coarse aggregate area in grayscale image.
[0034] An electronic device includes: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus; the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the method.
[0035] A computer program product includes a computer program that, when executed by a processor, implements the method.
[0036] The embodiments of this application have the following advantages compared with the prior art:
[0037] (1) Based on data such as the splitting tensile strength of asphalt mixture and the cohesive strength of asphalt mortar, this application embodiment uses a training set to perform data fitting processing and establish a corresponding training model for the tensile strength of asphalt mixture. Then, the training model for the tensile strength of asphalt mixture is tested using a test set, and a corresponding prediction model for the tensile strength of asphalt mixture is generated based on the comparison results between the relative error and the preset threshold. This application embodiment establishes a mathematical model to establish the mapping relationship between the cohesive strength of asphalt mortar and the splitting tensile strength of asphalt mixture. Only a pull-out test of asphalt mortar is needed to predict the tensile strength of the mixture, which can save a lot of test costs, improve evaluation efficiency, and eliminate the need to provide molded specimens every time the tensile strength test of asphalt mixture is conducted, thus shortening the test cycle and reducing the accuracy requirements of the test instruments. It can obtain the tensile strength value of asphalt mixture efficiently and economically.
[0038] (2) This application obtains the model fitting effect by reasonably setting the predicted temperature range. For example, when the base asphalt and modified asphalt are used as asphalt mixtures and the predicted temperature range is 10℃-25℃, the model fitting effect is better than 95%. By applying the asphalt mixture tensile strength prediction model to asphalt mixtures, the purpose of quickly and efficiently calculating the tensile strength of asphalt mixtures is achieved.
[0039] (3) The embodiments of this application also realize the processing of asphalt mixture images through image enhancement technology and application of the mean filtering algorithm. The uniformity of mortar and aggregate distribution of different asphalt mixture samples can be measured by KLD divergence value, thereby evaluating the reliability and accuracy of the asphalt mixture tensile strength prediction model. Attached Figure Description
[0040] To more clearly illustrate the specific implementation methods of the embodiments of this application or the technical solutions in the prior art, the drawings used in the description of the specific implementation methods or the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0041] Figure 1 is a flowchart of a method for predicting the tensile strength of asphalt mixtures based on the cohesive strength of asphalt mortar.
[0042] Figure 1A is a flowchart of the optimization technical solution from steps S11 to S13.
[0043] Figure 1B is a flowchart of the optimized technical solution for steps S121 to S123.
[0044] Figure 2 is a diagram of the architecture of the asphalt mixture tensile strength prediction system based on the cohesive strength of asphalt mortar.
[0045] Figure 3 is a flowchart of a specific application of the asphalt mixture tensile strength prediction model.
[0046] Figure 4 is a coordinate graph of pull-out strength versus splitting strength.
[0047] Figure 5 is a schematic diagram of the electronic device. Embodiments of the present invention
[0048] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of the embodiments of this application.
[0049] Figure 1 shows a method for predicting the tensile strength of asphalt mixtures based on the cohesive strength of asphalt mortar. This method is applied to generate a prediction model for the tensile strength of asphalt mixtures, including:
[0050] Step S1: Obtain the splitting tensile strength of asphalt mixture and the cohesive strength of asphalt mortar. In step S1, the splitting tensile strength of asphalt mixture can be obtained by splitting test, and the cohesive strength of asphalt mortar at different temperatures can be obtained by pull-out test.
[0051] Step S2: Divide the datasets of splitting tensile strength of asphalt mixture and cohesive strength of asphalt mortar into training set and test set. Perform data fitting processing on the training set to obtain the training model of tensile strength of asphalt mixture. The training model of tensile strength of asphalt mixture includes: the independent variable is the cohesive strength of asphalt mortar, the dependent variable is the splitting tensile strength of asphalt mixture, and the dependent variable is the natural logarithm of the independent variable.
[0052] Step S3: Test the asphalt mixture tensile strength training model using the test set, and detect the relative error between the test value and the actual test value. If the relative error is less than the preset threshold, generate the asphalt mixture tensile strength prediction model.
[0053] The technical solutions provided in steps S1 to S3 aim to predict the tensile strength of asphalt mixtures. The splitting tensile strength of asphalt mixtures and the cohesive strength of asphalt mortar are obtained experimentally. These data are then divided into training and testing sets. A tensile strength prediction model for asphalt mixtures is established using the training set data. This model uses the cohesive strength of asphalt mortar as the independent variable and the natural logarithm of the splitting tensile strength of asphalt mixtures as the dependent variable. The model is validated using the testing set. If the relative error between the model's prediction and the actual experimental value is within an acceptable range, then the model can serve as an effective prediction tool for evaluating the tensile strength of asphalt mixtures.
[0054] The inventors discovered that the splitting tensile strength of asphalt mixtures is mainly composed of the strength of the asphalt mortar and the adhesion between asphalt and aggregates. However, a functional model relating these two factors has not yet been proposed. The technical solutions provided in steps S1 to S3 are based on this technical problem and aim to reveal the relationship between splitting tensile strength, asphalt mortar strength, and the adhesion between asphalt and aggregates. The technical solutions provided in steps S1 to S3 enable the establishment of a mathematical model for the tensile strength of asphalt mixtures. This mathematical model obtains key physical performance parameters, namely the splitting tensile strength of the asphalt mixture and the cohesive strength of the asphalt mortar, through experimental methods. These physical performance parameters are then transformed into a predictive model for the tensile strength of asphalt mixtures. This predictive model reveals the relationship between the strength of the asphalt mortar and the tensile properties of the asphalt mixture, and also quantifies the impact of the adhesion between asphalt and aggregates on the overall performance.
[0055] The asphalt mixture tensile strength prediction model enhances its generalization ability by dividing the dataset into training and test sets. The training set is used to build the model, while the test set is used to verify the model's prediction accuracy. Correctly establishing the training and test sets ensures that the asphalt mixture tensile strength prediction model is not only theoretically sound but also highly reliable in practical applications. When the relative error between the model's prediction and the actual experimental value is within an acceptable range, the tensile strength of asphalt mixtures can be evaluated under different environments and conditions, providing a scientific basis for road design and construction. This improves the efficiency and accuracy of asphalt mixture performance evaluation, significantly reduces reliance on traditional destructive testing, lowers testing costs, accelerates the research and development and performance improvement of asphalt materials, optimizes the mix design and construction process of asphalt mixtures, significantly improves road durability and reliability, reduces maintenance costs, extends road service life, and provides strong support for promoting technological improvements in road engineering.
[0056] As shown in Figure 1A, in step S1, obtaining the splitting tensile strength of the asphalt mixture and the cohesive strength of the asphalt mortar further includes:
[0057] Step S11: Prepare asphalt mixture specimens and conduct asphalt mixture splitting tests at different temperatures to obtain the splitting tensile strength of the asphalt mixture.
[0058] Step S12: Prepare asphalt mortar and conduct a pull-out test at the corresponding temperature to obtain the asphalt mortar cohesive strength. Specifically, the content of each aggregate and the asphalt content in the mortar are kept consistent with the original mixture. Prepare asphalt mortar and use a pull-out test to obtain the asphalt mortar cohesive strength at different temperatures.
[0059] Step S13: The conditions for the splitting test of asphalt mixture and the pull-out test of asphalt mortar are matched, and both adopt the test methods of water bath insulation and uniform loading.
[0060] Step S14: Based on the obtained splitting tensile strength of asphalt mixture and cohesive strength of asphalt mortar, a training set and a test set are formed. The tensile strength prediction model of asphalt mixture is obtained by fitting the training set.
[0061] The optimized technical solutions provided in steps S11 to S14 systematically obtain key mechanical performance parameters of asphalt mixtures and asphalt mortars through experimental methods, thereby constructing a mathematical model capable of predicting the tensile strength of asphalt mixtures. Firstly, the optimized technical solutions in steps S11 to S14 employ data-driven model construction. Splitting tests are conducted at different temperatures to prepare asphalt mixture specimens to obtain their splitting tensile strength. The actual data obtained through experiments provides a solid foundation for the model, ensuring the consistency between the model's predictions and actual conditions. Furthermore, the influence of temperature is fully considered; experiments are conducted at different temperatures to account for the impact of ambient temperature on asphalt mixture performance, enhancing the model's adaptability to different environmental conditions. Combining experimental results with mathematical modeling improves the accuracy of predictions, providing a scientific basis for the design and construction of asphalt mixtures. This reduces reliance on actual destructive testing, thereby lowering testing costs and improving R&D efficiency. Establishing a corresponding predictive model through detailed and rigorous experimental data helps to better understand the relationship between the cohesive strength of asphalt mortar and the splitting tensile strength of asphalt mixtures, optimizing the mix proportions of asphalt mixtures and improving their performance.
[0062] In the optimized technical solutions provided in steps S11 to S14, the aggregate content of the mortar is consistent with that of the mixture, so that the prediction model has a principle to follow. This is because not any asphalt mortar can predict the performance of asphalt mixtures, and it prevents the situation where the prediction model has no principle to follow. Since the mortar is a part of the asphalt mixture and bears the main tensile strength, the prepared mortar must meet the gradation and the asphalt content must be consistent with that of the mixture.
[0063] As shown in Figure 1B, preferably, the process of preparing asphalt mortar in step S12 further includes the following steps:
[0064] Step S121: Determine the amount of asphalt used by the specific surface area method based on the maximum particle size of the fine aggregate in the mortar. In step S121, the maximum particle size of the fine aggregate can be selected as 0.6 mm, or a range of numbers around 0.6 mm can be selected to ensure that the content of each grade of aggregate and the asphalt content in the mortar are consistent with the original mixture, and to keep the mixing time and temperature the same as the mixture.
[0065] Step S122: Set the size of the stone slab, the pull-out rate, and the diameter of the pull-out head to match the lithology of the fine aggregate required for the pull-out test. Heat the pull-out head and the stone slab. Apply the prepared asphalt mortar to the groove of the pull-out head. Press the pull-out head against the stone slab until it contacts the slab. Let it cool to room temperature. In step S122, heating the pull-out head and the stone slab can be done using an oven at approximately 160°C for about 1 hour.
[0066] In step S123, after water bath treatment, a pull-out test is performed to read the maximum tensile force when the asphalt mortar is damaged, and the average value is taken as the experimental result. In step S123, the water bath is kept at the experimental temperature or room temperature for 1 hour. During the process of taking the average value, each experiment is repeated 4 times and the average value is taken as the experimental result.
[0067] The optimized technical solution provided in steps S121 to S123 prepares asphalt mortar through a series of precisely controlled experimental steps and accurately measures its cohesive strength. By precisely controlling the amount of asphalt and the test conditions, the consistency and repeatability of the asphalt mortar samples are ensured, making the experimental data reliable and accurate. By simulating the temperature and pressure conditions in actual construction, the experimental results better reflect the behavior of asphalt mortar in practical applications. Furthermore, by measuring the maximum tensile force of the asphalt mortar in the pull-out test, its cohesive performance can be directly evaluated, accurately obtaining data on the mechanical characteristics and durability of the asphalt material. Standardized experimental procedures and conditions allow for efficient large-scale testing, thereby rapidly accumulating data and optimizing material design. Repeating experiments and taking average values reduces the impact of random errors and improves the reliability of experimental results. In summary, steps S121 to S123 provide a scientific, accurate, and efficient experimental method for evaluating the performance of asphalt mortar.
[0068] In step S2, the data set of splitting tensile strength of asphalt mixture and cohesive strength of asphalt mortar is divided into a training set and a test set. The training set is then subjected to data fitting processing to obtain a training model for the tensile strength of asphalt mixture. This further includes:
[0069] The independent variable in the asphalt mixture tensile strength training model is the asphalt mortar cohesive strength, and the dependent variable is the asphalt mixture splitting tensile strength. The dependent variable is the natural logarithm of the independent variable, satisfying the following formula:
[0070] ...(1)
[0071] In this context, the cohesive strength of asphalt mortar is the independent variable x, the splitting tensile strength of asphalt mixture is the dependent variable y, C is a constant, and A is the coefficient of the dependent variable.
[0072] In the process of fitting the training set to data, different functions are fitted, and the corresponding model parameters are adjusted.
[0073] The tensile strength training model of asphalt mixture was iterated multiple times, and the model parameters were adjusted until the model reached fitting convergence under the logarithmic function. The tensile strength training model of asphalt mixture was then used to predict the test set to obtain the corresponding predicted values.
[0074] The relative error between the predicted value and the actual test value is calculated until the tensile strength training model of asphalt mixture meets the error threshold, and then the tensile strength prediction model of asphalt mixture is generated.
[0075] The core of step S2 is to establish a training model for the tensile strength of asphalt mixtures that can predict the splitting tensile strength of asphalt mixtures through mathematical modeling and data fitting methods. This model uses the cohesive strength of asphalt mortar as the independent variable and the natural logarithm of the splitting tensile strength of asphalt mixtures as the dependent variable. The relationship between the two is described by determining the constant C and coefficient A in the model. The training model for the tensile strength of asphalt mixtures divides the datasets of splitting tensile strength of asphalt mixtures and cohesive strength of asphalt mortar into training and testing sets. Using the training set data, a predictive model for the tensile strength of asphalt mixtures is constructed through fitting different functions and adjusting parameters. The model is then iterated multiple times, continuously optimizing the model parameters until the relative error between the model's predicted values and the actual experimental values on the testing set reaches an acceptable range, achieving model convergence and forming the predictive model for the tensile strength of asphalt mixtures.
[0076] The asphalt mixture tensile strength prediction model, developed through data fitting, forms a prediction model based on the natural logarithm. This allows the model to more accurately capture the relationship between the cohesive strength of asphalt mortar and the splitting tensile strength of asphalt mixtures, thus providing more accurate prediction results. The model also ensures good generalization ability, making it applicable to different data and conditions. Finally, through multiple iterations and parameter adjustments, the model finds the optimal parameter combination, thereby improving the accuracy and reliability of the prediction. Compared with traditional experimental methods, the prediction model can significantly reduce the number of experiments and costs, improve the efficiency of research and evaluation, provide a scientific basis for the design and construction of asphalt mixtures, and help optimize material selection and construction techniques.
[0077] Figure 2 shows the architecture of the asphalt mixture tensile strength prediction system based on the cohesive strength of asphalt mortar, which includes:
[0078] The asphalt material data acquisition module is used to obtain the splitting tensile strength of asphalt mixtures and the cohesive strength of asphalt mortar.
[0079] The asphalt mixture tensile strength training model generation module divides the datasets of asphalt mixture splitting tensile strength and asphalt mortar cohesive strength into training set and test set. The training set is subjected to data fitting processing to obtain the asphalt mixture tensile strength training model. The asphalt mixture tensile strength training model includes: the independent variable is asphalt mortar cohesive strength, the dependent variable is asphalt mixture splitting tensile strength, and the dependent variable is the natural logarithm of the independent variable.
[0080] The asphalt mixture tensile strength prediction model generation module tests the asphalt mixture tensile strength training model using a test set, detects the relative error between the test values and the actual test values, and generates the asphalt mixture tensile strength prediction model if the relative error is less than a preset threshold.
[0081] It is worth noting that although only some basic functional modules are disclosed in the embodiments of this application, it does not mean that the composition of this system is limited to the above-mentioned basic functional modules. On the contrary, the meaning expressed by the embodiments of this application is that, based on the above-mentioned basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with the prior art to form an infinite number of embodiments or technical solutions. That is to say, this system is open rather than closed. The fact that the embodiments of this application only disclose a few basic functional modules does not mean that the scope of protection of the claims of the embodiments of this application is limited to the disclosed basic functional modules. At the same time, for the convenience of description, the above devices are described separately according to their functions as various units and modules. Of course, when implementing the embodiments of this application, the functions of each unit and module can be implemented in one or more software and / or hardware.
[0082] Figure 3 illustrates a specific application of the aforementioned asphalt mixture tensile strength prediction model, including:
[0083] Step T1 involves inputting one or more asphalt mixtures into the asphalt mixture tensile strength prediction model, setting the prediction temperature range, obtaining the model fitting effect, and thus obtaining the tensile strength of the asphalt mixture. In step T1, the various asphalt mixtures can be base asphalt and modified asphalt, and the optimal model fitting effect is greater than 95%. The tensile strength of the asphalt mixture obtained using the asphalt mixture tensile strength prediction model is a predicted value, and its reliability requires further verification.
[0084] Step T2 involves acquiring asphalt mixture samples, generating corresponding asphalt mixture images, and performing corresponding binarization processing. Rectangular color slice images of the asphalt mixture samples are obtained using the sample slicing method and digital image scanning technology. In step T2, an appropriate threshold needs to be selected to distinguish between asphalt mortar and aggregate areas.
[0085] Step T3: The rectangular slice color image is cropped at the image center. The representative volume element RVE is set as a sliding window to obtain the processed rectangular slice color image. The calculation is performed based on the inherent uniformity and relative uniformity of the asphalt mixture sample.
[0086] Step T4: Fit the normal distribution curves of different asphalt mixtures, select the normal distribution curve of the asphalt mixture as the benchmark for calculation, obtain the KLD divergence value of different asphalt mixtures, and determine the uniformity of the asphalt mixture sample based on the KLD divergence value.
[0087] In step T2, the asphalt mortar region and the aggregate region can be separated using a connected component labeling algorithm, forming different region labels. The distribution of the asphalt mortar region's pixel values is analyzed by calculating its histogram. The connected component labeling algorithm is a technique used in image processing and computer vision to identify and label connected regions in an image. A connected region is a set of pixels in an image that have the same attributes (such as color, intensity, or texture) and are connected to each other. These regions can be foreground objects, background parts, or any other meaningful image features. The connected component labeling algorithm provides a foundation for image analysis and understanding; by labeling and analyzing connected regions, image data can be better understood and processed.
[0088] Optionally, step T2 can employ a rotational sampling method to evaluate the directional uniformity of the mortar. Using the image center as the origin, the vertically upward direction is defined as 0°. By setting a sampling line every 10°, the proportion of mortar pixels to the total number of pixels on the sampling lines is calculated, and the coefficient of variation (COV) in different directions is calculated to quantify the directional uniformity of the mortar distribution, thus forming an evaluation of positional uniformity. In the evaluation of positional uniformity, the four-quadrant method is used to analyze the mortar distribution. Again, using the image center as the origin, the image is divided into four quadrants using a Cartesian coordinate system. The centroid coordinates of the mortar in each quadrant are calculated, and the coefficient of variation (COP) of these four quadrant centroid coordinates is calculated to evaluate the positional uniformity of the mortar distribution.
[0089] The evaluation of location uniformity also considers the direction and location uniformity of mortar distribution, defining the Uniformity Index of Mortar (UIM), which is calculated as the sum of Coefficient of Performance (COP) and Coefficient of Value (COV). UIM provides a comprehensive index for evaluating the uniformity of mortar distribution in asphalt mixtures, offering a new perspective for asphalt mixture design and performance optimization. Through UIM, the microstructure of asphalt mixtures can be more comprehensively understood and controlled, thereby improving their macroscopic properties.
[0090] In step T3, the representative volume element (RVE) is used as a sliding window concept, and its main application areas are materials science and image analysis. For example, it can be used to analyze the microstructure of multiphase materials (such as asphalt mixtures).
[0091] A representative volume element (RVE) is a sufficiently large volumetric unit that encompasses all the microstructural features within a material and represents the statistical properties of the entire material or structure. In image analysis, the RVE can be viewed as a virtual window, which is controlled to slide across a two-dimensional or three-dimensional image of the material to analyze its internal structural features. By using the RVE as a sliding window, local information, such as aggregate distribution, porosity, and material phase interfaces, can be extracted from different regions of the image. In asphalt mixture analysis, the RVE window can be used to assess the homogeneity of the mixture. By sliding the RVE window across the image, parameters such as aggregate distribution and area ratio within each window region can be calculated to quantify the homogeneity of the mixture and assess the spatial distribution of different components.
[0092] In practice, the size and shape of the Representative Volume Element (RVE) window can be determined based on the material properties and analytical objectives. For example, in asphalt mixtures, the RVE window can be set to include a certain number of aggregate particles to ensure statistical significance. By sliding the RVE window across the image and calculating relevant parameters at each location, a detailed distribution map of the material's internal structure can be obtained. This provides an observational method for analyzing the microstructure of asphalt materials, and can be used to reduce errors caused by local variability when evaluating the uniformity and performance of asphalt materials, providing a more accurate analysis of asphalt material properties.
[0093] The technical solutions provided in steps T1 to T4 configure and operate the model by setting temperature, acquiring and processing images, cropping and evaluating uniformity, and fitting normal distribution curves and determining uniformity. Different types of asphalt mixtures (including base asphalt and modified asphalt) are input into a prediction model, and a prediction temperature range is set to obtain the model's fitting effect, ensuring that the best fitting effect is greater than 95%. Color images of asphalt mixture samples are acquired through sample slicing and digital image scanning technology, and binarized to prepare for subsequent image analysis. The images are center-cropped, and the representative volume element RVE is used as a sliding window to process the images. Based on image analysis, the self-uniformity and relative uniformity index of the asphalt mixture samples are calculated. The normal distribution curves of different asphalt mixtures are fitted, and the KLD divergence value is calculated based on the normal distribution curve of the asphalt mixture, ultimately determining the uniformity of the asphalt mixture samples. The predicted tensile strength of asphalt mixtures obtained from the aforementioned asphalt mixture tensile strength prediction model is further combined with the uniformity of the asphalt mixture samples obtained from the KLD divergence value. The reliability and accuracy of the asphalt mixture tensile strength prediction model are jointly evaluated from two dimensions: the predicted value and the uniformity of the actual image. If the uniformity of the actual image is not ideal, i.e., KLD divergence > 5, then steps S1-S3 need to be repeated to verify or correct the asphalt mixture tensile strength prediction model.
[0094] The technical solutions provided in steps T1 to T4 determine the homogeneity of asphalt mixture samples, compare the differences in aggregate distribution homogeneity among different asphalt mixture samples, and quantify this using statistical methods such as Kullback-Leibler divergence (KLD divergence), measuring the distance between two probability distributions. KLD divergence can be used to fit a normal distribution to the aggregate area ratio of multiple mixture samples and is an important parameter for evaluating asphalt mixture quality. By assessing the homogeneity of the mixture, the performance and durability of asphalt pavements can be predicted and guaranteed, thereby optimizing the preparation and construction processes of asphalt mixtures to improve the performance of the final asphalt product, contributing to improved road engineering quality, extended road service life, and reduced maintenance costs. This provides a comprehensive, accurate, and efficient technical solution for the performance evaluation of asphalt mixtures.
[0095] Preferably, in step T2, the rectangular slice color image is preprocessed by using image enhancement technology and median filtering algorithm to eliminate brightness unevenness and image noise, and by using image binarization algorithm to define the mortar area and coarse aggregate area in the grayscale image with different colors. For example, the mortar area can be defined as black, while the coarse aggregate can be defined as white.
[0096] In optimizing step T2, image processing techniques were used to preprocess the color images of the asphalt mixture samples to improve the accuracy and reliability of subsequent image analysis. Improving image quality made the detailed features of the asphalt mixture samples more apparent, facilitating subsequent analysis. A mean square filtering algorithm was applied to eliminate brightness inhomogeneities and noise in the image, reducing random interference and further improving image clarity and readability. An image binarization algorithm was used to convert the grayscale image into an image containing only two colors. By defining the mortar area and coarse aggregate area as different colors, different components in the asphalt mixture could be distinguished. This provides a foundation for automated processing and analysis of asphalt mixture images, contributing to the automation and standardization of asphalt mixture performance evaluation.
[0097] As a further improvement, the process of image enhancement and median filtering algorithms satisfies the following formula:
[0098]
[0099] ...(2)
[0100] Among them: I original (x,y) represents the pixel value of the original image at coordinates (x,y).
[0101] I enhanced (x,y) represents the pixel value of the enhanced image at coordinates (x,y).
[0102] L represents the contrast stretching factor, used to adjust the contrast of an image. The value of L is usually a positive number, used to control the degree of contrast enhancement.
[0103] α represents the gain factor, which is used to control the adjustment of the overall image brightness. α can be any real number greater than 0.
[0104] β represents the weighting factor of the median filter, used to control the degree of influence of the median filter on the final image. The value of β is between 0 and 1.
[0105] M(I original (x,y) represents the pixel value at coordinates (x,y) in the image after median filtering. Median filtering is a non-linear filtering technique used to replace each pixel value with the median of its neighboring pixel values, thereby reducing noise.
[0106] γ represents the offset, used to adjust the brightness level of the image. The value of γ can be any real number; a positive number increases brightness, and a negative number decreases brightness.
[0107] Contrast enhancement can be achieved by applying formula (1). The logarithmic function can expand the range of pixel values in low-contrast areas, making the dark details of the image more obvious. Brightness adjustment is achieved through α and γ. α can amplify or reduce the brightness range of the image, while γ can increase or decrease the overall brightness of the image. Finally, median filtering is achieved through β•M(Ioriginal(x,y) to remove salt-and-pepper noise in the image while preserving edge information.
[0108] Formula (1) combines the effects of contrast enhancement, brightness adjustment, and median filtering to achieve a comprehensive improvement in image quality. The values of α, β, and γ can be adjusted to optimize for different image and noise conditions.
[0109] As shown in Figure 4, this application provides an implementation method in a specific application scenario. In this implementation method, the asphalt mixture tensile strength prediction model establishes a mapping relationship between the cohesive strength of asphalt mortar and the splitting tensile strength of asphalt mixture. The tensile strength of the mixture can be predicted by only performing pull-out tests on the asphalt mortar, which can save a lot of test costs and improve evaluation efficiency. The specific steps of the method are as follows:
[0110] Step 1: Obtain the prediction model for the tensile strength of asphalt mixtures. The prediction model includes the functional relationship between the cohesive strength of asphalt mortar and the tensile strength of the mixture.
[0111] Step 2: Design the asphalt mixture, calculate that the aggregate and asphalt content of the mortar are consistent with the mixture, and prepare the asphalt mortar;
[0112] Step 3: Conduct a pull-out test on the mortar at the selected temperature to obtain the cohesive strength;
[0113] Step four: Input the obtained cohesive strength into the prediction model and use the functional relationship to calculate the tensile strength of the asphalt mixture.
[0114] The methods for constructing the prediction model include the following:
[0115] Multiple asphalt mixture specimens with the same gradation were prepared by selecting various asphalts and keeping the porosity consistent. Splitting tests were conducted on the asphalt mixtures at different temperatures to obtain the splitting tensile strength.
[0116] The content of each aggregate and the asphalt content in the mortar are kept consistent with the original mixture to prepare asphalt mortar. The cohesive strength of the asphalt mortar at different temperatures is obtained by pull-out test.
[0117] The obtained mortar cohesive strength and asphalt mixture splitting tensile strength data sets are divided into training and testing sets. The training set is then fitted to obtain the asphalt mixture tensile strength prediction model: ,in denoted as σi represents the splitting tensile strength of the asphalt mixture (MPa), and x represents the cohesive strength of the asphalt mortar (MPa).
[0118] The model is used to make predictions on the test set. The relative error between the predicted value and the actual experimental value is calculated. If the error is less than 10%, the training ends and the model is determined.
[0119] The prediction model is applicable to various asphalt mixtures (including base asphalt and modified asphalt). When the prediction temperature range is 10℃-25℃, the model fit is the best, greater than 95%.
[0120] In the process of preparing mortar, the fine aggregate with a maximum particle size of 0.6mm is selected. The amount of asphalt is determined by the specific surface area method to ensure that the content of each grade of aggregate and the asphalt content in the mortar are consistent with the original mixture, and the mixing time and temperature are kept the same as the mixture.
[0121] ... (3)
[0122] - Mortar asphalt-aggregate ratio: %
[0123] -Total specific surface area of aggregates in the mixture: ;
[0124] Total specific surface area of aggregates below -0.6: ;
[0125] -Optimal asphalt-aggregate ratio for the mixture: %
[0126] The steps for conducting a pull-out test are as follows:
[0127] The pull-out test used a 10cm*10cm slab of stone with the same lithology as the fine aggregate, the pull-out rate was 0.7MPa / s, and the diameter of the pull-out head was 20mm.
[0128] Heat the pulling head and the stone slab in an oven at 160℃ for 1 hour. Apply the mixed asphalt mortar into the groove of the pulling head, press the pulling head against the stone slab until it contacts the stone slab, and then cool it to room temperature.
[0129] The test was conducted by bathing the sample in water at the experimental temperature for 1 hour and then performing a pull-out test. The maximum tensile force at failure was recorded. Each test was repeated 4 times, and the average value was taken as the experimental result.
[0130] The conditions for the splitting test of asphalt mixture were matched with those for the pull-out test of asphalt mortar, using a water bath for 2 hours and a uniform loading rate of 50 mm / min.
[0131] By fitting different functions to the data sets of mortar cohesive strength and asphalt mixture splitting tensile strength, and adjusting the model parameters, it was found that the fitting converged after 6 iterations under the logarithmic function.
[0132] Table 1 - Establishing the Model Training Data Set
[0133]
[0134] Table 2 - Error Analysis of Model Training Set
[0135]
[0136] Relative error is an important indicator for measuring the accuracy of model predictions. The data in Table 2 shows that the model's predictions are very close to the actual experimental values, exhibiting high prediction accuracy. Even though the largest relative error is 6.48%, which is higher than the previous two, it is still within an acceptable range, especially considering the natural variability of material properties and experimental errors. The data in Table 2 indicate that the prediction model has high accuracy and reliability in predicting the tensile strength of asphalt mixtures. The prediction model can provide valuable references, aiding in data-driven decision-making and fulfilling its decision support function.
[0137] As shown in Figure 5, this application provides, in addition to the method for predicting the tensile strength of asphalt mixtures based on the cohesive strength of asphalt mortar, corresponding electronic equipment and computer program products:
[0138] An electronic device includes: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus; the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the method.
[0139] A computer program product includes a computer program that, when executed by a processor, implements the method.
[0140] Figure 5 is a schematic diagram of an electronic device provided in an embodiment of this application. Figure 5 shows a block diagram of an exemplary electronic device suitable for implementing the embodiments of this application. The electronic device shown in Figure 5 is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application. This electronic device can typically be a device in an electronic product based on the asphalt mixture tensile strength prediction method based on the cohesive strength of asphalt mortar in the above embodiments. As shown in Figure 5, the electronic device 500 is represented in the form of a general-purpose computing device. The components of the electronic device 500 may include, but are not limited to: one or more processing units or processors 516, a memory 528, and a bus 518 connecting different system components (including the memory 528 and the processor 516). The bus 518 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus structures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Microchannel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus. Electronic device 500 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 500, including volatile and non-volatile media, removable and non-removable media. Memory 528 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 530 and / or cache memory 532. Electronic device 500 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 534 may be used to read and write non-removable, non-volatile magnetic media (not shown in the figure, commonly referred to as a "hard disk drive"). Although not shown in the figure, storage system 534 may provide a disk drive for reading and writing to removable non-volatile disks (e.g., floppy disks, portable hard drives, hot-swappable storage media) and an optical disk drive for reading and writing to removable non-volatile optical disks (e.g., CD-ROMs, DVD-ROMs, or other optical media). In these cases, each drive may be connected to bus 518 through one or more data media interfaces. The memory 528 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present application. A program / utility 540 having a set (at least one) of program modules 542 may be stored, for example, in the memory 528. Such program modules 542 include, but are not limited to, an operating system, one or more applications, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment.Program module 542 typically performs the functions and / or methods described in the embodiments of this application. Electronic device 500 can also communicate with one or more external devices 514 (e.g., keyboard, pointing device, display 524, etc.), and with one or more devices that enable a user to interact with the electronic device 500, and / or with any device that enables the electronic device 500 to communicate with one or more other computing devices (e.g., network interface card, modem, etc.). Such communication can be performed via input / output (I / O) interface 522. Furthermore, electronic device 500 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 520. Network adapter 520 communicates with other modules of electronic device 500 via bus 518. It should be understood that, although not shown in the figures, those skilled in the art can use other hardware and / or software modules in conjunction with electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems. The processor 516 executes various functional applications and data processing by running programs stored in the memory 528, such as implementing the methods provided in any one or more embodiments of this application.
[0141] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0142] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are meant to be within the scope of the embodiments of this application and form different embodiments. For example, any one of the embodiments claimed in the claims can be used in any combination of embodiments of this application.
[0143] In the description of this specification, the references to terms such as "an embodiment," "example," "specific example," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of the embodiments of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0144] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the corresponding claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the corresponding claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.
[0145] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of this application, and are not intended to limit them. Although the embodiments of this application have been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.
Claims
1. A method for predicting the tensile strength of asphalt mixtures based on the cohesive strength of asphalt mortar, applied to generating a prediction model for the tensile strength of asphalt mixtures, characterized in that, include: To obtain the splitting tensile strength of asphalt mixtures and the cohesive strength of asphalt mortars; The datasets of splitting tensile strength of asphalt mixture and cohesive strength of asphalt mortar are divided into training set and test set. The training set is subjected to data fitting processing to obtain the training model of tensile strength of asphalt mixture. The training model of tensile strength of asphalt mixture includes: the independent variable is the cohesive strength of asphalt mortar, the dependent variable is the splitting tensile strength of asphalt mixture, and the dependent variable is the natural logarithm of the independent variable. The training model for the tensile strength of asphalt mixtures is tested using a test set to detect the relative error between the test values and the actual test values. If the relative error is less than a preset threshold, a prediction model for the tensile strength of asphalt mixtures is generated. Then, the generated prediction model is used to predict the tensile strength of one or more input asphalt mixtures.
2. The method for predicting the tensile strength of asphalt mixtures based on the cohesive strength of asphalt mortar according to claim 1, characterized in that, The method of obtaining the splitting tensile strength of asphalt mixture and the cohesive strength of asphalt mortar further includes: Asphalt mixture specimens were prepared, and splitting tensile strength of asphalt mixtures was obtained by conducting splitting tensile tests at different temperatures. Asphalt mortar was prepared, and a pull-out test was conducted at the corresponding temperature to obtain the cohesive strength of the asphalt mortar. Specifically, the content of each aggregate and the asphalt content in the mortar were kept consistent with the original mixture. Asphalt mortar was prepared, and the cohesive strength of the asphalt mortar at different temperatures was obtained by pull-out test. The conditions for the splitting test of asphalt mixtures and the pull-out test of asphalt mortar were matched, and both tests used water bath insulation and uniform loading. Based on the obtained splitting tensile strength of asphalt mixture and cohesive strength of asphalt mortar, training set and test set are formed. The tensile strength prediction model of asphalt mixture is obtained by fitting the training set.
3. The method for predicting the tensile strength of asphalt mixtures based on the cohesive strength of asphalt mortar according to claim 2, characterized in that, In the process of preparing asphalt mortar, the aggregate distribution of mortar is converted according to the asphalt mixture gradation, and the asphalt content is determined by the specific surface area method. Set the size of the slab, the pull rate, and the diameter of the pull head required for the pull test. Heat the pull head and the slab. Apply the same mass of asphalt mortar to the groove of the pull head. Press the pull head against the slab until it contacts the slab. Let it stand and cool to room temperature. After water bath temperature control, a pull-out test was conducted to read the maximum tensile force when the asphalt mortar was damaged, and the average value was taken as the experimental result.
4. The method for predicting the tensile strength of asphalt mixtures based on the cohesive strength of asphalt mortar according to claim 1, characterized in that, The datasets for splitting tensile strength of asphalt mixtures and cohesive strength of asphalt mortar are divided into training and testing sets. The training set is then subjected to data fitting processing to obtain a training model for the tensile strength of asphalt mixtures. This further includes: The independent variable in the asphalt mixture tensile strength training model is the asphalt mortar cohesive strength, and the dependent variable is the asphalt mixture splitting tensile strength. The dependent variable is the natural logarithm of the independent variable, satisfying the formula: In this equation, the cohesive strength of asphalt mortar is the independent variable x, the splitting tensile strength of asphalt mixture is the dependent variable y, C is a constant, and A is the coefficient of the dependent variable.
5. The method for predicting the tensile strength of asphalt mixtures based on the cohesive strength of asphalt mortar according to claim 4, characterized in that, In the process of fitting the training set to data, different functions are fitted, and the corresponding model parameters are adjusted. The tensile strength training model of asphalt mixture was iterated multiple times, and the model parameters were adjusted until the model reached fitting convergence under the logarithmic function. The tensile strength training model of asphalt mixture was then used to predict the test set to obtain the corresponding predicted values. The relative error between the predicted value and the actual test value is calculated until the tensile strength training model of asphalt mixture meets the error threshold, and then the tensile strength prediction model of asphalt mixture is generated.
6. The method for predicting the tensile strength of asphalt mixtures based on the cohesive strength of asphalt mortar according to claim 5, characterized in that, Also includes: One or more asphalt mixtures are input into the asphalt mixture tensile strength prediction model, the prediction temperature range is set, the model fitting effect is obtained, and the tensile strength of the asphalt mixture is obtained.
7. The method for predicting the tensile strength of asphalt mixtures based on the cohesive strength of asphalt mortar according to claim 6, characterized in that, Also includes: Asphalt mixture samples are obtained, corresponding asphalt mixture images are generated and binarized accordingly, a threshold is selected to distinguish asphalt mortar and aggregate areas, and rectangular slice color images of asphalt mixture samples are obtained using the sample slicing method and digital image scanning technology. The asphalt mortar region and the aggregate region are separated by a connected component labeling algorithm to form different region labels. The distribution of the asphalt mortar region is analyzed by calculating the pixel value histogram of the asphalt mortar region in the image. The rectangular slice color image is cropped at the image center, and a representative volume element is set as a sliding window to obtain the processed rectangular slice color image. Calculations are then performed based on the inherent and relative uniformity of the asphalt mixture sample. The normal distribution curves of different asphalt mixtures are fitted, and the normal distribution curve of the asphalt mixture is selected as the benchmark for calculation to obtain the KLD divergence value of different asphalt mixtures. The uniformity of the asphalt mixture sample is determined based on the KLD divergence value.
8. The method for predicting the tensile strength of asphalt mixtures based on the cohesive strength of asphalt mortar according to claim 7, characterized in that, The process of obtaining asphalt mixture samples, generating corresponding asphalt mixture images and performing corresponding binarization processing, and obtaining rectangular slice color images of asphalt mixture samples using sample slicing and digital image scanning techniques, further includes: The rectangular slice color image is preprocessed by using image enhancement technology and median filtering algorithm to eliminate brightness unevenness and image noise, and by using image binarization algorithm to define different colors for mortar area and coarse aggregate area in grayscale image.
9. An electronic device, characterized in that, include: The system includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus; the memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the method according to any one of claims 1 to 8.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 8.