Multi-scene asphalt mixture design system based on comprehensive performance scoring reliability

Abstract

The invention relates to the technical field of asphalt mixture design, in particular to a multi-scene asphalt mixture design system based on comprehensive performance scoring reliability. According to the invention, opinions of multiple experts are integrated through the multi-scene expert evaluation agent module, a mapping model of climate partitions and road performance importance degrees is constructed by using an artificial intelligence algorithm, and evaluation differences of different experts on climate partitions of high temperature, low temperature, rainfall and the like are standardized. The standardized process not only ensures that evaluation standards under different climate partitions are consistent, but also dynamically adapts to multi-scene requirements through the proxy model, so that the universality and credibility of a design scheme are remarkably improved, the problem of scheme conflict or performance imbalance caused by standard fuzziness in traditional manual evaluation is avoided, and the evaluation efficiency is improved. And finally, a high-reliability scheme is optimized by calculating beta value comparison. The method solves the technical problems of non-uniform standards and low credibility in the existing mode of manually optimizing the asphalt mixture.

Description

Technical Field

[0001] The present invention relates to the technical field of asphalt mixture design, and in particular to a multi-scenario asphalt mixture design system based on comprehensive performance scoring reliability. Background Art

[0002] Asphalt mixtures are widely used on roads of all levels due to their excellent road performance and ease of construction. However, there are many types of asphalt mixtures on the market, and the quality of products varies. The road performance of different asphalt mixtures is not the same. In order to select the asphalt mixture scheme that is most suitable for the actual project under a specific construction application environment, it is usually necessary for technicians with rich design experience to design the asphalt mixture based on the actual construction application environment and the results of indoor road performance test indicators, using manual confirmation. This method of manual selection is highly dependent on human judgment and is highly subjective. In actual application, there are shortcomings such as insufficient standard uniformity and the results are easily affected by individual cognitive limitations, which to a certain extent limits its feasibility and credibility. Summary of the Invention

[0003] In response to the shortcomings of the existing technology, the present invention provides a multi-scenario asphalt mixture design system based on comprehensive performance scoring reliability, which solves the technical problems of inconsistent standards and low credibility in the current method of manually optimizing asphalt mixtures.

[0004] To solve the above technical problems, the present invention provides the following technical solution: a multi-scenario asphalt mixture design system based on comprehensive performance scoring reliability, the system comprising:

[0005] A custom design parameter determination module is used to obtain all regional samples within the sample area according to designer requirements, classify the regional samples according to preset rules to set several levels of climate zones, and set the road performance of asphalt mixtures for different climate zones;

[0006] A multi-scenario expert evaluation agent module is used to obtain the evaluations of several experts on the importance of asphalt mixture road performance under different climate zones, and to establish a multi-scenario expert evaluation agent model to unify the evaluations of the importance of road performance under different climate zones;

[0007] A multi-scenario expert scoring agent module is used to obtain road performance data of asphalt mixtures to establish a road performance database, and based on the unified road performance importance evaluation, uses the analytic hierarchy process to obtain road performance weights and calculate the comprehensive performance score of the asphalt mixture;

[0008] Reliability design module, the reliability design module is used to establish the function function and the type of random variable of the function function according to the comprehensive performance score, action effect and resistance of the asphalt mixture road, and calculate the reliability index of the new asphalt mixture through the reliability index function, and then select the asphalt mixture with the largest reliability index as the optimal design scheme.

[0009] Preferably, the custom design parameter determination module includes:

[0010] A climate zoning unit, which is used to set several levels of climate zoning and division rules, and divide regional samples into different climate zones according to the climate, soil conditions and traffic load of the regional samples;

[0011] The road performance unit is used to set the road performance required for asphalt mixture to be used in different climate zones.

[0012] Preferably, the multi-scenario expert evaluation agent module includes:

[0013] An expert evaluation acquisition unit is used to collect a number of expert opinions, obtain the evaluation of the importance of road performance in different climate zones by each expert, construct the road performance importance vector of different climate zones, and establish a multi-scenario expert scoring database;

[0014] An evaluation agent model establishment unit, the evaluation agent model establishment unit being used to construct a mapping relationship between climate zones and road performance importance through an artificial intelligence algorithm, so as to establish a multi-scenario expert evaluation agent model that simulates the thinking and evaluation logic of experts;

[0015] The importance proxy unit is used to re-input each road performance importance vector in the multi-scenario expert scoring database into the model, and obtain the road performance importance value through the multi-scenario expert evaluation proxy model.

[0016] Preferably, the evaluation agent model establishment unit adopts a self-help method to use 80% of the samples in the obtained multi-scenario expert scoring database as a training set, and the remaining 20% of the samples as a test set. The climate zone combination in the training set is used as the input of the artificial intelligence machine learning model, and the road performance importance vector corresponding to the climate zone is used as the output of the artificial intelligence machine learning model. After training, a multi-scenario expert evaluation agent model is obtained. The model output layer adopts a linear activation function to output the importance score of the road performance. The model loss function adopts the mean square error loss function. The MSE loss function formula is:

[0017]

[0018] In the above formula, LOSS is the mean square error loss value, n represents the number of samples in the multi-scenario expert scoring database, C is the number of road performance that needs to be considered, and y ic is the actual expert score of the i-th road performance, The importance score of the i-th road performance item predicted by the multi-scenario expert evaluation agent model is given, and the score reflects the importance of various road performance items.

[0019] Preferably, the multi-scenario expert scoring agent module includes:

[0020] A road performance acquisition unit, which is used to acquire road performance data of asphalt mixture and integrate it into a road performance database;

[0021] An expert scoring calculation unit, the expert scoring calculation unit being used to obtain the weight of the road performance using a hierarchical analysis method based on the expert's evaluation of the importance of the road performance, and to calculate the comprehensive performance score of different asphalt mixtures based on the obtained weight and samples of the road performance database;

[0022] A scoring proxy model establishment unit is used to construct a mapping relationship from the importance of road performance, road performance to comprehensive performance scores through an artificial intelligence algorithm to establish a multi-scenario comprehensive performance scoring model.

[0023] Preferably, the calculation formula for the comprehensive performance score of the asphalt mixture is:

[0024]

[0025] In the above formula, P j is the comprehensive performance score of any asphalt mixture, α i is the data value of the indoor test index of the road performance of asphalt mixture i, α i，max is the maximum value of the i-th road performance indoor test index data in the road performance indoor test index database.

[0026] Preferably, the reliability design module includes:

[0027] a random variable determination unit, the random variable determination unit being used to determine the type of the performance function random variable according to the comprehensive performance score;

[0028] a function determination unit, the function determination unit being configured to establish a function according to a relationship between an action effect and a resistance;

[0029] A reliability index calculation unit, wherein the reliability index calculation unit is used to establish a reliability index function of the comprehensive performance of the asphalt mixture by using a first-order second moment method;

[0030] The asphalt mixture design unit is used to conduct a road performance test on a new asphalt mixture, calculate a reliability index according to a reliability index function, and select an asphalt mixture with a large reliability index as the optimal design solution.

[0031] Through the above technical solution, the present invention provides a multi-scenario asphalt mixture design system based on comprehensive performance scoring reliability, which has at least the following beneficial effects:

[0032] 1. The present invention integrates the opinions of multiple experts through a multi-scenario expert evaluation agent module, uses artificial intelligence algorithms to construct a mapping model between climate zones and the importance of road performance, and standardizes the differences in evaluations of different experts on climate zones such as high temperature, low temperature, and rainfall. This standardized process not only ensures consistent evaluation standards under different climate zones, but also dynamically adapts to multi-scenario requirements through the agent model, significantly improving the universality and credibility of design solutions, and avoiding solution conflicts or performance imbalances caused by vague standards in traditional manual evaluations.

[0033] 2. Based on the analytic hierarchy process and a road performance database, this invention combines expert weights and test data to calculate a comprehensive performance score, ensuring the comparability of the scoring results. Furthermore, an AI model is used to establish a nonlinear mapping relationship between road performance and the score, dynamically correcting weight deviations and reducing human subjective intervention. Compared with traditional empirical evaluation, this method significantly improves the objectivity of the score and its engineering applicability through data-driven quantitative analysis, providing precise input for subsequent reliability design.

[0034] 3. Based on the analysis of performance functions and random variables, the present invention converts the comprehensive performance score into a reliability index, quantitatively evaluates the failure probability of asphalt mixtures, constructs the performance function through the first-order second moment method, combines the road performance random variables with the log-normal distribution, calculates the mean and standard deviation of the performance function, and finally derives the reliability index β value. The high-reliability solution is selected by comparing the β values. This method breaks through the limitations of the empirical limits in traditional specifications, quantifies the redundancy of material performance from a probabilistic perspective, provides a scientific basis for the design of asphalt mixtures under extreme climates or complex load conditions, and significantly improves the durability and safety reserve of road structures.

[0035] 4. The present invention uses a custom design parameter module to divide the road into multiple climate zones based on multi-dimensional parameters such as climate, soil, and traffic load, and dynamically configures road performance priorities in combination with secondary zones such as salt corrosion and traffic volume. By establishing mapping rules between climate zones and performance requirements, the system can automatically generate targeted design goals, such as enhancing corrosion resistance in salt corrosion zones and focusing on water stability in humid zones. This refined zoning strategy ensures that asphalt mixtures can achieve optimal performance configuration in differentiated scenarios such as high temperature and rain, severe cold and snow, and saline-alkali corrosion, solving the problems of material waste or performance shortcomings caused by traditional "one-size-fits-all" design. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0037] Figure 1 This is a structural block diagram of the multi-scenario asphalt mixture design system based on comprehensive performance scoring reliability of the present invention.

[0038] In the figure: 1. Custom design parameter determination module; 11. Climate zoning unit; 12. Road performance unit; 2. Multi-scenario expert evaluation agent module; 21. Expert evaluation acquisition unit; 22. Evaluation agent model establishment unit; 23. Importance agent unit; 3. Multi-scenario expert scoring agent module; 31. Road performance acquisition unit; 32. Expert scoring calculation unit; 33. Scoring agent model establishment unit; 4. Reliability design module; 41. Random variable determination unit; 42. Function determination unit; 43. Reliability index calculation unit; 44. Asphalt mixture design unit. DETAILED DESCRIPTION

[0039] To make the above-mentioned objectives, features, and advantages of the present invention more clearly understood, the present invention is further described below in detail with reference to the accompanying drawings and specific embodiments. This will enable a full understanding of how this application uses technical means to solve technical problems and achieve technical effects, and to implement the invention accordingly.

[0040] Reliability theory is a reliable quantitative calculation method that has been widely used in the field of civil engineering, especially in the design of engineering structures and components. However, unlike engineering structures and components with relatively clear load effects, in road structures, due to the viscoelastic properties of asphalt mixtures, their effects under load are difficult to clarify. Unlike clear mechanical indicators such as compressive strength, which can be directly used as the basis for road structure design using reliability theory, a large number of road performance indicators do not have clear design values. The empirical minimum values of road performance indoor test indicators in the specifications are often used to standardize road asphalt mixture design. This unified minimum limit makes it difficult to apply reliability theory in asphalt mixture design. In fact, after modification with various admixtures, the road performance indoor test indicator values of asphalt mixtures have often far exceeded the minimum values in the specifications.

[0041] Therefore, in order to solve the technical problems of inconsistent standards and low reliability in the current manual selection of asphalt mixtures, the present invention provides a multi-scenario asphalt mixture design system based on comprehensive performance score reliability. This system can quantitatively calculate the comprehensive performance score reliability to obtain the probability that the asphalt mixture will meet the expected design performance under different road service conditions. This system can more directly and reliably select the asphalt mixture with the best comprehensive performance. The system includes:

[0042] A custom design parameter determination module 1 is used to obtain all regional samples in the sample area according to the designer's needs, and classify the regional samples according to preset rules to set several levels of climate zones, and set the road performance of asphalt mixtures for different climate zones. For example, if China is set as the sample area, the possible climate zone combinations of all regions in China (i.e., regional samples) are obtained, and then the road performance that may affect the performance of asphalt mixtures can be set according to the climate zones; a multi-scenario expert evaluation agent module 2 is used to obtain the evaluation of the importance of the road performance of asphalt mixtures under different climate zones by several experts, and a multi-scenario expert evaluation agent model is established to unify the evaluation of the importance of road performance under different climate zones to eliminate the differences in opinions among different experts; A multi-scenario expert scoring agent module 3 is used to obtain the road performance data of asphalt mixtures to establish a road performance database, and according to the unified road performance importance evaluation, a hierarchical analysis method is used to obtain the weight of the road performance and calculate the comprehensive performance score of the asphalt mixture; a reliability design module 4 is used to establish the type of functional function and functional function random variable according to the comprehensive performance score of the asphalt mixture road, the effect and the resistance relationship, and calculate the reliability index of the new asphalt mixture through the reliability index function, and then select the asphalt mixture with the largest reliability index as the optimal design scheme, so that the quantitative evaluation of different asphalt mixtures is completed through the above-mentioned improved reliability index calculation method applicable to asphalt mixtures, so that the asphalt mixture with the best comprehensive performance can be selected more objectively and scientifically.

[0043] Module 1 for determining custom design parameters involves the division of climate zones. The following is a more detailed introduction to the division of climate zones. This module includes:

[0044] It is used to set several levels of climate zones and division rules, and divide regional samples into climate zone units 11 within different climate zones according to the climate, soil conditions and traffic loads of regional samples. For example, the climate zones are divided into primary zones and secondary zones, wherein the primary zones include high temperature zones, low temperature zones, rainfall zones, salt erosion zones and traffic volume zones. Furthermore, the secondary zones will make detailed divisions of the primary zones, wherein the high temperature zones are divided into hot summer zones, hot summer zones and cool summer zones, the low temperature zones are divided into severe winter zones, cold winter zones and warm winter zones, the rainfall zones are divided into humid zones, wet zones and arid zones, the salt erosion zones are divided into heavy salt erosion zones, medium and light salt erosion zones and no salt erosion zones, the traffic volume zones are divided into super-heavy traffic zones, heavy traffic zones and medium and light traffic zones. The primary zones that need to be considered are selected according to the designer's wishes, and the secondary zones are arranged and combined to retain the feasible climate zone combinations within China. , remove other climate zoning combinations that will not appear in the actual area. Specifically, the secondary zoning can refer to the following division standards: high temperature zoning: the average maximum temperature of the hottest month is greater than 35℃ for the hot summer zone, 20~35℃ for the hot summer zone, and less than 25℃ for the cool summer zone; low temperature zoning: the extreme minimum temperature is less than -21.5℃ for the severe winter zone, -21.5~-9℃ for the cold winter zone, and greater than -9℃ for the warm winter zone; rainfall zoning: annual rainfall greater than 1 000mm is the humid zone, 250-1000mm is the moist zone, and less than 250mm is the arid zone; salt erosion zoning: soil salt content greater than 0.4% is the severe salt erosion zone, 0.1%-0.4% is the medium-light salt erosion zone, and less than 0.1% is the no salt erosion zone; traffic volume zoning: the cumulative equivalent axle times greater than 10 million times is the super-heavy load traffic zone, 1 million to 10 million times is the heavy load traffic zone, and less than 1 million times is the medium-light traffic zone.

[0045] The system also includes a road performance unit 12 for setting the road performance required for asphalt mixtures used in different climate zones.

[0046] The following further describes the detailed functions of the multi-scenario expert evaluation agent module 2, including:

[0047] The expert evaluation acquisition unit 21 is used to collect the opinions of several experts and obtain the evaluation of the importance of road performance under different climate zones by each expert, so as to construct the road performance importance vector of different climate zones and establish a multi-scenario expert scoring database. Specifically, all possible climate zone combinations in China and the road performance that needs to be considered can be obtained according to the designer's wishes. The expert survey method is adopted to obtain the importance scores of various road performance under different secondary climate zone combinations by multiple experts in the form of emails, questionnaires, etc. For example, in Fujian, an area with high temperature and heavy rain in summer, high temperature and rain have a significant impact on asphalt mixture, and the traffic volume in Fujian is not low, which will cause repeated effects of vehicle loads. However, it is rare to see sub-zero temperatures throughout the year. Taking the high temperature performance, low temperature performance, water stability and fatigue performance of asphalt mixtures as an example, it is considered that it is equally important to consider high temperature performance and water stability in the design of asphalt mixtures. High temperature performance and water stability are more important than fatigue performance, and both are significantly more important than low temperature performance. In this way, they can be scored from 9 to 1 according to the importance from high to low. The higher the score, the more important it is. Then the experts may finally give 9 points for both high temperature performance and low temperature performance, 6 points for fatigue performance, and 1 point for low temperature performance, thus forming an importance vector X = (9, 1, 6, 9). The higher the importance, the greater the score value. The road performance importance vector X = (x1, x2, ..., x i ), where x i represents the importance score of the i-th road performance. The road performance importance vector represents the various road performance importance scores under all possible climate zone combinations in China. The climate zone combinations and the corresponding expert road performance importance scores are formed into a multi-scenario expert scoring database.

[0048] An evaluation agent model establishment unit 22 is used to construct a mapping relationship between climate zones and road performance importance through an artificial intelligence algorithm to establish a multi-scenario expert evaluation agent model that simulates the thinking and evaluation logic of experts. The evaluation agent model establishment unit 22 uses a self-service method to use 80% of the samples in the obtained multi-scenario expert scoring database as a training set, and the remaining 20% of the samples as a test set. The climate zone combination in the training set is used as the input of the artificial intelligence machine learning model, and the road performance importance vector corresponding to the climate zone is used as the output of the artificial intelligence machine learning model. After training, a multi-scenario expert evaluation agent model is obtained. The model output layer uses a linear activation function to output the road performance importance score. The model loss function uses a mean square error loss function. The MSE loss function formula is:

[0049]

[0050] In the above formula, LOSS is the mean square error loss value, n represents the number of samples in the multi-scenario expert scoring database, C is the number of road performance that needs to be considered, and y ic is the actual expert score of the i-th road performance, The importance score of the i-th road performance item predicted by the multi-scenario expert evaluation agent model is given, and the score reflects the importance of various road performance items.

[0051] The importance proxy unit 23 is used to re-input each road performance importance vector in the multi-scenario expert scoring database into the model's importance proxy unit 23, and obtain the road performance importance value through the multi-scenario expert evaluation proxy model. The artificial intelligence machine learning algorithm is used to fully learn the underlying logic of the data and understand the experts' way of thinking, so that the expert opinions are effectively unified, eliminating the evaluation differences caused by differences in the experts' personal prior knowledge, and unifying the evaluation standards for the importance of road performance.

[0052] The following details the functions of the multi-scenario expert scoring agent module 3, including:

[0053] The road performance acquisition unit 31 is used to acquire road performance data of asphalt mixtures and integrate them into a road performance database. This can be achieved by collecting and importing road performance data samples from public datasets, laboratory road performance measured data samples, and paper or public text road performance test data samples. Missing values and outliers are removed through data preprocessing, and the data is normalized to obtain road performance data. The expert score calculation unit 32 is used to calculate the weight of road performance based on the expert's evaluation of the importance of road performance, and adopts the hierarchical analysis method to obtain the weight of road performance. The comprehensive performance score of different asphalt mixtures is calculated based on the obtained weight and the samples in the road performance database. For example, based on the multi-scenario expert evaluation agent model and the reconstructed road performance importance evaluation, the 1-9 scaling method is used to establish a road performance judgment matrix under different scenarios, and the hierarchical single ranking method is used to calculate the weight of each road performance. Then, a consistency test is performed. The multi-scenario expert evaluation agent model is used to objectify the subjective scoring weight of experts in the hierarchical analysis method, which is more universal and correct. The calculation formula of the comprehensive performance score of asphalt mixture is:

[0054]

[0055] In the above formula, P j is the comprehensive performance score of any asphalt mixture, α i is the data value of the indoor test index of the road performance of asphalt mixture i, α i，max is the maximum value of the i-th road performance indoor test index data in the road performance indoor test index database.

[0056] The scoring agent model establishment unit 33 is used to construct a mapping relationship from the importance of road performance, road performance to the comprehensive performance score through an artificial intelligence algorithm to establish a multi-scenario comprehensive performance scoring model. Specifically, based on the road performance database, the reconstructed road performance importance evaluation and the comprehensive performance scores of the aforementioned samples at different road performance importance levels, a multi-scenario road performance-scoring database is established, and a self-service method is used to use 80% of the samples in the multi-scenario road performance-scoring database as a training set, and the remaining 20% as a test set. The reconstructed road performance importance evaluation and the asphalt mixture road performance data in the training set are used as inputs of the artificial intelligence machine learning model, and the asphalt mixture comprehensive performance score is used as output. The training set is used to train to obtain a multi-scenario comprehensive performance scoring model, and the test set is used to verify the model prediction accuracy and adjust hyperparameters, so as to obtain the best multi-scenario comprehensive performance scoring model.

[0057] The following is a detailed introduction to the various functions in the reliability design module 4, including:

[0058] The random variable determination unit 41 is used to determine the type of the performance function random variable based on the comprehensive performance score. Specifically, the road performance and its importance evaluation are each regarded as a random variable. The road performance random variable is regarded as a random variable that satisfies the lognormal distribution. Its mean and standard deviation are obtained through test data. Several parallel test data of a road performance are considered as independent samples to participate in the calculation of the statistical parameters of the road performance random variable. The road performance importance evaluation random variable is regarded as a random variable with a fixed mean and a standard deviation of zero. Its mean is the input value of the road performance importance in the multi-scenario comprehensive performance scoring model. i represents the random variable of the ith road performance indoor test index, N i represents the i-th road performance importance score random variable, then the multi-scenario comprehensive performance scoring model can be regarded as a resistance nonlinear function R(X1,…,X i ,…,X C ,N1,…,N i ,…,N C ).

[0059] The function function determining unit 42 is used to establish a function function based on the relationship between the action effect and the resistance. Specifically, a scoring value P required by the designer to meet the actual needs of the project is selected, and the effect function is S=P. Based on the effect function, the resistance nonlinear function and the function function, a function function for scoring the comprehensive performance of the asphalt mixture is established. The function function expression is as follows:

[0060] Z=g(X1,…,X i ,…,XC ,N1,…,N i ,…,N C )=R(X1,…,X i ,…,X C ,N1,…,N i ,…,N C )

[0061] In the above formula, Z is the functional function, g is the function name of the functional function, R is the function name of the resistance nonlinear function, and S is the effect function.

[0062] The reliability index calculation unit 43 is used to establish a reliability index function of the comprehensive performance of the asphalt mixture by the first-order second moment method. Specifically, the function function Z of the comprehensive performance score of the asphalt mixture is expanded according to the Taylor series at the mean of each random variable according to the mean first-order second moment method, and only the linear terms are retained. The approximate expression of the function function is as follows:

[0063]

[0064] In the above formula, Z' is the approximate expression of the performance function, Denoted as a random variable X i The mean of is the partial derivative of the function with respect to the random variable at the mean The assignment of is the random variable N i The mean of is the partial derivative of the function with respect to the random variable at the mean The assignment at .

[0065] The expression of the mean value of the performance function is as follows:

[0066]

[0067] The expression for the standard deviation of the performance function is as follows:

[0068]

[0069] In the above formula, μ z is the mean of the performance function; σ z is the standard deviation of the performance function, is a random variable X i The standard deviation of is the random variable N i The standard deviation of .

[0070] The asphalt mixture design unit 44 is used to perform a road performance test on a new asphalt mixture, and calculates a reliability index based on a reliability index function, and selects the asphalt mixture with a large reliability index as the optimal design solution. Specifically, based on the mean and standard deviation of the performance function obtained in the above steps, the reliability index β of different asphalt mixtures is calculated. The larger the reliability index β, the more reliable the asphalt mixture. The reliability index β can be calculated as follows:

[0071]

[0072] Those skilled in the art will appreciate that all or part of the steps in the above-mentioned embodiment methods can be accomplished by instructing the relevant hardware through a program. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0073] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to in detail. For the above embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For relevant parts, please refer to the partial description of the method embodiments.

[0074] The above embodiments provide a detailed introduction to the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core ideas. At the same time, for those skilled in the art, according to the ideas of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

Claims

1. A multi-scenario asphalt mixture design system based on comprehensive performance scoring reliability, characterized by: The system includes: A custom design parameter determination module (1) is used to obtain all regional samples within a sample area according to designer requirements, classify the regional samples according to preset rules to set several levels of climate zones, and set the road performance of asphalt mixtures for different climate zones; A multi-scenario expert evaluation agent module (2) is used to obtain the importance evaluations of asphalt mixture road performance under different climate zones by several experts, and to establish a multi-scenario expert evaluation agent model to unify the importance evaluations of road performance under different climate zones; A multi-scenario expert scoring agent module (3) is used to obtain road performance data of asphalt mixtures to establish a road performance database, and based on the unified road performance importance evaluation, use a hierarchical analysis method to obtain the weight of the road performance and calculate the comprehensive performance score of the asphalt mixture; A reliability design module (4) is used to establish a function function and the type of a function function random variable according to the relationship between the comprehensive performance score, action effect and resistance of the asphalt mixture road, and calculate the reliability index of the new asphalt mixture through the reliability index function, and then select the asphalt mixture with the largest reliability index as the optimal design solution.

2. The asphalt mixture design system according to claim 1, characterized in that: The custom design parameter determination module (1) comprises: A climate zoning unit (11), wherein the climate zoning unit (11) is used to set a plurality of levels of climate zoning and division rules, and to divide regional samples into different climate zones according to the climate, soil conditions and traffic load of the regional samples; A road performance unit (12) is used to set the road performance required for asphalt mixtures used in different climate zones.

3. The asphalt mixture design system according to claim 1, characterized in that: The multi-scenario expert evaluation agent module (2) includes: An expert evaluation acquisition unit (21) is used to collect a plurality of expert opinions, obtain the evaluation of the importance of road performance under different climate zones by each expert, so as to construct the road performance importance vector of different climate zones, and establish a multi-scenario expert scoring database; An evaluation agent model establishment unit (22), wherein the evaluation agent model establishment unit (22) is used to construct a mapping relationship between climate zones and road performance importance through an artificial intelligence algorithm, so as to establish a multi-scenario expert evaluation agent model that simulates the thinking and evaluation logic of experts; The importance proxy unit (23) is used to re-input each road performance importance vector in the multi-scenario expert scoring database into the model, and obtain the road performance importance value through the multi-scenario expert evaluation proxy model.

4. The asphalt mixture design system according to claim 3, characterized in that: The evaluation agent model establishment unit (22) adopts a self-help method to use 80% of the samples in the obtained multi-scenario expert scoring database as a training set, and the remaining 20% of the samples as a test set, and uses the climate zone combination in the training set as the input of the artificial intelligence machine learning model, and uses the road performance importance vector corresponding to the climate zone as the output of the artificial intelligence machine learning model. After training, a multi-scenario expert evaluation agent model is obtained, and the model output layer adopts a linear activation function to output the road performance importance score. The model loss function adopts a mean square error loss function, and the MSE loss function formula is: In the above formula, LOSS is the mean square error loss value, n represents the number of samples in the multi-scenario expert scoring database, C is the number of road performance that needs to be considered, and y ic is the actual expert score of the i-th road performance, The importance score of the i-th road performance item predicted by the multi-scenario expert evaluation agent model is given, and the score reflects the importance of various road performance items.

5. The asphalt mixture design system according to claim 1, characterized in that: The multi-scenario expert scoring agent module (3) includes: A road performance acquisition unit (31), the road performance acquisition unit (31) is used to acquire road performance data of the asphalt mixture and integrate the data into a road performance database; An expert scoring calculation unit (32), the expert scoring calculation unit (32) is used to obtain the weight of the road performance according to the expert's evaluation of the importance of the road performance by using the hierarchical analysis method, and calculate the comprehensive performance score of different asphalt mixtures according to the obtained weight and samples of the road performance database; A scoring proxy model establishment unit (33) is used to construct a mapping relationship from the importance of road performance, road performance to comprehensive performance scores through an artificial intelligence algorithm to establish a multi-scenario comprehensive performance scoring model.

6. The asphalt mixture design system according to claim 5, characterized in that: The calculation formula for the comprehensive performance score of the asphalt mixture is: In the above formula, P j is the comprehensive performance score of any asphalt mixture, α i is the data value of the indoor test index of the road performance of asphalt mixture i, α i，max is the maximum value of the i-th road performance indoor test index data in the road performance indoor test index database.

7. The asphalt mixture design system according to claim 1, characterized in that: The reliability design module (4) comprises: A random variable determination unit (41), the random variable determination unit (41) is used to determine the type of the performance function random variable according to the comprehensive performance score; A function determination unit (42), the function determination unit (42) being used to establish a function according to the relationship between the action effect and the resistance; A reliability index calculation unit (43), wherein the reliability index calculation unit (43) is used to establish a reliability index function of the comprehensive performance of the asphalt mixture by a first-order second moment method; An asphalt mixture design unit (44) is used to conduct a road performance test on a new asphalt mixture, calculate a reliability index according to a reliability index function, and select an asphalt mixture with a large reliability index as an optimal design solution.

Images