Proportioning optimization method and system for asphalt mixture

Abstract

The invention relates to the technical field of asphalt mixing, and discloses a proportioning optimization method and system for an asphalt mixture, and the system comprises an acquisition module, a feature construction module, a comparative analysis module, a judgment regulation and control module and a database module. The method comprises the following steps: constructing a structural feature set and a response evolution factor set by collecting mixing response data, compaction response data and volume change data of samples with different proportions; comparing the difference between the current sample and the historical sample, calculating the ratio response deviation degree and grading; and when the grade is a second grade, generating a ratio optimization strategy by combining the change direction relationship between the structural characteristics and the response factors. According to the invention, ratio intelligent judgment and regulation and control strategy output can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of asphalt mixing, and more particularly, to a method and system for optimizing the proportion of asphalt mixtures. Background Art

[0002] As one of the most commonly used paving materials in road engineering, the performance stability of asphalt mixtures directly affects the structural strength, service life and construction adaptability of road surfaces. In existing engineering practices, the proportioning parameters of asphalt mixtures are usually initially set based on laboratory trial mixing data or empirical formulas, and then adjusted through repeated tests to approximate the target performance. This method not only has a long cycle and low efficiency, but also lacks a systematic correlation between the proportioning structure and the actual response, resulting in difficulty in predicting in advance the performance evolution trend during the material mixing, compaction and cooling processes, and affecting the consistency of engineering quality and the real-time nature of regulation.

[0003] Some studies have attempted to introduce data-driven methods to model and evaluate the performance of asphalt mixtures, but most of them only focus on the mapping relationship between mechanical indexes and static proportions, ignoring the response evolution process during construction, such as the viscosity change during the mixing process, the density growth trend during the compaction stage, and the volume shrinkage behavior after cooling. These key factors have a significant impact on the final performance.

[0004] Therefore, there is an urgent need to construct a proportioning optimization system that integrates structural characteristics and response evolution information. Through a path deduction and grade judgment mechanism, accurately identify the structural differences and the matching degree of response trends between the current state and historical samples, and then realize the intelligent and closed-loop optimization of the proportioning structure. Summary of the Invention

[0005] In view of this, the present invention proposes a method and system for optimizing the proportion of asphalt mixtures to solve the above problems.

[0006] On the one hand, a proportioning optimization system for asphalt mixtures proposed by the present invention includes:

[0007] A collection module configured to obtain the mixing response data, compaction response data, and volume change data during the cooling process of several asphalt mixture samples with different proportioning parameters in historical data;

[0008] A feature construction module configured to construct a set of structural features according to the proportioning parameters, and construct a set of response evolution factors according to the mixing response data, compaction response data, and volume change data;

[0009] A comparative analysis module, configured to obtain a set of structural characteristics and response evolution factors of a current mixture sample to be tested, compare them with a set of structural characteristics and response evolution factors of historical samples, calculate the degree of deviation of the ratio response, and match the degree of deviation of the ratio response with a set grading standard to determine the grade; the grades include a first grade and a second grade with an increasing degree of deviation of the ratio response in sequence.

[0010] A judgment and regulation module, configured to, when the grade is the second grade, analyze the matching relationship between the change direction of the set of structural characteristics of the mixture sample to be tested and the change direction of the response evolution factors; and output a ratio optimization strategy according to the relationship between the change direction of the set of structural characteristics and the change direction of the response evolution factors.

[0011] A database module, configured to establish a database including a set of structural characteristics, response evolution factors and grades of calibrated ratio samples.

[0012] Further, it further includes:

[0013] A path deduction module, configured to compare the mixture sample to be tested and the database according to the set of structural characteristics and response evolution factors, obtain adjacent mixture samples, and output an adjustable parameter interval and a risk of structural deviation trend of the mixture sample to be tested based on the historical response evolution factor change direction and label grade of the adjacent mixture samples.

[0014] Before the judgment and regulation module is started, the path deduction module is called in advance.

[0015] Further, the ratio parameters include: the ratio of coarse and fine aggregates, which is the mass ratio of coarse aggregates to fine aggregates; the mineral powder content, which is the filler content of the asphalt mixture; the asphalt content, which is the asphalt content of the asphalt mixture; the target void ratio, which is the air volume fraction of the asphalt mixture.

[0016] The mixing response data is the viscosity change curve during the mixing process; the compaction response data is the process data of the density changing with the compaction angle or compaction times during the compaction process; the volume change data is the volume change curve of the asphalt mixture during the natural cooling process.

[0017] Further, the set of structural characteristics constructed by the feature construction module includes:

[0018] The relative deviation value between the ratio of coarse and fine aggregates and the standard gradation curve, the fitting residual value between the mineral powder content and the target void ratio, and the wrapping factor between the specific surface area of unit aggregate and the asphalt content; the coupling offset between the target void ratio and the stable compaction value of the compaction prediction model.

[0019] The set of response evolution factors constructed by the feature construction module includes:

[0020] During the mixing stage, the time period from the start of mixing to the moment when the viscosity reaches its maximum value, and the first-order slope value obtained by fitting the viscosity change curve within this time period using the least squares method; during the compaction stage, the average compaction density growth rate within the first 25% range of the total compaction times, and the standard deviation of the compaction density change within the last 25% range of the total compaction times; during the cooling stage, from the moment of unloading until the temperature drops to room temperature, the maximum change rate of the shrinkage rate in the volume change curve and the duration during which the maximum change rate continuously exceeds twice the average change rate in the volume change curve;

[0021] Wherein, the specific surface area of the unit aggregate is the total specific surface area corresponding to the aggregate per unit mass or per unit volume under the current mix proportion structure.

[0022] Further, the comparative analysis module specifically includes:

[0023] Calculate the vectorized similarity based on the structural feature set and the response evolution factor set respectively, and calculate the degree of difference between the current mixture sample to be measured and the historical samples in the database through Euclidean distance, cosine angle or Mahalanobis distance;

[0024] Generate a mix proportion response deviation vector according to the similarity, and the index values in the deviation vector are weighted by normalization to obtain the mix proportion response deviation degree;

[0025] Match the mix proportion response deviation degree with the set classification standard threshold, and assign the first grade or the second grade respectively; when the mix proportion response deviation degree exceeds the upper limit of the second grade, it is classified into the second grade.

[0026] Further, when the judgment and regulation module receives the second grade, it performs the following operations:

[0027] Obtain the numerical change directions of the proportion of coarse and fine aggregates, the content of mineral powder and the content of asphalt in the current mixture sample to be measured in the structural feature set;

[0028] At the same time, extract from the response evolution factor set: the time period from the start of mixing to the moment when the viscosity reaches its maximum value, the first-order slope value obtained by fitting the viscosity change curve, the average compaction density growth rate, the standard deviation of the compaction density change, the maximum change rate of the shrinkage rate and the change direction of the duration;

[0029] If the change directions of the proportion of coarse and fine aggregates, the content of mineral powder and the content of asphalt in the structural feature set are consistent with the change direction of any index in the response evolution factor set, it is judged that the structural adjustment and the performance response are in line, and at this time, the asphalt content is finely adjusted;

[0030] If the change direction of any parameter in the structural feature set is opposite to the directions of two or more indicators in the response evolution factor set, it is determined as a proportion disturbance mismatch, and the coarse and fine aggregate ratio and mineral powder content are re-evaluated, and the adjustment of the asphalt content is postponed.

[0031] If the maximum change rate of the shrinkage rate and its duration index both exceed twice the average level of historical samples, an abnormal volume stability prompt is output, and the target void ratio is adjusted or the cooling process configuration is optimized.

[0032] Furthermore, based on the matching results of the structural feature set and the response evolution factor set in the database, the path deduction module performs the following operations:

[0033] Select the top five historical samples with the smallest Euclidean distance from the structural feature set of the current mixture sample to be tested as adjacent mixture samples;

[0034] Extract the corresponding response evolution factor sets from these adjacent mixture samples, including the first-order slope value of the viscosity change curve, the average density growth rate, the standard deviation of density change, the maximum change rate of shrinkage rate and the duration;

[0035] Construct a response path trajectory according to the numerical change direction of the response evolution factor set and the corresponding proportion parameter adjustment record;

[0036] Based on the change trend of the response evolution factor set of the mixture sample to be tested under different proportion parameter adjustment conditions, a structural response prediction sequence is formed, and the prediction result is output to the judgment and control module.

[0037] Furthermore, the path deduction module further includes a structural risk analysis unit, and the structural risk analysis unit is configured to:

[0038] Calculate the adjustable parameter interval of the mixture sample to be tested under the current structural condition according to the combined change history of the structural feature set and the response evolution factor set in the adjacent mixture samples;

[0039] Calculate the structural deviation trend risk level according to whether the maximum change rate of the shrinkage rate and the duration are higher than the 95% confidence interval corresponding to the samples in the database;

[0040] When both the maximum change rate of the shrinkage rate and the duration are in the abnormal interval, a high risk level is output. If only one index is high, a medium risk level is output. When both are in the normal interval, a low risk level is output.

[0041] Furthermore, when the number of adjacent mixture samples in the database that meet the following conditions is less than three, a supplementary mechanism is executed:

[0042] The Euclidean distance between the set of structural feature sets and the current mixture sample to be measured is less than or equal to the set threshold value; the set of response evolution factors includes the first-order slope value of the viscosity change curve and the average compaction growth rate within the set floating range;

[0043] The supplementary mechanism includes collecting three groups of mixture samples and collecting the corresponding mixing response data, compaction response data, and volume change data;

[0044] The feature construction module constructs the structural feature set and the response evolution factor set and incorporates them into the database module.

[0045] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0046] By constructing structural feature parameters such as the relative deviation of the coarse and fine aggregate ratio, the wrapping factor, and the coupling offset, and combining dynamic response evolution factors such as the slope of the viscosity curve, the compaction growth rate, and the volume shrinkage rate, an intermediate characterization mechanism between structure and performance is established to improve the discrimination ability of complex mixing ratio structure states.

[0047] Introduce the degree of ratio response deviation and the grading mechanism to enhance the pertinence and grading of the regulation judgment

[0048] The system generates a normalized ratio response deviation degree by calculating the similarity between the structural feature set and the response evolution factor through vectorized comparison, and divides the first level and the second level accordingly, providing a clear classification basis for subsequent strategy decision-making and avoiding blind adjustment or hasty correction. A collaborative judgment path for the structural and response change directions is constructed to improve the rationality and refinement level of the optimization strategy generation. In the second-level state, the system determines whether the adjustment of the structure leads to performance improvement by analyzing whether the change directions of the coarse and fine aggregate ratios, mineral powder content, and asphalt content match the change trends of the respective response evolution factors. If the directions are the same, it is defined as collaborative optimization, and the asphalt content is preferentially and finely adjusted; if the directions are opposite, it is identified as perturbation mismatch to prevent incorrect optimization and improve the pertinence of the ratio adjustment. A path deduction module and a structural risk analysis mechanism are introduced to achieve predictive control and safety boundary prompt. The system constructs a response path trajectory based on historical adjacent samples and outputs a structural response prediction sequence, making the ratio adjustment no longer dependent on single-point response and having trend foresight; at the same time, the structural offset risk level is calculated based on the position of the maximum shrinkage rate and its duration relative to the 95% confidence interval in the database, providing a quantifiable support for the cooling stability assessment. When the number of adjacent samples is insufficient, the system can automatically trigger a fast sampling mechanism to collect boundary samples and construct their structural feature sets and response evolution factors, which are supplemented to the database to effectively solve the inference fault problem caused by sample sparsity and maintain the stability and effectiveness of the control strategy generation. The system of the present invention can be widely applied to links such as initial ratio optimization, on-site trial mixing parameter adjustment, quality anomaly diagnosis, and construction rhythm control in road engineering, can dynamically perceive the behavior of materials and provide reasonable strategies, and significantly improve the consistency and intelligent level of the whole process of engineering material design-production-construction.

[0049] On the other hand, a method for optimizing the ratio of asphalt mixture proposed by the present invention includes:

[0050] S1: Obtain the mixing response data, compaction response data, and volume change data during the cooling process of several asphalt mixture samples with different ratio parameters in historical data;

[0051] S2: Construct a structural feature set according to the ratio parameters, and construct a response evolution factor set according to the mixing response data, compaction response data, and volume change data;

[0052] S3: Obtain the structural feature set and response evolution factor of the current mixture sample to be tested, compare them with the structural feature set and response evolution factor set of the historical samples, calculate the ratio response deviation degree, and match the ratio response deviation degree with the set grading standard to determine the level; the levels include a first level and a second level with gradually increasing ratio response deviation degrees;

[0053] S4: When the level is the second level, analyze the matching relationship between the change direction of the structural feature set of the mixture sample to be tested and the change direction of the response evolution factor; according to the relationship between the change direction of the structural feature set and the change direction of the response evolution factor, and output a mixing ratio optimization strategy.

[0054] S5: Establish a database including the structural feature set, response evolution factor, and level of the calibrated mixing ratio samples.

[0055] It should be noted that a mixing ratio optimization method for asphalt mixture of the present invention has the same beneficial effects as its system, which will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0057] Figure 1 is a functional block diagram of a mixing ratio optimization system for asphalt mixture provided by an embodiment of the present invention.

[0058] Figure 2 is a flowchart of a mixing ratio optimization method for asphalt mixture provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] The exemplary embodiments disclosed in the present application will be described in more detail below with reference to the drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0060] Refer to Figure 1 As shown, an embodiment of the present invention provides a mixing ratio optimization system for asphalt mixture, including:

[0061] A collection module, configured to obtain the mixing response data, compaction response data, and volume change data during the cooling process of several asphalt mixture samples with different mixing ratio parameters in historical data.

[0062] A feature construction module, configured to construct a set of structural features according to the mixing ratio parameters, and construct a set of response evolution factors according to the mixing response data, compaction response data, and volume change data.

[0063] A comparative analysis module, configured to obtain the set of structural features and response evolution factors of the current mixture sample to be tested, compare them with the set of structural features and response evolution factors of the historical samples, calculate the degree of deviation of the mixing ratio response, and match the degree of deviation of the mixing ratio response with the set grading criteria to determine the grade; the grades include a first grade and a second grade with an increasing degree of deviation of the mixing ratio response in sequence.

[0064] A judgment and regulation module, configured to analyze the matching relationship between the change direction of the set of structural features and the change direction of the response evolution factors of the mixture sample to be tested when the grade is the second grade; according to the relationship between the change direction of the set of structural features and the change direction of the response evolution factors, and output a mixing ratio optimization strategy.

[0065] A database module, configured to establish a database including the set of structural features, response evolution factors, and grades of the calibrated mixing ratio samples.

[0066] It should be noted that by collecting the full-process response data in the mixing, compaction, and cooling stages, a multi-dimensional parameter set of structural features and response evolution factors is constructed to realize the quantitative evaluation and grade division of the asphalt mixture mixing ratio performance; when it is identified as the second grade with a large deviation, the optimization strategy is further deduced in combination with the relationship between the structural and response change directions, so as to improve the pertinence and scientificity of the regulation. This system has functions of intelligent comparison, trend discrimination, and strategy output, can significantly improve the efficiency and quality of mixing ratio adjustment, and enhance the stability and adaptability of asphalt mixture design.

[0067] In some embodiments of the present application, it further includes: a path deduction module, configured to compare the mixture sample to be tested and the database according to the set of structural features and response evolution factors, obtain adjacent mixture samples, and output the adjustable parameter interval and structural deviation trend risk of the mixture sample to be tested based on the historical response evolution factor change direction and label grade of the adjacent mixture samples.

[0068] Before the judgment and regulation module is started, the path deduction module is called in advance.

[0069] In this embodiment, the specific implementation steps of the path deduction module include: 1. Sample matching stage: The path deduction module first receives the set of structural features and response evolution factors of the current mixture sample to be tested; subsequently, it calls the database module to screen out the first several groups of adjacent samples with the smallest Euclidean distance between the set of structural features and the set of structural features of the current sample from the historical samples as the matching sample set.

[0070] 2. Response path extraction stage: For each sample in the matching sample set, extract its corresponding set of response evolution factors, and divide them into three stages: mixing, compaction, and cooling; analyze the change directions of the response evolution factors in each stage (such as the increase or decrease of the first-order slope, the increase in compaction speed, or the expansion of stability fluctuations, etc.) and the corresponding historical changes in structural characteristics; associate the change direction of the response evolution factor with the label level (the first level or the second level) to form an evolution path sample group of structure-response-level.

[0071] 3. Structural response trend deduction stage: Substitute the set of structural characteristics of the current mixture sample to be tested into the above-mentioned structure-response path group respectively to simulate the change of the response trend under the existing historical evolution path; if the trend of the response evolution factor in the simulation result is highly similar to the path of the corresponding second-level sample in history, it is determined that there is a risk of structural deviation trend, and the risk level is recorded.

[0072] 4. Adjustable parameter interval calculation stage: Analyze the adjustment direction and amplitude of the structural parameters (such as the ratio of coarse and fine aggregates, the content of mineral powder, the content of asphalt) in the process of optimizing from the second level to the first level in the path; calculate the maximum and minimum boundaries for the current structural parameters to achieve performance improvement in different paths to form the adjustable parameter interval of the current mixture sample to be tested.

[0073] 5. Risk output and module linkage: Output the adjustable parameter interval and the structural deviation trend risk level in the above deduction result to the judgment and control module; before the judgment and control module is officially started, the system control process automatically pre-calls the path deduction module to complete the above calculations to ensure that the generation of the control strategy has a basis for trend prediction.

[0074] In some embodiments of the present application, the mixing ratio parameters include: the ratio of coarse and fine aggregates, which is the mass ratio of coarse aggregates to fine aggregates; the content of mineral powder, which is the filler content of the asphalt mixture; the content of asphalt, which is the asphalt content of the asphalt mixture; the target void ratio, which is the air volume fraction of the asphalt mixture; the mixing response data is the viscosity change curve during the mixing process; the compaction response data is the process data of the change of the compaction degree with the compaction angle or the number of compaction times during the compaction process; the volume change data is the volume change curve of the asphalt mixture during the natural cooling process.

[0075] It should be noted that the coarse and fine aggregate ratio refers to the mass ratio or volume ratio between coarse aggregates (such as crushed stones) and fine aggregates (such as sands), which is used to control the grading curve of the mixture. The filler content refers to the proportion of the filler (such as limestone powder) added to the unit mixture, which has a significant impact on the filling property and bonding property. The asphalt content is the mass percentage of asphalt in the unit mixture, which is a key parameter for controlling the bonding performance, durability and rutting resistance. The target void ratio is the volume fraction of air expected to be retained in the total volume inside the formed mixture under the design requirements, which determines the density, durability, etc.

[0076] In some embodiments of the present application, the set of structural features constructed by the feature construction module includes: the relative deviation value between the coarse and fine aggregate ratio and the standard grading curve, the fitting residual value between the filler content and the target void ratio, and the wrapping factor between the specific surface area per unit aggregate and the asphalt content; the coupling offset between the target void ratio and the stable density value of the compaction prediction model; the set of response evolution factors constructed by the feature construction module includes: in the mixing stage, the time period from the start of mixing to the moment when the viscosity reaches the maximum value, and the first-order slope value obtained by fitting the viscosity change curve during this time period by the least squares method; in the compaction stage, the average density growth rate within the first 25% interval of the total compaction times, and the standard deviation of the density change within the last 25% interval of the total compaction times; in the cooling stage, from the unloading moment to the moment when the temperature drops to room temperature, the maximum change rate of the shrinkage rate in the volume change curve and the duration during which the maximum change rate continuously exceeds twice the average change rate in the volume change curve; where the specific surface area per unit aggregate is the total specific surface area corresponding to the aggregate per unit mass or unit volume under the current mixing ratio structure.

[0077] It should be noted that the construction steps of the set of structural features: Obtain the mixing ratio parameters of the current mixture sample: including the coarse and fine aggregate ratio, the filler content, the asphalt content, and the target void ratio. Calculate the relative deviation value between the coarse and fine aggregate ratio and the standard grading curve.

[0078] Fit and compare the particle size grading data of the current coarse and fine aggregates with the target standard grading curve; calculate the difference at each particle size point, normalize it and take the absolute value average as the relative deviation value for output.

[0079] Calculate the fitting residual value between the filler content and the target void ratio, and use the existing statistical regression model of the filler content and the target void ratio for prediction; compare the actually measured void ratio with the model prediction value, and take the residual value as the feature output.

[0080] Calculate the wrapping factor between the specific surface area of unit aggregate and the asphalt content: Obtain the particle size composition and density of all aggregates in the current mix ratio; Estimate the specific surface area per unit mass or volume based on the aggregate particle size and shape; Establish a ratio relationship model between the specific surface area and the asphalt content, and output the wrapping factor representing the asphalt wrapping ability.

[0081] Calculate the coupling offset between the target void ratio and the stable compaction value of the compaction prediction model: Call the compaction prediction model established in the database, input the current structural parameters, and predict its final compaction value; Take the difference between the predicted density and the target void ratio as the coupling offset and output it.

[0082] Index extraction in the mixing stage: Extract the time period from the start of mixing to when the viscosity reaches the maximum value, locate the starting point and peak of the viscosity curve from the collected mixing response data; Calculate the time interval between the two as the viscosity rising time period and output it.

[0083] Fit the viscosity change curve and extract the first-order slope value: Perform least squares linear fitting on the viscosity data within the above time period; Take the first derivative value of this linear function, which is the first-order slope value of viscosity growth.

[0084] Index extraction in the compaction stage: Calculate the average density growth rate within the first 25% compaction times interval, and extract the total compaction times from the compaction response data; Intercept the first 25% of the compaction process data, calculate the ratio of density growth to compaction times, and output the average growth rate.

[0085] Calculate the standard deviation of density change in the last 25% interval: Extract the data in the last 25% compaction stage, calculate the standard deviation of density change within this interval, which is used to reflect the later compaction volatility.

[0086] Index extraction in the cooling stage: Calculate the maximum change rate of the shrinkage rate in the volume change curve, perform derivative processing on the volume change curve to obtain the volume change rate per unit time; Obtain the maximum change rate from the derivative curve, that is, the point with the maximum negative slope.

[0087] Calculate the average value of the derivative of the volume change curve; Identify the time length when the derivative value is greater than twice the average value within a continuous time interval and output this duration.

[0088] Method for obtaining the specific surface area of unit aggregate: For each particle size of aggregate, set its shape factor and surface area estimation coefficient (determined by experience or preliminary tests); Obtain the total specific surface area of the current sample by weighted average according to mass or volume ratio; Output the specific surface area of unit aggregate per unit mass (g / m²) or volume (cm² / cm³) as one of the structural characteristic indicators.

[0089] It should be noted that the establishment process of the compaction prediction model includes the following steps: First, collect the mix proportion parameters and corresponding compaction response data of historical asphalt mixture samples. The mix proportion parameters include the proportion of coarse and fine aggregates, the mineral powder content, the asphalt content, and the target void ratio. The compaction response data includes the complete curve of the density changing with the number of compaction passes. Second, based on the compaction curve of each group of samples, extract the average density of the stable interval at the end section as the stable density value label, and use the relative deviation value between the proportion of coarse and fine aggregates in the structural feature set and the standard gradation curve, the fitting residual value between the mineral powder content and the target void ratio, the wrapping factor between the specific surface area of unit aggregate and the asphalt content, etc. as input variables to construct the input-output mapping relationship. Subsequently, use a non-linear regression model or a regression model based on the gradient boosting algorithm for training, optimize the model performance through the mean square error or the mean absolute error, and use cross-validation to select the appropriate model structure and parameters. After the model training is completed, compare the predicted stable density value with the theoretical density value obtained by converting the target void ratio of the sample, and calculate its offset. This offset is used as the coupling offset index in the structural feature set for subsequent mix proportion coordination judgment and path deduction. This model can be continuously trained with the update of the database to improve the prediction accuracy of the compaction trend under different mix proportion structures.

[0090] In some embodiments of the present application, the comparative analysis module specifically includes: calculating the vectorized similarity based on the structural feature set and the response evolution factor set respectively, and calculating the difference degree between the current mixture sample to be tested and the historical samples in the database through the Euclidean distance, cosine angle or Mahalanobis distance; generating a mix proportion response deviation vector according to the similarity, and the index values of each item in the deviation vector are weighted by normalization to obtain the mix proportion response deviation degree; matching the mix proportion response deviation degree with the set grading standard threshold, and assigning the first grade or the second grade respectively; when the mix proportion response deviation degree exceeds the upper limit of the second grade, it is classified into the second grade.

[0091] In this embodiment, the specific implementation steps of the comparative analysis module include the following contents: First, obtain the structural feature set and the response evolution factor set of the current mixture sample to be tested. The structural feature set includes: the relative deviation value between the proportion of coarse and fine aggregates and the standard gradation curve, the fitting residual value between the mineral powder content and the target void ratio, the wrapping factor between the specific surface area of unit aggregate and the asphalt content, and the coupling offset between the target void ratio and the stable density value of the compaction prediction model; the response evolution factor set includes: the viscosity growth time period and the first-order slope value in the mixing stage, the average density growth rate and the density change standard deviation in the compaction stage, and the maximum change rate and the duration of the shrinkage rate in the cooling stage.

[0092] Then, perform numerical normalization on the above structural feature set and response evolution factor set, and convert them into vector forms of a unified dimension. Next, select all the calibrated historical samples in the database, extract the corresponding structural feature set and response evolution factor set, and also normalize them into vectors.

[0093] After the vector data preparation is completed, calculate the similarity between the current sample to be tested and each historical sample in terms of the structural feature dimension and response factor dimension respectively in ways such as Euclidean distance, cosine angle, or Mahalanobis distance. Combine the similarity indexes of each dimension into a matching response deviation vector.

[0094] Subsequently, apply normalized weighted calculation to each index in the deviation vector to obtain the comprehensive matching response deviation degree value. The larger this value is, the more significant the overall deviation between the current ratio and the historical database samples in terms of structure and response.

[0095] Finally, compare the calculated matching response deviation degree with the classification criteria set by the system: if it is within the range of the first-level threshold, assign the first-level label; if it is within the range of the second-level threshold or exceeds the upper threshold, uniformly assign the second-level label, but the system will simultaneously issue a structural adjustment strategy to assist the judgment and control module for subsequent analysis. This process can be combined with a dynamic threshold update mechanism to automatically adjust the level judgment criteria according to the continuous expansion of the database samples to improve the classification accuracy.

[0096] In some embodiments of the present application, when the judgment and control module receives the second level, it performs the following operations: Obtain the numerical change directions of the proportion of coarse and fine aggregates, mineral powder content, and asphalt content in the structural feature set of the current sample to be tested for the mixture; at the same time, extract from the response evolution factor set: the time period from the start of mixing to the moment when the viscosity reaches the maximum value, the first-order slope value obtained by fitting the viscosity change curve, the average density growth rate, the standard deviation of density change, the maximum change rate of the shrinkage rate, and the change direction of the duration; if the change directions of the proportion of coarse and fine aggregates, mineral powder content, and asphalt content in the structural feature set are consistent with the change direction of any index in the response evolution factor set, it is judged that the structural adjustment and performance response are consistent, and at this time, finely adjust the asphalt content; if the change direction of any parameter in the structural feature set is opposite to the directions of two or more indexes in the response evolution factor set, it is judged that the ratio disturbance is mismatched, re-evaluate the proportion of coarse and fine aggregates and the mineral powder content, and suspend the adjustment of the asphalt content; if the maximum change rate of the shrinkage rate and its duration index both exceed twice the average level of historical samples, output a prompt for abnormal volume stability, and adjust the target void ratio or optimize the cooling process configuration.

[0097] Specifically, for extracting the direction of structural parameter changes: First, extract the proportion parameters from the current mixture sample to be tested, namely the proportion of coarse and fine aggregates, the content of mineral powder, and the content of asphalt; compare them with the mean value of the structural feature set in the historical samples or the reference sample to determine the change direction (increase, decrease, or basically unchanged) of each structural parameter in the current sample.

[0098] Next, separately extract from the response evolution factor set of this sample: during the mixing stage, the time period from the start of mixing to when the viscosity reaches the maximum value; the first-order slope value obtained by least-squares fitting of the viscosity change curve during this time period; the average density growth rate during the compaction stage; and the standard deviation of density change in the later stage of the compaction stage.

[0099] The maximum change rate of the shrinkage rate of the volume change curve and the duration during which this change rate continuously exceeds twice the average change rate during the cooling stage.

[0100] Compare these indicators with the historical data to determine the change trend (increase, decrease, or stability) of their values.

[0101] If the change direction of any one of the proportion of coarse and fine aggregates, the content of mineral powder, and the content of asphalt is the same as the change direction of any one response evolution factor (such as an increase in the aggregate proportion accompanied by an increase in the viscosity growth slope), it is inferred that the structural adjustment is reflected as a synergistic enhancement relationship in the performance response. At this time, perform a refined adjustment operation on the asphalt content (for example, a fine adjustment within ±0.1%).

[0102] If the change direction of any one of the above three structural parameters is opposite to the change direction of two or more response evolution factors (such as an increase in the mineral powder content but a decrease in the average density growth rate and an increase in density fluctuation), it is determined that the current proportion structure leads to performance mismatch, and it is determined as a disturbance mismatch type anomaly. At this time, suspend the adjustment of the asphalt content and re-evaluate the proportion of coarse and fine aggregates and the content of mineral powder.

[0103] When both the maximum change rate of the shrinkage rate and its abnormal duration during the cooling stage exceed twice the historical average value of the database (based on statistical indicators), the system determines that there is a volume stability problem; at this time, the system outputs a volume stability anomaly prompt, recommending that the user correct the target void ratio or adjust the process parameters during the cooling stage (such as extending the natural cooling time, optimizing the unloading time point, etc.) to reduce the later volume strain.

[0104] In some embodiments of the present application, based on the matching results of the structural feature set and the response evolution factor set in the database, the path deduction module performs the following operations: select the top five historical samples with the smallest Euclidean distance from the structural feature set of the current mixture sample to be tested as neighboring mixture samples; extract the corresponding response evolution factor sets from these neighboring mixture samples, including the first-order slope value of the viscosity change curve, the average density growth rate, the standard deviation of density change, the maximum change rate and duration of the shrinkage rate; construct a response path trajectory according to the numerical change direction of the response evolution factor set and the corresponding ratio parameter adjustment record; based on the change trend of the response evolution factor set of the mixture sample to be tested under different ratio parameter adjustment conditions, form a structural response prediction sequence, and output the prediction result to the judgment and control module.

[0105] Specifically, based on the matching results of the structural feature set and the response evolution factor set in the database, the specific implementation manner of the path deduction module is as follows: First, the system vectorizes the structural feature set of the current mixture sample to be tested and calculates the Euclidean distance between it and the structural feature sets of all calibrated historical samples in the database. The system automatically screens out the top five historical samples with the smallest Euclidean distance as neighboring mixture samples to ensure that the structural similarity is higher than the set matching threshold, so as to enhance the reliability of the response trend deduction.

[0106] Subsequently, extract the corresponding response evolution factor sets of the above neighboring mixture samples, including the first-order slope value of its viscosity change curve, the average density growth rate and the standard deviation of density change during the compaction process, as well as key parameters such as the maximum change rate of the shrinkage rate and the duration of this change rate during the cooling stage.

[0107] Next, the system combines the historical adjustment records of each ratio parameter in the neighboring samples, analyzes the numerical change direction of its response evolution factors, constructs multiple response path trajectories, and forms a mapping relationship graph of ratio perturbation - performance response as the basis for subsequent prediction.

[0108] Finally, the system performs path extrapolation simulation on the current mixture sample to be tested within the set adjustable ratio parameter range, calculates the trend change of its response evolution factor set, generates a structural response prediction sequence, and submits this prediction sequence together with the response trend stability index to the judgment and control module for subsequent reference in ratio optimization strategies and adjustment decision-making.

[0109] In some embodiments of the present application, the path deduction module further includes a structural risk analysis unit, which is configured to: calculate the adjustable parameter range of the mixture sample to be measured under the current structural conditions according to the combined change history of the structural feature set and the response evolution factor set in the adjacent mixture samples; calculate the structural deviation trend risk level according to whether the maximum change rate and duration of the shrinkage rate are higher than the 95% confidence interval corresponding to the samples in the database; when both the maximum change rate and duration of the shrinkage rate are in the abnormal range, output a high risk level, if only one index is on the high side, output a medium risk level, and output a low risk level when both are in the normal range.

[0110] Specifically, first, select multiple adjacent samples with a high degree of similarity to the structural feature set of the current mixture sample to be measured from the database (such as the first several groups with the smallest Euclidean distance).

[0111] Extract the relevant data in the corresponding structural feature set and response evolution factor set from these adjacent samples respectively, and construct a "structure-response" combined change history trajectory.

[0112] Analyze the historical adjustment records of the above adjacent samples on each structural feature parameter (such as the ratio of coarse and fine aggregates, the content of mineral powder, the content of asphalt) and the improvement trend of the corresponding response evolution factors, and identify which parameter adjustments have led to performance improvement (such as reduced density fluctuation, reduced shrinkage rate).

[0113] Integrate the value ranges of these successfully adjusted parameters to form the adjustable parameter range of the mixture to be measured under the current structural conditions. For example, if reducing the asphalt content from 5.3% to 5.0% in the historical adjacent samples has significantly reduced the shrinkage rate, the system can set 5.0 - 5.2% as the recommended adjustable range of asphalt for the current sample.

[0114] Risk index statistical analysis: Extract from the volume change data of the cooling stage of the current mixture sample: the maximum change rate of the shrinkage rate; the duration during which this change rate continuously exceeds twice the average change rate. Correspondingly, count the distribution of these two indicators from all the calibrated samples in the database, and calculate the 95% confidence interval respectively (for example: the upper limit of the maximum change rate is 0.012 mm / min, and the upper limit of the duration is 180 s).

[0115] If both the maximum change rate of the shrinkage rate and the duration of the current sample are higher than the upper limit of the above 95% confidence interval, that is, fall into the abnormal range, it is judged as a high risk level; if only one of the indicators exceeds, while the other is still within the normal range, it is judged as a medium risk level; if neither of the two indicators exceeds, it is judged as a low risk level.

[0116] The system automatically outputs the risk level of the structural offset trend based on the above analysis results, and can combine with the adjustable parameter range to generate a strategy for the judgment and control module, indicating whether to allow the execution of the structural adjustment operation or whether to prioritize the control of the cooling process.

[0117] In some embodiments of the present application, when the number of adjacent mixture samples that meet the following conditions in the database is less than three groups, a supplementary mechanism is executed: the Euclidean distance between the structural feature set and the current mixture sample to be measured is less than or equal to the set threshold; the response evolution factor set includes that the first-order slope value of the viscosity change curve and the average density growth rate are within the set floating range; the supplementary mechanism includes collecting three groups of mixture samples, and collecting the corresponding mixing response data, compaction response data and volume change data; the structural feature set and the response evolution factor set are constructed by the feature construction module and incorporated into the database module.

[0118] Specifically, when the number of adjacent mixture samples that meet the similarity conditions in the database is less than three groups, the system automatically triggers the supplementary mechanism, and its specific implementation method is as follows: Adjacent sample screening and judgment: First, the system performs comparison and retrieval on the current mixture sample to be measured in the following two dimensions: In the dimension of the structural feature set, calculate the Euclidean distance between all historical samples and the current sample, and screen out the samples with a distance less than or equal to the set threshold; in the dimension of the response evolution factor set, further screen out the samples in which the first-order slope value of the viscosity change curve and the average density growth rate are both within the set floating range.

[0119] If the number of samples that finally meet the above double conditions is less than three groups, the supplementary mechanism process is entered.

[0120] Based on the boundary conditions of the current mixing ratio parameters and the abnormal performance of their response evolution factors, the structural configurations of the three groups of supplementary samples to be collected should preferably cover the parameter combinations with the largest numerical change or the highest uncertainty in the current structural feature set. For example: if the ratio of coarse and fine aggregates deviates significantly from the standard grading curve, preferably collect a group of samples with the ratio of coarse and fine aggregates readjusted; if the fitting residual between the mineral powder content and the target void ratio is high, supplement a group of samples with the mineral powder content adjusted; if the wrapping factor corresponding to the asphalt content is significantly abnormal, supplement a group of samples with the asphalt content optimized.

[0121] Real-time collection of response data: For the three groups of designed supplementary structural samples, carry out standardized process flow operations, and record respectively: the viscosity change curve data during the mixing process; the density change data during the compaction process; the volume change curve during the natural cooling process.

[0122] All data collection needs to synchronize the time stamp and process control parameters to ensure data consistency and comparability.

[0123] Feature and factor construction: The system call feature construction module parses the original data of three groups of supplementary samples to generate a set of structural features and a set of response evolution factors. The calculation content should include: the proportion deviation of coarse and fine aggregates, the residual of mineral powder void ratio, the wrapping factor, the coupling offset; the first-order slope value of the viscosity curve, the density growth rate, the density standard deviation, the change rate and duration of the shrinkage rate.

[0124] Database supplementation and regression call: Supplement the above-mentioned constructed set of structural features and set of response evolution factors into the database module, update the database index, and automatically re-run the path deduction module for structural response matching and output of optimization strategies to ensure the sustainable operation of the subsequent regulation module and the accuracy of strategy generation.

[0125] See Figure 2 As shown, the embodiment of the present invention provides a method for optimizing the proportion of asphalt mixture, including:

[0126] S1: Obtain the mixing response data, compaction response data, and volume change data during the cooling process of several asphalt mixture samples with different proportion parameters in the historical data.

[0127] S2: Construct a set of structural features according to the proportion parameters, and construct a set of response evolution factors according to the mixing response data, compaction response data, and volume change data.

[0128] S3: Obtain the set of structural features and response evolution factors of the current mixture sample to be tested, compare them with the set of structural features and response evolution factors of the historical samples, calculate the degree of proportion response deviation, and match the degree of proportion response deviation with the set grading standard to determine the grade; the grades include the first grade and the second grade with the degree of proportion response deviation increasing in turn.

[0129] S4: When the grade is the second grade, analyze the matching relationship between the change direction of the set of structural features of the mixture sample to be tested and the change direction of the response evolution factors; according to the relationship between the change direction of the set of structural features and the change direction of the response evolution factors, and output the proportion optimization strategy.

[0130] S5: Establish a database including the set of structural features, response evolution factors, and grades of the calibrated proportion samples.

[0131] Finally, it should be noted that: The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: It is still possible to modify the specific implementation manners of the present invention or make equivalent replacements, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A mix proportion optimization system for asphalt mixture, characterized in that Including: A collection module configured to obtain the mixing response data, compaction response data, and volume change data during the cooling process of several asphalt mixture samples with different proportion parameters in historical data; A feature construction module configured to construct a structural feature set according to the proportion parameters, and construct a response evolution factor set according to the mixing response data, compaction response data, and volume change data; A comparison and analysis module configured to obtain the structural feature set and response evolution factors of the current mixture sample to be tested, compare them with the structural feature set and response evolution factor set of the historical samples, calculate the proportion response deviation degree, and match the proportion response deviation degree with the set grading standard to determine the grade; the grade includes a first grade and a second grade with gradually increasing proportion response deviation degrees; A judgment and regulation module configured to, when the grade is the second grade, analyze the matching relationship between the change direction of the structural feature set of the mixture sample to be tested and the change direction of the response evolution factors; and output a proportion optimization strategy according to the relationship between the change direction of the structural feature set and the change direction of the response evolution factors; A database module configured to establish a database including the structural feature set, response evolution factors, and grades of calibrated proportion samples; 2. The proportion optimization system for asphalt mixture according to claim 1, characterized in that Also including: A path deduction module configured to compare the mixture sample to be tested with the database according to the structural feature set and response evolution factors, obtain adjacent mixture samples, and output the adjustable parameter range and structural deviation trend risk of the mixture sample to be tested based on the historical response evolution factor change direction and label grade of the adjacent mixture samples; Before the judgment and regulation module is started, the path deduction module is called in advance; 3. The proportion optimization system for asphalt mixture according to claim 2, wherein The proportion parameters include: the coarse and fine aggregate ratio, which is the mass ratio of coarse aggregate to fine aggregate; the mineral powder content, which is the filler content of the asphalt mixture; the asphalt content, which is the asphalt content of the asphalt mixture; the target void ratio, which is the air volume fraction of the asphalt mixture; The mixing response data is the viscosity change curve during the mixing process; the compaction response data is the process data of the density changing with the compaction angle or compaction times during the compaction process; the volume change data is the volume change curve of the asphalt mixture during the natural cooling process; 4. The proportion optimization system for asphalt mixture according to claim 3, characterized in that, The structural feature set constructed by the feature construction module includes: The relative deviation value between the coarse and fine aggregate ratio and the standard gradation curve, the fitting residual value between the mineral powder content and the target void ratio, and the wrapping factor between the specific surface area per unit aggregate and the asphalt content; the coupling offset between the target void ratio and the stable compaction value of the compaction prediction model; The response evolution factor set constructed by the feature construction module includes: During the mixing stage, the time period from the start of mixing to the moment when the viscosity reaches its maximum value, and the first-order slope value obtained by fitting the viscosity change curve within this time period using the least squares method; during the compaction stage, the average density growth rate within the first 25% interval of the total compaction times, and the standard deviation of density change within the last 25% interval of the total compaction times; during the cooling stage, from the moment of unloading until the temperature drops to room temperature, the maximum change rate of the shrinkage rate in the volume change curve and the duration during which the maximum change rate continuously exceeds twice the average change rate in the volume change curve; Among them, the specific surface area of the unit aggregate is the total specific surface area corresponding to the aggregate per unit mass or unit volume under the current mixing ratio structure.

5. The proportion optimization system for asphalt mixture according to claim 4, characterized in that, The comparative analysis module specifically includes: Calculating the vectorized similarity based on the structural feature set and the response evolution factor set respectively, and calculating the degree of difference between the current mixture sample to be measured and the historical samples in the database through Euclidean distance, cosine angle or Mahalanobis distance; Generating a mixing ratio response deviation vector according to the similarity, and obtaining the mixing ratio response deviation degree by normalizing and weighting the index values in the deviation vector; Matching the mixing ratio response deviation degree with the set classification standard threshold, and assigning the first grade or the second grade respectively; when the mixing ratio response deviation degree exceeds the upper limit of the second grade, it is classified into the second grade.

6. The proportion optimization system for asphalt mixture according to claim 5, wherein When receiving the second grade, the judgment and regulation module performs the following operations: Obtaining the numerical change directions of the proportion of coarse and fine aggregates, the mineral powder content and the asphalt content in the structural feature set of the current mixture sample to be measured; At the same time, extracting from the response evolution factor set: the time period from the start of mixing to the moment when the viscosity reaches its maximum value, the first-order slope value obtained by fitting the viscosity change curve, the average density growth rate, the standard deviation of density change, the maximum change rate of the shrinkage rate and the change directions of the duration; If the change directions of the proportion of coarse and fine aggregates, the mineral powder content and the asphalt content in the structural feature set are consistent with the change direction of any index in the response evolution factor set, it is judged that the structural adjustment and performance response are in line, and at this time, the asphalt content is finely adjusted; If the change direction of any parameter in the structural feature set is opposite to the directions of two or more indexes in the response evolution factor set, it is judged that the mixing ratio perturbation is mismatched, and the proportion of coarse and fine aggregates and the mineral powder content are re-evaluated, and the adjustment of the asphalt content is postponed; If the maximum change rate of the shrinkage rate and its duration index both exceed twice the average level of historical samples, an abnormal volume stability prompt is output, and the target void ratio is adjusted or the cooling process configuration is optimized.

7. The proportion optimization system for asphalt mixture according to claim 6, characterized in that, Based on the matching results of the structural feature set and the response evolution factor set in the database, the path deduction module performs the following operations: Selecting the top five historical samples with the smallest Euclidean distance from the structural feature set of the current mixture sample to be measured as the adjacent mixture samples; Extracting the corresponding response evolution factor sets from these adjacent mixture samples, including the first-order slope value of the viscosity change curve, the average density growth rate, the standard deviation of density change, the maximum change rate of the shrinkage rate and the duration; Construct a response path trajectory according to the numerical change direction of the response evolution factor set and the corresponding ratio parameter adjustment record. Based on the change trend of the response evolution factor set of the mixture sample to be tested under different ratio parameter adjustment conditions, form a structural response prediction sequence and output the prediction result to the judgment and control module.

8. The proportion optimization system for asphalt mixture according to claim 7, wherein, The path deduction module further includes a structural risk analysis unit, and the structural risk analysis unit is configured to: Calculate the adjustable parameter interval of the mixture sample to be tested under the current structural condition according to the combined change history of the structural feature set and the response evolution factor set in the adjacent mixture samples. Calculate the structural deviation trend risk level according to whether the maximum change rate and the duration of the shrinkage rate are higher than the 95% confidence interval corresponding to the samples in the database. When both the maximum change rate and the duration of the shrinkage rate are in the abnormal interval, output a high risk level. If only one index is high, output a medium risk level. When both are in the normal interval, output a low risk level.

9. The proportion optimization system for asphalt mixture according to claim 8, wherein, When the number of adjacent mixture samples in the database that meet the following conditions is less than three groups, execute the supplement mechanism: The Euclidean distance between the structural feature set and the current mixture sample to be tested is less than or equal to the set threshold; the response evolution factor set includes the first-order slope value of the viscosity change curve and the average density growth rate within the set floating range. The supplement mechanism includes collecting three groups of mixture samples and collecting the corresponding mixing response data, compaction response data, and volume change data. The feature construction module constructs a structural feature set and a response evolution factor set and incorporates them into the database module.

10. A method for optimizing the mix proportion of asphalt mixture, characterized in that, Applied to the system according to any one of claims 1-9, the method includes: S1: Obtain the mixing response data, compaction response data, and volume change data during the cooling process of several asphalt mixture samples with different ratio parameters in the historical data. S2: Construct a structural feature set according to the ratio parameters, and construct a response evolution factor set according to the mixing response data, compaction response data, and volume change data. S3: Obtain the structural feature set and response evolution factors of the current mixture sample to be tested, compare them with the structural feature set and response evolution factor set of the historical samples, calculate the ratio response deviation degree, and match the ratio response deviation degree with the set grading standard to determine the grade; the grades include a first grade and a second grade with the ratio response deviation degree increasing in sequence. S4: When the grade is the second grade, analyze the matching relationship between the change direction of the structural feature set and the change direction of the response evolution factors of the mixture sample to be tested; according to the relationship between the change direction of the structural feature set and the change direction of the response evolution factors, and output a ratio optimization strategy. S5: Establish a database including the structural feature set, response evolution factors, and grades of the calibrated ratio samples.

Images