CN120409167A - A method and system for optimizing the ratio of asphalt mixture - Google Patents
A method and system for optimizing the ratio of asphalt mixtureInfo
- Publication number
- CN120409167A CN120409167A CN202510898952.8A CN202510898952A CN120409167A CN 120409167 A CN120409167 A CN 120409167A CN 202510898952 A CN202510898952 A CN 202510898952A CN 120409167 A CN120409167 A CN 120409167A
- Authority
- CN
- China
- Prior art keywords
- response
- change
- ratio
- mixture
- structural
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/25—Design optimisation, verification or simulation using particle-based methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Road Paving Machines (AREA)
Abstract
The invention relates to the technical field of asphalt mixing, and discloses a proportioning optimization method and system for asphalt mixtures. The method comprises the steps of collecting mixing response data, compaction response data and volume change data of samples with different proportions, constructing a structural feature set and a response evolution factor set, comparing differences of current samples and historical samples, calculating proportion response deviation degree, classifying the proportion response deviation degree, and generating a proportion optimization strategy by combining the change direction relation of the structural features and the response factors when the classification is a second classification. The invention can realize intelligent judgment of the proportion and output of the regulation strategy.
Description
Technical Field
The invention relates to the technical field of asphalt mixing, in particular to a proportioning optimization method and system for asphalt mixture.
Background
Asphalt mixture is used as one of the most commonly used paving materials in road engineering, and the performance stability of the asphalt mixture directly influences the structural strength, the service life and the construction adaptability of the road surface. In the prior engineering practice, the proportioning parameters of the asphalt mixture are generally preliminarily set according to laboratory trial-and-error data or an empirical formula, and then are adjusted through repeated experiments to approach the target performance. The method has long period and low efficiency, and the systematic association between the proportioning structure and the actual response is lacking, so that the performance evolution trend in the processes of material mixing, compaction and cooling is difficult to predict in advance, and the consistency of engineering quality and the real-time property of regulation and control are affected.
Some researches attempt to introduce a data driving method to model and evaluate the performance of the asphalt mixture, but focus on the mapping relation between the mechanical index and the static proportion, neglect the response evolution process in the construction process, such as viscosity change in the mixing process, compactness increasing trend in the compacting stage and volume shrinkage behavior after cooling, and the key factors have significant influence on the final performance.
Therefore, it is needed to construct a matching optimization system for fusing structural features and response evolution information, accurately identify the structural difference and response trend matching degree between the current state and the historical sample through a path deduction and grade judgment mechanism, and further realize intelligent closed-loop optimization of the matching structure.
Disclosure of Invention
In view of the above, the present invention provides a method and a system for optimizing the mixture ratio of asphalt mixture, so as to solve the above problems.
On one hand, the proportioning optimization system for the asphalt mixture provided by the invention comprises the following components:
The collecting module is configured to obtain mixing response data, compaction response data and volume change data in the cooling process of a plurality of asphalt mixture samples with different proportioning parameters in the historical data;
The characteristic construction module is configured to construct a structural characteristic set according to the proportioning parameters and construct a response evolution factor set according to the mixing response data, the compaction response data and the volume change data;
The comparison analysis module is configured to acquire a structural feature set and a response evolution factor of a current mixture sample to be tested, compare the structural feature set and the response evolution factor set of a historical sample, calculate a proportion response deviation degree, and match the proportion response deviation degree with a set grading standard to determine grades, wherein the grades comprise a first grade and a second grade with the proportion response deviation degree increased in sequence;
The judging and regulating module is configured to analyze the matching relation between the structural feature set change direction and the response evolution factor change direction of the mixture sample to be tested when the grade is the second grade;
and the database module is configured to establish a database comprising the structural feature set of the calibrated proportioning sample, the response evolution factors and the grades.
Further, the method further comprises the following steps:
The path deduction module is configured to compare a to-be-tested mixture sample with the database according to the structural feature set and the response evolution factor, acquire an adjacent mixture sample, and output an adjustable parameter interval and a structural deviation trend risk of the to-be-tested mixture sample based on the historical response evolution factor change direction and the label grade of the adjacent mixture sample;
And before the judging and regulating module is started, the path deduction module is called in advance.
Further, the proportioning parameters comprise the proportion of coarse aggregates to fine aggregates, the mineral powder doping amount, the asphalt content of the asphalt mixture, the target void fraction and the air volume fraction of the asphalt mixture, wherein the proportion of the coarse aggregates to the fine aggregates is the mass ratio of the coarse aggregates to the fine aggregates;
The mixing response data is a viscosity change curve in the mixing process, the compaction response data is process data of the compactness along with the change of compaction angle or compaction times in the compaction process, and the volume change data is a volume change curve of the asphalt mixture in the natural cooling process.
Further, the structural feature set constructed by the feature construction module includes:
The relative deviation value between the coarse and fine aggregate proportion and the standard grading curve, the fitting residual value between the mineral powder blending amount and the target void ratio, and the wrapping factor between the specific surface area of unit aggregate and the asphalt blending amount; a coupling offset between the target void fraction and a stable compaction value of the compaction prediction model;
the response evolution factor set constructed by the feature construction module comprises:
a compaction stage, in which the average compaction rate in the interval 25% before the total compaction time and the standard deviation of the compaction rate in the interval 25% after the total compaction time are increased, a cooling stage, in which the maximum change rate of the shrinkage rate in the volume change curve and the maximum change rate continuously exceed the duration of twice the average change rate in the volume change curve from the unloading time to the temperature falling to the room temperature;
the specific surface area of the aggregate unit is the total specific surface area corresponding to the aggregate unit mass or unit volume under the current proportioning structure.
Further, the contrast analysis module specifically includes:
Respectively calculating vectorization similarity based on the structural feature set and the response evolution factor set, and calculating the difference degree between the current mixture sample to be tested and the historical sample in the database through Euclidean distance, cosine included angle or Markov distance;
Generating a proportioning response deviation vector according to the similarity, and obtaining the proportioning response deviation degree by normalizing and weighting all index values in the deviation vector;
And matching the proportioning response deviation degree with a set grading standard threshold value, respectively endowing the proportioning response deviation degree with a first grade or a second grade, and classifying the proportioning response deviation degree into the second grade when the proportioning response deviation degree exceeds the upper limit of the second grade.
Further, when the judgment regulation module receives the second level, the judgment regulation module executes the following operations:
Acquiring the numerical variation direction of the coarse and fine aggregate proportion, the mineral powder doping amount and the asphalt doping amount in the structural feature set in the current mixture sample to be tested;
Simultaneously extracting a response evolution factor set, wherein the time period from the mixing starting moment to the time when the viscosity reaches the maximum value, a first-order slope value obtained by fitting the viscosity change curve, the average compactness increasing rate, the compactness change standard deviation and the change direction of the maximum change rate and the duration time of the shrinkage rate are taken;
If the change direction of the coarse and fine aggregate proportion, the mineral powder doping amount and the asphalt doping amount in the structural feature set is consistent with the change direction of any index in the response evolution factor set, judging that the structural adjustment is consistent with the performance response, and finely adjusting the asphalt doping amount at the moment;
if the change direction of any parameter in the structural feature set is opposite to the direction of two or more indexes in the response evolution factor set, judging that the parameters are in proportion disturbance mismatch, re-evaluating the proportion of coarse and fine aggregates and the mixing amount of mineral powder, and temporarily adjusting the mixing amount of asphalt;
And if the maximum change rate of the shrinkage rate and the duration time index of the shrinkage rate exceed the average level of the historical samples by more than two times, outputting a volume stability abnormality prompt, and adjusting the target void ratio or optimizing the cooling process configuration.
Further, the path deduction module performs the following operations based on a matching result of the structural feature set and the response evolution factor set in the database:
selecting the first five groups of history samples with the smallest Euclidean distance with the structural feature set of the current mixture sample to be detected as adjacent mixture samples;
Extracting corresponding response evolution factor sets in the adjacent mixture samples, wherein the response evolution factor sets comprise a first-order slope value of a viscosity change curve, an average compactness increasing rate, a compactness change standard deviation, and a maximum change rate and duration of a shrinkage rate;
according to the numerical variation direction of the response evolution factor set and the corresponding proportioning parameter adjustment record, constructing a response path track;
based on the change trend of the response evolution factor set of the mixture sample to be tested under different proportioning parameter adjustment conditions, a structural response prediction sequence is formed, and a prediction result is output to the judging and regulating module.
Further, the path deduction module further comprises a structural risk analysis unit configured to:
calculating an adjustable parameter interval of the mixture sample to be measured 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 sample;
calculating the structural deviation trend risk level according to whether the maximum change rate and duration of the shrinkage rate are higher than 95% confidence intervals corresponding to samples in a database;
when the maximum change rate and the duration time of the shrinkage rate are both in an abnormal interval, a high risk level is output, if only one index is higher, a medium risk level is output, and when both are in a normal interval, a low risk level is output.
Further, a complementary mechanism is performed when the number of adjacent mix samples in the database that satisfies the following condition is less than three groups:
The Euclidean distance between the structural feature set and the current mixture sample to be tested is smaller than or equal to a set threshold value, and the response evolution factor set comprises a first-order slope value of a viscosity change curve and an average compactness increasing rate within a set floating range;
The supplementing mechanism comprises the steps of collecting three groups of mixture samples, and collecting corresponding mixing response data, compaction response data and volume change data;
and constructing a structural feature set and a response evolution factor set by a feature construction module, and incorporating the structural feature set and the response evolution factor set into a database module.
Compared with the prior art, the invention has the beneficial effects that:
By constructing structural characteristic parameters such as relative deviation of coarse aggregate proportion, package factors, coupling offset and the like and combining dynamic response evolution factors such as viscosity curve slope, compactness growth rate, volume shrinkage rate and the like, an intermediate characterization mechanism between structures and performances is established, and the discrimination capability of complex proportioning structural states is improved.
Introducing a proportion response deviation degree and grading mechanism to enhance pertinence and grading of regulation and control judgment
The system generates normalized proportioning response deviation degree by vectorizing comparison and calculating the similarity between the structural feature set and the response evolution factor, and divides the first grade and the second grade accordingly, thereby providing clear classification basis for subsequent strategy decision and avoiding blind adjustment or light rate correction. And constructing a cooperative judgment path of the structure and the response change direction, improving the rationality and the refinement level of the generation of the optimization strategy, and judging whether the structure adjustment leads to performance improvement by analyzing whether the change direction of the coarse and fine aggregate proportion, the mineral powder doping amount and the asphalt doping amount is matched with the change trend of each response evolution factor or not in a second level state. If the directions are consistent, the method is definitely collaborative optimization, the asphalt mixing amount is preferentially and finely adjusted, and if the directions are opposite, the method is identified as disturbance mismatch, error optimization is prevented, and the pertinence of proportioning adjustment is improved. And a path deduction module and a structural risk analysis mechanism are introduced to realize predictive regulation and control and safety boundary prompt. The system constructs a response path track based on historical adjacent samples, outputs a structural response prediction sequence, enables proportioning adjustment to have trend foresight without depending on single-point response, calculates structural deviation risk level through the position of the maximum shrinkage rate and the duration time relative to a 95% confidence interval in a database, and provides quantifiable support for cooling stability assessment. When the number of the adjacent samples is insufficient, the system can automatically trigger a rapid sampling mechanism to collect boundary samples, construct a structural feature set and a response evolution factor thereof, supplement the boundary samples into a database, effectively solve the problem of reasoning faults caused by sample sparseness, and keep the stability and the effectiveness of regulation strategy generation. The system can be widely applied to links such as proportioning preliminary setting optimization, on-site trial mixing parameter adjustment, quality abnormality diagnosis, construction rhythm regulation and control and the like in road engineering, can dynamically sense material behaviors and provide reasonable strategies, and remarkably improves the consistency and the intelligent level of the whole process of engineering material design, production and construction.
On the other hand, the proportioning optimization method for the asphalt mixture provided by the invention comprises the following steps:
s1, mixing response data, compaction response data and volume change data in a cooling process of a plurality of asphalt mixture samples with different proportioning parameters in historical data are obtained;
S2, constructing a structural feature set according to the proportioning parameters, and constructing a response evolution factor set according to the mixing response data, the compaction response data and the volume change data;
s3, acquiring a structural feature set and a response evolution factor of a current mixture sample to be tested, comparing the structural feature set with the response evolution factor set, calculating a proportioning response deviation degree, and matching the proportioning response deviation degree with a set grading standard to determine grades, wherein the grades comprise a first grade and a second grade with proportioning response deviation degrees increased in sequence;
S4, when the grade is the second grade, analyzing the matching relation between the structural feature set change direction and the response evolution factor change direction of the mixture sample to be tested;
And S5, establishing a database comprising a structural feature set of calibrated proportioning samples, response evolution factors and grades.
It should be noted that the ratio optimization method for asphalt mixture of the present invention has the same beneficial effects as the system thereof, and will not be described in detail herein.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
fig.1 is a functional block diagram of a ratio optimizing system for asphalt mixtures according to an embodiment of the present invention.
Fig. 2 is a flowchart of a method for optimizing the mixture ratio of an asphalt mixture according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
Referring to fig. 1, an embodiment of the present invention provides a ratio optimizing system for asphalt mixture, including:
the collection module is configured to obtain mixing response data, compaction response data and volume change data in the cooling process of a plurality of asphalt mixture samples with different proportioning parameters in the historical data.
The characteristic construction module is configured to construct a structural characteristic set according to the proportioning parameters and construct a response evolution factor set according to the mixing response data, the compaction response data and the volume change data.
The comparison analysis module is configured to acquire a structural feature set and a response evolution factor of a current mixture sample to be tested, compare the structural feature set and the response evolution factor set of a historical sample, calculate a proportion response deviation degree, match the proportion response deviation degree with a set grading standard and determine grades, wherein the grades comprise a first grade and a second grade with the proportion response deviation degree increased in sequence.
The judging and regulating module is configured to analyze the matching relation between the structural feature set change direction and the response evolution factor change direction of the mixture sample to be tested when the grade is the second grade, and output a proportion optimizing strategy according to the relation between the structural feature set change direction and the response evolution factor change direction.
And the database module is configured to establish a database comprising the structural feature set of the calibrated proportioning sample, the response evolution factors and the grades.
The quantitative evaluation and grading of the proportioning performance of the asphalt mixture are realized by collecting the whole process response data of the mixing, compacting and cooling stages and constructing a multidimensional parameter set of structural features and response evolution factors, and when the second grade with larger deviation is identified, an optimization strategy is deduced by further combining the relation between the structure and the response change direction, so that the pertinence and scientificity of regulation are improved. The system has the functions of intelligent comparison, trend discrimination and strategy output, can obviously improve the efficiency and quality of proportioning adjustment, and enhances the stability and adaptability of asphalt mixture design.
In some embodiments of the application, the system further comprises a path deduction module, wherein the path deduction module is configured to compare the to-be-measured mixture sample with the database according to the structural feature set and the response evolution factor, obtain the adjacent mixture sample, and output an adjustable parameter interval and a structural deviation trend risk of the to-be-measured mixture sample based on the historical response evolution factor change direction and the label grade of the adjacent mixture sample.
Before the judging and controlling module is started, a path deduction module is called in advance.
The method comprises the steps of 1. In a sample matching stage, the path deduction module firstly receives a structural feature set and a response evolution factor set of a current mixture sample to be tested, and then invokes a database module to screen a plurality of groups of adjacent samples with the minimum Euclidean distance between the structural feature set and the structural feature set of the current sample from a historical sample, and the adjacent samples are used as matching sample sets.
2. The response path extraction stage comprises the steps of extracting a corresponding response evolution factor set of each sample in a matched sample set, dividing the samples according to three stages of mixing, compacting and cooling, analyzing the change direction (such as first-order slope increase and decrease, compactness speed increase and improvement or stability fluctuation expansion and the like) of the response evolution factors in each stage and the corresponding structural feature change history, and associating the change direction of the response evolution factors with a label grade (a first grade or a second grade) to form a structure-response-grade evolution path sample group.
3. And a structural response trend deduction stage, namely substituting the structural feature set of the current mixture sample to be tested into the structural-response path group respectively to simulate the response trend change of the current mixture sample under the existing historical evolution path, judging that the structural deviation trend risk exists if the response evolution factor trend in the simulation result is similar to the corresponding second-level sample path in the history, and recording the risk level.
4. The calculation stage of adjustable parameter interval includes analyzing the regulating direction and amplitude of structural parameters in the path, including coarse and fine aggregate proportion, mineral powder mixing amount and asphalt mixing amount, in the process of optimizing from the second level to the first level; and calculating the maximum and minimum boundaries of the current structural parameters for realizing performance improvement in different paths to form an adjustable parameter interval of the current mixture sample to be tested.
5. And before the judging and regulating module is formally started, the path deduction module is automatically and pre-called by a system control flow to finish the calculation, so that the regulation strategy is ensured to generate a trend pre-judging basis.
In some embodiments of the application, the proportioning parameters comprise coarse and fine aggregate proportion, mineral powder blending amount, asphalt mixture filler content, asphalt blending amount, asphalt mixture asphalt content, target void ratio, air volume fraction of the asphalt mixture, mixing response data, compaction response data and volume change data, wherein the coarse and fine aggregate proportion is the mass ratio of coarse aggregate to fine aggregate, the mineral powder blending amount is the asphalt mixture filler content, the asphalt mixture asphalt content is the target void ratio is the air volume fraction of the asphalt mixture, the mixing response data is a viscosity change curve in the mixing process, the compaction response data is process data of compaction degree changing along with compaction angle or compaction times in the compacting process, and the volume change data is a volume change curve of the asphalt mixture in the natural cooling process.
The coarse-fine aggregate ratio refers to the mass ratio or volume ratio between coarse aggregate (such as broken stone) and fine aggregate (such as sand) for controlling the grading curve of the mixture. The mineral powder mixing amount refers to the proportion of filler (such as limestone powder) added into unit mixture, and has obvious influence on filling property and cohesiveness. The amount of asphalt, i.e., the mass fraction of asphalt in the unit mix, is a key parameter in controlling the binding properties, durability and rut resistance. The target void fraction, i.e., the air volume fraction desired to be retained in the total volume within the molding compound under design requirements, has a determining effect on solidity, durability, and the like.
In some embodiments of the application, the structural feature set constructed by the feature construction module comprises a relative deviation value between a coarse aggregate proportion and a standard grading curve, a fitting residual value between a mineral powder doping amount and a target void ratio, and a wrapping factor between a unit aggregate specific surface area and an asphalt doping amount, a coupling offset between the target void ratio and a stable compaction value of a compaction prediction model, and a response evolution factor set constructed by the feature construction module comprises a time period from a mixing starting moment to a viscosity reaching a maximum value in a mixing stage, and a first-order slope value obtained by fitting a viscosity change curve in the time period through a least square method, wherein in a compaction stage, an average compactness increasing rate in a section 25% before the total compaction time and a compactness change standard deviation in a section 25% after the total compaction time, and a duration that the maximum change rate of a shrinkage rate in a volume change curve continuously exceeds twice the average change rate in the volume change curve from the unloading moment to the temperature falling to the room temperature in a cooling stage, and the unit aggregate specific surface area is the corresponding unit mass of the unit aggregate or the total specific surface area of the unit aggregate under the current structure.
The construction step of the structural feature set comprises the step of obtaining proportioning parameters of a current mixture sample, wherein the proportioning parameters comprise coarse and fine aggregate proportion, mineral powder blending amount, asphalt blending amount and target void ratio. And calculating the relative deviation value between the coarse and fine aggregate proportion and the standard grading curve.
And calculating the difference value of each particle size point, normalizing, taking absolute value average, and outputting as a relative deviation value.
Calculating a fitting residual value between the mineral powder doping amount and the target void ratio, predicting by using a statistical regression model of the existing mineral powder doping amount and the target void ratio, comparing the actually measured void ratio with a model predicted value, and taking the residual value as a characteristic to output.
The method comprises the steps of calculating a wrapping factor between specific surface area of unit aggregate and asphalt mixing amount, obtaining particle size composition and density of all aggregates in the current proportion, estimating specific surface area of unit mass or volume according to particle size and shape of the aggregates, modeling the specific surface area and asphalt mixing amount in a ratio relation manner, and outputting the wrapping factor representing asphalt wrapping capability.
The coupling offset between the target porosity and the stable compaction value of the compaction prediction model is calculated by calling the compaction prediction model established in the database, inputting the current structural parameters, predicting the compaction final value of the compaction prediction model, and outputting the difference between the predicted compaction and the target porosity as the coupling offset.
The mixing stage index extraction comprises the steps of extracting a time period from the mixing starting moment to the time period when the viscosity reaches the maximum value, positioning the starting point and the peak value of a viscosity curve from the collected mixing response data, and calculating the time interval between the starting point and the peak value as a viscosity rising time period to be output.
Fitting a viscosity change curve, extracting a first-order slope value, namely performing least square linear fitting on the viscosity data in the time period, and taking a first derivative value of the linear function, namely the viscosity increase first-order slope value.
The compaction stage index extraction comprises the steps of calculating the average compaction degree increase rate in the interval of 25% of the compaction times before compaction, extracting the total compaction times from compaction response data, intercepting the compaction process data of 25% before compaction, calculating the ratio of the compaction degree increase to the compaction times, and outputting the average increase rate.
And calculating the standard deviation of the compactness change of the interval of 25 percent after the calculation, namely extracting data of the compaction stage of 25 percent after the calculation, and calculating the standard deviation of the compactness change of the interval for reflecting the later compaction fluctuation.
And the index extraction in the cooling stage comprises the steps of calculating the maximum change rate of the shrinkage rate in the volume change curve, performing derivative processing on the volume change curve to obtain the volume change rate in unit time, and obtaining the maximum change rate, namely a maximum negative slope point, from the derivative curve.
And identifying the time length of which the derivative value is more than twice the average value in the continuous time interval, and outputting the duration.
The specific surface area of the unit aggregate is obtained by setting a shape coefficient and a surface area estimation coefficient (determined by experience or pre-experiment) of the aggregate with each particle size, obtaining the total specific surface area of the current sample according to weighted average of mass or volume proportion, and outputting the specific surface area of the unit aggregate as one of structural characteristic indexes according to unit mass (g/m 2) or volume (cm 2/cm 3).
Firstly, collecting proportioning parameters of historical asphalt mixture samples and corresponding compaction response data, wherein the proportioning parameters comprise coarse and fine aggregate proportion, mineral powder doping amount, asphalt doping amount and target void ratio, and the compaction response data comprise a complete curve of compactness changing along with compaction times. And secondly, extracting a compactness mean value of a final-stage steady-state zone of each group of samples based on a compaction curve of each group of samples, taking the compactness mean value as a stable compaction value label, taking a relative deviation value between a proportion parameter and a coarse and fine aggregate proportion in a structural feature set and a standard grading curve, a fitting residual value between a mineral powder mixing amount and a target void ratio, a wrapping factor between a specific surface area of a unit aggregate and a asphalt mixing amount and the like as input variables, and constructing an input-output mapping relation. And then training by adopting a nonlinear regression model or a regression model based on a gradient lifting algorithm, optimizing the model performance by using a minimum mean square error or an average absolute error, and selecting proper model structures and parameters by using cross verification. After model training is completed, comparing the predicted stable compact value with the theoretical compact value obtained by converting the sample target void ratio, and calculating the offset of the theoretical compact value, wherein the offset is used as a coupling offset index in a structural feature set and used for subsequent matching coordination judgment and path deduction. The model can be continuously trained along with updating of the database so as to improve the prediction precision of compaction trend under different proportioning structures.
In some embodiments of the application, the comparison analysis module specifically comprises the steps of calculating vectorization similarity based on a structural feature set and a response evolution factor set respectively, calculating the difference degree between a current mixture sample to be tested and a historical sample in a database through Euclidean distance, cosine included angle or Mahalanobis distance, generating a proportioning response deviation vector according to the similarity, obtaining proportioning response deviation degree through normalization weighting of all index values in the deviation vector, matching the proportioning response deviation degree with a set grading standard threshold, respectively assigning the proportioning response deviation degree to a first grade or a second grade, and classifying the proportioning response deviation degree to the second grade when the proportioning response deviation degree exceeds the upper limit of the second grade.
In this embodiment, the specific implementation steps of the comparison analysis module include firstly, obtaining a structural feature set and a response evolution factor set of a current mixture sample to be tested. The structural feature set comprises a relative deviation value between the coarse and fine aggregate proportion and a standard grading curve, a fitting residual value between the mineral powder mixing amount and a target void fraction, a wrapping factor between the specific surface area of unit aggregate and the asphalt mixing amount, and a coupling offset between the target void fraction and a stable compaction value of a compaction prediction model, and the response evolution factor set comprises a viscosity increase time period and a first-order slope value of a mixing stage, an average compaction rate increase and a compaction rate change standard deviation of a compaction stage, and a shrinkage rate maximum change rate and a duration of a cooling stage.
And then, carrying out numerical normalization processing on the structural feature set and the response evolution factor set, and converting the structural feature set and the response evolution factor set into a vector form with uniform dimension. And then, selecting all calibrated historical samples in the database, extracting a corresponding structural feature set and a response evolution factor set, and normalizing the corresponding structural feature set and the response evolution factor set into vectors.
After vector data preparation is completed, similarity between the current sample to be detected and each historical sample in the structural feature dimension and the response factor dimension is calculated in a Euclidean distance mode, a cosine included angle mode or a Markov distance mode. And combining the similarity indexes of all the dimensions into a proportioning response deviation vector.
And then, carrying out normalized weighted calculation on each index in the deviation vector to obtain the comprehensive proportioning response deviation degree value. The larger this value is indicative of the more significant the overall deviation in structure and response of the current recipe from the historical database sample.
And finally, comparing the calculated proportioning response deviation degree with a grading standard set by a system, namely, giving a first grade label if the proportioning response deviation degree is within a first grade threshold range, and giving a second grade label uniformly if the proportioning response deviation degree is within a second grade threshold range or exceeds an upper limit threshold, wherein the system simultaneously sends out a structure adjustment strategy for assisting a judgment and regulation module in carrying out subsequent analysis. The process can combine with a dynamic threshold updating mechanism, and automatically adjust the grade judgment standard according to continuous expansion of database samples so as to improve classification accuracy.
In some embodiments of the application, when the second level is received, the judging and regulating module performs the following operations of obtaining the numerical variation direction of the coarse and fine aggregate proportion, the mineral powder doping amount and the asphalt doping amount in the structural feature set in the current mixture sample to be tested, simultaneously extracting the first-order slope value, the average compactness increasing rate, the compactness standard deviation and the maximum variation rate of the shrinkage rate obtained by fitting the viscosity variation curve in the response evolution factor set from the time period from the mixing starting moment to the time when the viscosity reaches the maximum value, judging that the structural feature set is in accordance with the structural adjustment and performance response when the structural feature set is in opposite to the asphalt doping amount, judging that the mixing ratio is mismatched when the structural feature set is in opposite to the response evolution factor set, re-evaluating the coarse and fine aggregate proportion and the mineral powder doping amount, temporarily slowing down the asphalt doping amount, and prompting that the maximum variation rate of the shrinkage rate is more than twice as the volume of the structural feature set and the cooling time exceeds the target configuration by more than the average cooling time, and optimizing the cooling time.
The method comprises the steps of firstly, extracting proportioning parameters, namely coarse and fine aggregate proportion, mineral powder mixing amount and asphalt mixing amount, from a current mixture sample to be tested, comparing the proportioning parameters, the coarse and fine aggregate proportion, the mineral powder mixing amount and the asphalt mixing amount with a mean value of a structural feature set in a historical sample or a reference sample, and judging the fluctuation direction (increasing, decreasing or basically unchanged) of each structural parameter in the current sample.
And respectively extracting from the response evolution factor set of the sample, wherein in the mixing stage, the time period from the mixing start to the viscosity reaching the maximum value, the first-order slope value obtained by fitting the viscosity change curve in the time period through a least square method, the average compactness increasing rate in the compacting stage and the compactness change standard deviation in the later stage of the compacting stage.
The maximum rate of change of the shrinkage rate of the volume change curve in the cooling phase is continued with the rate of change for a duration that is higher than twice the average rate of change.
These indices are compared with the history data, and the change trend (rising, falling or stabilizing) of the values is determined.
If any one of the coarse-fine aggregate proportion, the mineral powder blending amount and the asphalt blending amount has the same change direction as the change direction of any response evolution factor (such as the increase of the aggregate proportion and the increase of the viscosity increase slope), the inferred structure adjustment is reflected in the performance response in a synergistic enhancement relationship, and at this time, the fine adjustment operation (such as fine adjustment within +/-0.1%) of the asphalt blending amount is executed.
If any one of the three structural parameters has a change direction opposite to the change direction of two or more response evolution factors (such as that the mineral powder doping amount is increased, the average compactness growth rate is reduced and the compactness fluctuation is increased), the current proportioning structure is judged to cause performance mismatch, and the disturbance mismatch type abnormality is judged. At this time, the asphalt blending amount adjustment was suspended, and the coarse and fine aggregate proportion and the mineral powder blending amount were re-evaluated.
When the maximum change rate of the shrinkage rate and the abnormal duration time in the cooling stage are both more than twice of the historical average value of the database (based on statistical indexes), the system judges that the volume stability problem exists, and at the moment, the system outputs a volume stability abnormal prompt, and recommends a user to correct the target void ratio or adjusts the process parameters (such as prolonging the natural cooling time, optimizing the unloading time point and the like) of the cooling stage so as to reduce the later volume strain.
In some embodiments of the application, the path deduction module is used for selecting the first five groups of history samples with the smallest Euclidean distance with the structural feature set of the current mixture sample to be tested as adjacent mixture samples based on the matching result of the structural feature set and the response evolution factor set in the database, extracting the corresponding response evolution factor set in the adjacent mixture samples, including a first-order slope value of a viscosity change curve, an average compactness increasing rate, a standard deviation of compactness change, a maximum change rate and duration of a shrinkage rate, adjusting records according to the numerical variation direction of the response evolution factor set and the corresponding proportioning parameters, constructing a response path track, forming a structural response prediction sequence based on the change trend of the response evolution factor set of the mixture sample to be tested under different proportioning parameter adjustment conditions, and outputting the prediction result to the judgment and regulation module.
Firstly, the system carries out vectorization processing on the structural feature set of the current mixture sample to be tested, and calculates Euclidean distances between the structural feature set and all calibrated historical sample structural feature sets in the database. The system automatically screens out the first five groups of history samples with the smallest Euclidean distance as the adjacent mixture samples, and ensures that the structural similarity is higher than a set matching threshold so as to enhance the reliability of response trend deduction.
And then, extracting a response evolution factor set corresponding to the adjacent mixture sample, wherein the response evolution factor set comprises key parameters such as a first-order slope value of a viscosity change curve, an average compactness increasing rate and a compactness change standard deviation in a compacting process, a maximum change rate of a shrinkage rate in a cooling stage, a duration time of the change rate and the like.
Then, the system combines the historical adjustment records of each proportioning parameter in the adjacent samples, analyzes the numerical variation direction of the response evolution factors, constructs a plurality of groups of response path tracks, and forms a mapping relation map of proportioning disturbance-performance response as a follow-up prediction basis.
And finally, carrying out path extrapolation simulation on the current mixture sample to be tested in a set adjustable proportioning parameter range by the system, calculating the trend change condition of a response evolution factor set, generating a structural response prediction sequence, and submitting the prediction sequence and a response trend stability index to a judgment and regulation module for reference and adjustment decision basis of a follow-up proportioning optimization strategy.
In some embodiments of the present application, the path deduction module further includes a structural risk analysis unit configured to calculate an adjustable parameter interval of the mixture sample to be tested under the current structural condition according to a combined change history of the structural feature set and the response evolution factor set in the adjacent mixture sample, calculate a structural deviation trend risk level according to whether a maximum change rate and a duration of the shrinkage rate are higher than 95% confidence intervals corresponding to the samples in the database, output a high risk level when the maximum change rate and the duration of the shrinkage rate are both in an abnormal interval, output a medium risk level if only one index is higher, and output a low risk level when both are in a normal interval.
Specifically, first, a plurality of adjacent samples (such as the first several groups with the smallest euclidean distance) with higher similarity to the structural feature set of the current mixture sample to be tested are screened from the database.
And respectively extracting relevant data in the corresponding structure feature set and the response evolution factor set from the adjacent samples to construct a structure-response combined change history track.
Analyzing the history adjustment records of the adjacent samples on each structural characteristic parameter (such as coarse and fine aggregate proportion, mineral powder doping amount and asphalt doping amount) and the improvement trend of the corresponding response evolution factors, and identifying which parameter adjustment results in performance improvement (such as reduced compactness fluctuation and reduced shrinkage).
And synthesizing the successfully adjusted parameter value ranges to form an adjustable parameter interval of the mixture to be tested under the current structural condition. For example, if adjusting the asphalt mix from 5.3% to 5.0% in a historically adjacent sample has significantly reduced the shrinkage rate, the system may set the asphalt adjustment range from 5.0 to 5.2% as recommended for the current sample.
And (3) carrying out statistical analysis on the risk indexes, namely extracting the maximum change rate of the shrinkage rate from the volume change data of the cooling stage of the current mixture sample, wherein the maximum change rate continuously exceeds the duration of twice the average change rate. Correspondingly, the distribution of the two indexes is counted from all calibrated samples in the database, and 95% confidence intervals are respectively calculated (for example, the upper limit of the maximum change rate is 0.012mm/min and the upper limit of the duration is 180 s).
If the maximum change rate and the duration of the contraction rate of the current sample are both higher than the upper limit of the 95% confidence interval, namely, fall into an abnormal interval, the current sample is judged to be in a high risk level, if only one index is exceeded and the other index is still in a normal interval, the current sample is judged to be in a medium risk level, and if both indexes are not exceeded, the current sample is judged to be in a low risk level.
The system automatically outputs the risk level of the structure deviation trend according to the analysis result, and can combine the adjustable parameter interval to generate a strategy for judging the regulation module, so as to prompt whether the structure regulation operation is allowed to be executed or whether the cooling process needs to be controlled preferentially.
In some embodiments of the application, when the number of adjacent mixture samples in the database is smaller than three, a complementary mechanism is executed, wherein the Euclidean distance between the structural feature set and the current mixture sample to be tested is smaller than or equal to a set threshold value, the response evolution factor set comprises a first-order slope value of a viscosity change curve and an average compactness growth rate within a set floating range, the complementary mechanism comprises three groups of mixture samples, corresponding mixing response data, compaction response data and volume change data are collected, and the structural feature set and the response evolution factor set are constructed by a feature construction module and are incorporated into the database module.
The method comprises the steps of firstly, comparing and searching the current mixture sample to be tested by the system in the dimension of a structural feature set, calculating Euclidean distances between all historical samples and the current sample, screening out samples with the distances smaller than or equal to a set threshold value, and further screening out samples with the first-order slope value and the average compactness growth rate of a viscosity change curve in the samples in a set floating range in the dimension of a response evolution factor set.
If the number of samples finally meeting the dual condition is less than three groups, entering a supplementary mechanism flow.
The system preferentially covers the parameter combination with the largest numerical variation or highest uncertainty in the current structural feature set according to the boundary condition of the current proportioning parameter and the abnormal expression of the response evolution factor of the current proportioning parameter. For example, if the proportion of coarse aggregate and fine aggregate deviates from a standard grading curve by a large amount, a group of samples for readjusting the proportion of coarse aggregate and fine aggregate are collected preferentially, if the fitting residual error of the mineral powder doping amount and the target void ratio is high, a group of mineral powder doping amount adjusting samples are supplemented, and if the asphalt doping amount corresponding to the wrapping factor is remarkably abnormal, a group of samples with optimized asphalt doping amount are supplemented.
And acquiring response data in real time, namely carrying out operation of a standardized process flow on the designed three groups of supplementary structure samples, and respectively recording viscosity change curve data in the mixing process, compactness change data in the compacting process and volume change curve in the natural cooling process.
All data collection needs to synchronize time stamps and process control parameters, so that data consistency and comparability are ensured.
And (3) feature and factor construction, namely, a system calls a feature construction module to analyze the original data of the three groups of supplementary samples, and a structural feature set and a response evolution factor set are generated. The calculation content comprises coarse and fine aggregate proportion deviation, mineral powder void ratio residual error, wrapping factors and coupling offset, and viscosity curve first-order slope value, compactness increasing rate, compactness standard deviation, shrinkage rate change rate and duration.
And (3) supplementing the constructed structural feature set and the response evolution factor set into a database module, updating the database index, and automatically rerun the path deduction module to carry out structural response matching and optimizing strategy output so as to ensure the sustainable operation and strategy generation accuracy of the follow-up regulation and control module.
Referring to fig. 2, the embodiment of the invention provides a method for optimizing the proportion of an asphalt mixture, which comprises the following steps:
S1, mixing response data, compaction response data and volume change data in the cooling process of a plurality of asphalt mixture samples with different proportioning parameters in historical data are obtained.
S2, constructing a structural feature set according to the proportioning parameters, and constructing a response evolution factor set according to the mixing response data, the compaction response data and the volume change data.
And S3, acquiring a structural feature set and a response evolution factor of a current mixture sample to be tested, comparing the structural feature set and the response evolution factor set of a historical sample, calculating a proportioning response deviation degree, matching the proportioning response deviation degree with a set grading standard, and determining grades, wherein the grades comprise a first grade and a second grade with sequentially increased proportioning response deviation degree.
And S4, when the grade is the second grade, analyzing the matching relation between the structural feature set change direction and the response evolution factor change direction of the mixture sample to be tested, and outputting a proportion optimization strategy according to the relation between the structural feature set change direction and the response evolution factor change direction.
And S5, establishing a database comprising a structural feature set of calibrated proportioning samples, response evolution factors and grades.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the specific embodiments of the present invention without departing from the spirit and scope of the present invention, and any modifications and equivalents are intended to be included in the scope of the claims of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510898952.8A CN120409167B (en) | 2025-07-01 | 2025-07-01 | A method and system for optimizing the ratio of asphalt mixture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510898952.8A CN120409167B (en) | 2025-07-01 | 2025-07-01 | A method and system for optimizing the ratio of asphalt mixture |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120409167A true CN120409167A (en) | 2025-08-01 |
| CN120409167B CN120409167B (en) | 2025-10-17 |
Family
ID=96522964
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510898952.8A Active CN120409167B (en) | 2025-07-01 | 2025-07-01 | A method and system for optimizing the ratio of asphalt mixture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120409167B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4383864A (en) * | 1980-02-21 | 1983-05-17 | Riguez Associates | Adaptive mix proportioning method for use in asphaltic concrete mixing plants |
| EP2071329A2 (en) * | 2007-12-13 | 2009-06-17 | ENI S.p.A. | Method for predecting a parameter of a bitumen and relative prevision system |
| CN103553438A (en) * | 2013-10-09 | 2014-02-05 | 哈尔滨工业大学 | Control method for quality of asphalt mixture |
| CN108279578A (en) * | 2018-01-30 | 2018-07-13 | 西南交通大学 | Hot-mix asphalt mixture gradation differentials simulation and optimization control system and method |
| CN117252107A (en) * | 2023-11-03 | 2023-12-19 | 哈尔滨工业大学 | Asphalt mixture volume index prediction and design optimization method empowered by interpretable machine learning model |
| CN118380086A (en) * | 2024-06-24 | 2024-07-23 | 苏交科集团股份有限公司 | An intelligent design method and system for asphalt mixture ratio |
| CN119356415A (en) * | 2024-10-21 | 2025-01-24 | 青铜峡铝业股份有限公司青铜峡铝业分公司 | An intelligent asphalt mix ratio optimization and dynamic adjustment method and system |
| CN119964706A (en) * | 2025-04-09 | 2025-05-09 | 深圳市龙盛工程建设有限公司 | A method for establishing an asphalt material database management system |
-
2025
- 2025-07-01 CN CN202510898952.8A patent/CN120409167B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4383864A (en) * | 1980-02-21 | 1983-05-17 | Riguez Associates | Adaptive mix proportioning method for use in asphaltic concrete mixing plants |
| EP2071329A2 (en) * | 2007-12-13 | 2009-06-17 | ENI S.p.A. | Method for predecting a parameter of a bitumen and relative prevision system |
| CN103553438A (en) * | 2013-10-09 | 2014-02-05 | 哈尔滨工业大学 | Control method for quality of asphalt mixture |
| CN108279578A (en) * | 2018-01-30 | 2018-07-13 | 西南交通大学 | Hot-mix asphalt mixture gradation differentials simulation and optimization control system and method |
| CN117252107A (en) * | 2023-11-03 | 2023-12-19 | 哈尔滨工业大学 | Asphalt mixture volume index prediction and design optimization method empowered by interpretable machine learning model |
| CN118380086A (en) * | 2024-06-24 | 2024-07-23 | 苏交科集团股份有限公司 | An intelligent design method and system for asphalt mixture ratio |
| CN119356415A (en) * | 2024-10-21 | 2025-01-24 | 青铜峡铝业股份有限公司青铜峡铝业分公司 | An intelligent asphalt mix ratio optimization and dynamic adjustment method and system |
| CN119964706A (en) * | 2025-04-09 | 2025-05-09 | 深圳市龙盛工程建设有限公司 | A method for establishing an asphalt material database management system |
Non-Patent Citations (3)
| Title |
|---|
| 何忠义 等: "含除冰剂的沥青性能研究", 华东交通大学学报, vol. 36, no. 3, 30 June 2019 (2019-06-30), pages 119 - 124 * |
| 张争奇;边秀奇;杜群乐;石鑫;: "沥青混合料压实特性影响因素研究", 武汉理工大学学报, no. 06, 30 June 2012 (2012-06-30) * |
| 申承金: "纤维增强水工沥青混凝土配合比优化及剪切性能试验研究", 中国硕士学位论文全文数据库 工程科技Ⅱ辑, no. 04, 15 April 2025 (2025-04-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120409167B (en) | 2025-10-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118380086B (en) | An intelligent design method and system for asphalt mixture ratio | |
| CN104794263A (en) | Hybrid modeling method for rotary cement kiln burning zone temperature based on LS_SVM soft measurement | |
| CN111339478B (en) | Meteorological data quality assessment method based on improved fuzzy analytic hierarchy process | |
| CN102601881A (en) | Method for monitoring on-line quality and updating prediction model of rubber hardness | |
| CN102357934A (en) | Quality monitor soft sensing method based on rubber mixing process | |
| CN112418270A (en) | A blast furnace comprehensive state prediction method and system | |
| CN119670197A (en) | A method and system for optimizing the durability of cement concrete for airport runways | |
| CN116644655A (en) | A soft sensor method for industrial process based on weighted target feature regression neural network | |
| CN120409167B (en) | A method and system for optimizing the ratio of asphalt mixture | |
| CN109342279B (en) | Hybrid Soft Sensing Method Based on Grinding Mechanism and Neural Network | |
| CN112329269A (en) | A Modeling Prediction Method of Sintering Ignition Temperature Based on Working Conditions Identification | |
| Bahia et al. | Using the Superpave gyratory compactor to estimate rutting resistance of hot-mix asphalt | |
| CN120072154B (en) | Evaluation method and system of pavement materials in construction process based on volume-mechanical index synergy | |
| CN119296702B (en) | Optimized processing method for compound combination used for modified asphalt | |
| CN117455321B (en) | Intelligent assessment method and system for performance of fluidized solidified soil | |
| CN120213611A (en) | A multi-scale evaluation method and system for mechanical strength of construction waste mixture for roads | |
| Lee | Improvement in dynamic modulus and cyclic fatigue testing of asphalt mixture | |
| CN119443327A (en) | A method for predicting and adjusting energy efficiency of heating furnace based on subjective and objective combined weighting | |
| CN117316328A (en) | A method for predicting the rheology number of asphalt mixture and its application | |
| Kandhal et al. | Field management of hot mix asphalt volumetric properties | |
| CN115545878A (en) | Machine learning-based bond risk assessment method and system | |
| CN118171543B (en) | Cement stabilized macadam basic unit compaction quality governing system based on machine learning | |
| CN120080471B (en) | An intelligent battery cover loading and unloading and vulcanization control system | |
| CN120235363B (en) | Statistical analysis method and system for civil engineering test data of hydropower engineering | |
| CN117892928B (en) | A rural highway technical condition assessment system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |