A flexible improvement method for emulsified asphalt

Abstract

The present invention provides a flexible improvement method for emulsified asphalt, which relates to the field of concrete technology, including: screening historical emulsification control records of similar asphalts of target emulsified asphalt in a flexible improvement database; extracting the first historical emulsification record in the historical emulsification control record, including the first historical emulsification control information and the first historical asphalt micronization information; reading a predetermined emulsification index, traversing the first historical emulsification control information, and obtaining the first historical emulsification control parameter; introducing a micronization evaluation function for evaluation and analysis, and obtaining the first historical micronization index; performing supervised learning to obtain a micronization prediction model; and dynamically regulating the emulsification control parameters of the target emulsified asphalt through the model. The present invention solves the technical problem that the prior art generally adopts a static control method for the emulsification stage of flexible improvement, lacks real-time dynamic regulation of the emulsification control parameters, and leads to poor production flexibility and stability.

Description

Technical Field

[0001] The invention relates to the technical field of concrete, and in particular to a method for improving the flexibility of emulsified asphalt. Background Art

[0002] Emulsified asphalt is widely used in the construction of infrastructure such as roads, bridges, and airport runways. The flexible improvement of emulsified asphalt includes the raw material preparation stage, premixing stage, emulsification stage, and maturation stage, among which the emulsification stage has an important impact on the performance, durability, and stability of the final infrastructure. In actual production, the production environment and material properties during the emulsification stage may change, which requires real-time dynamic adjustment of the emulsification control parameters to ensure the stability and consistency of the micronization effect. However, the existing technology usually adopts a static control method, which is difficult to adapt to various changes in the production process, resulting in poor production flexibility and stability. Summary of the invention

[0003] The present application provides a flexible improvement method for emulsified asphalt, aiming to solve the technical problem that the existing technology usually adopts a static control method for the emulsification stage of flexible improvement, lacks real-time dynamic regulation of emulsification control parameters, and leads to poor production flexibility and stability.

[0004] The present application discloses a flexible improvement method for emulsified asphalt, the method comprising: screening historical emulsification control records of similar asphalts of target emulsified asphalt in a flexible improvement database; extracting a first historical emulsification record from the historical emulsification control records, the first historical emulsification record comprising first historical emulsification control information and first historical asphalt micronization information; reading a predetermined emulsification index, and traversing the first historical emulsification control information based on the predetermined emulsification index to obtain a first historical emulsification control parameter; introducing a micronization evaluation function to evaluate and analyze the first historical asphalt micronization information to obtain a first historical micronization index; performing supervised learning on a first data group formed based on the first historical emulsification control parameter and the first historical micronization index to obtain a micronization prediction model; and dynamically regulating the emulsification control parameters of the target emulsified asphalt through the micronization prediction model.

[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0006] The historical emulsification control records of similar asphalts of the target emulsified asphalt are screened in the flexible improved database. By screening the historical records of similar asphalts, past data similar to the target asphalt can be obtained to provide basic data for subsequent analysis; the analysis object is selected in the historical emulsification records to obtain the first historical emulsification record and related information of the first historical emulsification record, including the first historical emulsification control information and the first historical micronization information. These information include the emulsification process control parameters and micronization conditions of the asphalt, providing specific data support for the analysis; the predetermined emulsification index is read, and the first historical emulsification control information is traversed to obtain the first historical emulsification control parameters, ensuring that the data used matches the actual situation of the target asphalt, thereby improving the prediction accuracy. The accuracy of the measurement is improved; the micronization information of historical asphalt is analyzed using the micronization evaluation function to obtain the micronization index, which provides a detailed evaluation of the emulsification process and quantifies the micronization effect; a data set is constructed based on the historical emulsification control parameters and the micronization index, and supervised learning is performed to obtain a micronization prediction model. This model is trained with historical data to learn the impact of different control parameters on the micronization effect, thereby predicting the micronization of the target asphalt; the control parameters of the target emulsified asphalt are dynamically adjusted through the micronization prediction model, so that the emulsification process of the target asphalt can be optimized in real time to achieve the expected micronization effect, thereby realizing the precise control and optimization of the emulsified asphalt production process and improving production efficiency and product quality.

[0007] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic flow chart of a flexible improvement method for emulsified asphalt is provided for an embodiment of the present application;

[0009] Figure 2 A schematic flow chart of obtaining historical emulsification control records in a flexible improvement method for emulsified asphalt is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0010] The embodiments of the present application provide a method for improving the flexibility of emulsified asphalt, thereby solving the technical problem that the prior art generally adopts a static control method for the emulsification stage of flexibility improvement and lacks real-time dynamic regulation of emulsification control parameters, resulting in poor production flexibility and stability.

[0011] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0012] like Figure 1 As shown, the embodiment of the present application provides a method for improving the flexibility of emulsified asphalt, the method comprising:

[0013] Screen the historical emulsification control records of similar asphalts to the target emulsified asphalt in the flexible improvement database.

[0014] The flexible improvement database contains detailed records of multiple stages in the improvement process, including the raw material preparation stage, premixing stage, emulsification stage, maturation stage, etc. This application is carried out for the emulsification stage. For the emulsification stage, the database stores the emulsification control records of multiple asphalt samples under different conditions.

[0015] Before screening, the key features of the target emulsified asphalt are clarified, including material preparation dimension features and premixing dimension features. These features are used as the criteria for screening historical records and are used to match historical records in the database. Based on the material preparation dimension features and premixing dimension features, the target multidimensional feature parameters of the target emulsified asphalt are extracted.

[0016] From the flexible improved database, based on the target multidimensional characteristic parameters of the target emulsified asphalt, historical emulsification records with similar characteristics are screened out. Specifically, the target multidimensional characteristic parameters of the target emulsified asphalt are compared with the characteristic parameters of each asphalt sample in the database, and the historical emulsification control records of the same type of asphalt that meet the similarity threshold are screened out as the basic data for subsequent analysis.

[0017] A first historical emulsification record in the historical emulsification control record is extracted, wherein the first historical emulsification record includes first historical emulsification control information and first historical asphalt micronization information.

[0018] An analysis object is randomly extracted from the historical emulsification control record as the first historical emulsification record. The first historical emulsification record includes the first historical emulsification control information and the first historical asphalt micronization information. The emulsification control information includes a detailed record of the control parameters in the emulsification process, such as shear rate, emulsification temperature, stirring speed, order of emulsifier addition, etc. These control information reflect the specific operation steps and parameter settings taken to achieve the target emulsification effect in the historical emulsification process; asphalt micronization information refers to the specific conditions of asphalt particle formation and distribution in the emulsification process. This information includes the average size of the particles, the uniformity of the distribution of the particles, the morphological characteristics of the particles, etc. The method for extracting the micronization information is as follows: key indicators are extracted from the particle size distribution data collected during the emulsification process, such as the average diameter of the particles, the standard deviation, the particle concentration, etc. If there is image data of the particle morphology, the morphological characteristics of the particles can be extracted by image processing technology, including shape, boundary clarity, etc. The extracted micronization data is statistically analyzed to calculate key micronization parameters, such as the average value, standard deviation, coefficient of variation, etc. of the particle size, to obtain the asphalt micronization information.

[0019] A predetermined emulsification index is read, and the first historical emulsification control information is traversed based on the predetermined emulsification index to obtain a first historical emulsification control parameter.

[0020] The predetermined emulsification index is a key parameter used to control the emulsification process during the emulsification process. It is a predefined index, including shear rate and temperature. The shear rate is the shear rate applied to the material during the emulsification process, which directly affects the dispersion of asphalt particles; the temperature is the temperature control during the emulsification process, which affects the interaction between the emulsifier and the asphalt. The predetermined emulsification index is matched with each data item in the first historical emulsification control information, and the specific control parameters corresponding to these indicators are screened, such as the shear rate and temperature at a certain time point, to obtain the first historical emulsification control parameters.

[0021] A micronization evaluation function is introduced to evaluate and analyze the first historical asphalt micronization information to obtain a first historical micronization index.

[0022] The micronization evaluation function is used to evaluate the quality of micronization during asphalt emulsification. The function measures the effect of micronization based on multiple parameters. The first historical asphalt micronization information contains detailed data about asphalt micronization in historical records, such as the size, distribution, and shape of the particles. During the evaluation and analysis process, these data are evaluated through the micronization evaluation function, and the intermediate results reflecting the micronization effect are extracted to obtain the first historical micronization index, which is used to characterize the quality of the micronization effect during the emulsification process.

[0023] A supervised learning is performed on a first data set formed based on the first historical emulsification control parameter and the first historical micronization index to obtain a micronization prediction model.

[0024] The first historical emulsification control parameter is paired with the first historical micronization index to obtain a first data set, and so on, by pairing the control parameter in each historical record with the corresponding micronization index, a multidimensional data set is formed, and this data set serves as the basis for supervised learning.

[0025] In order to perform supervised learning, the data set is divided into two parts, including a training set and a test set. The training set contains most of the historical data and is used to train the micro-granular prediction model. Through multiple iterations, the internal parameters of the model are gradually adjusted to maximize the prediction accuracy. The test set contains a small amount of data that has not participated in the training, which is used to verify the generalization ability of the model and the actual prediction effect.

[0026] Select a supervised learning algorithm, such as random forest, neural network, etc. During the training process, the algorithm learns the relationship between the historical emulsification control parameters and the historical micronization index based on the training set. As the training progresses, the model gradually learns how to extract information from the control parameters and predict the micronization effect with higher accuracy. After the model training is completed, the model is verified using the test set to evaluate its predictive effect and generalization ability. If the model does not perform well on the test set, the model's hyperparameters need to be adjusted until the preset effect is achieved. Finally, a micronization prediction model is obtained, which can predict the micronization effect of asphalt emulsification in real time based on the input emulsification control parameters.

[0027] The emulsification control parameters of the target emulsified asphalt are dynamically regulated through the micronization prediction model.

[0028] Obtain the target emulsification control parameters of the target emulsified asphalt, and input the obtained target emulsification control parameters into the micronization prediction model. The model will predict the target predicted micronization index under the target emulsification control parameters based on the trained algorithm, which is used to evaluate the micronization effect of the target asphalt under the current control parameters. Compare the target predicted micronization index with the predetermined micronization standard. If the predicted result meets the standard, it means that the current emulsification control parameters are appropriate and the production process can continue; if the predicted result does not meet the predetermined standard, the emulsification control parameters need to be adjusted to optimize the micronization effect. Specific parameter regulation includes adjusting the shear rate and adjusting the temperature to improve the micronization effect and ensure that the emulsification control parameters in the production process are always in the best state.

[0029] Furthermore, if Figure 2 As shown, including:

[0030] Based on the predetermined emulsified asphalt dimension, multi-dimensional features of the target emulsified asphalt are collected to obtain target multi-dimensional feature parameters; the first flexibility improvement record of the first asphalt in the flexibility improvement database is extracted, and the first flexibility improvement record includes a first multi-dimensional feature parameter and a first emulsification control record; it is determined whether the first similarity between the target multi-dimensional feature parameter and the first multi-dimensional feature parameter meets the predetermined similarity limit; if so, the first asphalt is recorded as the first asphalt of the same type, and the first emulsification control record of the first asphalt of the same type is added to the historical emulsification control record.

[0031] The dimensions of pre-defined emulsified asphalt include material preparation and pre-mixing. The material preparation dimension includes the raw material characteristics related to asphalt production. The main characteristics include base asphalt characteristics and emulsifier characteristics. The base asphalt characteristics include at least viscosity, softening point and asphaltene content. These characteristics determine the basic physical properties of emulsified asphalt. The emulsifier characteristics include at least type, proportion and formula. These characteristics affect the dispersion and stability of asphalt particles during the emulsification process. The pre-mixing dimension involves the pre-mixing stage in the emulsification process. The main characteristics include the mixing speed, mixing intensity and mixing time of the emulsifier.

[0032] During the production process, based on the above dimensions, multiple characteristic parameters related to the target emulsified asphalt are collected to obtain the target multi-dimensional characteristic parameters. These parameters can be obtained through sensors, laboratory analysis or operation records for accurate matching with historical records.

[0033] The flexible improvement database stores historical data of multiple asphalt improvement projects. A first asphalt is randomly selected from the flexible improvement database, and a first flexible improvement record of the first asphalt is extracted. The first flexible improvement record includes a first multidimensional characteristic parameter and a first emulsification control record.

[0034] Compare the target multidimensional feature parameters of the target emulsified asphalt with the first multidimensional feature parameters of the first asphalt, and evaluate their similarity. Specifically, encode the classification features and convert them into a form suitable for calculation. Use a distance metric method, such as Euclidean distance, Manhattan distance, etc., to calculate the distance between the two feature vectors. Calculate the similarity based on the distance metric, and the similarity can be expressed in terms of ratio, correlation coefficient, etc. Compare the calculated similarity with a predetermined similarity limit, which is a pre-set standard for determining whether two samples are sufficiently similar.

[0035] If the characteristic similarity meets the predetermined similarity limit, the first asphalt is marked as the first asphalt of the same type, and the first emulsification control record of the first asphalt of the same type is added to the historical emulsification control record, which means that these records will become reference data for the current emulsification process and can be used to adjust and optimize the production process.

[0036] Furthermore, the predetermined emulsified asphalt dimensions include material preparation dimensions and premixing dimensions, the material preparation dimensions include base asphalt characteristics and emulsifier characteristics, the premixing dimensions include emulsifier mixing speed, mixing intensity and mixing time, wherein the base asphalt characteristics include at least viscosity, softening point and asphaltene content, and the emulsifier characteristics include at least type, proportion and formula.

[0037] The predefined asphalt emulsion dimensions include material preparation dimensions and premixing dimensions, which involve different stages and characteristics in the asphalt emulsion process.

[0038] The material preparation dimension involves the raw material characteristics of emulsified asphalt, mainly including the characteristics of the base asphalt and the emulsifier. The base asphalt characteristics include at least viscosity, softening point and asphaltene content. Among them, viscosity is used to measure the fluidity and consistency of asphalt. The softening point refers to the temperature at which asphalt begins to soften during heating. This characteristic reflects the stability of asphalt at high temperatures. The asphaltene content is the content of organic matter dissolved in asphalt, which affects the hardness and adhesion of asphalt. Emulsifier characteristics include at least type, proportion and formula, which refers to the combination of the chemical composition and additives of the emulsifier, which affects the effect of the emulsification process and the quality of the final product.

[0039] The premixing dimension involves the mixing process of the emulsifier in the base asphalt, including the mixing speed, mixing intensity and mixing time of the emulsifier. Among them, the mixing speed of the emulsifier is the speed at which the emulsifier is added to the base asphalt. Too fast or too slow mixing speed may affect the emulsification effect. The mixing intensity is the force or energy applied during the mixing process, which directly affects the dispersion and uniformity of the emulsifier. The mixing time is the mixing time of the emulsifier and the base asphalt. The length of time affects the integrity and stability of the emulsification.

[0040] Further, including:

[0041] The target multidimensional feature parameter and the classified data in the first multidimensional feature parameter are encoded in turn to obtain a target encoding value and a first encoding value, respectively; the target multidimensional feature parameter and the numerical data in the first multidimensional feature parameter are subjected to variance stabilization transformation in turn to obtain a target transformation value and a first transformation value, respectively; the target encoding value and the target transformation value constitute a target parameter vector, and the first encoding value and the first transformation value constitute a first parameter vector; the target parameter vector and the first parameter vector are compared and analyzed to obtain the first similarity.

[0042] Categorized data refers to features whose values ​​are finite discrete categories, such as asphalt type, emulsifier type, etc. Encoding processing converts categorized data into digital format for similarity calculation. Common encoding methods include label encoding, one-hot encoding, etc. For example, one-hot encoding is used to create a binary feature for each category. Each category corresponds to an independent feature, with 1 at the position corresponding to the category and 0 at the other positions. For example, asphalt types A, B, and C are encoded into three binary features, each of which represents a category.

[0043] All categorized data are extracted from the target multidimensional feature parameters and the first multidimensional feature parameters in turn, and the categorized data in the target multidimensional feature parameters and the first multidimensional feature parameters are encoded using the above encoding method to generate target encoding values ​​and first encoding values, respectively, for subsequent similarity calculations.

[0044] Numerical data are features that take continuous values, such as viscosity, softening point, and emulsifier ratio. The purpose of variance stabilization transformation is to keep the variance of numerical data in a relatively stable range. Variance stabilization transformation methods include logarithmic transformation, square root transformation, Z-score standardization, etc. Exemplarily, the Z-score standardization method is used to convert the data into a standard normal distribution with a mean of 0 and a variance of 1.

[0045] All numerical data are extracted from the target multidimensional feature parameters and the first multidimensional feature parameters in turn, and the above-mentioned variance stabilization transformation method is used to perform corresponding variance stabilization transformation on the numerical data in the target multidimensional feature parameters and the first multidimensional feature parameters, and target transformation values ​​and first transformation values ​​are generated respectively for subsequent similarity calculation.

[0046] The target encoding value and the target transformation value are integrated to form a target parameter vector, and the first encoding value and the first transformation value are integrated to form a first parameter vector. A similarity measurement method is selected, such as cosine similarity, and the cosine value of the angle between the target parameter vector and the first parameter vector is calculated to represent the directional similarity of the two vectors. The first similarity is calculated to represent the similarity between the target asphalt and the first asphalt.

[0047] Furthermore, the predetermined emulsification indexes include shear rate and temperature.

[0048] The predetermined emulsification indicators include shear rate and temperature. The shear rate refers to the rate of shear force between the emulsifier and the asphalt matrix during the emulsification process, specifically the rotation speed of the stirring or mixing equipment, which affects the dispersion degree and emulsification effect of the emulsifier. The temperature refers to the temperature control during the emulsification process, which has an important influence on the rheological properties of asphalt and the activity of the emulsifier. At different temperatures, the viscosity of asphalt and the reaction characteristics of the emulsifier will change.

[0049] Further, including:

[0050] The first historical emulsification record also includes first historical emulsification environment information; the first historical asphalt micronization information and the first historical emulsification environment information are evaluated and analyzed using the micronization evaluation function to obtain the first historical micronization index, wherein the expression of the micronization evaluation function is as follows:

[0051] ;

[0052] in, Characterizing the First Historical Asphalt in the First Historical Emulsion Record The first historical micronization index, Characterizing the First Historical Asphalt The first historical emulsified air density, Characterize the first historical emulsified environmental information Environmental characteristic parameters, Characterizing the The first historical emulsification environment information includes the environmental temperature characteristic parameter, the environmental humidity characteristic parameter and the environmental pressure characteristic parameter, that is, , and respectively characterize the particle size parameter and the particle distribution uniformity parameter in the first historical asphalt micronization information, and represent the first coefficient of variation and the second coefficient of variation respectively, and .

[0053] The first historical emulsification record also includes first historical emulsification environment information, wherein the historical emulsification environment information includes an environmental temperature characteristic parameter, an environmental humidity characteristic parameter, and an environmental pressure characteristic parameter.

[0054] The first historical asphalt micronization information and the first historical emulsification environment information are evaluated and analyzed using the micronization evaluation function to obtain the first historical micronization index, wherein the expression of the micronization evaluation function is as follows:

[0055] ;

[0056] in, Characterizing the First Historical Asphalt in the First Historical Emulsion Record The first historical micronization index, which is the output value of the function, is used to describe the micronization degree of asphalt under specific emulsification conditions. Characterizing the First Historical Asphalt The first historical emulsified air density, ambient temperature, humidity, air pressure and other parameters will affect the change of air density during the emulsification process, and then affect the micronization effect of asphalt. The function captures these influences through this part. and The particle size parameter and particle distribution uniformity parameter in the first historical asphalt micronization information are respectively characterized, which are key indicators for evaluating the micronization quality. The function is This section quantifies the contribution of these features to the micronization index.

[0057] Finally, the function combines the influence of air density and particle characteristics by weight to obtain a comprehensive micronization index, thus providing a basis for subsequent emulsification control. This function provides a method for accurately evaluating the micronization quality during asphalt emulsification by combining the influence of environmental factors and micronization characteristics. This evaluation not only takes into account the changes in the external environment, but also reflects the state of the particle characteristics inside the asphalt, thus achieving a multi-dimensional and comprehensive evaluation.

[0058] Furthermore, it also includes:

[0059] Dynamically obtain the target emulsification control parameters of the target emulsified asphalt; analyze the target emulsification control parameters through the micronization prediction model to obtain a target predicted micronization index; when the target predicted micronization index does not meet the predetermined micronization constraint, dynamically adjust the target emulsification control parameters.

[0060] In the actual production process of the target emulsified asphalt, the control parameters of the emulsification process are obtained in real time through sensors, data acquisition systems, etc., to obtain the target emulsification control parameters.

[0061] The acquired target emulsification control parameters are input into the pre-trained micronization prediction model. The micronization prediction model analyzes these parameters based on the input control parameters and the learned patterns and rules to predict the micronization effect of emulsified asphalt under the current control conditions and output the target predicted micronization index, which reflects the predicted micronization degree of emulsified asphalt.

[0062] Set a predetermined micronization constraint, that is, the minimum threshold that the target predicted micronization index needs to reach. This constraint value can be determined based on production requirements, product quality standards, historical data analysis, etc. When the target predicted micronization index does not meet the predetermined micronization constraint, first analyze the specific reasons for non-compliance, such as the mismatch of shear rate, temperature and other parameters, and determine the emulsification control parameters that need to be adjusted first. For example, if the temperature has a greater impact on micronization, the temperature parameter is adjusted first. According to the analysis results, the control parameters that do not meet the requirements are adjusted immediately through the automatic control system. For example, if the shear rate is low, the shear rate can be increased by adjusting the working speed of the shearing device. The adjusted parameters are input into the micronization prediction model again, and the new target predicted micronization index is calculated in real time until the target predicted micronization index meets the predetermined micronization constraint.

[0063] Furthermore, it also includes:

[0064] Activate the conductivity probe to perform dynamic conductivity monitoring on the target emulsified asphalt to obtain a target conductivity, wherein the target conductivity includes multiple conductivity values ​​of multiple emulsification points; extract a first emulsification point from the multiple emulsification points, and match the first conductivity of the first emulsification point among the multiple conductivity values; when the first conductivity meets a predetermined label constraint, generate a target conductivity visual graph according to a first corresponding relationship between the first emulsification point and the first conductivity; and perform micronized visual analysis on the target emulsified asphalt according to the target conductivity visual graph.

[0065] The conductivity probe has high sensitivity and can capture tiny conductivity changes in real time. Multiple key points in the emulsification process are selected as multiple emulsification points. The emulsification points are distributed in different areas of the emulsification equipment to ensure comprehensive monitoring. Conductivity probes are installed at the multiple emulsification points to monitor conductivity changes during the emulsification process. The conductivity probe continuously collects conductivity data at each emulsification point. These data can reflect the dispersion state and stability of particles in the emulsified asphalt. The conductivity values ​​of all emulsification points are summarized to obtain the target conductivity. The target conductivity includes multiple conductivity values ​​of multiple emulsification points.

[0066] An analysis object is randomly selected from a plurality of emulsification points as a first emulsification point, and a conductivity value corresponding to the first emulsification point is extracted as a first conductivity.

[0067] The predetermined marker constraint is a threshold range set according to experimental data or theoretical standards, which is used to evaluate the reliability of conductivity data. For example, the conductivity value must be within a reasonable range, and the fluctuation should be within an acceptable range. The first conductivity is compared with the predetermined marker constraint. When the first conductivity meets the predetermined marker constraint, it indicates that the conductivity detection value is normal, indicating that the detection is correct and the data is accurate, which can be used for visual analysis. In this case, the first conductivity is matched with the first emulsification point, and a target conductivity visual graph is generated based on this set of data. The visual graph is generated using data visualization tools, such as a line graph or a heat map. The line graph can show the conductivity change trend during the emulsification process, while the heat map can more intuitively show the conductivity distribution of different emulsification points.

[0068] On the generated target conductivity visual graph, the conductivity changes at different emulsification points are analyzed to determine the trend and law of micronization. For example, a sudden increase or decrease in conductivity at certain points may mean aggregation or dispersion of particles. By comparing and analyzing each stage of the emulsification process, the key factors affecting the micronization effect can be found. Based on the results of micronization visual analysis, suggestions for optimizing emulsification control parameters are put forward to further improve the emulsification effect. For example, the mixing rate or shear rate of the emulsifier can be adjusted, or the emulsification temperature can be changed, etc., to guide the optimization of the subsequent emulsification process and make the production process more efficient and stable.

[0069] Further, including:

[0070] Extract a second emulsification point from the multiple emulsification points, and match a second conductivity of the second emulsification point in the multiple conductivity values, wherein a spatial distance between the second emulsification point and the first emulsification point is within a predetermined distance limit; obtain a conductivity difference between the second conductivity and the first conductivity; when the conductivity difference is within a predetermined difference limit, the first conductivity meets the predetermined tag constraint.

[0071] Among multiple emulsification points, a second emulsification point is extracted, and the spatial distance between the second emulsification point and the first emulsification point is within a predetermined distance limit. The predetermined distance limit is a threshold for determining the spatial neighborhood range between two emulsification points. It is used to ensure that the conductivity data of points at similar positions can be compared with each other and reflect the changes in the local emulsification process. That is, the second emulsification point is a neighborhood point of the first emulsification point. From the conductivity data obtained by dynamic monitoring, the conductivity value corresponding to the second emulsification point, that is, the second conductivity, is extracted.

[0072] The conductivity difference between the second conductivity and the first conductivity is calculated. The conductivity difference reflects the change in conductivity between two adjacent points. A larger difference indicates uneven emulsification or unstable micronization, while a smaller difference indicates that the emulsification process is relatively uniform.

[0073] The predetermined difference limit is a pre-set threshold value used to determine whether the first conductivity meets the standard, and can be set based on experimental data, historical records or process standards. The calculated conductivity difference is compared with the predetermined difference limit. If the conductivity difference is greater than the predetermined difference limit, it means that the conductivity difference between the two points is too large, there may be an abnormality in the emulsification process, or the first conductivity data may have errors and is not suitable for subsequent analysis; if the conductivity difference is less than or equal to the predetermined difference limit, it means that the conductivity difference between the two points is within the allowable range, indicating that the first conductivity data has a high degree of credibility and can be considered accurate. In this case, it is determined that the first conductivity meets the predetermined tag constraint.

[0074] In summary, the method for improving the flexibility of emulsified asphalt provided in the embodiments of the present application has the following technical effects:

[0075] The historical emulsification control records of similar asphalts of the target emulsified asphalt are screened in the flexible improved database. By screening the historical records of similar asphalts, past data similar to the target asphalt can be obtained to provide basic data for subsequent analysis; the analysis object is selected in the historical emulsification records to obtain the first historical emulsification record and related information of the first historical emulsification record, including the first historical emulsification control information and the first historical micronization information. These information include the emulsification process control parameters and micronization conditions of the asphalt, providing specific data support for the analysis; the predetermined emulsification index is read, and the first historical emulsification control information is traversed to obtain the first historical emulsification control parameters, ensuring that the data used matches the actual situation of the target asphalt, thereby improving the prediction accuracy. The accuracy of the measurement is improved; the micronization information of historical asphalt is analyzed using the micronization evaluation function to obtain the micronization index, which provides a detailed evaluation of the emulsification process and quantifies the micronization effect; a data set is constructed based on the historical emulsification control parameters and the micronization index, and supervised learning is performed to obtain a micronization prediction model. This model is trained with historical data to learn the impact of different control parameters on the micronization effect, thereby predicting the micronization of the target asphalt; the control parameters of the target emulsified asphalt are dynamically adjusted through the micronization prediction model, so that the emulsification process of the target asphalt can be optimized in real time to achieve the expected micronization effect, thereby realizing the precise control and optimization of the emulsified asphalt production process and improving production efficiency and product quality.

[0076] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for improving the flexibility of emulsified asphalt, characterized in that: The method comprises: Screen the historical emulsification control records of similar asphalts of the target emulsified asphalt in the flexible improvement database; Extracting a first historical emulsification record from the historical emulsification control record, wherein the first historical emulsification record includes first historical emulsification control information and first historical asphalt micronization information; Reading a predetermined emulsification index, and traversing the first historical emulsification control information based on the predetermined emulsification index to obtain a first historical emulsification control parameter; Introducing a micronization evaluation function to evaluate and analyze the first historical asphalt micronization information to obtain a first historical micronization index; Performing supervised learning on a first data set formed based on the first historical emulsification control parameter and the first historical micronization index to obtain a micronization prediction model; Dynamically regulating the emulsification control parameters of the target emulsified asphalt through the micronization prediction model; The first historical emulsification record also includes first historical emulsification environment information; The first historical asphalt micronization information and the first historical emulsification environment information are evaluated and analyzed using the micronization evaluation function to obtain the first historical micronization index, wherein the expression of the micronization evaluation function is as follows: ； in, Characterizing the First Historical Asphalt in the First Historical Emulsion Record The first historical micronization index, Characterizing the First Historical Asphalt The first historical emulsified air density, Characterize the first historical emulsified environmental information Environmental characteristic parameters, Characterizing the The coefficients of environmental characteristic parameters, and the first historical emulsification environment information includes environmental temperature characteristic parameters, environmental humidity characteristic parameters and environmental pressure characteristic parameters, that is, , and respectively characterize the particle size parameter and the particle distribution uniformity parameter in the first historical asphalt micronization information, and characterize the first coefficient of variation and the second coefficient of variation, respectively, and .

2. A method for improving the flexibility of emulsified asphalt according to claim 1, characterized in that: include: Based on the predetermined emulsified asphalt dimension, multi-dimensional feature collection is performed on the target emulsified asphalt to obtain target multi-dimensional feature parameters; Extracting a first flexibility improvement record of a first asphalt in the flexibility improvement database, wherein the first flexibility improvement record includes a first multidimensional characteristic parameter and a first emulsification control record; Determining whether a first similarity between the target multidimensional feature parameter and the first multidimensional feature parameter meets a predetermined similarity limit; If it meets the requirements, the first asphalt is recorded as the first asphalt of the same type, and the first emulsification control record of the first asphalt of the same type is added to the historical emulsification control record.

3. A method for improving the flexibility of emulsified asphalt according to claim 2, characterized in that: The predetermined emulsified asphalt dimensions include material preparation dimensions and premixing dimensions. The material preparation dimensions include base asphalt characteristics and emulsifier characteristics. The premixing dimensions include emulsifier mixing speed, mixing intensity and mixing time. The base asphalt characteristics include at least viscosity, softening point and asphaltene content, and the emulsifier characteristics include at least type, proportion and formula.

4. A method for improving the flexibility of emulsified asphalt according to claim 3, characterized in that: include: Sequentially encode the target multidimensional feature parameter and the categorized data in the first multidimensional feature parameter to obtain a target encoding value and a first encoding value, respectively; Sequentially performing variance stabilization transformation processing on the target multidimensional feature parameter and the numerical data in the first multidimensional feature parameter to obtain a target transformation value and a first transformation value respectively; The target coded value and the target transformed value constitute a target parameter vector, and the first coded value and the first transformed value constitute a first parameter vector; The target parameter vector and the first parameter vector are compared and analyzed to obtain the first similarity.

5. The method for improving the flexibility of emulsified asphalt according to claim 1, characterized in that: The predetermined emulsification parameters include shear rate and temperature.

6. The method for improving the flexibility of emulsified asphalt according to claim 1, characterized in that: Also includes: Dynamically obtaining target emulsification control parameters of the target emulsified asphalt; Analyzing the target emulsification control parameter by using the micronization prediction model to obtain a target predicted micronization index; When the target predicted micronization index does not meet the predetermined micronization constraint, the target emulsification control parameter is dynamically adjusted.

7. The method for improving the flexibility of emulsified asphalt according to claim 1, characterized in that: Also includes: Activate the conductivity probe to perform dynamic conductivity monitoring on the target emulsified asphalt to obtain a target conductivity, wherein the target conductivity includes multiple conductivity values ​​at multiple emulsification points; Extracting a first emulsification point from the plurality of emulsification points, and matching a first conductivity of the first emulsification point among the plurality of conductivity values; When the first conductivity meets the predetermined mark constraint, generating a target conductivity visual graph according to a first corresponding relationship between the first emulsification point and the first conductivity; The target emulsified asphalt is subjected to a micronization visual analysis based on the target conductivity visual graph.

8. A method for improving the flexibility of emulsified asphalt according to claim 7, characterized in that: include: Extracting a second emulsification point from the plurality of emulsification points, and matching a second conductivity of the second emulsification point among the plurality of conductivity values, wherein a spatial distance between the second emulsification point and the first emulsification point is within a predetermined distance limit; Obtaining a conductivity difference between the second conductivity and the first conductivity; When the conductivity difference is within a predetermined difference limit, then the first conductivity complies with the predetermined signature constraint.

Images