CN119361013B - Flexible improvement method of emulsified asphalt - Google Patents
Flexible improvement method of emulsified asphalt Download PDFInfo
- Publication number
- CN119361013B CN119361013B CN202411962370.3A CN202411962370A CN119361013B CN 119361013 B CN119361013 B CN 119361013B CN 202411962370 A CN202411962370 A CN 202411962370A CN 119361013 B CN119361013 B CN 119361013B
- Authority
- CN
- China
- Prior art keywords
- emulsification
- historical
- target
- asphalt
- conductivity
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Chemical & Material Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Feedback Control In General (AREA)
Abstract
The invention provides a flexible improvement method of emulsified asphalt, which relates to the technical field of concrete and comprises the steps of screening historical emulsification control records of similar asphalt of target emulsified asphalt in a flexible improvement database, extracting first historical emulsification control records in the historical emulsification control records, including first historical emulsification control information and first historical asphalt atomization information, reading preset emulsification indexes, traversing the first historical emulsification control information to obtain first historical emulsification control parameters, introducing an atomization evaluation function to evaluate and analyze to obtain first historical atomization indexes, performing supervised learning to obtain an atomization prediction model, and dynamically regulating and controlling the emulsification control parameters of the target emulsified asphalt through the model. The invention solves the technical problems of poor production flexibility and stability caused by the lack of real-time dynamic regulation and control of emulsification control parameters in the prior art that a static control method is generally adopted in the emulsification stage of the improvement of flexibility.
Description
Technical Field
The invention relates to the technical field of concrete, in particular to a flexible improvement method of emulsified asphalt.
Background
Emulsified asphalt is widely used for construction of infrastructures such as roads, bridges, airport runways and the like, and the flexible improvement of the emulsified asphalt comprises a raw material preparation stage, a premixing stage, an emulsifying stage, a curing stage and the like, wherein the emulsifying stage has important influence on the performance, durability and stability of the final infrastructures. In actual production, the production environment and material characteristics of the emulsification stage may change, which requires real-time dynamic adjustment of the emulsification control parameters to ensure stability and consistency of the micronization effect, whereas the prior art generally adopts a static control method, so that various changes in the production process are difficult to adapt, and the flexibility and stability of production are poor.
Disclosure of Invention
The application provides a flexible improvement method of emulsified asphalt, which aims to solve the technical problems of poor production flexibility and stability caused by the lack of real-time dynamic regulation and control of emulsification control parameters in the prior art that a static control method is generally adopted in an emulsification stage of flexible improvement.
The application discloses a flexible improvement method of emulsified asphalt, which comprises the steps of screening historical emulsification control records of similar asphalt of target emulsified asphalt in a flexible improvement database, extracting a first historical emulsification record in the historical emulsification control records, wherein the first historical emulsification record comprises first historical emulsification control information and first historical asphalt atomization information, reading a preset emulsification index, traversing the first historical emulsification control information based on the preset emulsification index to obtain a first historical emulsification control parameter, introducing an atomization evaluation function to evaluate and analyze the first historical emulsification control parameter to obtain a first historical atomization index, performing supervised learning on a first data set established based on the first historical emulsification control parameter and the first historical atomization index to obtain an atomization prediction model, and dynamically regulating and controlling the emulsification control parameter of the target emulsified asphalt through the atomization prediction model.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
The method comprises the steps of screening historical emulsification control records of similar asphalt of target emulsified asphalt in a flexible improvement database, obtaining past data similar to the target asphalt through screening the historical records of the similar asphalt, providing basic data for subsequent analysis, selecting an analysis object in the historical emulsification records, obtaining a first historical emulsification record and related information of the first historical emulsification record, wherein the related information comprises first historical emulsification control information and first historical atomization information, the information comprises emulsification process control parameters and atomization conditions of the asphalt, providing specific data support for analysis, reading a preset emulsification index, traversing the first historical emulsification control information to obtain the first historical emulsification control parameters, ensuring that the used data are matched with the actual conditions of the target asphalt, improving the accuracy of prediction, utilizing an atomization evaluation function to analyze the atomization information of the historical asphalt, obtaining an atomization index, providing detailed evaluation on an emulsification process, quantifying the atomization effect, constructing a data set based on the historical emulsification control parameters and the atomization index, performing supervision learning, obtaining a historical emulsification prediction model, training through the data, learning different control parameters, optimizing the emulsification control parameters and optimizing the emulsification control parameters, optimizing the emulsification process of the target asphalt, optimizing the emulsification control parameters, optimizing the emulsification production quality, and optimizing the emulsification control parameters, and optimizing the emulsification production quality.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
FIG. 1 is a schematic flow chart of a flexible improvement method for emulsified asphalt according to an embodiment of the application;
fig. 2 is a schematic diagram of a process for obtaining a history emulsion control record in a flexible improvement method of emulsified asphalt according to an embodiment of the present application.
Detailed Description
The embodiment of the application solves the technical problems of poor production flexibility and stability caused by the lack of real-time dynamic regulation and control of emulsification control parameters by adopting a static control method for the emulsification stage of the flexible improvement in the prior art by providing the flexible improvement method of the emulsified asphalt.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
As shown in fig. 1, an embodiment of the present application provides a method for improving flexibility of emulsified asphalt, the method comprising:
historical emulsification control records of the same class of bitumen of the target emulsified bitumen are screened in a flexible improvement database.
The flexible improvement database comprises detailed records of multiple stages in the improvement process, including a raw material preparation stage, a premixing stage, an emulsification stage, a curing stage and the like.
Before screening, key features of the target emulsified asphalt are defined, including material preparation dimension features and premix dimension features, which serve as criteria for screening histories for matching with histories in a database. And extracting target multidimensional characteristic parameters of the target emulsified asphalt based on the material preparation dimensional characteristics and the premixing dimensional characteristics.
And screening historical emulsification records with similar characteristics based on the target multidimensional characteristic parameters of the target emulsified asphalt from the flexible improvement database, specifically, comparing the target multidimensional characteristic parameters of the target emulsified asphalt with characteristic parameters of each asphalt sample in the database, and screening historical emulsification control records of similar asphalt meeting a similarity threshold as basic data of subsequent analysis.
And extracting a first historical emulsification record in the historical emulsification control records, wherein the first historical emulsification record comprises first historical emulsification control information and first historical asphalt atomization information.
An analysis object is randomly extracted from a historical emulsification control record as a first historical emulsification record, wherein the first historical emulsification record comprises first historical emulsification control information and first historical asphalt micronization information, the emulsification control information comprises detailed records of control parameters in the emulsification process, such as a shearing rate, an emulsification temperature, a stirring speed, an addition sequence of an emulsifying agent and the like, the control information reflects specific operation steps and parameter settings adopted in the historical emulsification process for realizing a target emulsification effect, the asphalt micronization information refers to specific conditions of asphalt particle formation and distribution in the emulsification process, the information comprises average size of particles, uniformity of particle distribution, particle morphology characteristics and the like, the extraction method of the micronization information is as follows, key indexes such as average diameter of particles, standard deviation, particle concentration and the like are extracted from particle size distribution data collected in the emulsification process, if image data of particle morphology is available, the morphological characteristics of the particles including shape, boundary sharpness and the like can be extracted through image processing technology, statistical analysis is carried out on the extracted micronization data, calculated key granulating parameters such as average value of particle size, standard deviation, variation coefficient and the asphalt is obtained.
And reading a preset emulsification index, and traversing the first historical emulsification control information based on the preset emulsification index to obtain a first historical emulsification control parameter.
The preset emulsifying index is a key parameter used for controlling the emulsifying process in the emulsifying process and is a predefined index comprising a shear rate and a temperature, wherein the shear rate is the shear rate applied to materials in the emulsifying process and directly influences the dispersion degree of asphalt particles, and the temperature is the temperature control in the emulsifying process and influences the interaction of an emulsifying agent and asphalt. And matching the preset emulsification index with each data item in the first historical emulsification control information, and screening out specific control parameters corresponding to the indexes, such as shear rate, temperature and the like at a certain time point to obtain the first historical emulsification control parameters.
And introducing a micronization evaluation function to evaluate and analyze the first historical asphalt micronization information to obtain a first historical micronization index.
The micronization evaluation function is used to evaluate the quality of the micronization during the asphalt emulsification process, and the function measures the effect of the micronization based on a number of parameters. The first historical asphalt atomization information comprises detailed data about asphalt atomization in a historical record, such as the size, distribution, shape and the like of particles, and in the evaluation and analysis process, the data are evaluated through an atomization evaluation function, an intermediate result reflecting the atomization effect is extracted, and a first historical atomization index is obtained and used for representing the advantages and disadvantages of the atomization effect in the emulsification process.
And performing supervised learning on a first data set established based on the first historical emulsification control parameters and the first historical atomization index to obtain an atomization prediction model.
Pairing the first historical emulsification control parameters with the first historical micronization indexes to obtain a first data set, and so on, forming a multi-dimensional data set by pairing the control parameters in each historical record with the corresponding micronization indexes, wherein the data set is used as the basis of supervised learning.
In order to conduct supervised learning, the data component is divided into two parts, namely a training set and a testing set, wherein the training set comprises most historical data and is used for training a micronized prediction model, internal parameters of the model are gradually adjusted through multiple iterations to maximize prediction accuracy, and the testing set comprises a small amount of data which does not participate in training and is used for verifying the generalization capability and the actual prediction effect of the model.
Selecting a supervised learning algorithm, such as a random forest, a neural network and the like, wherein in the training process, the algorithm learns the relation between historical emulsification control parameters and historical micronization indexes based on a training set, along with the progress of training, a model gradually learns how to extract information from the control parameters, predicts the micronization effect with higher precision, and after the model training is finished, a test set is used for verifying the model to evaluate the prediction effect and the generalization capability of the model, if the model performs non-ideal on the test set, the super parameters of the model are required to be adjusted until the preset effect is reached, and finally, a micronization prediction model is obtained, which can predict the micronization effect of asphalt emulsification in real time according to the input emulsification control parameters.
And dynamically regulating and controlling the emulsification control parameters of the target emulsified asphalt through the micronization prediction model.
The method comprises the steps of obtaining target emulsification control parameters of target emulsified asphalt, inputting the obtained target emulsification control parameters into a micronization prediction model, and predicting target prediction micronization indexes under the target emulsification control parameters based on a trained algorithm for evaluating the micronization effect of the target asphalt under the current control parameters. Comparing the target predicted micronization index with a preset micronization standard, if the predicted result meets the standard, indicating that the current emulsification control parameter is proper, and continuing the production process, and if the predicted result does not meet the preset standard, adjusting the emulsification control parameter to optimize the micronization effect. The specific parameter regulation and control comprises the adjustment of the shearing rate and the adjustment of the temperature, so that the micronizing effect is improved, and the emulsification control parameters in the production process are always in the optimal state.
Further, as shown in fig. 2, the method includes:
The method comprises the steps of carrying out multidimensional feature collection on target emulsified asphalt based on preset emulsified asphalt dimensions to obtain target multidimensional feature parameters, extracting first flexible improvement records of first asphalt in the flexible improvement database, judging whether first similarity between the target multidimensional feature parameters and the first multidimensional feature parameters accords with preset similarity limit values or not, if so, marking the first asphalt as first similar asphalt, and adding the first emulsification control records of the first similar asphalt to the historical emulsification control records.
The predetermined emulsified asphalt dimensions include a material preparation dimension and a premix dimension, wherein the material preparation dimension includes raw material characteristics associated with asphalt production, and the main characteristics include a matrix asphalt characteristic including at least viscosity, softening point, and asphaltene content, which determine the basic physical properties of the emulsified asphalt, and an emulsifier characteristic including at least a kind, proportion, and formulation, which affect the dispersion and stability of asphalt particles during emulsification. The premix dimension relates to the premix stage in the emulsification process and includes the mixing speed, mixing intensity and mixing duration of the emulsifier.
In the production process, according to the dimensions, a plurality of characteristic parameters related to the target emulsified asphalt are collected to obtain target multidimensional characteristic parameters, and the parameters can be obtained through a sensor, laboratory analysis or operation record and are used for accurately matching with a history record.
The flexible improvement database stores historical data of a plurality of asphalt improvement projects, first asphalt is randomly selected in the flexible improvement database, and a first flexible improvement record of the first asphalt is extracted, wherein the first flexible improvement record comprises a first multidimensional characteristic parameter and a first emulsification control record.
Comparing the target multi-dimensional characteristic parameters of the target emulsified asphalt with the first multi-dimensional characteristic parameters of the first asphalt, evaluating the similarity of the target multi-dimensional characteristic parameters, specifically, encoding the classified characteristics, converting the classified characteristics into a form suitable for calculation, calculating the distance between the two characteristic vectors by using a distance measurement method such as Euclidean distance, manhattan distance and the like, and calculating the similarity based on the distance measurement, wherein the similarity can be expressed in a proportion, a correlation coefficient and the like. The calculated similarity is compared to a predetermined similarity limit, which is a predetermined criterion for determining whether the two samples are sufficiently similar.
If the feature similarity meets a predetermined similarity limit, the first asphalt is marked as a first-class asphalt and a first emulsification control record of the first-class asphalt 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.
Further, the predetermined emulsified asphalt dimensions include a material preparation dimension including a matrix asphalt characteristic including at least a viscosity, a softening point, and an asphaltene content, and an emulsifier characteristic including at least a type, a ratio, and a formulation, and a premix dimension including a mixing speed, a mixing intensity, and a mixing duration of the emulsifier.
The predetermined emulsified asphalt dimensions include a material preparation dimension and a premix dimension, which relate to the different stages and characteristics of the emulsified asphalt process.
The material preparation dimension relates to raw material characteristics of emulsified asphalt, and mainly comprises a matrix asphalt characteristic and an emulsifier characteristic, wherein the matrix asphalt characteristic at least comprises viscosity, a softening point and an asphaltene content, the viscosity is used for measuring fluidity and consistency of asphalt, the softening point refers to the temperature at which the asphalt starts to soften in a heating process, the characteristic reflects the stability of the asphalt at high temperature, and the asphaltene content is the content of dissolved organic substances in the asphalt and influences the hardness and adhesiveness of the asphalt. The characteristics of the emulsifier include at least the kind, proportion and formulation, meaning the combination of chemical components of the emulsifier and additives, which affect the effect of the emulsification process and the quality of the final product.
The premixing dimension relates to a mixing process of the emulsifier in the matrix asphalt, and comprises mixing speed, mixing strength and mixing duration of the emulsifier, wherein the mixing speed of the emulsifier is the speed of the emulsifier added into the matrix asphalt, the mixing speed is too high or too low, the emulsifying effect can be influenced, the mixing strength is force or energy applied in the mixing process, the dispersing degree and uniformity of the emulsifier are directly influenced, the mixing duration is the mixing time of the emulsifier and the matrix asphalt, and the emulsifying integrity and stability are influenced by the length of the mixing time.
Further, the method comprises the steps of:
The method comprises the steps of sequentially carrying out coding processing on classified data in a target multi-dimensional characteristic parameter and a first multi-dimensional characteristic parameter to obtain a target coding value and a first coding value respectively, sequentially carrying out variance stabilizing transformation processing on numerical data in the target multi-dimensional characteristic parameter and the first multi-dimensional characteristic parameter to obtain a target transformation value and a first transformation value respectively, forming a target parameter vector by the target coding value and the target transformation value, forming a first parameter vector by the first coding value and the first transformation value, and comparing and analyzing the target parameter vector and the first parameter vector to obtain the first similarity.
The classification data refers to the characteristics of limited discrete categories such as asphalt type, emulsifier type, etc. The encoding process converts the classified data into a digital format for similarity calculation, and common encoding methods include tag encoding, single-hot encoding, and the like, and illustratively, a single-hot encoding method is used to create a binary feature for each class, each class corresponds to an independent feature, 1 in the position of the corresponding class, and 0 in the rest positions, for example, the asphalt type a, type B, and type C are encoded into three binary features, each feature representing a class.
All the classified data are sequentially extracted from the target multidimensional feature parameters and the first multidimensional feature parameters, the classified data in the target multidimensional feature parameters and the first multidimensional feature parameters are subjected to coding processing by using the coding method, and a target coding value and a first coding value are respectively generated and used for subsequent similarity calculation.
The numerical data is characterized by continuous numerical values, such as viscosity, softening point, proportion of emulsifying agent, etc., and the variance stabilizing transformation aims to keep the variance of the numerical data in a relatively stable range, and the variance stabilizing transformation method comprises logarithmic transformation, square root transformation, Z-score standardization, etc., and the data is converted into a standard normal distribution with a mean value of 0 and a variance of 1 by adopting a Z-score standardization method.
All numerical data are sequentially extracted from the target multidimensional feature parameters and the first multidimensional feature parameters, and the corresponding variance stabilizing transformation is carried out on the numerical data in the target multidimensional feature parameters and the first multidimensional feature parameters by adopting the variance stabilizing transformation method, so that a target transformation value and a first transformation value are respectively generated and used for subsequent similarity calculation.
The target coding value and the target transformation value are integrated to form a target parameter vector, and the first coding value and the first transformation value are integrated to form a first parameter vector. And selecting a similarity measurement method, such as cosine similarity, calculating an included angle cosine value between the target parameter vector and the first parameter vector, representing the directional similarity of the two vectors, calculating to obtain first similarity, and representing the similarity degree of the first asphalt of the target asphalt.
Further, the predetermined emulsification indicators include shear rate and temperature.
The predetermined emulsification index comprises a shear rate and a temperature, wherein the shear rate refers to the rate of the shear force between the emulsifier and the asphalt matrix, particularly the rotating speed of stirring or mixing equipment in the emulsification process, so as to influence the dispersion degree and the emulsification effect of the emulsifier, and the temperature refers to temperature control in the emulsification process, so that the rheological property of asphalt and the activity of the emulsifier are greatly influenced, and the viscosity of asphalt and the reaction characteristic of the emulsifier are changed at different temperatures.
Further, the method comprises the steps of:
The first historical emulsification record further comprises first historical emulsification environment information, and the first historical asphalt atomization information and the first historical emulsification environment information are subjected to evaluation analysis by utilizing the atomization evaluation function to obtain the first historical atomization index, wherein the expression of the atomization evaluation function is as follows:
;
Wherein, Characterizing a first historical bitumen in the first historical emulsification recordIs characterized by a first historical micronization index,Characterizing the first historic asphaltIs a first historical emulsified air density of (c),Characterizing a first one of the first historical emulsification context informationThe parameters of the characteristics of the individual environment,Characterizing the firstThe first historical emulsification environment information comprises the environment temperature characteristic parameter, the environment humidity characteristic parameter and the environment air pressure characteristic parameter, namely,AndCharacterizing the particle size parameter and the particle distribution uniformity parameter in the first historical asphalt micronization information respectively,AndCharacterizing the first coefficient of variation and the second coefficient of variation, respectively, and。
The first historical emulsification record further comprises first historical emulsification environment information, wherein the historical emulsification environment information comprises an environment temperature characteristic parameter, an environment humidity characteristic parameter and an environment air pressure characteristic parameter.
And carrying out evaluation analysis on the first historical asphalt atomization information and the first historical emulsification environment information by using an atomization evaluation function to obtain a first historical atomization index, wherein the expression of the atomization evaluation function is as follows:
;
Wherein, Characterizing a first historical bitumen in the first historical emulsification recordIs an output value of a function describing the extent of atomization of the asphalt under specific emulsification conditions.Characterizing the first historic asphaltThe first historical emulsified air density, ambient temperature, humidity, air pressure, etc. parameters affect the density change of the air during the emulsification process, and thus affect the atomization effect of the asphalt, through which the function captures these effects.AndThe particle size parameter and the particle distribution uniformity parameter respectively representing the first historical asphalt atomization information are key indexes for evaluating the atomization quality, and the function is realized byThis section quantifies the contribution of these features to the micronization index.
Finally, the function combines the air density and the influence of the particle characteristics in a weighted manner to obtain a comprehensive micronization index, thereby providing a basis for subsequent emulsification control. The function provides a method for accurately evaluating the micronizing quality in the asphalt emulsification process by integrating the influence of environmental factors and micronizing characteristics, and the evaluation not only considers the change of external environment, but also reflects the state of the characteristics of particles in the asphalt, thereby realizing multidimensional and comprehensive evaluation.
Further, the method further comprises the following steps:
Dynamically acquiring a target emulsification control parameter of the target emulsified asphalt, analyzing the target emulsification control parameter through the atomization prediction model to obtain a target prediction atomization index, and dynamically adjusting the target emulsification control parameter when the target prediction atomization index does not accord with a preset atomization constraint.
In the actual production process of the target emulsified asphalt, the control parameters in the emulsification process are obtained in real time through a sensor, a data acquisition system and the like, and the target emulsification control parameters are obtained.
The obtained target emulsification control parameters are input into a pre-trained atomization prediction model, and the atomization prediction model analyzes the parameters according to the input control parameters and by utilizing the learned mode and rule so as to predict the atomization effect of the emulsified asphalt under the current control condition, output a target predicted atomization index and reflect the predicted atomization degree of the emulsified asphalt.
A predetermined micronization constraint, i.e., the minimum threshold value that the target predicted micronization index needs to reach, is set, and this constraint value may be determined based on production requirements, product quality criteria, historical data analysis, and the like. When the target predicted micronization index does not meet the preset micronization constraint, firstly analyzing the specific reasons of the non-compliance, such as the reasons caused by the non-matching of parameters such as the shearing rate, the temperature and the like, determining the emulsification control parameters needing to be adjusted preferentially, for example, if the influence of the temperature on the micronization is large, adjusting the temperature parameters preferentially, and according to the analysis result, performing real-time adjustment on the control parameters which are not met by the automatic control system, for example, if the shearing rate is low, improving the shearing rate by adjusting the working speed of the shearing equipment. And inputting the adjusted parameters into the micronization prediction model again, and calculating a new target prediction micronization index in real time until the target prediction micronization index accords with a preset micronization constraint.
Further, the method further comprises the following steps:
The method comprises the steps of activating a conductivity probe to monitor dynamic conductivity of target emulsified asphalt to obtain target conductivity, extracting a first emulsification point in the emulsification points, matching first conductivity of the first emulsification point in the conductivity values, generating a target conductivity visual view according to a first corresponding relation between the first emulsification point and the first conductivity when the first conductivity meets a preset marking constraint, and carrying out micronization visual analysis on the target emulsified asphalt according to the target conductivity visual view.
The conductivity probe has high sensitivity, can capture tiny conductivity change in real time, a plurality of key points are selected in the emulsification process to serve as a plurality of emulsification points, the emulsification points are distributed in different areas of the emulsification equipment so as to ensure comprehensive monitoring, the conductivity probe is arranged at the plurality of emulsification points so as to monitor conductivity change in the emulsification process, the conductivity probe continuously collects conductivity data of each emulsification point, the data can reflect dispersion state and stability of particles in emulsified asphalt, conductivity values of all emulsification points are summarized to obtain target conductivity, and the target conductivity comprises a plurality of conductivity values of a plurality of emulsification points.
And randomly selecting one analysis object from the plurality of emulsification points to serve as a first emulsification point, and extracting a conductivity value corresponding to the first emulsification point to serve as a first conductivity.
The predetermined signature constraint is a threshold range set according to experimental data or theoretical criteria for evaluating the reliability of the conductivity data, e.g. the conductivity value must be within a certain reasonable interval and the fluctuations should be within an acceptable range. And comparing the first conductivity with a preset mark constraint, and when the first conductivity accords with the preset mark constraint, indicating that the conductivity detection value is normal, indicating that the detection is error-free and the data is accurate, and being capable of being used for visual analysis. In this case, the first conductivity is matched with the first emulsification point, a visual view of the target conductivity is generated according to the set of data, and the visual view is generated by adopting a data visualization tool, such as a line graph or a heat map, wherein the line graph can show the conductivity change trend in the emulsification process, and the heat map can more intuitively show the conductivity distribution of different emulsification points.
On the generated target conductivity visual view, analyzing the conductivity changes of different emulsification points to determine the trend and rule of atomization, for example, the sudden increase or decrease of the conductivity of certain points may mean aggregation or dispersion of particles, and by comparing and analyzing each stage of the emulsification process, key factors influencing the atomization effect can be found, and based on the result of the atomization visual analysis, suggestions for optimizing the emulsification control parameters are provided to further improve the emulsification effect, for example, the mixing rate or the shearing rate of an emulsifier is adjusted, or the emulsification temperature is changed, so as to guide the optimization of the subsequent emulsification process, and the production process is more efficient and stable.
Further, the method comprises the steps of:
Extracting a second emulsification point in the emulsification point positions, and matching the second conductivity of the second emulsification point position in the conductivity values, wherein the spatial distance between the second emulsification point position and the first emulsification point position is in a preset distance limit value, acquiring a conductivity difference value between the second conductivity and the first conductivity, and when the conductivity difference value is in the preset difference value limit value, the first conductivity accords with the preset marking constraint.
And extracting a second emulsification point from the plurality of emulsification points, wherein the spatial distance between the second emulsification point and the first emulsification point is in a preset distance limit value, and the preset distance limit value is a threshold value for judging the spatial neighborhood range between the two emulsification points and is used for ensuring the points at similar positions, the conductivity data of the points can be compared with each other and reflect the change of the local emulsification process, namely the second emulsification point is the neighborhood point of the first emulsification point. And extracting the conductivity value corresponding to the second emulsification point position, namely the second conductivity from the conductivity data obtained by dynamic monitoring.
And calculating a conductivity difference value between the second conductivity and the first conductivity, wherein the conductivity difference value reflects the change condition of the conductivity between two adjacent points, a larger difference value represents uneven emulsification or unstable atomization, and a smaller difference value represents relatively uniform emulsification process.
The predetermined difference limit is a predetermined threshold for determining whether the first conductivity meets a criterion, which may be based on experimental data, historical records, or process criteria. And if the conductivity difference is smaller than or equal to the preset difference limit value, the conductivity difference between the two points is within an allowable range, which indicates that the first conductivity data has higher reliability and can be considered to be accurate, and in this case, the first conductivity is judged to be in accordance with the preset marking constraint.
In summary, the method for improving the flexibility of the emulsified asphalt provided by the embodiment of the application has the following technical effects:
The method comprises the steps of screening historical emulsification control records of similar asphalt of target emulsified asphalt in a flexible improvement database, obtaining past data similar to the target asphalt through screening the historical records of the similar asphalt, providing basic data for subsequent analysis, selecting an analysis object in the historical emulsification records, obtaining a first historical emulsification record and related information of the first historical emulsification record, wherein the related information comprises first historical emulsification control information and first historical atomization information, the information comprises emulsification process control parameters and atomization conditions of the asphalt, providing specific data support for analysis, reading a preset emulsification index, traversing the first historical emulsification control information to obtain the first historical emulsification control parameters, ensuring that the used data are matched with the actual conditions of the target asphalt, improving the accuracy of prediction, utilizing an atomization evaluation function to analyze the atomization information of the historical asphalt, obtaining an atomization index, providing detailed evaluation on an emulsification process, quantifying the atomization effect, constructing a data set based on the historical emulsification control parameters and the atomization index, performing supervision learning, obtaining a historical emulsification prediction model, training through the data, learning different control parameters, optimizing the emulsification control parameters and optimizing the emulsification control parameters, optimizing the emulsification process of the target asphalt, optimizing the emulsification control parameters, optimizing the emulsification production quality, and optimizing the emulsification control parameters, and optimizing the emulsification production quality.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411962370.3A CN119361013B (en) | 2024-12-30 | 2024-12-30 | Flexible improvement method of emulsified asphalt |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411962370.3A CN119361013B (en) | 2024-12-30 | 2024-12-30 | Flexible improvement method of emulsified asphalt |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119361013A CN119361013A (en) | 2025-01-24 |
| CN119361013B true CN119361013B (en) | 2025-05-16 |
Family
ID=94319545
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411962370.3A Active CN119361013B (en) | 2024-12-30 | 2024-12-30 | Flexible improvement method of emulsified asphalt |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119361013B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1084235A (en) * | 1992-09-09 | 1994-03-23 | 袁柏耕 | Multi-functional particulate carbohydrate remover for enriched carbohydrate-contained cotton and production method thereof |
| CN1628226A (en) * | 2002-02-08 | 2005-06-15 | 关口株式会社 | Incineration treatment method of waste liquid using industrial combustion equipment and mixed liquid |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10378324B2 (en) * | 2016-09-26 | 2019-08-13 | International Business Machines Corporation | Controlling operation of a steam-assisted gravity drainage oil well system by adjusting controls based on forecast emulsion production |
-
2024
- 2024-12-30 CN CN202411962370.3A patent/CN119361013B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1084235A (en) * | 1992-09-09 | 1994-03-23 | 袁柏耕 | Multi-functional particulate carbohydrate remover for enriched carbohydrate-contained cotton and production method thereof |
| CN1628226A (en) * | 2002-02-08 | 2005-06-15 | 关口株式会社 | Incineration treatment method of waste liquid using industrial combustion equipment and mixed liquid |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119361013A (en) | 2025-01-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Behnood et al. | Predicting the dynamic modulus of asphalt mixture using machine learning techniques: An application of multi biogeography-based programming | |
| CN118689157B (en) | Production monitoring system and method based on big data | |
| CN105930723A (en) | Intrusion detection method based on feature selection | |
| CN118761689B (en) | Construction site quality management evaluation system based on fuzzy C-means clustering | |
| Owais | Analysing Witczak 1-37A, Witczak 1-40D and Modified Hirsch Models for asphalt dynamic modulus prediction using global sensitivity analysis | |
| CN118550573B (en) | IT operation and maintenance management method and IT operation and maintenance management device | |
| CN109740890A (en) | A kind of influencing factors of quality correlation analysis | |
| CN120106690B (en) | Copper wire tensile quality detection method and system for elongation analysis | |
| Siroma et al. | Clustering aged bitumens through multivariate statistical analyses using phase angle master curve | |
| CN106685921B (en) | Network equipment risk assessment method | |
| CN117172556A (en) | A construction risk early warning method and system for bridge projects | |
| CN119249367B (en) | Intelligent environment monitoring method, system, equipment and readable storage medium | |
| Ji et al. | A Bayesian deep learning approach for rheological properties prediction of asphalt binders considering uncertainty of output | |
| CN119361013B (en) | Flexible improvement method of emulsified asphalt | |
| CN113392576A (en) | Staying balloon main cable tension state assessment early warning method | |
| CN107330454B (en) | Nonlinear massive high-dimensional sequence data classification characteristic visualization and quantitative analysis method | |
| CN119539292A (en) | Process optimization methods, devices, equipment and systems | |
| CN112651173B (en) | A non-destructive testing method and generalizable system for agricultural product quality based on cross-domain spectral information | |
| Ochodek et al. | SimSAX: A measure of project similarity based on symbolic approximation method and software defect inflow | |
| CN113988519A (en) | Method for representing risk of cultural relic preservation environment in collection of cultural relics | |
| CN117172125A (en) | Construction engineering stress assessment method and system based on convolutional neural network | |
| CN118963292B (en) | A production control optimization method and system for fastening functional parts | |
| CN119203010B (en) | Production data management system based on artificial intelligence | |
| KR102819231B1 (en) | Device and Method for Anomaly Detection Using Unsupervised Learning | |
| CN119090342B (en) | Comprehensive monitoring method and system for road construction |
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 |