Asphalt product performance prediction model construction method and device and asphalt product performance prediction method and device

By constructing the asphalt product performance prediction model, and using the amplified feature vector training of sample production feature vectors and predicted performance feature vectors, the problem of low performance prediction accuracy of asphalt product in the existing technology is solved, and the performance of different crude oil varieties and proportioning performance is achieved accurate prediction.

CN118897976AActive Publication Date: 2024-11-05CHINA PETROLEUM & CHEMICAL CORP +1
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202310485900.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-02
Publication Date
2024-11-05
Estimated Expiration
2043-05-02

AI Technical Summary

Technical Problem

In the prior art, the performance prediction accuracy of asphalt products is low, and relying on manual reference historical data and crude oil evaluation reports, there are many subjective factors that lead to prediction deviations.

Method used

By constructing the asphalt product performance prediction model, determine the sample production feature vector, extract the four-component feature vector of sample residue, input the initial regression model, obtain the predicted performance feature vector, and train the model based on the amplified feature vector to predict different crude oil varieties and combinations based on the amplified feature vector. Compared with the corresponding asphalt product performance.

Benefits of technology

Accurate prediction of the performance of asphalt products is achieved, the deviation introduced by manual prediction is reduced, and the prediction accuracy is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118897976A_ABST
    Figure CN118897976A_ABST
Patent Text Reader

Abstract

The invention provides an asphalt product performance prediction model construction method and device and an asphalt product performance prediction method and device, and the model construction method comprises the steps: determining a sample production feature vector of a sample asphalt product, the sample production feature vectors comprise feature vectors of different sample crude oil components corresponding to the sample asphalt product and sample performance feature vectors of the sample asphalt product; extracting sample residual oil four-component feature vectors in the sample production feature vectors, and inputting the sample residual oil four-component feature vectors into the initial regression model to obtain sample prediction performance feature vectors output by the initial regression model; and splicing the sample production feature vector and the sample prediction performance feature vector to obtain a sample amplification feature vector, and training based on the sample amplification feature vector to obtain an asphalt product performance prediction model. According to the invention, the asphalt product performance corresponding to different crude oil varieties and proportions can be accurately predicted based on the asphalt product performance prediction model, and the problem of prediction performance deviation caused by artificial prediction is avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of petrochemical technology, and in particular to the construction of an asphalt product performance prediction model, a performance prediction method and a device. Background Art

[0002] Asphalt is an important product in petroleum refining. Straight-run asphalt is directly produced by atmospheric and vacuum units and has low production costs. However, the performance of straight-run asphalt products varies with the quality and proportion of crude oil, so it is particularly important to select the appropriate crude oil proportion to ensure the performance of asphalt products.

[0003] At present, the performance of asphalt products obtained according to different crude oil varieties and proportions is mostly predicted by manual reference to historical production data and crude oil evaluation reports. However, this method introduces too many subjective factors, resulting in deviations in the predicted asphalt product performance. Summary of the invention

[0004] The present invention provides an asphalt product performance prediction model construction, a performance prediction method and a device, which are used to solve the defect of low asphalt product performance prediction accuracy in the prior art.

[0005] The present invention provides a method for constructing an asphalt product performance prediction model, comprising:

[0006] Determine a sample production feature vector of a sample asphalt product, wherein the sample production feature vector includes feature vectors of different sample crude oil components corresponding to the sample asphalt product and a sample performance feature vector of the sample asphalt product;

[0007] Extracting a sample residual oil four-component feature vector from the sample production feature vector, and inputting the sample residual oil four-component feature vector into an initial regression model to obtain a sample prediction performance feature vector output by the initial regression model;

[0008] The sample production feature vector and the sample prediction performance feature vector are spliced ​​to obtain a sample amplification feature vector, and based on the sample amplification feature vector, an asphalt product performance prediction model is trained.

[0009] According to a method for constructing an asphalt product performance prediction model provided by the present invention, the step of determining a sample production feature vector of a sample asphalt product comprises:

[0010] Determine the characteristic vectors of different sample crude oil components of the sample bitumen product;

[0011] According to the preset mixed oil weight, the characteristic vectors of the crude oil components of each sample are weighted and added to obtain the sample combination characteristic vector;

[0012] The sample combination feature vector and the sample performance feature vector are concatenated to obtain the sample production feature vector.

[0013] A method for constructing an asphalt product performance prediction model provided by the present invention also includes:

[0014] When the performance index corresponding to any sample performance characteristic vector is a range index, the corresponding sample performance characteristic vector is represented in the form of a discrete variable;

[0015] In the case that any sample crude oil component characteristic vector is missing, the average value of the remaining sample crude oil component characteristic vectors in the column where the missing sample crude oil component characteristic vector is located is used as the missing sample crude oil component characteristic vector;

[0016] When the performance index corresponding to any sample performance characteristic vector exceeds the instrument range, the maximum value of the column where the corresponding sample performance characteristic vector is located is used as the corresponding sample performance characteristic vector;

[0017] In the event that any sample performance feature vector is missing, the row position of the missing sample performance feature vector is identified, and before training the asphalt product performance prediction model, the data corresponding to the row position is deleted.

[0018] According to a method for constructing an asphalt product performance prediction model provided by the present invention, the initial regression model includes an initial linear regression model and an initial logistic regression model, and the sample prediction performance feature vector includes a sample continuous performance feature vector and a sample discrete performance feature vector;

[0019] The step of inputting the four-component feature vector of the sample residual oil into the initial regression model to obtain the sample prediction performance feature vector output by the initial regression model includes:

[0020] Inputting the four-component characteristic vector of the sample residual oil into the initial linear regression model to obtain the sample continuous performance characteristic vector output by the initial linear regression model;

[0021] The four-component characteristic vector of the sample residual oil is input into the initial logistic regression model to obtain the sample discrete performance characteristic vector output by the initial logistic regression model.

[0022] A method for constructing an asphalt product performance prediction model provided by the present invention also includes:

[0023] In the case where the sample performance feature vector is a continuous sample performance feature vector, the base learner of the asphalt product performance prediction model is constructed based on a classification and regression tree;

[0024] In the case where the sample performance feature vector is a discrete sample performance feature vector, the base learner of the asphalt product performance prediction model is constructed based on a multi-classification regression tree, and the multi-classification regression tree uses Softmax as the objective function.

[0025] The present invention also provides a method for predicting asphalt product performance, comprising:

[0026] Determine the target residue oil four-component characteristic vector of the target asphalt product;

[0027] Inputting the target residual oil four-component characteristic vector into the initial regression model to obtain the target prediction performance characteristic vector output by the initial regression model;

[0028] splicing the crude oil component feature vector of the target asphalt product and the target prediction performance feature vector to obtain a target amplified feature vector;

[0029] Inputting the target amplified feature vector into an asphalt product performance prediction model to obtain a performance prediction result of the target asphalt product output by the asphalt product performance prediction model;

[0030] Wherein, the asphalt product performance prediction model is determined based on the asphalt product performance prediction model construction method as described above.

[0031] The present invention provides a device for constructing an asphalt product performance prediction model, comprising:

[0032] A first determining unit is used to determine a sample production feature vector of a sample asphalt product, wherein the sample production feature vector includes feature vectors of different sample crude oil components corresponding to the sample asphalt product and a sample performance feature vector of the sample asphalt product;

[0033] A first prediction unit is used to extract a sample residual oil four-component feature vector from the sample production feature vector, and input the sample residual oil four-component feature vector into an initial regression model to obtain a sample prediction performance feature vector output by the initial regression model;

[0034] The model building unit is used to splice the sample production feature vector and the sample prediction performance feature vector to obtain a sample amplification feature vector, and train an asphalt product performance prediction model based on the sample amplification feature vector.

[0035] The present invention provides an asphalt product performance prediction device, comprising:

[0036] The second determination unit is used to determine the target residual oil four-component characteristic vector of the target asphalt product;

[0037] A second prediction unit is used to input the target residual oil four-component feature vector into the initial regression model to obtain the target prediction performance feature vector output by the initial regression model;

[0038] A vector concatenation unit, used for concatenating the crude oil component feature vector of the target asphalt product with the target prediction performance feature vector to obtain a target amplified feature vector;

[0039] A performance prediction unit, used for inputting the target amplified feature vector into an asphalt product performance prediction model to obtain a performance prediction result of the target asphalt product output by the asphalt product performance prediction model;

[0040] Wherein, the asphalt product performance prediction model is determined based on the asphalt product performance prediction model construction method as described above.

[0041] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for constructing a performance prediction model for an asphalt product, or the method for predicting performance of an asphalt product, as described above, is implemented.

[0042] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for constructing an asphalt product performance prediction model or the asphalt product performance prediction method as described above is implemented.

[0043] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for constructing a model for predicting the performance of an asphalt product, or a method for predicting the performance of an asphalt product.

[0044] The asphalt product performance prediction model construction, performance prediction method and device provided by the present invention use the sample amplification feature vector obtained by splicing the sample production feature vector and the sample prediction performance feature vector as the training set, and train the asphalt product performance prediction model, so as to accurately predict the asphalt product performance corresponding to different crude oil varieties and ratios based on the asphalt product performance prediction model, avoiding the problem of deviation in prediction performance due to manual prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1It is a schematic flow chart of the method for constructing an asphalt product performance prediction model provided by the present invention;

[0047] Figure 2 It is a schematic flow chart of the asphalt product performance prediction method provided by the present invention;

[0048] Figure 3 It is a schematic flow chart of another asphalt product performance prediction method provided by the present invention;

[0049] Figure 4 It is a schematic diagram of the structure of the asphalt product performance prediction model building device provided by the present invention;

[0050] Figure 5 It is a schematic diagram of the structure of the asphalt product performance prediction device provided by the present invention;

[0051] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] The invention provides a method for constructing an asphalt product performance prediction model. Figure 1 is a flow chart of the method for constructing the asphalt product performance prediction model provided by the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0054] Step 110: Determine a sample production feature vector of the sample asphalt product. The sample production feature vector includes feature vectors of different sample crude oil components corresponding to the sample asphalt product and a sample performance feature vector of the sample asphalt product.

[0055] Specifically, the sample asphalt products are obtained by processing sample crude oils with different proportions. The sample production feature vector of the sample asphalt products can be determined based on the historical production data of the sample asphalt products. The historical production data may include crude oil varieties, crude oil proportions, and sample asphalt product performance under different crude oil proportions. The sample asphalt product performance can be characterized by key indicators of the sample asphalt products, such as needle penetration, ductility, dynamic viscosity, etc.

[0056] The sample crude oil component feature vector includes the distillation data information of the sample crude oil and the composition property information of each fraction, and the sample performance feature vector includes the performance index information of the sample asphalt product. Optionally, the sample performance feature vector may include the key index information of the sample asphalt product.

[0057] In some specific implementations, the sample combination feature vector and the sample performance feature vector may be concatenated to obtain a sample production feature vector.

[0058] Step 120: extract the sample residual oil four-component feature vector from the sample production feature vector, and input the sample residual oil four-component feature vector into the initial regression model to obtain the sample prediction performance feature vector output by the initial regression model.

[0059] Specifically, the sample crude oil component characteristics include the sample residual oil four-component characteristics, so after determining the sample production feature vector including the sample crude oil component feature vector, the sample residual oil four-component feature vector can be extracted from the sample production feature vector.

[0060] The four-component feature vector of sample residue oil is used to characterize the information of sample residue oil fraction, namely, the information of saturated hydrocarbons, aromatic hydrocarbons, colloids and asphaltene. The four-component feature vector of sample residue oil is input into the initial regression model, and the initial regression model predicts the performance of sample asphalt product based on the four-component feature vector of sample residue oil to obtain the sample prediction performance feature vector.

[0061] Step 130: concatenate the sample production feature vector and the sample prediction performance feature vector to obtain a sample amplification feature vector, and train an asphalt product performance prediction model based on the sample amplification feature vector.

[0062] Specifically, after obtaining the sample prediction performance feature vector, the sample prediction performance feature vector can be used as a reference vector for predicting the performance of the sample asphalt product. Therefore, the embodiment of the present invention splices the sample production feature vector with the sample prediction performance feature vector to amplify the sample production feature vector to obtain the sample amplification vector, and trains the asphalt product performance prediction model based on the sample amplification feature vector.

[0063] In some specific embodiments, the sample crude oil component feature vector and the sample predicted performance feature vector in the sample amplification vector are used as input, and the sample performance feature vector in the sample amplification vector is used as a label to train the initial asphalt product performance prediction model to obtain the asphalt product performance prediction model.

[0064] It can be seen that the asphalt product performance prediction model construction method provided by the embodiment of the present invention uses the sample amplification feature vector obtained by concatenating the sample production feature vector and the sample prediction performance feature vector as the training set, and trains the asphalt product performance prediction model, so that the asphalt product performance corresponding to different crude oil varieties and ratios can be accurately predicted based on the asphalt product performance prediction model, avoiding the problem of deviation in prediction performance due to manual prediction.

[0065] Based on the above embodiment, determining the sample production feature vector of the sample asphalt product includes:

[0066] Determine the characteristic vectors of different sample crude oil components of the sample bitumen product;

[0067] According to the preset mixed oil weight, the characteristic vectors of the crude oil components of each sample are weighted and added to obtain the sample combination characteristic vector;

[0068] The sample combination feature vector and the sample performance feature vector are concatenated to obtain the sample production feature vector.

[0069] In some specific embodiments, the historical production data of the sample asphalt products are collected according to the LIMS system (Laboratory Information Management System), and the historical production data include the crude oil type and ratio of the sample asphalt products, operating conditions, and the property analysis report of the sample asphalt products. According to the historical production data, the various test properties and corresponding dates of the sample asphalt products are obtained, and then the sample crude oil types and proportions of the historical processing of the day are obtained according to the processing ledger. According to the name of each sample crude oil and the corresponding date, the latest evaluation report is queried in the sample crude oil database, and the distillation data and the composition properties of each fraction in the report are extracted to form the sample crude oil component feature vector of each sample asphalt product.

[0070]

[0071] The characteristic vectors of all sample crude oil components The sample combination feature vector of each sample asphalt product is obtained by weighted averaging according to the preset mixed oil weight.

[0072]

[0073] Among them, r i is the preset mixed oil weight of the i-th crude oil, and

[0074] Get the sample combination feature vector Then, the sample performance characteristic vector of the sample asphalt product is Concatenate the sample combination feature vector After that, the sample production feature vector of each sample asphalt product is obtained.

[0075]

[0076] Among them, y i1 ,y i2 ,…,y im These are m key indicators of sample asphalt products.

[0077] The historical production data of all sample asphalt products are expressed in the form of sample production feature vectors, and the sample production feature vectors of all sample asphalt products are obtained.

[0078]

[0079] Based on any of the above embodiments, the method further includes:

[0080] When the performance index corresponding to any sample performance characteristic vector is a range index, the corresponding sample performance characteristic vector is represented in the form of a discrete variable;

[0081] In the case that any sample crude oil component characteristic vector is missing, the average value of the remaining sample crude oil component characteristic vectors in the column where the missing sample crude oil component characteristic vector is located is used as the missing sample crude oil component characteristic vector;

[0082] When the performance index corresponding to any sample performance characteristic vector exceeds the instrument range, the maximum value of the column where the corresponding sample performance characteristic vector is located is used as the corresponding sample performance characteristic vector;

[0083] In the case that any sample performance feature vector is missing, the row position of the missing sample performance feature vector is identified, and the data corresponding to the row position is deleted before training the asphalt product performance prediction model.

[0084] In some specific embodiments, when the performance indicator corresponding to any sample performance characteristic vector is a range indicator, it indicates that the corresponding sample performance indicator is difficult to be represented by a precise detection value, but is represented by a numerical range. At this time, the corresponding sample performance characteristic vector can be stored in a discrete format, such as converting the corresponding numerical range into a discrete variable representation of 0, 1, 2, 3,... in sequence.

[0085] When any sample crude oil component characteristic vector is missing, it is filled in according to the average value of the remaining sample crude oil component characteristic vectors in the column where the missing sample crude oil component characteristic vector is located, that is, the average value is used as the missing sample crude oil component characteristic vector.

[0086] When the performance index corresponding to any sample performance characteristic vector exceeds the instrument range, the maximum value of the column where the corresponding sample performance characteristic vector is located is used as the corresponding sample performance characteristic vector.

[0087] When any sample performance feature vector is missing, the row position of the missing sample performance feature vector is identified so that the data corresponding to the row position can be discarded during the training process. This can be understood as deleting the data corresponding to the row position before training the asphalt product performance prediction model.

[0088] Based on any of the above embodiments, the initial regression model includes an initial linear regression model and an initial logistic regression model, and the sample prediction performance feature vector includes a sample continuous performance feature vector and a sample discrete performance feature vector;

[0089] The four-component feature vector of the sample residue oil is input into the initial regression model to obtain the sample prediction performance feature vector output by the initial regression model, including:

[0090] Input the characteristic vectors of the four components of the sample residue oil into the initial linear regression model to obtain the sample continuous performance characteristic vector output by the initial linear regression model;

[0091] The four-component characteristic vectors of sample residue oil are input into the initial logistic regression model to obtain the sample discrete performance characteristic vector output by the initial logistic regression model.

[0092] Specifically, the initial regression model includes an initial linear regression model and an initial logistic regression model. The initial linear regression model is used to predict the sample continuous performance characteristic vector, and the initial logistic regression model is used to predict the sample discrete performance characteristic vector. Among them, the sample continuous performance characteristic vector refers to a performance vector represented by a value range, and the sample discrete performance characteristic vector refers to a performance vector represented by a discrete value.

[0093] In some embodiments, a feature vector is generated from a sample Extract the four-component feature vector of sample residual oil Four-component characteristic vector of sample residue oil Each row of data is:

[0094]

[0095] Among them, Ar i ,Sa i ,At i ,Re i These are the four-component data of sample residual oil.

[0096] The four-component characteristic vector of sample residue oil is used Establish m initial linear regression models and initial logistic regression models, use the initial linear regression model to predict the sample continuous performance characteristic vector of the sample asphalt product, and use the initial logistic regression model to predict the sample discrete performance characteristic vector of the sample asphalt product. As a new feature vector, add it to the sample production feature vector The sample amplification feature vector is obtained

[0097] Based on any of the above embodiments, the method further includes:

[0098] When the sample performance feature vector is a continuous sample performance feature vector, the base learner of the asphalt product performance prediction model is constructed based on the classification and regression tree;

[0099] When the sample performance feature vector is a discrete sample performance feature vector, the base learner of the asphalt product performance prediction model is constructed based on a multi-classification regression tree, and the multi-classification regression tree uses Softmax as the objective function.

[0100] In some specific embodiments, when the sample performance feature vector is a continuous sample performance feature vector, the base learner of the asphalt product performance prediction model adopts conventional classification and regression tree construction (CART), the training target is regression, and the loss function is mean square error (MSE). Optionally, the asphalt product performance prediction model can be a boosted tree model.

[0101] When the sample performance feature vector is a discrete sample performance feature vector, the base learner of the asphalt product performance prediction model uses Softmax as the objective function of the multi-classification regression tree, and its judgment form is as follows:

[0102]

[0103] Among them, z i is the output of the classification tree, Softmax(z i ) represents the probability that the sample belongs to the i-th category.

[0104] Among them, the gradient boosting decision tree model with second-order Taylor expansion and regularization control is used in modeling The objective function consists of two parts: the loss function and the regularization term. The second-order Taylor expansion removes the constant term and optimizes the loss function term; the regularization term is expanded, the constant term is removed, and the regularization term is optimized; the coefficients of the first-order term and the second-order term are combined to obtain the final objective function. 85% of the sample amplification feature vectors are randomly divided into a training set and 15% into a validation set. The asphalt product performance prediction model is trained using the training set, and the effect of the asphalt product performance prediction model is observed on the validation set to control the model depth and prevent overfitting.

[0105] It can be understood that when determining the sample prediction performance feature vector, an independent regression model can be trained according to the performance indicators of each type of asphalt product, and the form of each regression model is fixed to input an n-dimensional feature vector and output 1 sample prediction performance feature vector.

[0106] Based on any of the above embodiments, the present invention also provides a method for predicting asphalt product performance, such as Figure 2 As shown, the method includes:

[0107] Step 210, determining the target residual oil four-component characteristic vector of the target asphalt product;

[0108] Step 220, inputting the target residual oil four-component characteristic vector into the initial regression model to obtain the target prediction performance characteristic vector output by the initial regression model;

[0109] Step 230, concatenating the crude oil component feature vector of the target asphalt product and the target prediction performance feature vector to obtain a target amplified feature vector;

[0110] Step 240: input the target amplified feature vector into the asphalt product performance prediction model to obtain the performance prediction result of the target asphalt product output by the asphalt product performance prediction model;

[0111] Among them, the asphalt product performance prediction model is determined based on the asphalt product performance prediction model construction method described in any of the above embodiments.

[0112] Here, the target asphalt product is the asphalt product for which performance prediction is required.

[0113] In some specific embodiments, the target residue oil four-component feature vector of the target asphalt product is determined with reference to the above method for determining the sample residue oil four-component feature vector. The target residue oil four-component feature vector is input into the initial regression model to obtain the target predicted performance feature vector output by the initial regression model. Among them, the target predicted performance feature vector includes a target continuous performance feature vector and a target discrete performance feature. The target continuous performance feature vector refers to a performance vector represented by a value range, and the target discrete performance feature vector refers to a performance vector represented by a discrete value. The initial regression model includes an initial linear regression model and an initial logistic regression model. The initial linear regression model is used to predict the target continuous performance feature vector, and the initial logistic regression model is used to predict the target discrete performance feature vector.

[0114] After obtaining the target prediction performance characteristic vector, the crude oil component characteristic vector of the target asphalt product is concatenated with the target prediction performance characteristic vector to obtain the target amplified characteristic vector, which can then be input into the asphalt product performance prediction model to obtain the performance prediction result of the target asphalt product output by the asphalt product performance prediction model.

[0115] Based on any of the above embodiments, the present invention also provides a method for predicting asphalt product performance, such as Figure 3 As shown, the method includes:

[0116] First, the historical production data of the sample asphalt products is obtained, and the characteristic vectors of different sample crude oil components corresponding to the sample asphalt products and the sample performance characteristic vectors of the sample asphalt products are extracted from the historical production data, and the characteristic vectors of different sample crude oil components and the sample performance characteristic vectors are concatenated to obtain the sample production characteristic vector.

[0117] The four-component feature vector of the sample residual oil in the sample production feature vector is extracted, and the four-component feature vector of the sample residual oil is input into the initial regression model to obtain the sample prediction performance feature vector output by the initial regression model.

[0118] The sample production feature vector and the sample prediction performance feature vector are spliced ​​to obtain the sample amplification feature vector, and based on the sample amplification feature vector, an asphalt product performance prediction model is trained.

[0119] After training to obtain the product performance prediction model, the target residue oil four-component feature vector of the target asphalt product is determined by referring to the above method for determining the sample residue oil four-component feature vector. The target residue oil four-component feature vector is input into the initial regression model to obtain the target prediction performance feature vector output by the initial regression model; the crude oil component feature vector of the target asphalt product is concatenated with the target prediction performance feature vector to obtain the target amplified feature vector; the target amplified feature vector is input into the asphalt product performance prediction model to obtain the performance prediction result of the target asphalt product output by the asphalt product performance prediction model.

[0120] The asphalt product performance prediction model construction device provided by the present invention is described below. The asphalt product performance prediction model construction device described below and the asphalt product performance prediction model construction method described above can be referenced to each other.

[0121] Based on any of the above embodiments, the present invention also provides a device for constructing an asphalt product performance prediction model, such as Figure 4 As shown, the device comprises:

[0122] A first determining unit 410 is used to determine a sample production feature vector of a sample asphalt product, wherein the sample production feature vector includes feature vectors of different sample crude oil components corresponding to the sample asphalt product and a sample performance feature vector of the sample asphalt product;

[0123] The first prediction unit 420 is used to extract the sample residual oil four-component feature vector from the sample production feature vector, and input the sample residual oil four-component feature vector into the initial regression model to obtain the sample prediction performance feature vector output by the initial regression model;

[0124] The model building unit 430 is used to concatenate the sample production feature vector and the sample prediction performance feature vector to obtain a sample amplification feature vector, and train an asphalt product performance prediction model based on the sample amplification feature vector.

[0125] The asphalt product performance prediction device provided by the present invention is described below. The asphalt product performance prediction device described below and the asphalt product performance prediction method described above can be referenced to each other.

[0126] Based on any of the above embodiments, the present invention also provides an asphalt product performance prediction device, such as Figure 5 As shown, the device comprises:

[0127] The second determination unit 510 is used to determine the target residual oil four-component characteristic vector of the target asphalt product;

[0128] The second prediction unit 520 is used to input the target residual oil four-component feature vector into the initial regression model to obtain the target prediction performance feature vector output by the initial regression model;

[0129] A vector concatenation unit 530 is used to concatenate the crude oil component feature vector of the target asphalt product with the target prediction performance feature vector to obtain a target amplified feature vector;

[0130] The performance prediction unit 540 is used to input the target amplified feature vector into the asphalt product performance prediction model to obtain the performance prediction result of the target asphalt product output by the asphalt product performance prediction model;

[0131] Wherein, the asphalt product performance prediction model is determined based on the asphalt product performance prediction model construction method described in any of the above embodiments.

[0132] Figure 6 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 6 As shown, the electronic device may include: a processor 610, a memory 620, a communications interface 630 and a communications bus 640, wherein the processor 610, the memory 620 and the communications interface 630 communicate with each other through the communications bus 640. The processor 610 may call the logic instructions in the memory 620 to execute the method for constructing the asphalt product performance prediction model, the method comprising: determining the sample production feature vector of the sample asphalt product, the sample production feature vector comprising the feature vectors of different sample crude oil components corresponding to the sample asphalt product and the sample performance feature vector of the sample asphalt product; extracting the sample residual oil four-component feature vector from the sample production feature vector, and inputting the sample residual oil four-component feature vector into the initial regression model to obtain the sample prediction performance feature vector output by the initial regression model; splicing the sample production feature vector and the sample prediction performance feature vector to obtain the sample amplification feature vector, and training the asphalt product performance prediction model based on the sample amplification feature vector.

[0133] Or, execute an asphalt product performance prediction method, the method comprising: determining a target residual oil four-component feature vector of a target asphalt product; inputting the target residual oil four-component feature vector into an initial regression model to obtain a target prediction performance feature vector output by the initial regression model; concatenating the crude oil component feature vector of the target asphalt product with the target prediction performance feature vector to obtain a target amplified feature vector; inputting the target amplified feature vector into an asphalt product performance prediction model to obtain a performance prediction result of the target asphalt product output by the asphalt product performance prediction model; wherein the asphalt product performance prediction model is determined based on the asphalt product performance prediction model construction method as described above.

[0134] In addition, the logic instructions in the above-mentioned memory 620 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0135] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the asphalt product performance prediction model construction method provided by the above methods, and the method includes: determining a sample production feature vector of a sample asphalt product, the sample production feature vector includes feature vectors of different sample crude oil components corresponding to the sample asphalt product and a sample performance feature vector of the sample asphalt product; extracting a sample residual oil four-component feature vector from the sample production feature vector, and inputting the sample residual oil four-component feature vector into an initial regression model to obtain a sample prediction performance feature vector output by the initial regression model; splicing the sample production feature vector and the sample prediction performance feature vector to obtain a sample amplification feature vector, and based on the sample amplification feature vector, training an asphalt product performance prediction model.

[0136] Or, execute an asphalt product performance prediction method, the method comprising: determining a target residual oil four-component feature vector of a target asphalt product; inputting the target residual oil four-component feature vector into an initial regression model to obtain a target prediction performance feature vector output by the initial regression model; concatenating the crude oil component feature vector of the target asphalt product with the target prediction performance feature vector to obtain a target amplified feature vector; inputting the target amplified feature vector into an asphalt product performance prediction model to obtain a performance prediction result of the target asphalt product output by the asphalt product performance prediction model; wherein the asphalt product performance prediction model is determined based on the asphalt product performance prediction model construction method as described above.

[0137] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the above-mentioned asphalt product performance prediction model construction method, the method comprising: determining a sample production feature vector of a sample asphalt product, the sample production feature vector comprising feature vectors of different sample crude oil components corresponding to the sample asphalt product and a sample performance feature vector of the sample asphalt product; extracting a sample residual oil four-component feature vector from the sample production feature vector, and inputting the sample residual oil four-component feature vector into an initial regression model to obtain a sample prediction performance feature vector output by the initial regression model; concatenating the sample production feature vector and the sample prediction performance feature vector to obtain a sample amplification feature vector, and based on the sample amplification feature vector, training an asphalt product performance prediction model.

[0138] Or, execute an asphalt product performance prediction method, the method comprising: determining a target residual oil four-component feature vector of a target asphalt product; inputting the target residual oil four-component feature vector into an initial regression model to obtain a target prediction performance feature vector output by the initial regression model; concatenating the crude oil component feature vector of the target asphalt product with the target prediction performance feature vector to obtain a target amplified feature vector; inputting the target amplified feature vector into an asphalt product performance prediction model to obtain a performance prediction result of the target asphalt product output by the asphalt product performance prediction model; wherein the asphalt product performance prediction model is determined based on the asphalt product performance prediction model construction method as described above.

[0139] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0140] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0141] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical feature vectors therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing an asphalt product performance prediction model, characterized in that: include: Determine a sample production feature vector of a sample asphalt product, wherein the sample production feature vector includes feature vectors of different sample crude oil components corresponding to the sample asphalt product and a sample performance feature vector of the sample asphalt product; Extracting a sample residual oil four-component feature vector from the sample production feature vector, and inputting the sample residual oil four-component feature vector into an initial regression model to obtain a sample prediction performance feature vector output by the initial regression model; The sample production feature vector and the sample prediction performance feature vector are spliced ​​to obtain a sample amplification feature vector, and based on the sample amplification feature vector, an asphalt product performance prediction model is trained.

2. The method for constructing an asphalt product performance prediction model according to claim 1, characterized in that: The step of determining a sample production feature vector of a sample asphalt product comprises: Determine the characteristic vectors of different sample crude oil components of the sample bitumen product; According to the preset mixed oil weight, the characteristic vectors of the crude oil components of each sample are weighted and added to obtain the sample combination characteristic vector; The sample combination feature vector and the sample performance feature vector are concatenated to obtain the sample production feature vector.

3. The method for constructing an asphalt product performance prediction model according to claim 1, characterized in that: Also includes: When the performance index corresponding to any sample performance characteristic vector is a range index, the corresponding sample performance characteristic vector is represented in the form of a discrete variable; In the case that any sample crude oil component characteristic vector is missing, the average value of the remaining sample crude oil component characteristic vectors in the column where the missing sample crude oil component characteristic vector is located is used as the missing sample crude oil component characteristic vector; When the performance index corresponding to any sample performance characteristic vector exceeds the instrument range, the maximum value of the column where the corresponding sample performance characteristic vector is located is used as the corresponding sample performance characteristic vector; In the event that any sample performance feature vector is missing, the row position of the missing sample performance feature vector is identified, and before training the asphalt product performance prediction model, the data corresponding to the row position is deleted.

4. The method for constructing an asphalt product performance prediction model according to claim 1, characterized in that: The initial regression model includes an initial linear regression model and an initial logistic regression model, and the sample prediction performance feature vector includes a sample continuous performance feature vector and a sample discrete performance feature vector; The step of inputting the four-component feature vector of the sample residual oil into the initial regression model to obtain the sample prediction performance feature vector output by the initial regression model includes: Inputting the four-component characteristic vector of the sample residual oil into the initial linear regression model to obtain the sample continuous performance characteristic vector output by the initial linear regression model; The four-component characteristic vector of the sample residual oil is input into the initial logistic regression model to obtain the sample discrete performance characteristic vector output by the initial logistic regression model.

5. The method for constructing an asphalt product performance prediction model according to claim 1, characterized in that: Also includes: In the case where the sample performance feature vector is a continuous sample performance feature vector, the base learner of the asphalt product performance prediction model is constructed based on a classification and regression tree; In the case where the sample performance feature vector is a discrete sample performance feature vector, the base learner of the asphalt product performance prediction model is constructed based on a multi-classification regression tree, and the multi-classification regression tree uses Softmax as the objective function.

6. A method for predicting asphalt product performance, characterized in that: include: Determine the target residue oil four-component characteristic vector of the target asphalt product; Inputting the target residual oil four-component characteristic vector into the initial regression model to obtain the target prediction performance characteristic vector output by the initial regression model; splicing the crude oil component feature vector of the target asphalt product and the target prediction performance feature vector to obtain a target amplified feature vector; Inputting the target amplified feature vector into an asphalt product performance prediction model to obtain a performance prediction result of the target asphalt product output by the asphalt product performance prediction model; Wherein, the asphalt product performance prediction model is determined based on the asphalt product performance prediction model construction method described in any one of claims 1 to 5.

7. A device for constructing an asphalt product performance prediction model, characterized in that: include: A first determining unit is used to determine a sample production feature vector of a sample asphalt product, wherein the sample production feature vector includes feature vectors of different sample crude oil components corresponding to the sample asphalt product and a sample performance feature vector of the sample asphalt product; A first prediction unit is used to extract a sample residual oil four-component feature vector from the sample production feature vector, and input the sample residual oil four-component feature vector into an initial regression model to obtain a sample prediction performance feature vector output by the initial regression model; The model building unit is used to splice the sample production feature vector and the sample prediction performance feature vector to obtain a sample amplification feature vector, and train an asphalt product performance prediction model based on the sample amplification feature vector.

8. An asphalt product performance prediction device, characterized in that: include: The second determination unit is used to determine the target residual oil four-component characteristic vector of the target asphalt product; A second prediction unit is used to input the target residual oil four-component feature vector into the initial regression model to obtain the target prediction performance feature vector output by the initial regression model; A vector concatenation unit, used for concatenating the crude oil component feature vector of the target asphalt product with the target prediction performance feature vector to obtain a target amplified feature vector; A performance prediction unit, used for inputting the target amplified feature vector into an asphalt product performance prediction model to obtain a performance prediction result of the target asphalt product output by the asphalt product performance prediction model; Wherein, the asphalt product performance prediction model is determined based on the asphalt product performance prediction model construction method described in any one of claims 1 to 5.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, it implements the asphalt product performance prediction model construction method as described in any one of claims 1 to 5, or when the processor executes the program, it implements the asphalt product performance prediction method as described in claim 6.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the method for constructing an asphalt product performance prediction model as described in any one of claims 1 to 5, or when the computer program is executed by a processor, it implements the method for predicting asphalt product performance as described in claim 6.

Citation Information

Patent Citations

  • Double-mapping learning compressed face image restoration method based on regression tree classification

    CN110852962A

  • Rubber asphalt compatibility evaluation method based on multivariable regression analysis

    CN115728185A

  • Asphalt emulsion formulation tool

    US20180348189A1