Method, device, and storage medium for predicting and analyzing properties of raw oil

Abstract

The application discloses a raw oil property prediction and analysis method, device, equipment and a storage medium, and comprises the following steps: generating a raw oil standard comparison model in the form of a vector matrix according to a property data sample set comprising property data of a large number of crude oil samples; each sample vector group in the vector matrix comprises vector elements including distillation point, equivalent double bond value and property data; when performing property analysis and prediction on the crude oil to be analyzed, a vector group comprising vector elements of distillation point and equivalent double bond value is generated according to the crude distillation point temperature data in the simple evaluation report and the carbon, hydrogen and nitrogen element content and the mixture molecular mass data under the corresponding distillation point; then, the corresponding similar sample is determined through the raw oil standard comparison model by means of Euclidean distance calculation, and the property data of the crude oil to be analyzed is predicted; and the application can greatly improve the detection and analysis efficiency, thereby improving the timeliness of oil product detection.

Description

Technical Field

[0001] This invention relates to the field of oil refining and chemical technology, and in particular to methods, apparatus, equipment and storage media for predicting and analyzing the physical properties of feedstock oils. Background Technology

[0002] Crude oil is a complex mixture, and the various trace elements it contains can cause a series of problems during the petroleum refining process, such as catalyst deactivation, reactor coking, and corrosion. Furthermore, when planning production and optimizing processes, accurate physical property parameters and models will bring higher sales revenue and a more stable production process to enterprises. Therefore, the analysis and testing of oil products is of paramount importance.

[0003] Currently, the main analytical methods for crude oil include chromatography, mass spectrometry, nuclear magnetic resonance, and infrared spectroscopy. Physical methods such as irradiating the oil sample with radiation to generate spectra or chromatograms are used to perform qualitative and quantitative analysis of the oil sample, or chemical methods such as chemical titration and colorimetry are used.

[0004] The inventors discovered through research that existing methods typically require a series of complex and cumbersome processes such as sample pretreatment, sample testing, and detection analysis, which makes the oil testing process too time-consuming and thus has poor timeliness.

[0005] The information disclosed in this background section is intended only to enhance the understanding of the overall background of the invention and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to improve the timeliness of oil product testing.

[0007] This invention provides a method for predicting and analyzing the physical properties of crude oil, comprising the following steps:

[0008] S11. A preset physical property data sample set includes physical property data of multiple crude oil samples;

[0009] S12. Generate sample vector groups corresponding to each type of feedstock sample in the crude oil physical property data sample set. Each vector element of the sample vector group includes the distillation range point, equivalent double bond value, and physical property data. Generate a vector matrix as a standard comparison model for feedstock based on each vector group.

[0010] S13. Based on the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture corresponding to each distillation point in the crude oil temperature data to be analyzed, a corresponding distribution curve is generated by polynomial fitting; the horizontal axis of the distribution curve is the distillation point, and the vertical axis is the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture.

[0011] S14. Determine the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture corresponding to each distillation point that is consistent with the sample vector group based on the distribution curve.

[0012] S15. Calculate the equivalent double bond values ​​corresponding to each distillation point that is consistent with the sample vector group, and generate the comparison vector group of the feedstock oil to be analyzed: the vector elements of the comparison vector group include distillation points and equivalent double bond values.

[0013] S16. Perform Euclidean distance calculation on the comparison vector group and the raw material oil standard comparison model to generate a sorting result with increasing distance;

[0014] S17. Based on the sorting results, similar vector elements are determined from the standard comparison model of the raw oil, and the corresponding physical property data are determined as the analysis results based on the vector group corresponding to the similar vector elements.

[0015] Preferably, in this invention, the sample vector group comprises n vector elements, and the number of vector elements is consistent with the number of distillation range points in the sample vector group;

[0016] The sample vector group includes: {(T1,D1,P1),(T2,D2,P2),...,(T n D n ,P n )}, where T is the distillation range point, including n; D is the equivalent double bond value; P is the physical property data; n is the number of vector elements in the sample vector group;

[0017] The vector matrix used as the standard comparison model for crude oil includes:

[0018]

[0019] Where m is the total number of the types of raw material oil samples;

[0020] The alignment vector group includes: {(T1,D1),(T2,D2),...,(T...} n D n )}; where T is the distillation point; D is the equivalent double bond value.

[0021] Preferably, in this invention, the equivalent double bond value is the sum of the number of rings and the number of double bonds in the molecule, and the formula for calculating the equivalent double bond DBE includes:

[0022]

[0023] Where c, h, and n represent the number of carbon, hydrogen, and nitrogen atoms in the crude oil mixture, respectively.

[0024] Preferably, in this invention, calculating the equivalent double bond values ​​corresponding to each distillation point consistent with the sample vector group includes:

[0025] Based on the distribution curve, the carbon, hydrogen, and nitrogen contents and the molecular weight of the mixture at each distillation point are read, and the number of carbon, hydrogen, and nitrogen atoms in the feedstock mixture is calculated according to formula (2):

[0026]

[0027] Where, x n y n z n They are respectively the Tth n The distillation range point corresponds to the number of carbon, hydrogen, and nitrogen atoms in the crude oil molecule formula. A n B n C n They are respectively the Tth n The elemental content of carbon, hydrogen, and nitrogen in crude oil corresponding to the distillation range point, M n For the Tth n The molecular weight of the feed oil mixture corresponding to the distillation range point;

[0028] After calculating the number of carbon, hydrogen, and nitrogen atoms according to formula (2), calculate the number of atoms in T according to formula (1). n The equivalent double bond value corresponding to the distillation range point.

[0029] Preferably, in this invention, the step of calculating the Euclidean distance between the comparison vector group and the raw material oil standard comparison model to generate a sorting result with increasing distance includes:

[0030] The Euclidean distance calculation formula includes:

[0031]

[0032] Where, d ij Let T be the distance between the i-th test sample and the j-th similar sample in the standard model. Bi T Aj D represents the temperature at point i of the sample to be tested and the temperature of the similar sample at point j in the standard model, respectively. Bi D Aj These are the equivalent double bond value at point i of the sample to be tested and the equivalent double bond value of the similar sample at point j in the standard model, respectively.

[0033] Preferably, in this invention, the step of determining similar vector elements from the raw oil standard comparison model based on the sorting results, and determining the corresponding physical property data as the analysis result based on the vector group corresponding to the similar vector elements, includes:

[0034] S21. Select K vector elements with the smallest distance to perform weighted probability calculation; the formula for calculating the weighted probability is shown in formula (4):

[0035]

[0036] Among them, f ij Let d be the weighted distance probability between the i-th test sample and the j-th similar sample in the standard model. ij Let be the distance between the i-th test sample and the j-th similar sample in the standard model, and k be the number of sample points with the smallest distance selected.

[0037] S22. Using distance-weighted probability calculation, taking the comparison vector group as the center, calculate the similarity between k minimum distance points and the comparison vector group, forming a similarity probability matrix f. i ={f k1 ,f k2 ,...,f k}, and the sum of all probabilities in the similarity probability matrix is ​​1;

[0038] S23. Traverse k minimum distance points and determine whether all probabilities in the weighted probability matrix are greater than P. K If not, decrement the k samples by 1 and return to step S21; if yes, use the similarity probability matrix as a weighted probability matrix.

[0039] S24. Multiply the weighted probabilities of the k similarity point vector elements in the weighted probability matrix with the physical properties of the corresponding similarity point vector elements in the crude oil standard comparison model, and sum the calculation results to obtain the physical property data of the crude oil to be analyzed; the formula for calculating the physical property multiplication includes:

[0040]

[0041] Where P represents the physical property data of the crude oil to be analyzed, and f i P is the weighted probability of the vector elements of the i-th similar sample point. i This refers to the physical property data of the vector element of the i-th similar sample point in the standard comparison model of crude oil.

[0042] In another aspect of the present invention, a feedstock oil property prediction and analysis device is also provided, comprising:

[0043] The sample set generation unit is used to pre-set a physical property data sample set that includes physical property data of multiple crude oil samples;

[0044] The model generation unit is used to generate sample vector groups corresponding to each type of feedstock sample in the crude oil physical property data sample set. Each vector element of the sample vector group includes the distillation range point, equivalent double bond value, and physical property data. Based on each vector group, a vector matrix is ​​generated as a feedstock standard comparison model.

[0045] The curve generation unit is used to generate corresponding distribution curves based on the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture corresponding to each distillation point in the crude oil temperature data. The horizontal axis of the distribution curve is the flow point, and the vertical axis is the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture.

[0046] The process point corresponding unit is used to determine the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture corresponding to each distillation point that is consistent with the sample vector group, based on the distribution curve.

[0047] An equivalent double bond calculation unit is used to calculate the equivalent double bond value corresponding to each distillation point that is consistent with the sample vector group, and generate a comparison vector group of the feedstock oil to be analyzed: the vector elements of the comparison vector group include distillation point and equivalent double bond value.

[0048] The Euclidean distance sorting unit is used to calculate the Euclidean distance between the comparison vector group and the raw oil standard comparison model, and generate a sorting result with increasing distance.

[0049] The result generation unit is used to determine similar vector elements from the raw oil standard comparison model based on the sorting results, and to determine the corresponding physical property data as the analysis results based on the vector group corresponding to the similar vector elements.

[0050] Preferably, in this invention, the sample vector group comprises n vector elements, and the number of vector elements is consistent with the number of process points in the sample vector group;

[0051] The sample vector group includes: {(T1,D1,P1),(T2,D2,P2),...,(T n D n ,P n )}, where T is the distillation range point, including n; D is the equivalent double bond value; P is the physical property data; n is the number of vector elements in the sample vector group;

[0052] The vector matrix used as the standard comparison model for crude oil includes:

[0053]

[0054] Where m is the total number of the types of raw material oil samples;

[0055] The alignment vector group includes: {(T1,D1),(T2,D2),...,(T...} n D n )}; where T is the distillation point; D is the equivalent double bond value.

[0056] Preferably, in this invention, the equivalent double bond value is the sum of the number of rings and the number of double bonds in the molecule, and the formula for calculating the equivalent double bond DBE includes:

[0057]

[0058] Where c, h, and n represent the number of carbon, hydrogen, and nitrogen atoms in the crude oil mixture, respectively.

[0059] Preferably, in this invention, calculating the equivalent double bond values ​​corresponding to each distillation point consistent with the sample vector group includes:

[0060] Based on the distribution curve, the carbon, hydrogen, and nitrogen contents and the molecular weight of the mixture at each distillation point are read, and the number of carbon, hydrogen, and nitrogen atoms in the feedstock mixture is calculated according to formula (2):

[0061]

[0062] Where, x n y n z n They are respectively the Tth n The distillation range point corresponds to the number of carbon, hydrogen, and nitrogen atoms in the crude oil molecule formula. A n B n C n They are respectively the Tth n The elemental content of carbon, hydrogen, and nitrogen in crude oil corresponding to the distillation range point, M n For the Tth n The molecular weight of the feed oil mixture corresponding to the distillation range point;

[0063] After calculating the number of carbon, hydrogen, and nitrogen atoms according to formula (2), calculate the number of atoms in T according to formula (1). n The equivalent double bond value corresponding to the distillation range point.

[0064] Preferably, in this invention, the step of calculating the Euclidean distance between the comparison vector group and the raw material oil standard comparison model to generate a sorting result with increasing distance includes:

[0065] The Euclidean distance calculation formula includes:

[0066]

[0067] Where, d ijLet T be the distance between the i-th test sample and the j-th similar sample in the standard model. Bi T Aj D represents the temperature at point i of the sample to be tested and the temperature of the similar sample at point j in the standard model, respectively. Bi D Aj These are the equivalent double bond value at point i of the sample to be tested and the equivalent double bond value of the similar sample at point j in the standard model, respectively.

[0068] Preferably, in this invention, the result generation unit includes:

[0069] The first calculation module is used to select K vector elements with the smallest distance for weighted probability calculation; the formula for calculating the weighted probability is shown in formula (4):

[0070]

[0071] Among them, f ij Let d be the weighted distance probability between the i-th test sample and the j-th similar sample in the standard model. ij Let be the distance between the i-th test sample and the j-th similar sample in the standard model, and k be the number of sample points with the smallest distance selected.

[0072] The second calculation module is used to calculate the similarity between the k minimum distance points and the comparison vector group, centered on the comparison vector group, through distance-weighted probability calculation, and form a similarity probability matrix f. i ={f k1 ,f k2 ,...,f k}, and the sum of all probabilities in the similarity probability matrix is ​​1;

[0073] The third calculation module is used to traverse k minimum distance points and determine whether all probabilities in the weighted probability matrix are greater than P. K If not, decrement the k samples by 1 and return to step S21; if yes, use the similarity probability matrix as a weighted probability matrix.

[0074] The fourth calculation module is used to multiply the weighted probabilities of the k similarity point vector elements in the weighted probability matrix with the physical properties of the corresponding similarity point vector elements in the crude oil standard comparison model, and sum the calculation results to obtain the physical property data of the crude oil to be analyzed; the physical property multiplication calculation formula includes:

[0075]

[0076] Where P represents the physical property data of the crude oil to be analyzed, and f i P is the weighted probability of the vector elements of the i-th similar sample point. iThis refers to the physical property data of the vector element of the i-th similar sample point in the standard comparison model of crude oil.

[0077] In another aspect of this invention, a feedstock oil property prediction and analysis device is also provided, comprising:

[0078] Memory, used to store computer programs;

[0079] A processor is used to invoke and execute the computer program to implement the various steps of the feedstock property prediction and analysis method as described in any of the preceding claims.

[0080] In another aspect of the present invention, a storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the various steps of the feedstock oil property prediction and analysis method as described in any of the preceding claims.

[0081] The feedstock oil property prediction and analysis device includes a computer program stored on a medium. The computer program includes program instructions. When the program instructions are executed by the computer, the computer performs the methods described in the above aspects and achieves the same technical effect.

[0082] Compared with the prior art, the present invention has the following beneficial effects:

[0083] As can be seen from the above scheme, the feedstock property prediction and analysis method, apparatus, equipment, and storage medium provided by the present invention generate a feedstock standard comparison model in the form of a vector matrix based on a sample set of property data including a large number of crude oil samples. The vector elements of each sample vector group in the vector matrix include distillation range point, equivalent double bond value, and property data. Thus, when performing property analysis and prediction on the crude oil to be analyzed, a vector group including distillation range point and equivalent double bond value can be generated based on the crude distillation range point temperature data and the carbon, hydrogen, and nitrogen content and molecular weight data of the feedstock mixture at the corresponding distillation range point in its brief review report. Then, by calculating the Euclidean distance, the corresponding similar samples are determined through the feedstock standard comparison model, thereby predicting the property data of the crude oil to be analyzed.

[0084] Since the physical property analysis in this invention no longer requires the oil product testing process, but only needs to calculate and predict its physical property data based on the data in the brief evaluation report of the crude oil to be analyzed, it can greatly improve the efficiency of testing and analysis, thereby improving the timeliness of oil product testing.

[0085] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it according to the contents of the specification, and to make the above and other objects, technical features and advantages of the present invention easier to understand, one or more preferred embodiments are listed below and described in detail with reference to the accompanying drawings. Attached Figure Description

[0086] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0087] Figure 1 This is a flowchart illustrating the steps of the method for predicting and analyzing the physical properties of raw oil described in this invention;

[0088] Figure 2 This is a schematic diagram of the structure of the feedstock oil property prediction and analysis device described in this invention;

[0089] Figure 3 This is a schematic diagram of the structure of the feedstock oil property prediction and analysis equipment described in this invention. Detailed Implementation

[0090] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings, but it should be understood that the scope of protection of the present invention is not limited to the specific embodiments.

[0091] Unless otherwise expressly stated, throughout the specification and claims, the term "comprising" or its variations such as "including" or "comprises" shall be understood to include the stated elements or components without excluding other elements or other components.

[0092] In this document, the terms "first," "second," etc., are used to distinguish two different elements or parts, and are not used to define specific positions or relative relationships. In other words, in some embodiments, the terms "first," "second," etc., can also be used interchangeably.

[0093] Example 1

[0094] To improve the timeliness of oil physical property analysis and testing, such as Figure 1 As shown, this embodiment of the invention provides a method for predicting and analyzing the physical properties of feedstock oil, including the following steps:

[0095] S11. A preset physical property data sample set includes physical property data of multiple crude oil samples;

[0096] In practical applications, a database of feedstock properties can be established based on the various feedstock property data accumulated by existing refining and chemical enterprises to generate a sample set of property data; a large amount of feedstock distillation point, equivalent double bond value and property data can be obtained through experimental analysis and calculation.

[0097] In this embodiment of the invention, the equivalent double bond value is the sum of the number of rings and the number of double bonds in the molecule, which can reflect the degree of condensation and structure of the molecule. The specific formula for calculating the equivalent double bond DBE can be:

[0098]

[0099] Where c, h, and n represent the number of carbon, hydrogen, and nitrogen atoms in the crude oil mixture, respectively. For example, in the chemical formula C2H4N2, c, h, and n are equivalent to its subscripts 2, 4, and 2. Molecular weight data is necessary to determine the number of carbon, hydrogen, and nitrogen atoms; the specific order can be: first read the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture corresponding to the distillation point to obtain the number of carbon, hydrogen, and nitrogen atoms, and then calculate the equivalent double bond value according to formula (1).

[0100] S12. Generate sample vector groups corresponding to each type of feedstock sample in the crude oil physical property data sample set. Each vector element of the sample vector group includes the distillation range point, equivalent double bond value, and physical property data. Generate a vector matrix as a standard comparison model for feedstock based on each vector group.

[0101] Based on the distillation range, equivalent double bond value, and physical property data of each feedstock sample, multiple vector groups (sample vector groups) can be generated, with one sample vector group corresponding to each feedstock sample; then multiple sample vector groups can form a vector matrix.

[0102] Specifically, in this embodiment of the invention, the vector elements of the sample vector group may include n, and the number of vector elements is consistent with the number of process points in the sample vector group; the number n of vector elements in this embodiment of the invention corresponds to the number of process points; in practical applications, the process points in the sample vector group may include the initial boiling point, and multiple points such as the distillation rate of 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, and the final boiling point. The number of process points set in the sample vector group can affect the accuracy of the final analysis and prediction results of this embodiment of the invention. The more process points set, the higher the accuracy of the prediction and analysis results; at the same time, the more process points set, the more vector elements in the sample vector group. Specifically, the sample vector group in this embodiment of the invention may include: {(T1,D1,P1),(T2,D2,P2),...,(T n D n ,P n )}, where T is the distillation range point, including n; D is the equivalent double bond value; P is the physical property data; n is the number of vector elements in the sample vector group;

[0103] After determining the sample vector group for each type of crude oil sample (which can be denoted as m types of crude oil samples) in the crude oil physical property data sample set, a vector matrix can be further constructed as a standard comparison model for crude oils. Specifically, this may include:

[0104]

[0105] Where m is the total number of the types of raw material oil samples.

[0106] S13. Based on the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture corresponding to each distillation point in the crude oil temperature data, a corresponding distribution curve is generated by polynomial fitting; the horizontal axis of the distribution curve is the flow point, and the vertical axis is the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture.

[0107] In practical applications, it is possible to obtain a brief evaluation report of the crude oil to be analyzed. This brief evaluation report can generally include temperature data of the crude distillation range point and the carbon, hydrogen, and nitrogen content and molecular weight data of the feed oil mixture at the corresponding distillation range point.

[0108] By using the correlation between the temperature data of each distillation point in the crude distillation range and the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture, a corresponding distribution curve can be generated through polynomial fitting; the horizontal axis of the distribution curve represents the flow point, and the vertical axis represents the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture.

[0109] S14. Determine the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture corresponding to each distillation point that is consistent with the sample vector group based on the distribution curve.

[0110] The number of flow points in the crude distillation range is generally less than the number of flow points in the sample vector group. This results in a mismatch between the number of flow points and the number of flow points in the sample vector group. After generating the corresponding distribution curve, since the distribution curve is a continuous curve, the corresponding carbon, hydrogen, and nitrogen contents and the molecular weight of the mixture can be obtained from the position of each flow point in the sample vector group based on the curve.

[0111] S15. Calculate the equivalent double bond values ​​corresponding to each distillation point that is consistent with the sample vector group, and generate the comparison vector group of the feedstock oil to be analyzed: the vector elements of the comparison vector group include distillation points and equivalent double bond values.

[0112] After obtaining the carbon, hydrogen, and nitrogen contents and the molecular weight of the mixture corresponding to each process point in the sample vector group based on the distribution curve, the equivalent double bond value corresponding to each process point can be calculated; specifically, it can be:

[0113] Based on the distribution curve, the carbon, hydrogen, and nitrogen contents and the molecular weight of the mixture at each distillation point are read, and the number of carbon, hydrogen, and nitrogen atoms in the feedstock mixture is calculated according to formula (2):

[0114]

[0115] Where, x n y n z n They are respectively the Tth n The distillation range point corresponds to the number of carbon, hydrogen, and nitrogen atoms in the crude oil molecule formula. A n B n C n They are respectively the Tth n The elemental content of carbon, hydrogen, and nitrogen in crude oil corresponding to the distillation range point, M n For the Tth n The molecular weight of the feed oil mixture corresponding to the distillation range point;

[0116] After calculating the number of carbon, hydrogen, and nitrogen atoms according to formula (2), the number of atoms in T can be calculated according to formula (1). n The equivalent double bond value corresponding to the distillation range point.

[0117] In this way, for the crude oil to be analyzed, the equivalent double bond value corresponding to each process point can be obtained, and then the corresponding comparison vector group can be generated: the vector elements of the comparison vector group include the distillation range point and the equivalent double bond value.

[0118] Specifically, the alignment vector group can be represented as: {(T1,D1),(T2,D2),...,(T n D n )}; where T is the distillation range point, including n points; D is the equivalent double bond value.

[0119] S16. Perform Euclidean distance calculation on the comparison vector group and the raw material oil standard comparison model to generate a sorting result with increasing distance;

[0120] Specifically, the Euclidean distance calculation formula used in embodiments of the present invention may include:

[0121]

[0122] Where, d ij Let T be the distance between the i-th test sample and the j-th similar sample in the standard model. Bi T Aj D represents the temperature at point i of the sample to be tested and the temperature of the similar sample at point j in the standard model, respectively. Bi D AjThese are the equivalent double bond value at point i of the sample to be tested and the equivalent double bond value of the similar sample at point j in the standard model, respectively.

[0123] S17. Based on the sorting results, similar vector elements are determined from the standard comparison model of the raw oil, and the corresponding physical property data are determined as the analysis results based on the vector group corresponding to the similar vector elements.

[0124] The specific sub-steps of this step may include:

[0125] K vector elements with the smallest distance are selected for weighted probability calculation; the formula for calculating the weighted probability is shown in formula (4):

[0126]

[0127] Among them, f ij Let d be the weighted distance probability between the i-th test sample and the j-th similar sample in the standard model. ij Let be the distance between the i-th test sample and the j-th similar sample in the standard model, and k be the number of sample points with the smallest distance selected.

[0128] S22. Using distance-weighted probability calculation, taking the comparison vector group as the center, calculate the similarity between k minimum distance points and the comparison vector group, forming a similarity probability matrix f. i ={f k1 ,f k2 ,...,f k}, and the sum of all probabilities in the similarity probability matrix is ​​1;

[0129] S23. Traverse k minimum distance points and determine whether all probabilities in the weighted probability matrix are greater than P. K If not, decrement the k samples by 1 and return to step S21; if yes, use the similarity probability matrix as a weighted probability matrix.

[0130] S24. Multiply the weighted probabilities of the k similarity point vector elements in the weighted probability matrix with the physical properties of the corresponding similarity point vector elements in the crude oil standard comparison model, and sum the calculation results to obtain the physical property data of the crude oil to be analyzed; the formula for calculating the physical property multiplication includes:

[0131]

[0132] Where P represents the physical property data of the crude oil to be analyzed, and f i P is the weighted probability of the vector elements of the i-th similar sample point. i This refers to the physical property data of the vector element of the i-th similar sample point in the standard comparison model of crude oil.

[0133] In summary, the feedstock property prediction and analysis method, apparatus, equipment, and storage medium provided in this embodiment of the invention generate a feedstock standard comparison model in the form of a vector matrix based on a sample set of property data including a large number of crude oil samples. Each sample vector group in the vector matrix includes vector elements comprising distillation range, equivalent double bond value, and property data. Thus, when performing property analysis and prediction on the crude oil to be analyzed, a vector group comprising distillation range and equivalent double bond value can be generated based on the crude distillation range temperature data and the carbon, hydrogen, and nitrogen content and molecular weight data of the feedstock mixture at the corresponding distillation range in its brief review report. Then, through Euclidean distance calculation, the corresponding similar samples are determined using the feedstock standard comparison model, thereby predicting the property data of the crude oil to be analyzed.

[0134] Since the physical property analysis in this invention no longer requires the oil product testing process, but only needs to calculate and predict its physical property data based on the data in the brief evaluation report of the crude oil to be analyzed, it can greatly improve the efficiency of detection and analysis, thereby improving the timeliness of oil product physical property analysis and detection.

[0135] Example 2

[0136] Corresponding to the method embodiment, another aspect of the present invention provides a feedstock oil property prediction and analysis device. Figure 3 This diagram illustrates the structure of a feedstock oil property prediction and analysis device provided in an embodiment of the present invention. The feedstock oil property prediction and analysis device is... Figure 1 The device corresponding to the feedstock oil property prediction and analysis method described in the corresponding embodiment is implemented through a virtual device. Figure 1 In the corresponding embodiment of the crude oil property prediction and analysis method, the various virtual modules constituting the crude oil property prediction and analysis device can be executed by electronic devices, such as network devices, terminal devices, or servers. Specifically, the crude oil property prediction and analysis device in this embodiment of the invention includes:

[0137] The feedstock oil property prediction and analysis device in this embodiment of the invention includes:

[0138] Sample set generation unit 01 is used to preset a physical property data sample set that includes physical property data of multiple crude oil samples;

[0139] In practical applications, a database of feedstock properties can be established based on the various feedstock property data accumulated by existing refining and chemical enterprises to generate a sample set of property data; a large amount of feedstock distillation point, equivalent double bond value and property data can be obtained through experimental analysis and calculation.

[0140] In this embodiment of the invention, the equivalent double bond value is the sum of the number of rings and the number of double bonds in the molecule, which can reflect the degree of condensation and structure of the molecule. The specific formula for calculating the equivalent double bond DBE can be:

[0141]

[0142] Where c, h, and n represent the number of carbon, hydrogen, and nitrogen atoms in the crude oil mixture, respectively. For example, in the chemical formula C2H4N2, c, h, and n are equivalent to its subscripts 2, 4, and 2. Molecular weight data is necessary to determine the number of carbon, hydrogen, and nitrogen atoms; the specific order can be: first read the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture corresponding to the distillation point to obtain the number of carbon, hydrogen, and nitrogen atoms, and then calculate the equivalent double bond value according to formula (1).

[0143] Model generation unit 02 is used to generate sample vector groups corresponding to each type of crude oil sample in the crude oil physical property data sample set. Each vector element of the sample vector group includes the distillation range point, equivalent double bond value and physical property data. A vector matrix is ​​generated as a standard comparison model for crude oil based on each vector group.

[0144] Based on the distillation range, equivalent double bond value, and physical property data of each feedstock sample, multiple vector groups (sample vector groups) can be generated, with one sample vector group corresponding to each feedstock sample; then multiple sample vector groups can form a vector matrix.

[0145] Specifically, in this embodiment of the invention, the vector elements of the sample vector group may include n, and the number of vector elements is consistent with the number of process points in the sample vector group; the number n of vector elements in this embodiment of the invention corresponds to the number of process points; in practical applications, the process points in the sample vector group may include the initial boiling point, and multiple points such as the distillation rate of 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, and the final boiling point. The number of process points set in the sample vector group can affect the accuracy of the final analysis and prediction results of this embodiment of the invention. The more process points set, the higher the accuracy of the prediction and analysis results; at the same time, the more process points set, the more vector elements in the sample vector group. Specifically, the sample vector group in this embodiment of the invention may include: {(T1,D1,P1),(T2,D2,P2),...,(T n D n ,P n )}, where T is the distillation range point, including n; D is the equivalent double bond value; P is the physical property data; n is the number of vector elements in the sample vector group;

[0146] After determining the sample vector group for each type of crude oil sample (which can be denoted as m types of crude oil samples) in the crude oil physical property data sample set, a vector matrix can be further constructed as a standard comparison model for crude oils. Specifically, this may include:

[0147]

[0148] Where m is the total number of the types of raw material oil samples;

[0149] The curve generation unit 03 is used to generate a corresponding distribution curve based on the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture corresponding to each distillation point in the crude oil temperature data. The horizontal axis of the distribution curve is the flow point, and the vertical axis is the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture.

[0150] In practical applications, it is possible to obtain a brief evaluation report of the crude oil to be analyzed. This brief evaluation report can generally include temperature data of the crude distillation range point and the carbon, hydrogen, and nitrogen content and molecular weight data of the feed oil mixture at the corresponding distillation range point.

[0151] By using the correlation between the temperature data of each distillation point in the crude distillation range and the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture, a corresponding distribution curve can be generated through polynomial fitting; the horizontal axis of the distribution curve represents the flow point, and the vertical axis represents the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture.

[0152] Process point corresponding unit 04 is used to determine the carbon, hydrogen, nitrogen content and molecular weight of the mixture corresponding to each distillation point that is consistent with the sample vector group based on the distribution curve;

[0153] The number of flow points in the crude distillation range is generally less than the number of flow points in the sample vector group. This results in a mismatch between the number of flow points and the number of flow points in the sample vector group. After generating the corresponding distribution curve, since the distribution curve is a continuous curve, the corresponding carbon, hydrogen, and nitrogen contents and the molecular weight of the mixture can be obtained from the position of each flow point in the sample vector group based on the curve.

[0154] The equivalent double bond calculation unit 05 is used to calculate the equivalent double bond value corresponding to each distillation point that is consistent with the sample vector group, and generate the comparison vector group of the feedstock oil to be analyzed: the vector elements of the comparison vector group include the distillation point and the equivalent double bond value.

[0155] After obtaining the carbon, hydrogen, and nitrogen contents and the molecular weight of the mixture corresponding to each process point in the sample vector group based on the distribution curve, the equivalent double bond value corresponding to each process point can be calculated; specifically, it can be:

[0156] Based on the distribution curve, the carbon, hydrogen, and nitrogen contents and the molecular weight of the mixture at each distillation point are read, and the number of carbon, hydrogen, and nitrogen atoms in the feedstock mixture is calculated according to formula (2):

[0157]

[0158] Where, x n y n z n They are respectively the Tth n The distillation range point corresponds to the number of carbon, hydrogen, and nitrogen atoms in the crude oil molecule formula. A n B n C n They are respectively the Tth n The elemental content of carbon, hydrogen, and nitrogen in crude oil corresponding to the distillation range point, M n For the Tth n The molecular weight of the feed oil mixture corresponding to the distillation range point;

[0159] After calculating the number of carbon, hydrogen, and nitrogen atoms according to formula (2), the number of atoms in T can be calculated according to formula (1). n The equivalent double bond value corresponding to the distillation range point.

[0160] In this way, for the crude oil to be analyzed, the equivalent double bond value corresponding to each process point can be obtained, and then the corresponding comparison vector group can be generated: the vector elements of the comparison vector group include the distillation range point and the equivalent double bond value.

[0161] Specifically, the alignment vector group can be represented as: {(T1,D1),(T2,D2),...,(T n D n )}; where T is the distillation range point, including n points; D is the equivalent double bond value.

[0162] Euclidean distance sorting unit 06 is used to calculate the Euclidean distance between the comparison vector group and the raw oil standard comparison model, and generate a sorting result with increasing distance.

[0163] Specifically, the Euclidean distance calculation formula used in embodiments of the present invention may include:

[0164]

[0165] Where, d ij Let T be the distance between the i-th test sample and the j-th similar sample in the standard model. Bi T Aj D represents the temperature at point i of the sample to be tested and the temperature of the similar sample at point j in the standard model, respectively. Bi D AjThese are the equivalent double bond value at point i of the sample to be tested and the equivalent double bond value of the similar sample at point j in the standard model, respectively.

[0166] Result generation unit 07 is used to determine similar vector elements from the raw material oil standard comparison model based on the sorting results, and to determine the corresponding physical property data as the analysis results based on the vector group corresponding to the similar vector elements.

[0167] The result generation unit 07 in this embodiment of the invention may specifically include:

[0168] The first calculation module is used to select K vector elements with the smallest distance for weighted probability calculation; the formula for calculating the weighted probability is shown in formula (4):

[0169]

[0170] Among them, f ij Let d be the weighted distance probability between the i-th test sample and the j-th similar sample in the standard model. ij Let be the distance between the i-th test sample and the j-th similar sample in the standard model, and k be the number of sample points with the smallest distance selected.

[0171] The second calculation module is used to calculate the similarity between the k minimum distance points and the comparison vector group, centered on the comparison vector group, through distance-weighted probability calculation, and form a similarity probability matrix f. i ={f k1 ,f k2 ,...,f k}, and the sum of all probabilities in the similarity probability matrix is ​​1;

[0172] The third calculation module is used to traverse k minimum distance points and determine whether all probabilities in the weighted probability matrix are greater than P. K If not, decrement the k samples by 1 and return to step S21; if yes, use the similarity probability matrix as a weighted probability matrix.

[0173] The fourth calculation module is used to multiply the weighted probabilities of the k similarity point vector elements in the weighted probability matrix with the physical properties of the corresponding similarity point vector elements in the crude oil standard comparison model, and sum the calculation results to obtain the physical property data of the crude oil to be analyzed; the physical property multiplication calculation formula includes:

[0174]

[0175] Where P represents the physical property data of the crude oil to be analyzed, and f i P is the weighted probability of the vector elements of the i-th similar sample point. iThis refers to the physical property data of the vector element of the i-th similar sample point in the standard comparison model of crude oil.

[0176] It should be noted that the specific implementation method and technical effects of the feedstock oil property prediction and analysis device in the embodiments of the present invention can be referred to Figure 1 The corresponding methods for predicting and analyzing the physical properties of raw oils will not be elaborated here.

[0177] Example 3

[0178] Corresponding to the method embodiments, this embodiment of the invention also provides a raw material oil property prediction and analysis device 03, such as a terminal, server, etc. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smartphone, tablet computer, laptop computer, desktop computer, etc., but is not limited to these.

[0179] An example diagram of the hardware structure block diagram of the crude oil property prediction and analysis equipment provided in this application is shown below. Figure 3 As shown, it may include:

[0180] Processor 1, communication interface 2, memory 3, and communication bus 4;

[0181] The processor 1, communication interface 2, and memory 3 communicate with each other via communication bus 4.

[0182] Optionally, communication interface 2 can be an interface of a communication module, such as the interface of a GSM module;

[0183] Processor 1 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0184] Memory 3 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0185] Specifically, processor 1 is used to execute the computer program stored in memory 3 to perform the following steps:

[0186] S11. A preset physical property data sample set includes physical property data of multiple crude oil samples;

[0187] S12. Generate sample vector groups corresponding to each type of feedstock sample in the crude oil physical property data sample set. Each vector element of the sample vector group includes the distillation range point, equivalent double bond value, and physical property data. Generate a vector matrix as a standard comparison model for feedstock based on each vector group.

[0188] S13. Based on the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture corresponding to each distillation point in the crude oil temperature data to be analyzed, a corresponding distribution curve is generated by polynomial fitting; the horizontal axis of the distribution curve is the distillation point, and the vertical axis is the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture.

[0189] S14. Determine the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture corresponding to each distillation point that is consistent with the sample vector group based on the distribution curve.

[0190] S15. Calculate the equivalent double bond values ​​corresponding to each distillation point that is consistent with the sample vector group, and generate the comparison vector group of the feedstock oil to be analyzed: the vector elements of the comparison vector group include distillation points and equivalent double bond values.

[0191] S16. Perform Euclidean distance calculation on the comparison vector group and the raw material oil standard comparison model to generate a sorting result with increasing distance;

[0192] S17. Based on the sorting results, similar vector elements are determined from the standard comparison model of the raw oil, and the corresponding physical property data are determined as the analysis results based on the vector group corresponding to the similar vector elements.

[0193] The above-described product can perform the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for performing the method. Technical details not described in detail in this embodiment can be found in the method for predicting and analyzing the physical properties of raw oil provided in the embodiments of the present invention.

[0194] Example 4

[0195] In this embodiment of the invention, a storage medium is also provided, which can store a program suitable for execution by a processor, the program being used for:

[0196] S11. A preset physical property data sample set includes physical property data of multiple crude oil samples;

[0197] S12. Generate sample vector groups corresponding to each type of feedstock sample in the crude oil physical property data sample set. Each vector element of the sample vector group includes the distillation range point, equivalent double bond value, and physical property data. Generate a vector matrix as a standard comparison model for feedstock based on each vector group.

[0198] S13. Based on the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture corresponding to each distillation point in the crude oil temperature data to be analyzed, a corresponding distribution curve is generated by polynomial fitting; the horizontal axis of the distribution curve is the distillation point, and the vertical axis is the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture.

[0199] S14. Determine the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture corresponding to each distillation point that is consistent with the sample vector group based on the distribution curve.

[0200] S15. Calculate the equivalent double bond values ​​corresponding to each distillation point that is consistent with the sample vector group, and generate the comparison vector group of the feedstock oil to be analyzed: the vector elements of the comparison vector group include distillation points and equivalent double bond values.

[0201] S16. Perform Euclidean distance calculation on the comparison vector group and the raw material oil standard comparison model to generate a sorting result with increasing distance;

[0202] S17. Based on the sorting results, similar vector elements are determined from the standard comparison model of the raw oil, and the corresponding physical property data are determined as the analysis results based on the vector group corresponding to the similar vector elements.

[0203] Optionally, the refined and extended functions of the program can be found in the description above.

[0204] The above-described product can execute the methods provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the methods. Technical details not described in detail in this embodiment can be found in the methods provided in other embodiments of the present invention.

[0205] The above-described product can execute the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method provided in the embodiments of the present invention.

[0206] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0207] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0208] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0209] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0210] It should be understood that in the embodiments of this application, the claims, various embodiments, and features can be combined with each other to solve the aforementioned technical problems.

[0211] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0212] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not 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

1. A method for predicting and analyzing the physical properties of crude oil, characterized in that, Including the following steps: S11. Preset a raw oil physical property data sample set that includes physical property data of multiple raw oil samples; S12. Generate sample vector groups corresponding to each type of feedstock sample in the feedstock property data sample set. Each vector element of the sample vector group includes the distillation range point, equivalent double bond value, and property data. Generate a vector matrix as a feedstock standard comparison model based on each vector group. S13. Based on the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture corresponding to each boiling point in the crude distillation temperature data of the feedstock oil to be analyzed, a corresponding distribution curve is generated by polynomial fitting; the horizontal axis of the distribution curve is the boiling point, and the vertical axis is the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture. S14. Determine the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture corresponding to each distillation point that is consistent with the sample vector group based on the distribution curve. S15. Calculate the equivalent double bond values ​​corresponding to each distillation point that is consistent with the sample vector group, and generate the comparison vector group of the feedstock oil to be analyzed: the vector elements of the comparison vector group include distillation points and equivalent double bond values. S16. Perform Euclidean distance calculation on the comparison vector group and the raw material oil standard comparison model to generate a sorting result with increasing distance; S17. Based on the sorting results, similar vector elements are determined from the standard comparison model of the raw oil, and the corresponding physical property data are determined as the analysis results based on the vector group corresponding to the similar vector elements.

2. The method for predicting and analyzing the physical properties of crude oil according to claim 1, characterized in that, The sample vector group has n vector elements, and the number of vector elements is the same as the number of distillation points in the sample vector group. The sample vector group includes: {(T1,D1,P1),(T2,D2,P2),...,(T n D n ,P n )}, where T is the distillation range point, including n; D is the equivalent double bond value; P is the physical property data; n is the number of vector elements in the sample vector group; The vector matrix used as the standard comparison model for crude oil includes: ； Where m is the total number of the types of raw material oil samples; The alignment vector group includes: {(T1,D1),(T2,D2),...,(T...} n D n )}; where T is the distillation point; D is the equivalent double bond value.

3. The method for predicting and analyzing the physical properties of crude oil according to claim 1, characterized in that, The equivalent double bond value is the sum of the number of rings and the number of double bonds in the molecule, and the formula for calculating the equivalent double bond DBE includes: Official (1); in, c, h, n These represent the number of carbon, hydrogen, and nitrogen atoms in the mixture of raw oils, respectively.

4. The method for predicting and analyzing the physical properties of crude oil according to claim 3, characterized in that, The calculation of the equivalent double bond values ​​corresponding to each distillation point consistent with the sample vector group includes: Based on the distribution curve, the carbon, hydrogen, and nitrogen contents and the molecular weight of the mixture at each distillation point are read, and the number of carbon, hydrogen, and nitrogen atoms in the feedstock mixture is calculated according to formula (2): Official (2); in, x n , y n , z n They are respectively the Tth n The distillation range point corresponds to the number of carbon, hydrogen, and nitrogen atoms in the molecular formula of the crude oil. A n 、 B n 、 C n They are respectively the Tth n The elemental content of carbon, hydrogen, and nitrogen in the crude oil corresponding to the distillation range point, M n For the Tth n The molecular weight of the feed oil mixture corresponding to the distillation range point; After calculating the number of carbon, hydrogen, and nitrogen atoms according to formula (2), calculate the number of atoms in T according to formula (1). n The equivalent double bond value corresponding to the distillation range point.

5. The method for predicting and analyzing the physical properties of crude oil according to claim 4, characterized in that, The step of calculating the Euclidean distance between the comparison vector group and the raw material oil standard comparison model to generate a sorting result in ascending distance includes: The Euclidean distance calculation formula includes: Official (3); Where, d ij For the first i The test sample and the first point in the standard model j The distance between similar samples T Bi , T Aj The samples to be tested are respectively i Point temperature, in the standard model j Temperature of similar samples D Bi , D Aj The samples to be tested are respectively i Point equivalent double bond value, the first in the standard model j Equivalent double bond values ​​for point-similar samples.

6. The method for predicting and analyzing the physical properties of crude oil according to claim 5, characterized in that, The step of determining similar vector elements from the standard comparison model of the raw oil based on the sorting results, and determining the corresponding physical property data as the analysis results based on the vector groups corresponding to the similar vector elements, includes: S21. Select k vector elements with the smallest distance to perform weighted probability calculation; the formula for calculating the weighted probability is shown in formula (4): Official (4); in, f ij Let be the weighted distance probability between the i-th test sample and the j-th similar sample in the standard model. d ij Let be the distance between the i-th test sample and the j-th similar sample in the standard model, and k be the number of sample points with the smallest distance selected. S22. By calculating the distance-weighted probability, taking the comparison vector group as the center, the similarity between the k minimum distance points and the comparison vector group is measured to form a similarity probability matrix. f ={ f 1, f 2, ..., f k }, and the sum of all probabilities in the similarity probability matrix is ​​1; S23. Traverse k minimum distance points and determine whether all probabilities in the weighted probability matrix are greater than P. K If not, decrement the k samples by 1 and return to step S21; if yes, use the similarity probability matrix as a weighted probability matrix. S24. Multiply the weighted probabilities of the k similarity point vector elements in the weighted probability matrix with the physical properties of the corresponding similarity point vector elements in the crude oil standard comparison model, and sum the calculation results to obtain the physical property data of the crude oil to be analyzed; the formula for calculating the physical property multiplication includes: Official (5); in, P For the physical property data of the feedstock oil to be analyzed, f i For the first i The weighted probability of the elements of a vector of similar sample points. P i The first in the standard comparison model of crude oil i The physical property data of vector elements of similar sample points.

7. A device for predicting and analyzing the physical properties of crude oil, characterized in that, include: The sample set generation unit is used to preset a physical property data sample set that includes physical property data of multiple crude oil samples; The model generation unit is used to generate sample vector groups corresponding to each type of feedstock sample in the feedstock physical property data sample set. Each vector element of the sample vector group includes the distillation range point, equivalent double bond value, and physical property data. Based on each vector group, a vector matrix is ​​generated as a feedstock standard comparison model. The curve generation unit is used to generate corresponding distribution curves based on the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture corresponding to each distillation point in the crude distillation temperature data of the feedstock oil to be analyzed, through polynomial fitting; the horizontal axis of the distribution curve is the distillation point, and the vertical axis is the carbon, hydrogen, and nitrogen content and the molecular weight of the mixture. The distillation point corresponding unit is used to determine the carbon, hydrogen, nitrogen content and molecular weight of the mixture corresponding to each distillation point that is consistent with the sample vector group, based on the distribution curve. An equivalent double bond calculation unit is used to calculate the equivalent double bond value corresponding to each distillation point that is consistent with the sample vector group, and generate a comparison vector group of the feedstock oil to be analyzed: the vector elements of the comparison vector group include distillation point and equivalent double bond value. The Euclidean distance sorting unit is used to calculate the Euclidean distance between the comparison vector group and the raw oil standard comparison model, and generate a sorting result with increasing distance. The result generation unit is used to determine similar vector elements from the raw oil standard comparison model based on the sorting results, and to determine the corresponding physical property data as the analysis results based on the vector group corresponding to the similar vector elements.

8. The feedstock oil property prediction and analysis device according to claim 7, characterized in that, The sample vector group has n vector elements, and the number of vector elements is the same as the number of distillation points in the sample vector group. The sample vector group includes: {(T1,D1,P1),(T2,D2,P2),...,(T n D n ,P n )}, where T is the distillation range point, including n; D is the equivalent double bond value; P is the physical property data; n is the number of vector elements in the sample vector group; The vector matrix used as the standard comparison model for crude oil includes: ； Where m is the total number of the types of raw material oil samples; The alignment vector group includes: {(T1,D1),(T2,D2),...,(T...} n D n )}; where T is the distillation point; D is the equivalent double bond value.

9. The feedstock oil property prediction and analysis device according to claim 7, characterized in that, The equivalent double bond value is the sum of the number of rings and the number of double bonds in the molecule, and the formula for calculating the equivalent double bond DBE includes: Official (1); in, c, h, n These represent the number of carbon, hydrogen, and nitrogen atoms in the mixture of raw oils, respectively.

10. The feedstock oil property prediction and analysis device according to claim 9, characterized in that, The calculation of the equivalent double bond values ​​corresponding to each distillation point consistent with the sample vector group includes: Based on the distribution curve, the carbon, hydrogen, and nitrogen contents and the molecular weight of the mixture at each distillation point are read, and the number of carbon, hydrogen, and nitrogen atoms in the feedstock mixture is calculated according to formula (2): Official (2); in, x n , y n , z n They are respectively the Tth n The distillation range point corresponds to the number of carbon, hydrogen, and nitrogen atoms in the molecular formula of the crude oil. A n 、 B n 、 C n They are respectively the Tth n The elemental content of carbon, hydrogen, and nitrogen in the crude oil corresponding to the distillation range point, M n For the Tth n The molecular weight of the feed oil mixture corresponding to the distillation range point; After calculating the number of carbon, hydrogen, and nitrogen atoms according to formula (2), calculate the number of atoms in T according to formula (1). n The equivalent double bond value corresponding to the distillation range point.

11. The feedstock oil property prediction and analysis device according to claim 10, characterized in that, The step of calculating the Euclidean distance between the comparison vector group and the raw material oil standard comparison model to generate a sorting result in ascending distance includes: The Euclidean distance calculation formula includes: Official (3); Where, d ij For the first i The test sample and the first point in the standard model j The distance between similar samples T Bi , T Aj The samples to be tested are respectively i Point temperature, in the standard model j Temperature of similar samples D Bi , D Aj The samples to be tested are respectively i Point equivalent double bond value, the first in the standard model j Equivalent double bond values ​​for point-similar samples.

12. The feedstock oil property prediction and analysis device according to claim 11, characterized in that, The result generation unit includes: The first calculation module is used to select k vector elements with the smallest distance for weighted probability calculation; the formula for calculating the weighted probability is shown in formula (4): Official (4); in, f ij Let be the weighted distance probability between the i-th test sample and the j-th similar sample in the standard model. d ij Let be the distance between the i-th test sample and the j-th similar sample in the standard model, and k be the number of sample points with the smallest distance selected. The second calculation module is used to calculate the similarity between the k minimum distance points and the comparison vector group, centered on the comparison vector group, through distance-weighted probability calculation, and form a similarity probability matrix. f ={ f 1, f 2, ..., f k }, and the sum of all probabilities in the similarity probability matrix is ​​1; The third calculation module is used to traverse k minimum distance points and determine whether all probabilities in the weighted probability matrix are greater than P. K If not, decrement the k samples by 1 and return to step S21; if yes, use the similarity probability matrix as a weighted probability matrix. The fourth calculation module is used to multiply the weighted probabilities of the k similarity point vector elements in the weighted probability matrix with the physical properties of the corresponding similarity point vector elements in the feedstock standard comparison model, and sum the calculation results to obtain the physical property data of the feedstock to be analyzed; the physical property multiplication calculation formula includes: Official (5); in, P For the physical property data of the feedstock oil to be analyzed, f i For the first i The weighted probability of the elements of a vector of similar sample points. P i The first in the standard comparison model of crude oil i The physical property data of vector elements of similar sample points.

13. A feedstock oil property prediction and analysis device, characterized in that, include: Memory, used to store computer programs; A processor is configured to invoke and execute the computer program to implement the steps of the feedstock oil property prediction and analysis method as described in any one of claims 1 to 6.

14. A storage medium, characterized in that, Includes a software program, said software program being adapted by a processor to perform the steps of the feedstock property prediction and analysis method as described in any one of claims 1 to 6.

Images