A method and device for determining a crude oil refining strategy based on the physical properties of crude oil

Abstract

This specification provides a method and apparatus for determining a crude oil refining strategy based on crude oil physical properties. The method includes: obtaining second crude oil physical property data associated with first crude oil physical property data to be predicted; processing the second crude oil physical property data using a crude oil physical property prediction model to obtain the first crude oil physical property data; and determining a crude oil refining strategy based on the first crude oil physical property data and the second crude oil physical property data. Based on the above method, the crude oil physical properties can be predicted at low cost, efficiently, and accurately, so that a reasonable crude oil refining strategy can be determined.

Description

Technical Field

[0001] This specification relates to the technical field of crude oil processing, and particularly to a method and device for determining a crude oil refining strategy based on crude oil physical properties. Background Art

[0002] Since different crude oils with different properties require different processing and refining schemes, by comprehensively and accurately understanding the properties of crude oil and then determining the appropriate scheme or operating parameters, production costs can be reduced and the purpose of increasing production and improving efficiency can be achieved.

[0003] Currently, common methods for obtaining crude oil properties include manual chemical analysis, rapid crude oil analysis technology, and prediction of crude oil properties based on specific algorithms. For the manual chemical analysis method, there are technical problems such as long analysis time, large sample volume required, and high analysis cost, which can no longer meet the needs of practical applications. For the rapid crude oil analysis technology, there are problems such as high economic and time costs for obtaining comprehensive and detailed property data of crude oil, dependence on complex experimental equipment, and inability to obtain detailed molecular composition data of crude oil. For the method of predicting crude oil properties based on specific algorithms, there are problems such as difficulty in obtaining sample data and inability to efficiently and accurately predict crude oil physical properties.

[0004] In response to the above problems, no effective solution has been proposed yet. Summary of the Invention

[0005] This specification provides a method and device for determining a crude oil refining strategy based on crude oil physical properties to solve the problem that the prior art cannot accurately, efficiently, and at low cost predict crude oil physical properties, thus unable to formulate a reasonable crude oil refining strategy.

[0006] On the one hand, an embodiment of this specification provides a method for determining a crude oil refining strategy based on crude oil physical properties, including:

[0007] Obtain second crude oil physical property data associated with the first crude oil physical property data to be predicted;

[0008] Process the second crude oil physical property data using a crude oil physical property prediction model to obtain the first crude oil physical property data;

[0009] Determine a crude oil refining strategy based on the first crude oil physical property data and the second crude oil physical property data.

[0010] Further, the method further includes:

[0011] Select a crude oil physical property prediction model that matches the first crude oil physical property data from multiple crude oil physical property prediction models; wherein, each crude oil physical property prediction model in the multiple crude oil physical property prediction models corresponds to crude oil physical property data;

[0012] Process the second crude oil physical property data by using the selected crude oil physical property prediction model.

[0013] Further, the crude oil physical property prediction model is established in the following manner:

[0014] Conduct a correlation analysis on multiple crude oil physical property data samples to select the crude oil physical property data samples associated with the target crude oil physical property data sample from the multiple crude oil physical property data samples;

[0015] Train the crude oil physical property prediction model according to the selected crude oil physical property data samples and the target crude oil physical property data sample.

[0016] Further, the first crude oil physical property data to be predicted includes the structural composition of the distillate oil. Correspondingly, the method further includes:

[0017] Obtain the refractive index, density, and molecular weight associated with the structural composition of the distillate oil;

[0018] Process the refractive index, density, and molecular weight by using the crude oil physical property prediction model associated with the structural composition of the distillate oil in the following manner:

[0019] Determine different intermediate factors at different temperatures according to the refractive index and the density;

[0020] Determine the structural composition of the distillate oil at different temperatures according to the molecular weight and the intermediate factors.

[0021] Further, the different intermediate factors at different temperatures include: the first factor and the second factor at the first temperature, and the first factor and the second factor at the second temperature. Correspondingly, the determining the structural composition of the distillate oil at different temperatures according to the molecular weight and the intermediate factors includes:

[0022] Determine the percentage of aromatic ring carbon atoms in the total carbon atoms and the number of aromatic rings at the first temperature according to the molecular weight and the first factor at the first temperature;

[0023] Determine the intermediate variable and the total number of rings at the first temperature according to the molecular weight and the second factor at the first temperature;

[0024] Determine the percentage of aromatic ring carbon atoms in the total carbon atoms and the number of aromatic rings at the second temperature according to the molecular weight and the first factor at the second temperature;

[0025] Determine the intermediate variable and the total number of rings at the second temperature according to the molecular weight and the second factor at the second temperature.

[0026] Further, the method further includes:

[0027] Determine the number of cycloalkane ring carbon atoms in the total carbon atoms according to the intermediate variable and the percentage of aromatic ring carbon atoms in the total carbon atoms;

[0028] Determine the number of alkane carbon atoms in the total carbon atoms according to the intermediate variable;

[0029] Determine the number of cycloalkane rings according to the total number of rings and the number of aromatic rings.

[0030] Further, the first crude oil physical property data to be predicted further includes the Reid vapor pressure. Correspondingly, the method further includes:

[0031] Obtain the characterization factor and the target boiling point associated with the Reid vapor pressure;

[0032] Process the characterization factor and the target boiling point data by using the crude oil physical property prediction model associated with the Reid vapor pressure in the following manner:

[0033] Determine the petroleum fraction vapor pressure according to the characterization factor and the target boiling point;

[0034] Determine the ratio according to the petroleum fraction vapor pressure;

[0035] Determine the Reid vapor pressure according to the ratio and the petroleum fraction vapor pressure.

[0036] Further, the first crude oil physical property data to be predicted further includes the cetane index. Correspondingly, the method further includes:

[0037] Obtain the aniline point and density data associated with the cetane index;

[0038] Process the aniline point and density data by using the crude oil physical property prediction model associated with the cetane index to obtain the cetane index.

[0039] On the other hand, the embodiments of the present specification further provide a device for determining a crude oil refining strategy based on crude oil physical properties, including:

[0040] An acquisition module, configured to acquire second crude oil physical property data associated with the first crude oil physical property data to be predicted;

[0041] A prediction module, configured to process the second crude oil physical property data by using a crude oil physical property prediction model to obtain the first crude oil physical property data;

[0042] A refining module, configured to determine a crude oil refining strategy according to the first crude oil physical property data and the second crude oil physical property data.

[0043] In another aspect, the present application also provides a device, including a processor and a memory for storing instructions executable by the processor. When the processor executes the instructions, the method for determining a crude oil refining strategy based on crude oil physical properties in the above embodiments is implemented.

[0044] In another aspect, the present application also provides a computer-readable storage medium, on which computer instructions are stored. When the computer-readable storage medium executes the instructions, the method for determining a crude oil refining strategy based on crude oil physical properties in the above embodiments is implemented.

[0045] A method and device for determining a crude oil refining strategy based on crude oil physical properties provided in this specification. First, second crude oil physical property data associated with the first crude oil physical property data to be predicted is obtained. Secondly, the second crude oil physical property data is processed using a crude oil physical property prediction model to obtain the first crude oil physical property data. Finally, a crude oil refining strategy is determined based on the first crude oil physical property data and the second crude oil physical property data. In the embodiments of this specification, by using the association between the crude oil physical property data to be predicted and the known crude oil physical property data, the corresponding known crude oil physical property data can be quickly determined. By processing the known crude oil physical property data through a crude oil physical property prediction model corresponding to the crude oil physical property data to be predicted, the predicted crude oil physical property data can be determined in a low-cost, high-efficiency, and high-accuracy manner, so that a reasonable crude oil refining strategy can be determined. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] To more clearly illustrate the embodiments of this specification, the drawings required for use in the embodiments will be briefly introduced below. The drawings described below are only some embodiments recorded in this specification. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0047] Figure 1 is a flowchart of a method for determining a crude oil refining strategy based on crude oil physical properties provided by an embodiment of this specification;

[0048] Figure 2 is a schematic diagram of the structural composition of a device for determining a crude oil refining strategy based on crude oil physical properties provided by an embodiment of this specification;

[0049] Figure 3 is a schematic diagram of the structural composition of an electronic device provided by an embodiment of this specification. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] In order to enable those skilled in the art to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in the embodiments of this specification in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on the embodiments in this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this specification.

[0051] Since different types of crude oil can adopt different processing and refining schemes, therefore, by comprehensively and accurately understanding the properties of crude oil and then determining appropriate schemes or operating parameters, the production cost can be reduced and the purpose of increasing production and improving efficiency can be achieved.

[0052] Currently, common methods for obtaining the properties of crude oil include manual chemical analysis, rapid crude oil analysis technology, and prediction of crude oil properties based on specific algorithms.

[0053] Among them, for manual chemical analysis, first, a sample of crude oil needs to be obtained, and then it is sent to the laboratory for true boiling point distillation of the crude oil and analysis of the properties of the crude oil and the properties of the distillate oils, so as to evaluate its processing performance. Although this method can obtain comprehensive and detailed crude oil property data, there are numerous types of crude oil, and crude oils from different years, different origins, and different types may have significant differences in properties. There are technical problems such as a relatively long analysis time, a relatively large amount of required samples, and high analysis costs. This method can no longer meet the actual needs.

[0054] The rapid crude oil analysis technology is a crude oil evaluation technology based on modern analytical instruments, which can obtain the property data of crude oil and various oil products in a short time, such as near-infrared spectroscopy (NIR), mid-infrared spectroscopy (IR), and nuclear magnetic resonance spectroscopy (NMR) technology. Infrared spectroscopy mainly reflects the fundamental frequency information of the vibration and rotation of matter molecules, can reflect the component information of the vast majority of organic compounds, and has the advantages of strong absorption signals, obvious spectral peaks, and easy resolution. Nuclear magnetic resonance analysis is an electromagnetic analysis technology that causes atomic nuclei to transition under a magnetic field and qualitatively and quantitatively analyzes various molecular structures through the position and intensity on the spectrum, and has the advantages of simple sample processing and good model robustness. However, this method has problems such as excessively high economic and time costs for obtaining comprehensive and detailed property data of crude oil, relying on complex experimental equipment, and being unable to obtain detailed molecular composition data of crude oil.

[0055] With the development of big data and artificial intelligence technologies, currently, prediction of crude oil properties based on specific algorithms is more commonly used. However, this method cannot predict unknown crude oil property data based on the correlation between known crude oil physical property data, has low prediction accuracy and poor reliability, and the required training sample data is difficult to obtain, resulting in high costs for predicting crude oil physical properties.

[0056] In view of the above problems existing in the existing methods and the specific reasons for the above problems, this specification introduces a method and device for determining a crude oil refining strategy based on crude oil physical properties, so as to solve the problem that the existing technology cannot accurately, efficiently and at low cost predict the crude oil physical properties, resulting in the inability to accurately formulate a crude oil refining strategy for crude oil refining.

[0057] Based on the above ideas, this specification proposes a method for determining a crude oil refining strategy based on crude oil physical properties. First, obtain second crude oil physical property data associated with the first crude oil physical property data to be predicted. Secondly, process the second crude oil physical property data using a crude oil physical property prediction model to obtain the first crude oil physical property data. Finally, determine the crude oil refining strategy according to the first crude oil physical property data and the second crude oil physical property data. Refer to Figure 1 As shown, the embodiments of this specification provide a method for determining a crude oil refining strategy based on crude oil physical properties. Specifically, when implemented, this method may include the following content.

[0058] S101: Obtain second crude oil physical property data associated with the first crude oil physical property data to be predicted.

[0059] In some embodiments, the second crude oil physical property data may be known crude oil physical property data, which may include: mid-boiling point, molecular weight, density (such as: density at 15°C and density at 20°C), aniline point, characterization factor, refractive index, etc. The known crude oil physical property data can be obtained from a crude oil physical property evaluation database, and the crude oil evaluation database may pre-store crude oil sample information, such as: source, collection time, location, collection method, etc. of the crude oil sample, crude oil property data, such as: test data of physical properties such as density, viscosity, calorific value of combustion, solubility, etc. of the crude oil, fraction composition data, such as: composition data of each fraction such as naphtha, gasoline, diesel, wax oil, residue, etc., thermodynamic property data, such as: flash point, pour point, ignition point, combustion heat property data, etc. of the crude oil. The first crude oil physical property data may be the crude oil physical property data to be predicted, and the first crude oil physical property data may include: refractive index, cetane index, Reid vapor pressure, fraction oil structure composition, etc. Among them, the second crude oil physical property data may be associated with the first crude oil physical property data. For example, the mid-boiling point, molecular weight, and density at 20°C in the second crude oil physical property data may be associated with the refractive index in the first crude oil physical property data, the density at 15°C and aniline point in the second crude oil physical property data may be associated with the cetane index in the first crude oil physical property data, the characterization factor and mid-boiling point in the second crude oil physical property data may be associated with the Reid vapor pressure in the first crude oil physical property data, and the refractive index, density at 20°C, and molecular weight in the second crude oil physical property data may be associated with the fraction oil structure composition in the first crude oil physical property data.

[0060] It should be noted that the parameter data included in the above first crude oil physical property data (crude oil physical property data to be predicted) and second crude oil physical property data (known crude oil physical property data) are not limited to the above examples. Those skilled in the art may make other changes under the inspiration of the technical essence of the embodiments of this specification. However, as long as the functions and effects achieved are the same as or similar to those of the embodiments of this specification, they should all be covered within the protection scope of the embodiments of this specification.

[0061] By obtaining the second crude oil physical property data associated with the first crude oil physical property data to be predicted, it can lay a foundation for accurately, efficiently, and at low cost predicting the corresponding first crude oil physical property data (crude oil physical property data to be predicted) based on the associated second crude oil physical property data (known crude oil physical property data) subsequently.

[0062] S102: Process the second crude oil physical property data using the crude oil physical property prediction model to obtain the first crude oil physical property data.

[0063] In some embodiments, there may be multiple above-mentioned crude oil physical property prediction models. The crude oil physical property prediction model that matches the first crude oil physical property data can be selected from the multiple crude oil physical property prediction models, and then the second crude oil physical property data associated with the first crude oil physical property data is processed based on the selected crude oil physical property prediction model. Specifically, in specific implementation, it may include the following content:

[0064] Select the crude oil physical property prediction model that matches the first crude oil physical property data from multiple crude oil physical property prediction models; wherein, each crude oil physical property prediction model among the multiple crude oil physical property prediction models corresponds to crude oil physical property data;

[0065] Process the second crude oil physical property data using the selected crude oil physical property prediction model.

[0066] In some embodiments, the above crude oil physical property prediction model that matches the first crude oil physical property data is the crude oil physical property prediction model that matches the crude oil physical property data to be predicted. For example: the crude oil physical property prediction model that matches the refractive index, the crude oil physical property prediction model that matches the cetane index, the crude oil physical property prediction model that matches the Reid vapor pressure, the crude oil physical property prediction model that matches the structural composition of the distillate oil. Each crude oil physical property prediction model among the multiple crude oil physical property prediction models corresponds to crude oil physical property data, that is, each crude oil physical property prediction model may correspond to known crude oil physical property data. For example: the crude oil physical property prediction model that matches the refractive index may correspond to data such as the average boiling point, molecular weight, density, etc.

[0067] In some embodiments, a crude oil physical property prediction model matching the first crude oil physical property data can be selected according to actual requirements. For example, if the refractive index needs to be predicted, a crude oil physical property prediction model matching the refractive index to be predicted can be selected from multiple crude oil physical property prediction models. If the structural composition of the distillate oil needs to be predicted, a crude oil physical property prediction model matching the structural composition of the distillate oil to be predicted can be selected from multiple crude oil physical property prediction models.

[0068] It should be noted that the above crude oil physical property prediction models are not limited to the above examples. Those skilled in the art may make other changes under the inspiration of the technical essence of the embodiments of this specification. However, as long as the functions and effects achieved are the same or similar to those of the embodiments of this specification, they should all be covered within the protection scope of the embodiments of this specification.

[0069] By screening out a crude oil physical property prediction model matching the first crude oil physical property data to be predicted from multiple crude oil physical property prediction models, the prediction efficiency and accuracy of crude oil physical properties can be effectively improved.

[0070] In some embodiments, the above crude oil physical property prediction model can be established in the following manner:

[0071] Perform a correlation analysis on multiple crude oil physical property data samples to select crude oil physical property data samples associated with the target crude oil physical property data sample from the multiple crude oil physical property data samples;

[0072] Train a crude oil physical property prediction model according to the selected crude oil physical property data samples and the target crude oil physical property data sample.

[0073] In some embodiments, multiple crude oil physical property data samples can be obtained from a crude oil evaluation database, and then a correlation analysis is performed on the multiple crude oil physical property data samples to select crude oil physical property data samples associated with the target crude oil physical property data sample (such as the crude oil physical property data sample to be predicted) from the multiple crude oil physical property data samples.

[0074] Specifically, assuming that the target crude oil physical property data sample includes refractive index, cetane index, Reid vapor pressure, and the structural composition of the distillate oil, it is necessary to obtain multiple crude oil physical property data samples and perform a correlation analysis on them to determine crude oil physical property data samples related to the refractive index, cetane index, Reid vapor pressure, and the structural composition of the distillate oil from the multiple crude oil physical property data samples.

[0075] For the refractive index, it refers to the refraction phenomenon that occurs when light enters from one medium into another due to the different densities of the media. The interaction between its molecules can be simplified as discrete spherical electrostatic dipoles. According to the electric field theory, when light passes through a medium, the propagation speed of light will decrease, which leads to the refraction phenomenon. The relationship between the refractive index of the medium and its number of molecules and density can be correlated for analysis, so that crude oil physical property data associated with the refractive index can be obtained, such as density.

[0076] For the cetane index, it can be obtained through statistical analysis of experimental data. In a large number of diesel samples, the cetane index and some physical property parameters (such as density, flash point, aniline point, etc.) can be measured, and then correlation analysis (such as regression analysis, data statistics, etc.) is performed on these data, so that crude oil physical property data associated with the cetane index can be determined, such as density, aniline point.

[0077] For the Reid vapor pressure, it can be obtained through the actual distillation test and Reid vapor pressure measurement of different samples. A large amount of data can be collected and correlation analysis is performed on these data, so that crude oil physical property data associated with the Reid vapor pressure can be determined, such as characterization factor, mean average boiling point.

[0078] For the structure composition of distillate oil, it is an optical property related to the electronic polarization characteristics of the molecules of the substance according to the refractive index. Since density and molecular weight provide the mass information of the substance, correlation analysis can be performed on these data, so that crude oil physical property data associated with the structure composition of distillate oil can be determined, such as refractive index, molecular weight, density.

[0079] After determining the crude oil physical property data sample associated with the target crude oil physical property data sample, the crude oil physical property prediction model can be jointly trained based on this crude oil physical property data sample and the target crude oil physical property data sample to improve the effect of model training, and a more accurate crude oil physical property prediction model can be obtained, laying a foundation for obtaining accurate crude oil physical property prediction data subsequently.

[0080] In some embodiments, the first crude oil physical property data to be predicted may include the structure composition of distillate oil. Correspondingly, when obtaining the first crude oil physical property data, in specific implementation, it may further include:

[0081] Obtain the refractive index, density, and molecular weight associated with the structure composition of distillate oil;

[0082] Use the crude oil physical property prediction model associated with the structure composition of distillate oil to process the refractive index, density, and molecular weight in the following manner:

[0083] Determine different intermediate factors at different temperatures according to the refractive index and the density;

[0084] Determine the structural composition of the fraction oil at different temperatures according to the molecular weight and the intermediate factor.

[0085] In some embodiments, the above-mentioned molecular weight can be calculated based on the density (density at 15°C) and the mean average boiling point. Among them, the density at 15°C can be obtained by converting the density at 20°C. The specific process of converting the density at 20°C to the density at 15°C can be shown as follows:

[0086] First, set list a and list b. Among them, list a represents the division intervals of the density at 20°C, and list b represents the correction coefficients within each interval. List a and list b can be shown as follows:

[0087] a = [0.70, 0.71, 0.72, 0.73, 0.74, 0.75, 0.76, 0.77, 0.78, 0.79, 0.80, 0.81, 0.82, 0.83, 0.84, 0.85, 0.86, 0.87, 0.88, 0.89, 0.90, 0.91, 0.92, 0.93, 0.94]

[0088] b = [0.0051, 0.005, 0.005, 0.0049, 0.0049, 0.0048, 0.0048, 0.0047, 0.0046, 0.0046, 0.0045, 0.0045, 0.0044, 0.0044, 0.0043, 0.0042, 0.0042, 0.0041, 0.0041, 0.004, 0.004, 0.0039, 0.0038, 0.0038, 0.0037]

[0089] Secondly, determine which interval in list a the current density at 20°C falls into.

[0090] If it is lower than the lower limit 0.70 of the interval in list a, the density conversion formula is:

[0091] sg_15 = sg_20 + b[0] + 0.01×(a[0] - sg_20)

[0092] If it is higher than the upper limit 0.94 of the interval in list a, the density conversion formula is:

[0093] sg_15 = sg_20 + b

[24] - 0.01×(sg_20 - a

[24] )

[0094] If it is between the upper and lower limits of list a, the density conversion formula is:

[0095] sg_15 = sg_20 + b[i]

[0096] Among them, sg_15 represents the density at 15°C, sg_20 represents the density at 20°C, a[0] and b[0] respectively represent the first elements in list a and list b, and a

[24] and b

[24] respectively represent the last elements in list a and list b. b[i] represents the i-th correction factor in b corresponding to the density at 20°C belonging to the i-th interval in a.

[0097] Finally, after converting the density at 20°C to the density at 15°C, the molecular weight can be calculated according to the following formula:

[0098] First, according to the mean average boiling point, calculate the normal boiling point according to the following formula:

[0099] tb = (meabp + A) × 1.8

[0100] Among them, tb represents the normal boiling point, A represents the coefficient related to the normal boiling point, and can take 273.15, and meabp represents the mean average boiling point.

[0101] Then, according to the normal boiling point and the density at 15°C, calculate the molecular weight according to the following formula:

[0102] mw = (A1 + A2 × sg_15 + (A3 - A4 × sg_15) × tb) + ((1 - A5 × sg_15 - A6 × sg_15 2 )

[0103] × (A7 - A8 / tb) × 10 7 / tb) + ((1 - A9 × sg_15 + A10 × sg_15 2 ) × (A11

[0104] - A12 / tb) × 10 12 / tb 3 )

[0105] Among them, mw represents the molecular weight, and A1, A2, A3, A4, A5, A6, A7, A8, A9, A10, A11, A12 represent the coefficients related to the molecular weight, and can take -12272.6, 9486.401, 4.6523, 3.3287, 0.77084, 0.02058, 1.3437, 720.79, 0.80882, 0.02226, 1.8828, 181.98 respectively, sg_15 represents the density at 15°C, and tb represents the normal boiling point.

[0106] In some embodiments, after calculating the molecular weight, the refractive index can be calculated according to the above molecular weight, the density at 20°C, and the mean average boiling point according to the following formula:

[0107]

[0108] Wherein, ri represents the refractive index, tmeabp represents the average boiling point, mw represents the molecular weight, sg_20 represents the density at 20°C, and B1, B2, B3, B4, C1, C2 represent coefficients related to the refractive index, and can respectively take values of 3.587, 273.15, 3.587, 273.15, 1.0848, -0.4439.

[0109] In some embodiments, after obtaining the refractive index and molecular weight, the structural composition of the distillate oil can be predicted based on the refractive index, molecular weight, and density. Specifically, a crude oil physical property prediction model associated with the structural composition of the distillate oil can be selected to process the refractive index, density, and molecular weight, and finally the structural composition of the distillate oil can be obtained. Among them, when using the crude oil physical property prediction model associated with the structural composition of the distillate oil to process the refractive index, density, and molecular weight, different intermediate factors at different temperatures can be determined first according to the calculated refractive index above and the pre-obtained density, and then the structural composition of the distillate oil at different temperatures can be determined according to the different intermediate factors and the calculated molecular weight above.

[0110] In some embodiments, the different intermediate factors at different temperatures described above may include: the first factor and the second factor at the first temperature, the first factor and the second factor at the second temperature (the first factor is different from the second factor, and the first temperature is different from the second temperature). Correspondingly, determining the structural composition of the distillate oil at different temperatures according to the molecular weight and the intermediate factor may specifically include:

[0111] Determining the percentage of aromatic ring carbon atoms in the total carbon atoms and the number of aromatic rings at the first temperature according to the molecular weight and the first factor at the first temperature;

[0112] Determining the intermediate variable and the total number of rings at the first temperature according to the molecular weight and the second factor at the first temperature;

[0113] Determining the percentage of aromatic ring carbon atoms in the total carbon atoms and the number of aromatic rings at the second temperature according to the molecular weight and the first factor at the second temperature;

[0114] Determining the intermediate variable and the total number of rings at the second temperature according to the molecular weight and the second factor at the second temperature.

[0115] In some embodiments, the first temperature described above may be 20°C, and the second temperature may be 70°C. It should be noted that the values of the temperature are not limited to the above examples. Those skilled in the art may make other changes under the inspiration of the technical essence of the embodiments of this specification, but as long as the functions and effects achieved are the same or similar to those of the embodiments of this specification, they should be covered within the protection scope of the embodiments of this specification.

[0116] The first factor at the first temperature can be calculated according to the following formula:

[0117] v1 = D1×(nd - D2) - (sg - D3)

[0118] Wherein, v1 represents the first factor at the first temperature, nd represents the refractive index, sg represents the density, and D1, D2, D3 represent coefficients related to the first factor at the first temperature, and can take 2.51, 1.475, 0.841.

[0119] The second factor at the first temperature can be calculated according to the following formula:

[0120] w1 = (sg - E1) - E2×(nd - E3)

[0121] Wherein, w1 represents the second factor at the first temperature, nd represents the refractive index, sg represents the density, and E1, E2, E3 represent coefficients related to the second factor at the first temperature, and can take 0.851, 1.11, 1.475.

[0122] The first factor at the second temperature can be calculated according to the following formula:

[0123] v2 = D4×(nd - D5) - (sg - D6)

[0124] Wherein, v2 represents the first factor at the second temperature, nd represents the refractive index, sg represents the density, and D4, D5, D6 represent coefficients related to the first factor at the second temperature, and can take 2.42, 1.46, 0.828.

[0125] The second factor at the second temperature can be calculated according to the following formula:

[0126] w2 = (sg - E4) - E5×(nd - E6)

[0127] Wherein, w2 represents the second factor at the second temperature, nd represents the refractive index, sg represents the density, and E4, E5, E6 represent coefficients related to the second factor at the second temperature, and can take 0.828, 1.11, 1.46.

[0128] In some embodiments, after determining the first factor at the first temperature and the second factor at the first temperature, it can be determined whether the first factor at the first temperature and the second factor at the first temperature are greater than a preset threshold (the preset threshold can be set to 0), and then the percentage of aromatic ring carbon atoms in the total carbon atoms, the number of aromatic rings, the intermediate variable, and the total number of rings at the first temperature can be determined. For example:

[0129] If the first factor at the first temperature is greater than 0, the percentage of aromatic ring carbon atoms in the total carbon atoms at the first temperature (or the percentage of aromatic ring carbon atoms in the average molecule of the fraction) and the number of aromatic rings (or the number of aromatic rings in the average molecule of the fraction) can be calculated successively according to the following formulas:

[0130] ca1 = F1×v1 + F2 / mw

[0131] ra1 = G1 + G2×mw×v1

[0132] Where ca1 represents the percentage of aromatic ring carbon atoms in the total carbon atoms at the first temperature, v1 represents the first factor at the first temperature, mw represents the molecular weight, ra1 represents the number of aromatic rings at the first temperature, F1 and F2 are coefficients related to the percentage of aromatic ring carbon atoms in the total carbon atoms at the first temperature, and can take values of 430.0 and 3660.0 respectively, and G1 and G2 are coefficients related to the number of aromatic rings at the first temperature, and can take values of 0.44 and 0.055 respectively.

[0133] If the first factor at the first temperature is less than 0, the percentage of aromatic ring carbon atoms in the total carbon atoms at the first temperature (or the percentage of aromatic ring carbon atoms in the average molecule of the fraction) and the number of aromatic rings (or the number of aromatic rings in the average molecule of the fraction) can be calculated successively according to the following formulas:

[0134] ca1 = F3×v1 + F4 / mw

[0135] ra1 = G3 + G4×mw×v1

[0136] Where ca1 represents the percentage of aromatic ring carbon atoms in the total carbon atoms at the first temperature, v1 represents the first factor at the first temperature, mw represents the molecular weight, ra1 represents the number of aromatic rings at the first temperature, F3 and F4 are coefficients related to the percentage of aromatic ring carbon atoms in the total carbon atoms at the first temperature, and can take values of 670.0 and 3660.0 respectively, and G3 and G4 are coefficients related to the number of aromatic rings at the first temperature, and can take values of 0.44 and 0.08 respectively.

[0137] If the second factor at the first temperature is greater than 0, the intermediate variable (cr1) and the total number of rings (or the total number of rings in the average molecule of the fraction) at the first temperature can be calculated successively according to the following formulas:

[0138] cr1 = H1×w1 + H2 / mw

[0139] rt1 = I1 + I2×mw×w1

[0140] Among them, cr1 represents the intermediate variable at the first temperature, w1 represents the second factor at the first temperature, mw represents the molecular weight, rt1 represents the total number of rings at the first temperature, H1 and H2 are coefficients related to the intermediate variable at the first temperature, and can take values of 820.0 and 10000.0 respectively. I1 and I2 represent coefficients related to the total number of rings at the first temperature, and can take values of 1.33 and 0.146 respectively.

[0141] If the second factor at the first temperature is less than 0, the intermediate variable (cr1) and the total number of rings (or the total number of rings in the average molecule of the fraction) at the first temperature can be calculated successively according to the following formula:

[0142] cr1 = H3 × w1 + H4 / mw

[0143] rt1 = I3 + I4 × mw × w1

[0144] Among them, cr1 represents the intermediate variable at the first temperature, w1 represents the second factor at the first temperature, mw represents the molecular weight, rt1 represents the total number of rings at the first temperature, H3 and H4 are coefficients related to the intermediate variable at the first temperature, and can take values of 1440.0 and 10600.0 respectively. I3 and I4 represent coefficients related to the total number of rings at the first temperature, and can take values of 1.33 and 0.18 respectively.

[0145] In some embodiments, after determining the first factor at the second temperature and the second factor at the second temperature, it can be determined whether the first factor at the second temperature and the second factor at the second temperature are greater than a preset threshold (the preset threshold can be set to 0), and then the percentage of aromatic ring carbon atoms in the total carbon atoms, the number of aromatic rings, the intermediate variable, and the total number of rings at the second temperature can be determined. For example:

[0146] If the first factor at the second temperature is greater than 0, the percentage of aromatic ring carbon atoms in the total carbon atoms (or the percentage of aromatic ring carbon atoms in the average molecule of the fraction) and the number of aromatic rings (or the number of aromatic rings in the average molecule of the fraction) at the second temperature can be calculated successively according to the following formula:

[0147] ca2 = F11 × v2 + F22 / mw

[0148] ra2 = G11 + G22 × mw × v2

[0149] Among them, ca2 represents the percentage of aromatic ring carbon atoms in the total carbon atoms at the second temperature, v2 represents the first factor at the second temperature, mw represents the molecular weight, ra2 represents the number of aromatic rings at the second temperature, F11 and F22 represent coefficients related to the percentage of aromatic ring carbon atoms in the total carbon atoms at the second temperature, and can take values of 410.0 and 3660.0 respectively, and G11 and G22 represent coefficients related to the number of aromatic rings at the second temperature, and can take values of 0.41 and 0.055 respectively.

[0150] If the first factor at the second temperature is less than 0, the percentage of aromatic ring carbon atoms in the total carbon atoms at the second temperature (or the percentage of aromatic ring carbon atoms in the average molecule of the fraction) and the number of aromatic rings (or the number of aromatic rings in the average molecule of the fraction) can be calculated successively according to the following formula:

[0151] ca2 = F33 × v2 + F44 / mw

[0152] ra2 = G33 + G44 × mw × v2

[0153] Among them, ca2 represents the percentage of aromatic ring carbon atoms in the total carbon atoms at the second temperature, v2 represents the first factor at the second temperature, mw represents the molecular weight, ra2 represents the number of aromatic rings at the second temperature, F33 and F44 represent coefficients related to the percentage of aromatic ring carbon atoms in the total carbon atoms at the second temperature, and can take values of 720.0 and 3660.0 respectively, and G33 and G44 represent coefficients related to the number of aromatic rings at the second temperature, and can take values of 0.41 and 0.08 respectively.

[0154] If the second factor at the second temperature is greater than 0, the intermediate variable (cr2) and the total number of rings (or the total number of rings in the average molecule of the fraction) at the second temperature can be calculated successively according to the following formula:

[0155] cr2 = H11 × w2 + H22 / mw

[0156] rt2 = I11 + I22 × mw × w2

[0157] Among them, cr2 represents the intermediate variable at the second temperature, w2 represents the second factor at the second temperature, mw represents the molecular weight, rt2 represents the total number of rings at the second temperature, H11 and H22 represent coefficients related to the intermediate variable at the second temperature, and can take values of 775.0 and 11500.0 respectively, and I11 and I22 represent coefficients related to the total number of rings at the second temperature, and can take values of 1.55 and 0.146 respectively.

[0158] If the second factor at the second temperature is less than 0, the intermediate variable (cr2) and the total number of rings (or the total number of rings in the average molecule of the fraction) at the second temperature can be calculated successively according to the following formula:

[0159] cr2 = H33 × w2 + H44 / mw

[0160] rt2 = I33 + I44 × mw × w2

[0161] Wherein, cr2 represents the intermediate variable at the second temperature, w2 represents the second factor at the second temperature, mw represents the molecular weight, rt2 represents the total number of rings at the second temperature, H33 and H44 represent coefficients related to the intermediate variable at the second temperature, and can be respectively 1440.0 and 12100.0, and I33 and I44 represent coefficients related to the total number of rings at the second temperature, and can be respectively 1.55 and 0.180.

[0162] In some embodiments, after determining the percentage of aromatic ring carbon atoms in the total carbon atoms, the number of aromatic rings, the intermediate variable, the total number of rings at the first temperature and the percentage of aromatic ring carbon atoms in the total carbon atoms, the number of aromatic rings, the intermediate variable, the total number of rings at the second temperature, the structural composition of other fraction oils can also be determined by the following methods:

[0163] Determine the percentage of naphthene ring carbon atoms in the total carbon atoms according to the intermediate variable and the percentage of aromatic ring carbon atoms in the total carbon atoms;

[0164] Determine the percentage of alkane carbon atoms in the total carbon atoms according to the intermediate variable;

[0165] Determine the number of naphthene rings according to the total number of rings and the number of aromatic rings.

[0166] In some embodiments, the structural composition of the fraction oil may include: total carbon atoms, the percentage of aromatic ring carbon atoms in the total carbon atoms, the percentage of naphthene ring carbon atoms in the total carbon atoms, the percentage of alkane carbon atoms in the total carbon atoms, the number of aromatic rings, the number of naphthene rings, the total number of rings, etc. After determining the percentage of aromatic ring carbon atoms in the total carbon atoms, the number of aromatic rings, and the total number of rings, the percentage of naphthene ring carbon atoms in the total carbon atoms can also be determined according to the above intermediate variable and the percentage of aromatic ring carbon atoms in the total carbon atoms according to the following formula:

[0167] cn = cr - ca

[0168] Wherein, cn represents the percentage of naphthene ring carbon atoms in the total carbon atoms, cr represents the intermediate variable, and ca represents the percentage of aromatic ring carbon atoms in the total carbon atoms.

[0169] It should be noted that the number of cycloalkane ring carbon atoms in the total carbon atoms at the first temperature can be determined using the above formula based on the intermediate variable at the first temperature and the percentage of cycloalkane ring carbon atoms in the total carbon atoms at the first temperature. Also, the number of cycloalkane ring carbon atoms in the total carbon atoms at the second temperature can be determined using the above formula based on the intermediate variable at the second temperature and the percentage of cycloalkane ring carbon atoms in the total carbon atoms at the second temperature.

[0170] Based on the above intermediate variable, the number of alkane carbon atoms in the total carbon atoms can be determined according to the following formula:

[0171] cp = 100 - cr

[0172] Wherein, cp represents the percentage of alkane carbon atoms in the total carbon atoms, and cr represents the intermediate variable.

[0173] It should be noted that the percentage of alkane carbon atoms in the total carbon atoms at the first temperature can be determined using the above formula based on the intermediate variable at the first temperature. Also, the percentage of alkane carbon atoms in the total carbon atoms at the second temperature can be determined using the above formula based on the intermediate variable at the second temperature.

[0174] Based on the above total number of rings and the above number of aromatic rings, the number of cycloalkane rings can be determined according to the following formula:

[0175] rn = rt - ra

[0176] Wherein, rn represents the number of cycloalkane rings, rt represents the total number of rings, and ra represents the number of aromatic rings.

[0177] It should be noted that the number of cycloalkane rings at the first temperature can be determined using the above formula based on the total number of rings at the first temperature and the number of aromatic rings at the first temperature. Also, the number of cycloalkane rings at the second temperature can be determined using the above formula based on the total number of rings at the second temperature and the number of aromatic rings at the second temperature.

[0178] By obtaining data on three properties, namely refractive index, density, and molecular weight, of the known crude oil properties, the structural composition of the distillate oil can be predicted simply, quickly, and at low cost, thereby laying a foundation for formulating a reasonable crude oil refining strategy based on the structural composition of the distillate oil.

[0179] In some embodiments, the above first crude oil physical property data to be predicted further includes Reid vapor pressure. Correspondingly, when obtaining the above first crude oil physical property data, in specific implementation, it may further include:

[0180] Obtaining the characteristic factor and the target boiling point associated with the Reid vapor pressure;

[0181] Processing the characteristic factor and the target boiling point data using the crude oil physical property prediction model associated with the Reid vapor pressure in the following manner:

[0182] Determine the vapor pressure of the petroleum fraction based on the characterization factor and the target boiling point;

[0183] Determine the ratio based on the vapor pressure of the petroleum fraction;

[0184] Determine the Reid vapor pressure based on the ratio and the vapor pressure of the petroleum fraction.

[0185] In some embodiments, the above target boiling point may be the mid-boiling point in the above-known physical properties data of the crude oil. The step of determining the vapor pressure of the petroleum fraction based on the characterization factor and the target boiling point may include:

[0186] First, based on the mid-boiling point, the normal boiling point can be determined according to the following formula:

[0187] Tb = meabp + N

[0188] where Tb represents the normal boiling point, meanbp represents the mid-boiling point, and N represents a coefficient related to the normal boiling point, which can take the value of 273.15.

[0189] Second, based on the calculated normal boiling point, the normal boiling point determinant can be determined according to the following formula:

[0190] F = (Tb - P) / 111.1

[0191] where F represents the normal boiling point determinant, Tb represents the normal boiling point, and P represents a coefficient related to the normal boiling point determinant, which can take the value of 366.5.

[0192] It should be noted that it can be judged whether the normal boiling point (Tb) is less than a certain preset threshold (for example: less than the coefficient 366.5 related to the normal boiling point determinant). If it is less than 366.5, the normal boiling point determinant F = 0.0. If it is greater than a certain preset threshold (for example: greater than 477.6), then F = 1.0. If it is between the two, the normal boiling point determinant can be calculated by the above formula.

[0193] Second, based on the normal boiling point determinant, the characterization factor K, and the normal boiling point, the index X can be calculated according to the following formula, where the index X is used to calculate the vapor pressure of the petroleum fraction:

[0194] Tb ′ = Tb - Q1×F×(satsnk - Q2)×log 10 (vpe / Q3)

[0195] X = (Tb ′ / T - Q4×10 -4 ×Tb ′) / (Q5 - Q6×Tb ′ )

[0196] wherein, Tb ′ represents an intermediate quantity (determined by the characterization factor and the estimated vapor pressure), Tb represents the normal boiling point, F represents the normal boiling point determining factor, satsnk represents the characterization factor K, vpe represents the estimated vapor pressure, X represents the vapor pressure parameter, T represents the thermodynamic temperature at the current temperature (where T = t + 273.15, t is the current temperature), Q1, Q2, Q3 represent coefficients related to Tb ′ and can take values of 1.39, 12.0, 1.013 respectively, Q4, Q5, Q6 represent coefficients related to the vapor pressure parameter X and can take values of 5.16, 748.1, 0.3861 respectively.

[0197] According to the calculated magnitude of the vapor pressure parameter X, it can be divided into three cases. That is: when X is less than 0.0013, k = 0; when X is greater than 0.0022, k = 2; when it is between the two, k = 1 (where k represents an index, and corresponding calculation coefficients can be taken from the coefficient matrix according to different X values). That is, according to the magnitude of different X, different calculation coefficient matrices c can be selected.

[0198] Among them, the calculation coefficient matrix can be set as follows:

[0199] c = [[2770.085, 6.412631, 36.0, 0.989679], [2663.129, 5.994296, 95.76, 0.972546], [3000.538, 6.761560, 43.0, 0.987672]]

[0200] Finally, according to the selected calculation coefficients and the vapor pressure parameter X, the vapor pressure of the petroleum fraction can be determined according to the following formula:

[0201] vp = 10 ((c[k][0]×X-c[k][1]) / (c[k][2]×X-c[k][3])-2.8750)

[0202] wherein, vp represents the vapor pressure of the petroleum fraction, X represents the vapor pressure parameter, c represents a 3×4 - dimensional calculation coefficient matrix, the index k is obtained according to different X values, different calculation coefficients are obtained from the matrix c, and c[k][i] represents the value at the (k + 1)-th row and the (i + 1)-th column position in the matrix c. (For example, when X is less than 0.0013, k = 0, c[k][0] = 2770.085, c[k][1] = 6.412631, c[k][2] = 36.0, c[k][3] = 0.989679)

[0203] It should be noted that for the estimated vapor pressure (vpe), the initial value can be set to 0. The vp obtained from each iterative calculation is assigned to vpe, and the iteration is continuously performed until the deviation between vp and vpe is less than a certain threshold (e.g., less than 10 -5 ) or the number of iterations exceeds 100, then the iteration stops. It should be noted that the above threshold and the number of iterations can be set according to actual needs, and this specification does not make specific limitations in this regard.

[0204] In some embodiments, after obtaining the vapor pressure of the petroleum fraction, based on the vapor pressure of the petroleum fraction, the ratio can be determined according to the following formula:

[0205] When the vapor pressure of the petroleum fraction is less than 0.153, then the ratio Ratio = 1.02;

[0206] When the vapor pressure of the petroleum fraction is greater than 0.509, then the ratio Ratio = 1.06;

[0207] (Wherein, a ratio matrix can be pre - constructed, e.g., Ratio = [1.02, 1.03, 1.04, 1.05, 1.055, 1.06], and a vapor pressure matrix of petroleum fraction VpGas = [0.153, 0.206, 0.291, 0.367, 0.443, 0.509] can be constructed. When according to the vapor pressure of the petroleum fraction (vp) obtained before calculation, within the interval in VpGas, the Aitken interpolation algorithm can be used to calculate the ratio (Ratio) corresponding to the current vapor pressure of the petroleum fraction. When the vp value exceeds the upper and lower limits (0.153, 0.509) of VpGas, the interpolation algorithm is not used, and the upper and lower limit values (1.02, 1.06) of Ratio can be taken respectively.

[0208] It should be noted that the parameters in the above Ratio matrix and VpGas matrix are not limited to the above examples. Those skilled in the art may make other changes under the inspiration of the technical essence of the embodiments of this specification, but as long as the functions and effects achieved are the same or similar to those of the embodiments of this specification, they should all be covered within the protection scope of the embodiments of this specification.

[0209] When it is between the two, the Aitken interpolation is used to calculate the Ratio value.

[0210]

[0211] For the above Aitken interpolation, when using two nodes for interpolation, that is, first - order interpolation, the fixed interpolation point is set as x0, and the variable interpolation node is x i . Linear interpolation is performed according to the two nodes, and the calculation formula is:

[0212]

[0213] Among them, f1(x i ) represents the first interpolation result of node x, x0 is a fixed interpolation node, and x i is a variable interpolation node.

[0214] When there are two fixed interpolation nodes x0 and x1, and adding a variable interpolation node x i , interpolation is performed using three nodes, that is, quadratic interpolation, and the calculation formula is:

[0215]

[0216] After arrangement, f2(x i ) can be calculated from f1(x1) and f1(x i ), and the formula is:

[0217]

[0218] And so on, the formula for k - th interpolation is as follows:

[0219]

[0220] In some embodiments, after determining the vapor pressure and ratio of the petroleum fraction, the Reid vapor pressure can be determined according to the following formula:

[0221] rvp = vp / Ratio * L

[0222] Among them, rvp represents the Reid vapor pressure, vp represents the vapor pressure of the petroleum fraction, Ratio represents the ratio, and L represents a coefficient related to the Reid vapor pressure, which can take 100.0.

[0223] By obtaining the characteristic factor and the mid - average boiling point associated with the Reid vapor pressure, and then inputting the characteristic factor and the mid - average boiling point associated with the Reid vapor pressure into the crude oil physical property prediction model associated with the Reid vapor pressure, the prediction data of the Reid vapor pressure can be obtained accurately and quickly.

[0224] In some embodiments, the first crude oil physical property data to be predicted may further include the cetane index. Accordingly, when obtaining the first crude oil physical property data, specifically, it may further include:

[0225] Obtaining the aniline point and density data associated with the cetane index;

[0226] Using the crude oil physical property prediction model associated with the cetane index to process the aniline point and density data to obtain the cetane index.

[0227] In some embodiments, the density data associated with the cetane index may be the density at 15°C. The cetane index can be determined according to the following formula:

[0228] di=((W1×ta+W2)×(W3-W4×sg_15)) / (W5×sg_15)

[0229] where di represents the cetane index, ta represents the aniline point, sg_15 represents the density at 15°C, and W1, W2, W3, W4, and W5 represent the coefficients related to the cetane index, which can take the values of 1.8, 32.0, 141.5, 131.5, and 100.0 respectively.

[0230] By obtaining the aniline point and density data associated with the cetane index and then selecting the crude oil physical property prediction model associated with the cetane index, the cetane index can be accurately and quickly predicted.

[0231] Through the above crude oil physical property prediction models associated with the structural composition of distillate oil, the Reid vapor pressure, and the cetane index, some unknown physical properties of crude oil can be quickly calculated, providing basic data support and services for crude oil procurement, plan optimization, scheduling optimization, process simulation, etc., solving the technical problems of high cost and long detection cycle for crude oil physical property detection, and being able to predict the properties of crude oil at a lower cost, more efficiently, and more accurately.

[0232] S103: Determine the crude oil production and refining strategy according to the first crude oil physical property data and the second crude oil physical property data.

[0233] In some embodiments, after obtaining the predicted first crude oil physical property data, the refining strategy of the crude oil can be determined based on the first crude oil physical property data and the second crude oil physical property data, and the crude oil can be refined based on this refining strategy.

[0234] Through the known crude oil physical property data and the predicted crude oil physical property data, a reasonable crude oil refining strategy can be formulated, thereby improving the efficiency and accuracy of crude oil refining and saving a large amount of time and labor costs.

[0235] In some embodiments, after predicting the structural composition of the distillate oil, petrochemical products to be refined or produced can be determined based on the percentage of aromatic ring carbon atoms in the total carbon atoms, the percentage of naphthene ring carbon atoms in the total carbon atoms, the percentage of alkane carbon atoms in the total carbon atoms, the number of aromatic rings, the number of naphthene rings, etc. in the structural composition of the distillate oil. For example, a distillate oil structure with a high aromatic ring carbon content (e.g., a relatively high percentage of aromatic ring carbon atoms in the total carbon atoms) can be used to produce petrochemical products such as aromatics, solvents, and lubricating oils. A distillate oil structure with a high naphthene ring carbon content (e.g., a relatively high percentage of naphthene ring carbon atoms in the total carbon atoms) can be used to produce alkane fuels and lubricating oils, etc. Since different distillate oil structural compositions affect the properties and combustion behavior of fuels, distillates with a relatively high proportion of alkane carbon in the total carbon tend to have better combustion performance, while distillates with a relatively high proportion of aromatic ring carbon in the total carbon tend to have poorer combustion performance. Therefore, different distillate oil structural compositions will affect the properties and quality of petroleum processing products. By evaluating the structural composition of the distillate oil, the quality characteristics of the products that may be obtained during the petroleum processing can be predicted, thereby optimizing the production process and selecting appropriate raw materials, and solving the problems of high cost and time-consuming of obtaining the structural composition of the distillate oil through laboratory analysis in the existing methods.

[0236] After predicting the Reid vapor pressure, a refining strategy for refining crude oil into gasoline can be formulated based on the predicted Reid vapor pressure, and the crude oil can be refined. After predicting the cetane index, a refining strategy for refining crude oil into diesel can also be formulated, and the crude oil can be refined.

[0237] The above method will be described below in conjunction with a specific embodiment. However, it should be noted that this specific embodiment is only for better explaining the present application and does not constitute an improper limitation of the present application.

[0238] Before the specific implementation, a crude oil evaluation database can be established, and multiple known crude oil physical property data can be pre-stored in the database. Multiple crude oil physical property prediction models can also be pre-trained, and each crude oil physical property prediction model can predict different crude oil physical property data.

[0239] In specific implementation, first, known crude oil physical property data associated with the crude oil physical property data to be predicted can be obtained from the crude oil evaluation database. Second, according to the prediction requirements, a crude oil physical property prediction model that matches the crude oil physical property data to be predicted can be selected from multiple crude oil physical property prediction models, and then the known crude oil physical property data associated with the crude oil physical property data to be predicted is input into the crude oil physical property prediction model. Finally, the predicted crude oil physical property data that can meet the user's requirements can be obtained. Finally, a crude oil refining strategy can be generated based on the predicted crude oil physical property data and the known crude oil physical property data, and the crude oil can be refined based on the crude oil refining strategy, and finally petrochemical products after refining can be obtained with low cost, high efficiency and accuracy.

[0240] In a specific scenario example, the method for determining a crude oil refining strategy based on crude oil physical properties provided in the embodiments of this specification can be applied, and unknown crude oil physical property data can be predicted based on the known crude oil physical property data associated with the crude oil physical property data to be predicted. For example:

[0241] (1) The refractive index can be calculated based on the known average boiling point, molecular weight, and density at 20°C.

[0242] Density value (input) Average boiling point (input) Refractive index (output) 0.812 300 1.46

[0243] (2) The cetane index can be calculated based on the known density at 15°C and aniline point.

[0244] Density value (input) Average boiling point (input) Cetane index (output) 0.812 300 66.66

[0245] (3) The Reid vapor pressure can be calculated based on the known characterization factor K and average boiling point.

[0246] Characteristic factor K (input) Average boiling point (input) Reid vapor pressure (Pa) (output) 12.44 300 0.45

[0247] (4) The structural composition of the distillate oil can be calculated based on the known refractive index, density at 20°C, and molecular weight.

[0248] Input properties Refractive index Density at 20 °C Molecular weight Input value 1.4231 0.812 196

[0249]

[0250] Among them, the known crude oil physical property data and the predicted unknown crude oil physical property data can be as shown in the following table:

[0251] Serial number Known physical property data of crude oil Predicted unknown physical property data of crude oil 1 Average boiling point, molecular weight, density at 20 °C Refractive index 2 Density at 15 °C, aniline point Cetane index 3 Characteristic factor K, average boiling point Reid vapor pressure 4 Refractive index, density at 20 °C, molecular weight Structural composition of distillate oil

[0252] By using the correlation relationship between crude oil physical property data to predict unknown physical properties with known key physical properties, more comprehensive crude oil physical property data can be obtained quickly and accurately. By obtaining comprehensive and accurate crude oil physical property data, it can lay a foundation for accurate, fast and low-cost crude oil refining and processing.

[0253] Although this specification provides method operation steps or device structures as described in the following embodiments or as shown in the appended Figure 2 drawings, more or fewer operation steps or module units may be included in the method or device based on routine or non-creative labor. In steps or structures where there is no necessary causal relationship logically, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiments of this specification or the drawings. When the described method or module structure is applied to actual devices, servers or terminal products, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiments or the drawings (for example, in an environment of parallel processors or multi-threaded processing, and even including an implementation environment of distributed processing or server clusters).

[0254] Based on the above method for determining a crude oil refining strategy based on crude oil physical properties, this specification also presents an embodiment of a device for determining a crude oil refining strategy based on crude oil physical properties. As Figure 2 shown, the device may specifically include the following modules:

[0255] An acquisition module 201, which can be used to acquire second crude oil physical property data associated with first crude oil physical property data to be predicted;

[0256] A prediction module 202, which can be used to process the second crude oil physical property data using a crude oil physical property prediction model to obtain the first crude oil physical property data;

[0257] A refining module 203, which can be used to determine a crude oil refining strategy based on the first crude oil physical property data and the second crude oil physical property data.

[0258] In some embodiments, the above prediction module 202 may specifically be used to select a crude oil physical property prediction model that matches the first crude oil physical property data from multiple crude oil physical property prediction models; wherein, each crude oil physical property prediction model among the multiple crude oil physical property prediction models corresponds to crude oil physical property data; and use the selected crude oil physical property prediction model to process the second crude oil physical property data.

[0259] In some embodiments, the above prediction module 202 may specifically further be used to perform a correlation analysis on multiple crude oil physical property data samples to select crude oil physical property data samples associated with a target crude oil physical property data sample from the multiple crude oil physical property data samples; and train a crude oil physical property prediction model based on the selected crude oil physical property data samples and the target crude oil physical property data sample.

[0260] In some embodiments, the above-mentioned prediction module 202 may specifically be further configured to obtain the refractive index, density, and molecular weight associated with the structural composition of the distillate oil; process the refractive index, density, and molecular weight by using a crude oil physical property prediction model associated with the structural composition of the distillate oil in the following manner: determine different intermediate factors at different temperatures according to the refractive index and the density; determine the structural composition of the distillate oil at different temperatures according to the molecular weight and the intermediate factors.

[0261] In some embodiments, the different intermediate factors at different temperatures may include: the first factor and the second factor at the first temperature, and the first factor and the second factor at the second temperature. Correspondingly, the step of determining the structural composition of the distillate oil at different temperatures according to the molecular weight and the intermediate factors may include: determining the percentage of aromatic ring carbon atoms in the total carbon atoms and the number of aromatic rings at the first temperature according to the molecular weight and the first factor at the first temperature; determining the intermediate variable and the total number of rings at the first temperature according to the molecular weight and the second factor at the first temperature; determining the percentage of aromatic ring carbon atoms in the total carbon atoms and the number of aromatic rings at the second temperature according to the molecular weight and the first factor at the second temperature; determining the intermediate variable and the total number of rings at the second temperature according to the molecular weight and the second factor at the second temperature.

[0262] In some embodiments, the above-mentioned prediction module 202 may specifically be further configured to determine the percentage of naphthene ring carbon atoms in the total carbon atoms according to the intermediate variable and the percentage of aromatic ring carbon atoms in the total carbon atoms; determine the percentage of alkane carbon atoms in the total carbon atoms according to the intermediate variable; determine the number of naphthene rings according to the total number of rings and the number of aromatic rings.

[0263] In some embodiments, the above-mentioned prediction module 202 may specifically be further configured to obtain the characterization factor and the target boiling point associated with the Reid vapor pressure; process the characterization factor and the target boiling point data by using a crude oil physical property prediction model associated with the Reid vapor pressure in the following manner: determine the vapor pressure of the petroleum fraction according to the characterization factor and the target boiling point; determine the ratio according to the vapor pressure of the petroleum fraction; determine the Reid vapor pressure according to the ratio and the vapor pressure of the petroleum fraction.

[0264] In some embodiments, the above-mentioned prediction module 202 may specifically be further configured to obtain the aniline point and the density data associated with the cetane index; process the aniline point and the density data by using a crude oil physical property prediction model associated with the cetane index to obtain the cetane index.

[0265] It should be noted that the units, devices, modules, etc. illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. For the convenience of description, when describing the above devices, they are divided into various modules according to functions for separate description. Of course, when implementing this specification, the functions of each module can be implemented in the same or multiple software and / or hardware, or the modules implementing the same function can be realized by the combination of multiple sub-modules or sub-units, etc. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be in electrical, mechanical or other forms.

[0266] As can be seen from the above, based on the device for determining a crude oil refining strategy based on crude oil physical properties provided by the embodiments of this specification, the unknown physical properties can be predicted according to the known key physical properties through the correlation relationship between physical properties, so that more comprehensive crude oil physical property data can be obtained quickly and accurately, and thus a more reasonable and effective crude oil refining strategy can be determined, and different crude oils with different properties can be reasonably refined into different petrochemical products.

[0267] The embodiments of this specification also provide an electronic device for a method of determining a crude oil refining strategy based on crude oil physical properties, including a processor and a memory for storing processor-executable instructions. When specifically implemented, the processor can execute the following steps according to the instructions: obtaining second crude oil physical property data associated with the first crude oil physical property data to be predicted; processing the second crude oil physical property data by using a crude oil physical property prediction model to obtain the first crude oil physical property data; and determining a crude oil refining strategy according to the first crude oil physical property data and the second crude oil physical property data.

[0268] In order to be able to complete the above instructions more accurately, refer to Figure 3 As shown, the embodiments of this specification also provide another specific electronic device. Among them, the electronic device includes a network communication port 301, a processor 302, and a memory 303. The above structures are connected by internal cables so that each structure can perform specific data interactions.

[0269] Among them, the network communication port 301 can specifically be used to obtain second crude oil physical property data associated with the first crude oil physical property data to be predicted.

[0270] The processor 302 can specifically be used to process the second crude oil physical property data by using the crude oil physical property prediction model to obtain the first crude oil physical property data; and determine the crude oil refining strategy according to the first crude oil physical property data and the second crude oil physical property data.

[0271] The memory 303 can specifically be used to store corresponding instruction programs.

[0272] In this embodiment, the network communication port 301 can be bound to different communication protocols, so as to send or receive different data. For example, the network communication port can be a port responsible for web data communication, can also be a port responsible for FTP data communication, and can also be a port responsible for mail data communication. In addition, the network communication port can also be a physical communication interface or communication chip. For example, it can be a wireless mobile network communication chip, such as GSM, CDMA, etc.; it can also be a Wifi chip; it can also be a Bluetooth chip.

[0273] In this embodiment, the processor 302 can be implemented in any suitable manner. For example, the processor can be in the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, etc. This specification does not make any limitations.

[0274] In this embodiment, the memory 303 can include multiple levels. In a digital system, anything that can store binary data can be a memory; in an integrated circuit, a circuit without a physical form but with a storage function is also called a memory, such as RAM, FIFO, etc.; in a system, a storage device with a physical form is also called a memory, such as a memory module, a TF card, etc.

[0275] An embodiment of this specification also provides a computer storage medium based on the above-mentioned method for determining a crude oil refining strategy based on crude oil physical properties. The computer storage medium stores computer program instructions, and when the computer program instructions are executed, it realizes: obtaining second crude oil physical property data associated with the first crude oil physical property data to be predicted; processing the second crude oil physical property data by using the crude oil physical property prediction model to obtain the first crude oil physical property data; and determining the crude oil refining strategy according to the first crude oil physical property data and the second crude oil physical property data.

[0276] In this embodiment, the above storage medium includes, but is not limited to, Random Access Memory (RAM), Read-Only Memory (ROM), Cache, Hard Disk Drive (HDD), or Memory Card. The memory can be used to store computer program instructions. The network communication unit can be set according to the standards specified by the communication protocol and is an interface for network connection and communication.

[0277] Although this specification provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-creative means. The step order listed in the embodiments is only one of the ways of the execution order of numerous steps and does not represent the only execution order. When the actual device or client product is executed, it can be executed in the order of the method shown in the embodiments or the drawings or executed in parallel (for example, in a parallel processor or multi-threaded processing environment, or even in a distributed data processing environment). The term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, product or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, product or device. Without further limitation, there is no exclusion of the presence of additional identical or equivalent elements in the process, method, product or device comprising the said elements. The terms first, second, etc. are used to denote names and do not denote any particular order.

[0278] Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, the method steps can be logically programmed to enable the controller to implement the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Therefore, such a controller can be regarded as a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or the structures within the hardware component.

[0279] This specification can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform specific tasks or implement specific abstract data types. This specification can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0280] From the description of the above embodiments, those skilled in the art can clearly understand that this specification can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of this specification can essentially be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, mobile terminal, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments of this specification.

[0281] The various embodiments in this specification are described in a progressive manner. For the same or similar parts between the various embodiments, reference can be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments. This specification can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on.

[0282] Although this specification is depicted through embodiments, those of ordinary skill in the art know that this specification has many variations without departing from the spirit of this specification. It is hoped that the appended claims will cover these variations without departing from the spirit of this specification.

Claims

1. A method for determining a crude oil refining strategy based on the physical properties of crude oil, characterized in that, Including: Obtain second crude oil physical property data associated with the first crude oil physical property data to be predicted; Process the second crude oil physical property data using a crude oil physical property prediction model to obtain the first crude oil physical property data; Determine a crude oil refining strategy based on the first crude oil physical property data and the second crude oil physical property data; The first crude oil physical property data to be predicted includes the structural composition of the distillate oil. Correspondingly, the method further includes: Obtain the refractive index, density, and molecular weight associated with the structural composition of the distillate oil; Process the refractive index, density, and molecular weight using a crude oil physical property prediction model associated with the structural composition of the distillate oil in the following manner: Determine different intermediate factors at different temperatures based on the refractive index and the density; the different intermediate factors at different temperatures include: the first factor and the second factor at the first temperature, and the first factor and the second factor at the second temperature; Determine the structural composition of the distillate oil at different temperatures based on the molecular weight and the intermediate factors; Among them, the step of determining the structural composition of the distillate oil at different temperatures based on the molecular weight and the intermediate factors includes: Determine the percentage of aromatic ring carbon atoms in the total carbon atoms and the number of aromatic rings at the first temperature based on the molecular weight and the first factor at the first temperature; Determine the intermediate variable and the total number of rings at the first temperature based on the molecular weight and the second factor at the first temperature; Determine the percentage of aromatic ring carbon atoms in the total carbon atoms and the number of aromatic rings at the second temperature based on the molecular weight and the first factor at the second temperature; Determine the intermediate variable and the total number of rings at the second temperature based on the molecular weight and the second factor at the second temperature.

2. The method according to claim 1, wherein The method further includes: Select a crude oil physical property prediction model that matches the first crude oil physical property data from multiple crude oil physical property prediction models; among them, each crude oil physical property prediction model in the multiple crude oil physical property prediction models corresponds to crude oil physical property data; Process the second crude oil physical property data using the selected crude oil physical property prediction model.

3. The method according to claim 1, wherein The crude oil physical property prediction model is established by the following method: Conduct a correlation analysis on multiple crude oil physical property data samples to select crude oil physical property data samples associated with the target crude oil physical property data sample from the multiple crude oil physical property data samples; Train a crude oil physical property prediction model based on the selected crude oil physical property data samples and the target crude oil physical property data samples.

4. The method according to claim 1, characterized in that, The method further includes: Determine the percentage of naphthene ring carbon atoms in the total carbon atoms based on the intermediate variable and the percentage of aromatic ring carbon atoms in the total carbon atoms; Determine the percentage of alkane carbon atoms in the total carbon atoms based on the intermediate variable; Determine the number of naphthene rings based on the total number of rings and the number of aromatic rings.

5. The method according to claim 1, characterized in that, The first crude oil physical property data to be predicted further includes the Reid vapor pressure. Correspondingly, the method further includes: Obtain the characterization factor and the target boiling point associated with the Reid vapor pressure; Process the characterization factor and the target boiling point data using a crude oil physical property prediction model associated with the Reid vapor pressure in the following manner: Determine the vapor pressure of the petroleum fraction based on the characterization factor and the target boiling point; Determine the ratio; Determine the Reid vapor pressure based on the ratio and the vapor pressure of the petroleum fraction.

6. The method according to claim 1, characterized in that The first crude oil physical property data to be predicted further includes the cetane index. Correspondingly, the method further includes: Obtaining aniline point and density data associated with the cetane index; Processing the aniline point and density data by using a crude oil physical property prediction model associated with the cetane index to obtain the cetane index.

7. An apparatus for determining a crude oil refining strategy based on the physical properties of crude oil, characterized in that, Including: An acquisition module for obtaining second crude oil physical property data associated with the first crude oil physical property data to be predicted; A prediction module for processing the second crude oil physical property data by using a crude oil physical property prediction model to obtain the first crude oil physical property data; A refining module for determining a crude oil refining strategy according to the first crude oil physical property data and the second crude oil physical property data; The first crude oil physical property data to be predicted includes the structural composition of the distillate oil. Correspondingly, the device further includes: Obtaining the refractive index, density, and molecular weight associated with the structural composition of the distillate oil; Processing the refractive index, density, and molecular weight by using a crude oil physical property prediction model associated with the structural composition of the distillate oil in the following manner: Determining different intermediate factors at different temperatures according to the refractive index and the density; the different intermediate factors at different temperatures include: a first factor and a second factor at a first temperature, and a first factor and a second factor at a second temperature; Determining the structural composition of the distillate oil at different temperatures according to the molecular weight and the intermediate factors; Wherein, the determining the structural composition of the distillate oil at different temperatures according to the molecular weight and the intermediate factors includes: Determining the percentage of aromatic ring carbon atoms in the total carbon atoms and the number of aromatic rings at the first temperature according to the molecular weight and the first factor at the first temperature; Determining an intermediate variable and the total number of rings at the first temperature according to the molecular weight and the second factor at the first temperature; Determining the percentage of aromatic ring carbon atoms in the total carbon atoms and the number of aromatic rings at the second temperature according to the molecular weight and the first factor at the second temperature; Determining an intermediate variable and the total number of rings at the second temperature according to the molecular weight and the second factor at the second temperature.

8. A computer-readable storage medium, characterized in that, Stored thereon are computer instructions which, when executed by a processor, implement the steps of the method according to any one of claims 1 to 6.

Images