A method, device and equipment for calculating molecular composition of a distillate fraction and a storage medium

Abstract

The present disclosure relates to a distillate molecular composition calculation method, device, equipment and storage medium, the method comprising: obtaining molecular composition data of feed of a fractionating device, and distillation range data and yield data of each product distillate, constructing a distillate cutting model based on the distillation range data and yield data, the distillate cutting model comprising temperature intervals, and content data corresponding to each temperature interval, calculating separation coefficients of each distillate in each temperature interval by using a separation coefficient calculation formula based on the distillate cutting model, obtaining a single molecule separation coefficient model, obtaining boiling point data of each single molecule in the feed based on the molecular composition data of the feed, and obtaining the content of each single molecule in each distillate based on the boiling point data and the single molecule separation coefficient model; the single molecule separation coefficient model is obtained through the distillation range data and yield data of the distillate, and the content of the single molecule in each distillate after distillation of the feed can be determined based on the separation coefficient.

Description

Technical Field

[0001] This disclosure relates to the field of petroleum processing technology, and in particular to a method, apparatus, equipment and storage medium for calculating the molecular composition of a fraction. Background Technology

[0002] The composition of crude oil products is very complex. In some technical solutions, the different boiling points of individual molecules in crude oil products are utilized to distill different product fractions, including naphtha, diesel, wax oil and residue oil, from crude oil products.

[0003] However, due to the overlap in distillation ranges between different components, the separation accuracy can easily be low. Summary of the Invention

[0004] To address the problems existing in the prior art, at least one embodiment of this specification provides a method, apparatus, device, and storage medium for calculating the molecular composition of a fraction.

[0005] Firstly, embodiments of this specification provide a method for calculating the single molecules of a distillate, the method comprising:

[0006] Obtain molecular composition data of the feed to the fractionation unit, as well as distillation range data and yield data of each product fraction;

[0007] A fraction cutting model is constructed based on the distillation range data and yield data. The fraction cutting model includes temperature ranges and content data corresponding to each temperature range.

[0008] Based on the aforementioned fraction cutting model, the separation coefficient of each fraction in each temperature range is calculated using the separation coefficient calculation formula, thus obtaining the single-molecule separation coefficient model.

[0009] Based on the molecular composition data of the feed, the boiling point data of various single molecules in the feed are obtained;

[0010] Based on the boiling point data and the single-molecule separation coefficient model, the content of each single molecule in each fraction is obtained.

[0011] Based on the above technical solutions, the embodiments of this specification can be further improved as follows.

[0012] In one possible implementation, the step of constructing a fractional cut model based on the distillation range data and yield data, wherein the fractional cut model includes temperature range and content data of the fractions, includes:

[0013] Obtain the temperature range covered by the distillation range data of each fraction;

[0014] The temperature range is divided using the distillation range data to obtain multiple temperature intervals;

[0015] A fractional division sub-model is constructed using the yield data of each fraction and the content of the corresponding fraction in each temperature range.

[0016] All fractionation sub-models are merged to obtain the fractionation model.

[0017] In one possible implementation, the separation coefficient is calculated as follows:

[0018]

[0019] Where, n ij m represents the separation coefficient of the i-th fraction in the j-th temperature range. ij Y represents the content of the i-th fraction in the j-th temperature range. i This represents the yield of the i-th fraction.

[0020] In one possible implementation, the distillation range data includes the initial boiling point and the final boiling point.

[0021] In one possible implementation, the step of acquiring the feed single-molecule data and the boiling point data of each single molecule includes:

[0022] Obtain the content of each monomer in the feed;

[0023] Calculate the boiling point of each unimolecular.

[0024] In one possible implementation, calculating the boiling point of each unimolecular molecule includes:

[0025] For each of the aforementioned monomolecules, the number of each group constituting the monomolecule is obtained, and the contribution value of each group to the boiling point is obtained;

[0026] The number of each group constituting the monomolecule and the contribution value of each group to the boiling point are input into a pre-trained physical property calculation model to obtain the boiling point of the monomolecule output by the physical property calculation model.

[0027] The boiling point of the unimolecular molecules is calculated using the following property calculation model:

[0028]

[0029] Where T is the boiling point of the monomolecule, SOL is the monomolecule vector obtained by converting the number of each group constituting the monomolecule, and GROUP 11 The first contribution value vector is obtained by converting the contribution value of the primary group to the boiling point. 12The second contribution value vector is obtained by converting the contribution value of secondary groups to the boiling point. 1N The Nth contribution value vector is obtained by converting the contribution value of the Nth-level group to the boiling point. Numh is the number of atoms other than hydrogen atoms in a single molecule, d is the first preset constant, b is the second preset constant, and c is the third preset constant; N is a positive integer greater than or equal to 2.

[0030] In one possible implementation, before inputting the number of each group constituting the monomolecule and the contribution of each group to the boiling point into a pre-trained property calculation model, the method further includes:

[0031] The number of each group constituting the monomolecule is compared with the molecular information of template monomolecules with known boiling points pre-stored in the database; the molecular information includes: the number of each group constituting the template monomolecule.

[0032] Determine whether there exists a template monomolecule identical to the monomolecule described above;

[0033] If a template molecule identical to the single molecule exists, the boiling point of the template molecule is output as the boiling point of the single molecule.

[0034] If no template monomolecule identical to the monomolecule exists, then the step of inputting the number of each group constituting the monomolecule and the contribution value of each group to the boiling point into the pre-trained property calculation model is performed.

[0035] In one possible implementation, the step of training the physical property calculation model includes:

[0036] Construct a computational model for the physical properties of a single molecule;

[0037] The number of each group constituting a sample molecule is obtained; the physical properties of the sample molecule are known.

[0038] Input the number of each type of group contained in the sample single molecule into the physical property calculation model;

[0039] Obtain the predicted physical properties of the sample single molecule output by the physical property calculation model;

[0040] If the deviation between the predicted property and the known property is less than a preset deviation threshold, the property calculation model is determined to be converged. The contribution value of each group is obtained from the converged property calculation model and stored as the contribution value of the group to the property.

[0041] If the deviation between the predicted property and the known property is greater than or equal to the preset deviation threshold, the contribution value of each group in the property calculation model is adjusted until the property calculation model converges.

[0042] In one possible implementation, the step of obtaining the content of each monomolecule in each fraction based on the boiling point data and the monomolecule separation coefficient model includes:

[0043] The boiling point data of each monomolecule is compared with the temperature range in the monomolecule separation coefficient model to determine the temperature range to which each monomolecule belongs.

[0044] The content of each single molecule is obtained from the molecular composition data of the feed;

[0045] The content of each single molecule in each fraction is obtained based on the separation coefficient corresponding to the temperature range and the content of each single molecule.

[0046] Secondly, embodiments of this specification provide a computing device for fraction molecules, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0047] Memory, used to store computer programs;

[0048] A processor, when executing a program stored in memory, implements a method for calculating the molecular composition of a fraction in the first aspect or any possible implementation of the first aspect.

[0049] Thirdly, embodiments of this specification provide a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the method for calculating the molecular composition of a fraction in the first aspect or any possible implementation of the first aspect.

[0050] Fourthly, embodiments of this specification provide a calculation device for the molecular composition of a fraction, the device comprising:

[0051] The first acquisition module acquires the molecular composition data of the feed to the fractionation unit, as well as the distillation range data and yield data of each product fraction;

[0052] The construction module constructs a fraction cutting model based on the distillation range data and yield data. The fraction cutting model includes temperature ranges and content data corresponding to each temperature range.

[0053] The modeling module, based on the fraction cutting model, calculates the separation coefficient of each fraction in each temperature range using the separation coefficient calculation formula, and obtains the single-molecule separation coefficient model.

[0054] The second acquisition module acquires the boiling point data of various single molecules in the feed based on the molecular composition data of the feed.

[0055] The calculation module, based on the boiling point data and the single-molecule separation coefficient model, obtains the content of each single molecule in each fraction.

[0056] In one possible implementation, the building module includes:

[0057] The acquisition unit acquires the temperature range covered by the distillation range data of each fraction;

[0058] The cutting unit uses the distillation range data to cut the temperature range into multiple temperature intervals;

[0059] The construction unit utilizes the yield data of each fraction and the content of the corresponding fraction in each temperature range to construct the fractional cutting sub-model of the corresponding fraction;

[0060] The merging unit combines all the fractionation sub-models to obtain the fractionation model.

[0061] In one possible implementation, the separation coefficient is calculated as follows:

[0062]

[0063] Where, n ij m represents the separation coefficient of the i-th fraction in the j-th temperature range. ij Y represents the content of the i-th fraction in the j-th temperature range. i This represents the yield of the i-th fraction.

[0064] In one possible implementation, the distillation range data includes the initial boiling point and the final boiling point.

[0065] Compared with existing technologies, the above-described technical solution in this specification has the following advantages: This specification constructs a fractionation model based on distillation range data and yield data, thereby obtaining a single-molecule separation coefficient model. Then, based on the boiling point data and the single-molecule separation coefficient model, the content of single molecules in each fraction is obtained. This allows for the determination of the content of single molecules in each fraction after distillation of the feedstock based on the separation coefficient. Using this solution, in the rectification / distillation process of crude oil, by utilizing the actual production data of the unit and the single-molecule data of the crude oil, the content of the same single molecule in different fractions can be determined. That is, based on the separation coefficient, the accurate molecular composition of molecules in each fraction obtained when crude oil is used as feedstock for distillation can be determined. Attached Figure Description

[0066] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0067] Figure 1 The diagram shown is a schematic flowchart of a method for calculating the molecules of a distillate provided in an embodiment of this specification.

[0068] Figure 2 The diagram shown is a schematic flowchart of a method for calculating the molecules of another fraction provided in an embodiment of this specification.

[0069] Figure 3 The diagram shown is a schematic representation of a fraction cutting model provided in an embodiment of this specification.

[0070] Figure 4 The figure shown is a schematic diagram of a molecular segregation coefficient model provided in an embodiment of this specification;

[0071] Figure 5 The diagram shown is a flowchart of the method for calculating the boiling point of a molecule according to an embodiment of this specification.

[0072] Figure 6 The diagram shown is a flowchart of the method for training a physical property calculation model according to an embodiment of this specification;

[0073] Figure 7 The diagram shown is a flowchart of another method for calculating the boiling point of a molecule according to an embodiment of this specification.

[0074] Figure 8 The diagram shown is a schematic diagram of a computational device for calculating the molecules of a distillate, as provided in an embodiment of this specification.

[0075] Figure 9 The diagram shown is a schematic diagram of the structure of a calculation device for calculating the molecular composition of a fraction, as described in an embodiment of this specification.

[0076] [Explanation of Labels in the Attached Image]

[0077] 1110. Processor;

[0078] 1120. Communication interface;

[0079] 1130. Memory;

[0080] 1140. Communication bus;

[0081] 901. First Acquisition Module;

[0082] 902. Building Modules;

[0083] 903. Modeling Module;

[0084] 904. Second Acquisition Module;

[0085] 905. Calculation Module. Detailed Implementation

[0086] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this specification.

[0087] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0088] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0089] like Figure 1 As shown in the embodiments of this specification, a method for calculating the molecules of a distillate includes:

[0090] Step 101: Obtain the molecular composition data of the feed to the fractionation unit, as well as the distillation range data and yield data of each product fraction;

[0091] Step 102: Construct a fraction cutting model based on the distillation range data and yield data. The fraction cutting model includes temperature ranges and content data corresponding to each temperature range.

[0092] Step 103: Based on the fraction cutting model, calculate the separation coefficient of each fraction in each temperature range using the separation coefficient calculation formula to obtain the single-molecule separation coefficient model.

[0093] Step 104: Based on the molecular composition data of the feed, obtain the boiling point data of various single molecules in the feed;

[0094] Step 105: Based on the boiling point data and the single-molecule separation coefficient model, obtain the content of each single molecule in each fraction.

[0095] The molecular composition data of the feed includes the types of monomers in the feed and the content of each monomer. Figure 2 The flowchart of the single-molecule calculation method is shown. In this embodiment, a fraction cutting model is constructed based on the distillation range data and yield data of the fraction, thereby obtaining a single-molecule separation coefficient model. Then, based on the boiling point data and the single-molecule separation coefficient model, the content of single molecules in each fraction is obtained. The content of single molecules in each fraction after distillation of the feed can be determined based on the separation coefficient.

[0096] Based on the above embodiments, such as Figure 3 As shown, the step of constructing a fraction cutting model based on the distillation range data and yield data, wherein the fraction cutting model includes temperature ranges and content data corresponding to each temperature range, includes:

[0097] Obtain the temperature range covered by the distillation range data of each fraction;

[0098] The temperature range is divided using the distillation range data to obtain multiple temperature intervals;

[0099] A fractional division sub-model is constructed using the yield data of each fraction and the content of the corresponding fraction in each temperature range.

[0100] All fractionation sub-models are merged to obtain the fractionation model.

[0101] In some embodiments, the temperature range (60°C-360°C) covered by the distillation range data of each fraction (e.g., including 60°C, 165°C, 170°C, 180°C, 310°C, and 360°C) is obtained.

[0102] The temperature range is divided using the distillation range data to obtain multiple temperature intervals (e.g., 60℃-165℃, 165℃-170℃, 170℃-180℃, 180℃-310℃, and 310℃-360℃); in the embodiments of this specification, the temperature range of the distillation range may or may not include the boundary value itself. Figure 3The values ​​for the initial boiling point and final boiling point shown are all temperature values, in °C.

[0103] Using the yield data (Y1) of the first fraction and the content (m) of the first fraction in different temperature ranges 1j Construct a fractional division sub-model for the first fraction, wherein the yield data (Y1) of the first fraction and the content (m) of the first fraction in the corresponding temperature range are combined. 1j The product of (m) 1j ×Y1) is used as the value of the first fraction in each temperature range (m 1j ×Y1);

[0104] Using the yield data of the second fraction (Y2) and the content of the second fraction in different temperature ranges (m) 2j Construct a fractional cut-off model for the second fraction, wherein the yield data (Y2) of the second fraction is correlated with the content (m) of the second fraction in the corresponding temperature range. 2j The product of (m) 2j ×Y2) is used as the value of the second fraction in each temperature range;

[0105] Using the temperature range as a reference, all fractionation sub-models are merged to obtain the fractionation model.

[0106] Therefore, this embodiment can establish a fractionation model with the fewest possible temperature ranges, thereby simplifying the subsequent calculation process.

[0107] Based on the above embodiments, the formula for calculating the separation coefficient is:

[0108]

[0109] Where, n ij m represents the separation coefficient of the i-th fraction in the j-th temperature range. ij Y represents the content of the i-th fraction in the j-th temperature range. i This represents the yield of the i-th fraction.

[0110] In some embodiments, such as Figure 4 As shown, in the fractionation model, the sum of the values ​​of all fractions within a first temperature range (e.g., 60℃-165℃) is obtained to obtain the elemental sum (m) of the first temperature range. 11 ×Y1+0+0);

[0111] Perform the above steps for each temperature range to obtain the sum of elements for each temperature range.

[0112] The value of the first fraction in the first temperature range (m) 11×Y1) and the sum of the elements in the first temperature range (m 11 The separation coefficient (n) of the first fraction in the first temperature range is obtained by comparing it with (×Y1+0+0). 11 (1)

[0113] Perform the above steps for each temperature range to obtain the separation coefficient of the first fraction in each temperature range.

[0114] Perform the above steps for each fraction to obtain the separation coefficient of each fraction in each temperature range.

[0115] A separation coefficient matrix is ​​constructed based on all separation coefficients to form a single-molecule separation coefficient model.

[0116] Through the technical solution of this embodiment, multiple separation coefficients n can be obtained. ij This allows for the construction of a single-molecule separation coefficient model, and the content of single molecules in each fraction can be obtained based on the boiling point data and the single-molecule separation coefficient model. This enables the determination of single molecules in each fraction after distillation of the feed based on the separation coefficient.

[0117] Based on the above embodiments, the step of obtaining the boiling point data of various single molecules in the feed based on the molecular composition data of the feed includes:

[0118] Based on the molecular composition data of the feed, the boiling point data of each single molecule is calculated using a pre-trained physical property calculation model.

[0119] In some embodiments, crude oil has many types of molecules, and different single molecules have different boiling points, requiring distillation at different temperatures for separation. Generally speaking, the larger the molecular weight of a single molecule in crude oil, the higher its boiling point, and the more difficult it is to separate. During the crude oil separation process, the distillation range is divided according to the type of oil product distilled and the boiling point of the molecules. Each distillation range corresponds to a type of oil product to complete the separation of crude oil. In this step, the single molecules in the crude oil and the content of each single molecule are obtained.

[0120] In some embodiments, the molecular composition of a mixture can be determined by one or more of the following methods: full two-dimensional gas chromatography, quadrupole gas chromatography-mass spectrometry, gas chromatography / field ionization-time-of-flight mass spectrometry, gas chromatography, near-infrared spectroscopy, sensor method, nuclear magnetic resonance spectroscopy, Raman spectroscopy, and topological index method. Of course, the molecular composition of a mixture can also be determined by other methods, such as by methods specified in ASTM D2425, SH / T0606, and / or ASTM D8144-18.

[0121] The aforementioned molecular detection methods can detect the structure of molecules and thus determine their types. However, due to the large number of molecular types in crude oil, although it's possible to re-detect the crude oil molecules when it's reused, the workload and time consumption of detecting each single molecule are substantial. Therefore, this approach also utilizes a structure-guided lumped molecular characterization method (SOL) to construct single molecules. This method uses 24 structural increment fragments to characterize the basic structure of complex hydrocarbon molecules. Any petroleum molecule can be represented by a specific set of structural increment fragments. The SOL method is a lumped representation at the molecular scale, reducing the number of molecules in the actual system from millions to thousands, significantly reducing the complexity of the simulation. This characterization method can represent not only alkanes and cycloalkanes, but also complex aromatic structures containing 50-60 carbon atoms, as well as alkenes or cycloalkenes as intermediate or secondary reaction products. It also considers compounds containing heteroatoms such as sulfur, nitrogen, and oxygen.

[0122] In some embodiments, the boiling point of each monomolecule can be calculated by obtaining the number of each group constituting the monomolecule and the contribution value of each group to the boiling point, inputting them into a pre-trained property calculation model, and obtaining the boiling point of the monomolecule output by the property calculation model. The groups constituting the monomolecule are the 24 structural increment fragments based on the SOL molecular characterization method in the above embodiments.

[0123] The calculation of the boiling point of a single molecule is described in further detail below.

[0124] like Figure 5 The diagram shown is a flowchart of a method for calculating the boiling point of a molecule according to an embodiment of this specification. The flowchart includes:

[0125] Step 501: For a single molecule, obtain the number of each type of group constituting the single molecule, and obtain the contribution value of each type of group to the physical properties.

[0126] In some embodiments, single molecules are constructed based on the structure-guided lumped molecular characterization method, which is the SOL molecular characterization method that uses 24 structural increment fragments to characterize the basic structure of complex hydrocarbon molecules. Any petroleum molecule can be represented by a specific set of structural increment fragments. The SOL molecular characterization method is a lumped representation at the molecular scale, reducing the number of molecules in the actual system from millions to thousands, greatly reducing the complexity of the simulation. This characterization method can represent not only alkanes and cycloalkanes, but also complex aromatic structures containing 50-60 carbon atoms, as well as alkenes or cycloalkenes as intermediates or secondary reaction products. It also considers compounds containing heteroatoms such as sulfur, nitrogen, and oxygen. The molecular structure can be determined by one or more of the following methods: Raman spectroscopy, quadrupole gas chromatography-mass spectrometry, gas chromatography / field ionization-time-of-flight mass spectrometry, gas chromatography, near-infrared spectroscopy, sensor method, and nuclear magnetic resonance spectroscopy. Then, the single molecule is constructed using a structure-guided lumped molecular characterization method. In this step, the number of each group constituting the single molecule and the contribution value of each group to the physical properties are obtained. Since the physical properties of a molecule are determined by its structure, this scheme constructs a single molecule by grouping and obtains the number of each group and the contribution value of each group to the physical properties.

[0127] In some embodiments, based on the SOL molecular characterization method, the functional groups contained in each monomolecule are determined; and in each monomolecule, the number of each functional group and the contribution value of each functional group to the physical property are determined. Since there are multiple physical properties of a monomolecule, it is necessary to determine the contribution value of each functional group to each physical property in the monomolecule.

[0128] Step 502: Input the number of each group that makes up the single molecule and the contribution value of each group to the physical properties into the pre-trained physical property calculation model, and obtain the physical properties of the single molecule output by the physical property calculation model.

[0129] In some embodiments, multiple physical properties of the single molecule are obtained by inputting the number of each group and the contribution value of each group to the physical property into a pre-trained physical property calculation model.

[0130] like Figure 6 The diagram shows a flowchart of a method for training a physical property calculation model according to an embodiment of this specification. The method in the diagram includes:

[0131] Step 601: Construct a single-molecule property calculation model.

[0132] In some embodiments, the property calculation model includes: a contribution value of each functional group to the property. This contribution value is adjustable and is an initial value during initial training. Further, the property calculation model includes: a contribution value of each functional group to each property.

[0133] Step 602: Obtain the number of each group that constitutes the sample monomolecule; the physical properties of the sample monomolecule are known.

[0134] In some embodiments, a training sample set is pre-set. The training sample set includes information on multiple sample single molecules. The sample single molecule information includes, but is not limited to, the number of each group constituting the sample single molecule, and the physical properties of the sample single molecule.

[0135] Step 603: Input the number of each type of group contained in the sample molecule into the property calculation model.

[0136] Step 604: Obtain the predicted physical properties of the sample single molecule output by the physical property calculation model.

[0137] Step 605: If the deviation between the predicted property and the known property is less than the preset deviation threshold, the property calculation model is determined to be converged. The contribution value of each group is obtained in the converged property calculation model and stored as the contribution value of the group to the property.

[0138] Since a single molecule may have multiple physical properties, the contribution value of each group to each physical property can be obtained from the converged physical property calculation model.

[0139] For each functional group, the contribution value of that functional group to each property is stored so that when calculating the properties of a single molecule, the contribution value of each functional group in the single molecule to the property to be known can be obtained. The number of each functional group in the single molecule and the contribution value of each functional group to the property to be known are used as inputs to the property calculation model. The property calculation model uses the number of each functional group in the single molecule as the model variable and the contribution value of each functional group to the property to be known as the model parameter (replacing the adjustable contribution value of each functional group to the property in the property calculation model) to calculate the property to be known.

[0140] Step 606: If the deviation between the predicted property and the known property is greater than or equal to the deviation threshold, adjust the contribution value of each group in the property calculation model until the property calculation model converges.

[0141] In some embodiments, if there are multiple physical properties of a single sample molecule, then the predicted physical properties of the single sample molecule output by the physical property calculation model will also be multiple. In this case, the deviation value between each predicted physical property and the corresponding known physical property is calculated, and it is determined whether the deviation values ​​between all predicted physical properties and the corresponding known physical properties are less than a preset deviation value. If so, it is determined that the physical property calculation model has converged. The contribution value of each group to the physical property can be obtained from the converged physical property calculation model. The contribution value of each group to different physical properties can be obtained through the above scheme.

[0142] The following presents two property calculation models that can be used for different physical properties. Those skilled in the art should understand that these two property calculation models are merely illustrative of this embodiment and are not intended to limit this embodiment.

[0143] Model 1: Establish the following physical property calculation model:

[0144] f=a+∑ i n i Δf i ;

[0145] Where f represents the physical property of a single molecule of the sample, and n i Let Δf be the number of groups of the i-th type. i Let be the contribution value of the i-th group to the physical properties, and a be the correlation constant.

[0146] For example, regarding boiling point, in the SOL-based molecular characterization method, all 24 functional groups are treated as primary functional groups. Among these 24 functional groups, the simultaneous presence of one or more of the following functional groups—N6, N5, N4, N3, me, AA, NN, RN, NO, RO, and KO—contributes to the boiling point. However, the contribution value of each functional group to a different property varies, but the contribution value of the same functional group to the same property is consistent across different molecules. Based on this approach, in some embodiments, the aforementioned property calculation model is constructed. By training the constructed property calculation model, the model converges, i.e., the contribution value of each functional group to the property is obtained from the training model, ultimately yielding the contribution value of each functional group to the property.

[0147] In some embodiments, the groups constituting a monomolecule can be further divided into hierarchical groups. Further, primary and hierarchical groups are identified among all groups in the monomolecule; wherein, all groups constituting the monomolecule are considered primary groups; multiple groups that coexist and contribute to the same physical property are considered hierarchical groups, and the number of these multiple groups is considered the level of the hierarchical group. Hierarchical groups are defined based on the coexistence of multiple groups that work together to affect the same physical property. Specifically, for example, when N6 and N4 groups exist separately in different molecules, they will have a certain impact on the physical property; however, when they coexist in one molecule, their contribution to the physical property will fluctuate based on their original contribution. We can also classify hierarchical groups according to a preset bond force range based on the molecular bond forces between groups. Different molecular bond forces will have different effects on different physical properties; specifically, the classification can be based on the influence of molecular stability on the physical property.

[0148] Model 2: Based on the division of multi-level groups, the following property calculation model can be established:

[0149] f=a+∑ i m 1i Δf 1i +∑ j m 2j Δf 2j ……+∑ l m Nl Δf Nl ;

[0150] Where f represents the physical property of a single molecule of the sample, and m 1i Δf represents the number of groups of the i-th type in the primary groups. 1i m is the contribution of the i-th group in the primary group to the physical property. 2j Δf represents the number of groups of the j-th type in the secondary groups. 2j The contribution of the j-th group in the secondary group to the physical property; m Nl Δf represents the number of groups of type l in the N-order groups. Nl denoted as l, where l is the contribution of the l-th group in the N-order group to the physical property; a is the correlation constant; and N is a positive integer greater than or equal to 2.

[0151] In addition to the general property calculation model mentioned above, property calculation models can also be constructed for each type of property according to its specific characteristics.

[0152] For example: Calculate the boiling point of a single molecule based on the following property calculation model:

[0153]

[0154] Where T is the boiling point of a single molecule, SOL is the single molecule vector obtained by converting the number of each type of group constituting the single molecule, and GROUP 11 This is the first contribution value vector obtained by converting the contribution value of primary groups to boiling point, GROUP 12 This is the second contribution value vector obtained by converting the contribution value of secondary groups to boiling point, GROUP 1N The Nth contribution value vector is derived from the contribution of Nth-order groups to the boiling point, where Numh is the number of atoms other than hydrogen atoms in the monomolecule, d is a first preset constant, b is a second preset constant, and c is a third preset constant; N is a positive integer greater than or equal to 2. The monomolecule vector is derived from the number of each type of group constituting the monomolecule, including: using the total number of all groups constituting the monomolecule as the dimension of the monomolecule vector; and using the number of each type of group as the element value of the corresponding dimension in the monomolecule vector. The first contribution value vector is derived from the contribution of each primary group of the monomolecule to the boiling point, including: using the number of primary groups as the dimension of the first contribution value vector; and using the contribution of each primary group to the boiling point as the element value of the corresponding dimension in the first contribution value vector. The second contribution value vector is derived from the contribution of each secondary group of the monomolecule to the boiling point, including: using the number of secondary groups as the dimension of the second contribution value vector; and using the contribution of each secondary group to the boiling point as the element value of the corresponding dimension in the second contribution value vector. Similarly, the Nth contribution value vector, obtained by converting the contribution values ​​of each Nth-order group of a single molecule to the boiling point, includes: using the number of Nth-order groups as the dimension of the Nth contribution value vector; and using the contribution value of each Nth-order group to the boiling point as the element value of the corresponding dimension in the Nth contribution value vector.

[0155] After calculating the boiling point of the corresponding monomolecule in the above steps, the monomolecule is used as a template monomolecule, and the number of each group constituting the monomolecule and the corresponding boiling point are stored in the database.

[0156] Before step 502 above, such as Figure 7 The diagram shown is a flowchart of another method for calculating the boiling point of a molecule according to an embodiment of this specification. The calculation method further includes:

[0157] Step 701: Compare the number of each group constituting the monomolecule with the molecular information of template monomolecules with known boiling points pre-stored in the database; the molecular information includes: the number of each group constituting the template monomolecule.

[0158] Step 702: Determine whether there is a template monomolecule that is identical to the monomolecule.

[0159] Step 703: If a template monomolecule with the same properties as the monomolecule exists, output the boiling point of the template monomolecule as the boiling point of the monomolecule.

[0160] Step 704: If there is no template monomolecule identical to the monomolecule, then input the number of each group constituting the monomolecule and the contribution value of each group to the boiling point into the pre-trained property calculation model.

[0161] After obtaining the number of each group that constitutes a single molecule, this scheme confirms whether the structure and boiling point of the single molecule have been stored in the database by comparing the corresponding number of groups. After confirming the existence of a template single molecule that matches the single molecule, the boiling point of the single molecule is directly output, thereby improving the calculation efficiency of the single molecule boiling point and reducing the amount of computation.

[0162] Based on the above embodiments, the step of obtaining the content of each single molecule in each fraction based on the boiling point data and the single molecule separation coefficient model includes:

[0163] The boiling point data of each single molecule is compared with the temperature range in the single molecule separation coefficient model to determine the temperature range to which each single molecule belongs.

[0164] The content of each single molecule is obtained from the molecular composition data of the feed;

[0165] The content of each single molecule in each fraction is obtained based on the separation coefficient corresponding to the temperature range and the content of each single molecule.

[0166] In some embodiments, after obtaining the boiling point of each monomer, the boiling point data of each monomer is compared with the temperature range in the monomer separation coefficient model to determine the temperature range to which each monomer belongs. For example, after obtaining the boiling point of the first monomer as 168°C, 168°C is compared with the temperature range in the monomer separation coefficient model to determine that the temperature range to which the first monomer belongs is the second temperature range (165°C-170°C). Based on this, since the molecular composition data of the feed includes the types of monomers in the feed and the content of each monomer, the content of the first monomer (e.g., 10) is obtained from the molecular composition data of the feed, thereby determining the separation coefficient (n) corresponding to the second temperature range. 12 n 22 The contents of the first monomolecule (e.g., 10) are multiplied by the contents of the first monomolecule in each fraction (e.g., 10 × n) to obtain the contents of the first monomolecule in each fraction (e.g., 10 × n). 12 10×n 22 (10×0). The above operation is performed sequentially on each type of monomolecule to obtain the content of each monomolecule in each fraction, thus obtaining the content of each monomolecule in each fraction.

[0167] Based on the above embodiments, such as Figure 8 As shown in the embodiment of this specification, a computing device for fraction molecules is provided, including a processor 1110, a communication interface 1120, a memory 1130 and a communication bus 1140, wherein the processor 1110, the communication interface 1120 and the memory 1130 communicate with each other through the communication bus 1140.

[0168] Memory 1130 is used to store computer programs;

[0169] When processor 1110 executes the program stored in memory 1130, it implements the following method for calculating the single-molecule composition of a distillate:

[0170] Obtain molecular composition data of the feed to the fractionation unit, as well as distillation range data and yield data of each product fraction;

[0171] A fraction cutting model is constructed based on the distillation range data and yield data. The fraction cutting model includes temperature ranges and content data corresponding to each temperature range.

[0172] Based on the aforementioned fraction cutting model, the separation coefficient of each fraction in each temperature range is calculated using the separation coefficient calculation formula, thus obtaining the single-molecule separation coefficient model.

[0173] Based on the molecular composition data of the feed, the boiling point data of various single molecules in the feed are obtained;

[0174] Based on the boiling point data and the single-molecule separation coefficient model, the content of each single molecule in each fraction is obtained.

[0175] Based on the above technical solutions, the embodiments of this specification can be further improved as follows.

[0176] In some embodiments, the step of constructing a fractional cut model based on the distillation range data and yield data, wherein the fractional cut model includes temperature range and content data of the fractions, includes:

[0177] Obtain the temperature range covered by the distillation range data of each fraction;

[0178] The temperature range is divided using the distillation range data to obtain multiple temperature intervals;

[0179] A fractional division sub-model is constructed using the yield data of each fraction and the content of the corresponding fraction in each temperature range.

[0180] All fractionation sub-models are merged to obtain the fractionation model.

[0181] In some embodiments, the separation coefficient is calculated as follows:

[0182]

[0183] Where, n ij m represents the separation coefficient of the i-th fraction in the j-th temperature range. ij Y represents the content of the i-th fraction in the j-th temperature range. i This represents the yield of the i-th fraction.

[0184] In some embodiments, the distillation range data includes the initial boiling point and the final boiling point.

[0185] In some embodiments, the step of acquiring the feed single-molecule data and the boiling point data of each single molecule includes:

[0186] Obtain the content of each monomer in the feed;

[0187] Calculate the boiling point of each unimolecular.

[0188] In some embodiments, calculating the boiling point of each unimolecular molecule includes:

[0189] For each of the aforementioned monomolecules, the number of each group constituting the monomolecule is obtained, and the contribution value of each group to the boiling point is obtained;

[0190] The number of each group constituting the monomolecule and the contribution value of each group to the boiling point are input into a pre-trained physical property calculation model to obtain the boiling point of the monomolecule output by the physical property calculation model.

[0191] In some embodiments, before inputting the number of each group constituting the monomolecule and the contribution value of each group to the boiling point into a pre-trained property calculation model, the method further includes:

[0192] The number of each group constituting the monomolecule is compared with the molecular information of template monomolecules with known boiling points pre-stored in the database; the molecular information includes: the number of each group constituting the template monomolecule.

[0193] Determine whether there exists a template monomolecule identical to the monomolecule described above;

[0194] If a template molecule identical to the single molecule exists, the boiling point of the template molecule is output as the boiling point of the single molecule.

[0195] If no template monomolecule identical to the monomolecule exists, then the step of inputting the number of each group constituting the monomolecule and the contribution value of each group to the boiling point into the pre-trained property calculation model is performed.

[0196] In some embodiments, the step of training the physical property calculation model includes:

[0197] Construct a computational model for the physical properties of a single molecule;

[0198] The number of each group constituting a sample molecule is obtained; the physical properties of the sample molecule are known.

[0199] Input the number of each type of group contained in the sample single molecule into the physical property calculation model;

[0200] Obtain the predicted physical properties of the sample single molecule output by the physical property calculation model;

[0201] If the deviation between the predicted property and the known property is less than a preset deviation threshold, the property calculation model is determined to be converged. The contribution value of each group is obtained from the converged property calculation model and stored as the contribution value of the group to the property.

[0202] If the deviation between the predicted property and the known property is greater than or equal to the preset deviation threshold, the contribution value of each group in the property calculation model is adjusted until the property calculation model converges.

[0203] In some embodiments, the step of obtaining the content of each single molecule in each fraction based on the boiling point data and the single molecule separation coefficient model includes:

[0204] The boiling point data of each monomolecule is compared with the temperature range in the monomolecule separation coefficient model to determine the temperature range to which each monomolecule belongs.

[0205] The content of each single molecule is obtained from the molecular composition data of the feed;

[0206] The content of each single molecule in each fraction is obtained based on the separation coefficient corresponding to the temperature range and the content of each single molecule.

[0207] The aforementioned communication bus 1140 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus 1140 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, it is represented by only one thick line in the figure, but this does not indicate that there is only one bus or one type of bus.

[0208] The communication interface 1120 is used for communication between the above-mentioned electronic device and other devices.

[0209] The memory 1130 may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory 1130 may also be at least one storage device located remotely from the aforementioned processor 1110.

[0210] The processor 1110 mentioned above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0211] Based on the same concept described in this specification, embodiments of this specification provide a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the steps of the single-molecule composition calculation method for fractions in any of the above possible implementations.

[0212] Optionally, the storage medium may be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0213] Based on the same concept described in this specification, embodiments of this specification also provide a computer program product, including a computer program that, when executed by a processor, implements the steps of the method for calculating the molecular composition of fractions in any of the above possible implementations.

[0214] Based on the same instruction manual concept, such as Figure 9 The diagram shown is a schematic diagram of a calculation device for calculating the molecular composition of a fraction according to an embodiment of this specification. The device includes: a first acquisition module 901, a construction module 902, a modeling module 903, a second acquisition module 904, and a calculation module 905.

[0215] The first acquisition module 901 acquires the molecular composition data of the feed to the fractionation unit, as well as the distillation range data and yield data of each product fraction.

[0216] Module 902 constructs a fraction cutting model based on the distillation range data and yield data. The fraction cutting model includes temperature ranges and content data corresponding to each temperature range.

[0217] Modeling module 903, based on the fraction cutting model, calculates the separation coefficient of each fraction in each temperature range using the separation coefficient calculation formula, and obtains a single-molecule separation coefficient model;

[0218] The second acquisition module 904 acquires the boiling point data of various single molecules in the feed based on the molecular composition data of the feed.

[0219] The calculation module 905, based on the boiling point data and the single-molecule separation coefficient model, obtains the content of each single molecule in each fraction.

[0220] In one possible implementation, the building module 902 includes:

[0221] The acquisition unit acquires the temperature range covered by the distillation range data of each fraction;

[0222] The cutting unit uses the distillation range data to cut the temperature range into multiple temperature intervals;

[0223] The construction unit utilizes the yield data of each fraction and the content of the corresponding fraction in each temperature range to construct the fractional cutting sub-model of the corresponding fraction;

[0224] The merging unit combines all the fractionation sub-models to obtain the fractionation model.

[0225] In one possible implementation, the separation coefficient is calculated as follows:

[0226]

[0227] Where, n ij m represents the separation coefficient of the i-th fraction in the j-th temperature range. ij Y represents the content of the i-th fraction in the j-th temperature range. i This represents the yield of the i-th fraction.

[0228] In one possible implementation, the distillation range data includes the initial boiling point and the final boiling point.

[0229] It should be understood that in the various embodiments of this specification, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this specification.

[0230] It should also be understood that, in the embodiments of this specification, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this specification generally indicates that the preceding and following related objects have an "or" relationship.

[0231] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this specification can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this specification.

[0232] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0233] In the several embodiments provided in this specification, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connections shown or discussed may be indirect coupling or communication connections through some interfaces, devices, or units, or they may be electrical, mechanical, or other forms of connection.

[0234] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments described in this specification, depending on actual needs.

[0235] Furthermore, the functional units in the various embodiments of this specification can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0236] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this specification, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this specification. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0237] This specification uses specific embodiments to illustrate the principles and implementation methods of this specification. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this specification. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this specification. Therefore, the content of this specification should not be construed as a limitation of this specification.

Claims

1. A method for calculating the molecular composition of a distillate, characterized in that, The method includes: Obtain molecular composition data of the feed to the fractionation unit, as well as distillation range data and yield data of each product fraction; A fraction cutting model is constructed based on the distillation range data and yield data. The fraction cutting model includes temperature ranges and content data corresponding to each temperature range. Based on the aforementioned fraction cutting model, the separation coefficient of each fraction in each temperature range is calculated using the separation coefficient calculation formula, thus obtaining the single-molecule separation coefficient model. Based on the molecular composition data of the feed, the boiling point data of various single molecules in the feed are obtained; Based on the boiling point data and the single-molecule separation coefficient model, the content of each single molecule in each fraction is obtained; The formula for calculating the separation coefficient is: ； Where, n ij m represents the separation coefficient of the i-th fraction in the j-th temperature range. ij Y represents the content of the i-th fraction in the j-th temperature range. i This represents the yield of the i-th fraction.

2. The method according to claim 1, characterized in that, The step of constructing a fraction cutting model based on the distillation range data and yield data, wherein the fraction cutting model includes temperature ranges and content data corresponding to each temperature range, includes: Obtain the temperature range covered by the distillation range data of each fraction; The temperature range is divided using the distillation range data to obtain multiple temperature intervals; A fractional division sub-model is constructed using the yield data of each fraction and the content of the corresponding fraction in each temperature range. All fractionation sub-models are merged to obtain the fractionation model.

3. The method according to claim 1, characterized in that, The distillation range data includes the initial boiling point and the final boiling point.

4. The method according to claim 1, characterized in that, The step of obtaining boiling point data for various single molecules in the feed based on the molecular composition data of the feed includes: Based on the molecular composition data of the feed, the boiling point data of each single molecule is calculated using a pre-trained physical property calculation model.

5. The method according to claim 4, characterized in that, The calculation of the boiling point of each unimolecular element includes: For each of the aforementioned monomolecules, the number of each group constituting the monomolecule is obtained, and the contribution value of each group to the boiling point is obtained; The number of each group constituting the monomolecule and the contribution value of each group to the boiling point are input into a pre-trained physical property calculation model to obtain the boiling point of the monomolecule output by the physical property calculation model. The boiling point of the unimolecular molecules is calculated using the following property calculation model: ； in, The boiling point of the unimolecular element is [value missing]. This is a single-molecule vector obtained by transforming the number of each group constituting the single molecule. This is the first contribution value vector obtained by converting the contribution value of the primary functional group to the boiling point. This is a second contribution value vector obtained by converting the contribution value of secondary groups to the boiling point. This is the Nth contribution value vector obtained by converting the Nth-order group's contribution to the boiling point. This represents the number of atoms other than hydrogen atoms in a single molecule. For the first preset constant, For the second preset constant, The third preset constant is N; N is a positive integer greater than or equal to 2.

6. The method according to claim 5, characterized in that, Before inputting the number of each group constituting the monomolecule and the contribution value of each group to the boiling point into the pre-trained property calculation model, the method further includes: The number of each group constituting the monomolecule is compared with the molecular information of template monomolecules with known boiling points pre-stored in the database; the molecular information includes: the number of each group constituting the template monomolecule. Determine whether there exists a template monomolecule identical to the monomolecule described above; If a template molecule identical to the single molecule exists, the boiling point of the template molecule is output as the boiling point of the single molecule. If no template monomolecule identical to the monomolecule exists, then the step of inputting the number of each group constituting the monomolecule and the contribution value of each group to the boiling point into the pre-trained property calculation model is performed.

7. The method according to claim 5, characterized in that, The steps for training the physical property calculation model include: Construct a computational model for the physical properties of a single molecule; The number of each group constituting a sample molecule is obtained; the physical properties of the sample molecule are known. Input the number of each type of group contained in the sample single molecule into the physical property calculation model; Obtain the predicted physical properties of the sample single molecule output by the physical property calculation model; If the deviation between the predicted property and the known property is less than a preset deviation threshold, the property calculation model is determined to be converged. The contribution value of each group is obtained from the converged property calculation model and stored as the contribution value of the group to the property. If the deviation between the predicted property and the known property is greater than or equal to the preset deviation threshold, the contribution value of each group in the property calculation model is adjusted until the property calculation model converges.

8. The method according to claim 1, characterized in that, The step of obtaining the content of each single molecule in each fraction based on the boiling point data and the single molecule separation coefficient model includes: The boiling point data of each monomolecule is compared with the temperature range in the monomolecule separation coefficient model to determine the temperature range to which each monomolecule belongs. The content of each single molecule is obtained from the molecular composition data of the feed; The content of each single molecule in each fraction is obtained based on the separation coefficient corresponding to the temperature range and the content of each single molecule.

9. A computing device for the molecular composition of a distillate, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method of any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, which can be executed by one or more processors to implement the method of any one of claims 1 to 8.

11. A device for calculating the molecular composition of a distillate, characterized in that, The device includes: The first acquisition module acquires the molecular composition data of the feed to the fractionation unit, as well as the distillation range data and yield data of each product fraction; The construction module constructs a fraction cutting model based on the distillation range data and yield data. The fraction cutting model includes temperature ranges and content data corresponding to each temperature range. The modeling module, based on the aforementioned fractionation model, calculates the separation coefficient of each fraction in each temperature range using the separation coefficient calculation formula, thereby obtaining a single-molecule separation coefficient model; wherein, the separation coefficient calculation formula is: ； Where, n ij m represents the separation coefficient of the i-th fraction in the j-th temperature range. ij Y represents the content of the i-th fraction in the j-th temperature range. i This represents the yield of the i-th fraction; The second acquisition module acquires the boiling point data of various single molecules in the feed based on the molecular composition data of the feed. The calculation module, based on the boiling point data and the single-molecule separation coefficient model, obtains the content of each single molecule in each fraction.

12. The apparatus according to claim 11, characterized in that, The building module includes: The acquisition unit acquires the temperature range covered by the distillation range data of each fraction; The cutting unit uses the distillation range data to cut the temperature range into multiple temperature intervals; The construction unit utilizes the yield data of each fraction and the content of the corresponding fraction in each temperature range to construct the fractional cutting sub-model of the corresponding fraction; The merging unit combines all the fractionation sub-models to obtain the fractionation model.

13. The apparatus according to claim 11, characterized in that, The distillation range data includes the initial boiling point and the final boiling point.

Images