Method and system for predicting condensation point and cold filter plugging point of diesel oil

Abstract

The invention relates to the technical field of diesel oil condensation point and cold filter plugging point prediction, in particular to a diesel oil condensation point and cold filter plugging point prediction method and system.The method comprises the following steps that diesel oil is analyzed and tested through an analysis instrument, and an actual value of a first property is obtained; obtaining main homologues in the diesel oil structure, and obtaining a central molecule set according to the main homologues; expanding the central molecule set according to a preset rule to obtain virtual molecules; applying a preset structure and property relationship to the virtual molecules to obtain a virtual molecule content and first property calculation function; optimizing the first property calculation function through an optimization algorithm to obtain the relative content of the virtual molecules; obtaining a diesel molecular matrix according to the relative content and the structure vector; and sending the diesel molecular matrix into the neural network model for prediction to obtain the condensation point and the cold filter plugging point of the diesel. According to the method, diesel oil can be better described on the molecular level, and the condensation point and the cold filter plugging point can be predicted more conveniently, economically and accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of predicting diesel freezing point and cold filter plugging point, and is a method and system for predicting diesel freezing point and cold filter plugging point. Background Art

[0002] The freezing point and cold filter plugging point are important indicators characterizing the low-temperature performance of diesel. The freezing point (SP) is the highest temperature at which diesel loses fluidity in a low-temperature environment. The cold filter plugging point (CF) can indicate the highest temperature at which diesel can cause the filter screen to be blocked when passing through the fuel supply system of a diesel engine. The cold filter plugging point is directly related to the low-temperature performance of diesel, and the freezing point is mainly related to the storage and transportation of diesel. When the diesel temperature drops to the cold filter plugging point temperature, the wax crystals formed will block the filter and affect the normal fuel supply of the fuel pipeline, thereby affecting the normal operation of the engine.

[0003] With the development of computer and analysis technologies, the development of petroleum processing process models has risen to the molecular level, and a theoretical model with strong universality can be constructed according to the chemical composition of raw materials. The rapid development of large-scale analysis technologies such as mass spectrometry, nuclear magnetic resonance, and infrared spectroscopy provides the necessary conditions for establishing a model at the molecular scale, and computer technology provides sufficient support for dealing with complex molecular dynamics calculation problems. Based on the molecular composition of diesel, the molecular composition and component content are described using matrices, and properties such as molecular weight, element content, density, and distillation range in diesel can be obtained according to the group contribution method with relatively small errors, but the calculated results of the freezing point and cold filter plugging point deviate greatly from the actual values. Summary of the Invention

[0004] The present invention provides a method and system for predicting diesel freezing point and cold filter plugging point, which overcomes the deficiencies of the above-mentioned prior art and can effectively solve the problem that the calculated results of the freezing point and cold filter plugging point deviate greatly from the actual values.

[0005] One technical solution of the present invention is achieved by the following measures: A method for predicting diesel freezing point and cold filter plugging point includes the following steps:

[0006] Analyze and test diesel through an analytical instrument to obtain the actual value of the first property; obtain the main homologues in the diesel structure, and obtain the central molecule set according to the main homologues;

[0007] Expand the central molecule set according to a preset rule to obtain virtual molecules; apply the preset structure-property relationship to the virtual molecules to obtain the calculation function of the virtual molecule content and the first property;

[0008] Optimize the first property calculation function through an optimization algorithm, limit the error between the actual value of the first property and the calculated value of the first property to be less than a preset value, and obtain the relative content of virtual molecules in the virtual diesel;

[0009] Obtain a diesel molecular matrix based on the relative content and structural vector of virtual molecules; input the diesel molecular matrix into a neural network model for prediction to obtain the pour point and cold filter plugging point of diesel.

[0010] The following is a further optimization and / or improvement of one of the above-mentioned technical solutions of the invention:

[0011] When inputting the diesel molecular matrix into a neural network model for prediction to obtain the pour point and cold filter plugging point of diesel, it may specifically include the following steps: divide the diesel molecular matrix into a training set and a prediction set; input the training set into an initial neural network for training to obtain a neural network model; input the prediction set into the neural network model for prediction to obtain the pour point and cold filter plugging point of diesel.

[0012] When expanding the central molecular set according to a preset rule to obtain virtual molecules, it may specifically include the following steps: add a methyl group to the central molecule in the central molecular set according to a preset rule to obtain a virtual molecule; where the preset rule includes one or a combination of the following: without considering isomers, only changing the carbon number of alkanes, first satisfying the increase in the number of methyl groups in the ring structure, and when adding a side chain to the ring, the cycloalkane ring is preferred over the aromatic ring.

[0013] The above-mentioned central molecular set may include 40 to 70 central molecules.

[0014] The above-mentioned preset structure-property relationship may include one or a combination of the following: structure and element content, structure and average molecular weight, structure and saturate content, structure and aromatic content, structure and boiling point.

[0015] The above-mentioned optimization algorithm may include one or a combination of the following: ant colony algorithm, simulated annealing method, genetic algorithm, artificial neural network algorithm.

[0016] The above-mentioned neural network model may include one or a combination of the following: single-layer neural network, feedforward neural network, radial basis function network, deep feedforward network, recurrent neural network.

[0017] The second technical solution of the present invention is achieved through the following measures: A prediction system for the pour point and cold filter plugging point of diesel, including:

[0018] An analysis module for analyzing and testing diesel through an analysis instrument to obtain the actual value of the first property;

[0019] An acquisition module for acquiring the main homologues in the diesel structure and obtaining a central molecular set according to the main homologues;

[0020] An expansion module for expanding the central molecular set according to a preset rule to obtain virtual molecules;

[0021] An application module for applying a preset structure-property relationship to virtual molecules to obtain a calculation function of the content of virtual molecules and a first property;

[0022] An optimization module for optimizing the first-property calculation function through an optimization algorithm, limiting the error between the actual value of the first property and the calculated value of the first property to be less than a preset value, and obtaining the relative content of virtual molecules in virtual diesel;

[0023] A matrix acquisition module for obtaining a diesel molecule matrix based on the relative content of virtual molecules and a structure vector;

[0024] A prediction module for sending the diesel molecule matrix into a neural network model for prediction to obtain the cloud point and cold filter plugging point of diesel.

[0025] The third technical solution of the present invention is achieved by the following measures: A computer device includes a memory and a processor. A program that can run on the processor is stored on the memory. When the processor executes the program, the above-mentioned prediction method for the cloud point and cold filter plugging point of diesel is implemented.

[0026] The fourth technical solution of the present invention is achieved by the following measures: A storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the above-mentioned prediction method for the cloud point and cold filter plugging point of diesel.

[0027] The present invention analyzes and tests diesel through certain analytical instruments to obtain the actual value of the first property; according to the main homologues in the diesel structure, some molecules with similar reaction characteristics or structural features are grouped to obtain a certain central molecule set; the central molecule set is used to obtain virtual molecules according to certain rules, and the virtual molecules are applied with a preset structure-property relationship to obtain a calculation function of the content of virtual molecules and the first property; a certain optimization algorithm is used to limit the error between the calculated value of the property and the actual value to be less than a preset value to obtain the relative content of each molecule in virtual diesel; the diesel molecule matrix is obtained by combining a certain relationship between the structure vector and the molecular content; by applying the method of neural network and inputting the diesel molecule matrix, the cloud point and cold filter plugging point of diesel are obtained. This prediction method has a high accuracy in predicting the cloud point and cold filter plugging point of diesel; using the raw material molecule matrix can better describe diesel at the molecular level. The present invention applies neural network to analyze complex diesel molecular structure information and predict molecular properties, and can more conveniently, economically and accurately predict the cloud point and cold filter plugging point. Using the form of matrix is convenient for editing and storage and is convenient for computer recognition. The present invention can better describe diesel at the molecular level and can more conveniently, economically and accurately predict the cloud point and cold filter plugging point. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] APPENDIX Figure 1Schematic diagram of the steps of the prediction method for diesel freezing point and cold filter plugging point in Embodiment 1 of the present invention.

[0029] Appendix Figure 2 Schematic diagram of the steps of the prediction method for diesel freezing point and cold filter plugging point in Embodiment 2 of the present invention.

[0030] Appendix Figure 3 Schematic diagram of the steps of the prediction method for diesel freezing point and cold filter plugging point in Embodiment 3 of the present invention.

[0031] Appendix Figure 4 Schematic block diagram of the structure of the prediction system for diesel freezing point and cold filter plugging point in Embodiment 4 of the present invention.

[0032] Appendix Figure 5 Schematic block diagram of the structure of the computer device in Embodiment 6 of the present invention.

[0033] Appendix Figure 6 Schematic diagram of the steps of the prediction method for diesel freezing point and cold filter plugging point in Embodiment 5 of the present invention.

[0034] Appendix Figure 7 Flow chart of the prediction method for diesel freezing point and cold filter plugging point in Embodiment 5 of the present invention.

[0035] Appendix Figure 8 Schematic diagram of the thinking of the prediction method for diesel freezing point and cold filter plugging point in Embodiment 5 of the present invention.

[0036] Appendix Figure 9 Schematic diagram of the central molecule of straight-run diesel in the prediction method for diesel freezing point and cold filter plugging point in Embodiment 5 of the present invention. Detailed implementation manners

[0037] The present invention is not limited by the following embodiments, and the specific implementation manners can be determined according to the technical solutions of the present invention and the actual situation.

[0038] The present invention will be further described below in conjunction with embodiments:

[0039] Embodiment 1: As Figure 1 shown, the embodiment of the present invention provides a prediction method for diesel freezing point and cold filter plugging point, including the following steps:

[0040] Step S102: Analyze and test the diesel through an analytical instrument to obtain the actual value of the first property;

[0041] Step S104: Expand the central molecule set according to a preset rule to obtain virtual molecules;

[0042] Step S106: Apply the preset structure-property relationship to the virtual molecules to obtain the calculation function of the virtual molecule content and the first property;

[0043] Step S108: Optimize the first property calculation function through an optimization algorithm, limit the error between the actual value of the first property and the calculated value of the first property to be less than a preset value, and obtain the relative content of virtual molecules in the virtual diesel; wherein, the preset value is generally less than 0.01 - 0.05.

[0044] Step S110: Obtain the diesel molecular matrix according to the relative content of virtual molecules and the structure vector;

[0045] Step S112: Send the diesel molecular matrix into a neural network model for prediction to obtain the pour point and cold filter plugging point of the diesel.

[0046] According to the prediction method of the pour point and cold filter plugging point of diesel provided in this embodiment, first, diesel is analyzed and tested by certain analytical instruments to obtain the actual value of the first property. Then, according to the main homologues in the diesel structure, some molecules with similar reaction characteristics or structural features are merged to obtain a certain set of central molecules. The central molecule set obtains virtual molecules according to a certain rule, and the virtual molecules apply the preset structure-property relationship to obtain the virtual molecule content and the first property calculation function. A certain optimization algorithm is used to limit the error between the property calculation value and the actual value to be less than the preset value, and the relative content of each molecule in the virtual diesel is obtained. The diesel molecular matrix is obtained by combining the relationship between a certain structure vector and the molecular content. Using the method of neural network, inputting the diesel molecular matrix, the pour point and cold filter plugging point of the diesel are obtained. This prediction method has a high accuracy in predicting the pour point and cold filter plugging point of diesel. Using the raw material molecular matrix can better describe diesel at the molecular level. Applying neural network to analyze the complex diesel molecular structure information and predict the molecular properties can more conveniently, economically and accurately predict the pour point and cold filter plugging point. Using the form of matrix is convenient for editing and storage and is convenient for computer recognition.

[0047] Embodiment 2: As Figure 2 shown, in this prediction method of the pour point and cold filter plugging point of diesel, sending the diesel molecular matrix into a neural network model for prediction to obtain the pour point and cold filter plugging point of the diesel specifically includes the following steps:

[0048] Step S202: Divide the diesel molecular matrix into a training set and a prediction set;

[0049] Step S204: Input the training set into the initial neural network for training to obtain the neural network model;

[0050] Step S206: Input the prediction set into the neural network model for prediction to obtain the pour point and cold filter plugging point of the diesel.

[0051] In this embodiment, the diesel molecular matrix is fed into a neural network model for prediction to obtain the pour point and cold filter plugging point of diesel. Specifically, the diesel molecular matrix is first divided into a training set and a prediction set. Then, the training set is input into the initial neural network for training to obtain a neural network model. Finally, the prediction set is input into the neural network model for prediction to obtain the pour point and cold filter plugging point of diesel. By using a neural network to analyze complex diesel molecular structure information and predict molecular properties, it is possible to more conveniently, economically, and accurately predict the pour point and cold filter plugging point.

[0052] Embodiment 3: As Figure 3 shown, in this method for predicting the pour point and cold filter plugging point of diesel, the central molecular set is expanded according to a preset rule to obtain virtual molecules, which specifically includes the following steps:

[0053] Step S302: Add a methyl group to the central molecule in the central molecular set according to the preset rule to obtain a virtual molecule;

[0054] Among them, the preset rule includes one or a combination of the following: ignoring isomerism, only changing the carbon number of alkanes, first satisfying the increase in the number of methyl groups in the ring structure, and when adding a side chain to the ring, the cycloalkane ring is preferred over the aromatic ring.

[0055] In this embodiment, the central molecular set is expanded according to the preset rule to obtain virtual molecules. Specifically, the central molecular set adds a methyl group to the central molecule according to the preset rule, and there is a priority order when adding, including but not limited to ignoring isomerism, only changing the carbon number of alkanes, first satisfying the increase in the number of methyl groups in the ring structure, and when adding a side chain to the ring, the cycloalkane ring is preferred over the aromatic ring. After removing some unreasonable molecules, multiple virtual molecules are obtained and used as all the molecules describing diesel. Specifically, according to the preset rule, 40 to 70 central molecules can be expanded to 500 to 1000 molecules. Among them, the number of virtual molecules can be 803.

[0056] In the above embodiment, diesel includes but is not limited to one or a combination of straight-run diesel, catalytic diesel, coking diesel, hydrofined diesel, and hydrocracked diesel.

[0057] In some embodiments, the analytical instrument includes but is not limited to a comprehensive two-dimensional gas chromatography-time-of-flight mass spectrometry instrument, a nuclear magnetic resonance instrument, a gas chromatography-mass spectrometry instrument, an inductively coupled plasma emission spectrometer, a Fourier transform infrared spectrometer, and an elemental analyzer, alone or in combination. Specifically, by using a nuclear magnetic resonance instrument to analyze diesel raw material molecules, the aromatic carbon ratio, aliphatic carbon ratio, aromatic ring substitution degree, and alkane chain branching degree of diesel can be obtained. By using a comprehensive two-dimensional gas chromatography-time-of-flight mass spectrometry instrument, the composition and content of diesel can be obtained.

[0058] In the above embodiments, the first property includes but is not limited to one or more combinations of element content, average molecular weight, saturate content, aromatic content, and fraction.

[0059] In the above embodiments, the central molecule set determines 40 to 70 central molecules.

[0060] In some embodiments, the preset structure-property relationship includes but is not limited to one or more relationships between structure and element content, structure and average molecular weight, structure and saturate content, structure and aromatic content, and structure and boiling point.

[0061] In the above embodiments, the optimization algorithm includes but is not limited to one or more of ant colony algorithm, simulated annealing method, genetic algorithm, and artificial neural network algorithm. Specifically, by using the simulated annealing algorithm, it is specified that the error between the calculated value and the actual value of the first property should be less than 1×10 -6 , and the relative content of each molecule in the virtual diesel is obtained.

[0062] In the above embodiments, the neural network model includes but is not limited to methods such as single-layer neural network, feedforward neural network, radial basis function network, deep feedforward network, and recurrent neural network.

[0063] In some embodiments, according to the relative content and structure vector of the virtual molecules, a diesel molecule matrix is obtained, and structure fragments H2, and the molecular content, a total of 17, are selected to describe the diesel molecules.

[0064] Example 4: As Figure 4 shown, an embodiment of the present invention provides a prediction system for diesel pour point and cold filter plugging point, including: an analysis module for analyzing and testing diesel through an analytical instrument to obtain the actual value of the first property; an acquisition module for acquiring the main homologues in the diesel structure and obtaining a central molecule set according to the main homologues; an expansion module for expanding the central molecule set according to preset rules to obtain virtual molecules; an application module for applying the preset structure-property relationship to the virtual molecules to obtain a calculation function of the virtual molecule content and the first property; an optimization module for optimizing the calculation function of the first property through an optimization algorithm and specifying that the error between the actual value and the calculated value of the first property is less than a preset value to obtain the relative content of the virtual molecules in the virtual diesel; a matrix acquisition module for obtaining a diesel molecule matrix according to the relative content and structure vector of the virtual molecules; and a prediction module for sending the diesel molecule matrix into a neural network model for prediction to obtain the pour point and cold filter plugging point of the diesel.

[0065] According to the prediction system for diesel freezing point and cold filter plugging point provided by this embodiment, it includes an analysis module, an acquisition module, an expansion module, an application module, an optimization module, a matrix acquisition module, and a prediction module. Among them, the analysis module is used to analyze and test diesel through an analysis instrument to obtain the actual value of the first property. The acquisition module is used to obtain the main homologues in the diesel structure and, based on the main homologues, obtain the central molecule set. The expansion module is used to expand the central molecule set according to preset rules to obtain virtual molecules. The application module is used to apply the preset structure-property relationship to the virtual molecules to obtain the calculation function of the virtual molecule content and the first property. The optimization module is used to optimize the first property calculation function through an optimization algorithm, limit the error between the actual value of the first property and the calculated value of the first property to be less than a preset value, and obtain the relative content of virtual molecules in the virtual diesel. The matrix acquisition module is used to obtain the diesel molecule matrix based on the relative content of virtual molecules and the structure vector. The prediction module is used to send the diesel molecule matrix into a neural network model for prediction to obtain the freezing point and cold filter plugging point of diesel. Using the raw material molecule matrix can better describe diesel at the molecular level. Applying neural networks to analyze complex diesel molecular structure information and predict molecular properties can more conveniently, economically, and accurately predict the freezing point and cold filter plugging point. Using the form of a matrix is convenient for editing and storage and is easy for the computer to recognize.

[0066] Example 5: As Figure 6 , Figure 7 , Figure 8 and Figure 9 shown, a specific prediction method for diesel freezing point and cold filter plugging point provided by an embodiment of the present invention includes:

[0067] Step S402: Use a certain analysis instrument to analyze and test diesel to obtain the actual value of property a;

[0068] Step S404: Based on the main homologues in the diesel structure, obtain a certain central molecule set;

[0069] Step S406: Obtain virtual molecules from the central molecule set according to a certain rule;

[0070] Step S408: Apply a certain structure-property relationship b to the virtual molecules to obtain the calculation function of the virtual molecule content and property a;

[0071] Step S410: Use a certain optimization algorithm to limit the error between the calculated value and the actual value of property a to be less than a certain value, and solve the function to obtain the relative content of each molecule in the virtual diesel;

[0072] Step S412: Combine a certain structure vector and the molecule content relationship to obtain the diesel molecule matrix;

[0073] Step S414: Predict the freezing point and cold filter plugging point by applying the method combining the molecular matrix and the neural network.

[0074] Specifically, nuclear magnetic resonance was used to analyze the straight-run diesel raw material molecules, and the aromatic carbon ratio, aliphatic carbon ratio, degree of aromatic ring substitution, and degree of alkane chain branching of diesel were obtained. A comprehensive two-dimensional gas chromatography-time-of-flight mass spectrometry was used to obtain the composition and content of diesel. At the same time, the average molecular weight of diesel and the elemental contents of C, H, O, and heteroatoms N and S were detected.

[0075] As Figure 9 shown, according to the main homologues in the straight-run diesel structure, some molecules with similar reaction characteristics or structural features were grouped together to obtain 46 central molecules.

[0076] The central molecule set added -CH3 to the central molecules according to the rules. When adding, there was a priority order, including but not limited to not considering isomers, only changing the carbon number of alkanes, first satisfying the increase in the number of methyl groups in the ring structure, and when adding side chains to the ring, cycloalkane rings were preferred over aromatic rings. After removing some unreasonable molecules, 803 virtual molecules were obtained and used as all the molecules describing diesel.

[0077] The virtual molecules were applied with the group contribution method to obtain the relationship between structure and properties, including the relationship between structure and elemental content, structure and average molecular weight, structure and saturate content, structure and aromatic content, and structure and fraction, and the calculation function of virtual molecule content and properties was obtained.

[0078] The simulated annealing algorithm was used to limit the error between the calculated property value and the actual value to be less than 1×10 -6 , and the relative content of each molecule in the virtual diesel was obtained.

[0079] Combining the relationship between 16 structural vectors and molecular content, a diesel molecular matrix was obtained, and this matrix contained 803 molecules. As shown in Table 1, the error between the experimental value and the calculated value was within 5%, verifying the reliability of this matrix.

[0080] Table 1

[0081]

[0082] The neural network was applied to analyze the complex diesel molecular structure information and predict the molecular properties. The molecular matrix was sent into the neural network for training to obtain the freezing point and cold filter plugging point of diesel. As shown in Table 2, the error between the calculated value and the experimental value was within 0.6%.

[0083] Table 2

[0084]

[0085] The beneficial effects of the embodiments of the present invention are as follows: (1) The raw material molecular matrix is used to better describe diesel at the molecular level. (2) The neural network is applied to analyze the complex diesel molecular structure information and predict the molecular properties, so as to more conveniently, economically and accurately predict the pour point and cold filter plugging point. (3) Using the matrix form is convenient for editing and storage and is easy for computer recognition.

[0086] Embodiment 6: The embodiment of the present invention provides a computer device, which includes a memory, a processor, a communication interface and a communication bus. A program that can run on the processor is stored in the memory. When the processor executes the program, the prediction method of the pour point and cold filter plugging point of diesel described in the above embodiments is realized.

[0087] The processor can be a central processing unit, and the processor can also be other general-purpose processors, digital signal processors, application-specific integrated circuits, field programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. chips, or a combination of the above types of chips.

[0088] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs, non-transitory computer-executable programs and units, such as the corresponding program units in the above method embodiments of the present invention. The processor executes various functional applications and work data processing of the processor by running the non-transitory software programs, instructions and modules stored in the memory, that is, the prediction method of the pour point and cold filter plugging point of diesel described in the above embodiments is realized.

[0089] The memory can include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created by the processor and the like. In addition, the memory can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage devices. The memory can optionally include a memory remotely set relative to the processor, and these remote memories can be connected to the processor through a network. The one or more programs are stored in the memory and, when executed by the processor, implement the prediction method of the pour point and cold filter plugging point of diesel described in the above embodiments.

[0090] Embodiment 7: The embodiment of the present invention provides a storage medium for computer-readable storage. The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the prediction method of the pour point and cold filter plugging point of diesel provided in any one of the above method embodiments.

[0091] Among them, the storage medium can be an internal storage unit of a computer device, such as the hard disk or memory of the computer device. The storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card, a secure digital card, a flash card, etc. equipped on the computer device.

[0092] In the present invention, the terms "first", "second", and "third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance; the term "plurality" means two or more, unless otherwise clearly defined. Terms such as "installed", "connected", "connected to", and "fixed" should all be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; "connected" can be a direct connection or an indirect connection through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0093] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by terms such as "upper", "lower", "front", and "rear" is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or module referred to must have a specific direction, be constructed and operated in a specific orientation, and therefore cannot be construed as a limitation to the present invention.

[0094] In the description of this specification, the description of terms such as "one embodiment", "some embodiments", and "specific embodiments" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or instance. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0095] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

[0096] The above technical features constitute the embodiments of the present invention, which have strong adaptability and implementation effects. Non-essential technical features can be added or subtracted according to actual needs to meet the requirements of different situations.

Claims

1. A method for predicting diesel pour point and cold filter point, characterized in that The following steps are involved: Analyze and test diesel through analytical instruments to obtain the actual value of the first property; obtain the main homologues in the diesel structure, and obtain the central molecule set based on the main homologues; Expand the central molecule set according to the preset rules to obtain virtual molecules; apply the preset structure and property relationship to the virtual molecules to obtain the virtual molecule content and the first property calculation function; The first property calculation function is optimized by an optimization algorithm, and the error between the actual value of the first property and the calculated value of the first property is limited to be less than a preset value, so as to obtain the relative content of the virtual molecules in the virtual diesel; The diesel molecular matrix is ​​obtained according to the relative content and structural vector of the virtual molecules; the diesel molecular matrix is ​​sent to the neural network model for prediction to obtain the pour point and cold filter point of the diesel.

2. The method for predicting diesel pour point and cold filter plugging point according to claim 1, characterized in that When the diesel molecular matrix is ​​input into the neural network model for prediction to obtain the pour point and cold filter plugging point of the diesel, the following steps are specifically included: dividing the diesel molecular matrix into a training set and a prediction set; inputting the training set into the initial neural network for training to obtain the neural network model; inputting the prediction set into the neural network model for prediction to obtain the pour point and cold filter plugging point of the diesel.

3. The method for predicting diesel pour point and cold filter plugging point according to claim 1, characterized in that When the central molecule set is expanded according to the preset rules to obtain the virtual molecule, the following steps are specifically included: according to the preset rules, a methyl group is added to the central molecule of the central molecule set to obtain the virtual molecule; wherein the preset rules include one of the following or a combination thereof: isomerism is not considered, the chain alkane only changes its carbon number, the ring structure first satisfies the increase in the number of methyl groups, and the cycloalkane ring is superior to the aromatic ring when a side chain is added to the ring.

4. The method for predicting the diesel pour point and cold filter plugging point according to claim 1, 2 or 3, characterized in that The central molecule collection includes 40 to 70 central molecules.

5. The method for predicting the diesel pour point and cold filter plugging point according to claim 1, 2 or 3, characterized in that The preset structure-property relationship includes one of the following or a combination thereof: structure and element content, structure and average molecular weight, structure and saturated content, structure and aromatic content, structure and boiling point.

6. The method for predicting the diesel pour point and cold filter plugging point according to claim 1, 2 or 3, characterized in that The optimization algorithm includes one of the following or a combination thereof: ant colony algorithm, simulated annealing method, genetic algorithm, artificial neural network algorithm.

7. The method for predicting the diesel pour point and cold filter plugging point according to claim 1, 2 or 3, characterized in that The neural network model includes one of the following or a combination thereof: a single-layer neural network, a feedforward neural network, a radial basis function network, a deep feedforward network, and a recurrent neural network.

8. A prediction system for diesel pour point and cold filter point, characterized in that include: An analysis module, used for analyzing and testing the diesel through an analytical instrument to obtain an actual value of the first property; An acquisition module is used to acquire the main homologues in the diesel structure and obtain a central molecule set based on the main homologues; An expansion module is used to expand the central molecule set according to preset rules to obtain virtual molecules; An application module, used for applying a preset structure and property relationship to a virtual molecule to obtain a virtual molecule content and a first property calculation function; An optimization module is used to optimize the first property calculation function through an optimization algorithm, limit the error between the actual value of the first property and the calculated value of the first property to be less than a preset value, and obtain the relative content of virtual molecules in the virtual diesel; A matrix acquisition module is used to obtain a diesel molecular matrix according to the relative content and structure vector of the virtual molecules; The prediction module is used to send the diesel molecular matrix into the neural network model for prediction to obtain the diesel's pour point and cold filter point.

9. A computer device comprising a memory and a processor, wherein the memory stores a program that can be run on the processor, characterized in that: When the processor executes the program, the method for predicting the diesel pour point and cold filter plugging point as described in any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the method for predicting diesel pour point and cold filter plugging point as described in any one of claims 1 to 7.

Images