Method and device for extracting characteristics of distillate oil product

Abstract

The invention provides a distillate oil product characteristic extraction method and device. The method comprises the following steps: determining product characteristic original data of each distillate oil at a representative temperature point; optimizing the sparse representation of the original data of the product characteristics by taking the minimization of the difference between the estimated data of the product characteristics of each distillate oil at the representative temperature point and the measured data of the product characteristics of each distillate oil at the representative temperature point as a target to obtain a sparse coefficient vector; determining a product characteristic curve graph based on the sparse coefficient vector; and based on the product characteristic curve graph, extracting product characteristics of distillate oil corresponding to different temperatures. According to the method, the product characteristic curve graph is determined based on the sparse coefficient vector, so that the product characteristics of the distillate oil corresponding to any temperature can be accurately and rapidly extracted based on the product characteristic curve graph, and the problem that the physical properties of the distillate oil in any temperature section cannot be obtained in a traditional method is avoided.

Description

Technical Field

[0001] The invention relates to the technical field of distillate oil estimation, and in particular to a method and a device for extracting characteristics of distillate oil products. Background Art

[0002] Crude oil evaluation data is an important resource for the petrochemical industry and plays a supporting role in all aspects of the petrochemical industry.

[0003] Crude oil evaluation can be divided into general property evaluation, conventional evaluation and comprehensive evaluation according to different needs, among which general property evaluation is the most commonly used crude oil evaluation method. General property evaluation includes the general properties of crude oil, the fraction composition of crude oil and the physical properties of the fractions, the chemical composition of each fraction and the performance of use. In the general property evaluation brief report, crude oil fractions are usually divided into light end, naphtha, aviation fuel oil, diesel fraction, vacuum light wax oil, vacuum heavy wax oil, atmospheric residue oil, and vacuum residue oil fractions. However, the above is usually analyzed as a whole according to the fraction, so the analysis data contains data corresponding to a specific temperature section, and the physical properties of the distillate oil in any temperature section cannot be obtained. Summary of the invention

[0004] The present invention provides a method and device for extracting characteristics of distillate oil products, which are used to solve the defect in the prior art that the physical properties of distillate oil in any temperature range cannot be obtained.

[0005] The present invention provides a method for extracting characteristics of distillate oil products, comprising:

[0006] Determine the original data of product characteristics of each distillate at representative temperature points;

[0007] The sparse representation of the original data of the product characteristics is optimized to obtain a sparse coefficient vector with the goal of minimizing the difference between the estimated data of the product characteristics of each distillate at a representative temperature point and the measured data of the product characteristics of each distillate at a representative temperature point; the estimated data of the product characteristics is determined based on the sparse representation;

[0008] Determining a product characteristic curve graph based on the sparse coefficient vector;

[0009] Based on the product characteristic curve, the product characteristics of the distillate oil corresponding to different temperatures are extracted.

[0010] According to a method for extracting product characteristics of distillate oil provided by the present invention, the original data of product characteristics are sparsely represented based on a sparse basis.

[0011] According to a method for extracting product characteristics of distillate oil provided by the present invention, determining a product characteristic curve graph based on the sparse coefficient vector comprises:

[0012] Based on the sparse basis and the sparse coefficient vector, the product characteristic curve graph is determined.

[0013] According to a method for extracting product characteristics of distillate oil provided by the present invention, the process of determining the original data of product characteristics of each distillate oil at a representative temperature point comprises:

[0014] Based on the crude oil evaluation data, determine the evaluation data of each fraction;

[0015] Based on the evaluation data of each fraction, the original data of product characteristics of each fraction oil at a representative temperature point is determined.

[0016] According to a method for extracting characteristics of a distillate oil product provided by the present invention, the crude oil evaluation data includes at least one of density, freezing point, sulfur content, nitrogen content, acid value, metal content, characteristic factor and yield.

[0017] According to a method for extracting product characteristics of distillate oil provided by the present invention, the product characteristic estimation data is determined based on the following steps:

[0018] Based on the sparse representation, determining a sparse basis matrix and signal sparse domain coefficients;

[0019] The product characteristic estimation data is determined based on the observation matrix, the sparse base matrix and the signal sparse domain coefficients.

[0020] The present invention also provides a device for extracting characteristics of distillate oil products, comprising:

[0021] A first determination unit is used to determine the original data of product characteristics of each distillate oil at a representative temperature point;

[0022] an optimization unit, configured to optimize the sparse representation of the original data of the product characteristics with the goal of minimizing the difference between the estimated data of the product characteristics of each distillate at a representative temperature point and the measured data of the product characteristics of each distillate at a representative temperature point, so as to obtain a sparse coefficient vector; the estimated data of the product characteristics is determined based on the sparse representation;

[0023] A second determining unit, configured to determine a product characteristic curve graph based on the sparse coefficient vector;

[0024] The extraction unit is used to extract the product characteristics of the distillate oil corresponding to different temperatures based on the product characteristic curve diagram.

[0025] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any of the above-mentioned methods for extracting characteristics of distillate oil products is implemented.

[0026] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for extracting characteristics of a distillate oil product as described in any one of the above is implemented.

[0027] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for extracting characteristics of a distillate oil product as described above is implemented.

[0028] The distillate oil product characteristic extraction method and device provided by the present invention determine the product characteristic curve diagram based on the sparse coefficient vector, so that the product characteristics of the distillate oil corresponding to any temperature can be accurately and quickly extracted based on the product characteristic curve diagram, avoiding the problem that the physical properties of the distillate oil in any temperature range cannot be obtained in the traditional method. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1 It is a schematic flow diagram of the method for extracting characteristics of distillate oil products provided by the present invention;

[0031] Figure 2 It is a schematic diagram of the structure of the distillate oil product characteristic extraction device provided by the present invention;

[0032] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] Crude oil evaluation can be divided into general property evaluation, conventional evaluation and comprehensive evaluation according to different needs, among which general property evaluation is the most commonly used crude oil evaluation method. General property evaluation includes the general properties of crude oil, the fraction composition of crude oil and the physical properties of the fractions, the chemical composition of each fraction and the performance of use. In the general property evaluation brief report, crude oil fractions are usually divided into light end, naphtha, aviation fuel oil, diesel fraction, vacuum light wax oil, vacuum heavy wax oil, atmospheric residue oil, and vacuum residue oil fractions. However, the amount of crude oil evaluation data is small and the distribution is highly dispersed, and the above is usually analyzed as a whole according to the fraction, so the analysis data contains data corresponding to a specific temperature segment, and the physical properties of the distillate oil in any temperature segment cannot be obtained.

[0035] To this end, the present invention provides a method for extracting characteristics of distillate oil products. Figure 1 Schematic diagram of the process of extracting the characteristics of distillate oil products provided by the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0036] Step 110: determine the original data of product characteristics of each distillate oil at a representative temperature point.

[0037] Here, distillate oil refers to different oil products separated by distillation during crude oil processing. Crude oil is heated and fractionated in a distillation tower, and different oil products are separated in different temperature ranges to obtain different distillates. Among them, distillates can include gasoline, kerosene, diesel, jet fuel, lubricating oil, heavy oil, naphtha, solvent oil, etc.

[0038] During the distillation process, distillate oil will be separated at different temperature points, among which the representative temperature points of distillate oil may include initial distillation temperature, average boiling point, final distillation temperature, 90% evaporation temperature, etc. Initial distillation temperature refers to the temperature at which crude oil begins to evaporate, average boiling point refers to the average evaporation temperature of crude oil, final distillation temperature refers to the temperature at which crude oil completely evaporates, and 90% evaporation temperature refers to the temperature at which 90% of the mass of the crude oil has evaporated.

[0039] Optionally, the representative temperature of each distillate oil can be determined by the central temperature point, that is, if the upper limit of the temperature range of the distillate is 300°C and the lower limit of the temperature range is 320°C, then the original data of the product characteristics of the distillate, such as yield, sulfur content, API (American Petroleum Institute), etc., corresponds to a representative temperature of (320+300)÷2=310°C.

[0040] The raw data of product characteristics are used to characterize the product characteristics of each distillate oil, which may include the yield, physical properties and other data of each distillate oil.

[0041] Step 120, with the goal of minimizing the difference between the estimated product characteristic data of each distillate oil at a representative temperature point and the measured product characteristic data of each distillate oil at a representative temperature point, optimize the sparse representation of the original product characteristic data to obtain a sparse coefficient vector; the product characteristic estimated data is determined based on the sparse representation.

[0042] Specifically, the product characteristic estimation data is the data estimated based on the sparse representation. The product characteristic measurement data can be understood as the measured product characteristic data, that is, the actual product characteristic data. Since the product characteristic estimation data is determined based on the sparse representation, the smaller the difference between the product characteristic estimation data and the product measurement data, the closer the product characteristic information contained in the sparse representation is to the actual product characteristic information, that is, the higher the accuracy of the sparse representation.

[0043] After optimizing the sparse representation of the original data of product characteristics with the goal of minimizing the difference between the estimated data of product characteristics of each distillate at a representative temperature point and the measured data of product characteristics of each distillate at a representative temperature point, the obtained sparse representation is optimal, and the accuracy of the obtained sparse coefficient vector is also high.

[0044] Among them, sparse representation is a data representation method that aims to represent data by using as few non-zero elements (or a small number of non-zero coefficients) as possible. In sparse representation, data is represented as a linear combination of a set of basis vectors, where only a few basis vectors have non-zero coefficients. A sparse coefficient vector refers to a coefficient vector that contains fewer non-zero coefficient elements. In sparse representation, data is represented as a linear combination of a set of basis vectors, where a few basis vectors have non-zero coefficients, and these non-zero coefficients constitute a sparse coefficient vector.

[0045] Step 130: Determine a product characteristic curve based on the sparse coefficient vector.

[0046] Step 140: extract product characteristics of distillate oils corresponding to different temperatures based on the product characteristic curve.

[0047] Optionally, the sparse coefficient vector can be multiplied by the transformation matrix corresponding to the sparse representation to obtain a product characteristic curve, wherein the product characteristic curve is used to characterize the product characteristics of distillate oil corresponding to different temperatures, and then the product characteristics of distillate oil corresponding to any temperature UI can be obtained based on the product characteristic curve.

[0048] It can be seen that the method for extracting distillate oil product characteristics provided in the embodiment of the present invention determines the product characteristic curve diagram based on the sparse coefficient vector, so that the product characteristics of the distillate oil corresponding to any temperature can be accurately and quickly extracted based on the product characteristic curve diagram, thereby avoiding the problem that the physical properties of the distillate oil in any temperature range cannot be obtained in the traditional method.

[0049] Based on the above embodiment, the original data of product characteristics is sparsely represented based on a sparse basis.

[0050] Specifically, sparse basis means that when the original data of product characteristics is projected onto the orthogonal transformation basis, the absolute values ​​of most of the transformation coefficients are very small, and the resulting transformation vector is sparse or approximately sparse, which can be regarded as a concise expression of high-resolution data. This is a priori condition for compressed sensing, that is, the signal must be sparsely represented under a certain transformation. Usually, the transformation basis can be flexibly selected according to the characteristics of the signal itself. Commonly used ones include discrete cosine transform basis, fast Fourier transform basis, discrete wavelet transform basis, Curvelet basis, Gabor basis, and redundant dictionary. In the specific implementation process, a transformation method that can sparsely represent the coefficients of the original data of product characteristics is selected in the above transformations as appropriate.

[0051] Based on any of the above embodiments, determining a product characteristic curve graph based on the sparse coefficient vector includes:

[0052] Based on the sparse basis and the sparse coefficient vector, a product characteristic curve graph is determined.

[0053] Specifically, the sparse basis can be understood as a transformation matrix used in sparse representation, which is a matrix composed of atoms or basis vectors, each basis vector representing a feature of the data.

[0054] Optionally, the sparse basis and the sparse coefficient vector may be multiplied to obtain a product characteristic curve graph.

[0055] Based on any of the above embodiments, determining the original data of product characteristics of each distillate oil at a representative temperature point includes:

[0056] Based on the crude oil evaluation data, determine the evaluation data of each fraction;

[0057] Based on the evaluation data of each fraction, the original data of product characteristics of each fraction oil at a representative temperature point is determined.

[0058] Specifically, the crude oil evaluation data may include Enn-Schmidt distillation data, true boiling point distillation data, API data, density data, sulfur content, etc. According to the crude oil evaluation data, the evaluation data corresponding to different fractions can be obtained, and the original data of product characteristics of each fraction oil at a representative temperature point can be calculated based on the evaluation data of each fraction. The original data of product characteristics may include yield, density, viscosity, sulfur content, etc.

[0059] Among them, the yield of each fraction can be calculated according to the output of each fraction and the total crude oil output, such as yield = (fraction section output / total crude oil output) × 100%.

[0060] In addition, the physical property data of each fraction can be obtained through experimental testing or estimation. Common physical property data include density, viscosity, sulfur content, etc.

[0061] Density can be calculated by measuring the mass and volume of a fraction. Viscosity is a measure of a liquid's resistance to flow and is usually expressed in terms of dynamic viscosity (in Pascal seconds, Pa·s) or kinematic viscosity (in square meters per second, m 2 The sulfur content is an indicator of the sulfide content in the fraction and is usually expressed in mass percentage (wt%).

[0062] Based on any of the above embodiments, the crude oil evaluation data includes at least one of density, freezing point, sulfur content, nitrogen content, acid value, metal content, characteristic factor and yield.

[0063] Specifically, crude oil density refers to the mass of crude oil per unit volume. The freezing point of crude oil refers to the temperature at which crude oil changes from liquid to solid under specific conditions. Different crude oils have different freezing points, and the influence of freezing point needs to be considered when transporting and storing crude oil. The sulfur content in crude oil refers to the mass percentage of sulfides in crude oil. The nitrogen content in crude oil refers to the mass percentage of nitrogen compounds in crude oil. The acid value or acidity of crude oil refers to the concentration of acidic substances contained in crude oil. The metal content in crude oil usually refers to the content of metal elements such as sodium (Na), nickel (Ni), vanadium (V), and iron (Fe). The performance factor is a comprehensive indicator used to describe crude oil. It involves multiple factors such as density, freezing point, sulfur content, etc., and can be used to roughly evaluate the quality and use of crude oil. The yield of various petroleum products (such as gasoline, diesel, lubricating oil, etc.) in crude oil refers to the amount of specific petroleum products obtained from a unit volume or mass of crude oil.

[0064] In addition, crude oil evaluation data can also include crude oil API, which refers to the API gravity index of crude oil, which is an indicator to measure the weight of crude oil. The API gravity index is a value calculated based on the density of crude oil, which is used to describe the weight of crude oil. The higher the API gravity index, the lighter the crude oil and the lower its density; the lower the API gravity index, the heavier the crude oil and the higher its density.

[0065] Based on any of the above embodiments, the product characteristic estimation data is determined based on the following steps:

[0066] Based on the sparse representation, a sparse basis matrix and signal sparse domain coefficients are determined;

[0067] Product characteristic estimation data is determined based on the observation matrix, the sparse basis matrix and the signal sparse domain coefficients.

[0068] Specifically, the optimization method used in the embodiment of the present invention to optimize the sparse representation refers to a general term for some disciplines on how to seek certain factors (quantities) under given constraints to optimize a certain (or certain) indicator. It usually refers to an algorithm that minimizes the error between the calculated value and the observed value. Commonly used optimization algorithms include gradient descent method, quasi-Newton method, heuristic algorithm, neural network algorithm, etc. The reconstruction process can be expressed as:

[0069] y=φψs

[0070] Wherein, y is the observed signal (i.e., product characteristic estimation data), φ is the observation matrix, ψ is the sparse basis matrix, and s is the signal sparse domain coefficient. In the embodiment of the present invention, φ is selected as random unequally spaced subsampling, and a Bernouli matrix can be selected. For the sparse basis matrix ψ, the commonly used discrete Fourier transform (DCT) sparse basis can be expressed as:

[0071]

[0072]

[0073] Where G represents the frequency domain signal after DCT transformation, and M is the transformation matrix dimension. y, φ and ψ are all known quantities, and the sparse domain signal s is solved, and then the crude oil yield (physical property) data is constructed through x=ψs.

[0074] In the embodiment of the present invention, the reconstruction process is a zero norm (L0) minimization problem, which is an NP-complete problem (a problem with no fast solution), so it is often converted into L1 norm minimization, and the optimization objective function is solved as follows: Among them, y s Represents product characteristic measurement data.

[0075] The distillate oil product characteristic extraction device provided by the present invention is described below. The distillate oil product characteristic extraction device described below and the distillate oil product characteristic extraction method described above can be referenced to each other.

[0076] Based on any of the above embodiments, the present invention also provides a device for extracting characteristics of distillate oil products, such as Figure 2 As shown, the device comprises:

[0077] The first determination unit 210 is used to determine the original data of product characteristics of each distillate oil at a representative temperature point;

[0078] The optimization unit 220 is used to optimize the sparse representation of the original data of the product characteristics with the goal of minimizing the difference between the estimated data of the product characteristics of each distillate oil at the representative temperature point and the measured data of the product characteristics of each distillate oil at the representative temperature point to obtain a sparse coefficient vector; the estimated data of the product characteristics is determined based on the sparse representation;

[0079] A second determining unit 230, configured to determine a product characteristic curve graph based on the sparse coefficient vector;

[0080] The extraction unit 240 is used to extract the product characteristics of the distillate oil corresponding to different temperatures based on the product characteristic curve.

[0081] Based on any of the above embodiments, the original data of product characteristics is sparsely represented based on a sparse basis.

[0082] Based on any of the above embodiments, determining a product characteristic curve graph based on the sparse coefficient vector includes:

[0083] Based on the sparse basis and the sparse coefficient vector, a product characteristic curve graph is determined.

[0084] Based on any of the above embodiments, determining the original data of product characteristics of each distillate oil at a representative temperature point includes:

[0085] Based on the crude oil evaluation data, determine the evaluation data of each fraction;

[0086] Based on the evaluation data of each fraction, the original data of product characteristics of each fraction oil at a representative temperature point is determined.

[0087] Based on any of the above embodiments, the crude oil evaluation data includes at least one of density, freezing point, sulfur content, nitrogen content, acid value, metal content, characteristic factor and yield.

[0088] Based on any of the above embodiments, the product characteristic estimation data is determined based on the following steps:

[0089] Based on the sparse representation, a sparse basis matrix and signal sparse domain coefficients are determined;

[0090] Product characteristic estimation data is determined based on the observation matrix, the sparse basis matrix and the signal sparse domain coefficients.

[0091] Figure 3 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 3As shown, the electronic device may include: a processor 310, a memory 320, a communications interface 330 and a communications bus 340, wherein the processor 310, the memory 320 and the communications interface 330 communicate with each other through the communications bus 340. The processor 310 may call the logic instructions in the memory 320 to execute the distillate oil product characteristic extraction method, which includes: determining the product characteristic original data of each distillate oil at a representative temperature point; optimizing the sparse representation of the product characteristic original data to obtain a sparse coefficient vector with the goal of minimizing the difference between the product characteristic estimation data of each distillate oil at a representative temperature point and the product characteristic measurement data of each distillate oil at a representative temperature point; determining the product characteristic estimation data based on the sparse representation; determining the product characteristic curve diagram based on the sparse coefficient vector; extracting the product characteristics of the distillate oil corresponding to different temperatures based on the product characteristic curve diagram.

[0092] In addition, the logic instructions in the above-mentioned memory 320 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0093] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the distillate oil product characteristic extraction method provided by the above-mentioned methods, and the method includes: determining the original data of the product characteristics of each distillate oil at a representative temperature point; optimizing the sparse representation of the original data of the product characteristics with the goal of minimizing the difference between the estimated data of the product characteristics of each distillate oil at the representative temperature point and the measured data of the product characteristics of each distillate oil at the representative temperature point to obtain a sparse coefficient vector; the product characteristic estimation data is determined based on the sparse representation; based on the sparse coefficient vector, a product characteristic curve diagram is determined; based on the product characteristic curve diagram, the product characteristics of the distillate oil corresponding to different temperatures are extracted.

[0094] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the above-mentioned distillate oil product characteristic extraction method, the method comprising: determining the original data of the product characteristics of each distillate oil at a representative temperature point; optimizing the sparse representation of the original data of the product characteristics with the goal of minimizing the difference between the estimated data of the product characteristics of each distillate oil at the representative temperature point and the measured data of the product characteristics of each distillate oil at the representative temperature point to obtain a sparse coefficient vector; the product characteristic estimation data is determined based on the sparse representation; based on the sparse coefficient vector, a product characteristic curve diagram is determined; based on the product characteristic curve diagram, the product characteristics of the distillates corresponding to different temperatures are extracted.

[0095] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0096] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for extracting characteristics of distillate oil products, characterized in that: include: Determine the original data of product characteristics of each distillate at representative temperature points; The sparse representation of the original data of the product characteristics is optimized to obtain a sparse coefficient vector with the goal of minimizing the difference between the estimated data of the product characteristics of each distillate at a representative temperature point and the measured data of the product characteristics of each distillate at a representative temperature point; the estimated data of the product characteristics is determined based on the sparse representation; Determining a product characteristic curve graph based on the sparse coefficient vector; Based on the product characteristic curve, the product characteristics of the distillate oil corresponding to different temperatures are extracted.

2. The method for extracting characteristics of distillate oil products according to claim 1, characterized in that: The product characteristic original data is sparsely represented based on a sparse basis.

3. The method for extracting characteristics of distillate oil products according to claim 2, characterized in that: The step of determining a product characteristic curve graph based on the sparse coefficient vector comprises: Based on the sparse basis and the sparse coefficient vector, the product characteristic curve graph is determined.

4. The method for extracting characteristics of distillate oil products according to any one of claims 1 to 3, characterized in that: The original data of product characteristics of each distillate oil at a representative temperature point are determined, including: Based on the crude oil evaluation data, determine the evaluation data of each fraction; Based on the evaluation data of each fraction, the original data of product characteristics of each fraction oil at a representative temperature point is determined.

5. The method for extracting characteristics of distillate oil products according to claim 4, characterized in that: The crude oil evaluation data includes at least one of density, freezing point, sulfur content, nitrogen content, acid value, metal content, characteristic factor and yield.

6. The method for extracting characteristics of distillate oil products according to any one of claims 1 to 3, characterized in that: The product characteristic estimation data is determined based on the following steps: Based on the sparse representation, determining a sparse basis matrix and signal sparse domain coefficients; The product characteristic estimation data is determined based on the observation matrix, the sparse base matrix and the signal sparse domain coefficients.

7. A device for extracting characteristics of distillate oil products, characterized in that: include: A first determination unit is used to determine the original data of product characteristics of each distillate oil at a representative temperature point; an optimization unit, configured to optimize the sparse representation of the original data of the product characteristics with the goal of minimizing the difference between the estimated data of the product characteristics of each distillate at a representative temperature point and the measured data of the product characteristics of each distillate at a representative temperature point, so as to obtain a sparse coefficient vector; the estimated data of the product characteristics is determined based on the sparse representation; A second determining unit, configured to determine a product characteristic curve graph based on the sparse coefficient vector; The extraction unit is used to extract the product characteristics of the distillate oil corresponding to different temperatures based on the product characteristic curve diagram.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for extracting characteristics of a distillate oil product according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for extracting characteristics of a distillate oil product according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for extracting characteristics of a distillate oil product according to any one of claims 1 to 6 is implemented.

Images