A crude oil blending method, system, and storage medium

Abstract

The application provides a crude oil blending method, system and storage medium. The crude oil blending method comprises the following steps: obtaining a plurality of physicochemical property values of a target crude oil sample to construct a first feature vector of the target crude oil sample; obtaining a plurality of single-product crude oil samples, and performing exhaustive combination on at least two of the plurality of single-product crude oil samples according to minimum ratio difference to obtain a plurality of combined crude oil samples; calculating a plurality of physicochemical property values of each combined crude oil sample respectively to construct a second feature vector of each combined crude oil sample; calculating the distance between the first feature vector and each second feature vector respectively; and determining the type and proportion of single-product crude oil samples required for blending the target crude oil sample according to the type and proportion of the combined crude oil sample corresponding to the second feature vector with the minimum distance from the first feature vector.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of petroleum chemical industry, and in particular to a crude oil blending method, a crude oil blending system, and a computer readable storage medium. BACKGROUND

[0002] Crude oil is oil that has not been processed. The physicochemical properties of crude oil from different production areas differ greatly. The crude oil processing flow of a petrochemical enterprise is very complex, and slight changes in the physicochemical properties of crude oil will have a great impact on subsequent production and processing devices. Therefore, petrochemical enterprises will blend crude oil from different production areas, compositions and physicochemical properties to form a crude oil suitable for actual production needs of the plant, i.e. mixed crude oil. In the production process, obtaining the physicochemical properties of mixed crude oil is the basis for stable operation and operation optimization of the refinery production device.

[0003] In the prior art, a crude oil detailed evaluation can provide comprehensive physicochemical properties of crude oil. However, due to the high cost and long time consumption of the crude oil detailed evaluation, the producer usually does not perform a crude oil detailed evaluation on the mixed crude oil, but performs a rough calculation on the comprehensive physicochemical properties of the mixed crude oil through the proportion of the blending instruction. The calculation result will be affected by errors caused by internal and external factors such as crude oil property fluctuations and crude oil blending operations, and the result will not be timely. In order to realize real-time monitoring of the physicochemical properties of crude oil, some large refineries have deployed an online crude oil rapid evaluation system, but the rapid evaluation system can only provide a limited type of crude oil physicochemical property data, which cannot meet the data needs of the operation optimization of the crude oil unit. Therefore, developing a mixed crude oil proportion calculation method to realize the combination of the comprehensiveness of the crude oil detailed evaluation and the real-time performance of the crude oil rapid evaluation has important practical significance for ensuring the stable operation of the device and improving the operation optimization level of the device.

[0004] CN101988895B discloses a method for predicting the content of a single crude oil in a mixed crude oil from near-infrared spectroscopy. The absorbance of the near-infrared spectrum of the crude oil is associated with the simulation of the single crude oil in the corresponding simulated mixed crude oil to establish a mathematical model for predicting the content of the single crude oil. However, this method is limited by the principle of near-infrared spectroscopy analysis, and requires a stable performance spectrometer and a large number of crude oil spectra for modeling, which has the defect of long time consumption.

[0005] CN107976420B discloses a method for predicting the composition of a mixed crude oil from near-infrared spectroscopy. The near-infrared spectrometer is used to measure the near-infrared spectrum of a single crude oil and a mixed crude oil, respectively, to calculate the polar coordinate projection score of the absorbance of two spectral regions to form a score composition matrix, and then use the non-negative constrained least squares method to calculate the content vector of the single crude oil. However, this method has high requirements for the repeatability of the near-infrared spectrometer.

[0006] CN112326811A discloses a method for predicting the content of a single crude oil in a mixed crude oil, mixing single or component crude oils in any proportion to form a mixed crude oil, using a gas chromatography method to determine the content of p-fluorobenzoate in the oil phase, and obtaining the proportion of the single or component crude oil in the mixed crude oil. However, this method cannot be used to measure the proportion of the mixed crude oil in the crude oil pipeline online.

[0007] Therefore, there is an urgent need in the art for a technology for determining the type and proportion of crude oil blending to improve the above-mentioned deficiencies in the prior art. SUMMARY

[0008] The following gives a brief overview of one or more aspects to provide a basic understanding of these aspects. This overview is not an extensive overview of all contemplated aspects, and is not intended to identify key or critical elements of all aspects or to delineate the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description presented later.

[0009] To overcome the above-mentioned defects of the prior art, the present application provides a crude oil blending method, a crude oil blending system, and a computer readable storage medium, which can determine the similarity of the physicochemical properties of the target crude oil sample and the combined crude oil sample with different mixing proportions by calculating the distance of the physicochemical property feature vectors of the two, thereby solving the problem of crude oil proportion calculation, providing a solution for the rapid analysis of mixed crude oil proportion and detailed physicochemical properties, and realizing the combination of crude oil full evaluation comprehensiveness and crude oil rapid evaluation real-time, so as to improve the automation level and economic benefit of the refinery.

[0010] Specifically, the above-mentioned crude oil blending method according to the first aspect of the present application comprises the following steps: obtaining a plurality of physicochemical property values of a target crude oil sample to construct a first feature vector of the target crude oil sample; obtaining a plurality of single crude oil samples and performing exhaustive combination on at least two of the plurality of single crude oil samples according to the minimum proportion difference to obtain a plurality of combined crude oil samples; calculating a plurality of physicochemical property values of each of the combined crude oil samples to construct a second feature vector of each of the combined crude oil samples; calculating the distance between the first feature vector and each of the second feature vectors; and determining the type and proportion of single crude oil samples required for blending the target crude oil sample according to the type and proportion of the combined crude oil sample corresponding to the second feature vector with the smallest distance from the first feature vector.

[0011] Preferably, in an embodiment of the present application, the step of calculating the values of the plurality of physicochemical properties of each of the combined crude oil samples respectively to construct the second feature vector of each of the combined crude oil samples comprises: determining the types and proportions of single-product crude oil samples contained in the combined crude oil sample; performing linear calculation and / or nonlinear calculation on the values of the plurality of physicochemical properties of each of the single-product crude oil samples contained in the combined crude oil sample according to the types and proportions to determine the values of the plurality of physicochemical properties of the combined crude oil sample; and constructing the second feature vector of each of the combined crude oil samples according to the values of the plurality of physicochemical properties of the combined crude oil sample.

[0012] Preferably, in an embodiment of the present application, the values of the physicochemical properties are selected from one or more physicochemical properties in mass fraction, such as sulfur content, residual carbon, diesel yield, naphtha yield, wax oil yield, residual oil yield, etc., and the step of performing linear calculation and / or nonlinear calculation on the values of the plurality of physicochemical properties of each of the single-product crude oil samples contained in the combined crude oil sample according to the types and proportions to determine the values of the plurality of physicochemical properties of the combined crude oil sample comprises: performing linear calculation on the sulfur content, the residual carbon, the diesel yield, the naphtha yield, the wax oil yield, and / or the residual oil yield:

[0013] γ mix = n1γ1+ n2γ2… n i γ i

[0014] wherein γ mix is the value of the physicochemical property of the combined crude oil sample, n i represents the mass fraction of the i-th single-product crude oil sample in the combined crude oil sample, and γ i represents the value of the physicochemical property of the i-th single-product crude oil sample.

[0015] Preferably, in an embodiment of the present application, the values of the physicochemical properties include but are not limited to crude oil density, and the step of performing linear calculation and / or nonlinear calculation on the values of the plurality of physicochemical properties of each of the single-product crude oil samples contained in the combined crude oil sample according to the types and proportions to determine the values of the plurality of physicochemical properties of the combined crude oil sample comprises: performing nonlinear calculation on the crude oil density:

[0016] ρ mix = (n1+ n2… n i ) / 1 / ρ1+ n2 / ρ2… + n i / ρ i )

[0017] wherein ρ mix represents the value of the crude oil density of the combined crude oil sample, n iThis represents the mass fraction of the i-th single crude oil sample in the combined crude oil sample. i This represents the crude oil density of the i-th type of single-product crude oil sample.

[0018] Preferably, in one embodiment of the present invention, the first feature vector is represented as

[0019]

[0020] Wherein, a1 is the first physicochemical property value of the target crude oil sample, a2 is the second physicochemical property value of the target crude oil sample, and a n The nth physicochemical property value of the target crude oil sample, and / or the second eigenvector is represented as...

[0021]

[0022] Among them, a 1, a is the first physicochemical property value of the combined crude oil sample. 2, a is the second physicochemical property value of the combined crude oil sample. n,mix This represents the nth physicochemical property value of the combined crude oil sample.

[0023] Preferably, in one embodiment of the present invention, the step of calculating the distance between the first feature vector and each of the second feature vectors includes: calculating the distance between the first feature vector and each of the second feature vectors. With the second feature vector Euclidean distance between them:

[0024]

[0025] Where EucD is the Euclidean distance value, the smaller the value, the smaller the distance, indicating that the combined crude oil and the mixed crude oil are more similar; and / or calculate the first feature vector. With the second feature vector Cosine distance between them:

[0026]

[0027] Where cosD is the cosine distance, the smaller the value, the smaller the distance, indicating that the combined crude oil and the mixed crude oil are more similar; and / or calculate the first feature vector. With the second feature vector Mahalanobis distance between them:

[0028]

[0029] Where, mahD is the Mahalanobis distance, the smaller the value, the smaller the distance, indicating that the combined crude oil and the mixed crude oil are more similar, and S is the covariance matrix.

[0030] Preferably, in an embodiment of the present application, before calculating the distance between the first feature vector and each of the second feature vectors respectively, the crude oil blending method further comprises the steps of: obtaining a plurality of raw physicochemical property values of the target crude oil sample and / or the combined crude oil sample; and performing normalization and / or standardization processing on the plurality of raw physicochemical property values to determine a plurality of physicochemical property values of the target crude oil sample and / or the combined crude oil sample.

[0031] Preferably, in an embodiment of the present application, the step of determining the types and proportions of single crude oil samples required for blending the target crude oil sample according to the type and proportion of the combined crude oil sample corresponding to the second feature vector with the smallest distance from the first feature vector comprises: detecting a plurality of physicochemical property values of the combined crude oil sample corresponding to the second feature vector with the smallest distance from the first feature vector; in response to any of the physicochemical property values deviating from the corresponding physicochemical property value of the target crude oil sample by more than a pre-set deviation threshold, determining that the combined crude oil sample is an outlier and excluding the combined crude oil sample; and determining the types and proportions of single crude oil samples required for blending the target crude oil sample according to the type and proportion of at least one combined crude oil sample that has passed the outlier screening.

[0032] In addition, the above-mentioned crude oil blending system according to the second aspect of the present application comprises a memory and a processor. The memory has computer instructions stored thereon. The processor is connected to the memory and is configured to execute the computer instructions stored on the memory to implement the crude oil blending method provided by any one of the above-mentioned embodiments.

[0033] In addition, the above-mentioned computer readable storage medium according to the second aspect of the present application has computer instructions stored thereon. The computer instructions are executed by a processor to implement the crude oil blending method provided by any one of the above-mentioned embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0034] The above features and advantages of the present application can be better understood by reading the detailed description of embodiments of the present application in conjunction with the following drawings, in which: the components are not necessarily drawn to scale, and components of similar or identical function or features can have the same or similar reference label.

[0035] Figure 1 A flowchart of a crude oil blending method according to some embodiments of the present application is shown. DETAILED DESCRIPTION

[0036] The advantages and benefits of the present application will become apparent upon reading the following description in conjunction with the accompanying drawings. While the application will be described with reference to the preferred embodiment, it is to be understood that the application is not limited to that embodiment. To the contrary, the application is intended to encompass a variety of alternatives, modifications and equivalents. For the purpose of illustration only, the following description will be in one specific embodiment. The application can be practiced without the specific details that will be set forth below to provide a thorough description of the embodiments of the application. In addition, certain terminology will be used in the following description for the purpose of reference only and will not be limiting.

[0037] In the description of the present application, it is to be understood that the terms "mounting", "connected", "connecting" should be construed broadly according to the context in which they are used, for example, they can be fixed connection, or detachable connection, or integral connection; can be mechanical connection, or electrical connection; can be directly connected, or indirectly connected through an intermediate medium, or internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0038] In addition, "up", "down", "left", "right", "top", "bottom", "horizontal", "vertical" used in the following description should be understood as the orientation shown in the section and the related drawings. The relative terms are only for the convenience of description, and do not mean that the device described thereby must be manufactured or operated in a particular orientation, and therefore should not be understood as a limitation on the application.

[0039] It is to be understood that although the terms "first", "second", "third", etc. can be used herein to describe various components, regions, layers and / or sections, these components, regions, layers and / or sections should not be limited by these terms, and these terms are only used to distinguish different components, regions, layers and / or sections. Therefore, the first component, region, layer and / or section discussed below can be referred to as the second component, region, layer and / or section without departing from some embodiments of the application.

[0040] As described above, in the process of crude oil blending, the existing comprehensive evaluation of the physicochemical properties of crude oil has the defects of high cost and long time consumption. Although the existing rapid evaluation system can ensure real-time performance, it can only provide a limited number of physicochemical property data, which cannot meet the data requirements of the operation optimization of the crude oil unit. Therefore, the existing blending technology is generally limited by equipment requirements or scheme restrictions, and cannot achieve comprehensive calculation and real-time calculation of the physicochemical properties of crude oil.

[0041] In order to overcome the above-mentioned defects in the prior art, the present application provides a crude oil blending method, a crude oil blending system and a computer readable storage medium, which can determine the similarity of the physicochemical properties of the target crude oil sample and the combined crude oil sample with different mixing ratios by calculating the distance of the physicochemical property feature vectors of the target crude oil sample and the combined crude oil sample, thereby solving the problem of difficult calculation of the crude oil ratio, providing a solution for rapid analysis of the mixed crude oil ratio and detailed physicochemical properties of the mixed crude oil, and realizing the combination of comprehensive crude oil evaluation and real-time crude oil rapid evaluation, so as to improve the automation level of the refinery and economic benefits.

[0042] In some non-limiting embodiments, the above-mentioned crude oil blending method provided by the first aspect of the present application can be implemented by the above-mentioned crude oil blending system provided by the second aspect of the present application. Specifically, the crude oil blending system can be configured with a memory and a processor. The memory includes but is not limited to the above-mentioned computer readable storage medium provided by the third aspect of the present application, and the computer instructions are stored on the computer readable storage medium. The processor is connected to the memory and is configured to execute the computer instructions stored on the memory to implement the crude oil blending method provided by the first aspect of the present application.

[0043] The working principle of the above-mentioned crude oil blending system will be described below in combination with some embodiments of the text matching method. Those skilled in the art can understand that the embodiments of the crude oil blending method are only some non-limiting embodiments provided by the present application, which are intended to clearly demonstrate the main idea of the present application and provide some specific solutions for the public to implement, rather than to limit the overall function or overall working mode of the crude oil blending system. Similarly, the crude oil blending system is also only a non-limiting embodiment provided by the present application, and the execution subject and execution order of each step in the text matching method are not limited.

[0044] Please refer to Figure 1 , Figure 1 The flowchart of the crude oil blending method provided by some embodiments of the present application is shown.

[0045] As Figure 1 shown, in step S1 of the crude oil blending method, the crude oil blending system can first collect a group of samples of mixed crude oil as a target crude oil sample, then obtain a plurality of physicochemical property values of the target crude oil sample, and construct a first feature vector of the target crude oil sample according to the obtained plurality of physicochemical property values.

[0046] In some non-limiting embodiments, the way of obtaining the plurality of physicochemical property values of the crude oil includes, but is not limited to, near-infrared crude oil rapid evaluation, nuclear magnetic crude oil rapid evaluation, standard test method for crude oil evaluation, or other crude oil evaluation method. The physicochemical property values of the crude oil include physical properties and chemical properties, including but not limited to density, sulfur content, nitrogen content, chlorine content, acid value, carbon residue, naphtha yield, diesel yield, wax oil yield, residual oil yield, distillation range, and the like.

[0047] Here, the first feature vector of the target crude oil sample is represented as

[0048]

[0049] wherein a1 is the first physicochemical property value of the target crude oil sample, a2 is the second physicochemical property value of the target crude oil sample, a n is the n-th physicochemical property value of the target crude oil sample.

[0050] Subsequently, in step S2 of the crude oil blending method, the crude oil blending system can obtain a plurality of single crude oil samples, obtain a plurality of physicochemical property values of each single crude oil sample, and perform exhaustive combination of at least two of the plurality of single crude oil samples according to the minimum proportion difference to obtain a plurality of combined crude oil samples.

[0051] Further, the minimum proportion difference can be set to 1%, 0.1%, or 0.01%, etc. The crude oil blending system can exhaustively combine 2, 3, 4, or more single crude oil samples according to the minimum proportion difference described above, to form a plurality of combined crude oil samples.

[0052] Subsequently, in step S3 of the crude oil blending method, the crude oil blending system can calculate a plurality of physicochemical property values of each combined crude oil sample according to the plurality of physicochemical property values of each single crude oil sample, to construct a second feature vector of each combined crude oil sample.

[0053] Specifically, the crude oil blending system can first determine the types and proportions of single crude oil samples contained in the combined crude oil sample, and then perform linear calculation and / or nonlinear calculation on the plurality of physicochemical property values of each single crude oil sample contained in the combined crude oil sample according to the types and proportions, to determine the plurality of physicochemical property values of the combined crude oil sample, and then construct the second feature vector of each combined crude oil sample according to the plurality of physicochemical property values of the combined crude oil sample.

[0054] In this case, the physical and chemical property values of the combined crude oil sample, such as sulfur content, carbon residue, diesel yield, naphtha yield, wax oil yield and / or residue yield, meet the linear condition, and the crude oil blending system can perform linear calculation on the sulfur content, carbon residue, diesel yield, naphtha yield, wax oil yield and / or residue yield of each single crude oil sample to determine the sulfur content, carbon residue, diesel yield, naphtha yield, wax oil yield and / or residue yield of the combined crude oil sample, and the formula is:

[0055] γ mix = n1γ1+ n2γ2… n i γ i

[0056] wherein γ mix is the physical and chemical property value of the combined crude oil sample, n i represents the mass fraction of the i-th single crude oil sample in the combined crude oil sample, γ i represents the physical and chemical property value of the i-th single crude oil sample.

[0057] In addition, the physical and chemical property values of the combined crude oil sample, such as crude oil density, do not meet the linear condition after combination, and therefore the crude oil blending system can perform nonlinear calculation on the physical and chemical property values of each single crude oil sample to determine the crude oil density of the combined crude oil sample:

[0058] ρ mix = (n1+ n2… n i ) / 1 / ρ1+ n2 / ρ2… + n i / ρ i )

[0059] wherein ρ mix represents the crude oil density value of the combined crude oil sample, n i represents the mass fraction of the i-th single crude oil sample in the combined crude oil sample, i represents the crude oil density of the i-th single crude oil sample.

[0060] In this way, the second feature vector of each combined crude oil sample can be represented as

[0061]

[0062] wherein a 1, is the first physical and chemical property value of the combined crude oil sample, a 2, is the second physical and chemical property value of the combined crude oil sample, and a n,mix is the n-th physical and chemical property value of the combined crude oil sample.

[0063] Afterwards, in step S4 of the crude oil blending method, the crude oil blending system can calculate the distance between the first feature vector and each second feature vector respectively to determine the similarity of the physicochemical properties of the target crude oil sample and the combined crude oil sample with various mixing ratios.

[0064] Here, the distance between the first feature vector and each second feature vector can be represented in the form of Euclidean distance, cosine distance, Mahalanobis distance, etc. Specifically, the Euclidean distance between the first feature vector and the second feature vector can be represented as:

[0065]

[0066] wherein a i,mix is the i-th physicochemical property of the combined crude oil sample, a i is the i-th physicochemical property of the target crude oil sample, and EucD is the Euclidean distance value, wherein the smaller the value, the smaller the distance, and the more similar the combined crude oil and the mixed crude oil.

[0067] In addition, the cosine distance between the first feature vector and the second feature vector can be represented as:

[0068]

[0069] wherein cosD is the cosine distance, and the smaller the value, the smaller the distance, and the more similar the combined crude oil and the mixed crude oil.

[0070] In addition, the Mahalanobis distance between the first feature vector and the second feature vector can be represented as:

[0071]

[0072] wherein mahD is the Mahalanobis distance, and the smaller the value, the smaller the distance, and the more similar the combined crude oil and the mixed crude oil, and S is the covariance matrix.

[0073] In particular, the three distances can be combined with normalization / standardization processing to eliminate the order-of-magnitude difference between the numerical values of different physicochemical properties of the crude oil, so as to obtain more accurate calculation results. Specifically, after obtaining the multiple original physicochemical property values of the target crude oil sample and / or the combined crude oil sample, the crude oil blending system can perform normalization processing and / or standardization processing on the multiple original physicochemical property values, thereby determining the multiple physicochemical property values of the target crude oil sample and / or the combined crude oil sample.

[0074] Here, the normalization processing can be calculated by the following formula:

[0075] a' = (a - a min ) / (a max -a min )

[0076] wherein a' is the normalized physicochemical property value, a is the original physicochemical property value, a max is the maximum value of the crude oil physicochemical property value in all samples, a min is the minimum value of the crude oil physicochemical property value in all samples.

[0077] The standardization process can be calculated by the following formula:

[0078] a' = (a - a avg ) / σ

[0079] wherein a' is the standardized physicochemical property value, a is the original physicochemical property value, a avg is the average value of the physicochemical property value of all samples, and σ is the variance of the physicochemical property value of all samples.

[0080] After that, in step S5 of the crude oil blending method, the crude oil blending system can sort the obtained distances from small to large, and determine the types and proportions of single crude oil samples required for blending the target crude oil sample according to the types and proportions of the combined crude oil sample corresponding to the second feature vector with the smallest distance from the first feature vector.

[0081] Further, in some embodiments, the crude oil blending system can further perform an outlier screening test on the similar combined crude oil sample determined in step S5 to exclude abnormal results with significant differences in physicochemical properties from the target crude oil sample. Specifically, the crude oil blending system can first detect the multiple physicochemical property values of the combined crude oil sample corresponding to the second feature vector with the smallest distance from the first feature vector. Then, the crude oil blending system can test the deviation of the multiple physicochemical property values of the combined crude oil sample from the corresponding physicochemical property values of the target crude oil sample one by one according to a preset deviation threshold. In response to the deviation of any one physicochemical property value from the corresponding physicochemical property value of the target crude oil sample exceeding the preset deviation threshold, the crude oil blending system can determine that the combined crude oil sample is an outlier and exclude the combined crude oil sample. In this way, after completing the outlier screening test on all combined crude oil samples similar to the target crude oil sample, the crude oil blending system can determine the types and proportions of single crude oil samples required for blending the target crude oil sample according to the types and proportions of at least one combined crude oil sample that has passed the outlier screening.

[0082] The following is a specific non-limiting preferred embodiment, according to which the crude oil blending method proposed by the present application is further explained.

[0083] Firstly, in the process of blending target crude oil, the crude oil blending system can perform step S1, obtain multiple physicochemical property values of the target crude oil sample through near-infrared crude oil rapid evaluation method, and construct a first feature vector of the target crude oil sample according to the obtained multiple physicochemical property values Here, the physicochemical property values of the crude oil can include sulfur content, residual carbon, naphtha yield, diesel yield, gas oil yield, residual oil yield, and crude oil density.

[0084] After that, the crude oil blending system can perform step S2, prepare 19 single-product crude oil samples, and obtain multiple physicochemical property values of each single-product crude oil sample through near-infrared crude oil rapid evaluation method, and then perform an exhaustive combination on each single-product crude oil sample according to a preset minimum proportion difference of 1%. For example, all proportions of mixing 2, 3, and 4 single-product crude oils are exhausted, and then the single-product crude oils are combined into 2, 3, and 4 crude oil combinations, respectively, so as to obtain multiple combined crude oil samples.

[0085] After that, the crude oil blending system can perform step S3, linearly calculate the sulfur content, residual carbon, naphtha yield, diesel yield, gas oil yield, and residual oil yield of each single-product crude oil sample, and nonlinearly calculate the crude oil density of each single-product crude oil sample, so as to obtain multiple physicochemical property values of each combined crude oil sample, and construct a second feature vector of each combined crude oil sample

[0086] After that, the crude oil blending system can perform step S4, combine the normalization and standardization processing, and use the Euclidean distance, the included angle cosine distance, and the Mahalanobis distance to respectively calculate the distances between the first feature vector and each second feature vector , so as to determine the similarity of the physicochemical properties of the target crude oil sample and the combined crude oil samples with different mixing proportions.

[0087] After that, the crude oil blending system can perform step S5, sort the distances calculated for the above-mentioned 2, 3, and 4 crude oil combinations from small to large. In this way, the type and proportion of the combined crude oil sample corresponding to the second feature vector with the smallest distance are the type and proportion of the single-product crude oil sample required for the closest blended target crude oil sample.

[0088] Finally, in order to improve the reliability of the crude oil blending method, the crude oil blending system can perform outlier detection and screening on the similar combined crude oil samples determined in step S5 according to a preset deviation threshold. Here, the deviation threshold of the crude oil density is ±1%, and the thresholds of the sulfur content, residual carbon, diesel yield, naphtha yield, gas oil yield, and residual oil yield are all ±10%.

[0089] Based on the above steps, the present application provides three groups of experimental data of blending schemes of different crude oil mixing types and proportions for the same target crude oil sample.

[0090] When the Euclidean distance calculation method is used to predict the crude oil proportion of the blending target crude oil, the prediction results are shown in Table 1, wherein the physical and chemical property data of the combined crude oil samples are within the set threshold.

[0091] Table 1: Prediction results of target crude oil sample using Euclidean distance

[0092]

[0093]

[0094] When the cosine distance calculation method is used to predict the crude oil proportion of the blending target crude oil, the prediction results are shown in Table 2, wherein a total of 8 groups of combined crude oil samples with a deviation greater than the set threshold are excluded.

[0095] Table 2: Prediction results of target crude oil sample using cosine distance

[0096]

[0097]

[0098] When the Mahalanobis distance calculation method is used to predict the crude oil proportion of the blending target crude oil, the prediction results are shown in Table 3, wherein a total of 15 groups of combined crude oil samples with a deviation greater than the set threshold are excluded.

[0099] Table 3: Prediction results of mixed crude oil using Mahalanobis distance

[0100]

[0101] As shown in Tables 1, 2 and 3, using the Euclidean distance, cosine distance and Mahalanobis distance to calculate the distance between the first characteristic vector of the target crude oil sample and the second characteristic vector of each combined crude oil sample, a group of combined crude oil samples closest to the target crude oil sample can be obtained, thereby obtaining the comprehensive physical and chemical properties of the target crude oil sample.

[0102] As known by those skilled in the art, the dimension of the characteristic vector directly affects the distance calculation, and the higher the dimension, the higher the calculation accuracy but the longer the time consumption. The distribution, variance and mean value of each dimension of the characteristic vector will have different degrees of influence on the three distance calculation methods. When calculating the crude oil proportion using the present application, the skilled person can select the calculation method according to the characteristics of each dimension of the characteristic vector and the threshold exclusion results, thereby improving the accuracy.

[0103] Compared with the prior art, the crude oil blending method, the crude oil blending system and the computer readable storage medium provided by the present application can realize the estimation of the physical and chemical properties and the proportion of crude oil without expert experience, reduce the difficulty of technical application, and provide a method for rapid detection of the proportion of mixed crude oil. Secondly, by using a plurality of distance calculation methods, the present application can ensure the accuracy of the calculation result. Finally, the present application supports a plurality of test methods, can effectively exclude abnormal values, and thus improves the reliability of the calculation result.

[0104] Although the above methods are illustrated and described as a series of acts for simplicity, it is understood and appreciated that the methods are not limited by the order of acts, as some acts may, in accordance with one or more embodiments, occur in different orders and / or concurrently with other acts from that depicted and described herein.

[0105] Those skilled in the art will understand that information, signals, and data can be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that can be referenced throughout the above description can be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0106] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans can implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

[0107] Those skilled in the art will further appreciate that the computer readable storage medium described above can include without limitation magnetic-based storage devices (e.g., hard disk, floppy disk, magnetic strips), optical-based storage devices (e.g., compact disc (CD), digital versatile disc (DVD)), smart cards, and flash-based memory devices (e.g., electrically erasable programmable read-only memory (EPROM), card, stick, key drive). Additionally, the various storage mediums described herein can represent one or more devices and / or other machine-readable media for storing information. The term "machine-readable medium" can include, without limitation, wireless channels and various other media (and / or storage media) that can store, contain, and / or carry the codes and / or instructions and / or data.

[0108] The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other variations without departing from the spirit or scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for blending crude oil, characterized in that, Includes the following steps: Multiple physicochemical properties of the target crude oil sample are obtained by nuclear magnetic resonance crude oil rapid evaluation or crude oil evaluation standard test methods to construct the first feature vector of the target crude oil sample; Obtain multiple single-product crude oil samples, and exhaustively combine at least two of the multiple single-product crude oil samples according to the minimum ratio difference to obtain multiple combined crude oil samples; Calculate the values ​​of various physicochemical properties of each of the combined crude oil samples to construct the second feature vector of each of the combined crude oil samples; Calculate the distance between the first feature vector and each of the second feature vectors respectively; as well as Based on the types and proportions of combined crude oil samples corresponding to the second feature vector that has the smallest distance from the first feature vector, determine the types and proportions of single crude oil samples required to blend the target crude oil sample.

2. The crude oil blending method as described in claim 1, characterized in that, The step of calculating various physicochemical property values ​​for each of the combined crude oil samples to construct a second feature vector for each of the combined crude oil samples includes: Determine the types and proportions of individual crude oil samples included in the combined crude oil sample; Based on the stated types and proportions, linear and / or nonlinear calculations are performed on the various physicochemical properties of each individual crude oil sample included in the composite crude oil sample to determine the various physicochemical properties of the composite crude oil sample; and Based on the various physicochemical properties of the combined crude oil samples, a second feature vector is constructed for each of the combined crude oil samples.

3. The crude oil blending method as described in claim 2, characterized in that, The physicochemical property values, expressed as mass fractions, are selected from at least one of sulfur content, residual carbon, diesel yield, naphtha yield, wax oil yield, and residue oil yield. The step of performing linear and / or nonlinear calculations on the various physicochemical property values ​​of each individual crude oil sample included in the composite crude oil sample, based on the types and proportions, to determine the various physicochemical property values ​​of the composite crude oil sample includes: Linear calculations were performed on the sulfur content, residual carbon, diesel yield, naphtha yield, wax oil yield, and / or residue oil yield: c mix =n1γ1+n2γ2…..+n i c i Where, γ mix n represents the physicochemical property values ​​of the combined crude oil sample. i γ represents the mass fraction of the i-th single crude oil sample in the combined crude oil sample. i This represents the physicochemical property value of the i-th type of crude oil sample.

4. The crude oil blending method as described in claim 2, characterized in that, The physicochemical properties include crude oil density. The step of performing linear and / or nonlinear calculations on the various physicochemical properties of each individual crude oil sample included in the composite crude oil sample, based on the type and proportion, to determine the various physicochemical properties of the composite crude oil sample includes: The density of the crude oil was calculated nonlinearly: r mix =(n1+n2…..+n i ) / (n1 / ρ1+n2 / ρ2……+n i / r i ) Where, ρ mix n represents the crude oil density value of the combined crude oil sample. i ρ represents the mass fraction of the i-th single crude oil sample in the combined crude oil sample. i This represents the crude oil density of the i-th type of single-product crude oil sample.

5. The crude oil blending method as described in claim 1, characterized in that, The first feature vector is represented as Wherein, a1 is the first physicochemical property value of the target crude oil sample, a2 is the second physicochemical property value of the target crude oil sample, and a n The nth physicochemical property value of the target crude oil sample, and / or The second feature vector is represented as Among them, a 1,mix a is the first physicochemical property value of the combined crude oil sample. 2,mix a is the second physicochemical property value of the combined crude oil sample. n,mix This represents the nth physicochemical property value of the combined crude oil sample.

6. The crude oil blending method as described in claim 1, characterized in that, The step of calculating the distance between the first feature vector and each of the second feature vectors includes: Calculate the first feature vector With the second feature vector Euclidean distance between them: Where EucD is the Euclidean distance value, the smaller the value, the smaller the distance, indicating that the combined crude oil and the blended crude oil are more similar; and / or Calculate the first feature vector With the second feature vector Cosine distance between them: Where cosD is the cosine distance, the smaller the value, the smaller the distance, indicating that the combined crude oil and the mixed crude oil are more similar; and / or Calculate the first feature vector With the second feature vector Mahalanobis distance between them: Where, mahD is the Mahalanobis distance, the smaller the value, the smaller the distance, indicating that the combined crude oil and the mixed crude oil are more similar, and S is the covariance matrix.

7. The crude oil blending method as described in claim 6, characterized in that, Before calculating the distances between the first feature vector and each of the second feature vectors, the crude oil blending method further includes the following steps: Obtain multiple raw physicochemical property values ​​of the target crude oil sample and / or the combined crude oil sample; The multiple original physicochemical property values ​​are normalized and / or standardized to determine the multiple physicochemical property values ​​of the target crude oil sample and / or the combined crude oil sample.

8. The crude oil blending method as described in claim 1, characterized in that, The step of determining the type and proportion of single-origin crude oil samples required for blending the target crude oil sample based on the type and proportion of the combined crude oil sample corresponding to the second feature vector that has the smallest distance from the first feature vector includes: Detect multiple physicochemical properties of the combined crude oil sample corresponding to the second feature vector that has the smallest distance from the first feature vector; In response to any deviation of the physicochemical property value from the corresponding physicochemical property value of the target crude oil sample exceeding a preset deviation threshold, the combined crude oil sample is determined to be an outlier and is removed from the list; and Based on the types and proportions of at least one composite crude oil sample that has been screened for outliers, determine the types and proportions of single crude oil samples required to blend the target crude oil sample.

9. A crude oil blending system, characterized in that, include: Memory, on which computer instructions are stored; as well as A processor, connected to the memory, and configured to execute computer instructions stored on the memory to implement the crude oil blending method as described in any one of claims 1 to 8.

10. A computer-readable storage medium storing computer instructions thereon, characterized in that, When the computer instructions are executed by the processor, the crude oil blending method as described in any one of claims 1 to 8 is implemented.

Images