Method and device for directly predicting property of reforming raw material from crude oil, electronic equipment and storage medium

Abstract

The invention relates to the technical field of near infrared spectrum analysis, in particular to a method and device for directly predicting the property of a reforming raw material from crude oil, electronic equipment and a storage medium, and the method comprises the following steps: collecting a first near infrared spectrum corresponding to the crude oil, and inputting the first near infrared spectrum into a pre-constructed spectrum conversion model; and outputting a second near infrared spectrum corresponding to a reforming raw material fraction cut from the crude oil, inputting the second near infrared spectrum into a pre-constructed reforming raw material property detection model, and outputting property information of the reforming raw material fraction. According to the method, the spectrum of the reforming raw material fraction can be obtained only by collecting the spectrum of the crude oil once through the pre-constructed spectrum conversion model between the crude oil and the reforming raw material fraction subjected to actual boiling point cutting and the reforming raw material property detection model, and then the property of the reforming raw material fraction is obtained through analysis. The raw material property detection process of the reforming device can be advanced before crude oil processing, the reforming raw material fraction property after crude oil processing can be quickly predicted, and a huge optimization and improvement space is provided for operation of the reforming device.

Description

Technical Field

[0001] The invention relates to the technical field of near infrared spectroscopy analysis, and is a method, a device, an electronic device and a storage medium for directly predicting the properties of reforming raw materials from crude oil. Background Art

[0002] The catalytic reforming unit of a refinery usually uses a mixture of straight-run naphtha from a atmospheric distillation unit (CDU) or a secondary processed gasoline from hydrocracking as raw materials. It is very important to understand the properties of these raw materials, which directly affect the production efficiency and product quality of the reforming unit.

[0003] Under the action of the catalyst, these raw materials undergo dehydrogenation cyclization, hydrocracking and isomerization reactions to rearrange the hydrocarbon molecules into new molecular structures, mainly producing C6 to C8 aromatic products or high-octane gasoline. At the same time, the device can use the hydrogen produced as a by-product of reforming to supply the secondary processing of thermal cracking, delayed coking gasoline or diesel hydrotreating refining process units.

[0004] In related technologies, some refining and chemical companies have begun to adopt rapid detection methods based on near-infrared spectroscopy. By scanning the sample spectrum, they can build models (such as partial least squares regression or topology) to calculate the key properties of the sample.

[0005] For example, a Chinese patent document with publication number CN107367481A discloses a method for predicting the general properties of crude oil using near-infrared spectroscopy, the steps of which include: installing a near-infrared detection system on the crude oil pipeline; selecting a crude oil sample set and using the partial least squares method to establish a calibration model for predicting the general properties of crude oil; and using the near-infrared detection system to measure the content data of the general properties of the crude oil to be tested in real time.

[0006] For example, a Chinese patent document with authorization announcement number CN103364364B discloses a method for rapid detection of crude oil properties based on composite prediction technology. This method is aimed at refining and chemical companies. It is based on a near-infrared spectral database and a corresponding crude oil property database. First, topological modeling technology is used to determine whether the prediction of topological modeling technology is credible. If it is credible, topological modeling technology is used to predict the key properties of crude oil. If it is not credible, partial least squares method is used to predict the key properties of crude oil to ensure the prediction accuracy of the key properties of crude oil.

[0007] Although the above-mentioned existing disclosed methods can quickly detect the key properties of atmospheric and vacuum straight-run products or reforming raw materials, they all need to obtain the reforming raw material samples before analyzing their key properties, that is, before the reforming raw materials are obtained, it is impossible to directly predict the properties of the reforming raw materials through crude oil, which affects production optimization. Therefore, it is necessary to study a new technology using near-infrared spectral analysis and spectral transfer, construct a spectral conversion model from crude oil to reforming raw material fractions and a reforming raw material property detection model, so as to directly predict the property information of the reforming raw material fraction from the crude oil spectrum. Summary of the invention

[0008] The present invention provides a method, device, electronic device and storage medium for directly predicting the properties of reforming raw materials from crude oil, which overcomes the shortcomings of the above-mentioned prior art and can effectively solve the problem that the existing detection method requires obtaining the reforming raw material sample first before analyzing its key properties, which affects production optimization.

[0009] One of the technical solutions of the present invention is achieved by the following measures: A method for directly predicting the properties of reforming raw materials from crude oil, comprising: Collecting the first near-infrared spectrum corresponding to the crude oil; Inputting the first near-infrared spectrum into a pre-constructed spectral conversion model, and outputting a second near-infrared spectrum corresponding to the reforming raw material fraction cut from the crude oil, wherein the spectral conversion model is constructed by using the near-infrared spectra of the crude oil sample and the corresponding reforming raw material fraction sample using a partial least squares method; The second near-infrared spectrum is input into a pre-constructed reforming raw material property detection model to output property information of the reforming raw material fraction, wherein the reforming raw material property detection model is constructed using the partial least squares method using the near-infrared spectra and property information of the reforming raw material fraction sample and the actual reforming raw material fraction sample.

[0010] The following is a further optimization and / or improvement of one of the above-mentioned technical solutions: The above-mentioned spectrum conversion model includes a sub-spectrum conversion model corresponding to at least one target wave number point in the target wave number band, and the first near infrared spectrum is input into the pre-constructed spectrum conversion model, and the second near infrared spectrum corresponding to the reforming raw material fraction cut from the crude oil is output, including: extracting first spectrum data related to a target wave number point from the first near infrared spectrum; The first spectral data is input into the sub-spectral conversion model corresponding to the target wavenumber point, and the second spectral data corresponding to the reforming raw material fraction at the target wavenumber point is output. The second spectral data corresponding to the reforming raw material fraction at at least one target wavenumber point constitutes a second near-infrared spectrum.

[0011] The sub-spectrum conversion model adopts a moving window partial least squares conversion based on a preset number of windows, and extracts first spectrum data related to the target wave number point from the first near-infrared spectrum, including: Determine adjacent wave number points centered on the target wave number point, and the number of wave number points of the target wave number point and the adjacent wave number point is consistent with the number of preset windows; First spectrum data corresponding to the target wave number point and the adjacent wave number points are extracted from the first near infrared spectrum.

[0012] After collecting the first near infrared spectrum corresponding to the crude oil, the method further includes: The target wave number band of the first near infrared spectrum is preprocessed, wherein the preprocessing includes at least one of the following: wavelet transformation processing and standard normal transformation processing.

[0013] Before inputting the first near-infrared spectrum into the pre-built spectrum conversion model, the method further includes: Obtaining at least one group of crude oil samples, and collecting a third near infrared spectrum corresponding to each group of crude oil samples; Perform actual boiling point distillation on each group of crude oil samples to cut out corresponding reforming raw material fraction samples within a preset temperature range; collecting a fourth near infrared spectrum corresponding to each group of reforming raw material fraction samples; A spectral conversion model is constructed according to the third near-infrared spectrum and the fourth near-infrared spectrum.

[0014] The spectrum conversion model constructed according to the third near infrared spectrum and the fourth near infrared spectrum includes: determining a target wavenumber band, wherein the target wavenumber band includes at least one target wavenumber point; For each target wavenumber point in the target wavenumber band, extract third spectrum data related to the target wavenumber point from the third near-infrared spectrum, and extract fourth spectrum data corresponding to the target wavenumber point from the fourth near-infrared spectrum; A sub-spectrum conversion model corresponding to the target wavenumber point is constructed according to the third spectrum data and the fourth spectrum data, and at least one sub-spectrum conversion model corresponding to the target wavenumber point constitutes a spectrum conversion model.

[0015] The above-mentioned extracting the third spectrum data related to the target wave number point from the third near-infrared spectrum includes: Determine the adjacent wave number points centered on the target wave number point. The number of wave number points of the target wave number point and the adjacent wave number point is consistent with the number of preset windows. extracting third spectrum data corresponding to the target wave number point and the adjacent wave number point from the third near infrared spectrum; Extracting fourth spectrum data related to the target wave number point from the fourth near infrared spectrum includes: Determine the adjacent wave number points centered on the target wave number point. The number of wave number points of the target wave number point and the adjacent wave number point is consistent with the number of preset windows. Extracting fourth spectrum data corresponding to the target wave number point and the adjacent wave number point from the fourth near infrared spectrum; Constructing a sub-spectrum conversion model corresponding to the target wave number point according to the third spectrum data and the fourth spectrum data, including: According to the third spectrum data and the fourth spectrum data, a sub-spectrum conversion model is constructed by adopting a moving window least squares conversion method with a preset number of windows.

[0016] The above-mentioned determination of the target wave number band includes: Obtaining first property information corresponding to each group of reforming raw material fraction samples; Constructing the weight coefficients of the wave number points corresponding to the reforming raw material fraction samples according to the fourth near infrared spectrum and the first property information of each group of reforming raw material fraction samples; The wavenumber band whose relevant weight coefficient is greater than the preset value is determined as the target wavenumber band.

[0017] Before constructing the spectrum conversion model according to the third near infrared spectrum and the fourth near infrared spectrum, the method further includes: The target wave number bands of the third near infrared spectrum and the fourth near infrared spectrum are preprocessed, and the preprocessing includes at least one of the following: wavelet transformation processing and standard normal transformation processing.

[0018] Before inputting the second near infrared spectrum into the pre-built reforming feedstock property detection model, the method further includes: Obtaining first property information corresponding to each group of reforming raw material fraction samples; Collecting a fifth near infrared spectrum corresponding to at least one group of actual reforming raw material fraction samples, and obtaining second property information corresponding to each group of actual reforming raw material fraction samples; A reforming raw material property detection model is constructed according to the fourth near infrared spectrum, the fifth near infrared spectrum and the corresponding first property information and second property information.

[0019] The reforming raw material property detection model is constructed according to the fourth near infrared spectrum, the fifth near infrared spectrum and the corresponding first property information and second property information, including: According to the fourth near infrared spectrum, the fifth near infrared spectrum and the corresponding first property information and second property information, a reforming raw material property detection model is constructed using the partial least squares method.

[0020] Before constructing the reforming raw material property detection model, the following steps are also included: The target wave number bands of the fourth near infrared spectrum and the fifth near infrared spectrum are preprocessed, and the preprocessing includes at least one of the following: wavelet transformation processing and standard normal transformation processing.

[0021] The second technical solution of the present invention is achieved by the following measures: a device for applying the method of directly predicting the properties of reforming raw materials from crude oil, comprising: A collection module, used for collecting a first near-infrared spectrum corresponding to crude oil; A conversion module, used for inputting the first near infrared spectrum into a pre-built spectrum conversion model, and outputting a second near infrared spectrum corresponding to the reforming raw material fraction cut from the crude oil; The prediction module is used to input the second near infrared spectrum into a pre-built reforming raw material property detection model and output the property information of the reforming raw material fraction.

[0022] The third technical solution of the present invention is achieved by the following measures: an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the steps of the method for directly predicting the properties of reforming raw materials from crude oil when executing the program stored in the memory.

[0023] The fourth technical solution of the present invention is achieved through the following measures: a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method for directly predicting the properties of reforming raw materials from crude oil are implemented.

[0024] The present invention uses a pre-constructed spectrum conversion model between crude oil and the reforming raw material fraction cut by the actual boiling point and a reforming raw material property detection model to achieve the goal of obtaining the reforming raw material fraction spectrum by collecting the crude oil spectrum once, and then analyzing and obtaining the reforming raw material fraction properties. This method moves the raw material property detection process of the reforming device to before crude oil processing, can quickly predict the properties of the reforming raw material fraction after crude oil processing, and provides huge optimization and improvement space for the operation of the reforming device. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Attached Figure 1 A schematic flow chart of a method for directly predicting the properties of reforming feedstock from crude oil provided in an embodiment of the present invention; Attached Figure 2 for Figure 1 A detailed flow chart of step S102 in the illustrated embodiment; Attached Figure 3 A schematic diagram of a process for constructing a spectrum conversion model provided by an embodiment of the present invention; Attached Figure 4 for Figure 3 A detailed flow chart of step S304 in the illustrated embodiment; Attached Figure 5 A schematic flow chart of a method for constructing a reforming raw material property detection model provided by an embodiment of the present invention; FIG6 is a schematic flow chart of another method for directly predicting the properties of reforming feedstock from crude oil provided by an embodiment of the present invention, wherein FIG6 is a schematic flow chart of another method for directly predicting the properties of reforming feedstock from crude oil provided by an embodiment of the present invention, Figure 6-1 The schematic diagram of the method flow in the model building phase is shown in Figure 2. Figure 6-2 It is a schematic diagram of the method flow in the model application phase; Attached Figure 7 A near infrared spectrum of 20 groups of crude oil samples provided in an embodiment of the present invention ; Attached Figure 8 A near infrared spectrum of a reforming raw material fraction sample cut from 20 groups of crude oil samples provided in an embodiment of the present invention ; Attached Fig. 9 A spectrum of 20 groups of crude oil samples after near infrared spectra preprocessing provided in an embodiment of the present invention ; Attached Fig.10 A near infrared spectrum of a reforming raw material fraction sample cut from 20 groups of crude oil samples provided in an embodiment of the present invention after preprocessing ; Attached Fig.11 A schematic diagram of the structure of a device for directly predicting the properties of reforming raw materials from crude oil provided by an embodiment of the present invention; Attached Fig.12 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments 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.

[0027] Figure 1 A flow chart of a method for directly predicting the properties of reforming feedstock from crude oil provided by an embodiment of the present invention is as follows: Figure 1 As shown, the method includes: Step S101: collecting a first near-infrared spectrum corresponding to crude oil.

[0028] Specifically, a near infrared (NIR) spectrometer can be used to scan the crude oil to obtain the absorption characteristics of the crude oil within the near infrared spectrum, that is, the first near infrared spectrum. In addition, when sampling the crude oil, an automatic crude oil pretreatment system can be used to filter, maintain constant temperature and pressure, and set the sampling conditions as shown in Table 1.

[0029] Table 1 .

[0030] Step S102: input the first near infrared spectrum into a pre-built spectrum conversion model, and output a second near infrared spectrum corresponding to the reforming raw material fraction cut from the crude oil.

[0031] Specifically, the pre-constructed spectral conversion model (or spectral transfer model) can convert the near-infrared spectrum of crude oil into the near-infrared spectrum corresponding to the reforming raw material fraction cut from the crude oil. In this step, by inputting the first near-infrared spectrum of crude oil into the spectral conversion model, the spectral information of crude oil is converted into the second near-infrared spectrum corresponding to the reforming raw material fraction.

[0032] Step S103: input the second near infrared spectrum into a pre-constructed reforming feedstock property detection model, and output property information of the reforming feedstock fraction.

[0033] Specifically, the pre-constructed reforming material property detection model can predict the property information of the reforming material fraction, such as density, distillation range, etc., based on the input near infrared spectrum. In this step, the second near infrared spectrum corresponding to the reforming material fraction obtained in step S102 is input into the reforming material property detection model to predict the property information of the reforming material fraction.

[0034] In some embodiments, the spectrum conversion model includes a sub-spectrum conversion model corresponding to at least one target wavenumber point in the target wavenumber band. Figure 2 for Figure 1 A detailed flow chart of step S102 in the embodiment shown is as follows: Figure 2 As shown, step S102 includes: Step S1021: extracting first spectrum data related to a target wave number point from a first near-infrared spectrum.

[0035] Step S1022, input the first spectrum data into the sub-spectrum conversion model corresponding to the target wavenumber point, output the second spectrum data corresponding to the reforming raw material fraction at the target wavenumber point, and the second spectrum data corresponding to the reforming raw material fraction at at least one target wavenumber point constitutes a second near-infrared spectrum.

[0036] Specifically, the target wavenumber band can be understood as a characteristic spectral band that has a greater impact on the key properties of the reforming feed fraction, such as 4000cm-1 Up to 4800cm -1 、5600cm -1 Up to 6200cm -1 Characteristic spectrum, each characteristic spectrum includes multiple target wave number points, such as 5830cm -1 、5832cm -1 、5834cm -1 etc.; the sub-spectrum conversion model can be understood as a spectrum conversion model corresponding to a wave number point, such as 5832cm -1 Corresponding sub-spectrum conversion model; the first spectrum data and the second spectrum data can be understood as relevant parameters in the near-infrared spectrum, such as absorbance, etc.

[0037] In this embodiment, first, absorbance data related to the target wavenumber point is extracted from the first near-infrared spectrum of the crude oil, wherein the absorbance data related to the target wavenumber point can be understood as the absorbance corresponding to the target wavenumber point and the target wavenumber point related to the target wavenumber point (usually the adjacent wavenumber point); then the absorbance related to the target wavenumber point is input into the sub-spectrum conversion model to obtain the absorbance of the reforming raw material fraction at the target wavenumber point, and so on, to obtain the absorbance of the reforming raw material fraction at multiple target wavenumber points, forming the second near-infrared spectrum of the reforming raw material fraction.

[0038] In some embodiments, the sub-spectrum conversion model adopts a moving window partial least squares conversion based on a preset window number, and step S1021 includes: determining adjacent wavenumber points centered on the target wavenumber point, and the number of wavenumber points of the target wavenumber point and the adjacent wavenumber point is consistent with the preset window number; extracting the first spectral data corresponding to the target wavenumber point and the adjacent wavenumber point from the first near-infrared spectrum.

[0039] Specifically, a sub-spectrum conversion model is constructed based on a moving window partial least squares conversion with a preset number of windows. -1 The sub-spectrum conversion model corresponding to the wave number point is explained as an example. First, take 5832cm -1 The wave number point is the center, and its adjacent wave number point is determined to be 5826cm -1 、5828cm -1 、5830cm -1 、5834cm -1 、5836cm -1 、5838cm -1 , there are 7 target wavenumber points and adjacent wavenumber points, which is consistent with the preset window number k=7; the absorbance corresponding to these 7 wavenumber points is extracted from the first near-infrared spectrum of crude oil and input into 5832cm -1 In the sub-spectrum conversion model corresponding to the wave number point, the output reforming raw material fraction is at 5832cm -1The absorbance at the wavenumber point can be deduced by analogy to output the absorbance corresponding to the reforming raw material fraction in the target wavenumber band, forming the second near-infrared spectrum of the reforming raw material fraction.

[0040] In some embodiments, after step S101, the method further includes: preprocessing the target wavenumber band of the first near-infrared spectrum, wherein the preprocessing includes at least one of the following: wavelet transform processing and standard normal transform processing.

[0041] Specifically, the first near-infrared spectrum of crude oil is preprocessed. In order to improve efficiency, the target wave number band of the first near-infrared spectrum is preprocessed. First, wavelet transform (WT) processing is performed to eliminate spectral noise, where the general form of the wavelet function is shown in formula (1): in, s Represents the scale, which is used to control the expansion and contraction of the wavelet function and corresponds to the frequency (inversely proportional); Represents the translation, which is used to control the translation of the wavelet function, corresponding to time, Represents the result of wavelet transform, which is about s and Function of Represents the original signal to be analyzed, which is a function of time t; Represents the scaled and shifted wavelet basis function; Represents the convolution operation; It represents the integration operation of time t from negative to positive infinity.

[0042] Then, based on the wavelet transform, the standard normal transform (SNV) processing is performed to remove the spectral signal variation, as shown in formula (2): in, Indicates j The near infrared spectrum of the target wave number point, , m is the number of target wavenumber points corresponding to the target wavenumber segment, represents the first j Near infrared spectrum of target wavenumber points.

[0043] Finally, the preprocessed first near-infrared spectrum is input into the spectrum conversion model to obtain the second near-infrared spectrum corresponding to the reforming raw material fraction; the second near-infrared spectrum is input into the reforming raw material property detection model to predict the properties of the reforming raw material fraction.

[0044] The method for directly predicting the properties of reforming raw materials from crude oil provided in an embodiment of the present invention is implemented by collecting a first near-infrared spectrum corresponding to the crude oil; inputting the first near-infrared spectrum into a pre-constructed spectral conversion model, and outputting a second near-infrared spectrum corresponding to the reforming raw material fraction cut from the crude oil; inputting the second near-infrared spectrum into a pre-constructed reforming raw material property detection model, and outputting property information of the reforming raw material fraction; that is, through the pre-constructed spectral conversion model between the crude oil and the reforming raw material fraction cut by the actual boiling point and the reforming raw material property detection model, it is achieved that the spectrum of the reforming raw material fraction can be obtained by collecting the crude oil spectrum only once, and then the key properties of the reforming raw material fraction can be predicted. This method advances the raw material property detection process of the reforming device to before the crude oil processing, and can quickly predict the properties of the reforming raw material fraction after the crude oil is processed after it is stored in the factory, providing huge optimization and improvement space for the operation of the reforming device.

[0045] Based on the above embodiments, Figure 3 A schematic diagram of a process for constructing a spectrum conversion model provided by an embodiment of the present invention is shown in FIG. Figure 3 As shown, the method includes: Step S301: Obtain at least one group of crude oil samples, and collect a third near-infrared spectrum corresponding to each group of crude oil samples.

[0046] Step S302: Perform actual boiling point distillation on each group of crude oil samples to cut out corresponding reforming raw material fraction samples within a preset temperature range.

[0047] Step S303, collecting the fourth near infrared spectrum corresponding to each group of reforming raw material fraction samples.

[0048] Step S304: construct a spectrum conversion model according to the third near infrared spectrum and the fourth near infrared spectrum.

[0049] Specifically, before executing step S102, it is necessary to pre-construct a spectral conversion model by executing steps S301-S304. In this embodiment, firstly, multiple groups of crude oil samples are obtained, and the near-infrared spectrum of each group of crude oil samples is collected, wherein the crude oil samples can be typical processed crude oil of a refining enterprise, including incoming component crude oil, incoming tank mixed crude oil, incoming device mixed crude oil, etc., which basically covers the quality changes in the current crude oil storage, transfer, and processing process of the enterprise. When collecting the near-infrared spectrum of the crude oil sample, the crude oil automatic pretreatment system can be used to filter, constant temperature, and constant pressure the crude oil sample, and the spectrum is collected based on the spectrum collection conditions shown in Table 1; then, the real boiling point distillation instrument in the enterprise laboratory can be used to perform real boiling point atmospheric distillation on each group of crude oil samples, and according to the standard heating method, each group of crude oil samples distills out a reforming raw material fraction of 15~140°C under the same operating conditions; then, based on the same spectrum collection conditions as Table 1, the near-infrared spectrum of the reforming raw material fraction cut by the enterprise laboratory is collected; finally, according to the near-infrared spectrum of the crude oil and the near-infrared spectrum of the reforming raw material fraction, the spectral conversion model is constructed.

[0050] Figure 4 for Figure 3 A detailed flow chart of step S304 in the embodiment shown is as follows: Figure 4 As shown, step S304 includes: Step S3041: determine a target wavenumber segment, where the target wavenumber segment includes at least one target wavenumber point.

[0051] Step S3042: for each target wavenumber point in the target wavenumber segment, extract third spectrum data related to the target wavenumber point from the third near-infrared spectrum, and extract fourth spectrum data corresponding to the target wavenumber point from the fourth near-infrared spectrum.

[0052] Step S3043: construct a sub-spectrum conversion model corresponding to the target wavenumber point according to the third spectrum data and the fourth spectrum data, and at least one sub-spectrum conversion model corresponding to the target wavenumber point constitutes a spectrum conversion model.

[0053] Specifically, first determine the target wavenumber band that has a greater impact on the key properties of the reforming feedstock fraction, such as 4000cm -1 Up to 4800cm -1 、5600cm -1 Up to 6200cm -1characteristic spectrum segment; then construct a sub-spectrum conversion model corresponding to each target wavenumber point in the target wavenumber segment, the process is as follows: extract the third spectrum data related to the target wavenumber point from the third near-infrared spectrum corresponding to each group of crude oil samples, extract the fourth spectrum data corresponding to the target wavenumber point from the fourth near-infrared spectrum corresponding to each group of reforming raw material fraction samples; construct a sub-spectrum conversion model at the target wavenumber point according to each third spectrum data and each fourth spectrum data; and so on, the sub-spectrum conversion models of multiple target wavenumber points constitute a spectrum conversion model.

[0054] In some embodiments, step S3042 extracts third spectral data related to the target wavenumber point from the third near-infrared spectrum, including: determining adjacent wavenumber points centered on the target wavenumber point, and the number of wavenumber points of the target wavenumber point and the adjacent wavenumber points is consistent with a preset window number; extracting third spectral data corresponding to the target wavenumber point and the adjacent wavenumber points from the third near-infrared spectrum; then step S3043 includes: constructing a sub-spectrum conversion model based on the third spectral data and the fourth spectral data, using a moving window least squares conversion method with a preset window number.

[0055] Specifically, the moving window partial least squares method is used to optimize the calculation of the spectrum conversion model from crude oil to reforming raw material fractions, and the window number is preset. , the spectrum conversion model established The corresponding coefficient matrix , as shown in formula (3): in, Each column in represents the j The coefficient matrix of the sub-spectrum conversion model corresponding to the target wave number points is ,in, j =1,2,…… m， For example, substituting j=1 into ,get , the positive corresponding coefficient matrix The coefficients of the first column.

[0056] In the preset window number k = 7, the spectrum of crude oil is converted to the spectrum corresponding to the reforming raw material fraction, as shown in formula (4), which means that according to the i The crude oil samples were j -3 wave points, j -2 wave number points, j -1 wave number point, j Wave number point, j +1 wave number point, j +2 wave points, j The absorbance at the +3 wave number point isj The product sum of the coefficient matrices of the sub-spectrum conversion models corresponding to the target wave number points is obtained. i The reforming feedstock fraction sample cut from the crude oil sample is j The absorbance at each wave number point When constructing the spectral conversion model, the objective function used is shown in formula (5). When the objective function converges to a minimum value, it indicates that the spectral conversion model is completed.

[0057] in, n Indicates the number of crude oil samples, m Indicates the number of target wavenumber points in the target wavenumber band of crude oil and reforming feed fractions, Indicates i The reforming feedstock fraction samples were j The absorbance of the target wave number point, Indicates i The reforming raw material fraction sample predicted by the spectral conversion model for the crude oil sample is j The absorbance of the target wave number point; Indicates that the i-th crude oil sample is in to The absorbance at the wave number point, for example, k=7 means the absorbance of the i-th crude oil sample at the j-3-th wave number point to the j+3-th wave number point; Represents the coefficients of the sub-spectrum conversion model corresponding to the j-th target wave number point, corresponding to the coefficient matrix The jth column in ; Indicates seeking n Crude oil samples m The objective function is to find the overall minimum value of the square of the absorbance difference before and after the spectrum conversion of the target wave number points.

[0058] In some embodiments, before step S304, the method further includes: preprocessing the target wavenumber bands of the third near-infrared spectrum and the fourth near-infrared spectrum, wherein the preprocessing includes at least one of the following: wavelet transformation processing and standard normal transformation processing.

[0059] Specifically, the third near infrared spectrum of each group of crude oil samples is subjected to wavelet transform (WT) and standard normal transform (SNV) to obtain the third near infrared spectrum after preprocessing as shown in formula (6); the fourth near infrared spectrum of each group of reforming raw material fraction samples is subjected to wavelet transform and standard normal transform to obtain the fourth near infrared spectrum after preprocessing as shown in formula (7); the constructed spectral conversion model is shown in formula (8), indicating that the third near infrared spectrum after preprocessing is input into the spectral conversion model to predict the near infrared spectrum of each group of reforming raw material fraction samples; when the spectral conversion model is constructed using the third near infrared spectrum and the fourth near infrared spectrum after preprocessing, the objective function adopted can be further changed from formula (5) to formula (9): in, The crude oil sample The number of target wave number points after preprocessing The absorbance matrix, Respectively represent the first crude oil sample to The absorbance of the wave number point after pretreatment. For example, when k=7, it means the absorbance of the wave number points j-3 to j+3 of the first crude oil sample after pretreatment. Similarly, Respectively represent the nth crude oil sample to The absorbance of the wave number point after pretreatment. For example, when k=7, it means the absorbance of the wave number points j-3 to j+3 of the nth crude oil sample after pretreatment; Indicates the first fraction of the reforming raw material cut from the crude oil The absorbance of the target wave number point after preprocessing, Respectively represent the first to nth reforming feedstock fractions cut from the crude oil samples The absorbance of the target wave number point after preprocessing, is the absorbance matrix of the jth target wave number point of the reforming feed fraction predicted based on the spectral conversion model, where represents the coefficient matrix of the spectral conversion model, represents a constant matrix; Indicates obtaining a single crude oil sample m The objective function is to minimize the square of the absorbance difference before and after the spectrum conversion of the target wave number points.

[0060] In some embodiments, step S3041 includes: obtaining first property information corresponding to each group of reforming raw material fraction samples; constructing relevant weight coefficients of each wavenumber point corresponding to the reforming raw material fraction samples based on the fourth near-infrared spectrum and the first property information of each group of reforming raw material fraction samples; and determining the wavenumber segment whose relevant weight coefficient is greater than a preset value as the target wavenumber segment.

[0061] Specifically, the key properties of each group of reforming raw material fraction samples can be first analyzed by standard methods, and then based on the properties and near-infrared spectra of these multiple groups of reforming raw material fraction samples, a weight coefficient curve related to each wave number point is established, as shown in formula (10): in, j Indicates j wave number points, p represents the pth property, for and The covariance of for The variance of for The variance of .

[0062] The final statistical correlation coefficient The wave number band is the target wave number band, such as 4000cm -1 Up to 4800cm -1 、5600cm -1 Up to 6200cm -1 is the target wave number band.

[0063] On the basis of the foregoing embodiments, at least one group of crude oil samples is obtained, and the third near-infrared spectrum corresponding to each group of crude oil samples is collected; each group of crude oil samples is subjected to actual boiling point distillation treatment, and the corresponding reforming raw material fraction samples within a preset temperature range are cut out; the fourth near-infrared spectrum corresponding to each group of reforming raw material fraction samples is collected; a spectral conversion model is constructed based on the third near-infrared spectrum and the fourth near-infrared spectrum, thereby realizing the construction of a spectral conversion model from the crude oil spectrum to the reforming raw material fraction spectrum, which provides a basis for the subsequent direct prediction of the properties of the reforming raw material fraction from the crude oil.

[0064] Based on the above embodiments, Figure 5 A schematic diagram of a method for constructing a reforming raw material property detection model provided by an embodiment of the present invention is shown in FIG. Figure 5 As shown, the method includes: Step S501, obtaining first property information corresponding to each group of reforming feedstock fraction samples.

[0065] Step S502: Collect a fifth near-infrared spectrum corresponding to at least one group of actual reforming feedstock fraction samples, and obtain second property information corresponding to each group of actual reforming feedstock fraction samples.

[0066] Step S503: construct a reforming raw material property detection model according to the fourth near infrared spectrum, the fifth near infrared spectrum and the corresponding first property information and second property information.

[0067] Specifically, before executing step S103, it is necessary to pre-construct a reforming raw material property detection model by executing steps S501-S503. First, the first property information of the reforming raw material fraction sample cut out by the actual boiling point of each group of crude oil samples, such as density, distillation range, etc., can be obtained based on the standard analysis method; then the fifth near-infrared spectra of multiple groups of actual reforming raw material fractions in the reforming device are collected, and the spectrum collection conditions are shown in Table 1, and the second property information of each group of actual reforming raw material fractions is obtained based on the standard analysis method; finally, the reforming raw material property detection model is established based on the first property information + second property information associated with the fourth near-infrared spectrum + the fifth near-infrared spectrum.

[0068] In some embodiments, step S503 includes: constructing a reforming raw material property detection model using partial least squares method according to the fourth near infrared spectrum, the fifth near infrared spectrum and the corresponding first property information and second property information.

[0069] In some embodiments, before step S503, the method further includes: preprocessing the target wavenumber bands of the fourth near-infrared spectrum and the fifth near-infrared spectrum, and the preprocessing includes at least one of the following: wavelet transformation processing and standard normal transformation processing.

[0070] Specifically, after obtaining the fourth near-infrared spectrum and the first property information corresponding to the reforming raw material fraction sample cut out by the actual boiling point of crude oil, as well as the fifth near-infrared spectrum and the second property information corresponding to the actual reforming raw material fraction sample, the fourth near-infrared spectrum and the fifth near-infrared spectrum are subjected to the same preprocessing, namely, wavelet transform and standard normal transform processing; using the preprocessed fourth near-infrared spectrum and the fifth near-infrared spectrum and the corresponding first property information and the second property information, the partial least squares method is used to construct a reforming raw material property detection model.

[0071] On the basis of the foregoing embodiments, by obtaining the first property information corresponding to each group of reforming raw material fraction samples; collecting the fifth near-infrared spectrum corresponding to at least one group of actual reforming raw material fraction samples, and obtaining the second property information corresponding to each group of actual reforming raw material fraction samples; constructing a reforming raw material property detection model according to the fourth near-infrared spectrum, the fifth near-infrared spectrum and the corresponding first property information and the second property information; the pre-construction of the reforming raw material property detection model is achieved, which provides a basis for the subsequent direct prediction of the reforming raw material fraction properties from crude oil.

[0072] To further understand the embodiment of the present invention, FIG. 6 is a flow chart of another method for directly predicting the properties of reforming feedstock from crude oil provided by the embodiment of the present invention. Figure 6-1 and Figure 6-2 As shown, the method includes: Step S601: Obtain at least one group of crude oil samples, and collect a third near-infrared spectrum corresponding to each group of crude oil samples.

[0073] Specifically, 20 groups of typical processed crude oils of refineries were collected, including incoming component crude oils, incoming tank mixed crude oils, incoming device mixed crude oils, etc. The crude oil samples basically cover the quality changes of crude oil storage, transfer, and processing in refineries; and crude oil samples were filtered, treated with constant temperature and constant pressure using automatic crude oil sample pretreatment, and spectra were collected under the spectral conditions shown in Table 1. Figure 7 A near infrared spectrum of 20 groups of crude oil samples provided in an embodiment of the present invention .

[0074] Step S602: Perform actual boiling point distillation on each group of crude oil samples to cut out corresponding reforming raw material fraction samples within a preset temperature range.

[0075] Specifically, the laboratory actual boiling point distiller of the refinery can be used to perform actual boiling point atmospheric pressure distillation on 20 groups of crude oil samples. According to the standard heating method, each group of crude oil samples can be distilled into a fraction of 15°C to 140°C under the same operating conditions.

[0076] Step S603: collecting the fourth near infrared spectrum corresponding to each group of reforming raw material fraction samples, and obtaining the first property information corresponding to each group of reforming raw material fraction samples.

[0077] Specifically, based on the same spectrum collection conditions as step S601, the near infrared spectrum of the reforming raw material fraction of 15°C to 140°C cut out from the crude oil laboratory is collected, such as Figure 8 A near infrared spectrum of a reforming raw material fraction sample cut from 20 groups of crude oil samples provided in an embodiment of the present invention ; Standard methods (as shown in Table 2) were used to analyze the key properties of the reforming feed fractions For example, the density of the reforming feed fraction is obtained by using the standard method of GB / T 29617; the normal alkanes, isoalkanes, cycloalkanes and aromatics of the reforming feed fraction are obtained by using the standard method of Q / SY DS 04.018; and the distillation temperatures of the reforming feed fraction are obtained by using the standard method of GB / T 6536.

[0078] Table 2 .

[0079] Step S604: constructing the weight coefficients of the wave number points corresponding to the reforming raw material fraction samples according to the fourth near infrared spectra and the first property information of each group of reforming raw material fraction samples.

[0080] Specifically, based on the near infrared spectra of 20 groups of reforming raw material fraction samples Key properties of reforming feed fractions , establish the relevant weight coefficient curve of each wave number point, as shown in formula (10).

[0081] Step S605: Determine a wavenumber segment whose correlation weight coefficient is greater than a preset value as a target wavenumber segment, where the target wavenumber segment includes at least one target wavenumber point.

[0082] Specifically, the statistical correlation coefficient The target wave number band was finally determined to be 4000cm -1 Up to 4800cm -1 、5600cm -1 Up to 6200cm -1 The target wave number band includes multiple target wave number points, such as 5830cm -1 、5832cm -1 、5834cm -1 wait.

[0083] Step S606: preprocessing the target wavenumber bands of the third near-infrared spectrum and the fourth near-infrared spectrum, wherein the preprocessing includes at least one of the following: wavelet transformation processing and standard normal transformation processing.

[0084] Specifically, the target wavenumber band of the third near-infrared spectra of 20 groups of crude oil samples was subjected to wavelet transform (WT) and standard normal transform (SNV), as follows: Fig. 9 A spectrum of 20 groups of crude oil samples after near infrared spectra preprocessing provided in an embodiment of the present invention ; The fourth near-infrared spectra of 20 groups of crude oil laboratory cut reforming raw material fractions were successively subjected to wavelet transform (WT) and standard normal transform (SNV), such as Fig.10 A near infrared spectrum of a reforming raw material fraction sample cut from 20 groups of crude oil samples provided in an embodiment of the present invention after preprocessing .

[0085] Step S607: for each target wavenumber point in the target wavenumber segment, adjacent wavenumber points centered on the target wavenumber point are determined, the number of wavenumber points of the target wavenumber point and the adjacent wavenumber points is consistent with the number of preset windows, and third spectrum data corresponding to the target wavenumber point and the adjacent wavenumber points are extracted from the third near-infrared spectrum.

[0086] Step S608: extract fourth spectrum data corresponding to the target wave number point from the fourth near-infrared spectrum.

[0087] Step S609: construct a sub-spectrum conversion model based on the third spectral data and the fourth spectral data by adopting a moving window least squares conversion method with a preset number of windows, and the sub-spectrum conversion model corresponding to at least one target wave number point constitutes a spectrum conversion model.

[0088] Specifically, based on the spectrum of the pretreated crude oil and its reforming raw material fraction spectrum, a moving window partial least squares transformation model with a preset window number of 7 was established. , to establish 5832cm -1 The sub-spectrum conversion model is taken as an example to illustrate.

[0089] At 5832cm -1 The absorbance matrix of crude oil after preprocessing with the preset window number of 7 As shown in Table 3, Crude01-Crude20 represent the 1st group of crude oil samples to the 20th group of crude oil samples, respectively, and each group of crude oil samples includes 7 target wavenumber points, namely 5826, 5828, 5830, 5832, 5834, 5836, and 5838.

[0090] Table 3 .

[0091] The reforming raw material fraction cut from each crude oil laboratory was pretreated at 5832 cm -1 Absorbance matrix corresponding to wave number points As shown in Table 4: Table 4 .

[0092] According to Tables 1 and 2, at 5832 cm -1 The sub-spectrum conversion model is established by using the moving window least squares conversion method with a preset number of windows: .

[0093] By analogy, a sub-spectrum conversion model corresponding to each wavenumber point in the target wavenumber band is established to form a spectrum conversion model.

[0094] Step S610: Collect a fifth near-infrared spectrum corresponding to at least one group of actual reforming raw material fraction samples, and obtain second property information corresponding to each group of actual reforming raw material fraction samples.

[0095] Specifically, 50 sets of fifth near-infrared spectra corresponding to the top naphtha of the atmospheric and vacuum unit were collected. , and the key properties were tested using standard methods as shown in Table 2 .

[0096] Step S611, preprocessing the target wave number band of the fifth near infrared spectrum, wherein the preprocessing includes at least one of the following: wavelet transformation processing and standard normal transformation processing.

[0097] Specifically, the fifth near infrared spectra of 50 groups of initial top naphtha were subjected to the same pretreatment as the fourth near infrared spectra of 20 groups of reforming feedstock fraction samples to obtain .

[0098] Step S612: construct a reforming raw material property detection model using partial least squares method according to the fourth near infrared spectrum, the fifth near infrared spectrum and the corresponding first property information and second property information.

[0099] Specifically, using the preprocessed , the set of associated properties , using partial least squares (PLS) method to establish a reforming raw material property detection model .

[0100] Step S613: collecting a first near-infrared spectrum corresponding to the crude oil.

[0101] Step S614, preprocessing the target wave number band of the first near infrared spectrum, wherein the preprocessing includes at least one of the following: wavelet transformation processing and standard normal transformation processing.

[0102] Step S615: input the first near infrared spectrum into a pre-built spectrum conversion model, and output a second near infrared spectrum corresponding to the reforming raw material fraction cut from the crude oil.

[0103] Step S616: input the second near infrared spectrum into a pre-constructed reforming feedstock property detection model, and output property information of the reforming feedstock fraction.

[0104] Specifically, after the spectral conversion model and the reforming raw material property detection model are constructed, the first near-infrared spectrum of the crude oil whose reforming raw material fraction properties are to be predicted can be collected, and the first near-infrared spectrum can be input into the spectral conversion model, and the second near-infrared spectrum corresponding to the reforming raw material fraction can be output, and then the second near-infrared spectrum can be input into the reforming raw material property detection model. In the experiment, the properties of the reforming feed fraction were obtained.

[0105] In summary, the present embodiment can be divided into a model building stage (corresponding to steps S601 to S612) and a model application stage (corresponding to steps S613 to S616); by establishing a spectral conversion model between crude oil and a fixed fraction segment (15°C to 140°C) cut by its actual boiling point, determining the target wavenumber segment by the weight coefficients related to each wavenumber point, using wavelet transform and standard normal transform to pre-process the spectrum, eliminating spectral noise and spectral variation in the spectrum signal, establishing a mixed raw material property detection model for the actual boiling point cut reforming raw material fraction and the distillation unit straight run reforming raw material fraction product, and performing key property prediction and analysis on the reforming raw material fraction spectrum after crude oil conversion; the present embodiment solves the problem of long time consumption for actual boiling point distillation of crude oil in traditional crude oil evaluation, and can quickly and accurately obtain the key properties of the reforming raw material fraction obtained by actual boiling point cutting of crude oil, helping enterprises to quickly obtain the physical property data of the reforming raw material fraction of crude oil processing products, and timely guiding enterprises to formulate processing plans and operate distillation units.

[0106] Optionally, after building the model, you can also evaluate the model. The evaluation process is as follows: Four groups of detailed evaluation crude oils were selected as test samples, and near-infrared spectra of the test samples were collected. After spectral preprocessing, the crude oil spectra were converted to reforming raw material fraction spectra through the constructed spectral conversion model. The reforming raw material property detection model was then used to detect the converted reforming raw material fraction spectra to obtain the reforming raw material fraction properties of crude oil cutting, as shown in Table 5: Table 5 .

[0107] By comparing the predicted values ​​and actual values ​​of the key properties in Table 5, it can be seen that the predicted value error is small. In other words, in this embodiment, only one spectrum acquisition of the crude oil sample is required to accurately predict the properties of the crude oil cutting and reforming raw material fraction. Through the spectrum conversion model, the crude oil spectrum is converted into the spectrum of the reforming raw material fraction, thereby obtaining the component properties of the light fraction in the crude oil. This analysis accuracy is sufficient to meet the requirements of production and processing.

[0108] Fig.11 A schematic diagram of a device for directly predicting the properties of reforming raw materials from crude oil provided by an embodiment of the present invention is shown in FIG. Fig.11 As shown, the device comprises: The acquisition module 1101 is used to acquire the first near-infrared spectrum corresponding to the crude oil; the conversion module 1102 is used to input the first near-infrared spectrum into a pre-constructed spectrum conversion model, and output the second near-infrared spectrum corresponding to the reforming raw material fraction cut from the crude oil; the prediction module 1103 is used to input the second near-infrared spectrum into a pre-constructed reforming raw material property detection model, and output the property information of the reforming raw material fraction.

[0109] In some embodiments, the spectral conversion model includes a sub-spectral conversion model corresponding to at least one target wavenumber point in the target wavenumber segment, and the conversion module 1102 is specifically used to: extract first spectral data related to the target wavenumber point from the first near-infrared spectrum; input the first spectral data into the sub-spectral conversion model corresponding to the target wavenumber point, and output second spectral data corresponding to the target wavenumber point of the reforming raw material fraction, and the second spectral data corresponding to the reforming raw material fraction at at least one target wavenumber point constitutes a second near-infrared spectrum.

[0110] In some embodiments, the sub-spectrum conversion model adopts a moving window partial least squares conversion based on a preset window number, and the conversion module 1102 is specifically used to: determine adjacent wavenumber points centered on the target wavenumber point, and the number of wavenumber points of the target wavenumber point and the adjacent wavenumber point is consistent with the preset window number; extract the first spectrum data corresponding to the target wavenumber point and the adjacent wavenumber point from the first near-infrared spectrum.

[0111] In some embodiments, the device further includes a preprocessing module 1104, which is used to preprocess the target wavenumber band of the first near-infrared spectrum, and the preprocessing includes at least one of the following: wavelet transformation processing and standard normal transformation processing.

[0112] In some embodiments, the device also includes a construction module 1105, which is used to: obtain at least one group of crude oil samples and collect a third near-infrared spectrum corresponding to each group of crude oil samples; perform real boiling point distillation on each group of crude oil samples to cut out corresponding reforming raw material fraction samples within a preset temperature range; collect a fourth near-infrared spectrum corresponding to each group of reforming raw material fraction samples; and construct a spectral conversion model based on the third near-infrared spectrum and the fourth near-infrared spectrum.

[0113] In some embodiments, construction module 1105 is specifically used to: determine a target wavenumber band, the target wavenumber band includes at least one target wavenumber point; for each target wavenumber point in the target wavenumber band, extract third spectral data related to the target wavenumber point from the third near-infrared spectrum, and extract fourth spectral data corresponding to the target wavenumber point from the fourth near-infrared spectrum; construct a sub-spectrum conversion model corresponding to the target wavenumber point based on the third spectral data and the fourth spectral data, and at least one sub-spectrum conversion model corresponding to the target wavenumber point constitutes a spectral conversion model.

[0114] In some embodiments, construction module 1105 is specifically used to: determine adjacent wavenumber points centered on a target wavenumber point, wherein the number of wavenumber points of the target wavenumber point and the adjacent wavenumber point is consistent with a preset window number; extract third spectral data corresponding to the target wavenumber point and the adjacent wavenumber point from the third near-infrared spectrum; and construct a sub-spectrum conversion model based on the third spectral data and the fourth spectral data using a moving window least squares conversion method with a preset window number.

[0115] In some embodiments, the construction module 1105 is specifically used to: obtain the first property information corresponding to each group of reforming raw material fraction samples; construct the relevant weight coefficients of each wavenumber point corresponding to the reforming raw material fraction samples according to the fourth near-infrared spectrum and the first property information of each group of reforming raw material fraction samples; and determine the wavenumber segment whose relevant weight coefficient is greater than a preset value as the target wavenumber segment.

[0116] In some embodiments, the construction module 1105 is further used to: pre-process the third near-infrared spectrum and the fourth near-infrared spectrum, and the pre-processing includes at least one of the following: wavelet transformation processing and standard normal transformation processing.

[0117] In some embodiments, the construction module 1105 is also used to: obtain first property information corresponding to each group of reforming raw material fraction samples; collect the fifth near-infrared spectrum corresponding to at least one group of actual reforming raw material fraction samples, and obtain second property information corresponding to each group of actual reforming raw material fraction samples; and construct a reforming raw material property detection model based on the fourth near-infrared spectrum, the fifth near-infrared spectrum and the corresponding first property information and the second property information.

[0118] In some embodiments, the construction module 1105 is specifically used to: construct a reforming raw material property detection model using partial least squares method according to the fourth near infrared spectrum, the fifth near infrared spectrum and the corresponding first property information and second property information.

[0119] In some embodiments, the construction module 1105 is further used to: preprocess the target wavenumber bands of the fourth near-infrared spectrum and the fifth near-infrared spectrum, and the preprocessing includes at least one of the following: wavelet transformation processing and standard normal transformation processing.

[0120] Technicians in the relevant field can clearly understand that, for the convenience and simplicity of description, the specific working process of the device for directly predicting the properties of reforming raw materials from crude oil and the corresponding beneficial effects described above can refer to the corresponding process in the aforementioned method example and will not be repeated here.

[0121] like Fig.12 As shown, an embodiment of the present invention provides an electronic device, including a processor 1201, a communication interface 1202, a memory 1203 and a communication bus 1204, wherein the processor 1201, the communication interface 1202, and the memory 1203 communicate with each other through the communication bus 1204. Memory 1203, used for storing computer programs; In one embodiment of the present invention, the processor 1201 is used to implement the steps of the method for directly predicting the properties of reforming feedstock from crude oil provided in any one of the aforementioned method embodiments when executing the program stored in the memory 1203.

[0122] The implementation principle and technical effect of the electronic device provided by the embodiment of the present invention are similar to those of the above embodiment and will not be described in detail here.

[0123] The above-mentioned memory 1203 can be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk or a ROM. The memory 1203 has a storage space for program codes for executing any method steps in the above-mentioned method. For example, the storage space for program codes may include various program codes for implementing various steps in the above method respectively. These program codes can be read from or written into one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks. Such computer program products are usually portable or fixed storage units. The storage unit may have a storage segment or storage space arranged similarly to the memory 1203 in the above-mentioned electronic device. The program code can be compressed, for example, in an appropriate form. Generally, the storage unit includes a program for executing the method steps according to an embodiment of the present invention, that is, a code that can be read by a processor such as a processor 1201, which, when run by an electronic device, causes the electronic device to execute various steps in the method described above.

[0124] The embodiment of the present invention further provides a storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for directly predicting the properties of reforming feedstock from crude oil are implemented.

[0125] The computer-readable storage medium may be included in the device / apparatus described in the above embodiment; or it may exist independently without being assembled into the device / apparatus. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present invention is implemented.

[0126] According to an embodiment of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device.

[0127] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0128] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features applied herein.

Claims

1. A method for directly predicting the properties of reforming feedstock from crude oil, characterized in that: include: Collecting the first near-infrared spectrum corresponding to the crude oil; Inputting the first near-infrared spectrum into a pre-constructed spectral conversion model, and outputting a second near-infrared spectrum corresponding to the reforming raw material fraction cut from the crude oil, wherein the spectral conversion model is constructed by using the near-infrared spectra of the crude oil sample and the corresponding reforming raw material fraction sample using a partial least squares method; inputting the second near infrared spectrum into a pre-constructed reforming feedstock property detection model, and outputting property information of the reforming feedstock fraction, wherein the reforming feedstock property detection model is constructed by using the near infrared spectra and property information of the reforming feedstock fraction sample and the actual reforming feedstock fraction sample, and adopting the partial least square method; The spectral conversion model includes a sub-spectral conversion model corresponding to at least one target wavenumber point in the target wavenumber band, the target wavenumber band is a wavenumber band whose weight coefficients related to each wavenumber point are greater than a preset value, and the weight coefficients related to each wavenumber point are constructed according to the near-infrared spectra and property information of each group of reforming raw material fraction samples; The first near infrared spectrum is input into the pre-built spectrum conversion model, and the second near infrared spectrum corresponding to the reforming raw material fraction cut from the crude oil is output, including: extracting first spectrum data related to a target wave number point from the first near infrared spectrum; The first spectral data is input into the sub-spectral conversion model corresponding to the target wavenumber point, and the second spectral data corresponding to the reforming raw material fraction at the target wavenumber point is output. The second spectral data corresponding to the reforming raw material fraction at at least one target wavenumber point constitutes a second near-infrared spectrum.

2. The method for directly predicting the properties of reforming feedstock from crude oil according to claim 1, characterized in that: The sub-spectrum conversion model uses a moving window partial least squares conversion based on a preset number of windows, and extracts first spectrum data related to the target wave number point from the first near-infrared spectrum, including: Determine adjacent wave number points centered on the target wave number point, and the number of wave number points of the target wave number point and the adjacent wave number point is consistent with the number of preset windows; First spectrum data corresponding to the target wave number point and the adjacent wave number points are extracted from the first near infrared spectrum.

3. The method for directly predicting the properties of reforming feedstock from crude oil according to claim 1 or 2, characterized in that: After collecting the first near infrared spectrum corresponding to the crude oil, the following steps are also included: The target wave number band of the first near infrared spectrum is preprocessed, wherein the preprocessing includes at least one of the following: wavelet transformation processing and standard normal transformation processing.

4. The method for directly predicting the properties of reforming feedstock from crude oil according to claim 1 or 2, characterized in that: Before inputting the first NIR spectrum into the pre-built spectral conversion model, it also includes: Obtaining at least one group of crude oil samples, and collecting a third near infrared spectrum corresponding to each group of crude oil samples; Perform actual boiling point distillation on each group of crude oil samples to cut out corresponding reforming raw material fraction samples within a preset temperature range; collecting a fourth near infrared spectrum corresponding to each group of reforming raw material fraction samples; A spectral conversion model is constructed according to the third near-infrared spectrum and the fourth near-infrared spectrum.

5. The method for directly predicting the properties of reforming feedstock from crude oil according to claim 4, characterized in that: A spectrum conversion model is constructed according to the third near infrared spectrum and the fourth near infrared spectrum, including: determining a target wavenumber band, wherein the target wavenumber band includes at least one target wavenumber point; For each target wavenumber point in the target wavenumber band, extract third spectrum data related to the target wavenumber point from the third near-infrared spectrum, and extract fourth spectrum data corresponding to the target wavenumber point from the fourth near-infrared spectrum; A sub-spectrum conversion model corresponding to the target wavenumber point is constructed according to the third spectrum data and the fourth spectrum data, and at least one sub-spectrum conversion model corresponding to the target wavenumber point constitutes a spectrum conversion model.

6. The method for directly predicting the properties of reforming feedstock from crude oil according to claim 5, characterized in that: Extracting third spectrum data related to the target wave number point from the third near infrared spectrum includes: Determine the adjacent wave number points centered on the target wave number point. The number of wave number points of the target wave number point and the adjacent wave number point is consistent with the number of preset windows. extracting third spectrum data corresponding to the target wave number point and the adjacent wave number point from the third near infrared spectrum; Extracting fourth spectrum data related to the target wave number point from the fourth near infrared spectrum includes: Determine the adjacent wave number points centered on the target wave number point. The number of wave number points of the target wave number point and the adjacent wave number point is consistent with the number of preset windows. Extracting fourth spectrum data corresponding to the target wave number point and the adjacent wave number point from the fourth near infrared spectrum; Constructing a sub-spectrum conversion model corresponding to the target wave number point according to the third spectrum data and the fourth spectrum data, including: According to the third spectrum data and the fourth spectrum data, a sub-spectrum conversion model is constructed by adopting a moving window least squares conversion method with a preset number of windows.

7. The method for directly predicting the properties of reforming feedstock from crude oil according to claim 5 or 6, characterized in that: Determine the target wave number band, including: Obtaining first property information corresponding to each group of reforming raw material fraction samples; Constructing the weight coefficients of the wave number points corresponding to the reforming raw material fraction samples according to the fourth near infrared spectrum and the first property information of each group of reforming raw material fraction samples; The wavenumber band whose relevant weight coefficient is greater than the preset value is determined as the target wavenumber band.

8. The method for directly predicting the properties of reforming feedstock from crude oil according to claim 4, characterized in that: Before constructing the spectrum conversion model according to the third near-infrared spectrum and the fourth near-infrared spectrum, it also includes: The target wave number bands of the third near infrared spectrum and the fourth near infrared spectrum are preprocessed, and the preprocessing includes at least one of the following: wavelet transformation processing and standard normal transformation processing.

9. The method of directly predicting the properties of reforming feedstock from crude oil according to claim 4, characterized in that: Prior to inputting the second NIR spectrum into the pre-built reformate feedstock property detection model, it also includes: Obtaining first property information corresponding to each group of reforming raw material fraction samples; Collecting a fifth near infrared spectrum corresponding to at least one group of actual reforming raw material fraction samples, and obtaining second property information corresponding to each group of actual reforming raw material fraction samples; A reforming raw material property detection model is constructed according to the fourth near infrared spectrum, the fifth near infrared spectrum and the corresponding first property information and second property information.

10. The method for directly predicting the properties of reforming feedstock from crude oil according to claim 9, characterized in that: A reforming raw material property detection model is constructed according to the fourth near infrared spectrum, the fifth near infrared spectrum and the corresponding first property information and second property information, including: According to the fourth near infrared spectrum, the fifth near infrared spectrum and the corresponding first property information and second property information, a reforming raw material property detection model is constructed using the partial least squares method.

11. The method for directly predicting the properties of reforming feedstock from crude oil according to claim 9 or 10, characterized in that: Before building the reforming raw material property detection model, it also includes: The target wave number bands of the fourth near infrared spectrum and the fifth near infrared spectrum are preprocessed, and the preprocessing includes at least one of the following: wavelet transformation processing and standard normal transformation processing.

12. A device for applying the method for directly predicting the properties of reforming feedstock from crude oil as claimed in any one of claims 1 to 11, characterized in that: include: A collection module, used for collecting a first near-infrared spectrum corresponding to crude oil; A conversion module, used for inputting the first near infrared spectrum into a pre-built spectrum conversion model, and outputting a second near infrared spectrum corresponding to the reforming raw material fraction cut from the crude oil; The prediction module is used to input the second near infrared spectrum into a pre-built reforming raw material property detection model and output the property information of the reforming raw material fraction.

13. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor is used to implement the steps of the method for directly predicting the properties of reforming feedstock from crude oil as described in any one of claims 1 to 11 when executing the program stored in the memory.

14. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for directly predicting the properties of reforming feedstock from crude oil are implemented as described in any one of claims 1 to 11.

Images