Method and apparatus for rapid analysis of molecular components of naphtha

Abstract

A method and apparatus for the rapid analysis of the molecular components of naphtha. The method comprises: receiving scanning spectrum data of target naphtha (S201); using a calibration spectrogram data set to calibrate the scanning spectrum data, wherein the calibration spectrogram data set is obtained by means of scanning a plurality of naphtha samples under preset detection conditions by using a plurality of spectrometers, and the scanning spectrum data is obtained by means of scanning the target naphtha on the basis of a first scanner among the plurality of spectrometers (S202); and performing, from a preset naphtha molecular composition library, matching to obtain a molecular composition corresponding to the calibrated scanning spectrum data, and obtaining predicted molecular properties of the target naphtha on the basis of the molecular composition, so as to determine macroscopic properties of the target naphtha, wherein the naphtha molecular composition library is obtained by using comprehensive two-dimensional gas chromatography technology (S203). The analysis of fraction molecular components of naphtha fractions and the characterization of macroscopic physical properties of petroleum fractions can be accurately and efficiently implemented.

Description

Method and device for rapid analysis of naphtha molecular components

[0001] This application claims priority to a Chinese patent application filed on October 8, 2023, with application number 202311294870.X and invention name “Method and device for rapid analysis of naphtha molecular components”. All contents of the patent are incorporated herein in their entirety. Technical Field

[0002] This specification relates to the technical field of oil analysis, and in particular to a method and device for rapid analysis of naphtha molecular components. Background Art

[0003] Petroleum fractions refer to a complex mixture of various hydrocarbon and non-hydrocarbon compounds that make up crude oil. The light fractions between the initial boiling point (initial boiling point) and 200°C (or 180°C) during atmospheric distillation are generally referred to as gasoline fractions (also known as light oil, naphtha, light distillate, or naphtha fraction). Existing naphtha composition analysis primarily utilizes spectroscopy to characterize the macroscopic physical properties of naphtha fractions and one-dimensional gas chromatography to analyze the molecular composition of light distillate fractions. However, due to limitations in the operating environment, sample handling, and separation time required for one-dimensional gas chromatography, these techniques cannot be widely applied in production sites. Furthermore, the variety of spectroscopy and one-dimensional gas chromatography instruments is complex and lacks unified standards. One-dimensional gas chromatography cannot analyze naphtha fractions above C8 in detail, but can only represent these components in aggregate form, resulting in low analytical accuracy. Therefore, accurately and efficiently analyzing the molecular composition of naphtha fractions and characterizing the macroscopic physical properties of petroleum fractions are urgent technical challenges.

[0004] Summary of the Invention

[0005] Given the current limitations of the operating environment, sample processing, and separation time for one-dimensional gas chromatography analysis, it cannot be widely used in production sites. In addition, there are many types of spectral instruments and one-dimensional gas chromatography analysis instruments, and there is no unified standard. When using one-dimensional gas chromatography to analyze naphtha fractions, it is impossible to analyze C8 and above components in detail, and C8 and above components can only be expressed in a lumped form, resulting in low analysis accuracy and efficiency. This solution is proposed to overcome the above problems or at least partially solve the above problems.

[0006] On the one hand, an object of some embodiments of this specification is to provide a method for rapid analysis of naphtha molecular components, the method comprising:

[0007] receiving scanning spectrum data of target naphtha;

[0008] Correcting the scanned spectral data using a calibration spectral dataset; wherein the calibration spectral dataset is obtained by scanning a plurality of naphtha samples using a plurality of spectrometers under preset detection conditions, and the scanned spectral data is obtained by scanning a target naphtha using a first scanner of the plurality of spectrometers;

[0009] From a preset naphtha molecular composition library, the molecular composition corresponding to the corrected scanned spectral data is matched, and the predicted molecular properties of the target naphtha are obtained based on the molecular composition, thereby determining the macroscopic properties of the target naphtha; wherein, the naphtha molecular composition library utilizes comprehensive two-dimensional gas chromatography technology to determine the monomer hydrocarbon components of multiple naphtha samples, and is established based on the monomer hydrocarbon components of multiple naphtha samples.

[0010] Furthermore, the correction spectrum data set includes at least first correction spectrum data and second correction spectrum data.

[0011] Furthermore, the calibration spectrum data set is constructed using the following steps:

[0012] Scanning at least one naphtha sample using a first spectrometer to obtain first calibration spectrum data;

[0013] Scanning at least one naphtha sample using a second spectrometer to obtain second calibration spectrum data;

[0014] A corresponding correction spectrum data set is constructed according to the first correction spectrum data and the second correction spectrum data.

[0015] Furthermore, the calibration spectrum data set is constructed using the following steps:

[0016] Scanning at least one naphtha sample using a first spectrometer, and performing a first preprocessing on the scan result to obtain first corrected spectrum data; the first preprocessing at least includes a sharpening process;

[0017] Scanning at least one naphtha sample using a second spectrometer, and performing a second preprocessing on the scan result to obtain second corrected spectrum data; wherein the second preprocessing includes at least a sharpening process;

[0018] A corresponding correction spectrum data set is constructed according to the first correction spectrum data and the second correction spectrum data.

[0019] Furthermore, the first spectrometer and the second spectrometer are Fourier transform near-infrared spectrometers;

[0020] The first spectrometer and the second spectrometer scan multiple naphtha samples under the following preset detection conditions:

[0021] Using transmission measurement method;

[0022] Scanning resolution not less than 8cm -1 ;

[0023] The scanning wave number range is 4000 cm -1 ~10000cm -1 ;

[0024] The cumulative number of scans is at least 64.

[0025] Furthermore, the use of the correction spectrum data set to correct the scanned spectrum data includes:

[0026] screening the spectrum data to be fitted corresponding to the scanned spectrum data from the first correction spectrum data;

[0027] Determining fitting parameters according to the spectrum data to be fitted and the scanned spectrum data;

[0028] The scanning spectrum data is corrected according to the fitting parameters and the second correction spectrum data.

[0029] Furthermore, determining fitting parameters based on the spectrum data to be fitted and the scanned spectrum data includes:

[0030] According to the spectrum data to be fitted and the scanned spectrum data, the fitting parameters are determined using the following formula:

[0031] Among them, X1 is the scanned spectrum data, n is the data volume of the spectrum data to be fitted, i is the ordinal number of the spectrum data to be fitted, ω 1i is the i-th fitting parameter, X 1i is the i-th spectrum data to be fitted.

[0032] Furthermore, determining fitting parameters based on the spectrum data to be fitted and the scanned spectrum data further includes:

[0033] Establishing an objective function based on the spectrum data to be fitted and the second corrected spectrum data;

[0034] Iterating the objective function using a preset interval of iterative data volume;

[0035] The data amount of the spectrogram data to be fitted is determined according to the iterative data amount corresponding to the minimum iterative output result.

[0036] Furthermore, the objective function is established using the following formula:

[0037] Among them, c mis the output value of the objective function, m is the iterative data amount of the spectrum data to be fitted, i is the ordinal number of the spectrum data to be fitted, is the i-th fitting parameter, is the i-th spectrum data corresponding to the i-th spectrum data to be fitted in the second correction spectrum data, X b It is the real spectrum data obtained by scanning the target naphtha using the second spectrometer.

[0038] Furthermore, the correcting the scanned spectrum data according to the fitting parameters and the second corrected spectrum data includes:

[0039] According to the fitting parameters and the second correction spectrum data, the scanning spectrum data is corrected using the following formula:

[0040] in, is the scanned spectrum data after correction, n is the data amount of the fitting parameter, i is the ordinal number of the fitting parameter, ω 1i is the i-th fitting parameter, X 2i is the i-th spectrum data corresponding to the i-th spectrum data to be fitted in the second correction spectrum data.

[0041] Furthermore, the molecular composition corresponding to the calibrated scan spectrum data is matched from a preset naphtha molecular composition library, including:

[0042] screening the spectrum data to be matched corresponding to the scanned spectrum data from the second corrected spectrum data;

[0043] Determining matching parameters based on the spectrum data to be matched and the corrected scan spectrum data;

[0044] Searching for a molecular composition to be matched corresponding to the spectrum data to be matched from a preset naphtha molecular composition library;

[0045] The molecular composition corresponding to the corrected scan spectrum data is determined based on the matching parameters and the molecular composition to be matched.

[0046] Furthermore, matching parameters are determined based on the spectrum data to be matched and the corrected scan spectrum data, including:

[0047] According to the spectrum data to be matched and the corrected scan spectrum data, the matching parameters are determined using the following formula:

[0048] in, is the scanned spectrum data after correction, l is the data volume of matching parameters, j is the ordinal number of matching parameters, ω 2j is the jth matching parameter, X 2jis the j-th type of spectrum data in the second corrected spectrum data corresponding to the j-th type of spectrum data to be matched.

[0049] Furthermore, determining matching parameters based on the spectrum data to be matched and the corrected scan spectrum data further includes:

[0050] Establishing an optimization function according to the spectrum data to be matched and the second correction spectrum data;

[0051] Iterating the optimization function using a preset interval of iterative data volume;

[0052] The matching parameter is determined according to the iterative data amount corresponding to the minimum iterative output result.

[0053] Furthermore, the optimization function is established using the following formula:

[0054] Among them, p k is the output value of the optimization function, k is the iterative data amount of the spectrum data to be matched, i is the ordinal number of the spectrum data to be matched, is the i-th matching parameter, z i is the molecular composition of the i-th naphtha sample in the naphtha molecular composition library corresponding to the i-th spectrum data to be matched, z b The real molecular composition of the target naphtha was obtained by using comprehensive two-dimensional gas chromatography technology.

[0055] Further, determining the molecular composition corresponding to the corrected scan spectrum data according to the matching parameters and the molecular composition to be matched includes:

[0056] According to the matching parameters and the molecular composition to be matched, the molecular composition corresponding to the corrected scan spectrum data is determined using the following formula:

[0057] Where z is the molecular composition of the target naphtha, l is the data volume of the matching parameter, and i is the ordinal number of the matching parameter. is the i-th matching parameter, z i is the molecular composition of the i-th naphtha sample corresponding to the i-th spectrum data to be matched in the naphtha molecular composition library.

[0058] Furthermore, the preset naphtha molecular composition library is established according to the following steps:

[0059] Comprehensive two-dimensional gas chromatography technology was used to detect a variety of naphtha samples and obtain the monomer hydrocarbon components of various naphtha samples;

[0060] The naphtha molecular composition library is established according to monomer hydrocarbon components of multiple naphtha samples.

[0061] Furthermore, the predicted molecular properties of the target naphtha are obtained based on the molecular composition, thereby determining the macroscopic properties of the target naphtha, including:

[0062] Determining molecular structure group information corresponding to the molecular composition; the molecular structure group information at least includes a basic group and a combined group of the molecular structure;

[0063] Inputting the molecular structure group information into a preset molecular property prediction model to obtain predicted molecular properties of the target naphtha;

[0064] The predicted molecular properties are input into a preset molecular property mixing model to obtain the macroscopic properties of the target naphtha.

[0065] Furthermore, the preset molecular property prediction model is trained using the following method:

[0066] Get historical naphtha analysis data;

[0067] The molecular structure group information in the historical naphtha analysis data is used as input, and the molecular property labels in the historical naphtha analysis data are used as output to construct training samples, and a supervised learning model is constructed based on the input and output;

[0068] The supervised learning model is trained using the training samples, and the trained supervised learning model is used as a molecular property prediction model.

[0069] Furthermore, in some embodiments, using the training samples to train the supervised learning model includes:

[0070] Dividing the training samples into a training set and a validation set;

[0071] Training the supervised learning model using the training set;

[0072] Input the molecular structure group information in the validation set into the trained supervised learning model;

[0073] Calculate the prediction accuracy based on the output of the supervised learning model and the molecular property labels in the validation set;

[0074] If the prediction accuracy is less than the set threshold, the supervised learning model is retrained until the prediction accuracy is not less than the set threshold.

[0075] Furthermore, the molecular property mixing model is constructed using the following formula:

[0076] Among them, ON Linear is a linear mixed submodel, ON NonLinear is the nonlinear correction submodel, h and g are the numbers of various compounds in different naphtha samples, and v h is the volume fraction of the hth compound, v g is the volume fraction of the g-th compound, ON h is the target property of the hth compound, ΔON hg is the target property of the hth compound after the hth compound is corrected based on the interaction between the hth compound and the gth compound, are the interaction parameters between the hth compound and the gth compound, respectively.

[0077] On the other hand, some embodiments of this specification further provide a device for rapidly analyzing the molecular components of naphtha, the device comprising:

[0078] A receiving module, used for receiving scanning spectrum data of target naphtha;

[0079] a correction module, configured to correct the scanned spectral data using a correction spectral dataset, wherein the correction spectral dataset is obtained by scanning a plurality of naphtha samples under preset detection conditions using a plurality of spectrometers, and the scanned spectral data is obtained by scanning a target naphtha using a first scanner of the plurality of spectrometers;

[0080] The determination module is used to match the molecular composition corresponding to the corrected scanned spectral data from a preset naphtha molecular composition library, and obtain the predicted molecular properties of the target naphtha based on the molecular composition, thereby determining the macroscopic properties of the target naphtha; wherein, the naphtha molecular composition library uses comprehensive two-dimensional gas chromatography technology to determine the monomer hydrocarbon components of multiple naphtha samples, and is established based on the monomer hydrocarbon components of multiple naphtha samples.

[0081] On the other hand, some embodiments of this specification further provide a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the computer program executes instructions of the above method when executed by the processor.

[0082] On the other hand, some embodiments of this specification further provide a computer storage medium having a computer program stored thereon, wherein the computer program executes the instructions of the above method when executed by a processor of a computer device.

[0083] On the other hand, some embodiments of this specification further provide a computer program product, which includes a computer program. When the computer program is executed by a processor of a computer device, the computer program executes instructions of the above method.

[0084] Some embodiments of this specification provide one or more technical solutions that have at least the following technical effects:

[0085] The embodiments of the present specification utilize a first scanner to scan the target naphtha to obtain scanning spectral data, and utilize multiple spectrometers to scan multiple naphtha samples under preset detection conditions to obtain a correction spectrum data set, and calibrate the scanning spectral data to improve the accuracy of the corrected scanning spectral data. On the basis of the corrected scanning spectral data, the monomer hydrocarbon components of multiple naphtha samples are determined by full two-dimensional gas chromatography technology, and a naphtha molecular composition library is established based on the monomer hydrocarbon components of the multiple naphtha samples to determine the molecular composition corresponding to the corrected scanning spectral data. This can accurately and conveniently analyze the molecular components of light distillate oil fractions and characterize the macroscopic physical properties of petroleum fractions.

[0086] The above description is only an overview of the technical solutions of some embodiments of this specification. In order to more clearly understand the technical means of some embodiments of this specification, they can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of some embodiments of this specification more obvious and easy to understand, the specific implementation methods of some embodiments of this specification are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] In order to more clearly illustrate some embodiments of this specification or technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments described in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without inventive work. In the drawings:

[0088] FIG1 shows a schematic diagram of an implementation system of a method for rapid analysis of naphtha molecular components in some embodiments of this specification;

[0089] FIG2 shows a flow chart of a method for rapid analysis of naphtha molecular components in some embodiments of this specification;

[0090] FIG3 is a schematic diagram of the steps of constructing a calibration spectrum data set in some embodiments of this specification;

[0091] FIG4 is a schematic diagram of the steps of processing first calibration spectrum data in some embodiments of this specification;

[0092] FIG5 is a schematic diagram of the steps of processing second calibration spectrum data in some embodiments of this specification;

[0093] FIG6 is a schematic diagram of the steps of correcting scan spectrum data in some embodiments of this specification;

[0094] FIG7 is a schematic diagram of the steps of determining fitting parameters in some embodiments of this specification;

[0095] FIG8 is a schematic diagram of the steps of matching the molecular composition corresponding to the corrected scan spectrum data in some embodiments of this specification;

[0096] FIG9 is a schematic diagram of the steps of determining matching parameters in some embodiments of this specification;

[0097] FIG10 is a schematic diagram of the steps of establishing a naphtha molecular composition library in some embodiments of this specification;

[0098] FIG11 is a schematic diagram of the steps for determining the macroscopic properties of target naphtha in some embodiments of this specification;

[0099] FIG12 is a schematic diagram of the steps of training a molecular property prediction model in some embodiments of this specification;

[0100] FIG13 is a schematic diagram of the steps of optimizing a molecular property prediction model in some embodiments of this specification;

[0101] FIG14 is a schematic structural diagram of a device for rapid analysis of naphtha molecular components according to some embodiments of this specification;

[0102] FIG15 is a schematic diagram of the computer device structure provided in some embodiments of this specification.

[0103] [Explanation of the accompanying drawings] 101, terminal; 102, server; 1401, receiving module; 1402, correction module; 1403, determination module; 1502, computer device; 1504, processor; 1506, memory; 1508, driving mechanism; 1510, input / output interface; 1512, input device; 1514, output device; 1516, presentation device; 1518, graphical user interface; 1520, network interface; 1522, communication link; 1524, communication bus. DETAILED DESCRIPTION

[0104] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings of some embodiments of this specification. Obviously, the embodiments described are only some of the embodiments of this specification, not all of them. All other embodiments obtained by those skilled in the art based on some of the embodiments in this specification without creative work should fall within the scope of protection of this specification.

[0105] It should be noted that the terms "first", "second", etc. in the specification and claims of this document and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of this document described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment. It should be noted that the acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of relevant laws and regulations.

[0106] As shown in FIG1 , a schematic diagram of an implementation system of a method for rapid analysis of naphtha molecular components according to an embodiment of the present invention may include: a terminal 101 and a server 102. The terminal 101 and the server 102 communicate with each other via a network. The network may include a local area network (LAN), a wide area network (WAN), the Internet, or a combination thereof, and is connected to a website, a user device (e.g., a computing device), and a back-end system. A staff member may send a request for rapid analysis of naphtha molecular components to the server 102 via the terminal 101. After receiving the request for rapid analysis of naphtha molecular components, the server 102 calls the data in the database for calculation and processing to obtain an analysis result, and sends the analysis result to the terminal 101 so that the staff member can process the business according to the analysis result.

[0107] In the embodiments of this specification, the server 102 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN, Content Delivery Network), and big data and artificial intelligence platforms.

[0108] In an optional embodiment, the terminal 101 may include, but is not limited to, electronic devices such as self-service terminals, desktop computers, tablet computers, laptop computers, and smart wearable devices. Optionally, the operating system running on the electronic device may include, but is not limited to, Android, iOS, Linux, and Windows. Of course, the terminal 101 is not limited to the aforementioned electronic devices having a certain physical form; it may also be software running on the aforementioned electronic devices.

[0109] In addition, it should be noted that what is shown in FIG. 1 is only an application environment provided by the present disclosure. In actual applications, multiple terminals 101 may be included, and this specification does not impose any limitation thereto.

[0110] FIG2 is a flow chart of a method for rapid analysis of naphtha molecular components provided by an embodiment of the present invention. This specification provides method operation steps as described in the embodiment or flow chart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the order of many steps and does not represent the only execution order. When the actual system or device product is executed, it can be executed in sequence or in parallel according to the method shown in the embodiment or the accompanying drawings. Specifically, as shown in FIG2, applied to the above-mentioned server side, the method may include:

[0111] S201: receiving scanning spectrum data of target naphtha;

[0112] S202: Correcting the scanned spectral data using a calibration spectrum data set; wherein the calibration spectrum data set is obtained by scanning a plurality of naphtha samples using multiple spectrometers under preset detection conditions, and the scanned spectral data is obtained by scanning a target naphtha using a first scanner among the multiple spectrometers;

[0113] S203: Match the molecular composition corresponding to the corrected scanned spectral data from a preset naphtha molecular composition library, and obtain the predicted molecular properties of the target naphtha based on the molecular composition, thereby determining the macroscopic properties of the target naphtha; wherein the naphtha molecular composition library utilizes comprehensive two-dimensional gas chromatography technology to determine the monomer hydrocarbon components of multiple naphtha samples, and is established based on the monomer hydrocarbon components of multiple naphtha samples.

[0114] The embodiments of the present specification utilize a first scanner to scan the target naphtha to obtain scanning spectral data, and utilize multiple spectrometers to scan multiple naphtha samples under preset detection conditions to obtain a correction spectrum data set, and calibrate the scanning spectral data to improve the accuracy of the corrected scanning spectral data. On the basis of the corrected scanning spectral data, the monomer hydrocarbon components of multiple naphtha samples are determined by full two-dimensional gas chromatography technology, and a naphtha molecular composition library is established based on the monomer hydrocarbon components of the multiple naphtha samples to determine the molecular composition corresponding to the corrected scanning spectral data. This can accurately and conveniently analyze the molecular components of light distillate oil fractions and characterize the macroscopic physical properties of petroleum fractions.

[0115] It can be understood that, in some embodiments, different spectra may be obtained by scanning the same naphtha sample using different spectrometers, and thus the obtained spectral data are also different. In order to achieve rapid analysis of the molecular components of the naphtha sample, the original spectral data of the target naphtha can be corrected using the established calibration spectral data set to obtain the corrected spectral data of the target naphtha, thereby improving the accuracy of the scanned spectral data. In the embodiments provided in this application, the molecular composition of the target naphtha is obtained from the established naphtha molecular composition library based on the corrected scanning spectral data of the target naphtha, thereby achieving the direct calculation of the molecular composition of the naphtha sample from the scanning spectrum of the naphtha sample, without the need to install a gas chromatograph analyzer at the production site, thereby saving the refinery a large amount of human resource costs and the capital cost of purchasing equipment, and having certain guiding significance for the formulation of subsequent naphtha processing plans.

[0116] Furthermore, in some embodiments, the correction spectrum data set includes at least first correction spectrum data and second correction spectrum data.

[0117] Referring to FIG. 3 , in some embodiments, the calibration spectrum dataset is constructed using the following steps:

[0118] S301: Scanning at least one naphtha sample using a first spectrometer to obtain first calibration spectrum data;

[0119] S302: Scanning at least one naphtha sample using a second spectrometer to obtain second calibration spectrum data;

[0120] S303: Constructing a corresponding correction spectrum data set according to the first correction spectrum data and the second correction spectrum data.

[0121] It can be understood that in some embodiments, the first calibration spectral data is spectral data of multiple naphtha samples obtained using a first spectrometer, and the second calibration spectral data is spectral data of multiple naphtha samples obtained using a second spectrometer. In specific implementations, the first spectrometer and the second spectrometer can be near-infrared spectrometers or other spectrometers, and are not limited to the description of this specification. Naphtha samples can be collected from a refinery, from various types of naphtha produced using different raw materials and processes. Constructing corresponding calibration spectral datasets using the first calibration spectral data and the second calibration spectral data can reduce errors in the spectral data, thereby improving the scanning accuracy of the target naphtha.

[0122] Referring to FIG. 4 , in some embodiments, the calibration spectrum dataset is constructed using the following steps:

[0123] S401: Scanning at least one naphtha sample using a first spectrometer, performing a first preprocessing on the scan result to obtain first calibrated spectrum data; the first preprocessing at least includes a sharpening process;

[0124] S402: Scanning at least one naphtha sample using a second spectrometer, and performing a second preprocessing on the scan result to obtain second corrected spectrum data; the second preprocessing at least includes a sharpening process;

[0125] S403: Constructing a corresponding correction spectrum data set according to the first correction spectrum data and the second correction spectrum data.

[0126] It can be understood that, in some embodiments, sharpening the first corrected scan spectrum data and / or the second corrected scan spectrum data can be performed by performing a first-order differential on the spectrum, which means using a first-order derivative method to obtain a first-order differential value at each spectral wavelength on the spectrum graph. The calculated first-order differential value can be used to obtain the rate of change of the spectrum at each wavelength, thereby better revealing the characteristics of the spectrum. It should be noted that in addition to sharpening, the first preprocessing and the second preprocessing can also include other spectral processing techniques, such as normalization processing, interpolation processing, etc., which are not limited in this document. Furthermore, the first preprocessing and the second preprocessing can be the same or different, which are not limited in this document.

[0127] Further, in some embodiments, the first spectrometer and the second spectrometer are Fourier transform near-infrared spectrometers;

[0128] 5 , in some embodiments, the first spectrometer and the second spectrometer scan multiple naphtha samples under the following preset detection conditions:

[0129] S501: adopts transmission measurement method;

[0130] S502: Scanning resolution is not less than 8cm -1 ;

[0131] S503: Scanning wave number range is 4000cm -1 ~10000cm -1 ;

[0132] S504: The cumulative number of scans is at least 64.

[0133] It can be understood that in some embodiments, the first spectrometer and the second spectrometer can be Fourier transform near-infrared spectrometers. The above-mentioned preset detection conditions can ensure the accuracy of the scanning results and the validity of the data. Specifically, the first Fourier transform near-infrared spectrometer is used to detect multiple naphtha samples according to the preset detection conditions to obtain a first spectrum of each naphtha sample. The second Fourier transform near-infrared spectrometer is used to detect multiple naphtha samples according to the preset detection conditions to obtain a second spectrum of each naphtha sample. Scanning multiple naphtha samples can improve the richness and completeness of the calibration spectrum dataset. In some embodiments, a near-infrared spectrometer can also be added to construct the calibration spectrum dataset. This is not limited herein. It should be noted that the sequence numbers S501-S504 in Figure 5 and the above description are only used to distinguish different detection conditions and do not mean that the detection conditions of the spectrometers need to be set in sequence. In common embodiments, the detection conditions corresponding to S501-S504 are indispensable to ensure effective and accurate scanning results.

[0134] 6 , in some embodiments, the use of the calibration spectrum data set to calibrate the scanned spectrum data may include:

[0135] S601: Filtering spectrum data to be fitted corresponding to the scanned spectrum data from the first correction spectrum data;

[0136] S602: Determine fitting parameters based on the spectrum data to be fitted and the scanned spectrum data;

[0137] S603: Correcting the scanned spectrum data according to the fitting parameters and the second corrected spectrum data.

[0138] It can be understood that, in some embodiments, from the first correction spectrum data, based on the similarity between the scanning spectrum data and the first correction spectrum data, the spectrum data to be fitted corresponding to the scanning spectrum data is screened. In the specific implementation process, a common method can be used to calculate the similarity between the scanning spectrum data and each type of spectrum data in the first correction spectrum data. It is not limited by the description of this specification. In the specific implementation process, a variety of methods can be used to screen out a variety of spectrum data to be fitted from the first correction spectrum data based on the similarity calculated above. For example, all the calculated similarities can be sorted, and the spectrum data corresponding to the first n similarities can be used as the spectrum data to be fitted. For another example, the spectrum data corresponding to the similarity greater than a preset threshold can be used as the spectrum data to be fitted, thereby ensuring the calibration accuracy of the correction of the scanning spectrum data.

[0139] Furthermore, in some embodiments, the fitting parameters are determined based on the spectrum data to be fitted and the scanned spectrum data, including

[0140] According to the spectrum data to be fitted and the scanned spectrum data, the fitting parameters are determined using the following formula:

[0141] Among them, X1 is the scanned spectrum data, n is the data volume of the spectrum data to be fitted, i is the ordinal number of the spectrum data to be fitted, ω 1i is the i-th fitting parameter, X 1i is the i-th spectrum data to be fitted.

[0142] In a specific implementation process, since the amount of the spectrum data to be fitted involved in the above calculation will affect the calculation accuracy of the fitting parameters, it is necessary to determine an appropriate amount of the spectrum data to be fitted involved in the calculation.

[0143] 7 , in some embodiments, determining fitting parameters based on the spectrum data to be fitted and the scanned spectrum data may further include:

[0144] S701: Establishing an objective function based on the spectrum data to be fitted and the second corrected spectrum data;

[0145] S701: Iterating the objective function using a preset interval of iterative data volume;

[0146] S702: Determine the data volume of the spectrum data to be fitted according to the iterative data volume corresponding to the minimum iterative output result.

[0147] It can be understood that, in some embodiments, the iterative data volume is a parameter, denoted as m, and m is located in a preset iterative data volume interval. According to different values ​​of the iterative data volume m of the multiple spectrogram data to be fitted that participate in the calculation, the objective function is iteratively solved to obtain multiple iterative output results, and the minimum value among the multiple iterative output results is obtained. The iterative data volume m corresponding to the minimum value is used as the data volume of the spectrogram data to be fitted. Specifically, in some embodiments, the objective function can be iteratively solved for different values ​​of the iterative data volume m in the objective function: 2, 3, 4, ..., 10, wherein when the iterative data volume m is 5, the value of the objective function obtained is the smallest. It can be determined that when the data volume of the spectrogram data to be fitted is 5, the accuracy of the calculation result of the fitting parameter obtained is the highest. Subsequently, 5 types of spectrogram data to be fitted can be screened out from the first correction spectrogram data to participate in the calculation of obtaining the fitting parameters.

[0148] Furthermore, in some embodiments, the objective function is established using the following formula:

[0149] Among them, c m is the output value of the objective function, m is the iterative data amount of the spectrum data to be fitted, i is the ordinal number of the spectrum data to be fitted, is the i-th fitting parameter, is the i-th spectrum data corresponding to the i-th spectrum data to be fitted in the second correction spectrum data, X b It is the real spectrum data obtained by scanning the target naphtha using the second spectrometer.

[0150] It can be understood that in some embodiments, the objective function determines whether the data amount of the current spectrum data to be fitted can ensure the accuracy of the fitting parameters by measuring the data distance between the i-th spectrum data corresponding to the i-th spectrum data to be fitted in the second correction spectrum data and the real spectrum data obtained by scanning the target naphtha using the second spectrometer. The output value of the objective function is the data distance. The smaller the data distance, the closer the spectrum data corresponding to the target naphtha matched from the second correction spectrum data (which can be regarded as a database) is to the real spectrum data, thereby ensuring the calculation accuracy of subsequent fitting parameters.

[0151] Furthermore, in some embodiments, the correcting the scanned spectrum data according to the fitting parameters and the second corrected spectrum data includes:

[0152] According to the fitting parameters and the second correction spectrum data, the scanning spectrum data is corrected using the following standard spectrum calculation formula:

[0153] in, is the scanned spectrum data after correction, n is the data amount of the fitting parameter, i is the ordinal number of the fitting parameter, ω 1i is the i-th fitting parameter, X 2i is the i-th spectrum data corresponding to the i-th spectrum data to be fitted in the second correction spectrum data.

[0154] It can be understood that in some embodiments, a standard spectrum calculation formula can be constructed using the database topology principle to calculate the corrected scanning spectrum data of the target naphtha. Furthermore, the original spectrum data obtained by scanning the target naphtha using any spectrometer can be corrected to obtain the corrected scanning spectrum data of the target naphtha, so that the corrected scanning spectrum data can be used to obtain the molecular composition of the target naphtha from the naphtha molecular composition library.

[0155] 8 , in some embodiments, matching the molecular composition corresponding to the corrected scan spectrum data from a preset naphtha molecular composition library may include:

[0156] S801: Filtering spectrum data to be matched corresponding to the scanned spectrum data from the second corrected spectrum data;

[0157] S802: determining matching parameters based on the spectrum data to be matched and the corrected scan spectrum data;

[0158] S803: searching for a molecular composition to be matched corresponding to the spectrum data to be matched from a preset naphtha molecular composition library;

[0159] S804: Determine the molecular composition corresponding to the corrected scan spectrum data according to the matching parameters and the molecular composition to be matched.

[0160] It can be understood that, in some embodiments, since the calibrated scanning spectrum data of the target naphtha to be tested is obtained by fitting, it is not one-to-one corresponding to the spectrum data in the second calibrated spectrum database. In order to obtain a more accurate molecular composition of the target naphtha to be tested from the established naphtha molecular composition library, the matching parameters can be obtained in the following way, and then the molecular composition of the target naphtha to be tested can be obtained according to the matching parameters and the molecular composition of the naphtha sample corresponding to the spectrum data to be matched in the naphtha molecular composition library. It should be noted that the naphtha molecular composition library belongs to a database, which contains multiple spectrum data and molecular composition data and the correspondence between the two.

[0161] Furthermore, in some embodiments, determining matching parameters based on the to-be-matched spectrum data and the corrected scan spectrum data includes:

[0162] According to the spectrum data to be matched and the corrected scan spectrum data, the matching parameters are determined using the following standard spectrum matching formula:

[0163] in, is the scanned spectrum data after correction, l is the data volume of matching parameters, j is the ordinal number of matching parameters, ω 2j is the jth matching parameter, X 2j is the j-th type of spectrum data in the second corrected spectrum data corresponding to the j-th type of spectrum data to be matched.

[0164] It can be understood that, in some embodiments, multiple spectral data to be matched and the corrected scanning spectral data of the target naphtha to be measured are substituted into the standard spectral matching formula shown above to obtain matching parameters that can ensure that the corrected scanning spectral data accurately corresponds to the spectral data in the second corrected spectral data.

[0165] 9 , in some embodiments, determining matching parameters based on the to-be-matched spectrum data and the corrected scan spectrum data may further include:

[0166] S901: establishing an optimization function according to the spectrum data to be matched and the second correction spectrum data;

[0167] S902: Iterating the optimization function using a preset interval of iterative data volume;

[0168] S903: Determine the matching parameter according to the iterative data volume corresponding to the minimum iterative output result.

[0169] It can be understood that in some embodiments, determining appropriate matching parameters can ensure the molecular composition analysis effect of the target naphtha. Therefore, in order to accurately determine the matching parameters, an optimization function is established according to the distance between the spectrum data to be matched and the second correction spectrum data, and the iterative data volume is increased or decreased according to the preset iterative data volume interval to obtain different optimization function output values. The matching parameters determined by the iterative data volume corresponding to the minimum optimization function output value can ensure the accuracy of the subsequent determination of the molecular composition.

[0170] Furthermore, in some embodiments, the optimization function is established using the following formula:

[0171] Among them, p k is the output value of the optimization function, k is the iterative data amount of the spectrum data to be matched, i is the ordinal number of the spectrum data to be matched, is the i-th matching parameter, z i is the molecular composition of the i-th naphtha sample in the naphtha molecular composition library corresponding to the i-th spectrum data to be matched, zb The real molecular composition of the target naphtha was obtained by using comprehensive two-dimensional gas chromatography technology.

[0172] It can be understood that, in some embodiments, when establishing an optimization function based on the distance between the to-be-matched spectrum data and the second corrected spectrum data, the optimization function can be established based on the deviation value between the molecular composition information corresponding to the to-be-matched spectrum data and the actual molecular composition information measured by an instrument related to the comprehensive two-dimensional gas chromatography technology. Specifically, z b and z i In terms of data form, they can all be represented as vectors. In terms of data processing, the optimization function calculates the difference in distance between the corresponding vector of the molecular composition in the spectrum data to be matched and the corresponding vector of the actual measured molecular composition. The smaller the data difference reflected by the optimization function, the more accurate the spectrum data to be matched and the matching parameters are.

[0173] Furthermore, in some embodiments, determining the molecular composition corresponding to the corrected scan spectrum data based on the matching parameters and the molecular composition to be matched includes:

[0174] According to the matching parameters and the molecular composition to be matched, the molecular composition corresponding to the corrected scan spectrum data is determined using the following formula:

[0175] Where z is the molecular composition of the target naphtha, l is the data volume of the matching parameter, and i is the ordinal number of the matching parameter. is the i-th matching parameter, z i is the molecular composition of the i-th naphtha sample corresponding to the i-th spectrum data to be matched in the naphtha molecular composition library.

[0176] It can be understood that in some embodiments, after determining the matching parameters and the molecular composition to be matched, the molecular composition corresponding to the scanning spectral data can be determined efficiently and accurately using linear regression fitting, so that the corresponding macroscopic properties can be determined subsequently using the molecular composition corresponding to the corrected scanning spectral data.

[0177] Referring to FIG. 10 , in some embodiments, the preset naphtha molecular composition library is established according to the following steps:

[0178] S1001: Using comprehensive two-dimensional gas chromatography technology, various naphtha samples are tested to obtain monomer hydrocarbon components of various naphtha samples;

[0179] S1002: Establishing the naphtha molecular composition library according to monomer hydrocarbon components of multiple naphtha samples.

[0180] It can be understood that in some embodiments, the target naphtha to be tested is a light oil product obtained by distilling crude oil or cutting the corresponding fraction from secondary petroleum processing. The naphtha molecular composition library includes monomer hydrocarbon components of multiple naphtha samples. Using comprehensive two-dimensional gas chromatography technology, multiple naphtha samples are tested to obtain monomer hydrocarbon components of multiple naphtha samples. In the specific implementation process, the monomer hydrocarbon composition of the naphtha sample can be detected by comprehensive two-dimensional gas chromatography according to the optimal conditions of comprehensive two-dimensional gas chromatography equipment analysis. The equipment analysis conditions may include but are not limited to the temperature program of the chromatographic column, carrier gas flow rate and pressure, etc. Since different types of naphtha samples contain different numbers of molecules, the naphtha molecular composition library may include all molecular component data of the naphtha sample that can be detected by comprehensive two-dimensional chromatography. In some embodiments, after the molecular composition library is established, the database can be continuously expanded. Furthermore, using comprehensive two-dimensional gas chromatography to detect the monomer hydrocarbon composition of naphtha samples can effectively solve the disadvantage that one-dimensional chromatography cannot analyze components above C8+.

[0181] 11 , in some embodiments, the predicted molecular properties of the target naphtha are obtained based on the molecular composition, thereby determining the macroscopic properties of the target naphtha, including:

[0182] S1101: Determine molecular structure group information corresponding to the molecular composition; the molecular structure group information includes at least basic groups and combined groups of the molecular structure;

[0183] S1102: Inputting the molecular structure group information into a preset molecular property prediction model to obtain predicted molecular properties of the target naphtha;

[0184] S1103: Inputting the predicted molecular properties into a preset molecular property mixing model to obtain macroscopic properties of the target naphtha.

[0185] It can be understood that in some embodiments, the macroscopic properties of the target naphtha to be measured include at least octane number, vapor pressure, and D86 distillation curve. Based on the molecular composition of the target naphtha to be measured, the group information of the molecular structure of various molecules contained in the target naphtha to be measured is determined, where the group information of the molecular structure includes at least basic groups and combined groups of the molecular structure. Basic groups may include, but are not limited to, methyl and methylene groups. Combined groups are groups formed by combining multiple basic groups. The combined groups can be used to distinguish and identify isomers and complex molecules in the naphtha sample. During the specific implementation process, the group information of the molecular structure of various molecules contained in the target naphtha to be measured can be input into the molecular property prediction sub-model to obtain the predicted properties of various molecules in the target naphtha to be measured (for example, octane number, vapor pressure, boiling point, critical properties, etc.), and the predicted molecular properties are input into the preset molecular property mixing model to quickly obtain the macroscopic properties of the target naphtha. It should be noted that the molecular property prediction model is obtained by supervised learning training using historical naphtha analysis data, and the molecular property mixing model can output the macroscopic properties corresponding to various molecular compositions with linear or nonlinear relationships in the target naphtha.

[0186] Referring to FIG. 12 , in some embodiments, the preset molecular property prediction model is trained using the following method:

[0187] S1201: Obtain historical naphtha analysis data;

[0188] S1202: Using the molecular structure group information in the historical naphtha analysis data as input and the molecular property labels in the historical naphtha analysis data as output, constructing a training sample and building a supervised learning model based on the input and output;

[0189] S1203: Using the training samples to train the supervised learning model, and using the trained supervised learning model as a molecular property prediction model.

[0190] It can be understood that in some embodiments, a molecular property prediction sub-model can be constructed based on a variety of supervised machine learning algorithms, such as support vector machines, random forests or artificial neural networks, etc., using the molecular structure group information in the historical naphtha analysis data as input, and the molecular property labels in the historical naphtha analysis data as output, constructing training samples and iterating training multiple times, which can ensure that the trained molecular property prediction model can output accurate predicted molecular properties based on the molecular structure group information of the target naphtha.

[0191] Referring to FIG. 13 , in some embodiments, training the supervised learning model using the training samples may include:

[0192] S1301: Divide the training samples into a training set and a validation set;

[0193] S1302: Training the supervised learning model using the training set;

[0194] S1303: Inputting the molecular structure group information in the validation set into the trained supervised learning model;

[0195] S1304: Calculating prediction accuracy based on the output of the supervised learning model and the molecular property labels in the validation set;

[0196] S1305: If the prediction accuracy is less than the set threshold, retrain the supervised learning model until the prediction accuracy is not less than the set threshold.

[0197] It can be understood that in some embodiments, the training samples are divided into a training set and a validation set. Considering the time cost of manually producing molecular property labels and the ratio setting commonly used in deep learning, the ratio of the training set to the validation set in the embodiment of this specification is 10:1. After training the supervised learning model with the training set, the molecular structure group information in the validation set is respectively input into the trained supervised learning model. According to the model output results and the molecular property labels in the validation set, the accuracy is calculated and the training process is iterated, which can improve the prediction accuracy of the molecular property prediction model.

[0198] Furthermore, in some embodiments, considering the interactions between various compounds in naphtha and their respective target physical properties, and taking into account both linear and nonlinear relationships when the compounds are mixed, specifically, for molecular target properties with linear relationships, such as boiling point, the following formula can be used to determine different linear macroscopic properties of the target naphtha:

[0199] Among them, P b is the target linear macroscopic property of target naphtha, P i is the target property of the i-th molecule in the target naphtha, x i is the percentage of the i-th molecule in the target naphtha, and n is the number of each molecule in the target naphtha. The target property of the molecule corresponds to the target macroscopic property of the naphtha to be predicted. For example, if the target macroscopic property of the naphtha to be tested is the boiling point of the naphtha to be tested, the target property of the molecule is the boiling point of the molecule.

[0200] Furthermore, in some embodiments, target properties of various molecules in the naphtha to be measured (e.g., octane number, etc.) have nonlinear relationships. A molecular property hybrid model for determining naphtha macroscopic properties with linear and nonlinear relationships can be constructed using the following formula to ensure the accuracy of the obtained molecular properties:

[0201] Among them, ON Linear is a linear mixed submodel, ON NonLinear is the nonlinear correction submodel, h and g are the numbers of various compounds in different naphtha samples, and v h is the volume fraction of the hth compound, v g is the volume fraction of the g-th compound, ON h is the target property of the hth compound, ΔON hg is the target property of the hth compound after the hth compound is corrected based on the interaction between the hth compound and the gth compound, are the interaction parameters between the hth compound and the gth compound, respectively.

[0202] It should be noted that although the operations of the method of the present invention are described in a specific order in the above embodiments and drawings, this does not require or imply that these operations must be performed in this specific order, or that all illustrated operations must be performed to achieve the desired results. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0203] Corresponding to the above-mentioned method for rapid analysis of naphtha molecular components, some embodiments of this specification further provide a device for rapid analysis of naphtha molecular components. Referring to FIG. 14 , in some embodiments, the device may include:

[0204] The receiving module 1401 is used to receive the scanning spectrum data of the target naphtha;

[0205] a correction module 1402 configured to correct the scanned spectral data using a correction spectral dataset, wherein the correction spectral dataset is obtained by scanning a plurality of naphtha samples using a plurality of spectrometers under preset detection conditions, and the scanned spectral data is obtained by scanning a target naphtha using a first scanner of the plurality of spectrometers;

[0206] Determination module 1403 is used to match the molecular composition corresponding to the corrected scan spectrum data from a preset naphtha molecular composition library, and obtain the predicted molecular properties of the target naphtha based on the molecular composition, thereby determining the macroscopic properties of the target naphtha; wherein the naphtha molecular composition library uses comprehensive two-dimensional gas chromatography technology to determine the monomer hydrocarbon components of multiple naphtha samples, and is established based on the monomer hydrocarbon components of multiple naphtha samples.

[0207] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0208] It should be noted that in the embodiments of this specification, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user and fully authorized by all parties.

[0209] The embodiments of this specification also provide a computer device. As shown in Figure 15, in some embodiments of this specification, the computer device 1502 may include one or more processors 1504, such as one or more central processing units (CPUs) or graphics processing units (GPUs), and each processing unit may implement one or more hardware threads. The computer device 1502 may also include any memory 1506, which is used to store any type of information such as code, settings, data, etc. In a specific embodiment, the computer program on the memory 1506 and capable of running on the processor 1504, when the computer program is run by the processor 1504, can execute the instructions of the method described in any of the above embodiments. Non-limitingly, for example, the memory 1506 may include any one or more combinations of the following: any type of RAM, any type of ROM, a flash memory device, a hard disk, an optical disk, etc. More generally, any memory can use any technology to store information. Further, any memory can provide volatile or non-volatile retention of information. Further, any memory can represent a fixed or removable component of the computer device 1502. In one embodiment, when the processor 1504 executes the associated instructions stored in any memory or combination of memories, the computer device 1502 can perform any operation of the associated instructions. The computer device 1502 also includes one or more drive mechanisms 1508 for interacting with any memory, such as a hard disk drive mechanism, an optical disk drive mechanism, etc.

[0210] The computer device 1502 may also include an input / output interface 1510 (I / O) for receiving various inputs (via input devices 1512) and for providing various outputs (via output devices 1514). A specific output mechanism may include a presentation device 1516 and an associated graphical user interface 1518 (GUI). In other embodiments, the input / output interface 1510 (I / O), input devices 1512, and output devices 1514 may not be included, and the computer device 1502 may simply be a computer device in a network. The computer device 1502 may also include one or more network interfaces 1520 for exchanging data with other devices via one or more communication links 1522. One or more communication buses 1524 couple the components described above together.

[0211] The communication link 1522 may be implemented in any manner, for example, via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 1522 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0212] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), computer-readable storage media, and computer program products of some embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processor to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processor produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0213] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processor to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0214] These computer program instructions can also be loaded onto a computer or other programmable data processor so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0215] In a typical configuration, a computer device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0216] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0217] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computer device. As defined in this specification, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0218] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0219] Embodiments of this specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. Embodiments of this specification may also be practiced in distributed computing environments where tasks are performed by remote processors connected via a communications network. In distributed computing environments, program modules may be located in local and remote computer storage media, including storage devices.

[0220] It should also be understood that in the embodiments of this specification, the term "and / or" is merely a description of the association relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0221] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0222] In the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiments of this specification. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0223] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for rapid analysis of naphtha molecular components, characterized in that: The method comprises: receiving scanning spectrum data of target naphtha; The scanned spectrum data is corrected using a correction spectrum data set; wherein the correction spectrum data set is obtained by scanning a plurality of naphtha samples under preset detection conditions using a plurality of spectrometers, and the scanned spectrum data is obtained by scanning a target naphtha using a first scanner among the plurality of spectrometers; From a preset naphtha molecular composition library, the molecular composition corresponding to the corrected scanning spectral data is matched, and the predicted molecular properties of the target naphtha are obtained based on the molecular composition, thereby determining the macroscopic properties of the target naphtha; wherein the naphtha molecular composition library utilizes comprehensive two-dimensional gas chromatography technology to determine the monomer hydrocarbon components of a variety of naphtha samples, and is established based on the monomer hydrocarbon components of a variety of naphtha samples.

2. The method according to claim 1, characterized in that: The calibration spectrum data set includes at least first calibration spectrum data and second calibration spectrum data.

3. The method according to claim 1, characterized in that The calibration spectrum data set is constructed using the following steps: Scanning at least one naphtha sample using a first spectrometer to obtain first calibration spectrum data; Scanning at least one naphtha sample using a second spectrometer to obtain second calibration spectrum data; A corresponding correction spectrum data set is constructed according to the first correction spectrum data and the second correction spectrum data.

4. The method according to claim 1, characterized in that: The calibration spectrum data set is constructed using the following steps: Scanning at least one naphtha sample using a first spectrometer, performing a first preprocessing on the scanning result to obtain first corrected spectrum data; the first preprocessing at least includes a sharpening process; Scanning at least one naphtha sample using a second spectrometer, and performing a second preprocessing on the scanning result to obtain second correction spectrum data; the second preprocessing at least includes sharpening processing; A corresponding correction spectrum data set is constructed according to the first correction spectrum data and the second correction spectrum data.

5. The method according to claim 3 or 4, characterized in that: The first spectrometer and the second spectrometer are Fourier transform near infrared spectrometers; The first spectrometer and the second spectrometer scan multiple naphtha samples under the following preset detection conditions: Using transmission measurement method; Scanning resolution no less than 8cm -1 ; The scanning wave number range is 4000cm -1 ~10000cm -1 ; The cumulative number of scans is at least 64.

6. The method according to claim 3 or 4, characterized in that: The method of correcting the scanned spectrum data by using the correction spectrum data set includes: Selecting the spectrum data to be fitted corresponding to the scanned spectrum data from the first corrected spectrum data; Determining fitting parameters according to the spectrum data to be fitted and the scanned spectrum data; The scanned spectrum data is corrected according to the fitting parameters and the second corrected spectrum data.

7. The method according to claim 6, characterized in that The step of determining fitting parameters according to the spectrum data to be fitted and the scanned spectrum data comprises: According to the spectrum data to be fitted and the scanned spectrum data, the fitting parameters are determined using the following formula: Among them, X1 is the scanned spectrum data, n is the amount of spectrum data to be fitted, i is the ordinal number of the spectrum data to be fitted, ω 1i is the i-th fitting parameter, X 1i is the ith spectrum data to be fitted.

8. The method according to claim 7, characterized in that The step of determining fitting parameters according to the spectrum data to be fitted and the scanned spectrum data further comprises: Establishing an objective function according to the spectrum data to be fitted and the second corrected spectrum data; Iterating the objective function using a preset interval of iterative data volume; The data amount of the spectrogram data to be fitted is determined according to the iterative data amount corresponding to the minimum iterative output result.

9. The method according to claim 8, characterized in that The objective function is established using the following formula: Among them, c m is the output value of the objective function, m is the iterative data amount of the spectrum data to be fitted, i is the ordinal number of the spectrum data to be fitted, is the i-th fitting parameter, is the i-th spectrum data corresponding to the i-th spectrum data to be fitted in the second correction spectrum data, X b It is the real spectrum data obtained by scanning the target naphtha using the second spectrometer.

10. The method according to claim 6, characterized in that The step of correcting the scanned spectrum data according to the fitting parameters and the second corrected spectrum data comprises: According to the fitting parameters and the second correction spectrum data, the scanning spectrum data is corrected using the following formula: in, is the corrected scanning spectrum data, n is the data volume of the fitting parameter, i is the ordinal number of the fitting parameter, ω 1i is the i-th fitting parameter, X 2i is the i-th spectrum data corresponding to the i-th spectrum data to be fitted in the second correction spectrum data.

11. The method according to claim 2, characterized in that From the preset naphtha molecular composition library, match the molecular composition corresponding to the calibrated scan spectrum data, including: Selecting the to-be-matched spectrum data corresponding to the scanned spectrum data from the second corrected spectrum data; Determining matching parameters according to the spectrum data to be matched and the corrected scanning spectrum data; Searching for a molecular composition to be matched corresponding to the spectrum data to be matched from a preset naphtha molecular composition library; The molecular composition corresponding to the corrected scanning spectrum data is determined according to the matching parameters and the molecular composition to be matched.

12. The method according to claim 11, characterized in that According to the spectrum data to be matched and the corrected scan spectrum data, matching parameters are determined, including: According to the spectrum data to be matched and the corrected scan spectrum data, the matching parameters are determined using the following formula: in, is the corrected scanning spectrum data, l is the data volume of the matching parameter, j is the ordinal number of the matching parameter, ω 2j is the jth matching parameter, X 2j is the j-th spectrum data in the second correction spectrum data corresponding to the j-th spectrum data to be matched.

13. The method according to claim 12, characterized in that The step of determining matching parameters according to the to-be-matched spectrum data and the corrected scan spectrum data further comprises: Establishing an optimization function according to the to-be-matched spectrum data and the second corrected spectrum data; Iterating the optimization function using a preset interval of iterative data volume; The matching parameter is determined according to the amount of iterative data corresponding to the minimum iterative output result.

14. The method according to claim 13, characterized in that The optimization function is established using the following formula: Among them, p k is the output value of the optimization function, k is the iterative data amount of the spectrum data to be matched, i is the ordinal number of the spectrum data to be matched, is the i-th matching parameter, z i is the molecular composition of the i-th naphtha sample in the naphtha molecular composition library corresponding to the i-th spectrum data to be matched, z b The real molecular composition of the target naphtha was obtained by using comprehensive two-dimensional gas chromatography technology.

15. The method according to claim 11, characterized in that Determining the molecular composition corresponding to the corrected scan spectrum data according to the matching parameters and the molecular composition to be matched includes: According to the matching parameters and the molecular composition to be matched, the molecular composition corresponding to the corrected scan spectrum data is determined using the following formula: Where z is the molecular composition of the target naphtha, l is the data volume of the matching parameter, and i is the ordinal number of the matching parameter. is the i-th matching parameter, z i is the molecular composition of the i-th naphtha sample corresponding to the i-th spectrum data to be matched in the naphtha molecular composition library.

16. The method according to claim 1, characterized in that The preset naphtha molecular composition library is established according to the following steps: Using comprehensive two-dimensional gas chromatography technology, various naphtha samples were tested to obtain the monomer hydrocarbon components of various naphtha samples; The naphtha molecular composition library is established according to monomer hydrocarbon components of a plurality of naphtha samples.

17. The method according to claim 1, characterized in that The predicted molecular properties of the target naphtha are obtained according to the molecular composition, thereby determining the macroscopic properties of the target naphtha, including: Determine the molecular structure group information corresponding to the molecular composition; the molecular structure group information at least includes the basic group and the combined group of the molecular structure; Inputting the molecular structure group information into a preset molecular property prediction model to obtain predicted molecular properties of the target naphtha; The predicted molecular properties are input into a preset molecular property mixing model to obtain the macroscopic properties of the target naphtha.

18. The method according to claim 17, characterized in that The preset molecular property prediction model is trained in the following manner: Get historical naphtha analysis data; The molecular structure group information in the historical naphtha analysis data is used as input, and the molecular property labels in the historical naphtha analysis data are used as output to construct training samples, and a supervised learning model is constructed based on the input and output; The supervised learning model is trained using the training samples, and the trained supervised learning model is used as a molecular property prediction model.

19. The method according to claim 18, characterized in that Training the supervised learning model using the training samples includes: Dividing the training samples into a training set and a validation set; Training the supervised learning model using the training set; Input the molecular structure group information in the validation set into the trained supervised learning model; Calculate the prediction accuracy based on the output of the supervised learning model and the molecular property labels in the validation set; If the prediction accuracy is less than a set threshold, the supervised learning model is retrained until the prediction accuracy is not less than the set threshold.

20. The method according to claim 17, characterized in that The molecular property mixing model is constructed using the following formula: Among them, ON Linear is a linear mixed submodel, ON NonLinear is the nonlinear correction submodel, h and g are the numbers of various compounds in different naphtha samples, and v h is the volume fraction of the hth compound, v g is the volume fraction of the g-th compound, ON h is the target property of the hth compound, ΔON hg is the target property of the hth compound after the hth compound is corrected based on the interaction between the hth compound and the gth compound, are the interaction parameters between the hth compound and the gth compound, respectively.

21. A device for rapid analysis of naphtha molecular components, characterized in that: The device comprises: A receiving module, used for receiving scanning spectrum data of target naphtha; A correction module, used to correct the scanned spectrum data using a correction spectrum data set; wherein the correction spectrum data set is obtained by scanning a plurality of naphtha samples using a plurality of spectrometers under preset detection conditions, and the scanned spectrum data is obtained by scanning a target naphtha using a first scanner among the plurality of spectrometers; A determination module is used to match the molecular composition corresponding to the corrected scanning spectral data from a preset naphtha molecular composition library, and obtain the predicted molecular properties of the target naphtha based on the molecular composition, thereby determining the macroscopic properties of the target naphtha; wherein the naphtha molecular composition library uses full two-dimensional gas chromatography technology to determine the monomer hydrocarbon components of a variety of naphtha samples, and is established based on the monomer hydrocarbon components of a variety of naphtha samples.

22. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: When the computer program is executed by the processor, the computer program executes the instructions of the method according to any one of claims 1 to 20.

23. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor of a computer device, the computer program executes instructions of the method according to any one of claims 1 to 20.

24. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the instructions of the method according to any one of claims 1 to 20 are executed.

Images