Big data-based origin traceability method and system

Abstract

The invention relates to the technical field of crude oil detection, in particular to a production place tracing method and system based on big data, and the method provided by the invention comprises the steps: obtaining spectral variation characteristics, calculating spectral variation characterization parameters for current to-be-detected crude oil, and determining the spectral variation category of the current to-be-detected crude oil. According to the spectrum variation characterization parameters, determining the beam diameter and the sample scanning time when spectrum analysis is carried out on the crude oil to be detected, determining spectrum data obtained in a preset time, and comparing obtained spectrum data fragments after the spectrum data is segmented in a time domain dimension, whether spectral analysis meets the standard or not is judged according to the similarity between the spectral data fragments, so that the scanning speed of the spectrograph is adjusted, the spectral data are obtained again and stored, or initial operation parameters of the spectrograph are maintained, and the spectral data are obtained and stored; the origin of the current crude oil to be detected is traced according to the similarity comparison result of the stored spectral data and the spectral data of the samples corresponding to the origin, so that the traceability accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of crude oil detection, and in particular to a method and system for tracing the origin of crude oil based on big data. Background Art

[0002] Spectrometers are important tools in the process of tracing the origin of crude oil. This is because crude oil from different origins has different chemical compositions, and the various chemical components in crude oil have unique absorption and emission characteristics for specific wavelengths of light. By analyzing these spectral characteristics, the presence and concentration of specific components in crude oil can be identified, thereby inferring the origin of the crude oil, which is of great significance to the authenticity and security of crude oil trade.

[0003] Chinese patent publication number: CN114280000A, discloses a method and system for tracing the origin based on big data. The method provided includes collecting crude oil samples from different countries and obtaining sample terahertz spectra of the crude oil samples; using a continuous wavelet algorithm to transform the sample terahertz spectrum into a wavelet space, extracting features from the wavelet space through cluster analysis and deep learning methods, and constructing a standard spectrum library of crude oil samples from different countries based on the weighted least squares method, and tracing the origin of the crude oil samples based on the standard spectrum library; the system includes a data acquisition module, a first data processing module, a second data processing module, a data storage module, and a display module; the device includes a terahertz time-domain spectrometer, a data processing and analysis device, and a display device; the advantage of the present invention is that the method of the present invention is simple, has strong structure and logic, and has a high traceability accuracy, providing a new technical idea for crude oil traceability.

[0004] However, there are still the following problems in the prior art:

[0005] When tracing the origin of crude oil, the accuracy of spectral data is required to be high. However, in actual situations, the particle size dispersion in crude oil will affect the transmittance and reflectivity of light, and the viscosity will lead to enhanced interactions between particles. The combination of the above factors can easily lead to spectral anomalies and inconsistency in spectrometer measurement results, reducing the accuracy of crude oil tracing. Summary of the invention

[0006] To this end, the present invention provides a method and system for tracing the origin of crude oil based on big data, which is used to solve the problem that in actual situations, the particle size dispersion in crude oil will affect the transmittance and reflectivity of light, and the viscosity will lead to enhanced interaction between particles. The combination of the above factors can easily lead to spectral abnormalities and inconsistency in spectrometer measurement results, thereby reducing the accuracy of crude oil origin tracing.

[0007] To achieve the above objectives, the present invention provides, on one hand, a method for tracing the origin of an item based on big data, which comprises:

[0008] Step S1, extracting an analysis sample from the crude oil to be tested, analyzing it, and obtaining spectral variation characteristics, wherein the analysis includes placing the analysis sample in a detection plane, obtaining particle size information of different regions of the analysis sample to obtain particle size dispersion, and measuring the viscosity of the analysis sample;

[0009] Step S2, calculating the spectral variation characterization parameter for the current crude oil to be tested according to the spectral variation characteristics, so as to determine the spectral variation category of the current crude oil to be tested;

[0010] Step S3, performing spectral analysis according to the spectral variation category of the currently tested crude oil to obtain spectral data, including:

[0011] Determine the beam diameter and sample scanning time for spectral analysis of the crude oil to be tested according to the spectral variation characterization parameter, determine the spectral data acquired within a predetermined time, compare the obtained spectral data segments after segmenting the spectral data in the time domain dimension, determine whether the spectral analysis meets the standard according to the similarity between the spectral data segments, adjust the scanning speed of the spectrometer, acquire the spectral data again and store it;

[0012] Or, maintaining the initial operating parameters of the spectrometer to obtain and store spectral data;

[0013] Step S4, tracing the origin of the current crude oil to be tested based on the similarity comparison result between the stored spectral data and the spectral data of the samples corresponding to each origin.

[0014] Furthermore, in step S1, the process of determining the particle size dispersion includes:

[0015] Determine the particle size information of different areas in the analysis sample to calculate the variance of the particle size information;

[0016] The square root of the variance was determined as the particle size dispersion.

[0017] Furthermore, in step S2, the process of calculating the spectral variation characterization parameter for the currently tested crude oil includes:

[0018] Determine the ratio of the reference particle size dispersion to the crude oil particle size dispersion as the first influencing parameter;

[0019] Determine the ratio of the crude oil viscosity to the benchmark crude oil viscosity as the second influencing parameter;

[0020] The weighted sum of the first influencing parameter and the second influencing parameter is determined as the spectral variation characterization parameter.

[0021] Furthermore, in step S2, the process of determining the spectral variation category of the currently tested crude oil includes:

[0022] If the spectral variation characterization parameter is greater than the spectral variation characterization parameter threshold, the spectral variation category is determined to be a strong variation category;

[0023] If the spectral variation characterization parameter is less than or equal to the spectral variation characterization parameter threshold, the spectral variation category is determined to be a weak variation category.

[0024] Furthermore, in step S3, spectral analysis is performed according to the spectral variation category of the currently tested crude oil, wherein:

[0025] If the spectrum variation category of the current crude oil to be tested is a strong variation category, the beam diameter and the sample scanning time when performing spectrum analysis on the crude oil to be tested are determined according to the spectrum variation characterization parameter, the spectrum data acquired within a predetermined time is determined, the spectrum data is segmented in the time domain dimension, and the obtained spectrum data segments are compared, and whether the spectrum analysis meets the standard is determined according to the similarity between the spectrum data segments, so as to adjust the scanning speed of the spectrometer, and acquire and store the spectrum data again;

[0026] Alternatively, the spectrometer is maintained at its initial operating parameters to acquire and store spectral data.

[0027] Furthermore, in step S3, the beam diameter and sample scanning time for spectral analysis of the crude oil to be tested are determined, wherein:

[0028] The beam diameter is negatively correlated with the spectral variation characterization parameter;

[0029] The sample scanning time is related to the spectral variation characterization parameter.

[0030] Furthermore, in step S3, the process of determining whether the spectral analysis meets the standard includes:

[0031] If the similarity between the spectral data segments is greater than or equal to the reference similarity, the spectral analysis is determined to meet the standard;

[0032] If the similarity between the spectral data segments is less than the reference similarity, it is determined that the spectral analysis does not meet the standard.

[0033] Furthermore, in step S3, the scanning speed of the spectrometer is adjusted, wherein:

[0034] If the average similarity between the spectral data segments is less than the benchmark similarity, reduce the scanning speed of the spectrometer;

[0035] If the average similarity between the spectral data segments is greater than or equal to the benchmark similarity, the scanning speed of the spectrometer is maintained.

[0036] Furthermore, in step S4, the process of tracing the origin of the current crude oil to be tested includes:

[0037] Calling the stored spectrum data of the crude oil to be tested;

[0038] Determine the similarity between the stored spectral data and the spectral data of the corresponding samples from each origin;

[0039] It is determined that the origin of the sample spectrum data corresponding to the maximum similarity is the origin of the current crude oil to be tested.

[0040] On the other hand, a crude oil origin tracing system is provided, which comprises:

[0041] A feature extraction module is used to extract an analysis sample from the crude oil to be tested, analyze it, and obtain spectral variation characteristics. The analysis includes placing the analysis sample in a detection plane, obtaining particle size information of different regions of the analysis sample to obtain particle size dispersion, and measuring the viscosity of the analysis sample;

[0042] An abnormality response module, which is connected to the sample analysis module and is used to calculate the spectral abnormality characterization parameter for the current crude oil to be tested according to the spectral abnormality characteristics, so as to determine the spectral abnormality category of the current crude oil to be tested;

[0043] The data analysis module is connected to the abnormal change response module and is used to perform spectral analysis and obtain spectral data according to the spectral abnormal change category of the current crude oil to be tested, including:

[0044] Determine the beam diameter and sample scanning time for spectral analysis of the crude oil to be tested according to the spectral variation characterization parameter, determine the spectral data acquired within a predetermined time, compare the obtained spectral data segments after segmenting the spectral data in the time domain dimension, determine whether the spectral analysis meets the standard according to the similarity between the spectral data segments, adjust the scanning speed of the spectrometer, acquire the spectral data again and store it;

[0045] Or, maintaining the initial operating parameters of the spectrometer to obtain and store spectral data;

[0046] The origin tracing module is connected to the data analysis module and is used to trace the origin of the current crude oil to be tested based on the similarity comparison result between the stored spectral data and the spectral data of the corresponding samples of each origin.

[0047] Compared with the prior art, the method provided by the present invention includes obtaining spectral variation characteristics, calculating spectral variation characterization parameters for the current crude oil to be tested, determining the spectral variation category of the current crude oil to be tested, determining the beam diameter and sample scanning time when performing spectral analysis on the crude oil to be tested according to the spectral variation characterization parameters, determining the spectral data obtained within a predetermined time, comparing the obtained spectral data segments after segmenting the spectral data in the time domain dimension, determining whether the spectral analysis meets the standard according to the similarity between the spectral data segments, adjusting the scanning speed of the spectrometer, obtaining and storing the spectral data again, or maintaining the initial operating parameters of the spectrometer to obtain and store the spectral data, tracing the origin of the current crude oil to be tested according to the similarity comparison result between the stored spectral data and the spectral data of the corresponding samples of each origin, thereby improving the accuracy of tracing.

[0048] In particular, the present invention calculates the spectral variation characterization parameters for the current crude oil to be tested. In the process of tracing the origin of crude oil, when the crude oil is subjected to spectral analysis, the particle size dispersion in the crude oil will affect the transmittance and reflectivity of light, and the viscosity will lead to enhanced interaction between particles, causing the spectral data to mutate. In this case, differences will occur in the analysis results of the spectrometer, resulting in inconsistent spectral data when analyzing the same crude oil. Based on this, the present invention calculates the spectral variation characterization parameters to determine the spectral variation category of the crude oil to be tested, and determines the spectral analysis method suitable for each category of crude oil, thereby improving the pertinence of crude oil analysis and the accuracy of crude oil origin tracing.

[0049] In particular, the present invention determines the beam diameter and sample scanning time for spectral analysis of the crude oil to be tested based on the spectral variation characterization parameters. In actual analysis, for the crude oil to be tested of the strong variation category, if the preset beam diameter and scanning time are still maintained, the analysis results of the spectrometer for the crude oil to be tested will be different, resulting in inconsistent spectral data. Based on this, the present invention determines the beam diameter and sample scanning time. Preferably, reducing the beam diameter of the spectrometer can reduce the number of times the crude oil is scattered, and increasing the scanning time can increase the signal-to-noise ratio of the spectral data, thereby improving the pertinence of the crude oil analysis and the accuracy of tracing the origin of the crude oil.

[0050] In particular, the present invention adjusts the scanning speed of the spectrometer to make the spectral analysis meet the standards. In actual situations, during the spectral analysis of crude oil, if the scanning speed of the spectrometer is too fast, it may lead to incomplete signal acquisition. If the scanning speed of the spectrometer is too slow, it may cause the collected data points to change slowly. Both situations will cause some spectral data segments to be abnormal. The abnormal segments may affect the accuracy of crude oil origin tracing. Based on this, the present invention considers adjusting the scanning speed of the spectrometer, re-analyzing and storing the spectral data with abnormal segments, thereby improving the pertinence of crude oil analysis and the accuracy of crude oil origin tracing. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A schematic diagram of the method steps of the origin tracing method based on big data according to an embodiment of the invention;

[0052] Figure 2 A logic block diagram for determining the spectral variation category of the crude oil to be tested in the embodiment of the invention;

[0053] Figure 3 A logic block diagram for determining whether the spectrum analysis of an embodiment of the invention complies with the standard;

[0054] Figure 4 A schematic diagram of the structure of a crude oil origin tracing system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0056] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0057] It should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0058] See also Figures 1 to 4 As shown, Figure 1 This is a schematic diagram of the method steps of the origin tracing method based on big data according to an embodiment of the invention. Figure 2The logic block diagram for determining the spectral variation category of the crude oil to be tested in the embodiment of the present invention is as follows: Figure 3 To determine whether the spectrum analysis of the embodiment of the invention meets the standard logic block diagram, Figure 4 The structural diagram of the crude oil origin tracing system of the embodiment of the invention is as follows: the origin tracing method based on big data of the invention comprises:

[0059] Step S1, extracting an analysis sample from the crude oil to be tested, analyzing it, and obtaining spectral variation characteristics. The analysis includes placing the analysis sample in a detection plane, obtaining particle size information of different areas of the analysis sample to obtain particle size dispersion, and measuring the viscosity of the analysis sample. It can be understood that there are many types of spectrometers for analyzing the analysis sample. Those skilled in the art can select a spectrometer based on actual conditions, which will not be described in detail.

[0060] Step S2, calculating the spectral variation characterization parameter for the current crude oil to be tested according to the spectral variation characteristics, so as to determine the spectral variation category of the current crude oil to be tested;

[0061] Step S3, performing spectral analysis according to the spectral variation category of the currently tested crude oil to obtain spectral data, including:

[0062] Determine the beam diameter and sample scanning time for spectral analysis of the crude oil to be tested according to the spectral variation characterization parameter, determine the spectral data acquired within a predetermined time, compare the obtained spectral data segments after segmenting the spectral data in the time domain dimension, determine whether the spectral analysis meets the standard according to the similarity between the spectral data segments, adjust the scanning speed of the spectrometer, acquire the spectral data again and store it;

[0063] Or, maintaining the initial operating parameters of the spectrometer to obtain and store spectral data;

[0064] Step S4, tracing the origin of the current crude oil to be tested based on the similarity comparison result between the stored spectral data and the spectral data of the samples corresponding to each origin.

[0065] Specifically, before analyzing the sample, a series of preparations need to be performed, including shaking, etc., to ensure the uniformity of the sample. This is existing technology and will not be described in detail.

[0066] Specifically, there is no limitation on the specific method for determining the similarity of spectral data. For example, the Spectral Angle Mapper (SAM) algorithm can be used to solve the similarity between spectral data. Of course, other methods can also be used, and those skilled in the art can freely choose, which will not be described in detail.

[0067] It can be understood that the scanning time refers to the total time required for the spectrometer to complete a full frequency range scan and record all data, and the scanning speed is the number of complete spectra that the spectrometer can collect per unit time.

[0068] Specifically, in step S1, the process of determining the particle size dispersion includes:

[0069] Determine the particle size information of different areas in the analysis sample to calculate the variance of the particle size information;

[0070] The square root of the variance was determined as the particle size dispersion.

[0071] Specifically, the particle size information includes the average particle size of the analyzed samples in the region. The particle size information can be measured by a laser particle size analyzer, which will not be described in detail here.

[0072] Specifically, in step S2, the process of calculating the spectral variation characterization parameter for the current crude oil to be tested includes:

[0073] Determine the ratio of the reference particle size dispersion to the crude oil particle size dispersion as the first influencing parameter;

[0074] Determine the ratio of the crude oil viscosity to the benchmark crude oil viscosity as the second influencing parameter;

[0075] The weighted sum of the first influencing parameter and the second influencing parameter is determined as the spectral variation characterization parameter.

[0076] Specifically, the reference particle size dispersion is pre-set, wherein a number of crude oil samples are obtained in advance for analysis, and the mean particle size dispersion of the number of crude oil samples is obtained, and the reference particle size dispersion is set within 1.15 times to 1.25 times the mean particle size dispersion.

[0077] Specifically, the benchmark crude oil viscosity is pre-set, wherein a number of crude oil samples are obtained in advance for analysis, and an average crude oil viscosity of the crude oil samples is obtained, and the benchmark crude oil viscosity is set within 1.1 times to 1.23 times the average crude oil viscosity.

[0078] Specifically, the weight coefficient of the first influencing parameter is 0.43, and the weight coefficient of the second influencing parameter is 0.57.

[0079] Specifically, the present invention calculates the spectral variation characterization parameters for the current crude oil to be tested. In the process of tracing the origin of crude oil, when spectrally analyzing the crude oil, the particle size dispersion in the crude oil will affect the transmittance and reflectivity of light, and the viscosity will cause the interaction between particles to be enhanced, causing the spectral data to mutate. In this case, it will cause differences in the analysis results of the spectrometer, resulting in inconsistent spectral data when analyzing the same crude oil. Based on this, the present invention calculates the spectral variation characterization parameters to determine the spectral variation category of the crude oil to be tested, and determines the spectral analysis method suitable for each category of crude oil, thereby improving the pertinence of crude oil analysis and the accuracy of crude oil origin tracing.

[0080] Specifically, in step S2, the process of determining the spectral variation category of the currently tested crude oil includes:

[0081] If the spectral variation characterization parameter is greater than the spectral variation characterization parameter threshold, the spectral variation category is determined to be a strong variation category;

[0082] If the spectral variation characterization parameter is less than or equal to the spectral variation characterization parameter threshold, the spectral variation category is determined to be a weak variation category.

[0083] Specifically, the threshold of the spectral variation characterization parameter is determined in the interval [1.12, 1.38].

[0084] Specifically, in step S3, spectral analysis is performed according to the spectral variation category of the crude oil to be tested, wherein:

[0085] If the spectrum variation category of the current crude oil to be tested is a strong variation category, the beam diameter and the sample scanning time when performing spectrum analysis on the crude oil to be tested are determined according to the spectrum variation characterization parameter, the spectrum data acquired within a predetermined time is determined, the spectrum data is segmented in the time domain dimension, and the obtained spectrum data segments are compared, and whether the spectrum analysis meets the standard is determined according to the similarity between the spectrum data segments, so as to adjust the scanning speed of the spectrometer, and acquire and store the spectrum data again;

[0086] Alternatively, the spectrometer is maintained at its initial operating parameters to acquire and store spectral data.

[0087] Specifically, the beam diameter may cause differences in spectral results. A beam diameter that is too large will lead to more light reflection, which will aggravate the spectral variation effect for crude oil with strong variation. Therefore, the beam diameter is adaptively determined based on the spectral variation characterization parameters.

[0088] Specifically, when the crude oil to be tested is of the strong variability category, the particle size dispersion in the crude oil is relatively high, which is easy to affect the transmittance and reflectivity of light. The high viscosity will lead to enhanced interaction between particles, affecting the variability of spectral data. Under the influence of the above factors, the scanning time during sample scanning is more critical and can easily affect the accuracy of the measurement results. For example, too little sample scanning time will lead to a reduction in the number of sampling points of spectral data, affecting the resolution and detail performance of the spectrum. Therefore, the sample scanning time is determined based on the adaptability of the spectral variability characterization parameters.

[0089] Specifically, the predetermined time is 20% of the sample scanning time.

[0090] Specifically, in step S3, the beam diameter and sample scanning time for spectral analysis of the crude oil to be tested are determined, wherein:

[0091] The beam diameter is negatively correlated with the spectral variation characterization parameter;

[0092] The sample scanning time is positively correlated with the spectral variation characterization parameter.

[0093] Specifically, when the spectral variation characterization parameter is greater than or equal to 1.5 times the spectral variation characterization parameter threshold, the beam diameter is 0.85 times the initial beam diameter, and the sample scanning time is 1.25 times the initial sample scanning time;

[0094] When the spectral variation characterization parameter is greater than 1.2 times the spectral variation characterization parameter threshold and less than 1.5 times the spectral variation characterization parameter threshold, the beam diameter is the initial beam diameter, and the sample scanning time is the initial sample scanning time;

[0095] When the spectral variation characterization parameter is less than or equal to 1.2 times the spectral variation characterization parameter threshold, the beam diameter is 1.25 times the reference beam diameter, and the sample scanning time is 0.85 times the initial sample scanning time.

[0096] Specifically, the present invention determines the beam diameter and sample scanning time for spectral analysis of the crude oil to be tested based on the spectral variation characterization parameters. In actual analysis, for the crude oil to be tested of the strong variation category, if the preset beam diameter and scanning time are still maintained, the analysis results of the spectrometer for the crude oil to be tested will be different, resulting in inconsistent spectral data. Based on this, the present invention determines the beam diameter and sample scanning time. Preferably, reducing the beam diameter of the spectrometer can reduce the number of times the crude oil is scattered, and increasing the scanning time can increase the signal-to-noise ratio of the spectral data, thereby improving the pertinence of the crude oil analysis and the accuracy of tracing the origin of the crude oil.

[0097] Specifically, in step S3, the process of determining whether the spectral analysis meets the standard includes:

[0098] If the similarity between the spectral data segments is greater than or equal to the reference similarity, the spectral analysis is determined to meet the standard;

[0099] If the similarity between the spectral data segments is less than the reference similarity, it is determined that the spectral analysis does not meet the standard.

[0100] Specifically, the benchmark similarity is preset, wherein a number of spectral data segments are obtained in advance for analysis, and the average similarity between the number of spectral data segments is obtained, and the benchmark similarity is set within 0.9 times to 1.2 times of the similarity average.

[0101] Specifically, in step S3, the scanning speed of the spectrometer is adjusted, wherein:

[0102] If the mean similarity between spectral data segments is less than the benchmark similarity, reducing the scanning speed of the spectrometer can improve the signal-to-noise ratio, reduce the error of rapid scanning, and reduce spectral variation.

[0103] If the average similarity between the spectral data segments is greater than or equal to the benchmark similarity, the scanning speed of the spectrometer is maintained.

[0104] Specifically, the present invention adjusts the scanning speed of the spectrometer so that the spectral analysis meets the standard. In actual situations, during the spectral analysis of crude oil, if the scanning speed of the spectrometer is too fast, it may lead to incomplete signal acquisition. If the scanning speed of the spectrometer is too slow, it may cause the collected data points to change slowly. Both situations will cause some spectral data segments to be abnormal. The abnormal segments may affect the accuracy of crude oil origin tracing. Based on this, the present invention considers adjusting the scanning speed of the spectrometer, re-analyzing and storing the spectral data with abnormal segments, thereby improving the pertinence of crude oil analysis and the accuracy of crude oil origin tracing.

[0105] Specifically, in step S4, the process of tracing the origin of the current crude oil to be tested includes:

[0106] Calling the stored spectrum data of the crude oil to be tested;

[0107] Determine the similarity between the stored spectral data and the spectral data of the corresponding samples from each origin;

[0108] It is determined that the origin of the sample spectrum data corresponding to the maximum similarity is the origin of the current crude oil to be tested.

[0109] The sample spectral data can be obtained by technicians in this field by pre-collecting spectral data corresponding to crude oil from various origins, which will not be described in detail here.

[0110] It is understandable that, in order to facilitate data acquisition, the collected sample spectral data may be stored in a crude oil fingerprint database, and the sample spectral data corresponds one-to-one to the crude oil production area.

[0111] Specifically, it also includes the crude oil origin traceability system, which includes:

[0112] A feature extraction module is used to extract an analysis sample from the crude oil to be tested, analyze it, and obtain spectral variation characteristics. The analysis includes placing the analysis sample in a detection plane, obtaining particle size information of different regions of the analysis sample to obtain particle size dispersion, and measuring the viscosity of the analysis sample;

[0113] An abnormality response module, which is connected to the sample analysis module and is used to calculate the spectral abnormality characterization parameter for the current crude oil to be tested according to the spectral abnormality characteristics, so as to determine the spectral abnormality category of the current crude oil to be tested;

[0114] The data analysis module is connected to the abnormal change response module and is used to perform spectral analysis and obtain spectral data according to the spectral abnormal change category of the current crude oil to be tested, including:

[0115] Determine the beam diameter and sample scanning time for spectral analysis of the crude oil to be tested according to the spectral variation characterization parameter, determine the spectral data acquired within a predetermined time, compare the obtained spectral data segments after segmenting the spectral data in the time domain dimension, determine whether the spectral analysis meets the standard according to the similarity between the spectral data segments, adjust the scanning speed of the spectrometer, acquire the spectral data again and store it;

[0116] Or, maintaining the initial operating parameters of the spectrometer to obtain and store spectral data;

[0117] The origin tracing module is connected to the data analysis module and is used to trace the origin of the current crude oil to be tested based on the similarity comparison result between the stored spectral data and the spectral data of the corresponding samples of each origin.

[0118] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A method for tracing origin based on big data, characterized in that: include: Step S1, extracting an analysis sample from the crude oil to be tested, analyzing it, and obtaining spectral variation characteristics, wherein the analysis includes placing the analysis sample in a detection plane, obtaining particle size information of different regions of the analysis sample to obtain particle size dispersion, and measuring the viscosity of the analysis sample; Step S2, calculating the spectral variation characterization parameter for the current crude oil to be tested according to the spectral variation characteristics, so as to determine the spectral variation category of the current crude oil to be tested; Step S3, performing spectral analysis according to the spectral variation category of the currently tested crude oil to obtain spectral data, including: Determine the beam diameter and sample scanning time for spectral analysis of the crude oil to be tested according to the spectral variation characterization parameter, determine the spectral data acquired within a predetermined time, compare the obtained spectral data segments after segmenting the spectral data in the time domain dimension, determine whether the spectral analysis meets the standard according to the similarity between the spectral data segments, adjust the scanning speed of the spectrometer, acquire the spectral data again and store it; Or, maintaining the initial operating parameters of the spectrometer to obtain and store spectral data; Step S4, tracing the origin of the current crude oil to be tested based on the similarity comparison result between the stored spectral data and the spectral data of the samples corresponding to each origin.

2. The origin tracing method based on big data according to claim 1 is characterized in that: In step S1, the process of determining the particle size dispersion includes: Determine the particle size information of different areas in the analysis sample to calculate the variance of the particle size information; The square root of the variance was determined as the particle size dispersion.

3. The origin tracing method based on big data according to claim 1 is characterized in that: In step S2, the process of calculating the spectral variation characterization parameter for the current crude oil to be tested includes: Determine the ratio of the reference particle size dispersion to the crude oil particle size dispersion as the first influencing parameter; Determine the ratio of the crude oil viscosity to the benchmark crude oil viscosity as the second influencing parameter; The weighted sum of the first influencing parameter and the second influencing parameter is determined as the spectral variation characterization parameter.

4. The origin tracing method based on big data according to claim 1 is characterized in that: In step S2, the process of determining the spectral variation category of the currently tested crude oil includes: If the spectral variation characterization parameter is greater than the spectral variation characterization parameter threshold, the spectral variation category is determined to be a strong variation category; If the spectral variation characterization parameter is less than or equal to the spectral variation characterization parameter threshold, the spectral variation category is determined to be a weak variation category.

5. The origin tracing method based on big data according to claim 1 is characterized in that: In step S3, spectral analysis is performed according to the spectral variation category of the crude oil to be tested, wherein: If the spectrum variation category of the current crude oil to be tested is a strong variation category, the beam diameter and the sample scanning time when performing spectrum analysis on the crude oil to be tested are determined according to the spectrum variation characterization parameter, the spectrum data acquired within a predetermined time is determined, the spectrum data is segmented in the time domain dimension, and the obtained spectrum data segments are compared, and whether the spectrum analysis meets the standard is determined according to the similarity between the spectrum data segments, so as to adjust the scanning speed of the spectrometer, and acquire and store the spectrum data again; Alternatively, the spectrometer is maintained at its initial operating parameters to acquire and store spectral data.

6. The origin tracing method based on big data according to claim 1 is characterized in that: In step S3, the beam diameter and sample scanning time for spectral analysis of the crude oil to be tested are determined, wherein: The beam diameter is negatively correlated with the spectral variation characterization parameter; The sample scanning time is positively correlated with the spectral variation characterization parameter.

7. The origin tracing method based on big data according to claim 1 is characterized in that: In step S3, the process of determining whether the spectral analysis meets the standard includes: If the similarity between the spectral data segments is greater than or equal to the reference similarity, the spectral analysis is determined to meet the standard; If the similarity between the spectral data segments is less than the reference similarity, it is determined that the spectral analysis does not meet the standard.

8. The origin tracing method based on big data according to claim 1 is characterized in that: In step S3, the scanning speed of the spectrometer is adjusted, wherein: If the average similarity between the spectral data segments is less than the benchmark similarity, reduce the scanning speed of the spectrometer; If the average similarity between the spectral data segments is greater than or equal to the benchmark similarity, the scanning speed of the spectrometer is maintained.

9. The origin tracing method based on big data according to claim 1 is characterized in that: In step S4, the process of tracing the origin of the current crude oil to be tested includes: Calling the stored spectrum data of the crude oil to be tested; Determine the similarity between the stored spectral data and the spectral data of the corresponding samples from each origin; It is determined that the origin of the sample spectrum data corresponding to the maximum similarity is the origin of the current crude oil to be tested.

10. A system using the origin tracing method based on big data according to any one of claims 1 to 9, characterized in that: include, A feature extraction module is used to extract an analysis sample from the crude oil to be tested, analyze it, and obtain spectral variation characteristics. The analysis includes placing the analysis sample in a detection plane, obtaining particle size information of different regions of the analysis sample to obtain particle size dispersion, and measuring the viscosity of the analysis sample; An abnormality response module, which is connected to the sample analysis module and is used to calculate the spectral abnormality characterization parameter for the current crude oil to be tested according to the spectral abnormality characteristics, so as to determine the spectral abnormality category of the current crude oil to be tested; The data analysis module is connected to the abnormal change response module and is used to perform spectral analysis and obtain spectral data according to the spectral abnormal change category of the current crude oil to be tested, including: Determine the beam diameter and sample scanning time for spectral analysis of the crude oil to be tested according to the spectral variation characterization parameter, determine the spectral data acquired within a predetermined time, compare the obtained spectral data segments after segmenting the spectral data in the time domain dimension, determine whether the spectral analysis meets the standard according to the similarity between the spectral data segments, adjust the scanning speed of the spectrometer, acquire the spectral data again and store it; Or, maintaining the initial operating parameters of the spectrometer to obtain and store spectral data; The origin tracing module is connected to the data analysis module and is used to trace the origin of the current crude oil to be tested based on the similarity comparison result between the stored spectral data and the spectral data of the corresponding samples of each origin.

Images