Method and system for identifying production equipment based on VOCs components

By dividing process sections and sampling in the production area of ​​petrochemical enterprises, and combining with the principal component analysis method, the problem of similar VOCs components in petrochemical enterprises is solved, and the accurate identification and distinction of VOCs components in production equipment is achieved, which improves the identification efficiency and accuracy .

CN113517039BActive Publication Date: 2024-11-05CHINA PETROLEUM & CHEMICAL CORP +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010283841.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-04-10
Publication Date
2024-11-05
Estimated Expiration
2040-04-10

AI Technical Summary

Technical Problem

The VOCs components in the production equipment of petrochemical enterprises are too close, which makes it difficult to distinguish and identify. The VOCs components in different locations are similar, making it difficult to identify production equipment in different locations.

Method used

The production area is divided into multiple process sections, multiple VOCs component sampling equipment are arranged, samples are collected and the relative amount of components is calculated, and the VOCs component distribution data of each production device is obtained through the principal component analysis method.

Benefits of technology

The accurate classification, identification and distinction of VOCs components of production equipment in petrochemical enterprises has been achieved, and the identification efficiency and accuracy have been improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113517039B_ABST
    Figure CN113517039B_ABST
Patent Text Reader

Abstract

The present invention provides a method and system for identifying production equipment based on VOCs components, belonging to the technical field of VOCs monitoring and identification. The method comprises: dividing different production equipment in a production area into multiple process sections, and arranging multiple VOCs component sampling devices in each process section; obtaining VOCs component samples in the production area through the multiple VOCs component sampling devices, calculating the relative amounts of the components of the VOCs component samples, filtering the relative amounts of some components, and then statistically analyzing the relative amounts of the filtered components to obtain VOCs component distribution data corresponding to each of the different production equipment. The present invention is used for monitoring volatile organic compounds and identifying volatile organic compounds in different production equipment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of VOCs monitoring and identification, and specifically to a method for identifying VOCs components of a production device, a system for identifying VOCs components of a production device, a method for identifying a production device using VOCs components, a system for identifying a production device using VOCs components, an electronic device and a computer-readable storage medium. Background Art

[0002] Volatile Organic Compounds (VOCs) are photochemically active and are important precursors to PM2.5 and ozone pollution. These important precursors have serious impacts on the atmospheric environment and human health, and are increasingly attracting attention. The country has issued a number of policy documents, explicitly requiring the strengthening of online monitoring of volatile organic compounds, determining the VOCs emission component spectrum of key pollution sources, and identifying key pollutants and key industries for VOCs control in key areas. VOCs pollution source identification is one of the important aspects of VOCs governance.

[0003] The traditional atmospheric odor pollution source tracing system and application solutions focus on the identification of odorous gases, using the odor activity value of fingerprint substances to establish fingerprint spectra, and using the similarity between spectra to trace the source. This method only involves tracing the source of odorous gases, and does not trace the source based on the concentration of pollutants. The traditional precise source tracing and identification solution for atmospheric pollutants proposes a system for tracing the source of atmospheric pollution, but does not provide research on the effect of tracing the source of pollution. The traditional principal component analysis method for evaluating the main air pollutants introduces the use of principal component analysis methods to evaluate the air quality of major pollutants in the air, such as PM2.5, PM10, CO, SO2 and other major pollutants. It mainly focuses on the evaluation of urban ambient air. These pollution indicators are not applicable to the evaluation of VOCs and the identification of pollution sources in refining and chemical enterprises. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for identifying production equipment based on VOCs components, so as to solve the technical problems that it is difficult to distinguish and identify VOCs components in petrochemical enterprise production equipment because the VOCs components in different location areas of petrochemical enterprise are too similar, and to solve the technical problems that it is difficult to distinguish and identify production equipment in different location areas because the VOCs components in different location areas of petrochemical enterprise are too similar.

[0005] In order to achieve the above object, an embodiment of the present invention provides a method for identifying VOCs components of a production device, the method comprising:

[0006] S1) Divide different production units in the production area into multiple process sections, and arrange multiple VOCs component sampling equipment in each process section;

[0007] S2) obtaining VOCs component samples of the production area through the multiple VOCs component sampling devices, calculating the relative amounts of components of the VOCs component samples, filtering part of the relative amounts of components, and then statistically analyzing the relative amounts of the filtered components to obtain VOCs component distribution data corresponding to each of the different production devices.

[0008] Specifically, in step S1), different production devices in the production area are divided into multiple process sections, specifically:

[0009] According to the production raw materials, processing technology and product requirements of different production units in the production area, each of the different production units is divided into multiple process sections, wherein the different production units in the production area include atmospheric and vacuum units, catalytic cracking units, catalytic reforming units, catalytic hydrogenation units, delayed coking units, sewage treatment plant units, chemical production area units and tank area units.

[0010] Specifically, in step S1), multiple VOCs component sampling devices are arranged, specifically:

[0011] Arrange multiple VOCs component sampling devices in each process section near the area where hydrocarbon components are concentrated,

[0012] Each VOCs component sampling device includes one or more air sampling cans, and the number of VOCs component sampling devices used as parallel samples among the multiple VOCs component sampling devices accounts for 10% of the number of the multiple VOCs component sampling devices.

[0013] Specifically, in step S2), the VOCs component samples of the production area are obtained by using the multiple VOCs component sampling devices, including:

[0014] The sampling conditions of each VOCs component sampling device are configured, wherein the sampling conditions include: the ambient wind speed is less than or equal to a preset wind speed threshold, the sampling flow rate is a preset flow rate, the sampling height is a fixed height, and the sampling time is a fixed time.

[0015] Specifically, the VOCs component sampling equipment in the method is selected as a 3.2L Summa tank and a passive tank sampler matched with the Summa tank, wherein the sampling conditions are specifically as follows:

[0016] The ambient wind speed is less than 0.5m / s, the sampling flow rate is 50ml / min, the sampling height is 1.5m and the sampling time is 1 hour.

[0017] Specifically, in step S2), the VOCs component samples of the production area are obtained by using the multiple VOCs component sampling devices, including:

[0018] Determine the target VOCs category, and use the multiple VOCs component sampling devices to perform sampling to obtain VOCs component samples of the production area;

[0019] According to the target VOCs category, the VOCs component samples of the production area are analyzed to obtain the concentration value of each VOCs component sample, which can be obtained by an analytical instrument and can be used for subsequent aromatics ratio calculation;

[0020] Wherein, a partial concentration gradient standard curve corresponding to the target VOCs category is selectively combined to perform a sample quality control operation.

[0021] Specifically, the target VOCs categories in step S2) include:

[0022] Alkanes, alkenes, benzene series, chlorinated hydrocarbons and oxygen-containing compounds.

[0023] Specifically, before sampling using the plurality of VOCs component sampling devices, step S2) further includes:

[0024] Each VOCs component sampling device is cleaned multiple times with nitrogen, and the gas in the cleaned VOCs component sampling device is extracted until the cleaned VOCs component sampling device is at a fixed negative pressure, thereby obtaining multiple VOCs component sampling devices with the fixed negative pressure.

[0025] Specifically, in step S2), selectively combining a portion of the concentration gradient standard curve corresponding to the target VOCs category to perform a sample quality control operation includes:

[0026] Prior to analysis, a mixed standard VOCs corresponding to the target VOCs category is determined, and the theoretical concentration of the mixed standard VOCs is obtained, and the mixed standard VOCs are used for calibration to obtain the actual calibration concentration of the mixed standard VOCs, and a preset concentration deviation percentage range and the theoretical concentration are combined to determine whether the calibration curve used for the analysis process is valid and can be used for calibration of the analytical instrument;

[0027] Before analysis, multiple concentration gradients corresponding to the mixed standard VOCs are used to establish standard curves about the multiple concentration gradients. Combined with the preset relative standard deviation range and the preset correlation score range, it is determined whether the standard curves about the multiple concentration gradients are valid and can be used for analytical instrument calibration.

[0028] Specifically, the preset concentration deviation percentage range in step S2) is:

[0029] Among the actual calibration concentrations of the mixed standard VOCs, more than 80% of the actual calibration concentrations have a deviation from the theoretical concentration of less than 10%.

[0030] Specifically, the preset relative standard deviation range in step S2) is selected as 1% to 10%, and the preset correlation score range is selected as 0.991 to 1.000.

[0031] Specifically, in step S2), the relative amounts of the components of the VOCs component sample are calculated, and the relative amounts of the components of the filtered part are calculated, including:

[0032] Calculating the aromatic ratio between components of the VOCs component sample;

[0033] According to the changes in the aromatic ratios between components of multiple VOCs component samples, some of the aromatic ratios between components are eliminated;

[0034] Calculate the statistical value corresponding to the aromatic hydrocarbon ratio between components remaining after elimination, determine the aromatic hydrocarbon ratio between components corresponding to the statistical value greater than the preset correlation coefficient, and obtain the aromatic hydrocarbon ratio between components after filtering, wherein the component content in the VOCs component sample corresponding to the aromatic hydrocarbon ratio between components after filtering is greater than the preset component content threshold.

[0035] Specifically, in step S2), the relative amounts of the filtered components are counted to obtain VOCs component distribution data corresponding to each of the different production devices, including:

[0036] The principal component analysis method is used to statistically analyze the relative amounts of the filtered components to obtain the principal component statistical data of the VOCs components corresponding to each of the different production devices and the principal component distribution map of the VOCs components corresponding to the location area of ​​each production device in the production area.

[0037] Specifically, in step S2), the relative amounts of the filtered components are statistically analyzed using the principal component analysis method, including:

[0038] Constructing a matrix about the relative amounts of the filtered components and the different production devices, processing the vectors in the matrix through a standardization operation to obtain a standardized parameter matrix;

[0039] Performing principal component analysis on the standardized parameter matrix by using a nonlinear iterative partial least squares algorithm, and judging whether the iterative calculation is completed in combination with a preset convergence condition;

[0040] After the iterative calculation is completed, the principal component score data corresponding to the different production devices are statistically obtained.

[0041] An embodiment of the present invention provides a system for identifying VOCs components of a production device, the system comprising:

[0042] The calculation module is configured to obtain VOCs component samples of the production area through multiple VOCs component sampling devices, calculate the relative amounts of components of the VOCs component samples, filter some relative amounts of components, and then perform statistics on the relative amounts of components after filtering to obtain VOCs component distribution data corresponding to each of the different production devices, wherein:

[0043] The multiple VOCs component sampling devices are configured in multiple process sections divided according to the location areas of different production devices in the production area.

[0044] An embodiment of the present invention provides a method for identifying a production device using VOCs components, the method comprising:

[0045] S1) obtaining VOCs component samples of a target production area through a plurality of VOCs component sampling devices, wherein the plurality of VOCs component sampling devices are arranged at different locations within the target production area;

[0046] S2) calculating the relative amounts of the components of the VOCs component sample, filtering the relative amounts of some components, and then performing statistics on the relative amounts of the filtered components to obtain the target VOCs component distribution data in the different location areas;

[0047] S3) According to the VOCs component distribution data obtained by the aforementioned method for identifying the VOCs components of the production device, query and identify the production device at the location area corresponding to the VOCs component distribution data in the target VOCs component distribution data.

[0048] An embodiment of the present invention provides a system for identifying a production device using VOCs components, the system comprising:

[0049] A calculation module is configured to obtain VOCs component samples of a target production area through a plurality of VOCs component sampling devices, wherein the plurality of VOCs component sampling devices are configured at different locations within the target production area;

[0050] The calculation module is configured to calculate the relative amount of the components of the VOCs component sample, filter the relative amount of some components, and then perform statistics on the relative amount of the filtered components to obtain the target VOCs component distribution data in the different location areas;

[0051] The calculation module is configured to query and identify the production device at the location area corresponding to each VOCs component distribution data in the target VOCs component distribution data based on the VOCs component distribution data obtained by the aforementioned method for identifying VOCs components of the production device.

[0052] In another aspect, an embodiment of the present invention provides an electronic device, including:

[0053] at least one processor;

[0054] a memory connected to the at least one processor;

[0055] The memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the aforementioned method by executing the instructions stored in the memory.

[0056] On the other hand, an embodiment of the present invention provides a computer-readable storage medium storing computer instructions, which, when executed on a computer, enable the computer to execute the aforementioned method.

[0057] The present invention is based on the VOCs composition of typical production units of petrochemical refineries, selects appropriate characteristic ratio parameters, and uses a nonlinear iterative partial least squares algorithm (NIPALS) to perform principal component analysis, thereby classifying and identifying the VOCs generated by different production units, and realizing the identification of production units based on VOCs component distribution data, with fast calculation speed, more accurate and more intuitive classification.

[0058] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0060] Figure 1 It is a schematic diagram of the main steps of an embodiment of the present invention;

[0061] Figure 2 This is a schematic diagram of the abbreviation comparison of the compounds in the examples of the present invention;

[0062] Figure 3 Schematic diagram of an exemplary partial matrix in a normalized characteristic ratio parameter matrix of an embodiment of the present invention;

[0063] Figure 4 Schematic diagram of an exemplary partial matrix in a normalized characteristic ratio parameter matrix of an embodiment of the present invention;

[0064] Figure 5 This is a schematic diagram of the main component scores of the VOCs components of the chemical industry area, reforming unit, wax oil hydrogenation unit and coking unit according to an embodiment of the present invention;

[0065] Figure 6 Schematic diagram of the distribution of characteristic ratio parameters of aromatics in a chemical zone device according to an embodiment of the present invention;

[0066] Figure 7 Schematic diagram of the distribution of characteristic ratio parameters of aromatics in a reforming device according to an embodiment of the present invention;

[0067] Figure 8 Schematic diagram of the distribution of characteristic ratio parameters of aromatics in a wax oil hydrogenation device according to an embodiment of the present invention;

[0068] Fig. 9 This is a schematic diagram of the principal component analysis results of VOCs components in the chemical area, reforming unit area, wax oil hydrogenation unit, and coking unit based on the characteristic aromatic ratio in an embodiment of the present invention;

[0069] Fig.10 This is a schematic diagram of the principal component analysis results of VOCs components in the chemical area, reforming unit area, wax oil hydrogenation unit, and coking unit based on all aromatic hydrocarbon ratios in an embodiment of the present invention. DETAILED DESCRIPTION

[0070] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0071] Example 1

[0072] like Figure 1 , an embodiment of the present invention provides a method for identifying VOCs components of a production device, the method comprising:

[0073] S1) Divide different production units in the production area into multiple process sections, and arrange multiple VOCs component sampling equipment in each process section;

[0074] S2) obtaining VOCs component samples of the production area through the multiple VOCs component sampling devices, calculating the relative amounts of components of the VOCs component samples, filtering part of the relative amounts of components, and then statistically analyzing the relative amounts of the filtered components to obtain VOCs component distribution data corresponding to each of the different production devices.

[0075] The relative amount of the components can be selected as a characteristic ratio between the components, such as the aromatic hydrocarbon ratio between the components; the distribution data can include statistical data (such as a bar graph) and a distribution diagram of the sampling point locations of the corresponding VOCs component sampling equipment.

[0076] Specifically, in step S1), different production devices in the production area are divided into multiple process sections, specifically:

[0077] According to the production raw materials, processing technology and product requirements (such as the component concentration ratio of the product) of different production units in the production area, each of the different production units is divided into multiple process sections, wherein the different production units in the production area include atmospheric and vacuum units, catalytic cracking units, catalytic reforming units, catalytic hydrogenation units, delayed coking units, sewage treatment plant units, chemical production area units and tank area units.

[0078] The production raw materials are the process characteristics of the raw material area of ​​the production equipment, the processing technology is the process characteristics of the processing area of ​​the production equipment, and the product requirements are the process characteristics of the product area of ​​the production equipment. Therefore, it can be divided into at least three process sections. Each process section can be further divided into different sections according to the specific production equipment, and at least one VOCs sampling device is set in each section.

[0079] Specifically, in step S1), multiple VOCs component sampling devices are arranged, specifically:

[0080] Arrange multiple VOCs component sampling devices in each process section near the area where hydrocarbon components are concentrated,

[0081] Each VOCs component sampling device includes one or more air sampling canisters, and the number of VOCs component sampling devices used as parallel samples among the multiple VOCs component sampling devices accounts for 10% of the number of the multiple VOCs component sampling devices;

[0082] In some specific implementations, in addition to setting up parallel samples, multiple sampling processes can be performed using VOCs component sampling equipment at the same sampling point. For example, VOCs component samples are collected at the same sampling point under different time ranges and different working conditions to obtain multiple VOCs component samples.

[0083] Specifically, in step S2), the VOCs component samples of the production area are obtained by using the multiple VOCs component sampling devices, including:

[0084] Configure sampling conditions for each VOCs component sampling device, wherein the sampling conditions include: the ambient wind speed is less than or equal to a preset wind speed threshold, the sampling flow rate is a preset flow rate, the sampling height is a fixed height, and the sampling time is a fixed time;

[0085] Common equipment in refineries (production areas) include atmospheric and vacuum units, catalytic cracking, catalytic reforming, catalytic hydrogenation, delayed coking, sewage treatment plants, chemical production, storage tank areas, etc. Different production units are divided into multiple process sections, which are divided according to production raw materials, processing technology, product requirements, etc.; multiple sampling points are set according to the process section (a sampling point is the distribution location of one or more VOCs component sampling equipment). When selecting sampling points, try to select process areas where hydrocarbon components are concentrated, set at flanges, pumps, valves and other parts where VOCs leakage may occur. When collecting samples, the wind speed is low (<0.5m / s) to reduce the impact of diffusion and transmission between the devices. Sampling uses a 3.2L Suma tank (ENTECH) with a passive tank sampler (ENTECH CS100E), with a sampling flow rate of 50ml / min, a sampling height of 1.5m, and a collection time of 1 hour; the above content can be called process analysis and sampling point selection.

[0086] Specifically, in step S2), the VOCs component samples of the production area are obtained by using the multiple VOCs component sampling devices, including:

[0087] Determine the target VOCs category, and use the multiple VOCs component sampling devices to perform sampling to obtain VOCs component samples of the production area;

[0088] According to the target VOCs category, the VOCs component samples of the production area are analyzed to obtain the concentration value of each VOCs component sample, which can be obtained by an analytical instrument and can be used for subsequent ratio calculation;

[0089] Wherein, a partial concentration gradient standard curve corresponding to the target VOCs category is selectively combined to perform a sample quality control operation.

[0090] Specifically, the target VOCs categories in step S2) include:

[0091] Alkanes, alkenes, benzene series, chlorinated hydrocarbons and oxygen-containing compounds.

[0092] Specifically, before sampling using the plurality of VOCs component sampling devices, step S2) further includes:

[0093] Each VOCs component sampling device is cleaned multiple times with nitrogen, and the gas in the cleaned VOCs component sampling device is extracted until the cleaned VOCs component sampling device is at a fixed negative pressure, thereby obtaining multiple VOCs component sampling devices with the fixed negative pressure.

[0094] Specifically, in step S2), selectively combining a portion of the concentration gradient standard curve corresponding to the target VOCs category to perform a sample quality control operation includes:

[0095] Prior to analysis, a mixed standard VOCs corresponding to the target VOCs category is determined, and the theoretical concentration of the mixed standard VOCs is obtained, and the mixed standard VOCs are used for calibration to obtain the actual calibration concentration of the mixed standard VOCs, and a preset concentration deviation percentage range and the theoretical concentration are combined to determine whether the calibration curve used for the analysis process is valid and can be used for calibration of the analytical instrument;

[0096] Before analysis, multiple concentration gradients corresponding to the mixed standard VOCs are used to establish standard curves about the multiple concentration gradients. Combined with the preset relative standard deviation range and the preset correlation score range, it is determined whether the standard curves about the multiple concentration gradients are valid and can be used for analytical instrument calibration.

[0097] Adopt the TO14 and TO15 methods recommended by US EPA, pre-concentration-GC-MS (analytical instrument) coupling, full spectrum analysis, standard curve calibration with different concentration gradients, to achieve accurate measurement;

[0098] Mainly analyze 107 volatile organic compounds in the C2-C14 range in PAMS+TO15, covering alkanes, olefins, benzene series, chlorinated hydrocarbons, oxygen-containing compounds and other substances;

[0099] Quality control means (sample quality control operation): Before sampling, use a tank cleaning instrument to clean the Suma tank with high-purity nitrogen for 3 times and pump it to a negative pressure of 6.5Pa, and take one Suma tank from each batch for blank detection; use TO15 and PAMS mixed standard gas for single-point quality control every day, and the deviation between the actual calibration concentration and the theoretical concentration of more than 80% of the substances is less than 10%, and the calibration curve is considered valid. If it exceeds, multi-point calibration is performed again; parallel samples account for 10% of the total number of samples;

[0100] Six concentration gradient mixed standards were used to establish a standard curve. Each concentration gradient was injected 5 times, and 4×10 -9 The internal standard has a relative standard deviation of 1% to 10% for each target, and the correlation of the standard curve is between 0.991 and 1.000; this step can be referred to as instrument calibration before sample analysis.

[0101] Specifically, in step S2), the relative amounts of the components of the VOCs component sample are calculated, and the relative amounts of the components of the filtered part are calculated, including:

[0102] Calculating the aromatic ratio between components of the VOCs component sample;

[0103] According to the changes in the aromatic ratios between components of multiple VOCs component samples, some of the aromatic ratios between components are eliminated;

[0104] Calculate the statistical value corresponding to the aromatic hydrocarbon ratio between components remaining after elimination, determine the aromatic hydrocarbon ratio between components corresponding to the statistical value greater than the preset correlation coefficient, and obtain the aromatic hydrocarbon ratio between components after filtering, wherein the component content in the VOCs component sample corresponding to the aromatic hydrocarbon ratio between components after filtering is greater than a preset component content threshold (selected according to the dimension and precision of the sample).

[0105] Specifically, in step S2), the relative amounts of the filtered components are counted to obtain VOCs component distribution data corresponding to each of the different production devices, including:

[0106] The relative amounts of the filtered components are statistically analyzed using a principal component analysis method to obtain principal component statistical data of the VOCs components corresponding to each of the different production devices and a principal component distribution map of the VOCs components corresponding to the location area of ​​each production device in the production area;

[0107] Specifically, in step S2), the relative amounts of the filtered components are statistically analyzed using the principal component analysis method, including:

[0108] Constructing a matrix about the relative amounts of the filtered components and the different production devices, processing the vectors in the matrix through a standardization operation to obtain a standardized parameter matrix;

[0109] Performing principal component analysis on the standardized parameter matrix by using a nonlinear iterative partial least squares algorithm, and judging whether the iterative calculation is completed in combination with a preset convergence condition;

[0110] After the iterative calculation is completed, the principal component score data corresponding to the different production devices are statistically obtained;

[0111] For multiple sampling points of multiple devices, MATLAB programming is used to calculate the aromatic ratios between VOCs components of different devices. Due to the poor stability of individual ratios (the ratios after multiple samplings change dramatically), it is difficult to achieve qualitative analysis. Therefore, multiple aromatic ratios are selected as analysis parameters. After standardization, statistical values ​​and correlation coefficients of statistical values ​​are obtained. Multiple aromatic ratios with large correlation coefficients and high component contents are selected. Based on the selected aromatic ratios, the principal component analysis method is used to perform statistical analysis on the VOCs composition of different devices, and the distribution map of VOCs composition at different points in three-dimensional space is obtained, thereby realizing the classification and identification of different devices; the aforementioned content can be called calculation and identification.

[0112] Example 2

[0113] Based on Example 1, the characteristic compound ratio method is a method for qualitatively identifying pollution source types based on the obvious differences in the ratios of different chemical components in different emission sources. The ratio method has been successfully applied in source type identification. The ratio can be used as a parameter to characterize the source type. The ratio between aromatic hydrocarbon components is a very important identification index in oil fingerprint identification. Therefore, the ratio method can be used for classification identification.

[0114] Principal component analysis: It is a method commonly used in statistics to reduce dimensionality. When calculating statistics, a large number of variables will increase the complexity of calculation and the difficulty of problem analysis. There may be a certain correlation between multiple variables, and information overlap will occur during calculation. The principal component analysis method can be used to recombine the original multiple correlated variables into a new set of several independent comprehensive variables through linear transformation. For example, when the first linear combination F1 is selected to reflect the information of the original multiple variables, F1 can obtain the maximum explained variance, and F1 is the first principal component. If F1 is not enough to represent the information of the original variables as the first principal component, then F2 will be selected as the second linear combination, and F1 and F2 are two unrelated variables, then F2 is the second principal component, and so on, to form multiple principal components. This statistical method is principal component analysis, and these comprehensive variables generated by recombination are principal components.

[0115] The main steps of principal component analysis using the NIPALS iterative algorithm are as follows:

[0116] If there are P samples, each sample has N parameters, forming the matrix X as follows:

[0117]

[0118] In formula ①, x pn Represents the measured value of parameter n of sample p, where p is less than or equal to P and n is less than or equal to N.

[0119] (1) Take any column (usually the first column) of X as the starting value of the first score vector t: t = x;

[0120] (2) Since there should be a linear relationship between t and X, the load vector p is calculated T :

[0121] p T =t T X / t T t ②

[0122] (3) T Normalize to get a unit length vector

[0123]

[0124] (4) Then according to the unit length vector There should be a linear relationship between X and regression to obtain a new score vector t new :

[0125]

[0126] (5) Relatively new t new and the old t to see whether the convergence condition is met. If so, continue with step (6), otherwise jump back to step (2). The convergence condition is, for example, t new The absolute value of the difference between t and t is less than or equal to a very small number ε, and the value of ε can be selected according to the accuracy of the specific sample and the dimension of the parameter;

[0127] (6) If the required principal components have been calculated, stop the calculation; otherwise, calculate the residual matrix E:

[0128] E=X-tp T ⑤

[0129] (7) Replace X with E and return to step (1) to find the next principal component.

[0130] Formula ① is to construct a matrix about the relative amount of the filtered components and the different production units, and formulas ② to ⑤ are the iterative calculation process in the principal component analysis of the standardized parameter matrix through the nonlinear iterative partial least squares algorithm; from the NIPALS iterative algorithm, it can be seen that the latter load and score are calculated by applying the residual left after the previous regression fitting, which reflects the remaining information of the original variable matrix that the previous principal component cannot explain and represent, and its information content is less than the previous load and score. Compared with the algorithm for finding the principal component based on the characteristic decomposition of the covariance matrix (or correlation matrix), the NIPALS algorithm does not need to find all scores and loads, which can reduce the workload of the principal component decomposition process and is suitable for PCA of large data matrices. The method of the present invention is suitable for the classification and identification of the main production units of refining enterprises. The VOCs samples collected in the example all adopt the TO14 and TO15 methods recommended by US EPA, pre-concentration-GC-MS combination, full spectrum analysis, and standard curve calibration with different concentration gradients to achieve accurate measurement. The correlation of the standard curve is between 0.991 and 1.000.

[0131] Example 3

[0132] Based on Example 2, a VOCs component spectrum database of major equipment in petrochemical refineries was established to extract characteristic ratios of aromatic components. Common equipment in refineries include atmospheric and vacuum units, catalytic cracking, catalytic reforming, catalytic hydrogenation, delayed coking, sewage treatment plants, chemical production, storage tank areas, etc. Different production equipment is divided into multiple process sections, which are divided according to production raw materials, processing technology, product requirements, etc.

[0133] As many VOCs samples as possible from different devices were collected, and the composition of the VOCs samples was obtained using GC-MS analysis instruments, including 107 compounds such as alkanes, alkenes, alkynes, aromatics, chlorinated hydrocarbons, oxygen-containing organic matter, and sulfides. According to the data processing principles, samples with contents below the detection limit were deleted, and a total of 10 samples were collected from the chemical area, coking area, catalytic reforming, and wax oil hydrogenation areas, covering the range of different production process sections of the four devices.

[0134] MATLAB programming was used to calculate the aromatic ratios between components of VOCs in different devices (or aromatic ratios between components, or aromatic component ratios between sample components), and the aromatic component ratios with higher composition contents (such as greater than the preset component content threshold) and greater correlation (such as greater than the preset correlation coefficient) were extracted. The ratios between benzene, toluene, ethylbenzene, xylene, trimethylbenzene, ethyltoluene, and naphthalene were preferred. The distribution of the characteristic ratio parameters of aromatics in different devices is shown in Figure 1. Figure 6-8 , where each group B m The column vectors (a total of 17 column vectors) include 10 characteristic ratio parameters corresponding to the chemical zone unit, the reforming unit or the wax oil hydrogenation unit, and m is 1, 2..., 10, for example Figure 6 , for the B1 column vector, from left to right, they correspond to the characteristic ratio parameters of Chemical Industry 1 to Chemical Industry 10, Figure 7 and Figure 8 Also in this corresponding manner; the main aromatics ratio is shown in Figure 2 .

[0135] Example 4

[0136] The VOCs components of different devices are classified according to the above-mentioned production area classification and process classification.

[0137] (1) The original data of the aromatics ratio obtained in Example 3 were standardized to eliminate the influence of different orders of magnitude on the results. The standardized results are shown in Figure 3 and Figure 4 , Standardization formula (the formula used in the standardization operation process):

[0138]

[0139] in, is the statistical value after sample standardization, (subscript j) is the mean, Var(x j ) is the variance,

[0140]

[0141] Wherein, j=1, 2, ..., p.

[0142] (1) After being processed by the NIPALS iterative algorithm, the principal component scores of the samples from different production units are obtained. Figure 5 .

[0143] (2) Use the principal component scores to plot in three-dimensional space, such as Fig. 9 , axis 1, axis 2 and axis 3 are the principal component score axes of different dimensions (T1, T2 and T3), the triangle "△" represents the principal component of the reforming unit, the plus sign "+" represents the principal component of the wax oil hydrogenation unit, the small circle "○" represents the principal component of the coking unit, and the asterisk "*" represents the principal component of the chemical zone unit. It can be seen from the figure that samples from the same unit are clustered together, and there is a clear dividing line between samples from different units.

[0144] Comparative Example of Example 4

[0145] The principal component analysis was performed using the aromatic component ratios (aromatic ratios) of all components of VOCs samples from different devices.

[0146] (1) All aromatic component ratios of the 40 VOCs samples obtained in Example 3 were standardized to eliminate the influence of different orders of magnitude on the results. Standardization formula:

[0147]

[0148] in, is the statistical value after sample standardization, is the mean, Var(x j ) is the variance,

[0149]

[0150] Wherein, j=1, 2, ..., p.

[0151] (2) After processing by the NIPALS iterative algorithm, the principal component scores of each sample from different production units were obtained.

[0152] (3) Use the principal component scores to plot in three-dimensional space, such as Fig.10, axis 1, axis 2 and axis 3 are the principal component score axes of different dimensions (T1, T2 and T3), the triangle "△" represents the principal component of the reforming unit, the plus sign "+" represents the principal component of the wax oil hydrogenation unit, the small circle "○" represents the principal component of the coking unit, the asterisk "*" represents the principal component of the chemical zone unit, and the elliptical coil represents distinguishability and identifiability. It can be seen from the figure that the samples from the same unit are scattered, while the coking unit and the wax oil hydrogenation unit cannot be completely separated.

[0153] Example 5

[0154] An embodiment of the present invention provides a system for identifying VOCs components of a production device, the system comprising:

[0155] The calculation module is configured to obtain VOCs component samples of the production area through multiple VOCs component sampling devices, calculate the relative amounts of components of the VOCs component samples, filter some relative amounts of components, and then perform statistics on the relative amounts of components after filtering to obtain VOCs component distribution data corresponding to each of the different production devices, wherein:

[0156] The multiple VOCs component sampling devices are configured in multiple process sections divided according to the location areas of different production devices in the production area.

[0157] The system may further include: a display module configured to present the VOCs component distribution data.

[0158] Example 6

[0159] Based on Examples 1 to 5, an embodiment of the present invention provides a method for identifying a production device using VOCs components, the method comprising:

[0160] S1) obtaining VOCs component samples of a target production area through a plurality of VOCs component sampling devices, wherein the plurality of VOCs component sampling devices are arranged at different locations within the target production area;

[0161] Specifically, in some specific implementations, the plurality of VOCs component sampling devices are configured in a plurality of process sections divided according to the location areas of different production devices in the production area, for example, to distinguish whether there are different production devices in the same location area;

[0162] S2) calculating the relative amounts of the components of the VOCs component sample, filtering the relative amounts of some components, and then performing statistics on the relative amounts of the filtered components to obtain the target VOCs component distribution data in the different location areas, wherein the calculation process, the filtering process and the statistical process can be performed in the manner of Example 1;

[0163] S3) querying and identifying the production device at the location area corresponding to the VOCs component distribution data in the target VOCs component distribution data according to the VOCs component distribution data obtained by the aforementioned method for identifying the VOCs components of the production device;

[0164] According to the VOCs component distribution data obtained by the aforementioned method for identifying the VOCs components of the production device, a relational database of the main production devices and the main components of the VOCs components with corresponding relationships can be established to facilitate rapid call and query;

[0165] For identifying the production device at the location area, it can be distinguishing whether different production devices exist in the same location area, or distinguishing whether the same production device exists in different location areas;

[0166] For the query and identification process, the similarity or distribution proximity (degree of proximity in terms of the size of the score, the relative size of the score values, and the distribution of the score values) between the data (the score of the main component of the VOCs component in the target VOCs component distribution data and the score of the main component of the VOCs component in the VOCs component distribution data obtained by the aforementioned method for identifying the VOCs components of the production device) can be checked based on the relational database to determine the production device corresponding to the main component of the VOCs component in the target VOCs component distribution data.

[0167] Example 7

[0168] Based on Examples 1 to 6, an embodiment of the present invention provides a system for identifying a production device using VOCs components, the system comprising:

[0169] A calculation module is configured to obtain VOCs component samples of a target production area through a plurality of VOCs component sampling devices, wherein the plurality of VOCs component sampling devices are configured at different locations within the target production area;

[0170] The calculation module is configured to calculate the relative amount of the components of the VOCs component sample, filter the relative amount of some components, and then perform statistics on the relative amount of the filtered components to obtain the target VOCs component distribution data in the different location areas;

[0171] The calculation module is configured to query and identify the production device at the location area corresponding to each VOCs component distribution data in the target VOCs component distribution data based on the VOCs component distribution data obtained by the aforementioned method for identifying VOCs components of the production device.

[0172] The above describes in detail the optional implementation modes of the embodiments of the present invention in combination with the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above implementation modes. Within the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical scheme of the embodiments of the present invention, and these simple modifications all belong to the protection scope of the embodiments of the present invention.

[0173] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0174] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including a number of instructions to enable a single-chip microcomputer, a chip or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0175] In addition, various implementations of the embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the embodiments of the present invention, they should also be regarded as the contents disclosed in the embodiments of the present invention.

Claims

1. A method for identifying VOCs components in a production facility, It is characterized in that The method includes: S1) Divide different production units in the production area into multiple process sections, and arrange multiple VOCs component sampling equipment in each process section; S2) obtaining VOCs component samples of the production area through the multiple VOCs component sampling devices, calculating the relative amounts of the components of the VOCs component samples, filtering some of the relative amounts of the components, and then performing statistics on the relative amounts of the filtered components to obtain VOCs component distribution data corresponding to each of the different production devices; Wherein, in step S2), the VOCs component samples of the production area are obtained by the multiple VOCs component sampling devices, including: determining the target VOCs category, sampling by the multiple VOCs component sampling devices, and obtaining the VOCs component samples of the production area; analyzing the VOCs component samples of the production area according to the target VOCs category, and obtaining the concentration value of each VOCs component sample; wherein, the sample quality control operation is performed by selectively combining a portion of the concentration gradient standard curve corresponding to the target VOCs category; In step S2), a partial concentration gradient standard curve corresponding to the target VOCs category is selectively combined to perform a sample quality control operation, including: before analysis, determining the mixed standard VOCs corresponding to the target VOCs category, and obtaining the theoretical concentration of the mixed standard VOCs, using the mixed standard VOCs for calibration, obtaining the actual calibration concentration of the mixed standard VOCs, and determining whether the calibration curve used for the analysis process is valid in combination with a preset concentration deviation percentage range and the theoretical concentration; before analysis, multiple concentration gradients corresponding to the mixed standard VOCs are used to establish standard curves for the multiple concentration gradients, and determining whether the standard curves for the multiple concentration gradients are valid in combination with a preset relative standard deviation range and a preset correlation score range; In step S2), the relative amounts of the filtered components are counted to obtain VOCs component distribution data corresponding to each of the different production devices, including: using a principal component analysis method to count the relative amounts of the filtered components to obtain principal component statistical data of VOCs components corresponding to each of the different production devices and a principal component distribution map of VOCs components corresponding to the location area of ​​each production device in the production area; In step S2), the relative amounts of the filtered components are statistically analyzed using a principal component analysis method, including: constructing a matrix about the relative amounts of the filtered components and the different production devices, processing the vectors in the matrix through a standardization operation, and obtaining a standardized parameter matrix; performing principal component analysis on the standardized parameter matrix through a nonlinear iterative partial least squares algorithm, and judging whether the iterative calculation is completed in combination with a preset convergence condition; after the iterative calculation is completed, obtaining statistically the principal component score data corresponding to the different production devices.

2. The method for identifying VOCs components in a production device according to claim 1, It is characterized in that In step S1), different production devices in the production area are divided into multiple process sections, specifically: According to the production raw materials, processing technology and product requirements of different production units in the production area, each of the different production units is divided into multiple process sections, wherein the different production units in the production area include atmospheric and vacuum units, catalytic cracking units, catalytic reforming units, catalytic hydrogenation units, delayed coking units, sewage treatment plant units, chemical production area units and tank area units.

3. The method for identifying VOCs components in a production device according to claim 1, It is characterized in that In step S1), multiple VOCs component sampling devices are arranged, specifically: Arrange multiple VOCs component sampling devices in each process section near the area where hydrocarbon components are concentrated, Each VOCs component sampling device includes one or more air sampling cans, and the number of VOCs component sampling devices used as parallel samples among the multiple VOCs component sampling devices accounts for 10% of the number of the multiple VOCs component sampling devices.

4. The method for identifying VOCs components in a production device according to claim 1, It is characterized in that In step S2), the VOCs component samples of the production area are obtained by using the multiple VOCs component sampling devices, including: The sampling conditions of each VOCs component sampling device are configured, wherein the sampling conditions include: the ambient wind speed is less than or equal to a preset wind speed threshold, the sampling flow rate is a preset flow rate, the sampling height is a fixed height, and the sampling time is a fixed time.

5. The method for identifying VOCs components in a production device according to claim 4, It is characterized in that The VOCs component sampling equipment in the method is selected as a 3.2L Summa tank and a passive tank sampler matched with the Summa tank, wherein the sampling conditions are specifically as follows: The ambient wind speed is less than 0.5m / s, the sampling flow rate is 50ml / min, the sampling height is 1.5m and the sampling time is 1 hour.

6. The method for identifying VOCs components in a production device according to claim 1, It is characterized in that The target VOCs categories in step S2) include: Alkanes, alkenes, benzene series, chlorinated hydrocarbons and oxygen-containing compounds.

7. The method for identifying VOCs components in a production device according to claim 1 or 6, It is characterized in that Step S2) before sampling using the plurality of VOCs component sampling devices, further comprises: Each VOCs component sampling device is cleaned multiple times with nitrogen, and the gas in the cleaned VOCs component sampling device is extracted until the cleaned VOCs component sampling device is at a fixed negative pressure, thereby obtaining multiple VOCs component sampling devices with the fixed negative pressure.

8. The method for identifying VOCs components in a production device according to claim 1, It is characterized in that The preset concentration deviation percentage range in step S2) is: Among the actual calibration concentrations of the mixed standard VOCs, more than 80% of the actual calibration concentrations have a deviation from the theoretical concentration of less than 10%.

9. The method for identifying VOCs components in a production device according to claim 1, It is characterized in that The preset relative standard deviation range in step S2) is selected to be 1% to 10%, and the preset correlation score range is selected to be 0.991 to 1.

000.

10. The method for identifying VOCs components in a production device according to claim 1, It is characterized in that Step S2) calculates the relative amounts of the components of the VOCs component sample and filters the relative amounts of the components, including: Calculating the aromatic ratio between components of the VOCs component sample; According to the changes in the aromatic ratios between components of multiple VOCs component samples, some of the aromatic ratios between components are eliminated; Calculate the statistical value corresponding to the aromatic hydrocarbon ratio between components remaining after elimination, determine the aromatic hydrocarbon ratio between components corresponding to the statistical value greater than the preset correlation coefficient, and obtain the aromatic hydrocarbon ratio between components after filtering, wherein the component content in the VOCs component sample corresponding to the aromatic hydrocarbon ratio between components after filtering is greater than the preset component content threshold.

11. A method for identifying production equipment using VOCs components, It is characterized in that The method includes: S1) obtaining VOCs component samples of a target production area through a plurality of VOCs component sampling devices, wherein the plurality of VOCs component sampling devices are arranged at different locations within the target production area; S2) calculating the relative amounts of the components of the VOCs component sample, filtering the relative amounts of some components, and then performing statistics on the relative amounts of the filtered components to obtain the target VOCs component distribution data in the different location areas; S3) According to the VOCs component distribution data obtained according to any one of claims 1 to 10, query and identify the production device at the location area corresponding to the VOCs component distribution data in the target VOCs component distribution data.

12. A system for identifying VOCs components in a production facility, It is characterized in that The system includes: The calculation module is configured to obtain VOCs component samples of the production area through multiple VOCs component sampling devices, calculate the relative amount of components of the VOCs component samples, filter the relative amount of some components, and then perform statistics on the relative amount of the filtered components to obtain VOCs component distribution data corresponding to each production device in different production devices, wherein: The plurality of VOCs component sampling devices are arranged in a plurality of process sections divided according to the location areas of different production devices in the production area; Wherein, the calculation module obtains the VOCs component samples of the production area through the multiple VOCs component sampling devices, including: determining the target VOCs category, sampling using the multiple VOCs component sampling devices, and obtaining the VOCs component samples of the production area; analyzing the VOCs component samples of the production area according to the target VOCs category to obtain the concentration value of each VOCs component sample; wherein, selectively combining a portion of the concentration gradient standard curve corresponding to the target VOCs category to perform a sample quality control operation; The calculation module selectively combines a portion of the concentration gradient standard curve corresponding to the target VOCs category to perform a sample quality control operation, including: before analysis, determining the mixed standard VOCs corresponding to the target VOCs category, and obtaining the theoretical concentration of the mixed standard VOCs, using the mixed standard VOCs for calibration, obtaining the actual calibration concentration of the mixed standard VOCs, and combining the preset concentration deviation percentage range and the theoretical concentration to determine whether the correction curve used for the analysis process is valid; before analysis, multiple concentration gradients corresponding to the mixed standard VOCs are used to establish standard curves about the multiple concentration gradients, and combining the preset relative standard deviation range and the preset correlation score range to determine whether the standard curves about the multiple concentration gradients are valid; The calculation module performs statistics on the relative amounts of the filtered components to obtain VOCs component distribution data corresponding to each of the different production devices, including: using a principal component analysis method to perform statistics on the relative amounts of the filtered components to obtain principal component statistical data of VOCs components corresponding to each of the different production devices and a principal component distribution map of VOCs components corresponding to the location area of ​​each production device in the production area; The principal component analysis method is used in the calculation module to perform statistics on the relative amounts of the filtered components, including: constructing a matrix about the relative amounts of the filtered components and the different production devices, processing the vectors in the matrix through standardization operations, and obtaining a standardized parameter matrix; performing principal component analysis on the standardized parameter matrix through a nonlinear iterative partial least squares algorithm, and judging whether the iterative calculation is completed in combination with a preset convergence condition; after the iterative calculation is completed, statistically obtaining principal component score data corresponding to the different production devices.

13. A system for identifying production equipment using VOCs components, It is characterized in that The system includes: A calculation module is configured to obtain VOCs component samples of a target production area through a plurality of VOCs component sampling devices, wherein the plurality of VOCs component sampling devices are configured at different locations within the target production area; The calculation module is configured to calculate the relative amount of the components of the VOCs component sample, filter the relative amount of some components, and then perform statistics on the relative amount of the filtered components to obtain the target VOCs component distribution data in the different location areas; The calculation module is configured to query and identify a production device at a location area corresponding to each VOCs component distribution data in the target VOCs component distribution data according to the VOCs component distribution data obtained according to any one of claims 1 to 10.

14. An electronic device, It is characterized in that include: at least one processor; a memory connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the method of any one of claims 1 to 11 by executing the instructions stored in the memory.

15. A computer-readable storage medium storing computer instructions, which, when executed on a computer, enables the computer to execute the method according to any one of claims 1 to 11.