Hydroprocessing unit operation optimization method, apparatus, device, and storage medium

Abstract

The application discloses a hydrogenation device operation optimization method, device, equipment and storage medium, and comprises the following steps: acquiring and storing various working condition data of a hydrogenation device to a preset database; constructing a mechanism model of the hydrogenation device according to the working condition data; generating working condition simulation data according to the mechanism model; generating modeling data according to the working condition data and the working condition simulation data, generating a machine learning model for predicting the optimal working condition state of the hydrogenation device through data training; acquiring current process parameter data of the hydrogenation device, acquiring working condition optimal data of a preset working condition of the optimal working condition state through the machine learning model; predicting working condition prediction data of the preset working condition of the hydrogenation device at the next moment through the mechanism model; and determining a regulation and control strategy of the hydrogenation device according to the difference between the preset working condition optimal data and the preset working condition prediction data. The application can fully utilize the maximum processing capacity of device design, thereby improving the production efficiency of the device.

Description

Technical Field

[0001] This invention relates to the field of residual oil hydrogenation, and particularly to methods, apparatus, equipment and storage media for optimizing the operation of hydrogenation units. Background Technology

[0002] With the increasing trend of crude oil becoming heavier and of lower quality, the efficient conversion and clean utilization of heavy oil has become a focus of attention in the world's refining industry.

[0003] Currently, among the technical solutions for residue hydrotreating, fixed-bed residue hydrotreating technology is relatively mature and widely used. However, problems such as catalyst deactivation, rapid rise in bed pressure caused by nickel and vanadium deposits in the reactor bed can lead to abnormal shutdowns of the unit, resulting in economic losses.

[0004] In existing technologies, the operating cycle of the equipment is often extended by switching reactors, introducing new metal removal technologies, or using more expensive moving beds or fluidized beds.

[0005] The inventors discovered through research that existing methods for extending the operating cycle of devices have at least the following drawbacks:

[0006] When avoiding abnormal shutdowns of the equipment, the maximum processing capacity designed for the equipment cannot be fully utilized, resulting in low production efficiency.

[0007] The information disclosed in this background section is intended only to enhance the understanding of the overall background of the invention and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0008] The purpose of this invention is to improve the production efficiency of the device by making full use of its maximum processing capacity while avoiding operation of the device under unreasonable working conditions and reducing abnormal downtime.

[0009] This invention provides a method for optimizing the operation of a hydrogenation unit, comprising the following steps:

[0010] S11. Acquire and store various operating condition data of the hydrogenation unit to a preset database; the operating condition data includes at least: process parameter data, feed property data, product material data, catalyst ratio data, actual operating temperature and actual operating pressure of the hydrogenation unit, as well as fault shutdown data and optimal operating condition data.

[0011] S12. Construct a mechanism model of the hydrogenation device based on the operating condition data;

[0012] S13. Using the operating condition data as input, generate operating condition simulation data according to the mechanism model; the operating condition simulation data includes simulation data corresponding to the preset operating condition data;

[0013] S14. Generate modeling data based on the operating condition data and the operating condition simulation data, and generate a machine learning model for predicting the optimal operating condition of the hydrogenation unit through data training.

[0014] S15. Real-time acquisition of the current process parameter data of the hydrogenation unit; using the current process parameter data as input, obtaining the optimal operating condition data of the preset operating condition when the optimal operating condition is obtained through the machine learning model; using the current process parameter data as input, predicting the operating condition prediction data of the preset operating condition of the hydrogenation unit at the next moment through the mechanism model.

[0015] S16. Determine the control strategy of the hydrogenation unit based on the difference between the preset optimal operating condition data and the preset predicted operating condition data.

[0016] Preferably, in this invention, acquiring and storing various operating condition data of the hydrogenation unit into a preset database includes:

[0017] Data on feedstock properties, catalyst ratio, operating temperature, and operating pressure of the hydrogenation unit are collected and recorded. Combined with corresponding fault shutdown data and optimal operating condition labels from historical data, an operating condition dataset for the hydrogenation unit is established.

[0018] Preferably, in this invention, the feed property data includes: the operating temperature, operating pressure, and hydrogen replenishment amount at the inlet and outlet of the hydrogenation unit;

[0019] The product material data includes: sulfur content, nitrogen content, metal content, residual carbon content, and slag blending ratio obtained by oil analysis of feed oil and / or mixed feed oil and the product obtained after processing;

[0020] The catalyst formulation data includes: catalyst type and gradation.

[0021] Preferably, in this invention, constructing the mechanism model of the hydrogenation device based on the operating condition data includes:

[0022] The mechanistic model includes a hydrorefining reaction kinetic model, a hydrocracking reaction kinetic model, and a catalyst deactivation kinetic model.

[0023] Based on the catalyst deactivation law, a deactivation dynamics equation model is established, including:

[0024]

[0025] in, This indicates deactivation caused by coke deposition. This indicates deactivation caused by metal deposition, and i indicates the type of impurities in the residue oil;

[0026] The catalyst deactivation kinetic model is expressed as follows:

[0027]

[0028] Where, α i Indicates catalyst deactivation rate, β i Let W represent the deactivation level, and W represent the ratio of the metal deposition amount MOC to the planned and overall mass. The metal deposition amount MOC is:

[0029]

[0030] c metal.0 and c metal.t The L represents the metal concentration at the inlet and outlet of the reactor in the residual oil hydrogenation liquid system. in and L out Indicates the inlet and outlet flow rates of the reactor bed; (Formula 3) is used to fit the relationship between the amount of metal deposition and time t based on the aforementioned operating data;

[0031] Establishing the kinetic model for the hydrogenation refining reaction includes:

[0032]

[0033] Among them, c i k represents the concentration of impurity i. i n represents the reaction rate constant of impurity i. i Let i be the reaction order of hydrogenation to remove impurities. Let k represent the catalyst deactivation function for impurity i, where LHSV is the liquid hourly space velocity (LHSV) and k is the catalyst deactivation function for impurity i. i Represented as:

[0034]

[0035] Substituting (Equation 2) and (Equation 5) into (Equation 4), the resulting kinetic model for the hydrogenation refining reaction includes:

[0036]

[0037]

[0038] Based on the operating condition data in the preset database, for k i,0 E a,i α i β i γ i and ni The unknown dynamic parameters are fitted and solved. The calculation results are used to determine whether the squared error between the calculated value and the experimental value has reached the minimum value through (Formula 7). The parameter values ​​are iteratively modified until the minimum value is reached, and the final results of each unknown dynamic parameter are generated.

[0039] For the hydrocracking reaction, a lumped kinetic model of the hydrocracking reaction is established.

[0040] Preferably, in this invention, the step of dividing and establishing a lumped model of the hydrocracking reaction includes:

[0041] The lumped group is divided into four lumped groups, and the flow of the reaction network corresponding to the lumped group division is determined;

[0042] Based on the reaction network flow, a first-order reaction kinetic model is established for both catalyst deactivation and the assumed reaction, including:

[0043]

[0044]

[0045]

[0046]

[0047] Where y represents the overall yield of each set. Represents the deactivation factor, k is the apparent rate constant of each reaction, and the specific reactions involved in hydrorefining include: hydrodesulfurization, hydrodemetallization, and hydrodecarbonization.

[0048] Impurities such as sulfur, residual carbon, nickel, and vanadium in the residue oil are considered as a lumped aggregate and described using an n-order power-law model. The same method is used to fit and generate the kinetic parameters of the hydrocracking reaction.

[0049] Preferably, in this invention, the step of generating operating condition simulation data based on the mechanism model using the operating condition data as input includes:

[0050] Using the operating condition data as input, operating condition simulation data with a sampling frequency greater than a preset multiple of the operating condition data is generated according to the mechanism model.

[0051] Preferably, in this invention, generating modeling data based on the operating condition data and the operating condition simulation data includes:

[0052] Based on two adjacent working condition data, the working condition simulation data whose sampling time point is between the two adjacent working condition data is filtered, and the working condition simulation data that meets the preset filtering rules is used as the filling data between the two adjacent working condition data.

[0053] The modeling data is generated by combining the operating condition data and the filling data.

[0054] Preferably, in this invention, the preset filtering rules include:

[0055] For a given set of operating condition data, calculate the slope of two adjacent sets of operating condition data, and the slope of each set of operating condition simulation data whose sampling time point is between two adjacent sets of operating condition data.

[0056] The simulation data of the operating condition whose slope is between the slopes of two adjacent operating condition data are determined as the fill data between the two adjacent operating condition data.

[0057] Preferably, in this invention, determining the control strategy of the hydrogenation unit based on the difference between the preset optimal operating condition data and the preset predicted operating condition data includes:

[0058] The preset operating conditions include operating temperature and / or operating pressure;

[0059] When the preset operating condition includes the operating temperature, the preset operating condition prediction data is set as the operating temperature prediction data T1; the preset operating condition optimal data is set as the operating temperature optimal data T2; the adjustment amount of the operating temperature is determined according to ΔT=T1-T2;

[0060] When the preset operating condition includes operating pressure, the preset operating condition prediction data is set as operating pressure prediction data P1; the preset operating condition optimal data is set as operating pressure optimal data P2; the adjustment amount of operating pressure is determined according to: ΔP=P1-P2.

[0061] In another aspect of the invention, an apparatus for optimizing the operation of a hydrogenation unit is also provided, comprising:

[0062] The data acquisition unit is used to acquire and store various operating condition data of the hydrogenation unit into a preset database; the operating condition data includes at least: process parameter data, feed property data, product material data, catalyst ratio data, actual operating temperature and actual operating pressure of the hydrogenation unit, as well as fault shutdown data and optimal operating condition data;

[0063] A mechanism model generation unit is used to construct a mechanism model of the hydrogenation device based on the operating condition data.

[0064] The simulation data generation unit is used to generate simulation data based on the mechanism model, taking the operating condition data as input; the simulation data includes simulation data corresponding to the preset operating condition data.

[0065] The learning model generation unit is used to generate modeling data based on the operating condition data and the operating condition simulation data, and to generate a machine learning model for predicting the optimal operating condition of the hydrogenation unit through data training.

[0066] The on-site operating condition calculation unit is used to acquire the current process parameter data of the hydrogenation unit in real time, and to obtain the optimal data of the preset operating condition when the optimal operating condition is obtained through the machine learning model using the current process parameter data as input; and to predict the preset operating condition prediction data of the hydrogenation unit at the next moment using the mechanism model using the current process parameter data as input.

[0067] The control strategy determination unit is used to determine the control strategy of the hydrogenation unit based on the difference between the preset operating condition optimal data and the preset operating condition prediction data.

[0068] In another aspect of this invention, a hydrogenation unit operation optimization device is also provided, comprising:

[0069] Memory, used to store computer programs;

[0070] A processor for invoking and executing the computer program to implement the various steps of the hydrogenation unit operation optimization method as described in any of the preceding claims.

[0071] In another aspect of the present invention, a storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the various steps of the hydrogenation apparatus operation optimization method as described in any of the preceding claims.

[0072] The hydrogenation unit operation optimization device includes a computer program stored on a medium. The computer program includes program instructions that, when executed by a computer, cause the computer to perform the methods described in the above aspects and achieve the same technical effects.

[0073] Compared with the prior art, the present invention has the following beneficial effects:

[0074] In this invention, a corresponding mechanism model is constructed based on historical data of the operating conditions of the hydrogenation unit. Then, the simulation data of the operating conditions obtained from the mechanism model is used to generate filler data for the operating conditions. In this way, by fusing the filler data with the operating conditions data, a sufficient amount of modeling data can be obtained for model training to generate a machine learning model for the hydrogenation unit.

[0075] This invention also uses real-time acquired current process parameter data of the hydrogenation unit as input, and performs calculations through a mechanistic model and a machine learning model to obtain optimal data and predicted data for preset operating conditions. This allows for the determination of adjustable preset operating conditions such as operating temperature and pressure, ensuring the hydrogenation unit operates under optimal conditions in real time. In this way, the hydrogenation unit can avoid operating under unreasonable conditions, reduce abnormal downtime, and fully utilize its maximum designed processing capacity, thereby improving production efficiency.

[0076] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it according to the contents of the specification, and to make the above and other objects, technical features and advantages of the present invention easier to understand, one or more preferred embodiments are listed below and described in detail with reference to the accompanying drawings. Attached Figure Description

[0077] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0078] Figure 1 This is a flowchart illustrating the steps of the hydrogenation unit operation optimization method described in this invention;

[0079] Figure 2 This is a schematic diagram of the reaction network process described in this invention;

[0080] Figure 3 This is a schematic diagram of the operation optimization device for the hydrogenation unit described in this invention;

[0081] Figure 4 This is a schematic diagram of the equipment structure for optimizing the operation of the hydrogenation device described in this invention. Detailed Implementation

[0082] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings, but it should be understood that the scope of protection of the present invention is not limited to the specific embodiments.

[0083] Unless otherwise expressly stated, throughout the specification and claims, the term "comprising" or its variations such as "including" or "comprises" shall be understood to include the stated elements or components without excluding other elements or other components.

[0084] In this document, the terms "first," "second," etc., are used to distinguish two different elements or parts, and are not used to define specific positions or relative relationships. In other words, in some embodiments, the terms "first," "second," etc., can also be used interchangeably.

[0085] Example 1

[0086] To improve production efficiency while avoiding unreasonable operating conditions and reducing abnormal shutdowns, it is essential to fully utilize the maximum processing capacity designed for the equipment. Figure 1 As shown, an embodiment of the present invention provides a method for optimizing the operation of a hydrogenation unit, comprising the following steps:

[0087] S11. Acquire and store various operating condition data of the hydrogenation unit to a preset database; the operating condition data includes at least: process parameter data, feed property data, product material data, catalyst ratio data, actual operating temperature and actual operating pressure of the hydrogenation unit, as well as fault shutdown data and optimal operating condition data.

[0088] Various operating condition data of the hydrogenation unit can be collected through DCS (Distributed Control System) or other instruments and meters. These include data on feedstock properties, catalyst ratios, operating temperature, and operating pressure. This data, combined with historical fault and shutdown data and optimal operating condition labels, forms the operating condition dataset for the hydrogenation unit. Specifically, feedstock property data can include operating temperature, operating pressure, and hydrogen replenishment at the hydrogenation unit's inlet and outlet points. Product material data can include sulfur content, nitrogen content, metal content, residual carbon content, and slag blending ratio obtained through oil analysis of the feedstock and / or blended feedstock, as well as the processed products. Catalyst ratio data can include catalyst type and gradation.

[0089] In practical applications, the default database can be set up on a cloud server.

[0090] S12. Construct a mechanism model of the hydrogenation device based on the operating condition data;

[0091] The mechanism model in the embodiments of the present invention may specifically include a hydrorefining reaction kinetic model, a hydrocracking reaction kinetic model, and a catalyst deactivation kinetic model;

[0092] The specific generation methods for each model in the mechanistic model can be as follows:

[0093] Based on the catalyst deactivation law, a deactivation dynamics equation model is established, including:

[0094]

[0095] (Formula 1), This indicates deactivation caused by coke deposition. This indicates deactivation caused by metal deposition, and i indicates the type of impurities in the residue oil;

[0096] The catalyst deactivation kinetic model can be expressed as:

[0097]

[0098] In (Formula 2), α i Indicates catalyst deactivation rate, β i Let W represent the deactivation level, and W represent the ratio of the metal deposition amount MOC to the planned and overall mass. The metal deposition amount MOC is:

[0099]

[0100] In (Formula 3), c metal.0 and c metal.t The L represents the metal concentration at the inlet and outlet of the reactor in the residual oil hydrogenation liquid system. in and L out Indicates the inlet and outlet flow rates of the reactor bed;

[0101] Establishing the kinetic model for the hydrogenation refining reaction includes:

[0102]

[0103] In (Formula 4), c i k represents the concentration of impurity i. i n represents the reaction rate constant of impurity i. i Let i be the reaction order of hydrogenation to remove impurities. Let k represent the catalyst deactivation function for impurity i, where LHSV is the liquid hourly space velocity (LHSV) and k is the catalyst deactivation function for impurity i. i Represented as:

[0104]

[0105] Substituting (Equation 2) and (Equation 5) into (Equation 4), the resulting kinetic model for the hydrogenation refining reaction includes:

[0106]

[0107]

[0108] Based on the operating condition data in the preset database, for k i,0 E a,i α i βi γ i and n i The unknown dynamic parameters are fitted and solved. The calculation results are used to determine whether the squared error between the calculated value and the experimental value has reached the minimum value through (Formula 7). The parameter values ​​are iteratively modified until the minimum value is reached, and the final results of each unknown dynamic parameter are generated.

[0109] For the hydrocracking reaction, a lumped model of the hydrocracking reaction is established.

[0110] When the lumped cluster is divided into four lumped clusters, establishing a hydrocracking reaction kinetic model may specifically include the following sub-steps:

[0111] The process for determining the reaction network corresponding to the lumped partitioning; the process of the reaction network is as follows: Figure 2 As shown;

[0112] Based on the reaction network flow, a first-order reaction kinetic model is established for both catalyst deactivation and the assumed reaction, including:

[0113]

[0114]

[0115]

[0116]

[0117] Where y represents the overall yield of each set. Represents the deactivation factor, k is the apparent rate constant of each reaction, and the specific reactions involved in hydrorefining include: hydrodesulfurization, hydrodemetallization, and hydrodecarbonization.

[0118] Impurities such as sulfur, residual carbon, nickel, and vanadium in the residual oil are considered as a lumped aggregate and described using an n-order power-law model. The same method is used to fit and generate the hydrocracking reaction kinetic parameters.

[0119] S13. Using the operating condition data as input, generate operating condition simulation data according to the mechanism model; the operating condition simulation data includes simulation data corresponding to the preset operating condition data;

[0120] The mechanism model in this embodiment of the invention can generate operating condition simulation data based on operating condition data, that is, estimate the operating condition simulation data at any point in time during the entire data acquisition period; in this way, a large amount of operating condition simulation data can be generated.

[0121] In this embodiment of the invention, the purpose of generating working condition simulation data is to address the issue that the amount of actual working condition data collected is too small to be used to build a high-performance machine learning model. Therefore, the sampling frequency of the working condition simulation data generated by the mechanism model is much greater than the sampling frequency of the actual working condition data. In practical applications, the sampling frequency of the generated working condition simulation data can be set to a preset multiple of the actual sampling frequency of the working condition data. It should be noted that this preset multiple can be set by those skilled in the art as needed, and no specific limitation is made here.

[0122] S14. Generate modeling data based on the operating condition data and the operating condition simulation data, and generate a machine learning model for predicting the optimal operating condition of the hydrogenation unit through data training.

[0123] Since the operating condition simulation data generated by the mechanism model in this embodiment of the invention are all estimated values, there may be data anomalies. Therefore, in this embodiment of the invention, abnormal data can be further filtered out by data screening, thereby improving the performance of the machine learning model generated from the operating condition simulation data.

[0124] Specific data filtering methods may include:

[0125] Based on two adjacent operating condition data points, the operating condition simulation data whose sampling time points are between the two adjacent operating condition data points are filtered, and the operating condition simulation data that meet the preset filtering rules are used as fill data between the two adjacent operating condition data points; preferably, the preset filtering rules may specifically include:

[0126] For a given set of operating condition data, calculate the slope of two adjacent sets of operating condition data, and the slope of each set of operating condition simulation data whose sampling time point is between two adjacent sets of operating condition data.

[0127] The simulation data of the operating condition whose slope is between the slopes of two adjacent operating condition data are determined as the fill data between the two adjacent operating condition data.

[0128] The modeling data is generated by combining the operating condition data and the filling data.

[0129] The following example, using operating temperature as the operating condition data, illustrates the relationship between operating condition simulation data and actual operating condition data in this embodiment of the invention:

[0130] Let the actual operating conditions be: T D =(T1) D ,...,T i D ,...,T n DThe sampling frequency is m, and the data volume is n. The corresponding operating condition simulation data has the same sampling time period as the operating condition data. The sampling frequency of the generated operating condition simulation data is i times the actual sampling frequency of the operating condition data (i.e., the sampling frequency is i*m), and the data volume of the operating condition simulation data is n*i. The operating condition simulation data is: T M =(T1) M ,…T n M ,T n+1 M ,…T n*i M Each i-th operating condition simulation data corresponds to one operating condition data; these i-th operating condition simulation data are the operating condition simulations between two adjacent operating condition data.

[0131] When the working condition simulation data slope at Satisfying the condition: When the simulation data of the working condition is determined to be usable as filler data, it is placed in the working condition data K during data fusion. i D and K i+1 D Between. It should be noted that in the above conditional formula, the operating condition simulation data For two adjacent operating condition data T i D and T i+1 D The operating condition simulation data between the two conditions The value of the subscript X is based on the working condition data K. i D The value of subscript i is determined, and the specific range of values ​​for X is: i*m≤X≤(i+1)*m; K i D It is the operating condition data T i D Slope at point K; i+1 D It is the operating condition data T i+1 D The slope at that point.

[0132] Based on the modeling data, a machine learning model is trained to fit the relationship between factors such as residue oil properties, finished oil properties, hydrogen consumption, catalyst, and optimal operating temperature and pressure, thereby establishing the optimal match between raw material processing properties and unit operating conditions.

[0133] S15. Real-time acquisition of the current process parameter data of the hydrogenation unit; using the current process parameter data as input, obtaining the optimal operating condition data of the preset operating condition when the optimal operating condition is obtained through the machine learning model; using the current process parameter data as input, predicting the operating condition prediction data of the preset operating condition of the hydrogenation unit at the next moment through the mechanism model.

[0134] The mechanism model in this embodiment of the invention can not only generate operating condition simulation data, but also predict the preset operating condition data of the hydrogenation unit at the next moment based on the current process parameter data (i.e., preset operating condition prediction data); such as the estimated operating temperature and operating pressure at the next moment (i.e., the preset operating condition prediction data are operating temperature prediction data and operating pressure prediction data), etc.

[0135] The machine learning model in this embodiment of the invention can predict the optimal operating condition data (i.e., the optimal data of the preset operating condition) that matches the best operating condition at the next moment; for example, the estimated optimal operating temperature and optimal operating pressure at the next moment (i.e., the optimal data of the preset operating condition is the optimal data of the operating temperature and the optimal data of the operating pressure).

[0136] In practical applications, the modeling algorithms used in the machine learning models in the embodiments of the present invention include, but are not limited to, support vector machines, random forests, neural networks, etc.

[0137] S16. Determine the control strategy of the hydrogenation unit based on the difference between the preset optimal operating condition data and the preset predicted operating condition data.

[0138] The difference between the optimal preset operating condition data and the predicted preset operating condition data is the target for the hydrogen refueling unit to adjust the preset operating condition at the next moment; therefore, the control strategy of the hydrogen refueling unit can be determined based on the difference between the optimal preset operating condition data and the predicted preset operating condition data.

[0139] Preferably, in this embodiment of the invention, the method for determining the control strategy of the hydrogenation unit may specifically include:

[0140] The preset operating conditions include operating temperature and / or operating pressure;

[0141] When the preset operating condition includes the operating temperature, the preset operating condition prediction data is set as the operating temperature prediction data T1; the preset operating condition optimal data is set as the operating temperature optimal data T2; the adjustment amount of the operating temperature is determined according to ΔT=T1-T2;

[0142] When the preset operating condition includes operating pressure, the preset operating condition prediction data is set as operating pressure prediction data P1; the preset operating condition optimal data is set as operating pressure optimal data P2; the adjustment amount of operating pressure is determined according to: ΔP=P1-P2.

[0143] In this embodiment of the invention, the current process parameter data of the hydrogenation unit is used as input in real time to generate adjustment amounts for each preset operating condition. The operator can then dynamically control the operating status of the unit according to the adjustment amounts for each preset operating condition, thereby ensuring that the hydrogenation unit is always in optimal operating condition.

[0144] In summary, in this embodiment of the invention, a corresponding mechanism model is constructed based on historical data of the operating conditions of the hydrogenation unit. Then, simulation data of the operating conditions obtained from the mechanism model is used to generate filler data for the operating conditions. In this way, by fusing the filler data with the operating conditions data, a sufficient amount of modeling data can be obtained for model training to generate a machine learning model for the hydrogenation unit.

[0145] This invention also uses real-time acquired current process parameter data of the hydrogenation unit as input, and performs calculations through a mechanistic model and a machine learning model to obtain optimal data and predicted data for preset operating conditions. This allows for the determination of adjustable preset operating conditions such as operating temperature and operating pressure, ensuring the hydrogenation unit operates under optimal conditions in real time. In this way, the hydrogenation unit can avoid operating under unreasonable conditions, reduce abnormal downtime, and fully utilize its maximum designed processing capacity, thereby improving production efficiency.

[0146] Example 2

[0147] Corresponding to the method embodiments, another aspect of the embodiments of the present invention also provides a hydrogenation unit operation optimization device. Figure 3 This diagram illustrates the structure of a hydrogenation unit operation optimization device provided in an embodiment of the present invention. The hydrogenation unit operation optimization device is... Figure 1 The device corresponding to the hydrogenation unit operation optimization method in the corresponding embodiment is implemented through a virtual device. Figure 1 In the corresponding embodiment of the hydrogen refueling unit operation optimization method, each virtual module constituting the hydrogen refueling unit operation optimization device can be executed by an electronic device, such as a network device, a terminal device, or a server. Specifically, the hydrogen refueling unit operation optimization device in the embodiment of the present invention includes:

[0148] Data acquisition unit 01 is used to acquire and store various operating condition data of the hydrogenation unit to a preset database; the operating condition data includes at least: process parameter data, feed property data, product material data, catalyst ratio data, actual operating temperature and actual operating pressure of the hydrogenation unit, as well as fault shutdown data and optimal operating condition data;

[0149] Mechanism model generation unit 02 is used to construct a mechanism model of the hydrogenation device based on the operating condition data;

[0150] The simulation data generation unit 03 is used to generate simulation data based on the mechanism model, taking the operating condition data as input; the simulation data includes simulation data corresponding to the preset operating condition data.

[0151] The learning model generation unit 04 is used to generate modeling data based on the operating condition data and the operating condition simulation data, and to generate a machine learning model for predicting the optimal operating condition of the hydrogenation unit through data training.

[0152] The on-site operating condition calculation unit 05 is used to acquire the current process parameter data of the hydrogenation unit in real time, and to obtain the optimal data of the preset operating condition when the optimal operating condition is obtained through the machine learning model using the current process parameter data as input; and to predict the preset operating condition prediction data of the hydrogenation unit at the next moment using the mechanism model using the current process parameter data as input.

[0153] The regulation strategy determination unit 06 is used to determine the regulation strategy of the hydrogenation unit based on the difference between the preset operating condition optimal data and the preset operating condition prediction data.

[0154] It should be noted that the specific implementation and technical effects of the hydrogenation unit operation optimization device in the embodiments of the present invention can be referred to... Figure 1 The corresponding optimization methods for hydrogenation unit operation will not be elaborated here.

[0155] Example 3

[0156] Corresponding to the method embodiments, this invention also provides a hydrogen refueling device operation optimization device, such as a terminal or server. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these.

[0157] An example diagram of the hardware structure block diagram of the hydrogenation unit operation optimization equipment provided in this application is shown below. Figure 4 As shown, it may include:

[0158] Processor 1, communication interface 2, memory 3, and communication bus 4;

[0159] The processor 1, communication interface 2, and memory 3 communicate with each other via communication bus 4.

[0160] Optionally, communication interface 2 can be an interface of a communication module, such as the interface of a GSM module;

[0161] Processor 1 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0162] Memory 3 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0163] Specifically, processor 1 is used to execute the computer program stored in memory 3 to perform the following steps:

[0164] S11. Acquire and store various operating condition data of the hydrogenation unit to a preset database; the operating condition data includes at least: process parameter data, feed property data, product material data, catalyst ratio data, actual operating temperature and actual operating pressure of the hydrogenation unit, as well as fault shutdown data and optimal operating condition data.

[0165] S12. Construct a mechanism model of the hydrogenation device based on the operating condition data;

[0166] S13. Using the operating condition data as input, generate operating condition simulation data according to the mechanism model; the operating condition simulation data includes simulation data corresponding to the preset operating condition data;

[0167] S14. Generate modeling data based on the operating condition data and the operating condition simulation data, and generate a machine learning model for predicting the optimal operating condition of the hydrogenation unit through data training.

[0168] S15. Real-time acquisition of the current process parameter data of the hydrogenation unit; using the current process parameter data as input, obtaining the optimal operating condition data of the preset operating condition when the optimal operating condition is obtained through the machine learning model; using the current process parameter data as input, predicting the operating condition prediction data of the preset operating condition of the hydrogenation unit at the next moment through the mechanism model.

[0169] S16. Determine the control strategy of the hydrogenation unit based on the difference between the preset optimal operating condition data and the preset predicted operating condition data.

[0170] The above-described product can execute the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the hydrogenation device operation optimization method provided in the embodiments of the present invention.

[0171] Example 4

[0172] In this embodiment of the invention, a storage medium is also provided, which can store a program suitable for execution by a processor, the program being used for:

[0173] S11. Acquire and store various operating condition data of the hydrogenation unit to a preset database; the operating condition data includes at least: process parameter data, feed property data, product material data, catalyst ratio data, actual operating temperature and actual operating pressure of the hydrogenation unit, as well as fault shutdown data and optimal operating condition data.

[0174] S12. Construct a mechanism model of the hydrogenation device based on the operating condition data;

[0175] S13. Using the operating condition data as input, generate operating condition simulation data according to the mechanism model; the operating condition simulation data includes simulation data corresponding to the preset operating condition data;

[0176] S14. Generate modeling data based on the operating condition data and the operating condition simulation data, and generate a machine learning model for predicting the optimal operating condition of the hydrogenation unit through data training.

[0177] S15. Real-time acquisition of the current process parameter data of the hydrogenation unit; using the current process parameter data as input, obtaining the optimal operating condition data of the preset operating condition when the optimal operating condition is obtained through the machine learning model; using the current process parameter data as input, predicting the operating condition prediction data of the preset operating condition of the hydrogenation unit at the next moment through the mechanism model.

[0178] S16. Determine the control strategy of the hydrogenation unit based on the difference between the preset optimal operating condition data and the preset predicted operating condition data.

[0179] Optionally, the refined and extended functions of the program can be found in the description above.

[0180] The above-described product can execute the methods provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the methods. Technical details not described in detail in this embodiment can be found in the methods provided in other embodiments of the present invention.

[0181] The above-described product can execute the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method provided in the embodiments of the present invention.

[0182] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0183] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0184] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0185] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0186] It should be understood that in the embodiments of this application, the claims, various embodiments, and features can be combined with each other to solve the aforementioned technical problems.

[0187] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0188] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for optimizing the operation of a hydrogenation unit, characterized in that, Including the following steps: S11. Acquire and store various operating condition data of the hydrogenation unit to a preset database; the operating condition data includes at least: process parameter data, feed property data, product material data, catalyst ratio data, actual operating temperature and actual operating pressure of the hydrogenation unit, as well as fault shutdown data and optimal operating condition data. S12. Construct a mechanism model of the hydrogenation device based on the operating condition data; S13. Using the operating condition data as input, generate operating condition simulation data according to the mechanism model; the operating condition simulation data includes simulation data corresponding to the preset operating condition data; S14. Generate modeling data based on the operating condition data and the operating condition simulation data, and generate a machine learning model for predicting the optimal operating condition of the hydrogenation unit through data training. S15. Real-time acquisition of the current process parameter data of the hydrogenation unit; using the current process parameter data as input, obtaining the optimal operating condition data of the preset operating condition when the optimal operating condition is obtained through the machine learning model; using the current process parameter data as input, predicting the operating condition prediction data of the preset operating condition of the hydrogenation unit at the next moment through the mechanism model. S16. Determine the control strategy of the hydrogenation unit based on the difference between the preset operating condition optimal data and the preset operating condition prediction data; The acquisition and storage of various operating condition data of the hydrogenation unit into a preset database includes: Data on feedstock properties, catalyst ratio, operating temperature, and operating pressure of the hydrogenation unit are collected and recorded. The operating condition dataset of the hydrogenation unit is then established by combining the corresponding fault shutdown data and the optimal operating condition label from historical data. The feed physical property data includes: the operating temperature, operating pressure and hydrogen replenishment amount at the inlet and outlet of the hydrogenation unit; The product material data includes: sulfur content, nitrogen content, metal content, residual carbon content, and slag blending ratio obtained by oil analysis of feed oil and / or mixed feed oil and the product obtained after processing; The catalyst formulation data includes: catalyst type and gradation; The construction of the mechanism model of the hydrogenation unit based on the operating condition data includes: The mechanistic model includes a hydrorefining reaction kinetic model, a hydrocracking reaction kinetic model, and a catalyst deactivation kinetic model. Based on the catalyst deactivation law, a deactivation dynamics equation model is established, including: ； in, This indicates deactivation caused by coke deposition. This indicates deactivation caused by metal deposition. Indicates the type of impurities in the residual oil; The catalyst deactivation kinetic model is expressed as follows: ； in, Indicates catalyst deactivation rate. Indicates the deactivation series. Indicates the amount of metal deposited Compared with the planned and overall quality, the amount of metal deposited for: ； This indicates the metal concentration at the inlet and outlet of the reactor in the residual oil hydrogenation liquid system. and Indicates the inlet and outlet flow rates of the reactor bed; Establishing the kinetic model for the hydrogenation refining reaction includes: ； in, Indicates impurities concentration, Indicates impurities The reaction rate constant, For hydrogenation to remove impurities The reaction order, Indicates the target impurities Catalyst deactivation function, is the liquid hourly space velocity, where Represented as: ； Substituting (Equation 2) and (Equation 5) into (Equation 4), the resulting kinetic model for the hydrorefining reaction includes: ； ； Based on the operating condition data in the preset database, The unknown dynamic parameters are fitted and solved. The calculation results are used to determine whether the squared error between the calculated value and the experimental value has reached the minimum value through Formula 7. The parameter values ​​are iteratively modified until the minimum value is reached, and the final results of each unknown dynamic parameter are generated. For the hydrocracking reaction, a lumped model of the hydrocracking reaction is established. The aforementioned hydrocracking reaction, through lumped partitioning, establishes a kinetic model of the hydrocracking reaction, including: The lumped group is divided into four lumped groups, and the flow of the reaction network corresponding to the lumped group division is determined; Based on the reaction network flow, a first-order reaction kinetic model is established for both catalyst deactivation and the assumed reaction, including: ； in, This represents the overall yield of each set. Indicates the inactivation factor. The apparent rate constants of each reaction, and the specific reactions involved in hydrorefining include: hydrodesulfurization, hydrodemetallization, and hydrodecarbonization. Impurities such as sulfur, residual carbon, nickel, and vanadium in residual oil are considered as a aggregate, and a method is adopted. The power-law model is used to describe the hydrocracking reaction kinetic parameters, and the same method is used to fit and generate them.

2. The method for optimizing the operation of a hydrogenation unit according to claim 1, characterized in that, The step of generating operating condition simulation data based on the mechanism model, using the operating condition data as input, includes: Using the operating condition data as input, operating condition simulation data with a sampling frequency greater than a preset multiple of the operating condition data is generated according to the mechanism model.

3. The method for optimizing the operation of a hydrogenation unit according to claim 2, characterized in that, The step of generating modeling data based on the operating condition data and the operating condition simulation data includes: Based on two adjacent working condition data, the working condition simulation data whose sampling time point is between the two adjacent working condition data is filtered, and the working condition simulation data that meets the preset filtering rules is used as the filling data between the two adjacent working condition data. The modeling data is generated by combining the operating condition data and the filling data.

4. The method for optimizing the operation of a hydrogenation unit according to claim 3, characterized in that, The preset filtering rules include: For a given set of operating condition data, calculate the slope of two adjacent sets of operating condition data, and the slope of each set of operating condition simulation data whose sampling time point is between two adjacent sets of operating condition data. The simulation data of the operating condition whose slope is between the slopes of two adjacent operating condition data are determined as the fill data between the two adjacent operating condition data.

5. The method for optimizing the operation of a hydrogenation unit according to claim 1, characterized in that, The step of determining the control strategy of the hydrogenation unit based on the difference between the preset optimal operating condition data and the preset predicted operating condition data includes: The preset operating conditions include operating temperature and / or operating pressure; When the preset operating condition includes operating temperature, the preset operating condition prediction data is defined as the operating temperature prediction data. The preset optimal operating condition data is the optimal operating temperature data. ;according to Determine the adjustment amount for the operating temperature; When the preset operating condition includes operating pressure, the preset operating condition prediction data is defined as the operating pressure prediction data. The preset optimal operating condition data is the optimal operating pressure data. ;according to: Determine the adjustment amount of the operating pressure.

6. A hydrogenation unit operation optimization apparatus, used to implement the hydrogenation unit operation optimization method as described in any one of claims 1 to 5; characterized in that, include: The data acquisition unit is used to acquire and store various operating condition data of the hydrogenation unit into a preset database; The operating data includes at least: process parameter data, feed property data, product material data, catalyst ratio data, actual operating temperature and actual operating pressure of the hydrogenation unit, as well as fault shutdown data and optimal operating condition data. A mechanism model generation unit is used to construct a mechanism model of the hydrogenation device based on the operating condition data. The simulation data generation unit is used to generate simulation data based on the mechanism model, taking the operating condition data as input; the simulation data includes simulation data corresponding to the preset operating condition data. The learning model generation unit is used to generate modeling data based on the operating condition data and the operating condition simulation data, and to generate a machine learning model for predicting the optimal operating condition of the hydrogenation unit through data training. The on-site operating condition calculation unit is used to acquire the current process parameter data of the hydrogenation unit in real time, and to obtain the optimal data of the preset operating condition when the optimal operating condition is obtained through the machine learning model using the current process parameter data as input; and to predict the preset operating condition prediction data of the hydrogenation unit at the next moment using the mechanism model using the current process parameter data as input. The control strategy determination unit is used to determine the control strategy of the hydrogenation unit based on the difference between the preset operating condition optimal data and the preset operating condition prediction data.

7. A device for optimizing the operation of a hydrogenation unit, characterized in that, include: Memory, used to store computer programs; A processor for invoking and executing the computer program to implement the steps of the hydrogenation unit operation optimization method as described in any one of claims 1-5.

8. A storage medium, characterized in that, Includes a software program adapted for execution by a processor of the steps of the hydrogenation apparatus operation optimization method as described in any one of claims 1-5.

Images