WO2023128826A1 - Système de pronostic de contenu en soufre de carburant diesel purifié par hydroraffinage - Google Patents

Système de pronostic de contenu en soufre de carburant diesel purifié par hydroraffinage Download PDF

Info

Publication number
WO2023128826A1
WO2023128826A1 PCT/RU2022/050374 RU2022050374W WO2023128826A1 WO 2023128826 A1 WO2023128826 A1 WO 2023128826A1 RU 2022050374 W RU2022050374 W RU 2022050374W WO 2023128826 A1 WO2023128826 A1 WO 2023128826A1
Authority
WO
WIPO (PCT)
Prior art keywords
flow rate
hydrotreater
inlet
model
diesel fuel
Prior art date
Application number
PCT/RU2022/050374
Other languages
English (en)
Russian (ru)
Inventor
Олег Сергеевич ВЕДЕРНИКОВ
Александр Васильевич ПАНОВ
Дмитрий Юрьевич КЛИМИН
Алексей Евгеньевич ПУЗЫРЕВ
Виталий Михайлович ПАМПУРА
Дамир МУХАЕВ
Андрей Андреевич КУСАКОВ
Руслан Фаридович МЕРКУЛОВ
Original Assignee
Публичное акционерное общество "Газпром нефть"
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from RU2021139603A external-priority patent/RU2786373C1/ru
Application filed by Публичное акционерное общество "Газпром нефть" filed Critical Публичное акционерное общество "Газпром нефть"
Publication of WO2023128826A1 publication Critical patent/WO2023128826A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/17—Function evaluation by approximation methods, e.g. inter- or extrapolation, smoothing, least mean square method
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/70—Machine learning, data mining or chemometrics

Definitions

  • the present invention generally relates to a system and method for controlling a process plant such as, for example, a middle distillate refinery, and more particularly to a system and method for predicting the sulfur content of hydrotreated diesel fuel.
  • the proposed invention relates to a computer-readable medium containing a software product that, when executed by a processor, provides the ability to predict the sulfur content of hydrotreated diesel fuel.
  • hydrotreating is a process of upgrading raw materials on the active surface of a catalyst in a hydrogen-containing gas (HCG) environment.
  • the kinetics of the hydrotreating process is significantly affected by a number of factors, including, for example, temperature, pressure, feed space velocity, HCG cycle times, cycle gas purity, hydrogen partial pressure, contact time of the feed with the catalyst in the reaction zone, activity catalyst. It is extremely difficult for the plant operator to control some of these parameters, but these parameters must be taken into account in order to effectively control the plant. In this case, the process is controlled primarily by changing the temperature in the reaction zone.
  • the proposed method, system and computer-readable medium provide the ability to accurately predict the sulfur content in hydrotreated diesel fuel between laboratory analyzes, which in turn allows you to optimize the diesel hydrotreatment process and reduce the frequency of laboratory analyzes.
  • Real-time product characterization without lab analysis avoids refining during diesel hydrotreating and reduces the risk of off-spec products.
  • a system for predicting the sulfur content of hydrotreated diesel fuel.
  • the proposed system includes a block for receiving parameter values, configured to receive the first set of parameter values of the hydrotreating process, while the parameter values of the hydrotreating process include data from laboratory analyzes of raw materials at the inlet of the diesel fuel hydrotreater (HD DF) and hydrotreated diesel fuel at the outlet of the said unit and data from the sensors of the installation of GO DT; a parameter value storage unit configured to store the received hydrotreating process parameter values as one or more time series; a filtering unit configured to filter the stored time series values using Shewhart's control charts; a model generation and training unit configured to: generate a training set based on the filtered values of the time series, determine the optimal size of the moving learning window based on the standard deviation of the sulfur content in hydrotreated diesel fuel and the maximum of the correlation coefficient, generate a model for predicting the sulfur content in hydrotreated diesel fuel , while the model is a polynomial regression model
  • the parameter receiving unit can be configured to receive new values of the parameters of the hydrotreating process
  • the model generation and training unit can be configured to automatically retrain the models based on the mentioned received new values of the parameters of the hydrotreating process.
  • the prediction block can be configured to transmit data on the predicted value of the temperature at the inlet to the reactor to the terminal of the operator and / or process engineer or to the control unit of the GO DF unit.
  • the adjacent members of the model generated by the formation and training unit can be in different combinations:
  • the model generated by the model generation and training unit may be of the following form: 4D Yu D a 4 D and 1 4 gg DD 4 Doi To D1
  • a system for predicting the sulfur content in hydrotreated diesel fuel including: a parameter value receiving unit configured to receive parameter values of the hydrotreating process, while the parameter values of the hydrotreating process include data from laboratory analyzes of raw materials on the inlet of the diesel fuel hydrotreater (GO DF) and the hydrotreated diesel fuel at the outlet of the mentioned installation and data from the sensors of the GO DF installation; a parameter value storage unit configured to store the received parameter values of the hydrotreating process; a prediction unit configured to predict the sulfur content of the hydrotreated diesel fuel GO DF at the outlet of the hydrotreater using a trained polynomial regression model with adjacent terms based on the mentioned values; at the same time, the regressors of the mentioned regression model are the mentioned parameters of the hydrotreatment process, including: the flow rate R1 of raw materials per thread, the point R2 of boiling point of 50% of the raw hydrotreating unit, feedstock consumption R5 for hydrotreatment unit, feedstock hydrogen
  • a method for predicting sulfur content in hydrotreated diesel fuel including: receiving and storing a first set of hydrotreating process parameter values in the form of one or more time series, wherein the hydrotreating process parameter values include data from laboratory analyzes of raw materials at the plant inlet hydrotreatment of diesel fuel (HD DF) and hydrotreated diesel fuel at the outlet of the mentioned installation and data from the sensors of the installation of GO DT; filtering stored time series values using Shewhart control charts; formation of a training set based on filtered time series; determining the optimal size of the moving learning window based on the standard deviation of the sulfur content in the GO of diesel fuel and the maximum of the correlation coefficient; formation of a model for predicting the sulfur content in the GO of diesel fuel, while the model is a polynomial regression model of an arbitrary order with adjacent terms, the regressors of which are the mentioned process parameters, including: consumption R1 of raw materials per string, point R2 of boiling 50% of raw materials at the in
  • the method may further include the step of obtaining new hydrotreating process parameter values and automatically retraining the model based on said new hydrotreating process parameter values.
  • the method may further include the step of transmitting the predicted reactor inlet temperature to an operator and/or process engineer's terminal or plant control unit.
  • the adjacent members of the model formed according to the method may be: the flow rate R1 of the raw material per thread and the boiling point R2 of 50% of the raw material at the inlet to the hydrotreater;
  • the model generated according to the proposed method may have the following form:
  • a method for predicting the sulfur content in hydrotreated diesel fuel including: receiving and storing the values of the parameters of the hydrotreating process in a memory device, while the values of the parameters of the hydrotreating process include data from laboratory analyzes of raw materials at the inlet of the diesel fuel hydrotreater (HD DF ) and hydrotreated diesel fuel at the outlet of the mentioned installation and data from sensors of the installation of GO DT; forecasting the sulfur content in hydrotreated diesel fuel at the outlet of the GO DF unit using a trained polynomial regression model with adjacent terms based on the mentioned set of values, while the regressors of the mentioned regression model are the mentioned parameters of the hydrotreating process, including: raw material consumption R1 per string, boiling point R2 50% Feedstock Inlet to Hydrotreater, Boil-Off Point R3 95% Feedstock Inlet to Hydrotreater, Density R4 Feedstock Inlet to Hydrotreater, Feedrate R5 Feed to Hydrotrea
  • a computer readable medium comprising a computer program product with program instructions that, when executed by a processor, perform the above methods.
  • Figure 1 is a schematic representation of a typical diesel hydrotreater in accordance with the prior art.
  • Figure 2 is a schematic diagram of a diesel hydrotreater with a hydrotreated diesel sulfur prediction system in accordance with the present invention
  • FIG. 3 shows a graph of the sulfur content in the DH HE built on the basis of real historical (retrospective) data, and a graph of the sulfur content in the DH HE built on the basis of the values calculated by the trained model.
  • FIG. 1 shows an example of a typical diesel fuel hydrotreater (HDF) unit 11 comprising, without limitation, two reactors 12 that can be used simultaneously.
  • HDF diesel fuel hydrotreater
  • This configuration of unit 11 provides for hydrotreatment in two independent parallel feed streams, which makes it possible to carry out repair work without a complete shutdown of production.
  • the installation 11 GO DF may contain a different number of reactors, for example, one or more than two.
  • the raw material from the buffer tanks 13 of the tank farm is fed by means of the pump 14 to the mixing tee 15, in which the raw material is mixed with circulating hydrogen-containing gas (CVG).
  • CVG hydrogen-containing gas
  • the raw materials can be, for example, light gas oil and straight-run diesel fractions.
  • the gas-feed mixture is heated in the GSS heating means 16, which may include furnaces and/or heat exchangers, and is fed to the inlet of the reactor 12.
  • the CVSG pressure in the hydrogen-containing gas circulation system is provided by the CVSG compressor 17, while in order to maintain the required hydrogen concentration, hydrogen can be supplied to the hydrogen-containing gas circulation system through the make-up WASH compressor 18, obtained, for example, at hydrogen production and / or catalytic reforming plants naphtha.
  • the hydrotreating reactor 12 is the main equipment of the hydrotreating process and is a vertical cylindrical vessel with a convex bottom of a spherical or close to elliptical shape, the height of which is greater than its diameter.
  • reactor 12 can be one-, two-, and multi-sectional: reactors with one or two catalyst beds are typical for distillate hydrodesulfurization plants, and for hydrocracking plants with four to five, cold recirculating HSG (quench) can be supplied to reactor 12, as an additional lever to control the temperature in the reactor 12.
  • Top and bottom layers catalyst may be limited to layers of porcelain beads and/or protective layers larger than the catalyst particles.
  • the catalyst layer becomes less permeable. This is especially true for the upper part. Therefore, the pressure drop in the reactor 12 at the end of the operating run is greater than at the beginning. This effect is explained by a number of factors, for example, the accumulation of corrosion products and coke in the layer, a decrease in the strength of catalyst particles, sintering, etc. With an increase in pressure drop, the costs of circulating hydrogen-containing gas increase.
  • Deactivation of the catalyst leads to a decrease in the activity of the catalyst and, as a consequence, to a decrease in the degree of desulfurization.
  • the consumption of make-up HSG or the pressure of the gas-feed mixture at the inlet to the reactor 12 is increased, or the partial pressure of hydrogen in the mixture is increased.
  • One of the main methods for leveling the deactivation of the catalyst is to increase the temperature of the feed stream at the inlet to the reactor 12. An increase in the temperature of the feed mixture at the inlet to the reactor due to the deactivation of the catalyst leads to an increase in the yield of by-products - gas and gasoline, and therefore reduces the efficiency of the unit 11 GO DF .
  • Catalyst sintering leads to a decrease in the surface of the support, as well as to "coalescence” or loss of fineness of the metal crystallites.
  • the loss of dispersity leads to a sharp decrease in activity. Poisoning by impurities proceeds under the influence of adsorption on the active centers of small amounts of a substance called poison and specific for this catalyst.
  • the feedstock is fed through a nozzle, which may be located in the upper part of the reactor 12, and is evenly distributed over the entire cross section of the reactor 12.
  • the reactor 12 can be provided with a radial input of feedstock.
  • mesh baskets immersed in the top layer of the catalyst can be used. Mesh baskets are not only a filtering device, but also serve to uniformly distribute raw materials with gases over the horizontal section of the reactor 12.
  • ACM aluminum-cobalt-molybdenum
  • AHM aluminum-nickel- molybdenum
  • ANKM mixed aluminum-nickel-cobalt-molybdenum
  • ANV aluminum-cobalt-tungsten catalysts
  • the choice of a particular catalyst depends on the physical and chemical characteristics required in the production, the shape and physical strength of the particles, selectivity, hydrogenation activity, desulfurization activity, operating pressure ranges, etc.
  • the main factors in the hydrotreatment process in the reactor 12 are, for example, temperature, pressure, feed space velocity, HCG cycle times, cycle gas purity, catalyst physicochemical characteristics.
  • the reaction temperature is one of the most important process parameters.
  • the depth and selectivity of hydrotreatment and hydrocracking reactions are very sensitive to it, since their rate constants increase exponentially with increasing temperature. Therefore, to achieve the required selectivity, the temperature must be selected in accordance with the chemistry of the process.
  • the temperature distribution in the reactor 12 is also affected by the loss of catalyst activity. During the cycle, it is compensated by a periodic increase in temperature, as a result of which the amplitude of the temperature profile gradually shifts upward. When the upper temperature limit reaches the maximum allowable for the reactor construction material, the cycle is terminated. At the end of the operating run, the average temperature in the reactor 12 may exceed the initial temperature, for example by 20-60°C. If the temperature along the axis of the reactor 12 is not correctly distributed, premature forced shutdown is possible - especially with a rapid loss of activity, as in the hydrotreatment of residues. In such cases, it is desirable to choose the lowest possible temperature rise in the layer in order to delay the moment of reaching the maximum allowable temperature. This means an increase in the number of layers and, accordingly, the dimensions of the reactor, which is necessary to accommodate additional equipment for intermediate cooling.
  • volumetric feed rate of raw materials Reducing the duration of contact as a result of increasing the space velocity of the feedstock (the ratio of the volume of liquid feedstock entering in 1 hour to the volume of the catalyst, counting by bulk density) reduces the depth of desulfurization. As a result, the consumption of hydrogen and the degree of coking of the catalyst are reduced.
  • the reaction products coming from the outlet of the reactor 12 are separated in the form of a gas-vapor mixture into hydrogen sulfide-enriched CVSG, hydrotreated gasoline and / or GO diesel fuel, as well as purification of hydrogen sulfide-enriched CVSG from reaction products with raw materials.
  • the corresponding devices known in the prior art refrigerators, heat exchangers, condensers, separators, stabilization columns, washing sections, etc. that are part of the purification unit 19 are not shown in the drawings and are not disclosed in this description. .
  • a system 20 for predicting sulfur content in hydrotreated diesel fuel using predictive models that are mathematical regression models is provided.
  • the regressors included in the model are the key parameters of the technological process and the quality indicators of raw materials and product flows.
  • the prediction system 20 includes a hydrotreating parameter value receiving unit 21, a parameter value storage unit 22, a filtering unit 23, a model generation and training unit 24, and a prediction unit 25.
  • the parameter value receiving unit 21 is configured to receive the values of the physical and/or chemical parameters of the hydrotreating process from sensors located on the unit 11.
  • the parameter receiving unit 21 together with the sensors can be, for example, an industrial data acquisition system (DSS), that is, a set of hardware or firmware that collects, selects, converts, stores, and initially processes various input analog and/or digital signals.
  • DSS industrial data acquisition system
  • the sensors can also be structurally and functionally separate devices containing one or more primary measuring transducers that generate a signal with information about the measurement in a form that is compatible with the block 21 receiving parameters.
  • the signal from each of the sensors can be transmitted to the parameter receiving unit 21 via, for example, a wired, fiber optic, wireless connection, or a combination thereof.
  • the sensors may include one or more of the following: a raw material flow sensor R1 per thread, which can be installed on the production line before the mixing tee 15, a raw material flow sensor R5 on installation 11, which can be installed on the production line between the buffer tank 13 and mixing tee 15; be installed at the inlet of the CVSG to the mixing tee 15, sensors R8 for the consumption of diesel fuel and R9 gasoline at the outlet of the unit 11, which can be installed at the outlets of the purification unit 19, sensor R10 for the flow of light gas oil (LG) at the unit 11, sensor R11 for the temperature at the inlet to the reactor 12, which can be installed in the feed line before entering the reactor 12, the pressure sensor R12 at the outlet of the heating means 16, which can be installed at the outlet of the HSS heating furnace.
  • a raw material flow sensor R1 per thread which can be installed on the production line before the mixing tee 15
  • a raw material flow sensor R5 on installation 11 which can be installed on the production line between the buffer tank 13 and mixing tee 15
  • the parameter receiving unit 21 can be configured to receive data from laboratory analyzes, for example, data on the sulfur content R13 in the final product, data on the boiling point R2 of 50% of the feedstock at the inlet of the installation 11 , data on the point R3 of the boiling point 95% of the raw material at the entrance to the installation 11, data on the density R4 of the raw material at the entrance to the installation 11.
  • the sequences of values received by the parameter receiving unit 21 are transferred to the parameter storage unit 22 for indexing these values by the time of measurement or by the time of acquisition and storage in the form of time series.
  • the parameter storage unit 22 can be configured to store the values of various parameters in the form of a plurality of one-dimensional time series, each of which reflects the development of only one process over time, or in the form of one or a plurality of multidimensional time series, each of which contains observations of the change more than one parameter.
  • the values of the time series are obtained by registering the corresponding parameter of the process under study at certain time intervals. In this case, depending on the nature of the data and the nature of the tasks being solved, either the current value or the sum of the values accumulated over a certain time interval can be recorded.
  • the parameter storage unit 22 can also be configured to aggregate data.
  • the parameter storage unit 22 may be configured to record, store, process data, and provide access to data.
  • the parameter storage unit 22 may be implemented using any kind of volatile or non-volatile storage devices or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory , magnetic or optical disk, disk array or other storage device, or any other medium capable of storing the required data and which can be accessed by a computing device.
  • SRAM Static Random Access Memory
  • EEPROM Electrically Erasable Programmable Read Only Memory
  • EPROM Erasable Programmable Read Only Memory
  • PROM Programmable Read Only Memory
  • ROM Read Only Memory
  • Magnetic Memory Flash Memory
  • magnetic or optical disk magnetic or optical disk array or other storage device, or any other medium capable of storing the required data and which can be accessed by a computing device.
  • the parameter storage unit 22 may
  • the filter unit 23 may be implemented with one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers. , microprocessors or other electronic components.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs programmable logic devices
  • FPGAs field programmable gate arrays
  • controllers microcontrollers.
  • microcontrollers microcontrollers or other electronic components.
  • the filtering unit 23 can also be implemented on the basis of a personal or industrial computer with sufficient computing power or a distributed network of such computing facilities.
  • the filter unit 23 may also be equipped with an input/output interface providing an interface between the filter unit 23 and peripheral devices such as a keyboard, display, and the like.
  • Peripheral devices can be used, for example, to make changes to the program code under which the filter unit 23 performs its functions.
  • the algorithms for filtering the source data are based on the principle of Shewhart's control charts.
  • the input of the filtering unit 23 receives data in a “raw” form for a period that is determined by the number of laboratory analysis points (or the retraining window).
  • the incoming data are sets of vectors of different lengths, from which the retraining matrix will be compiled.
  • Filtration of the initial data allows you to increase the accuracy of the model due to the fact that the model is trained only on the correct set of initial data, from which outliers, “broken” and erroneous values are excluded.
  • the filtering unit 23 can also be configured to additionally filter and transform the original data (time series) by methods known in the art to obtain a training set.
  • the prediction system 20 also includes a model generation and training unit 24 .
  • the model generation and training unit 24 may be implemented using one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), field programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs field programmable logic devices
  • FPGAs field programmable gate arrays
  • Block 24 of the formation and training of the model can also be implemented on the basis of a personal or industrial computer with sufficient computing power or a distributed network of such computing facilities.
  • the model building and learning unit 24 may also be equipped with an input/output interface providing an interface between the model building and learning unit 24 and peripheral devices such as a keyboard, display, and the like.
  • Peripheral devices can be used, for example, to make changes to the program code under the control of which the block 24 for generating and training the model performs its functions.
  • regression analysis is used, which, as it was found by the authors of the invention, is optimal for solving the problem and allows finding correlations between input and output variables.
  • each input parameter affects the resulting value with its own specific weight - the regression coefficient, which makes it possible to assess the physical reliability of the model.
  • the model generation and training unit 24 can be configured to determine the optimal size of the moving training window.
  • the calculation is made on the basis of the root-mean-square deviation of the sulfur content in the DF HE and the maximum correlation coefficient between the historical (retrospective) and predicted values of the sulfur content in the DF HE. For each of a predetermined set of moving learning window sizes, correlation coefficients are calculated and the size that provides the highest correlation coefficient is selected. Defining a learning window allows you to highlight the most significant data in the process history. From the entire time sample, a certain number of the latest points are selected, which are used for training to exclude old and weakly influencing data.
  • block 24 of the formation and training of the model can be made in the form of a software and hardware complex that allows the operator to manually set the size of the moving learning window.
  • the model building and training unit 24 can also be configured to evaluate the relative importance of regressors, search for multicollinear regressors, calculate regression coefficients, evaluate the model against historical data, add and remove regression coefficients, and perform other functionality that allows you to improve performance model quality.
  • the block 24 generation and training of the model allows you to generate polynomial models of arbitrary order with adjacent terms to build models that are more closely approximated to real non-linear systems. Polynomials of more than the first order include the products of regressors and their degrees of more than the first. Block 24 of the formation and training of the model can additionally be configured to build predictive models to reflect the impact of current readings of process parameters on possible subsequent changes in the final product. [0116] In one of the embodiments, the block 24 of the formation and training of the model can be made with the possibility of correcting the effects of individual technological parameters for the most accurate processing of possible disturbances. This functionality can be implemented, for example, by adding to the final result the product of the change in the parameter by the modifying coefficient when a significant perturbation in the modifying parameter is accumulated.
  • the following regressors can be included in the sulfur prediction model in GO DF: consumption R1 of raw materials per string, point R2 of boiling point of 50% of raw materials at the inlet to unit 11, point R3 of boiling out of 95% of raw materials at the inlet of hydrotreating unit 11, the density R4 of the feedstock at the inlet to the hydrotreatment unit 11, the flow rate R5 of the raw material to the hydrotreatment unit 11, the flow rate R6 of make-up hydrogen-containing gas (VSG) to the hydrotreatment unit 11, the flow rate R7 of the circulating hydrogen-containing gas (CVG) to the mixing tee 15, the flow rate R8 of diesel fuel (DF ) at the outlet of unit 11, consumption R9 of gasoline at the outlet of unit 11, consumption R10 of light gas oil (LG) at unit 11, temperature Rl 1 at the inlet to reactor 12, sulfur content R14 in the feedstock, pressure drop R15 between the inlet and outlet of the reactor, differential R16 temperature between the inlet and outlet of the reactor.
  • consumption R1 of raw materials per string point R2
  • the regression equation of the mathematical model may be of the following form: where S is the sulfur content in the product, Su is the coefficient, Ri is the regressor.
  • the block 24 for generating and training the model can also be configured to retrain the model with further accumulation of the historical sample, for example, with the arrival of new data from laboratory analyzes, with a change in the regression coefficients (automatically, if necessary). This allows you to correct the approximate functions of the models in the vicinity of the current equilibrium point of the real nonlinear process, thereby increasing their accuracy.
  • all data on technological parameters entering the model are taken on an hourly average.
  • FIG. 3 shows a graph of the sulfur content in diesel fuel HE based on real historical data, and a graph of the sulfur content in DH HE predicted by the proposed prediction system 20 using a trained model based on the obtained values.
  • a graph based on real historical data is plotted with a continuous line, and a graph predicted by the prediction system 20 is plotted with a dotted line.
  • the proposed the forecasting system 20 in most cases accurately predicts the trend in the change in the sulfur content in the GO of diesel fuel, but, at the same time, there are cases when the model does not reproduce all bursts in amplitude corresponding to real data.
  • the common practice for developing predictive regression models allows for partial non-capturing of sharp bursts.
  • the proposed system 20 for predicting the sulfur content can be used in the conduct of the technological process for predicting the sulfur content in GO DF.
  • the parameter receiving unit 21 may also be configured to receive a second set of values, which may be hydrotreating process parameter values that are not included in the training set, i.e., are not retrospective.
  • the parameter receiving unit 21 can also be configured to receive values of individual parameters from the operator, for example, to predict the effect on the sulfur content of a change in one of the parameters included in the model.
  • the new data received from the parameter receiving unit 21 is fed to the prediction unit 25, which calculates the predicted sulfur content based on the generated and trained model and the new parameters received.
  • the predictor 25 may be implemented with one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), field programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers. , microprocessors or other electronic components.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs field programmable logic devices
  • FPGAs field programmable gate arrays
  • controllers microcontrollers.
  • microcontrollers microcontrollers or other electronic components.
  • the prediction block 25 can also be implemented on the basis of a personal or industrial computer with sufficient computing power or a distributed network of such computing facilities.
  • the prediction unit 25 may also be equipped with an input/output interface providing an interface between the prediction unit 25 and peripheral devices such as a keyboard, display, and the like. Peripheral devices can be used, for example, to make changes to the program code under which the predictor 25 performs its functions.
  • the results of the prediction can be used to display key process parameters on the screen of the terminal 26 of the operator and/or process engineer, for example, through the construction of appropriate graphs. Wherein visualization of the process on the screen of the terminal 26 of the operator and/or process engineer can be carried out in real time. In this way, it is possible to follow real-time trends in sulfur content between laboratory analyzes.
  • the terminal 26 of the operator and/or process engineer may also provide the ability to select objects and parameters for analysis and monitoring using appropriate user interface elements.
  • the ability to set arbitrary values of controlled parameters using the terminal allows you to provide support in making decisions in real time.
  • the forecasting system provides the ability to build real-time forecasts of changes in the process when one or more parameters change.
  • the operator has the opportunity to assess the impact of the proposed changes on the process before they are directly implemented.
  • the corresponding commands can be transmitted from the terminal 26 of the operator and / or process engineer to the controller that controls the pump 14, the compressor 18, the valves installed on the production lines and / or the means 16 for heating the gas-feed mixture at the inlet to the reactor 2.
  • the temperature in the furnace of the heating means 16 is, for example, changed by increasing the supply of fuel gas to the furnace nozzles. Other temperatures can be changed by adjusting other parameters.
  • Commands from the terminal 26 of the operator and/or process engineer can also be sent to the appropriate controller and without the participation of the operator.
  • predefined commands may be sent to the controller when the model predicts that the predicted process variable will exceed a predetermined value after a predetermined time.
  • Operator and/or process engineer terminal 26 may be a computing device (such as a personal computer, industrial computer, server, laptop, or mobile computing device) or an appliance (such as a workstation (AWS)) .
  • Terminal 26 of the operator and/or process engineer may be equipped with a user interface and configured to receive, process and transmit data.
  • the invention also provides a method for predicting the sulfur content of hydrotreated diesel fuel based on prediction models, which are mathematical regression models, generated and trained, for example, by the prediction system 20 as described above.
  • a first set of hydrotreating process parameter values in the form of one or more time series is received in the parameter receiving block 21 and stored in the parameter storage block 22.
  • the values of the parameters of the hydrotreatment process include data from laboratory analyzes of raw materials at the inlet of the unit and hydrotreated diesel fuel at the outlet of the unit and data from the sensors of the GO DT unit.
  • the formation of a training set is performed and the size of the moving training window is determined based on the standard deviation of the sulfur content in the DH GO and the maximum of the correlation coefficient between historical and predicted values of the sulfur content in the DH GO.
  • a model for predicting the sulfur content in the GO of diesel fuel is performed based on a polynomial regression model of an arbitrary order with adjacent terms, the regressors of which are the mentioned process parameters, including: consumption R1 of raw materials per thread, point R2 of boiling 50% of raw materials at the inlet to the installation hydrotreater, point R3 of 95% boil-off of the feedstock at the inlet to the hydrotreater, density R4 of the feedstock at the inlet of the hydrotreater, flow rate R5 of feedstock to the hydrotreater, flow rate R6 of make-up hydrogen-containing gas (WGH) to the hydrotreater, flow rate R7 of circulating hydrogen-containing gas (CVG) into the mixing tee, consumption R8 of diesel fuel (DF) at the outlet of the installation, consumption R9 of gasoline at the outlet of the installation, consumption R10 of light gas oil (LG) at the installation, temperature R11 of the GSS at the inlet to the reactor.
  • the model After the model is formed, it is trained on the training set to obtain regression coefficients that provide indicators of the compliance of the modeled sulfur with historical values above a predetermined level. [0136] After the model has been trained, it can be used to predict the sulfur content in the GO of diesel fuel. To do this, using the parameter receiving unit 21, a second set of values of the physical parameters of the process is obtained and the specified second set is fed to the prediction unit 25, which predicts the sulfur content in the GO of diesel fuel at the outlet of the hydrotreater using a trained model based on the second set of values.
  • the present invention makes it possible to facilitate and implement support in the decision-making process by the operator when changing the parameters of technological processes, with the functions of online analysis of data arrays, calculation of the optimal temperature in the reactor, prediction of the residual catalyst life, allows to increase the flexibility of planning and control of technological processes, increase the loading of technological plants through better utilization of the catalytic system resource and better process controllability, increase the yield of more valuable products due to better process controllability and mitigation of regimes, reduce the time to involve the operating personnel of process plant to perform manual calculations to analyze the state of catalytic systems, increase target product yield due to milder processing conditions, increase the amount of processed feedstock on one catalyst, reduce catalyst operating costs, improve planning accuracy, increase the amount of processed feedstock on the catalyst.
  • the division into blocks used in the present description is only a division according to logical functions.
  • one or more functional blocks can be implemented, for example, in a single set of software and hardware (for example, a processor for processing signals of a general destination, microcontroller, RAM, hard disk, etc.).
  • several blocks or components can be combined or integrated into another system. Alternatively, some functions may be omitted or not performed.
  • an interconnection or direct connection or communication connection shown or discussed may be an indirect connection or communication connection via interfaces, devices or blocks, or may also be an electrical, mechanical or other type of connection.
  • the functionality of one or more units may be implemented, for example, by means of a computer-readable medium on which program code is recorded, when executed by the processor of the computing device, the computing device performs the corresponding functions.
  • the blocks are implemented in the form of separate software and hardware systems, communication between them, as well as with sensors at the 11 GO DT unit, can be carried out using wireless communication tools, for example, through the Industrial Internet of Things (IoT), technologies Wireless Local Area Network (WiFi), Long-Term Evolution (LTE), Broadcast Channels, Near Field Communication (NFC), Bluetooth (BT), and other wired and/or wireless technologies.
  • IoT Industrial Internet of Things
  • WiFi Wireless Local Area Network
  • LTE Long-Term Evolution
  • NFC Near Field Communication
  • BT Bluetooth
  • the blocks shown in figure 2 system 20 prediction can be implemented on the basis of an industrial computer or distributed network.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Mathematical Physics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Software Systems (AREA)
  • Chemical & Material Sciences (AREA)
  • Crystallography & Structural Chemistry (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Algebra (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Production Of Liquid Hydrocarbon Mixture For Refining Petroleum (AREA)

Abstract

L'invention concerne un procédé, un système et un support lisible par machine avec un produit de type logiciel permettant de pronostiquer le contenu en soufre de carburant diesel purifié par hydroraffinage à l'aide d'un modèle de pronostic de contenu en soufre de CDPH sur la base d'un modèle de régression polynomial d'ordre arbitraire avec des éléments contigus, dont les régresseurs sont lesdits paramètres du processus comprenant: le débit R1 de matière première vers la file; le point R2 d'ébullition de 50% de la matière première à l'entrée de l'installation d'hydroraffinage; le point R3 d'ébullition de 95% de la matière première à l'entrée de l'installation d'hydroraffinage; la densité R4 de la matière première à l'entrée de l'installation d'hydroraffinage; le débit R5 de matière première vers l'installation d'hydroraffinage; le débit R6 de gaz d'admission contenant de l'hydrogène (GCH) vers l'installation d'hydroraffinage; le débit R7 de gaz de circulation contenant de l'hydrogène (GCCH) vers le raccord en T de mélange; le débit R8 de carburant diesel (CD) à la sortie de l'installation; le débit R9 d'essence à la sortie de l'installation; le débit R10 de gasoil léger (GL) vers l'installation; et la température R11 à l'entrée dans le réacteur.
PCT/RU2022/050374 2021-12-29 2022-11-30 Système de pronostic de contenu en soufre de carburant diesel purifié par hydroraffinage WO2023128826A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
RU2021139603 2021-12-29
RU2021139603A RU2786373C1 (ru) 2021-12-29 Способ, система и машиночитаемый носитель с программным продуктом для прогнозирования содержания серы в гидроочищенном дизельном топливе

Publications (1)

Publication Number Publication Date
WO2023128826A1 true WO2023128826A1 (fr) 2023-07-06

Family

ID=87000019

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/RU2022/050374 WO2023128826A1 (fr) 2021-12-29 2022-11-30 Système de pronostic de contenu en soufre de carburant diesel purifié par hydroraffinage

Country Status (1)

Country Link
WO (1) WO2023128826A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060266018A1 (en) * 2005-05-31 2006-11-30 Caterpillar Inc. Exhaust control system implementing sulfur detection
RU2443472C2 (ru) * 2006-08-03 2012-02-27 Шелл Интернэшнл Рисерч Маатсхаппий Б.В. Высокостабильный катализатор гидрообессеривания тяжелых углеводородов и способы его получения и применения
RU2671868C1 (ru) * 2017-06-02 2018-11-07 Вячеслав Валентинович Пащенко Способ определения оптимальных параметров при облагораживании светлых нефтепродуктов и устройство для его осуществления
US20200191073A1 (en) * 2018-12-18 2020-06-18 Caterpillar Inc. Fuel content detection based on a measurement from a sensor and a model estimation of the measurement
CN111899813A (zh) * 2020-06-12 2020-11-06 中国石油天然气股份有限公司 柴油加氢装置的产物预测模型优化方法、系统、设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060266018A1 (en) * 2005-05-31 2006-11-30 Caterpillar Inc. Exhaust control system implementing sulfur detection
RU2443472C2 (ru) * 2006-08-03 2012-02-27 Шелл Интернэшнл Рисерч Маатсхаппий Б.В. Высокостабильный катализатор гидрообессеривания тяжелых углеводородов и способы его получения и применения
RU2671868C1 (ru) * 2017-06-02 2018-11-07 Вячеслав Валентинович Пащенко Способ определения оптимальных параметров при облагораживании светлых нефтепродуктов и устройство для его осуществления
US20200191073A1 (en) * 2018-12-18 2020-06-18 Caterpillar Inc. Fuel content detection based on a measurement from a sensor and a model estimation of the measurement
CN111899813A (zh) * 2020-06-12 2020-11-06 中国石油天然气股份有限公司 柴油加氢装置的产物预测模型优化方法、系统、设备及存储介质

Similar Documents

Publication Publication Date Title
Elfghi A hybrid statistical approach for modeling and optimization of RON: A comparative study and combined application of response surface methodology (RSM) and artificial neural network (ANN) based on design of experiment (DOE)
Jarullah et al. Kinetic model development and simulation of simultaneous hydrodenitrogenation and hydrodemetallization of crude oil in trickle bed reactor
AU2002331207B2 (en) Process to prepare a hydrocarbon product having a sulphur content of below 0.05 wt %
AU2007337863B2 (en) System and method for prediction of deterioration
Mederos et al. Steady‐state and dynamic reactor models for hydrotreatment of oil fractions: a review
US20210348066A1 (en) Predictive control systems and methods with hydrocracker conversion optimization
Iranshahi et al. Modeling and simulation of a novel membrane reactor in a continuous catalytic regenerative naphtha reformer accompanied with a detailed description of kinetics
CN108287474B (zh) 基于原料不确定性的催化重整反应器鲁棒操作优化方法
CN118098403A (zh) 一种提高催化柴油加氢转化产品收率的方法
Mik et al. Optimization of grading guard systems for trapping of particulates to prevent pressure drop buildup in gas oil hydrotreater
Ivanchina et al. Mathematical modeling and optimization of semi-regenerative catalytic reforming of naphtha
RU2786373C1 (ru) Способ, система и машиночитаемый носитель с программным продуктом для прогнозирования содержания серы в гидроочищенном дизельном топливе
RU2796210C1 (ru) Способ, система и машиночитаемый носитель с программным продуктом для прогнозирования оптимальной температуры газо-сырьевой смеси на входе в реактор установки гидроочистки дизельного топлива
RU2797753C1 (ru) Способ, система и машиночитаемый носитель с программным продуктом для прогнозирования изменения послойной активности катализатора в установке гидроочистки дизельного топлива
WO2023128826A1 (fr) Système de pronostic de contenu en soufre de carburant diesel purifié par hydroraffinage
RU2786783C1 (ru) Способ, система и машиночитаемый носитель с программным продуктом для прогнозирования изменения активности катализатора в установке гидроочистки дизельного топлива
Jarullah Kinetic Modelling Simulation and Optimal Operation of Trickle Bed Reactor for Hydrotreating of Crude Oil. Kinetic Parameters Estimation of Hydrotreating Reactions in Trickle Bed Reactor (TBR) via Pilot Plant Experiments; Optimal Design and Operation of an Industrial TBR with Heat Integration and Economic Evaluation.
WO2023128827A1 (fr) Pronostic de température d'un mélange gaz-matière première lors de la purification hydraulique de carburant diesel
WO2023128829A1 (fr) Procédé pour pronostiquer le changement de l'activité par couches d'un catalyseur de carburant
Shakoor Catalytic reforming of heavy naphtha, analysis and simulation
WO2023128828A1 (fr) Pronostic de changement d'activité d'un catalyseur dans une installation d'hydroraffinage de carburant diesel
CN102750454A (zh) 一种氢气消耗预测值获取方法、装置及系统
Sadighi et al. Modeling and optimizing a vacuum gas oil hydrocracking plant using an artificial neural network
Pinos et al. Modelling of H2 consumption and process optimization for hydrotreating of light gas oils
Gökçe Model predictive controller design of hydrocracker reactors

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22916896

Country of ref document: EP

Kind code of ref document: A1