WO2023119544A1 - プログラム、情報処理装置、及び方法 - Google Patents

プログラム、情報処理装置、及び方法 Download PDF

Info

Publication number
WO2023119544A1
WO2023119544A1 PCT/JP2021/047814 JP2021047814W WO2023119544A1 WO 2023119544 A1 WO2023119544 A1 WO 2023119544A1 JP 2021047814 W JP2021047814 W JP 2021047814W WO 2023119544 A1 WO2023119544 A1 WO 2023119544A1
Authority
WO
WIPO (PCT)
Prior art keywords
heavy oil
oil
model
parameter
cracking
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/JP2021/047814
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
秀紀 佐藤
英司 川井
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chiyoda Corp
Original Assignee
Chiyoda Corp
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
Application filed by Chiyoda Corp filed Critical Chiyoda Corp
Priority to PCT/JP2021/047814 priority Critical patent/WO2023119544A1/ja
Priority to JP2022563051A priority patent/JP7756105B2/ja
Priority to US18/719,517 priority patent/US20240428892A1/en
Priority to EP22910441.9A priority patent/EP4428635B1/en
Priority to KR1020247023889A priority patent/KR20240125618A/ko
Priority to PCT/JP2022/030118 priority patent/WO2023119711A1/ja
Priority to JP2023517661A priority patent/JP7354477B1/ja
Priority to TW111148866A priority patent/TWI827408B/zh
Priority to TW111148865A priority patent/TWI829479B/zh
Publication of WO2023119544A1 publication Critical patent/WO2023119544A1/ja
Anticipated expiration legal-status Critical
Priority to US19/269,154 priority patent/US20250342915A1/en
Ceased legal-status Critical Current

Links

Images

Classifications

    • 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
    • G16C20/10—Analysis or design of chemical reactions, syntheses or processes
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G05B13/048—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators using a predictor
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01J—CHEMICAL OR PHYSICAL PROCESSES, e.g. CATALYSIS OR COLLOID CHEMISTRY; THEIR RELEVANT APPARATUS
    • B01J19/00—Chemical, physical or physico-chemical processes in general; Their relevant apparatus
    • B01J19/0006—Controlling or regulating processes
    • B01J19/0033—Optimalisation processes, i.e. processes with adaptive control systems
    • C—CHEMISTRY; METALLURGY
    • C10—PETROLEUM, GAS OR COKE INDUSTRIES; TECHNICAL GASES CONTAINING CARBON MONOXIDE; FUELS; LUBRICANTS; PEAT
    • C10G—CRACKING HYDROCARBON OILS; PRODUCTION OF LIQUID HYDROCARBON MIXTURES, e.g. BY DESTRUCTIVE HYDROGENATION, OLIGOMERISATION, POLYMERISATION; RECOVERY OF HYDROCARBON OILS FROM OIL-SHALE, OIL-SAND, OR GASES; REFINING MIXTURES MAINLY CONSISTING OF HYDROCARBONS; REFORMING OF NAPHTHA; MINERAL WAXES
    • C10G11/00—Catalytic cracking, in the absence of hydrogen, of hydrocarbon oils
    • C10G11/14—Catalytic cracking, in the absence of hydrogen, of hydrocarbon oils with preheated moving solid catalysts
    • C10G11/18—Catalytic cracking, in the absence of hydrogen, of hydrocarbon oils with preheated moving solid catalysts according to the "fluidised-bed" technique
    • C—CHEMISTRY; METALLURGY
    • C10—PETROLEUM, GAS OR COKE INDUSTRIES; TECHNICAL GASES CONTAINING CARBON MONOXIDE; FUELS; LUBRICANTS; PEAT
    • C10G—CRACKING HYDROCARBON OILS; PRODUCTION OF LIQUID HYDROCARBON MIXTURES, e.g. BY DESTRUCTIVE HYDROGENATION, OLIGOMERISATION, POLYMERISATION; RECOVERY OF HYDROCARBON OILS FROM OIL-SHALE, OIL-SAND, OR GASES; REFINING MIXTURES MAINLY CONSISTING OF HYDROCARBONS; REFORMING OF NAPHTHA; MINERAL WAXES
    • C10G11/00—Catalytic cracking, in the absence of hydrogen, of hydrocarbon oils
    • C10G11/14—Catalytic cracking, in the absence of hydrogen, of hydrocarbon oils with preheated moving solid catalysts
    • C10G11/18—Catalytic cracking, in the absence of hydrogen, of hydrocarbon oils with preheated moving solid catalysts according to the "fluidised-bed" technique
    • C10G11/187—Controlling or regulating
    • C—CHEMISTRY; METALLURGY
    • C10—PETROLEUM, GAS OR COKE INDUSTRIES; TECHNICAL GASES CONTAINING CARBON MONOXIDE; FUELS; LUBRICANTS; PEAT
    • C10G—CRACKING HYDROCARBON OILS; PRODUCTION OF LIQUID HYDROCARBON MIXTURES, e.g. BY DESTRUCTIVE HYDROGENATION, OLIGOMERISATION, POLYMERISATION; RECOVERY OF HYDROCARBON OILS FROM OIL-SHALE, OIL-SAND, OR GASES; REFINING MIXTURES MAINLY CONSISTING OF HYDROCARBONS; REFORMING OF NAPHTHA; MINERAL WAXES
    • C10G47/00—Cracking of hydrocarbon oils, in the presence of hydrogen or hydrogen- generating compounds, to obtain lower boiling fractions
    • C10G47/36—Controlling or regulating
    • C—CHEMISTRY; METALLURGY
    • C10—PETROLEUM, GAS OR COKE INDUSTRIES; TECHNICAL GASES CONTAINING CARBON MONOXIDE; FUELS; LUBRICANTS; PEAT
    • C10G—CRACKING HYDROCARBON OILS; PRODUCTION OF LIQUID HYDROCARBON MIXTURES, e.g. BY DESTRUCTIVE HYDROGENATION, OLIGOMERISATION, POLYMERISATION; RECOVERY OF HYDROCARBON OILS FROM OIL-SHALE, OIL-SAND, OR GASES; REFINING MIXTURES MAINLY CONSISTING OF HYDROCARBONS; REFORMING OF NAPHTHA; MINERAL WAXES
    • C10G9/00—Thermal non-catalytic cracking, in the absence of hydrogen, of hydrocarbon oils
    • C—CHEMISTRY; METALLURGY
    • C10—PETROLEUM, GAS OR COKE INDUSTRIES; TECHNICAL GASES CONTAINING CARBON MONOXIDE; FUELS; LUBRICANTS; PEAT
    • C10G—CRACKING HYDROCARBON OILS; PRODUCTION OF LIQUID HYDROCARBON MIXTURES, e.g. BY DESTRUCTIVE HYDROGENATION, OLIGOMERISATION, POLYMERISATION; RECOVERY OF HYDROCARBON OILS FROM OIL-SHALE, OIL-SAND, OR GASES; REFINING MIXTURES MAINLY CONSISTING OF HYDROCARBONS; REFORMING OF NAPHTHA; MINERAL WAXES
    • C10G99/00—Subject matter not provided for in other groups of this subclass
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • 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
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2201/00—Features of devices classified in G01N21/00
    • G01N2201/12—Circuits of general importance; Signal processing
    • G01N2201/122—Kinetic analysis; determining reaction rate

Definitions

  • the present disclosure relates to an information processing device, method, and program.
  • the reaction state of heavy oil such as index values such as parameters related to reaction speed
  • index values such as parameters related to reaction speed
  • the purpose of the present disclosure is to provide a technology that can accurately predict the reaction state of heavy oil cracking and control the reaction.
  • An information processing device is an information processing device that includes a processor, and includes information about the oil properties of heavy oil to be cracked, and operating parameters related to the heavy oil cracking device that cracks the heavy oil. a step of receiving, as learning data, a value indicating a reaction state when the heavy oil is cracked in the heavy oil cracking unit according to the operating parameter; a step of learning, using the learning data, a first model for outputting the reaction state of the heavy oil cracking in response to inputting an operating parameter; and a step of storing the learned first model in a storage unit. and run
  • FIG. 1 is a block diagram showing the configuration of an information processing system 1;
  • FIG. 2 is a block diagram showing the configuration of the information processing device 10;
  • FIG. 2 is a diagram showing a configuration example of a heavy oil cracking device 20.
  • FIG. 2 is a block diagram showing the functional configuration of the information processing device 10;
  • FIG. 4 is a flowchart showing an example of the flow of learning processing by the information processing apparatus 10;
  • 4 is a flowchart showing an example of a flow of prediction processing by the information processing apparatus 10;
  • 4 is a flow chart showing an example of a flow of relearning processing by the information processing apparatus 10;
  • 4 is a flow chart showing an example of a flow of product yield calculation processing by the information processing apparatus 10.
  • FIG. 4 is a flowchart showing an example of the flow of optimization processing by the information processing apparatus 10;
  • 2 is a diagram showing a configuration example of a heavy oil cracking device 20.
  • FIG. 2 is a diagram showing a configuration example of a heavy oil cracking device 20.
  • FIG. 4 is a flowchart showing an example of the flow of optimization processing by the information processing apparatus 10;
  • 2 is a diagram showing a configuration example of a heavy oil cracking device 20.
  • FIG. 2 is a diagram showing a configuration example of a heavy oil cracking device 20.
  • a value indicating the reaction state when heavy oil is cracked is calculated from the operating parameters of a heavy oil cracking unit that cracks heavy oil and the oil properties of heavy oil. Describe the technology for prediction.
  • heavy oil is oil extracted from the bottom of an atmospheric distillation tower or a vacuum distillation tower when crude oil is distilled, or crude oil corresponding to this.
  • heavy oil will be described by taking an oil extracted from the bottom of an atmospheric distillation column as an example. Since the cracking reaction of heavy oil is a complex reaction that is affected by various operating parameters, it has been difficult to quantify, control, and optimize the reaction state in real time in actual operation. It was difficult to accurately predict the reaction state only by performing a simulation because it changes moment by moment in a heavy oil cracking unit that is actually in operation.
  • the reaction state of heavy oil is, for example, a parameter relating to the reaction rate of oily components of heavy oil, an index value indicating equilibrium catalyst activity, and the like.
  • the index value indicating the equilibrium catalyst activity is, for example, the activity value of the equilibrium catalyst obtained by analysis, the amount of metal components deposited on the catalyst, and the like.
  • the information processing system 1 uses this model to predict and quantify values that indicate the reaction state of heavy oil in real time.
  • the reaction can be controlled by inputting the values indicating the reaction state and the operating parameters into a physical model prepared in advance for predicting the product yield and the like. In this way, by optimizing the cracking reaction of heavy oil and contributing to the reduction of OPEX such as the improvement of product yield and the reduction of catalyst input, it is possible to contribute to the improvement of profitability of refineries. .
  • An information processing system 1 according to the present disclosure includes an information processing device 10 , a heavy oil cracking device 20 , a user terminal 30 and a network 40 .
  • FIG. 2 is a diagram showing the configuration of the information processing device 10.
  • the information processing device 10 is, for example, a laptop computer, a computer such as a rack-mount type or a tower type, a smartphone, or the like. Further, the information processing device 10 may be configured as a single system or configured redundantly by a plurality of information processing devices. The method of distributing a plurality of functions required to implement the information processing apparatus 10 can be appropriately determined in consideration of the processing capability of each piece of hardware, the specifications required for the information processing apparatus 10, and the like.
  • the information processing device 10 includes a processor 11, a memory 12, a storage 13, a communication IF 14, and an input/output IF 15.
  • the processor 11 is hardware for executing an instruction set described in a program, and is composed of arithmetic units, registers, peripheral circuits, and the like.
  • the memory 12 is for temporarily storing programs, data processed by the programs, etc., and is a volatile memory such as a DRAM (Dynamic Random Access Memory).
  • DRAM Dynamic Random Access Memory
  • the storage 13 is a storage device for storing data, such as flash memory, HDD (Hard Disc Drive), SSD (Solid State Drive).
  • HDD Hard Disc Drive
  • SSD Solid State Drive
  • the communication IF 14 is an interface for inputting and outputting signals so that the information processing device 10 communicates with an external device.
  • the communication IF 14 is wired or wirelessly connected to a network 40 such as LAN, Internet, wide area Ethernet.
  • the input/output IF 15 functions as an interface with an input device (for example, a pointing device such as a mouse, a keyboard) for accepting input operations, and an output device (display, speaker, etc.) for presenting information.
  • an input device for example, a pointing device such as a mouse, a keyboard
  • an output device for presenting information.
  • the heavy oil cracking device 20 is a device that cracks heavy oil into light cracked oil through a predetermined cracking reaction. Cracked oils are, for example, light gas (including LPG), gasoline, middle distillates, and the like.
  • the heavy oil cracking unit 20 cracks heavy oil by, for example, fluid catalytic cracking (FCC), thermal cracking, hydrocracking, or the like.
  • FCC fluid catalytic cracking
  • the FCC will be described below as the heavy oil cracking unit 20 .
  • the heavy oil cracking device 20 has a function of controlling the reactor 21 and the regenerator 22, and a function of transmitting and receiving predetermined information to and from the information processing device 10 through communication.
  • FIG. 3 is a diagram showing a configuration example of the heavy oil cracking device 20. As shown in FIG. The example of FIG. 3 is a case where the heavy oil cracking unit 20 cracks heavy oil by FCC. As shown in FIG. 3 , the heavy oil cracker 20 includes a reactor 21 and a regenerator 22 .
  • the reactor 21 is a device that brings the raw material heavy oil into contact with a catalyst to cause a cracking reaction and obtain a cracked product. Specifically, the reactor 21 brings the heavy oil into contact with the catalyst when the heavy oil, steam, and catalyst are input. Next, the reactor 21 obtains cracked oil by cracking the heavy oil through a cracking reaction caused by the contact of the heavy oil with the catalyst. Also, the reactor 21 introduces steam into the obtained cracked oil to remove the cracked oil adhering to the catalyst. The reactor 21 then outputs cracked oil. Also, the reactor 21 passes the used catalyst to the regenerator 22 .
  • the regenerator 22 regenerates the catalyst used in the reactor 21.
  • the catalyst When the catalyst is used for the cracking reaction of heavy oil, the catalyst deteriorates due to coke (carbon) adhering to the surface of the catalyst.
  • the regenerator 22 regenerates the coke adhering to the surface of the catalyst by burning it at a high temperature, and supplies the regenerated catalyst to the reactor 21 so as to keep the activity in the reactor 21 constant. Also, the regenerator 22 discharges exhaust gas generated by combustion.
  • the user terminal 30 is a terminal operated by a user.
  • the user is, for example, a person who operates and manages the heavy oil cracking device 20 .
  • the user terminal 30 is, for example, a smart phone, a personal computer, or the like.
  • the information processing device 10, the heavy oil cracking device 20, and the user terminal 30 are configured to communicate with each other via the network 40.
  • FIG. 4 is a block diagram showing the functional configuration of the information processing device 10. As shown in FIG. As shown in FIG. 2, the information processing apparatus 10 includes a communication section 110, a storage section 120, and a control section .
  • the communication unit 110 performs processing for the information processing device 10 to communicate with an external device.
  • the storage unit 120 stores data and programs used by the information processing device 10 .
  • the storage unit 120 stores a learning data DB 121, a model DB 122, and the like.
  • the learning data DB 121 is a database that holds learning data used when performing learning processing.
  • the learning data includes oil properties of heavy oil to be cracked, operating parameters related to the heavy oil cracking unit 20 that cracks the heavy oil, and the operation parameters in the heavy oil cracking unit 20. It is a set of actual data of values indicating the reaction state when heavy oil is cracked.
  • the oil properties of heavy oil are information related to the oil properties of heavy oil, such as the density, metal concentration, and nitrogen concentration of heavy oil.
  • the operating parameters are, for example, parameters such as the flow rate of heavy oil to the heavy oil cracking unit 20, the amount of catalyst, the amount of steam inflow, the pressure in the reactor 21, the internal temperature, the temperature of the catalyst, the ratio of the catalyst and the heavy oil, These parameters include the pressure inside the regenerator 22, the internal temperature, the temperature of the catalyst, and the like.
  • the learning data may be the first parameter relating to the cracking reaction of heavy oil among the operating parameters. to adopt.
  • reaction rate constant parameters related to reaction rate are reaction rate constant, frequency factor, activation energy, and the like.
  • the reaction rate constant of the Arrhenius equation is represented, for example, by the following equation. where k is the reaction rate constant, R is the gas constant, T is the absolute temperature, E is the activation energy and A is the frequency factor.
  • a reaction rate constant is used as an example of a parameter related to the reaction rate.
  • the second parameter regarding the equilibrium catalyst activity among the above operation parameters is adopted as the operating parameter.
  • the model DB 122 is a database that holds various models and model parameters.
  • the model DB 122 holds a heavy oil reaction state prediction model (hereinafter referred to as the first model).
  • the first model is a model that outputs the reaction state of heavy oil cracking in response to input of oil properties of heavy oil and operating parameters.
  • the first model is a reaction rate constant prediction model (hereinafter referred to as the second model).
  • the second model is a model that outputs reaction rate constants in response to inputs of oil properties of heavy oil and first parameters.
  • the first model may be an equilibrium catalytic activity prediction model (hereinafter referred to as the third model).
  • the third model is a model that outputs an index value indicating equilibrium catalyst activity in response to input of oil properties of heavy oil and a second parameter.
  • the first to third models may use, for example, a linear regression model to express the relationship between the oil properties of heavy oil, operating parameters, and the reaction state of heavy oil cracking.
  • the model DB 122 may hold both the second model and the third model. In this disclosure, an example in which the model DB 122 holds both the second model and the third model will be described.
  • model DB 122 holds models other than those described above.
  • the model DB 122 includes the oil properties of heavy oil, the first parameter, the reaction rate constant for cracking heavy oil determined by the second model, the second parameter, and the equilibrium catalyst determined by the third model. By inputting index values that indicate activity, a physical model is maintained that outputs product yields or index values that contribute to product yields.
  • the control unit 130 includes a reception control unit 131, a transmission control unit 132, an input unit 133, a learning unit 134, an acquisition unit 135, a prediction unit 136, and a determination unit 137 by the processor 11 of the information processing apparatus 10 performing processing according to a program. , the calculation unit 138, the optimization unit 139, the output unit 140, and the like.
  • the reception control unit 131 controls the process by which the information processing device 10 receives signals from an external device according to a communication protocol.
  • the transmission control unit 132 controls the process of transmitting a signal from the information processing device 10 to an external device according to a communication protocol.
  • the input unit 133 inputs the oil properties of the heavy oil to be cracked, the operating parameters related to the heavy oil cracking unit 20 that cracks the heavy oil, and the heavy oil cracking unit 20 based on the operating parameters. A value indicating a reaction state when heavy oil is cracked is accepted as learning data. Specifically, the input unit 133 acquires learning data from the learning data DB 121 .
  • the learning unit 134 learns the second model and the third model using the acquired learning data.
  • the learning unit 134 learns the second model using the oil property of heavy oil, the first parameter, and the reaction rate constant among the learning data. For example, if the second model is a linear regression model, the learning unit 134 learns the second model using the reaction rate constant as the objective variable, the oil properties of heavy oil, and the first parameter as explanatory variables.
  • the second model learns the first parameter for each of the oily components of the heavy oil, and the reaction rate constant and correlation of the cracking reaction when the heavy oil is cracked using the first parameter. do.
  • the learning unit 134 determines that the second model is oil equivalent to VR (vacuum residue), oil equivalent to VGO (vacuum gas oil), etc., which are oily components of heavy oil, by heavy oil decomposition. It learns the correlation between the reaction rate constant and the operating parameter so as to output the reaction rate constant that changes for each of gasoline, coke, exhaust gas, etc.
  • the learning unit 134 learning the second model in this way, not only the number of raw oil components but also a plurality of operating parameters interact in the cracking reaction of heavy oil having countless continuous boiling point components. It is possible to learn the correlation that The second model learned in this manner can accurately predict the reaction rate constant.
  • the learning unit 134 stores the learned second model in the model DB 122.
  • the learning unit 134 learns the third model using the oil property of the heavy oil, the second parameter, and the index value indicating the equilibrium catalytic activity among the learning data. For example, if the third model is a linear regression model, the learning unit 134 uses the index value indicating the equilibrium catalyst activity as the objective variable, the oil property of the heavy oil, and the second parameter as the explanatory variables to generate the third model. learn.
  • the catalyst circulates within the reactor 21 and regenerator 22 of the heavy oil cracking unit 20 .
  • the deterioration of the catalyst caused in the reactor 21 can be recovered to some extent in the regenerator 22, but since the deterioration of the catalyst cannot be completely recovered even in the regenerator 22, in order to keep the activity of the catalyst constant, the regenerator 22 It is necessary to supply new catalysts in addition to the recovery in However, the amount of new catalyst to be introduced is determined based on the empirical rule so far. In actual operation, the catalyst deterioration rate varies depending on changes in the heavy oil to be treated. Therefore, it has been difficult to adjust the catalytic activity to the desired level.
  • the learning unit 134 stores the learned third model in the model DB 122.
  • the learning unit 134 sets the first model as learning data, a third parameter that is an operating parameter for the heavy oil cracking unit 20 that is currently cracking heavy oil, and a value that indicates a predicted reaction state. can be re-learned using The learning unit 134 re-learns, for example, at the timing when the analysis result is acquired.
  • the learning unit 134 acquires learning data, a third parameter that is an operating parameter related to the heavy oil cracking unit 20 that is actually in operation, and a reaction state obtained by an analysis that will be described later. Get the indicated value and retrain each model. For example, the learning unit 134 re-learns the second model from the learning data, the first parameter of the third parameters, and the analyzed reaction rate constant. Also, for example, the learning unit 134 re-learns the third model from the learning data, the second parameter of the third parameters, and the analyzed index value indicating the equilibrium catalytic activity.
  • the learning unit 134 re-learns the second model and the third model at the timing when the analysis result is acquired, etc., so that the reaction rate constant and the index value indicating the equilibrium catalyst activity can be obtained more accurately in real time. be able to.
  • the reaction rate constant and the index value indicating the equilibrium catalyst activity can be obtained more accurately in real time. be able to.
  • it is necessary to analyze the equilibrium catalyst activity. Analysis of this equilibrium catalytic activity takes time after removal of the catalyst for analysis. Therefore, it takes time to reflect the analysis results in the simulation used for prediction.
  • the learning unit 134 can re-learn the second model and the third model at the timing when the analysis result is obtained, it is possible to obtain the index value indicating the reaction rate and the equilibrium catalyst activity more accurately in real time. For example, the prediction accuracy can quickly follow the influence of a catalyst change or the like.
  • the acquisition unit 135 acquires a third parameter, which is an operating parameter of the heavy oil cracking unit that is currently cracking heavy oil, the oil properties of the heavy oil, and the learned second and third models. do.
  • the acquisition unit 135 acquires the third parameter from the heavy oil cracker 20 and the oil properties of the heavy oil to be fed into the heavy oil cracker. Note that the acquisition unit 135 may acquire the third parameter and the oil properties of the heavy oil by receiving them from the user terminal 30 . Also, the acquisition unit 135 acquires the learned second model and the third model from the model DB 122 .
  • the acquisition unit 135 acquires the analysis result of the reaction state. Specifically, the acquiring unit 135 acquires the result of analyzing the reaction state based on actual operating parameters, decomposition products, catalysts, and the like.
  • the prediction unit 136 predicts a value indicating the reaction state by inputting the oil properties of the heavy oil and the third parameter into the first model.
  • the prediction unit 136 predicts the reaction rate constant by inputting the oil properties of the heavy oil and the first parameter out of the third parameters into the second model.
  • the prediction unit 136 predicts an index value indicating equilibrium catalyst activity by inputting the oil properties of the heavy oil and the second parameter out of the third parameters into the third model.
  • the determination unit 137 determines the optimal amount of new catalyst to be introduced into the heavy oil cracking unit 20 based on the index value indicating the equilibrium catalyst activity.
  • the determination unit 137 calculates the amount of catalyst to be introduced to bring the equilibrium catalyst activity to a predetermined value based on the index value indicating the equilibrium catalyst activity. Then, the determining unit 137 determines the calculated amount as the optimal new catalyst amount.
  • the calculation unit 138 uses the oil properties of the heavy oil, the third parameter, and the value indicating the reaction state to obtain the product yield or an index value that contributes to the product yield.
  • the calculation unit 138 first acquires the reaction model from the model DB 122 .
  • the calculation unit 138 calculates the oil properties of the heavy oil, the first parameter of the third parameter, the obtained reaction rate constant of cracking heavy oil, the second parameter of the third parameter,
  • the product yield or the index value contributing to the product yield is determined using the obtained index value indicating the equilibrium catalyst activity and the reaction model.
  • the product yield is, for example, the yield of cracked oil obtained by the heavy oil cracking unit 20 .
  • the index values that contribute to the product yield are operating parameters and the like necessary for determining the product yield.
  • the index values are, for example, reaction temperature, reaction time, catalyst concentration, and the like.
  • the optimization unit 139 uses the obtained product yield or the index value contributing to the product yield, the oil property of the heavy oil, the operating parameter, and the value indicating the reaction state to obtain the optimum product yield. Obtain the operating parameters to be realized.
  • the optimization unit 139 first, the product yield or an index value that contributes to the product yield, the oil properties of the heavy oil, the first parameter and the reaction rate constant of the third parameter,
  • the optimal product yield is determined using the second parameter of the third parameter and an index value indicative of equilibrium catalyst activity.
  • the optimization unit 139 inputs the oil properties of the heavy oil, the third parameter, the determined reaction rate, and the determined equilibrium catalytic activity into the model for searching for the optimum product yield. By doing so, we search for the optimum product yield.
  • the optimization unit 139 determines the oil properties of the heavy oil, the first parameter and the reaction rate of the third parameter, the second parameter of the third parameter and an index value indicating the equilibrium catalyst activity, Optimal operating parameters are determined using the determined optimal product species rate. Note that the optimization unit 139 may also be configured to obtain the optimum operating parameters using the learned second and third models.
  • the output unit 140 outputs the predicted reaction rate constant and the index value indicating the equilibrium catalyst activity to an output device or the like.
  • the index value indicating the predicted reaction rate constant and equilibrium catalyst activity may be configured to be output and displayed to an external device via communication by the output unit 140 .
  • the output unit 140 outputs the determined amount of the new catalyst.
  • the user issues a catalyst charging instruction from the user terminal 30 or the like to a catalyst charging device (not shown) or the like, and a new catalyst is charged to the heavy oil cracking device 20 .
  • the output unit 140 outputs the obtained product yield or an index value that contributes to the product yield.
  • the output unit 140 outputs the obtained optimum operating parameters.
  • FIG. 5 is a flowchart showing an example of the flow of learning processing by the information processing apparatus 10. As shown in FIG. The information processing apparatus 10 executes the process at any timing (for example, receiving a learning process start signal).
  • step S101 the input unit 133 inputs the oil properties of the heavy oil to be cracked, the operating parameters related to the heavy oil cracking unit 20 that cracks the heavy oil, and the heavy oil cracking parameters based on the operating parameters.
  • a value indicating the reaction state when the heavy oil is cracked in the device 20 is input as learning data.
  • step S102 the learning unit 134 learns the second model and the third model using the acquired learning data.
  • step S103 the learning unit 134 stores the learned second model and third model in the model DB 122, and ends the process.
  • FIG. 6 is a flow chart showing an example of the flow of prediction processing by the information processing device 10 .
  • the information processing device 10 executes the processing when the oil properties of the heavy oil and the operating parameters are input.
  • step S201 the acquisition unit 135 acquires the third parameter, which is the operating parameter for the heavy oil cracking unit 20 that is currently cracking heavy oil, the oil property of the heavy oil, the learned second model, and the 3 models.
  • step S202 the prediction unit 136 predicts the reaction rate constant by inputting the oil properties of the heavy oil and the first parameter out of the third parameters into the second model.
  • step S203 the prediction unit 136 predicts an index value indicating equilibrium catalytic activity by inputting the oil properties of the heavy oil and the second parameter out of the third parameters into the third model.
  • step S204 the output unit 140 outputs the predicted reaction rate constant and the index value indicating the equilibrium catalyst activity to an output device or the like.
  • the information processing device 10 can execute the prediction process at any timing, it is possible to predict the value indicating the reaction state of the heavy oil cracking device 20 in operation in real time.
  • FIG. 7 is a flow chart showing an example of the flow of relearning processing by the information processing apparatus 10 .
  • the information processing apparatus 10 executes the process at any timing (for example, acquisition of reaction state analysis results, reception of a relearning process start signal, etc.).
  • step S211 the acquisition unit 135 acquires the third parameter, which is the operating parameter of the heavy oil cracking unit 20 that is currently cracking heavy oil, the oil properties of the heavy oil, and the reaction state obtained by the analysis. , to acquire the second and third models that have been trained.
  • the third parameter which is the operating parameter of the heavy oil cracking unit 20 that is currently cracking heavy oil, the oil properties of the heavy oil, and the reaction state obtained by the analysis.
  • step S212 the learning unit 134 creates the second model based on the learning data, the third parameter that is the operating parameter of the heavy oil cracking unit 20 that is currently cracking the heavy oil, and the analyzed reaction rate constant. relearn using
  • step S213 the learning unit 134 creates the third model based on the learning data, the third parameter, which is the operating parameter of the heavy oil cracking unit 20 during heavy oil cracking, and the analyzed equilibrium catalyst activity. Re-learn using the indicated index value.
  • step S214 the learning unit 134 stores the re-learned second model and third model in the model DB 122, and ends the process.
  • the information processing device 10 can execute the prediction process at any timing, it is possible to predict the value indicating the reaction state of the heavy oil cracking device 20 in operation in real time.
  • FIG. 8 is a flow chart showing an example of the flow of product yield calculation processing by the information processing device 10 .
  • the information processing device 10 executes the processing when the oil properties of the heavy oil and the operating parameters are input.
  • symbol is attached
  • the calculation unit 138 uses the oil properties of the heavy oil, the third parameter, and the value indicating the reaction state to obtain the product yield or an index value that contributes to the product yield.
  • the output unit 140 outputs the obtained product yield or the index value contributing to the product yield, and ends the process.
  • FIG. 9 is a flow chart showing an example of the flow of optimization calculation processing by the information processing apparatus 10 .
  • the information processing apparatus 10 executes the process at arbitrary timing.
  • symbol is attached
  • the optimization unit 139 calculates the product yield or an index value contributing to the product yield, the oil properties of the heavy oil, the first parameter and the reaction rate of the third parameter, and the Optimal product yield is determined using the second parameter and an index value indicative of equilibrium catalyst activity.
  • the optimization unit 139 uses the obtained product yield or the index value contributing to the product yield, the oil property of the heavy oil, the operating parameter, and the value indicating the reaction state to obtain the optimum Determine the operating parameters that achieve a product yield of
  • the output unit 140 outputs the obtained optimum operating parameters, and ends the process.
  • the oil properties of the heavy oil to be cracked, the operating parameters related to the heavy oil cracking unit that cracks the heavy oil, and the heavy oil based on the operating parameters A value indicating the reaction state when the heavy oil is cracked in the cracker is received as learning data, and the oil property of the heavy oil and the operation parameter are input.
  • the first model for outputting the reaction state of oil cracking is learned using learning data, and the learned first model is stored in the storage unit, thereby predicting the reaction state of heavy oil cracking with high accuracy. 1 model can be obtained.
  • the third parameter which is the operating parameter for the heavy oil cracking unit that is currently cracking heavy oil, the oil properties of the heavy oil, and the learned first model are acquired.
  • the oil properties of the heavy oil and the third parameter are input into the first model to predict the value indicating the reaction state, and by outputting the value indicating the reaction state, the heavy oil can be obtained with high accuracy.
  • the reaction state of decomposition can be predicted.
  • the operating parameters Acquire the first model that outputs the value indicating the reaction state when the heavy oil is cracked in the heavy oil cracking unit, receive the oil properties of the heavy oil and the input of the operating parameters, Using the oil properties of the oil, the operating parameters, and the first model, the value indicating the reaction state is obtained, and the oil properties of the heavy oil, the operating parameters, and the value indicating the reaction state are used to calculate the product yield.
  • the value indicating the reaction state is obtained, and the oil properties of the heavy oil, the operating parameters, and the value indicating the reaction state are used to calculate the product yield.
  • the optimum product yield is obtained by using the obtained product yield or an index value contributing to the product yield, the oil properties of the heavy oil, the operating parameters, and the value indicating the reaction state.
  • Product yields can be improved by determining operating parameters that achieve yields.
  • each function of the information processing device 10 may be configured in another device.
  • each DB of the storage unit 120 may be constructed as an external database.
  • each function of the information processing device 10 may be configured in another device.
  • the heavy oil cracking unit 20 employs FCC has been described as an example, but it is not limited to this.
  • the configuration of the present disclosure can be applied even when the heavy oil cracking unit 20 is for thermal cracking and hydrocracking.
  • 10 and 11 show configuration examples of the heavy oil cracking unit 20 for thermal cracking and hydrocracking.
  • the following structural example is an example for explanation, and does not limit the heavy oil cracking apparatus 20 in thermal cracking and hydrocracking.
  • FIG. 10 is a diagram showing a configuration example of the heavy oil cracking device 20.
  • the example of FIG. 10 is a case where the heavy oil cracking device 20 cracks heavy oil by thermal cracking.
  • the heavy oil cracking unit 20 includes a distillation column 23 , a heating furnace 24 and a reactor 25 .
  • the heavy oil cracking unit 20 has a function of controlling the distillation column 23, the heating furnace 24, and the reactor 25, and a function of transmitting and receiving predetermined information to and from the information processing device 10 in thermal cracking.
  • the distillation column 23 receives heavy oil as a raw material, and separates each component of the heavy oil by distillation (light gas, naphtha fraction, middle distillate, each component up to heavy components, and coke) according to the boiling point and outputs it. do. Distillation column 23 passes heavy oil output from the bottom of distillation column 23 among the output components to heating furnace 24 .
  • the heating furnace 24 heats the heavy oil separated by the distillation column 23 to a temperature necessary for thermal cracking, and outputs high-temperature heavy oil.
  • the heating furnace 24 passes the output high temperature heavy oil to the reactor 25 .
  • the reactor 25 cracks the high-temperature heavy oil heated by the heating furnace 24 and outputs cracked gas and coke.
  • the reactor 25 performs batch cycle operation or semi-batch cycle operation. After the reaction, the reactor 25 is purged of the heavy oil remaining inside the reactor 25, decoked to remove coke adhering to the surface of the reactor 25, and then warmed up for the next reaction.
  • FIG. 11 is a diagram showing a configuration example of the heavy oil cracking device 20.
  • the example of FIG. 11 is a case where the heavy oil cracking unit 20 cracks heavy oil by hydrocracking.
  • heavy oil cracking unit 20 includes reactor 26 and hydrogen separation tank 27 .
  • the heavy oil cracking device 20 has a function of controlling the reactor 26 and the hydrogen separation tank 27 and a function of transmitting and receiving predetermined information to and from the information processing device 10 through communication.
  • the reactor 26 causes a cracking reaction by bringing the raw material heavy oil into contact with a catalyst and hydrogen, and produces cracking products (light gas, naphtha fraction, middle distillate, components up to heavy components, coke and sludge component). Specifically, when the heavy oil, hydrogen, and catalyst are input, the reactor 26 brings the heavy oil into contact with the hydrogen and the catalyst. Next, the reactor 26 obtains a cracked product obtained by cracking the heavy oil through a cracking reaction caused by contacting the heavy oil with hydrogen and a catalyst. The reactor 26 then outputs cracked oil.
  • the hydrogen separation tank 27 separates the decomposition products decomposed by the reactor 26 and hydrogen (including the catalyst in the case of slurry bed hydrocracking). Specifically, the hydrogen separation tank 27 has a high-pressure hydrogen separation tank, a medium-pressure hydrogen separation tank, and a low-pressure hydrogen separation tank (including a catalyst separation tank in the case of slurry bed hydrocracking). Products and hydrogen (and catalyst in the case of slurry bed hydrocracking) are separated. The hydrogen separation tank 27 outputs separated cracking products and hydrogen (catalyst in the case of slurry bed hydrocracking).
  • An information processing device (10) for predicting a heavy oil reaction state comprising a processor (11), Oil properties of heavy oil to be cracked, operating parameters related to a heavy oil cracking unit that cracks the heavy oil, and heavy oil cracking in the heavy oil cracking unit according to the operating parameters a step (S101) of receiving an input of a value indicating a reaction state at the time of oil cracking as learning data; An information processing apparatus that executes a step (102) of learning a first model that outputs a reaction state using the learning data, and a step (S103) of storing the learned first model in a storage unit.
  • the operating parameter is a first parameter related to the cracking reaction of the heavy oil among the operating parameters, and the value indicating the reaction state is the reaction rate of the heavy oil in the cracking of the heavy oil.
  • the first model is a model that outputs a parameter related to the reaction rate in response to inputting the oil properties of the heavy oil and the first parameter (Appendix 1 ).
  • the operating parameter is a second parameter related to equilibrium catalyst activity among the operating parameters, and the value indicating the reaction state is an index indicating the equilibrium catalyst activity of the heavy oil in the heavy oil cracking. is a value, and the first model is a model that outputs an index value indicating the equilibrium catalyst activity in response to inputting the oil properties of the heavy oil and the second parameter, ( The information processing apparatus according to appendix 1).
  • (Appendix 4) A step of acquiring a third parameter, which is an operating parameter relating to the heavy oil cracking unit that is currently cracking heavy oil, the oil properties of the heavy oil, and the learned first model (S201) and the step of predicting a value indicating the reaction state by inputting the oil property of the heavy oil and the third parameter into the first model (S202, S203);
  • the information processing apparatus according to any one of (Appendix 1) to (Appendix 3), which executes a step of outputting an indicated value (S204).
  • An information processing device (10) having a processor (11), which is an oil property of heavy oil to be cracked and an operating parameter related to the heavy oil cracking unit that cracks the heavy oil obtaining a first model that outputs a value indicating a reaction state when the heavy oil is cracked in the heavy oil cracking unit according to the operating parameter in response to inputting (S201); , a step (S202, S203) of receiving inputs of the oil properties of the heavy oil and the operating parameters, and using the oil properties of the heavy oil, the operating parameters, and the first model, the Contributing to the product yield or the product yield using the step of obtaining a value indicating a reaction state (S203), and using the oil properties of the heavy oil, the operating parameter, and the value indicating the reaction state.
  • An information processing apparatus that executes a step of obtaining an index value (S304) and a step of outputting the obtained product yield or the index value contributing to the product yield (S305).
  • the operating parameter is a first parameter related to the cracking reaction of the heavy oil among the operating parameters, and the value indicating the reaction state is the reaction rate of the heavy oil in the cracking of the heavy oil.
  • the first model is a model that outputs a parameter related to the reaction rate in response to inputting the oil properties of the heavy oil and the first parameter, and the product yield In the step of obtaining an index value contributing to the rate or the product yield, using the oil properties of the heavy oil, the first parameter, and the obtained parameter related to the reaction rate of cracking the heavy oil, The information processing device according to (Appendix 6), wherein the product yield or the index value contributing to the product yield is obtained.
  • the operating parameter is a second parameter related to equilibrium catalytic activity among the operating parameters, and the value indicating the reaction state is an index indicating the equilibrium catalytic activity of the heavy oil in the heavy oil cracking.
  • the first model is a model that outputs an index value indicating the equilibrium catalyst activity in response to inputting the oil properties of the heavy oil and the second parameter, and the In the step of obtaining an index value that contributes to the product yield, the oil properties of the heavy oil, the second parameter, and the obtained index value indicating the equilibrium catalyst activity are used to contribute to the product yield.
  • the information processing apparatus according to (Appendix 6), which obtains an index value for
  • S202 and in the acquiring step, acquire the oil properties of the heavy oil, the first model, and the second model, and contribute to the product yield or the product yield In the step of obtaining an index value to The information processing apparatus according to (Appendix 8), wherein the product yield or the index value contributing to the product yield is obtained using the index value indicating the activity.
  • the oil properties of the heavy oil, the first parameter, and the obtained heavy oil is calculated using a parameter related to the reaction rate of decomposition, the second parameter, the obtained index value indicating the equilibrium catalyst activity, and the reaction model.
  • the first model is a linear regression model or a neural network model, and in the learning step, the oil property of the heavy oil, the operating parameter, and the reaction state. 2.
  • the information processing apparatus according to any one of (Appendix 1) to (Appendix 11), wherein the first model is learned.
  • a computer for example, an information processing device 10) equipped with a processor (11) is used to determine the oil properties of heavy oil to be cracked and the operation of the heavy oil cracking unit that cracks the heavy oil.
  • a program to be executed by a computer having a processor (11), wherein the processor is provided with oil properties of heavy oil to be cracked and heavy oil
  • An input of an operating parameter relating to a heavy oil cracking unit for cracking and a value indicating a reaction state when the heavy oil is cracked in the heavy oil cracking unit using the operating parameter is accepted as learning data.
  • Reference Signs List 1 information processing system 10: information processing device 11: processor 12: memory 13: storage 14: communication IF 15: input/output IF 20: Heavy oil cracking device 21: Reactor 22: Regenerator 23: Distillation column 24: Heating furnace 25: Reactor 26: Reactor 27: Hydrogen separation tank 30: User terminal 40: Network 110: Communication unit 120: Storage unit 121: Learning data database 122: Model DB 130: control unit 131: reception control unit 132: transmission control unit 133: input unit 134: learning unit 135: acquisition unit 136: prediction unit 137: determination unit 138: calculation unit 139: optimization unit 140: output unit

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Oil, Petroleum & Natural Gas (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Organic Chemistry (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Chemical & Material Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Automation & Control Theory (AREA)
  • Computing Systems (AREA)
  • Crystallography & Structural Chemistry (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Data Mining & Analysis (AREA)
  • Analytical Chemistry (AREA)
  • Databases & Information Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Geometry (AREA)
  • Computer Hardware Design (AREA)
  • Thermal Sciences (AREA)
  • Production Of Liquid Hydrocarbon Mixture For Refining Petroleum (AREA)
  • Feedback Control In General (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
PCT/JP2021/047814 2021-12-23 2021-12-23 プログラム、情報処理装置、及び方法 Ceased WO2023119544A1 (ja)

Priority Applications (10)

Application Number Priority Date Filing Date Title
PCT/JP2021/047814 WO2023119544A1 (ja) 2021-12-23 2021-12-23 プログラム、情報処理装置、及び方法
JP2022563051A JP7756105B2 (ja) 2021-12-23 2021-12-23 プログラム、情報処理装置、及び方法
PCT/JP2022/030118 WO2023119711A1 (ja) 2021-12-23 2022-08-05 プログラム、情報処理装置、及び方法
EP22910441.9A EP4428635B1 (en) 2021-12-23 2022-08-05 Program, information processing device, and method
KR1020247023889A KR20240125618A (ko) 2021-12-23 2022-08-05 프로그램, 정보 처리 장치 및 방법
US18/719,517 US20240428892A1 (en) 2021-12-23 2022-08-05 Program, information processing device and method
JP2023517661A JP7354477B1 (ja) 2021-12-23 2022-08-05 プログラム、情報処理装置、及び方法
TW111148866A TWI827408B (zh) 2021-12-23 2022-12-20 資訊處理程式、資訊處理裝置、及資訊處理方法
TW111148865A TWI829479B (zh) 2021-12-23 2022-12-20 資訊處理程式、資訊處理裝置、及資訊處理方法
US19/269,154 US20250342915A1 (en) 2021-12-23 2025-07-15 Program, information processing device and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2021/047814 WO2023119544A1 (ja) 2021-12-23 2021-12-23 プログラム、情報処理装置、及び方法

Publications (1)

Publication Number Publication Date
WO2023119544A1 true WO2023119544A1 (ja) 2023-06-29

Family

ID=86901744

Family Applications (2)

Application Number Title Priority Date Filing Date
PCT/JP2021/047814 Ceased WO2023119544A1 (ja) 2021-12-23 2021-12-23 プログラム、情報処理装置、及び方法
PCT/JP2022/030118 Ceased WO2023119711A1 (ja) 2021-12-23 2022-08-05 プログラム、情報処理装置、及び方法

Family Applications After (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/030118 Ceased WO2023119711A1 (ja) 2021-12-23 2022-08-05 プログラム、情報処理装置、及び方法

Country Status (6)

Country Link
US (2) US20240428892A1 (https=)
EP (1) EP4428635B1 (https=)
JP (2) JP7756105B2 (https=)
KR (1) KR20240125618A (https=)
TW (2) TWI829479B (https=)
WO (2) WO2023119544A1 (https=)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0784606A (ja) * 1993-09-09 1995-03-31 Idemitsu Kosan Co Ltd 多段断熱反応器の最適化制御方法及びその装置
JP2003233402A (ja) * 2002-02-08 2003-08-22 Petroleum Energy Center 処理条件設定装置、その方法、そのプログラムおよび処理プラント
JP2018092511A (ja) * 2016-12-07 2018-06-14 三菱重工業株式会社 運用支援装置、機器運用システム、運用方法、制御方法及びプログラム
WO2018216746A1 (ja) * 2017-05-25 2018-11-29 コスモ石油株式会社 プラントの推奨運転条件を提供する方法、サーバ、コンピュータ可読命令および記録媒体
WO2019159280A1 (ja) * 2018-02-15 2019-08-22 千代田化工建設株式会社 プラント運転条件設定支援システム、学習装置、及び運転条件設定支援装置
WO2021245910A1 (ja) * 2020-06-05 2021-12-09 千代田化工建設株式会社 運転状態推定システム、学習装置、推定装置、状態推定器の生成方法、及び推定方法

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001273474A (ja) * 2000-01-20 2001-10-05 Idemitsu Kosan Co Ltd 分析値推定方法、およびこの方法を実行させるプログラムを記録したコンピュータ読み取り可能な記録媒体
JP3668405B2 (ja) * 2000-02-25 2005-07-06 株式会社日立製作所 ごみ焼却炉の制御方法及び装置
JP4828719B2 (ja) 2001-04-27 2011-11-30 一般財団法人石油エネルギー技術センター 石油コンビナートの運転条件の推定方法
JP2004008908A (ja) * 2002-06-06 2004-01-15 Mazda Motor Corp 流体中の所定成分の濃度変化予測方法及び反応速度解析法
US7113835B2 (en) * 2004-08-27 2006-09-26 Alstom Technology Ltd. Control of rolling or moving average values of air pollution control emissions to a desired value
CN101526814B (zh) * 2009-02-03 2011-05-04 东北大学 湿法冶金浸出过程浸出率预测与优化操作方法
US11885822B2 (en) * 2017-06-30 2024-01-30 Sri International Apparatuses for reaction screening and optimization, and methods thereof
US10901403B2 (en) * 2018-02-20 2021-01-26 Uop Llc Developing linear process models using reactor kinetic equations
US10996639B2 (en) * 2019-03-11 2021-05-04 Mitsubishi Electric Research Laboratories, Inc. Model predictive control of systems with continuous and discrete elements of operations
JP7376886B2 (ja) * 2019-03-29 2023-11-09 国立研究開発法人産業技術総合研究所 分子反応モデリング方法
US11853032B2 (en) * 2019-05-09 2023-12-26 Aspentech Corporation Combining machine learning with domain knowledge and first principles for modeling in the process industries
CN110648729B (zh) * 2019-10-29 2022-02-22 中国石油化工股份有限公司 一种催化裂化模型建立方法与装置
EP4102322B1 (en) * 2020-02-04 2025-08-27 Daicel Corporation Prediction device, prediction method, and program
CN111475957B (zh) * 2020-04-13 2024-02-02 华东理工大学 一种基于装置机理的炼油过程生产计划优化方法
JP7583535B2 (ja) * 2020-06-01 2024-11-14 株式会社クボタ 学習モデル生成装置
CN111899793B (zh) * 2020-06-12 2024-04-30 中国石油天然气股份有限公司 一种分子级装置的实时优化方法、装置、系统及存储介质
CN111863143A (zh) * 2020-07-31 2020-10-30 中国石油化工股份有限公司 一种用于催化裂化动力学模型的参数估值方法及装置
CN114203264B (zh) * 2021-11-30 2024-05-14 华南理工大学 基于深度学习的化学反应转化率预测方法、系统及介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0784606A (ja) * 1993-09-09 1995-03-31 Idemitsu Kosan Co Ltd 多段断熱反応器の最適化制御方法及びその装置
JP2003233402A (ja) * 2002-02-08 2003-08-22 Petroleum Energy Center 処理条件設定装置、その方法、そのプログラムおよび処理プラント
JP2018092511A (ja) * 2016-12-07 2018-06-14 三菱重工業株式会社 運用支援装置、機器運用システム、運用方法、制御方法及びプログラム
WO2018216746A1 (ja) * 2017-05-25 2018-11-29 コスモ石油株式会社 プラントの推奨運転条件を提供する方法、サーバ、コンピュータ可読命令および記録媒体
WO2019159280A1 (ja) * 2018-02-15 2019-08-22 千代田化工建設株式会社 プラント運転条件設定支援システム、学習装置、及び運転条件設定支援装置
WO2021245910A1 (ja) * 2020-06-05 2021-12-09 千代田化工建設株式会社 運転状態推定システム、学習装置、推定装置、状態推定器の生成方法、及び推定方法

Also Published As

Publication number Publication date
KR20240125618A (ko) 2024-08-19
EP4428635C0 (en) 2025-11-19
EP4428635A4 (en) 2025-01-22
US20250342915A1 (en) 2025-11-06
TW202407582A (zh) 2024-02-16
TWI827408B (zh) 2023-12-21
JP7756105B2 (ja) 2025-10-17
US20240428892A1 (en) 2024-12-26
JP7354477B1 (ja) 2023-10-02
TWI829479B (zh) 2024-01-11
WO2023119711A1 (ja) 2023-06-29
JPWO2023119711A1 (https=) 2023-06-29
EP4428635A1 (en) 2024-09-11
EP4428635B1 (en) 2025-11-19
JPWO2023119544A1 (https=) 2023-06-29
TW202326309A (zh) 2023-07-01

Similar Documents

Publication Publication Date Title
CN112749849A (zh) 连续催化重整工艺过程关键参数的集成学习在线预测方法
JP7730247B2 (ja) 生産性向上のためのリアルタイム機会発見
CN104463343A (zh) 一种预测催化裂化轻质油产率的方法
CN116449691B (zh) 原料油加工控制方法和装置
Sadighi et al. Optimizing an industrial scale naphtha catalytic reforming plant using a hybrid artificial neural network and genetic algorithm technique
JP7248823B1 (ja) 流体状態推定システム、学習装置、学習プログラム、推定装置、及び推定プログラム
US12505902B2 (en) Hybrid attribute reaction model (ARM) in molecule-based EO reactor (MB EORXR)
Niaei et al. The use of ANN and the mathematical model for prediction of the main product yields in the thermal cracking of naphtha
US20220220394A1 (en) Operation state estimation system, training device, estimation device, state estimator generation method, and estimation method
JP2023094622A (ja) プログラム、情報処理装置、及び方法
JP7756105B2 (ja) プログラム、情報処理装置、及び方法
Nguyen et al. A framework for developing a structure-based lumping kinetic model for the design and simulation of refinery reactors
Lukec et al. Prediction of sulphur content in the industrial hydrotreatment process
Shahzad et al. Grey‐box modelling for estimation of optimum cut point temperature of crude distillation column
CN119758924B (zh) 一种炼化装置参数控制方法、装置和设备
CN116463142B (zh) 一种石油催化裂化方案获取方法及装置
TR202014625A1 (tr) Hidrokraker reaktör sıcaklık optimizasyonu için hammadde içerisindeki azotun önceden tahminleme sistem ve yöntemi.
Chen et al. Scale-up of complex molecular reaction system by hybrid mechanistic modeling and deep transfer learning
US12599848B2 (en) Systems, analyzers, controllers, and associated methods to enhance fluid separation for distillation operations
CN117272074B (zh) 渣油加氢装置的优化方法、装置、电子设备与存储介质
Iplik Energy Savings for Petroleum Processing: Using Mathematical Models, Optimal Control and Diagnostics
US20260054194A1 (en) Systems, analyzers, controllers, and associated methods to enhance fluid separation for distillation operations
Martello et al. Enhancing Autoencoder-Based Machine Learning through the Use of Process Control Gain and Relative Gain Arrays as Cost Functions
CN118792076A (zh) 一种原油的加工方法、装置、电子设备以及存储介质
Goswami et al. Multi-objective optimization of hydrocracking processes using graph neural differential equations

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 2022563051

Country of ref document: JP

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

Ref document number: 21968981

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21968981

Country of ref document: EP

Kind code of ref document: A1