Information processing device, operation support method, program, and model generation method

Abstract

To enhance the economic performance of a catalytic reaction apparatus.SOLUTION: An information processing device 10 comprises an acquisition unit 12 configured to acquire a value of at least one catalyst parameter indicating a state of a catalyst sampled from a catalytic reaction apparatus at a first time and a value of at least one operation record parameter indicating an operation condition of the catalytic reaction apparatus from the first time to a second time, and a calculation unit 14 configured to calculate a value of at least one operation plan parameter indicating an operation plan of the catalytic reaction apparatus from the second time to a third time by using the value of the at least one catalyst parameter and the value of the at least one operation record parameter.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, a driving assistance method, a program, and a model generation method. [Background technology]

[0002] In plants such as oil refineries, catalytic reactors are used to pass feedstock oil through a catalyst to obtain refined oil. For example, a fluid catalytic cracking (FCC) unit, which is a type of catalytic reactor, uses a solid acid catalyst whose main component is zeolite or activated alumina. In catalytic reactors, the catalyst is regenerated and reused, and a makeup process is sometimes performed in which part of the catalyst is withdrawn and new catalyst is introduced to maintain the catalyst's activity (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2020-55899 Summary of the Invention [Problem to be solved by the invention]

[0004] From the viewpoint of economical operation of a catalytic reactor, it is preferable to maintain the catalyst activity at a predetermined reference value (e.g., a value that is optimal from the viewpoint of economic efficiency and profitability). However, since it is difficult to accurately measure the catalyst activity in real time, the actual catalyst activity value may deviate from the reference value depending on the frequency and accuracy of measuring the catalyst activity. If the difference between the actual catalyst activity value and the reference value becomes large, it will affect the economic efficiency of the catalytic reactor.

[0005] One exemplary object of certain aspects of the present disclosure is to provide techniques for improving the economics of catalytic reactors. [Means for solving the problem]

[0006] An information processing device according to one embodiment of the present disclosure includes an acquisition unit that acquires the value of at least one catalyst parameter indicating the state of the catalyst sampled from the catalytic reaction device at a first time and the value of at least one operating history parameter indicating the operating conditions of the catalytic reaction device from the first time to a second time, and a calculation unit that calculates the value of at least one operating schedule parameter indicating the operating schedule of the catalytic reaction device from the second time to a third time using the value of the at least one catalyst parameter and the value of the at least one operating history parameter.

[0007] Another aspect of the present disclosure is an operation assistance method, which includes the steps of acquiring a value of at least one catalyst parameter indicating a state of a catalyst sampled from a catalytic reactor at a first time, acquiring a value of at least one operating history parameter indicating an operating condition of the catalytic reactor from the first time to a second time, and calculating a value of at least one operation schedule parameter indicating an operating condition of the catalytic reactor from the second time to a third time using the value of the at least one catalyst parameter and the value of the at least one operating history parameter.

[0008] Yet another aspect of the present disclosure is a program that causes a computer to perform the following functions: acquire a value of at least one catalyst parameter that indicates a state of a catalyst sampled from a catalytic reactor at a first time; acquire a value of at least one operating history parameter that indicates an operating condition of the catalytic reactor from the first time to a second time; and calculate a value of at least one operation schedule parameter that indicates an operating condition of the catalytic reactor from the second time to a third time using the value of the at least one catalyst parameter and the value of the at least one operating history parameter.

[0009] Yet another aspect of the present disclosure is a model generation method, comprising the steps of: acquiring first training data including multiple data sets including a value of at least one operating history parameter indicating an operating condition of a catalytic reactor during a predetermined period, a first value of at least one catalyst parameter sampled from the catalytic reactor at the start of the predetermined period indicating a state of the catalyst, and a second value of at least one catalyst parameter sampled from the catalytic reactor at the end of the predetermined period; generating a first model using the first training data to predict the value of the at least one catalyst parameter; excluding at least some of the multiple data sets included in the first training data by analysis using the first model to generate second training data; and generating a second model using the second training data to predict the value of the at least one catalyst parameter. [Effects of the Invention]

[0010] According to the present disclosure, a technique for improving the economic efficiency of a catalytic reaction device can be provided. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a diagram showing an example of a schematic configuration of a catalytic reaction device according to an embodiment. [Figure 2] 1 is a diagram schematically illustrating a configuration of an information processing device according to an embodiment. [Figure 3] 3 is a flowchart illustrating an example of a driving assistance method according to an embodiment. [Figure 4] 1 is a flowchart illustrating an example of a model generation method according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] The present disclosure provides an overview. The present disclosure relates to a technology for calculating planned operating parameters for a catalytic reactor. In catalytic reactors, catalysts are sometimes recycled within the reactor, and a makeup process is sometimes performed in which a portion of the catalyst is discharged and new catalyst is introduced to maintain a constant catalyst activity. If the activity of the catalyst within the catalytic reactor can be measured in real time, the amount of new catalyst introduced can be appropriately adjusted so that the measured value indicating the catalyst activity matches a predetermined reference value. However, in order to measure the catalyst activity with high accuracy, the catalyst must be sampled and analyzed using equipment installed in a laboratory, etc., and it may take some time to obtain the analysis results. As a result, the less frequently and accurately the catalyst activity is measured, the more difficult it becomes to optimize the catalyst activity from an economical perspective.

[0013] In the present disclosure, the value of at least one catalyst parameter indicating the state of the catalyst sampled from the catalytic reactor at a first time and the value of at least one operating history parameter indicating the operating conditions of the catalytic reactor from the first time to a second time are used to calculate the value of at least one operation schedule parameter indicating the operation schedule of the catalytic reactor from a second time to a third time. The second time is, for example, the current time when the catalyst analysis results sampled at the first time are obtained. According to the present disclosure, at the second time when the catalyst analysis results are obtained, by taking into account the operating history from the first time to the second time, it is possible to accurately calculate the operation schedule parameter for maintaining the catalyst activity at or above a reference value until the third time. As a result, the catalytic reactor can be operated more economically.

[0014] The subject of the information processing device or method of the present disclosure includes a computer. The computer executes a computer program to realize the functions of the subject of the information processing device or method of the present disclosure. The computer includes, as its main hardware configuration, a processor that operates according to the computer program. The type of processor is not important as long as it can realize the functions by executing the computer program. The processor is composed of one or more electronic circuits including semiconductor integrated circuits (IC, LSI, etc.). The computer program is recorded on a non-transitory recording medium such as a computer-readable ROM, optical disk, or hard disk drive. The computer program may be pre-stored on the recording medium or may be supplied to the recording medium via a wide area communication network including the Internet.

[0015] The technology of the present disclosure will be described below with reference to the drawings based on preferred embodiments. The embodiments are illustrative and do not limit the invention, and all features and combinations thereof described in the embodiments are not necessarily essential to the invention. Identical or equivalent components, parts, and processes shown in each drawing are designated by the same reference numerals, and redundant descriptions will be omitted where appropriate. Furthermore, the scale and shape of each part shown in each drawing are set for convenience to facilitate explanation and should not be interpreted as limiting unless otherwise specified. Furthermore, when terms such as "first" and "second" are used in this specification or claims, unless otherwise specified, they do not represent any order or importance, but are used to distinguish one configuration from another.

[0016] 1 is a diagram showing an example of a schematic configuration of a catalytic reaction apparatus 50 according to an embodiment. The catalytic reaction apparatus 50 includes, for example, a reaction tower 52, a regeneration tower 54, a first pipe 70, and a second pipe 72. The reaction tower 52 and the regeneration tower 54 are connected by the first pipe 70 and the second pipe 72. The first pipe 70 is a pipe that transports the equilibrium catalyst 60 from the regeneration tower 54 to the reaction tower 52. The second pipe 72 is a pipe that transports the used catalyst 62 from the reaction tower 52 to the regeneration tower 54. The first pipe 70 and the second pipe 72 form a circulation path that circulates the catalyst within the catalytic reaction apparatus 50.

[0017] The reaction tower 52 has the function of reacting the feedstock 56 with the equilibrium catalyst 60 to produce a product oil 58. The feedstock 56 and the equilibrium catalyst 60 enter the reaction tower 52, and the product oil 58 and the spent catalyst 62 exit the reaction tower 52. The reaction tower 52 may include, for example, a reaction vessel (not shown) in which the feedstock 56 reacts with the equilibrium catalyst 60. Inside the reaction vessel, the feedstock 56 and the equilibrium catalyst 60 are mixed, and the reaction proceeds as the feedstock 56 comes into contact with the equilibrium catalyst 60. Note that the feedstock 56 may be supplied to the first pipe 70, whereby the feedstock 56 and the equilibrium catalyst 60 are mixed inside the first pipe 70, and the mixed feedstock 56 and the equilibrium catalyst 60 enter the reaction tower 52. The reaction tower 52 may include multiple reaction vessels connected in series or in parallel. The reaction tower 52 may also include a separation device for separating the product oil 58 and the spent catalyst 62 after the reaction. The reaction tower 52 may include a plurality of separation devices connected in series or in parallel. The separated spent catalyst 62 is sent to the regeneration tower 54 through a second pipe 72.

[0018] The regeneration tower 54 regenerates the spent catalyst 62 discharged from the reaction tower 52, increasing the catalyst's activity compared to before regeneration. The catalyst regenerated in the regeneration tower 54 enters the reaction tower 52 as the equilibrium catalyst 60. The regeneration tower 54 regenerates the spent catalyst 62 into the equilibrium catalyst 60, for example, by burning coke adhering to the spent catalyst 62. The regeneration tower 54 also functions as a heat source for the reaction tower 52 by supplying the equilibrium catalyst 60 heated by coke combustion to the reaction tower 52. The catalyst used in the reaction tower 52 and regenerated by the regeneration tower 54 deteriorates through cyclic use. Therefore, to maintain the activity of the equilibrium catalyst 60 at or above the standard value, a portion of the catalyst regenerated in the regeneration tower 54 must be extracted and discharged as spent catalyst 64, and new catalyst 66 must be introduced. The new catalyst 66 may have higher activity than the equilibrium catalyst 60, for example. For example, the amount of catalyst passing through the reaction tower 52 can be maintained constant by matching the amount of spent catalyst 64 discharged and the amount of new catalyst 66 charged. Note that the amount of spent catalyst 64 discharged and the amount of new catalyst 66 charged do not necessarily have to match, and the amount of catalyst passing through the reaction tower 52 may vary within a range in which normal operation of the catalytic reaction apparatus 50 can be continued. In other words, as long as a state in which the amount of catalyst required for normal operation of the catalytic reaction apparatus 50 passes through the reaction tower 52 can be maintained, there may be a short-term difference between the amount of spent catalyst 64 discharged and the amount of new catalyst 66 charged.

[0019] The catalytic reactor 50 may be, for example, a fluid catalytic cracker or a fluid catalytic reformer. In the case of a fluid catalytic cracker, the feedstock 56 may be, for example, a straight-run base stock obtained from an atmospheric distillation unit or a vacuum distillation unit, such as a light oil fraction or a heavy oil fraction. In the case of a fluid catalytic reformer, the feedstock 56 may be a straight-run base stock or a cracked base stock obtained from a catalytic cracker, such as a straight-run or cracked naphtha fraction, kerosene fraction, light oil fraction, or heavy oil fraction. The equilibrium catalyst 60 may be, for example, a particulate solid catalyst. The type and material of the equilibrium catalyst 60 are not particularly limited as long as it is a catalyst suitable for a fluid catalytic cracker or a fluid catalytic reformer. For example, zeolite carrying catalytic metals such as platinum group elements or rare earth elements may be used. The regenerator 54 removes impurities such as coke adhering to the spent catalyst 62 discharged from the reactor 52 to enhance the activity of the catalyst.

[0020] In the catalytic reactor 50 shown in FIG. 1 , the first pipe 70 is connected to the reaction tower 52, but is not limited thereto. The first pipe 70 may be connected, for example, to a pipe (not shown) for transporting the feed oil 56 to the reaction tower 52. In this case, the equilibrium catalyst 60 transported through the first pipe is mixed with the feed oil 56 inside the pipe for transporting the feed oil 56 and then supplied to the reaction tower 52. In this case, a circulation path for circulating the catalyst within the catalytic reactor 50 may be formed by the first pipe 70, the second pipe 72, and the pipe for transporting the feed oil 56.

[0021] 1, the new catalyst 66 is introduced into the second pipe 72, but this is not limiting. The new catalyst 66 may be introduced into the regenerator 54, for example.

[0022] In the catalytic reactor 50 shown in FIG. 1 , the spent catalyst 64 is discharged from the first pipe 70, but this is not limiting. The spent catalyst 64 may be discharged, for example, from a regeneration tower 54. In this case, the regeneration tower 54 may be equipped with, for example, a magnetic separator (not shown). The magnetic separator utilizes the property that the more metal component accumulation in a catalyst (i.e., the longer the catalyst has been in use and the more deteriorated it is), the stronger the magnetic force it will have in a magnetic field. This separates the catalyst from the equilibrium catalyst 60 to be discharged from the catalytic reactor 50 as the spent catalyst 64. The magnetic separator may be provided separately from the regeneration tower 54. In this case, the magnetic separator may be connected to the regeneration tower 54 via a pipe (not shown) as one of the devices constituting the catalytic reactor 50. In this case, the magnetic separator may be configured to transport the equilibrium catalyst 60 between the regeneration tower 54 and the regeneration tower 54 via a pipe (not shown) and to discharge the spent catalyst 64 separated from the equilibrium catalyst 60.

[0023] The operating conditions of the catalytic reactor 50 can be represented by the values ​​of a plurality of operating parameters. The plurality of operating parameters can include, for example, at least one of a parameter related to the temperature of the reactor 52, a parameter related to the feedstock 56, a parameter related to the product oil 58, and a parameter related to the catalyst (the equilibrium catalyst 60 or the fresh catalyst 66).

[0024] Parameters related to the temperature of the reaction tower 52 may include the internal temperature of a reaction vessel provided in the reaction tower 52, the temperature of the feed oil 56 entering the reaction vessel, and the temperature of the product oil 58 exiting the reaction vessel. Parameters related to the feed oil 56 may include, for example, the type of feed oil 56, the feed amount of the feed oil 56, the concentration of metal components contained in the feed oil 56 (also referred to as metal concentration), and the like. The feed amount of the feed oil 56 may be expressed as a "catalyst / feed oil ratio," which is the ratio of the equilibrium catalyst 60 entering the reaction vessel to the feed oil 56. Parameters related to the product oil 58 may include, for example, the production amount of the product oil 58, the liquid yield of the product oil 58, and the like.

[0025] The catalyst-related parameters may include catalyst parameters indicating the state of the catalyst. The catalyst parameters may include parameters related to the catalyst's activity and parameters related to the catalyst's metal concentration. The catalyst's activity-related parameters may include, for example, MAT (Micro Activity Test) activity, catalyst surface area, pore volume, etc. The MAT activity may be measured, for example, by a method conforming to ASTM (American Society for Testing and Materials) D7964 or D3907. The catalyst's metal concentration-related parameters may include the concentration of any metal component that affects the catalyst's activity, such as the concentration of iron (Fe), nickel (Ni), vanadium (V), sodium (Na), calcium (CaO), potassium (KO), titanium (TiO), rare earth elements (R2O3), etc. Here, rare earth elements (R) include lanthanum (La), cerium (Ce), gadolinium (Gd), ytterbium (Yb), etc.

[0026] The catalyst parameter values ​​indicating the state of the catalyst can be obtained, for example, by performing a predetermined analysis on the catalyst. The catalyst parameter values ​​are difficult to accurately analyze in real time and may require a period of, for example, one week, two weeks, three weeks, or one month. The catalyst parameter values ​​may include parameters related to the equilibrium catalyst 60 and parameters related to the new catalyst 66. The catalyst parameter values ​​may include at least one of a relative value, a sum value, and a difference value compared between the equilibrium catalyst 60 and the new catalyst 66.

[0027] The parameters related to the catalyst may include parameters related to the amount of new catalyst 66 introduced. The parameters related to the amount of new catalyst 66 introduced indicate, for example, the amount of new catalyst 66 introduced in a predetermined period (one hour, one day, one week, etc.).

[0028] 2 is a diagram schematically illustrating the functional configuration of an information processing device 10 according to an embodiment. The information processing device 10, a data management device 42, a plant management device 44, and a user terminal 46 are connected to each other via a network 40 in a state in which they can communicate with each other. The plant management device 44 is connected to a plant device 48 in a state in which they can communicate with each other.

[0029] The information processing device 10, the data management device 42, the plant management device 44, and the user terminal 46 are each a general-purpose computer such as a server, a workstation, or a personal computer, or a mobile terminal such as a smartphone or a tablet computer. As an example, the information processing device 10, the data management device 42, and the plant management device 44 are servers. As an example, the user terminal 46 is a personal computer.

[0030] Each block shown in the block diagrams of this disclosure can be realized in terms of hardware by elements or mechanical devices, such as a processor such as a computer's CPU (Central Processing Unit) and memories such as ROM (Read Only Memory) and RAM (Random Access Memory), and in terms of software by a computer program or the like. Here, functional blocks realized by cooperation between hardware and software are depicted. Those skilled in the art will understand that these functional blocks can be realized in various ways by combining hardware and software.

[0031] A computer program that implements the functions of at least some of the functional blocks shown in Fig. 2 may be installed in the storage of one or more computers. The CPUs of the one or more computers may load the installed computer program into their main memory and execute it to perform the functions of the functional blocks shown in Fig. 2.

[0032] 2 may be executed by a single computer or may be distributed among multiple computers. When the functions of the functional blocks shown in Fig. 2 are distributed among multiple computers, the multiple computers may transmit and receive data via a communication network including a LAN (Local Area Network), a WAN (Wide Area Network), and the Internet.

[0033] Network 40 is configured by a communication network including at least one of a local area network (LAN), a wide area network (WAN), the Internet, and various mobile communication systems constructed by wireless base stations. Examples of the mobile communication system include mobile communication systems such as 3G, 4G, and 5G, LTE (Long Term Evolution), and wireless networks (e.g., Wi-Fi (registered trademark)) that can be connected to the Internet via a predetermined access point.

[0034] The data management device 42 acquires and manages data used by the information processing device 10. The data management device 42 is, for example, a data server that collects and stores various data related to plant equipment 48. The data management device 42 acquires necessary data from, for example, the plant management device 44 or a user terminal 46. The data management device 42 transmits data required by the information processing device 10 to the information processing device 10 in response to a request from the information processing device 10, for example.

[0035] The plant management device 44 acquires and manages data from plant equipment 48. The plant equipment 48 is an equipment installed in a plant or a group of equipment consisting of multiple equipment installed in a plant. The plant equipment 48 includes, for example, a catalytic reaction equipment 50 and a sensor for acquiring actual measured values ​​of operating parameters that indicate the operating conditions of the catalytic reaction equipment 50. The type of sensor included in the plant equipment 48 is not particularly limited, and may include, for example, a temperature sensor, a pressure sensor, a flow rate sensor, etc. The plant management device 44 acquires the measured values ​​measured by the sensor included in the plant equipment 48.

[0036] The user terminal 46 is used by a user or operator who manages the plant. The user terminal 46 displays an input screen for inputting data to be used in the information processing device 10. The data input to the user terminal 46 is transmitted to, for example, the data management device 42 and managed by the data management device 42. The user terminal 46 displays information output from the information processing device 10.

[0037] The user terminal 46 receives input of the value of at least one catalyst parameter indicating the state of the catalyst used in the catalytic reactor 50. The user terminal 46 receives input of the value of a catalyst parameter indicating the state of the equilibrium catalyst 60 sampled from the catalytic reactor 50. The user terminal 46 receives input of the value of a catalyst parameter indicating the state of the new catalyst 66 to be introduced into the catalytic reactor 50. The catalyst parameters may include a parameter relating to the activity of the catalyst and a parameter relating to the metal concentration of the catalyst.

[0038] The information processing device 10 includes an acquisition unit 12, a calculation unit 14, a model generation unit 16, and an output unit 18. The memory unit 20 can include driving performance data 22, catalyst data 24, target data 26, and model data 28.

[0039] The acquisition unit 12 acquires the value of at least one operating history parameter indicating the operating conditions of the catalytic reaction device 50. The operating history parameter may include an actual measurement value of an operating parameter measured by a sensor provided in the catalytic reaction device 50. The types of operating parameters that can be measured by the sensor are not particularly limited, and examples include pressure, temperature, flow rate, concentration, and throughput. The operating history parameter may include an actual measurement value of an operating parameter input to the user terminal 46. The operating parameter input to the user terminal 46 is, for example, an actual measurement value or an analytical value of a parameter related to the equilibrium catalyst 60 or the new catalyst 66.

[0040] The parameter values ​​acquired by the acquisition unit 12 may be the sensor measurement values ​​themselves, or may be calculated values ​​calculated from measurements by one or more sensors. The acquisition unit 12 may acquire measurement values ​​by one or more sensors and calculate the value of at least one parameter using the acquired measurement values. For example, the acquisition unit 12 may acquire a first measurement value by a first sensor of the plant device 48 and a second measurement value by a second sensor of the plant device 48, and calculate the ratio of the first measurement value to the second measurement value as the parameter value. The acquisition unit 12 acquires the parameter value in association with the acquisition time. The acquisition time may be the time when the measurement is made by a sensor provided in the plant device 48, or the time when the data management device 42 or the plant management device 44 acquires the parameter value.

[0041] The acquiring unit 12 stores the acquired values ​​of the driving performance parameters in the storage unit 20 as driving performance data 22. The driving performance data 22 may include time-series values ​​of the driving performance parameters. The time-series values ​​of the driving parameters may include the values ​​of the driving performance parameters and the acquisition times of the values ​​of the driving performance parameters. The acquiring unit 12 may generate driving performance data 22 consisting of time-series values ​​of the driving performance parameters from the past to the present by accumulating the acquired time-series values ​​of the driving performance parameters in the storage unit 20. The time-series values ​​of the driving performance parameters recorded as the driving performance data 22 may be acquired at a relatively short time period (for example, every 1 minute, every 4 minutes, every 10 minutes, or every 30 minutes).

[0042] The acquisition unit 12 further acquires the value of at least one catalyst parameter indicating the state of the catalyst (e.g., equilibrium catalyst 60) sampled from the catalytic reaction device 50. The acquisition unit 12 acquires, for example, the catalyst parameter value input to the user terminal 46 and managed by the data management device 42. The acquisition unit 12 acquires the catalyst parameter value in association with the time at which the catalyst was sampled from the catalytic reaction device 50. The acquisition unit 12 stores the acquired catalyst parameter value as catalyst data 24 in the storage unit 20. The catalyst data 24 may include time-series values ​​of the catalyst parameter. The time-series values ​​of the catalyst parameter may be acquired at relatively long time intervals (e.g., every week, every half month, or every month). The time-series values ​​of the catalyst parameter do not have to be acquired periodically, but may be acquired irregularly. In other words, catalyst sampling analysis may be performed periodically or irregularly.

[0043] The acquisition unit 12 may further acquire the value of at least one target parameter indicating a target state of a catalyst (e.g., equilibrium catalyst 60) in the catalytic reaction device 50. The target parameter includes a parameter related to the activity of the catalyst, and may include, for example, the MAT activity of the catalyst (e.g., equilibrium catalyst 60), the catalyst surface area, the pore volume, etc. The acquisition unit 12 stores the acquired target parameter value in the storage unit 20 as target data 26.

[0044] The calculation unit 14 uses the operation history data 22 and the catalyst data 24 to calculate the value of at least one operation schedule parameter that indicates an operation schedule for the catalytic reaction apparatus 50. The operation schedule parameter may include operation parameters similar to the operation history parameters, and may include, for example, at least one of a parameter related to the temperature of the reaction tower 52, a parameter related to the feed oil 56, a parameter related to the refined oil 58, and a parameter related to the new catalyst 66. The operation schedule parameter may include, for example, a catalyst parameter that indicates the state of the new catalyst 66 and a parameter related to the amount of new catalyst 66 introduced.

[0045] The calculation unit 14 calculates the value of at least one operation schedule parameter indicating an operation schedule for the catalytic reactor 50 from the second time to the third time using the value of at least one catalyst parameter indicating the state of the catalyst sampled from the catalytic reactor 50 at the first time and the value of at least one operating history parameter indicating the operating conditions of the catalytic reactor from the first time to the second time. The first time is any time, for example, a past time. The second time is after the time when the analysis results of the catalyst sampled at the first time were obtained, for example, the present time. The third time is after the second time, for example, a future time. The first period from the first time to the second time is not particularly limited, but may correspond to the time required to analyze the catalyst, for example, one week, two weeks, three weeks, or one month. The second period from the second time to the third time corresponds to a period during which an operation schedule for the catalytic reactor 50 should be determined based on the analysis results obtained at the second time, for example, one week, two weeks, three weeks, or one month. The second period from the second time to the third time may correspond to a sampling or analysis period of the catalyst. The second period from the second time to the third time may be the same as, shorter than, or longer than the first period from the first time to the second time.

[0046] The calculation unit 14 can use a prediction model that receives as input the value of at least one catalyst parameter and the value of at least one operating history parameter, and outputs the value of at least one planned operation parameter. The calculation unit 14 can use, for example, a prediction model stored in the storage unit 20 as model data 28. The number of the at least one catalyst parameter input to the prediction model is, for example, 1 or more, 5 or more, or 10 or more, and, for example, 50 or less, 30 or less, or 20 or less. The number of the at least one operating history parameter input to the prediction model is, for example, 1 or more, 5 or more, or 10 or more, and, for example, 50 or less, 30 or less, or 20 or less.

[0047] The calculation unit 14 may further use the value of at least one target parameter indicating a target state of the catalyst of the catalytic reaction device 50 at the third time to calculate the value of at least one operation schedule parameter indicating an operation schedule for the catalytic reaction device 50 from the second time to the third time. The calculation unit 14 may use, for example, a parameter related to the activity of the equilibrium catalyst 60 as the at least one target parameter. The calculation unit 14 may use, for example, the MAT activity of the equilibrium catalyst 60 as the at least one target parameter. The calculation unit 14 may calculate the value of the at least one operation schedule parameter so that the MAT activity of the equilibrium catalyst 60 at the third time becomes a predetermined reference value (e.g., 70 wt%).

[0048] The calculation unit 14 may calculate the value of at least one operation schedule parameter indicating an operation schedule for the catalytic reaction device 50 from the first time to the third time using the value of at least one catalyst parameter of the equilibrium catalyst 60 sampled at the first time and the value of at least one target parameter indicating a target state of the equilibrium catalyst 60 at the third time. The calculation unit 14 may calculate the value of at least one operation schedule parameter from the second time to the third time using the value of at least one operation record parameter from the first time to the second time and the value of at least one operation schedule parameter from the first time to the third time. For example, the value of the operation schedule parameter indicating the planned amount of new catalyst 66 to be introduced from the second time to the third time can be calculated by subtracting the actual amount of new catalyst 66 introduced from the first time to the second time from the planned amount of new catalyst 66 to be introduced from the first time to the third time.

[0049] The calculation unit 14 may use a prediction model that receives as input the value of at least one catalyst parameter of the equilibrium catalyst 60 sampled at the first time and the value of at least one operation schedule parameter indicating the operation schedule of the catalytic reaction device 50 from the first time to the third time, and outputs the value of at least one catalyst parameter indicating the state of the equilibrium catalyst 60 at the third time. In this case, the calculation unit 14 may calculate the value of at least one operation schedule parameter indicating the operation schedule of the catalytic reaction device 50 from the first time to the third time by inverse problem analysis using the value of at least one catalyst parameter of the equilibrium catalyst 60 sampled at the first time and the value of at least one catalyst parameter indicating the target state of the equilibrium catalyst 60 at the third time. The calculation unit 14 can calculate the value of the planned operation parameter from the second time to the third time (e.g., the planned amount of new catalyst 66 to be added), for example, by subtracting the value of the actual operation parameter from the first time to the second time (e.g., the actual amount of new catalyst 66 to be added) from the value of the planned operation parameter from the first time to the third time (e.g., the planned amount of new catalyst 66 to be added).

[0050] The model generation unit 16 generates a prediction model to be used in the calculation unit 14. The model generation unit 16 generates the prediction model using the operating history data 22 and catalyst data 24 stored in the storage unit 20. The model generation unit 16 generates the prediction model using a data set including: a value of at least one operating history parameter indicating the operating conditions of the catalytic reactor 50 for a predetermined period (e.g., one week, two weeks, three weeks, or one month); a first value of at least one catalyst parameter indicating the state of the equilibrium catalyst 60 sampled from the catalytic reactor 50 at the start of the predetermined period; and a second value of at least one catalyst parameter indicating the state of the equilibrium catalyst 60 sampled from the catalytic reactor 50 at the end of the predetermined period. The model generation unit 16 can generate the prediction model using, for example, multiple data sets having the same length of the predetermined period but different times corresponding to the start or end of the predetermined period.

[0051] The model generation unit 16 may take as input a first value of at least one catalyst parameter at the start of a predetermined period and a second value of at least one catalyst parameter at the end of the predetermined period, and may generate a prediction model that outputs a value of at least one operating performance parameter for the predetermined period.The model generation unit 16 may take as input a first value of at least one catalyst parameter at the start of a predetermined period and a value of at least one operating performance parameter for the predetermined period, and may generate a prediction model that outputs a second value of at least one catalyst parameter at the end of the predetermined period.

[0052] The model generation unit 16 can generate a predictive model through machine learning using multiple data sets as training data. The model generation unit 16 can use, as a machine learning algorithm for generating the predictive model, at least one of linear regression, support vector machine, decision tree, K-nearest neighbor algorithm, naive Bayes, gradient boosting, factorization machine, neural network, and derivatives thereof. Furthermore, when the operating performance data 22 and the catalyst data 24 include time series values, the model generation unit 16 can use, in addition to the above examples of machine learning algorithms, time series models such as an autoregressive model, a moving average model, a state space model, an exponential smoothing model, a deep learning model, a generalized additive model, and derivatives thereof. For example, the model generation unit 16 can use at least one time series model such as an autoregressive integrated moving average (ARIMA) model, a Holt-Winters model, a Prophet model, a Kalman filter, a recurrent neural network (RNN), and a long short-term memory (LSTM).

[0053] The model generation unit 16 may generate a first model using first training data including a plurality of data sets, and then generate second training data by excluding at least some of the plurality of data sets included in the first training data through analysis using the first model, and generate the second model using the second training data. The model generation unit 16 may store the generated second model in the storage unit 20 as a prediction model to be used by the calculation unit 14. By generating a prediction model by excluding some of the data sets, the prediction accuracy of the prediction model can be improved.

[0054] The model generation unit 16 can generate second training data from the first training data by using a method of removing outliers through regression diagnosis. The model generation unit 16 can remove outlier data sets included in the first training data by using, for example, at least one of a residual plot, a normal QQ plot, a scale location plot, and a residual leverage plot.

[0055] According to one example of a prediction model, six catalyst parameters indicating the state of the equilibrium catalyst 60 sampled at the first time and two operating performance parameters indicating the operating conditions from the first time to the second time are input, and a model that outputs the MAT activity indicating the state of the equilibrium catalyst 60 at the third time can achieve a root mean square error (RMSE) of MAT activity of 2.0 wt% or less. By performing an inverse problem analysis using such a prediction model that can predict the state of the equilibrium catalyst 60 at the third time with high accuracy, it is possible to predict the planned operating parameters from the second time to the third time with high accuracy.

[0056] The information processing device 10 may not include the model generation unit 16. In this case, the information processing device 10 may acquire a prediction model generated by a device different from the information processing device 10 as model data 28. The calculation unit 14 may use the acquired model data 28 to calculate the value of at least one operation schedule parameter.

[0057] The output unit 18 outputs the predicted value calculated by the calculation unit 14. The output unit 18 may notify a user by outputting the predicted value to a user terminal 46. The output unit 18 may control the operating conditions of the catalytic reaction device 50 by outputting the predicted value to a plant device 48.

[0058] 3 is a flowchart showing an example of a driving assistance method according to an embodiment. The acquisition unit 12 acquires the value of at least one catalyst parameter indicating the state of the catalyst sampled from the catalytic reaction device 50 at a first time (S10). The acquisition unit 12 acquires the value of at least one operating history parameter indicating the operating conditions of the catalytic reaction device 50 from the first time to a second time (S12). The calculation unit 14 uses the acquired value of the at least one catalyst parameter and the acquired value of the at least one operating history parameter to calculate the value of at least one operation schedule parameter indicating the operation schedule of the catalytic reaction device 50 from the second time to a third time (S14). The output unit 18 outputs the calculated value of the at least one operation schedule parameter (S16).

[0059] FIG. 4 is a flowchart showing an example of a model generation method according to an embodiment. The acquisition unit 12 acquires a value of at least one operating history parameter indicating the operating conditions of the catalytic reactor 50 during a predetermined period (S30). The acquisition unit 12 acquires a first value of at least one catalyst parameter indicating the state of the catalyst sampled from the catalytic reactor 50 at the start of the predetermined period (S32). The acquisition unit 12 acquires a second value of at least one catalyst parameter indicating the state of the catalyst sampled from the catalytic reactor 50 at the end of the predetermined period (S34). The model generation unit 16 generates a first model for predicting the value of at least one catalyst parameter using first training data including multiple data sets including the acquired value of the at least one operating history parameter and the acquired first and second values ​​of the at least one catalyst parameter (S36). The model generation unit 16 generates second training data by excluding at least some of the multiple data sets included in the first training data through analysis using the first model (S38). The model generation unit 16 generates a second model for predicting the value of at least one catalyst parameter using the second training data (S40).

[0060] According to this embodiment, by using the catalyst parameter value indicating the catalyst state sampled at the first time and the operating result parameter value from the first time to the second time, it is possible to accurately calculate the operation schedule parameter value from the second time to the third time. As a result, it is possible to reduce the margin value for the amount of new catalyst 66 to be introduced in order to maintain the state of the equilibrium catalyst 60 at or above a predetermined reference value, and it becomes possible to operate the catalytic reaction device 50 more economically.

[0061] The present disclosure has been described above based on the embodiments. These embodiments are merely examples, and it will be understood by those skilled in the art that various modifications are possible in the combination of each component or each treatment process, and that such modifications are also within the scope of the present disclosure.

[0062] In the present disclosure, parameters or values ​​may be expressed as absolute values, relative values ​​from a predetermined value, or other corresponding information.

[0063] The embodiment may be a program for causing a computer to implement the functions for implementing the above-described method, or a recording medium for storing the program. The recording medium for storing such a program may be a non-transitory, tangible, computer-readable storage medium, such as a non-volatile memory, a magnetic recording medium such as a magnetic tape or a magnetic disk, or an optical recording medium such as an optical disk.

[0064] Several aspects of the present disclosure are described below.

[0065] The first aspect includes an acquisition unit that acquires the value of at least one catalyst parameter that indicates the state of the catalyst sampled from the catalytic reaction device at a first time, and the value of at least one operating history parameter that indicates the operating condition of the catalytic reaction device from the first time to a second time; and a calculation unit that calculates the value of at least one operation schedule parameter that indicates an operation schedule for the catalytic reaction device from the second time to the third time using the value of the at least one catalyst parameter and the value of the at least one operating history parameter. According to the first aspect, at the second time when analysis results of the sampled catalyst are obtained, the operation schedule parameter up to the third time can be calculated with high accuracy by taking into account the operating history from the first time to the second time. As a result, it becomes possible to operate the catalytic reaction device economically from the second time to the third time.

[0066] In a second aspect, in the information processing device according to the first aspect, the at least one catalyst parameter includes a parameter related to catalyst activity. According to the second aspect, by using the analysis result related to catalyst activity, it is possible to calculate with high accuracy operation schedule parameters for maintaining catalyst activity at or above a reference value.

[0067] In a third aspect, the at least one catalyst parameter further includes a parameter related to a metal concentration of the catalyst. According to the third aspect, by further using the analysis result related to the metal concentration that affects the catalyst activity, it is possible to calculate with high accuracy the operation schedule parameters for maintaining the catalyst activity at or above a reference value.

[0068] In a fourth aspect, in the information processing device according to any one of the first to third aspects, the at least one operating history parameter includes at least one of a parameter related to a feedstock oil entering the catalytic reactor and a parameter related to a product oil exiting the catalytic reactor. According to the fourth aspect, by taking into account the parameters related to the feedstock oil or the product oil of the catalytic reactor, it is possible to calculate with high accuracy the planned operating parameters for maintaining the activity of the catalyst at or above a reference value.

[0069] A fifth aspect is the information processing device according to any one of the first to fourth aspects, wherein the catalyst is an equilibrium catalyst, the catalytic reaction device is capable of extracting the equilibrium catalyst and introducing a new catalyst having higher activity than the equilibrium catalyst, and the at least one operating history parameter includes a parameter related to the new catalyst. According to the fifth aspect, by taking into account the operating history parameter related to the new catalyst, it is possible to calculate with high accuracy the operating schedule parameter for maintaining the activity of the equilibrium catalyst at or above a reference value.

[0070] A sixth aspect is the information processing device according to the fifth aspect, wherein the at least one operation schedule parameter includes a parameter related to a new catalyst. According to the sixth aspect, an operation schedule parameter related to a new catalyst for maintaining catalyst activity at or above a reference value is calculated, thereby improving user convenience.

[0071] A seventh aspect is the information processing device according to any one of the first to sixth aspects, wherein the acquisition unit further acquires a value of at least one target parameter indicating a target state of the catalyst in the catalytic reaction device at the third time, and the calculation unit further uses the value of the at least one target parameter to calculate a value of the at least one operation schedule parameter. According to the seventh aspect, it is possible to calculate an operation schedule parameter according to the target state of the catalyst, thereby improving convenience for a user.

[0072] In an eighth aspect, in the information processing device according to the seventh aspect, the at least one target parameter includes a parameter related to catalyst activity. According to the eighth aspect, it is possible to calculate an operation schedule parameter according to a target state related to catalyst activity, thereby improving user convenience.

[0073] A ninth aspect is the information processing device according to the seventh or eighth aspect, wherein the calculation unit uses a prediction model that receives as input the value of the at least one catalyst parameter and the value of the at least one operation schedule parameter and outputs the value of the at least one target parameter to calculate the value of the operation schedule parameter for setting the at least one target parameter to a predetermined value. According to the ninth aspect, the operation schedule parameter can be calculated so that the target parameter indicating the target state of the catalyst will be the predetermined value, thereby improving user convenience.

[0074] A tenth aspect is the information processing device according to the ninth aspect, wherein the prediction model is generated by learning second teacher data that excludes at least a portion of first teacher data including a plurality of data sets each including a value of the at least one catalyst parameter, a value of the at least one operation schedule parameter, and a value of the at least one target parameter, and the second teacher data is generated by elimination analysis using a first model generated by learning the first teacher data. According to the tenth aspect, the second model generated through elimination analysis using the first model can be used to calculate the operation schedule parameters with high accuracy.

[0075] An eleventh aspect is the information processing device according to any one of the first to sixth aspects, wherein the calculation unit calculates the values ​​of the operation schedule parameters using a prediction model generated by learning second teacher data that excludes at least some of first teacher data including a plurality of data sets each including a value of the at least one catalyst parameter, a value of the at least one operating history parameter, and a value of the at least one operation schedule parameter, and the second teacher data is generated by elimination analysis using a first model generated by learning the first teacher data. According to the eleventh aspect, the operation schedule parameters can be calculated with high accuracy by using the second model generated through elimination analysis using the first model.

[0076] A twelfth aspect is an operation assistance method comprising the steps of: acquiring a value of at least one catalyst parameter indicating the state of a catalyst sampled from a catalytic reactor at a first time; acquiring a value of at least one operating history parameter indicating the operating conditions of the catalytic reactor from the first time to a second time; and calculating a value of at least one operation schedule parameter indicating the operating conditions of the catalytic reactor from the second time to a third time using the value of the at least one catalyst parameter and the value of the at least one operating history parameter. According to the twelfth aspect, at the second time when analysis results of the sampled catalyst are obtained, the operating schedule parameter up to the third time can be calculated with high accuracy by taking into account the operating history from the first time to the second time. As a result, it is possible to operate the catalytic reactor economically from the second time to the third time.

[0077] A thirteenth aspect is a program that causes a computer to implement the following functions: acquiring the value of at least one catalyst parameter that indicates the state of the catalyst sampled from a catalytic reactor at a first time; acquiring the value of at least one operating history parameter that indicates the operating conditions of the catalytic reactor from the first time to a second time; and calculating the value of at least one operation schedule parameter that indicates the operating conditions of the catalytic reactor from the second time to a third time using the value of the at least one catalyst parameter and the value of the at least one operating history parameter. According to the thirteenth aspect, at the second time when analysis results of the sampled catalyst are obtained, the operating schedule parameter up to the third time can be calculated with high accuracy by taking into account the operating history from the first time to the second time. As a result, it is possible to operate the catalytic reactor economically from the second time to the third time.

[0078] A fourteenth aspect of the present invention provides a model generation method including the steps of: acquiring first training data including a plurality of data sets, each data set including a value of at least one operating history parameter indicating the operating conditions of a catalytic reactor during a predetermined period, a first value of at least one catalyst parameter sampled from the catalytic reactor at the start of the predetermined period indicating the state of the catalyst, and a second value of the at least one catalyst parameter sampled from the catalytic reactor at the end of the predetermined period; generating a first model using the first training data to predict the value of the at least one catalyst parameter; excluding at least some of the data sets included in the first training data by analysis using the first model to generate second training data; and generating a second model using the second training data to predict the value of the at least one catalyst parameter. According to the fourteenth aspect, a prediction model capable of predicting catalyst parameters with high accuracy can be generated by using the second model generated through the exclusion analysis using the first model.

[0079] Any combination of the configurations according to the above-described embodiments or aspects is also useful as an embodiment of the present disclosure. A new embodiment resulting from the combination will have the combined effects of the combined examples and modifications. It will also be understood by those skilled in the art that the functions to be performed by each component in the claims can be realized by each component shown in the examples and modifications, either individually or in combination. [Explanation of symbols]

[0080] 10...information processing device, 12...acquisition unit, 14...calculation unit, 16...model generation unit, 18...output unit, 20...memory unit, 22...operational performance data, 24...catalyst data, 26...target data, 28...model data, 50...catalytic reaction device, 52...reaction tower, 54...regeneration tower, 56...feedstock oil, 58...produced oil, 60...equilibrated catalyst, 62...spent catalyst, 64...waste catalyst, 66...new catalyst.

Claims

1. an acquisition unit that acquires the value of at least one catalyst parameter that indicates the state of the catalyst sampled from the catalytic reaction device at a first time and the value of at least one operating history parameter that indicates the operating condition of the catalytic reaction device from the first time to a second time; a calculation unit that calculates the value of at least one operation schedule parameter that indicates an operation schedule of the catalytic reaction device from the second time to a third time using the value of the at least one catalyst parameter and the value of the at least one operating history parameter, Information processing device.

2. The at least one catalyst parameter includes a parameter related to the activity of the catalyst. The information processing device according to claim 1 .

3. The at least one catalyst parameter further includes a parameter related to a metal concentration of the catalyst. The information processing device according to claim 2 .

4. The at least one operational performance parameter includes at least one of a parameter relating to a feedstock entering the catalytic reactor and a parameter relating to a product oil exiting the catalytic reactor. The information processing device according to claim 1 .

5. the catalyst is an equilibrium catalyst; The catalytic reaction device is capable of extracting the equilibrium catalyst and introducing a new catalyst having higher activity than the equilibrium catalyst, The at least one operating performance parameter includes a parameter related to a fresh catalyst. The information processing device according to claim 1 .

6. The at least one operational schedule parameter includes a parameter related to a fresh catalyst. The information processing device according to claim 5 .

7. the acquisition unit further acquires a value of at least one target parameter indicating a target state of the catalyst in the catalytic reaction device at the third time; The calculation unit further uses the value of the at least one target parameter to calculate the value of the at least one operation schedule parameter. The information processing device according to claim 1 .

8. the at least one target parameter includes a parameter related to the activity of the catalyst; The information processing device according to claim 7 .

9. the calculation unit uses a prediction model that receives as input the value of the at least one catalyst parameter and the value of the at least one operation schedule parameter and outputs the value of the at least one target parameter to calculate the value of the operation schedule parameter that will set the at least one target parameter to a predetermined value. The information processing device according to claim 7 .

10. the prediction model is generated by learning second teacher data that excludes at least a portion of first teacher data sets, the first teacher data set including a plurality of data sets each including a value of the at least one catalyst parameter, a value of the at least one operation schedule parameter, and a value of the at least one target parameter; The second teacher data is generated by elimination analysis using a first model generated by learning the first teacher data. The information processing device according to claim 9 .

11. the calculation unit calculates the value of the operation schedule parameter using a prediction model generated by learning second teacher data that excludes at least a portion of first teacher data, the first teacher data including a plurality of data sets each including a value of the at least one catalyst parameter, a value of the at least one operating record parameter, and a value of the at least one operation schedule parameter; The second teacher data is generated by elimination analysis using a first model generated by learning the first teacher data. The information processing device according to claim 1 .

12. obtaining a value of at least one catalyst parameter indicative of the condition of the catalyst sampled from the catalytic reactor at a first time; acquiring a value of at least one operating history parameter indicating an operating condition of the catalytic reaction device from the first time to the second time; and calculating a value of at least one operation schedule parameter indicating an operating condition of the catalytic reaction device from the second time to a third time using the value of the at least one catalyst parameter and the value of the at least one operating history parameter. Driving assistance methods.

13. obtaining a value of at least one catalyst parameter indicative of the state of the catalyst sampled from the catalytic reactor at a first time; a function of acquiring the value of at least one operating performance parameter indicating the operating condition of the catalytic reaction device from the first time to the second time; a function of calculating a value of at least one operation schedule parameter indicating an operating condition of the catalytic reaction device from the second time to the third time using the value of the at least one catalyst parameter and the value of the at least one operating history parameter; program.

14. a step of acquiring first teacher data comprising a plurality of data sets including a value of at least one operating history parameter indicating the operating conditions of a catalytic reaction device during a predetermined period, a first value of at least one catalyst parameter indicating the state of the catalyst sampled from the catalytic reaction device at the start of the predetermined period, and a second value of the at least one catalyst parameter indicating the state of the catalyst sampled from the catalytic reaction device at the end of the predetermined period; generating a first model that predicts a value of the at least one catalyst parameter using the first training data; A step of excluding at least a part of the data sets included in the first teacher data by analysis using the first model, and generating second teacher data; and generating a second model using the second training data to predict a value of the at least one catalyst parameter. Model generation method.

Images