Information processing device and information processing method

Abstract

To provide an information processing device, an information processing method, or a program for supporting active utilization of catalysts.SOLUTION: An information processing device according to the present disclosure includes a due temperature calculation unit that, on the basis of a first model indicative of a correlation between a plurality of parameters representing operation states of a catalyst reaction device that causes a feedstock oil to pass through a catalyst to obtain a formed oil and a deterioration degree of the catalyst, calculates a due temperature of the catalyst from operation data including the plurality of parameters, and a second model generation unit that, on the basis of the calculated due temperature and the values of the plurality of parameters used for the calculation of the due temperature, generates a second model indicative of a correlation between the due temperature and the plurality of parameters.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device and an information processing 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. It is known that the catalyst packed into catalytic reactors deteriorates with use. To maintain the desired catalytic activity, for example, it is necessary to increase the catalyst's reaction temperature depending on the degree of catalyst deterioration. A permissible temperature, which is the upper limit of the operating temperature, is set for catalytic reactors. If the reaction temperature required to obtain the desired catalytic activity exceeds the permissible temperature, the reactor cannot be operated to obtain the desired catalytic activity, and the catalyst reaches the end of its life. When the catalyst reaches the end of its life, it must be replaced.

[0003] To replace the catalyst packed in a catalytic reactor, all equipment related to the catalytic reactor must be shut down. Therefore, it is common to replace the catalyst at the scheduled timing of a statutory inspection of the catalytic reactor. From the perspective of economically operating a catalytic reactor, it is important to operate the catalytic reactor so that the catalyst's expiration temperature, which is the temperature at the specified expiration date for catalyst replacement, approaches the allowable temperature while not exceeding it. For example, a technology has been proposed that creates a catalyst deactivation function specific to a user and calculates recommended operating conditions for economically operating a catalytic reactor based on the catalyst deactivation function and the planned operating conditions (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2018 / 216746 Summary of the Invention [Problem to be solved by the invention]

[0005] An exemplary object of an embodiment of the present disclosure is to provide a technique for accurately predicting a temperature limit in order to operate a catalytic reactor economically. [Means for solving the problem]

[0006] An information processing device of one embodiment of the present disclosure includes: a deadline temperature calculation unit that calculates a deadline temperature of the catalyst from operating data including values ​​of multiple parameters based on a first model that shows the correlation between multiple parameters that indicate the operating state of a catalytic reaction device that passes raw oil through a catalyst to obtain a refined oil and the degree of deterioration of the catalyst; and a second model generation unit that generates a second model that shows the correlation between the deadline temperature and the multiple parameters based on the calculated deadline temperature and the values ​​of the multiple parameters used to calculate the deadline temperature.

[0007] Another aspect of the present disclosure is an information processing method, which includes the steps of: calculating a deadline temperature, which is the temperature of the catalyst at a predetermined deadline in the catalytic reactor, from operating data including values ​​of a plurality of parameters based on a first model that indicates a correlation between the degree of deterioration of the catalyst and a plurality of parameters that indicate the operating state of the catalytic reactor in which a feedstock oil is passed through a catalyst to produce a refined oil; and generating a second model that indicates the correlation between the deadline temperature and the plurality of parameters based on the calculated deadline temperature and the values ​​of the plurality of parameters used to calculate the deadline temperature. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a diagram illustrating an example of a schematic configuration of an information processing system and a catalytic reaction device according to an embodiment. [Figure 2] FIG. 1 is a diagram illustrating an example of a schematic hardware configuration of an information processing apparatus according to an embodiment. [Figure 3] FIG. 2 is a diagram illustrating an example of a configuration of operation data. [Figure 4] FIG. 2 is a diagram schematically illustrating an example of driving performance data. [Figure 5]FIG. 1 is a diagram schematically illustrating an example of a data set. [Figure 6] FIG. 10 is a diagram illustrating an example of a deterioration degree and an operating period. [Figure 7] FIG. 10 is a diagram illustrating an example of a time limit temperature and an operation period. [Figure 8] 10 is a flowchart showing an example of the flow of a generation process for generating a first model. [Figure 9] 10 is a flowchart showing an example of the flow of a generation process for generating a second model. [Figure 10] 10 is a flowchart showing an example of the flow of a prediction process for predicting a deadline temperature. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. The drawings are simplified, and components necessary for implementation other than those shown in the drawings are also included as appropriate. 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 component from another.

[0010] <Overall structure> FIG. 1 is a diagram showing an example of a schematic configuration of an information processing system 1 and a catalytic reaction device 500 according to this embodiment. The information processing system 1 includes an information processing device 100, a plant management device 200, a data management device 210, a user terminal 300, and a network 400. The information processing device 100, the plant management device 200, the data management device 210, and the user terminal 300 are connected to each other via the network 400 so as to be able to communicate with each other. The plant management device 200 is connected to the catalytic reaction device 500 so as to be able to communicate with each other via a wired or wireless connection. One or more user terminals 300 are provided.

[0011] Each of the information processing device 100, the plant management device 200, the data management device 210, and the user terminal 300 is, for example, a server, a workstation, or a personal computer. Each of the information processing device 100, the plant management device 200, the data management device 210, and the user terminal 300 may be, for example, a mobile terminal such as a smartphone or a tablet computer. In the present embodiment, as an example, the information processing device 100 and the plant management device 200 are servers, and the user terminal 300 is a personal computer.

[0012] The catalytic reactor 500 is an apparatus that passes a feedstock oil through a catalyst to obtain a product oil. The catalytic reactor 500 is installed, for example, in a plant. Although only one catalytic reactor 500 is shown in FIG. 1, a plurality of catalytic reactors 500 may be installed. The catalytic reactor 500 may be a group of apparatuses that perform various processes required to obtain the desired product oil. The catalytic reactor 500 is, for example, a hydrodesulfurization apparatus. The catalytic reactor 500 is not particularly limited as long as it is an apparatus that uses a catalyst.

[0013] The catalytic reactor 500 is provided with one or more sensors that measure multiple parameters that indicate the operating state of the catalytic reactor 500. The types of sensors provided in the catalytic reactor 500 are not particularly limited, and examples include a thermometer, a pressure gauge, a vibration meter, a flow meter, a tachometer, an ammeter, and a voltmeter. The operating state of the catalytic reactor 500 is represented by the values ​​of the multiple parameters. The values ​​of the multiple parameters that indicate the operating state are measured in real time, for example, at intervals of 1 to 5 minutes, by sensors provided in the catalytic reactor 500. The multiple parameters can include, for example, at least one of a parameter related to the feedstock oil, a parameter related to the product oil, and a parameter related to the operating conditions.

[0014] The network 400 is configured by a communication network including, for example, the Internet, a local area network (LAN), a wide area network (WAN), and various mobile communication systems configured by wireless base stations (not shown). 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.

[0015] The user terminal 300 is, for example, an information processing terminal used by a user or an operator who operates the catalytic reaction device 500. The user terminal 300 is installed in, for example, a head office, a branch office, a research institute, a refinery, a home, or the like, depending on the place where the user or operator works.

[0016] The user terminal 300 displays an input screen for inputting data or information to be used by the information processing device 100. The user terminal 300 also displays a setting screen for inputting operation settings for the information processing device 100. The data or information input to the user terminal 300 is transmitted to the information processing device 100, for example.

[0017] The user terminal 300 receives and displays the data or information output from the information processing device 100. The user can check the output from the information processing device 100 displayed on the user terminal 300 and operate the catalytic reaction device 500 efficiently.

[0018] The user terminal 300 may transmit and receive data or information directly to and from the information processing device 100, or may transmit and receive data or information indirectly to and from the information processing device 100. When the user terminal 300 and the information processing device 100 indirectly transmit and receive data or information to and from the information processing device 100, the user terminal 300 transmits and receives data or information to and from the information processing device 100 via the data management device 210, for example.

[0019] The user terminal 300 may be equipped with an application for exchanging data or information with the information processing device 100 or the data management device 210. The user terminal 300 may also exchange data or information with the information processing device 100 or the data management device 210 on a web browser basis.

[0020] The data management device 210 acquires and manages data or information used by the information processing device 100. The data management device 210 is, for example, a data server that acquires and stores various data or information related to the catalytic reaction device 500 from the plant management device 200. The data management device 210 may acquire and manage data or information received from the user terminal 300, or may acquire and manage data or information received from the information processing device 100. The data management device 210 may transmit the data or information that it manages in response to a request from the information processing device 100 or the user terminal 300. The data management device 210 may be omitted as appropriate. When the data management device 210 is omitted, the functions of the data management device 210 may be performed by, for example, the plant management device 200 or the information processing device 100.

[0021] The plant management device 200 collects and manages data or information from the catalytic reaction device 500. The plant management device 200 may acquire values ​​of multiple parameters measured by sensors provided in the catalytic reaction device 500, manage them in chronological order, and store them as operation history data. The plant management device 200 may also acquire signals (information) indicating the state of the catalytic reaction device 500, such as startup, shutdown, normal, or abnormal, detected by the sensors, manage them in chronological order, and store them as operation history data. The plant management device 200 may also manage signals (information) indicating the operating state of the catalytic reaction device 500, such as startup, shutdown, normal, or abnormal, detected by the sensors, in chronological order, and store them as operation data separate from the operation history data. The plant management device 200 may be omitted as appropriate. In this case, the functions of the plant management device 200 may be performed by, for example, the data management device 210 or the information processing device 100.

[0022] The information processing device 100 is a device for assisting the operation of the catalytic reaction device 500. The information processing device 100 generates a second model that indicates the correlation between the deadline temperature and a plurality of parameters. The information processing device 100 predicts the deadline temperature.

[0023] The information processing device 100 acquires data or information from the data management device 210. The information processing device 100 may acquire the data or information from the plant management device 200 or the user terminal 300. The information processing device 100 performs various information processes based on the acquired data or information.

[0024] <Hardware configuration> 2 is a diagram showing an example of the hardware configuration of an information processing device 100 according to this embodiment. The information processing device 100 includes a processor 1001, a memory 1002, a storage device 1003, an input device 1004, a display device 1005, and a communication device 1006. The information processing device 100 is configured as a computer device including a bus connecting these devices. The information processing device 100 may be configured to include one or more of the devices shown in FIG. 2, or may be configured without including some of the devices.

[0025] The processor 1001 performs arithmetic processing of various data and controls the information processing device 100 including the display device 1005, etc. The processor 1001 may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. The processor 1001 reads programs and the like required to execute processing in the information processing device 100 from at least one of the storage device 1003 and the communication device 1006 into the memory 1002, and executes processing in accordance with these programs and the like.

[0026] The memory 1002 is a computer-readable storage medium and may be configured by, for example, at least one of a ROM (Read Only Memory), an EPROM (Erasable Program ROM), an EEPROM (Electrically Erasable Program ROM), a RAM (Random Access Memory), etc. The memory 1002 stores various data, and stores programs (program codes) and the like necessary for executing processes in the information processing device 100.

[0027] The storage device 1003 is a non-transitory computer-readable storage medium, and is configured, for example, as a hard disk drive, a solid state drive, or the like. The storage device 1003 stores various programs and data necessary for executing processes in the information processing device 100, including the program according to this embodiment, as well as data resulting from the processing. Note that the non-transitory computer-readable storage medium may also be configured as at least one of a magnetic tape, a flexible disk, an optical disk, a digital versatile disk, a magneto-optical disk, a memory card, a USB memory, and the like. The storage device 1003 may also be called an auxiliary storage device.

[0028] The input device 1004 is an input device (for example, a keyboard, a mouse, etc.) that receives input from the outside. The display device 1005 is a display device (for example, a display, etc.) that outputs to the outside. The input device 1004 and the display device 1005 may be integrated into one unit (for example, a touch panel).

[0029] The communication device 1006 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network. The communication device 1006 is also called, for example, a network device, a network interface card, a network controller, a network module, or a communication module. The communication device 1006 transmits and receives various types of data to and from, for example, the plant management device 200, the data management device 210, and the user terminal 300.

[0030] The information processing device 100 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks described below may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0031] The information processing device 100 may be configured as a single information processing device, or may be configured as multiple information processing devices distributed over a communication network. Also, FIG. 2 shows only a portion of the main hardware configuration of the information processing device 100. The information processing device 100 may also have other configurations that are generally included in a server, for example. Furthermore, the hardware configurations of the plant management device 200, the data management device 210, and the user terminal 300 may also have the same configuration as the information processing device 100.

[0032] <Functional configuration of information processing device 100> 1, the information processing device 100 has, as its functional configuration, a processing unit 110, a storage unit 120, and a communication unit 130. The information processing device 100 may further include an input unit through which a user inputs data and a display unit that displays data to the user, both of which are not shown. The information processing device 100 may receive a user request from its own input unit. Furthermore, the information processing device 100 may display data processed by the processing unit 110 on its own display unit.

[0033] The functional components of the information processing device 100 are realized by the processor 1001 reading a program into the memory 1002 and executing it. Note that programs that implement at least some of the functions of these functional components may be installed in multiple storage devices. The processors of multiple computers may fulfill the functions of multiple functional components by reading the programs installed in their own devices into their memories and executing them. In other words, the functions of multiple functional components may be distributed and executed by multiple computers.

[0034] The communication unit 130 is a communication interface in the information processing device 100. The communication unit 130 is connected to the network 400 via an access line. The communication unit 130 communicates with at least one of the user terminal 300, the data management device 210, and the plant management device 200 via the network 400. The communication unit 130 performs various protocol processes required for communication with the user terminal 300, the data management device 210, and the plant management device 200.

[0035] The storage unit 120 stores data or information. The storage unit 120 stores, for example, data or information acquired from at least one of the plant management device 200, the data management device 210, and the user terminal 300. The storage unit 120 may store various data acquired, calculated, or generated by the processing unit 110. The storage unit 120 may store, for example, at least one of operation data, operation performance data, operation data, operation schedule data, equipment data, threshold data, a first model, a second model, a data set, and the like. The above-mentioned data may be stored in the storage unit 120 in advance. The data or information stored in the storage unit 120 is not limited to the above examples. Representative data or information that may be stored in the storage unit 120 will be described below.

[0036] The operating data is data including values ​​of multiple parameters that indicate the operating state of the catalytic reactor 500. The multiple parameters included in the operating data include at least one of parameters related to operating conditions, parameters related to the product oil, and parameters related to the feed oil. The operating data may be generated, for example, based on values ​​of multiple parameters measured by sensors provided in the catalytic reactor 500. The operating data may also be generated based on values ​​of multiple parameters that indicate the operating state of a catalytic reactor 500 simulated using MIRROR PLANT software (simulation).

[0037] The operating condition parameters include, for example, at least one of a parameter related to the catalyst degradation level, a parameter related to the catalyst temperature (temperature inside the reaction vessel), a parameter related to the throughput of the catalytic reactor 500, a parameter related to the pressure inside the reaction vessel, a parameter related to the reactant gas partial pressure, and a parameter related to the reactant gas supply rate. When the reactant gas supplied to the catalytic reactor 500 is hydrogen gas, the operating condition parameters may further include a parameter related to hydrogen. The hydrogen-related parameters include, for example, at least one of a parameter related to the supply rate of hydrogen gas to the catalytic reactor 500, a parameter related to the hydrogen gas partial pressure, a parameter related to the hydrogen gas components, and a parameter related to the hydrogen-oil ratio (amount of hydrogen gas supplied per amount of feedstock oil passed). Note that the hydrogen gas components (purity of hydrogen gas) are important from the perspective of hydrogenation performance because the amount of hydrogen gas usable for the reaction decreases relatively as the amount of impurities other than hydrogen gas (e.g., hydrogen sulfide gas, ammonia gas, etc.) contained in the hydrogen gas decreases. The same is true for the hydrogen-oil ratio, because the amount of hydrogen gas usable per amount of feedstock oil passed decreases relatively as the hydrogen-oil ratio value decreases. The lower the hydrogenation ability, the more accelerated the coke deterioration of the catalyst, which will be described later. Therefore, from the viewpoint of predicting the life of the catalyst, the components of the hydrogen gas and the hydrogen-oil ratio are important information.

[0038] Here, the degree of catalyst deterioration is an index that indicates the extent of deterioration of the catalyst. The degree of deterioration can be, for example, the residual activity ratio of the catalyst shown in the following formula (1). The residual activity ratio is the ratio of the apparent frequency factor At of the catalyst at time t (time t within the operating period or the elapsed time t since the start of operation) to the apparent frequency factor A0 (which indicates the degree of catalytic activity) of the catalyst at the start time (time 0) of operation of the catalytic reaction device 500, and is shown as formula (1). Φ represents the residual activity ratio.

number

[0039] The value of the residual activity ratio is 1 at the start of operation (time 0). The value of the residual activity ratio gradually decreases as the operating time of the catalytic reaction device 500 progresses. Catalyst deterioration is typically classified into coke deterioration and metal deterioration. Coke deterioration refers to catalyst deterioration caused by coke accumulating on the catalyst during the catalytic reaction process. Metal deterioration refers to catalyst deterioration caused by metals contained in the feed oil accumulating on the catalyst during the catalytic reaction process. In this way, the decrease in the value of the residual activity ratio (catalyst deterioration) is affected by the operating state of the catalytic reaction device 500.

[0040] The parameters related to the product oil include, for example, at least one of a parameter related to the sulfur concentration of the product oil, a parameter related to the metal concentration of the product oil, and a parameter related to the aromatic concentration of the product oil.

[0041] The parameters related to the feedstock oil include, for example, at least one of a parameter related to the sulfur concentration of the feedstock oil, a parameter related to the metal concentration of the feedstock oil, and a parameter related to the aromatic concentration of the feedstock oil.

[0042] When the stock oil is composed of multiple base stocks, the parameters related to the stock oil may include at least one of a parameter related to the content ratio of the base oils constituting the stock oil, a parameter related to the sulfur concentration of the base oil, a parameter related to the metal concentration of the base oil, and a parameter related to the aromatic concentration of the base oil.

[0043] When the feedstock is composed of M types of base oils ranging from 1 to M (M is an integer of 2 or greater), the parameters related to the feedstock may include at least one of a parameter related to the content ratio of the Xth base oil (X is an integer from 1 to M) of interest to the user, a parameter related to the sulfur concentration, a parameter related to the metal concentration, a parameter related to the aromatic component concentration, etc. Furthermore, when the feedstock is composed of M types of base oils, the parameters related to the feedstock may include at least one of a parameter related to the content ratio, a parameter related to the sulfur concentration, a parameter related to the metal concentration, a parameter related to the aromatic component concentration, etc., for at least one of the M types of base oils. Because the load on the catalyst varies depending on the type of feedstock, changing the content ratio of the base oils contained in the feedstock may change the deterioration tendency of the catalyst in the catalytic reaction device 500. For example, in the case of hydrodesulfurization, the catalyst tends to deteriorate more easily as the proportion of heavier base oils (with a higher carbon number) in the feedstock increases.

[0044] The type of base oil contained in the feedstock is not particularly limited, and any base oil that can be used to produce petroleum products such as gasoline, kerosene, or diesel can be used. For example, straight-run base oils obtained from atmospheric distillation units or vacuum distillation units, or cracked base oils obtained from fluid catalytic cracking units, can be used as base oils. Straight-run or cracked naphtha fractions, kerosene fractions, diesel fractions, or heavy oil fractions can be used. For example, light gas oil (LGO) or light cycle oil (LCO) can be used as base oils contained in the feedstock. For example, unconventional hydrocarbons such as FT synthetic oil, cracked kerosene from FT synthetic oil, and diesel fractions from FT synthetic oil can also be used as base oils contained in the feedstock. Furthermore, bio-derived oils, cracked kerosene from bio-derived oils, and diesel fractions from bio-derived oils can also be used as base oils contained in the feedstock. Furthermore, waste-derived oils (e.g., waste plastics, waste tires, waste cooking oil, etc.) and their cracked kerosene / diesel fractions can also be used as base oils contained in the feedstock.

[0045] FIG. 3 is a diagram schematically illustrating operational data. In FIG. 3, "Case ID" is an ID for identifying a set of values ​​of multiple parameters. In the example of FIG. 3, the multiple parameters include four or more parameters, namely, a first parameter, a second parameter, a third parameter, . . ., an Nth parameter. In the example of FIG. 3, the operational data is composed of 200 sets of values ​​of multiple parameters. Here, the "set of values ​​of multiple parameters" in the operational data refers to a set of values ​​of the first parameter to the Nth parameter for a certain Case ID. Note that the type of multiple parameters does not have to be singular, but may be two or more (N is an integer equal to or greater than two). Furthermore, the operational data does not have to include a Case ID, and may include information other than the set of values ​​of multiple parameters and the Case ID. In this embodiment, the first parameter is the throughput of the feedstock oil of the catalytic reaction device 500. The second parameter is the sulfur concentration of the feedstock oil. The third parameter is the content ratio of a specific base oil (e.g., LCO) contained in the feedstock oil. The user can appropriately select these parameters from at least one of parameters relating to operating conditions, parameters relating to the product oil, and parameters relating to the feed oil.

[0046] The operating history data includes values ​​of multiple parameters that indicate the past operating state of the catalytic reaction device 500. The operating history data includes, for example, the values ​​of the multiple parameters and the acquisition dates and times of the values ​​of the multiple parameters. The operating history data is generated, for example, by the plant management device 200 accumulating the values ​​of the multiple parameters acquired from sensors of the catalytic reaction device 500 and the acquisition dates and times. The values ​​of the multiple parameters included in the operating history data are recorded, for example, at a predetermined time interval. The predetermined time interval is not particularly limited, and examples include every minute, every five minutes, every ten minutes, every 30 minutes, every 60 minutes, and every day. The plant management device 200 acquires the parameter values ​​in association with the acquisition dates and times. The acquisition dates and times are, for example, the dates and times when the values ​​of the multiple parameters were measured by sensors provided in the catalytic reaction device 500. Note that the acquisition dates and times may also be the dates and times when the plant management device 200 acquired the parameter values.

[0047] The values ​​of the multiple parameters included in the operating performance data may be the sensor measurement values ​​themselves, or may be calculated values ​​calculated from the measurement values ​​of one or more sensors. The plant management system 200 may acquire measurement values ​​from one or more sensors and calculate the value of at least one parameter using the acquired measurement values. For example, the plant management system 200 may acquire a first measurement value from a first sensor of the catalytic reaction device 500 and a second measurement value from a second sensor of the catalytic reaction device 500, and calculate the ratio of the first measurement value to the second measurement value as the parameter value.

[0048] The operating history data may further include signals (information) indicating the operating state of the catalytic reaction device 500, such as start, stop, normal, or abnormal, sensed by a sensor. In this case, the plant management device 200 generates operating history data by storing not only the values ​​of the multiple parameters but also the signals indicating the operating state of the catalytic reaction device 500 in association with the acquisition date and time. Note that the plant management device 200 may replace the acquired signals indicating the operating state with other corresponding information and then store the replaced signals to generate operating history data.

[0049] FIG. 4 is a diagram illustrating a schematic example of driving performance data. In FIG. 4, the driving performance data is associated with the values ​​of multiple parameters for each time (acquisition date and time) from T1 to Tm. In the example of FIG. 4, the multiple parameters are shown as four or more parameters, namely, a first parameter, a second parameter, a third parameter, ..., an Nth parameter. In the example of FIG. 4, the driving performance data is composed of a set of m parameter values. Here, the "set of parameter values" in the driving performance data refers to a set of values ​​from the first parameter to the Nth parameter at a certain time. Note that in the example of FIG. 4, the multiple parameters included in the driving performance data are the same as the multiple parameters included in the driving data, but this is not limited thereto. The driving performance data only needs to include at least the multiple parameters included in the driving data.

[0050] The operation data is data including time-series information of signals (information) that indicate the operation state, such as start, stop, normal, or abnormal, of the catalytic reaction device 500, as sensed by a sensor. The operation data is data that is generated, for example, when the operation performance data does not include signals (information) that indicate the operation state. In this case, the plant management device 200 generates operation data by acquiring and accumulating signals in association with the acquisition date and time.

[0051] The operation schedule data is data including values ​​of multiple parameters that indicate the operation state planned for the catalytic reaction device 500. The types of parameters included in the operation schedule data may include at least the multiple parameters included in the second model. The values ​​of the multiple parameters included in the operation schedule data may be set for each time period, or may be set commonly regardless of time. The values ​​of the multiple parameters included in the operation schedule data may be values ​​that indicate the operation state that the user wishes to apply to the catalytic reaction device 500. In the present disclosure, a "set of multiple parameter values" in the operation schedule data refers to a set of values ​​from the first parameter to the Nth parameter at a certain time period. Note that when the values ​​of the multiple parameters included in the operation schedule data are set commonly regardless of time, the "set of multiple parameter values" can be considered as one. The operation schedule data can be changed (updated) as needed, for example, from the user terminal 300.

[0052] The operation schedule data may be determined in advance using constraints based on business information. Here, the business information may include, for example, parameters determined based on the plant operation environment, etc., and parameters determined based on plant operation decisions, etc. Parameters determined based on the plant operation environment, etc. are difficult to change based on decisions regarding plant operation. However, parameters determined based on plant operation decisions, etc. can be changed to a certain extent freely based on decisions regarding plant operation. Parameters determined based on the plant operation environment, etc. include, for example, parameters related to at least one of crude oil price, base oil price, feedstock price, and product oil price. Parameters determined based on plant operation decisions, etc. include, for example, parameters related to at least one of crude oil inventory, base oil inventory, feedstock inventory, and product oil inventory.

[0053] The constraint condition based on business information is a constraint equation that uses, for example, "gross profit" as an objective function and includes a parameter determined based on the plant operation environment, etc., a parameter determined by plant operation decisions, etc., and at least one of the multiple parameters included in the operation schedule data. In this case, the constraint condition based on business information can determine the value of at least one of the multiple parameters included in the constraint equation by deriving, for example, a combination of parameter values ​​that maximizes gross profit. This allows the user to prepare operation schedule data that is more economically rational. As a result, the catalyst in the catalytic reaction device 500 can be used more efficiently and economically.

[0054] The device data includes at least one of an operating limit, an allowable temperature, an allowable processing amount, and the like, which are predetermined for the catalytic reaction device 500.

[0055] The operation deadline is a deadline that is determined in advance based on, for example, a production plan or a maintenance plan related to the catalytic reaction apparatus 500. The operation deadline is, for example, the number of days that the catalytic reaction apparatus 500 is expected to continue operating, the number of days remaining until catalyst replacement scheduled for the catalytic reaction apparatus 500, or the date and time of catalyst replacement. Note that the operation deadline can be changed as appropriate based on, for example, an instruction from the user terminal 300.

[0056] The allowable temperature is a temperature that is determined in advance based on, for example, at least one of the heat resistance temperature of the catalytic reaction apparatus 500, the heat resistance temperature of the catalyst filled in the catalytic reaction apparatus 500, the heat resistance temperature of the feed oil supplied to the catalytic reaction apparatus 500, and the heat resistance temperature of the product oil produced by the catalytic reaction apparatus 500. The allowable temperature may be set with a margin as necessary for maintenance of the catalytic reaction apparatus 500 and quality control of the product oil. The allowable temperature can be changed as appropriate based on, for example, an instruction from the user terminal 300.

[0057] The allowable throughput is a quantity that is determined in advance based on the upper limit of the feedstock oil throughput that can be processed by the catalytic reaction device 500. The allowable throughput may be set with a margin as needed for the purpose of maintaining the catalytic reaction device 500 and controlling the quality of the produced oil. The allowable throughput can be changed as appropriate based on instructions from the user terminal 300, for example.

[0058] The threshold data is data including thresholds used to extract a set of specific parameter values ​​from the driving performance data in order to generate driving data from the driving performance data. The threshold data includes, for example, at least one of a first threshold and a second threshold corresponding to the first parameter, a third threshold and a fourth threshold corresponding to the second parameter, and a fifth threshold and a sixth threshold corresponding to the third parameter. The first threshold is set to, for example, a value smaller than the second threshold. The third threshold is set to, for example, a value smaller than the fourth threshold. The fifth threshold is set to, for example, a value smaller than the sixth threshold. In this embodiment, the first threshold is, for example, 20,000 BD. The second threshold is, for example, 40,000 BD. The third threshold is, for example, 0.5 wt%. The fourth threshold is, for example, 1.5 wt%. The fifth threshold is, for example, 0 vol%. The sixth threshold is, for example, 15 vol%. The threshold data may also include thresholds other than the above-mentioned thresholds. The value of each threshold value can be changed as appropriate depending on, for example, the type of parameter indicating the corresponding operating state or the set of multiple parameter values ​​that the user wants to extract.

[0059] The first model is a model that shows the correlation between multiple parameters that indicate the operating state of the catalytic reaction device 500 and the degree of catalyst deterioration. The first model is capable of outputting the degree of catalyst deterioration when values ​​of multiple parameters are input. The first model may be a linear function, or a more complex expression such as a nonlinear function, a multivariate polynomial, a rational expression, an irrational expression, or an expression including an exponent or a logarithm. The first model is, for example, a function that is generated or updated by determining the value of a deterioration contribution parameter included in the first reference model based on operating performance data. The deterioration contribution parameter may be a hyperparameter. Details of the method for generating and updating the first model will be described later.

[0060] The first reference model is, for example, a function including a plurality of input variables, a deterioration contribution parameter related to at least one of the plurality of input variables, and an output variable. The plurality of input variables are, for example, a plurality of parameters. The output variable is, for example, the degree of deterioration. The first reference model may be a linear function or a more complex expression such as a nonlinear function, a multivariate polynomial, a rational expression, an irrational expression, or an expression including an exponent or a logarithm.

[0061] The first reference model is a function derived from existing knowledge or experiments. The first reference model is derived using at least one of the following: technical information such as theoretical formulas described in literature; knowledge regarding the properties of the product oil and the degree of catalyst degradation under various operating conditions obtained through the use of the catalytic reactor 500; knowledge regarding the properties of the product oil and the degree of catalyst degradation under various operating conditions obtained through the use of an experimental device corresponding to the catalytic reactor 500; and knowledge regarding the properties of the product oil and the degree of catalyst degradation under various operating conditions obtained through the use of another catalytic reactor having equivalent functions to the catalytic reactor 500. Note that the experimental device corresponding to the catalytic reactor 500 is, for example, a test device that is relatively smaller than the catalytic reactor 500 and can collect data necessary for operating the catalytic reactor 500 at a lab scale, bench scale, or pilot scale. In addition, examples of other catalytic reaction apparatuses having equivalent functions to the catalytic reaction apparatus 500 include, for example, when the catalytic reaction apparatus 500 installed in a plant is a hydrodesulfurization apparatus, other hydrodesulfurization apparatuses installed in the plant, hydrodesulfurization apparatuses installed in other plants, etc.

[0062] Next, an example of the first reference model will be described. In this embodiment, for example, the first reference model is a model in which the time derivative of the logarithm of the remaining activity ratio Φ, which is an output variable, is expressed as a function of a plurality of deterioration contribution parameters p α ,p β ,p γ, ...and multiple parameters (input variables) H at time (operating time) t 1t ,H 2t ,…,H mt It is expressed as a function g of

number

[0063] The first reference model may use the left side (output variable) as the time differential of the logarithm of the remaining activity ratio Φ as shown in the above equation (2), but may use the left side (output variable) as the time differential of the remaining activity ratio Φ as shown in the following equation (2-1). Here, p α , p β , p δ , p ζ , p γ and p ε is a degradation contribution parameter. For example, p γ and p ε is a hyperparameter.

number

[0064] The first reference model may not have the left side (output variable) as the time differential of the logarithm of the remaining activity fraction Φ as shown in the above equation (2), but may have the left side (output variable) as the remaining activity fraction Φ and the right side as a function including the operating time t, i.e., a variable representing the operating time, as shown in the following equation (2-2), where exp is an exponential function and s is an arbitrary function.

number

[0065] The first reference model is not limited to the above-mentioned formulas (2), (2-1), and (2-2). The first reference model may be, for example, formula (2'), (2-1'), or (2-2') to which a new deterioration contribution parameter serving as a coefficient or multiplier is added to any input variable included in the above-mentioned formulas (2), (2-1), and (2-2). Note that although the same symbols are used for the input variables and deterioration contribution parameters in the above-mentioned formulas (2), (2-1), and (2-2), the input variables and deterioration contribution parameters do not necessarily have to be the same between these formulas.

[0066] The data set is, for example, a correspondence between a deadline temperature calculated using a first model and the operating data used to calculate the deadline temperature. FIG. 5 is a diagram schematically showing a data set. In FIG. 5, a deadline temperature and a set of multiple parameter values ​​corresponding to the deadline temperature are organized in each row. The example shown in FIG. 5 includes 200 data sets. The example in FIG. 5 exemplarily shows the operating data (a set of multiple parameter values) shown in FIG. 3 and the deadline temperature obtained from the operating data.

[0067] The second model is a model that shows the correlation between multiple parameters and deadline temperature. The second model can output a value of deadline temperature when values ​​of multiple parameters are input. The second model may be a linear function, or a more complex expression such as a nonlinear function, a multivariate polynomial, a rational expression, an irrational expression, or an expression including an exponent or a logarithm. The second model is, for example, a function that is generated or updated by determining the value of a temperature contribution parameter included in the second reference model based on a dataset. Note that the temperature contribution parameter may be a hyperparameter.

[0068] The second reference model is, for example, a function including a plurality of input variables, a temperature contribution parameter coefficient related to at least one of the plurality of input variables, and an output variable. The plurality of input variables are, for example, a plurality of parameters. The output variable is, for example, a deadline temperature. The second reference model may be a linear function or a more complex expression such as a nonlinear function, a multivariate polynomial, a rational expression, an irrational expression, or an expression including an exponent or a logarithm. The second reference model is, for example, a function derived from existing knowledge or experiments.

[0069] As an example of the second reference model, the following equation (3) is shown. In the equation (3), for example, a plurality of parameters are expressed as input variables y1 to y n and the deadline temperature is the output variable T EOR and multiple temperature contribution parameters k1 to k n+1 As an example, the temperature contribution parameter kn+1 is a hyperparameter. Note that the second reference model is not limited to equation (3) described later. The second reference model may be, for example, equation (3) to which a new temperature contribution parameter serving as a coefficient or multiplier is added for any input variable included in equation (3) described later.

number

[0070] Next, a description will be given of the details of the processing unit 110. The processing unit 110 includes, for example, an acquisition unit 111, a first model generation unit 112, an operating data generation unit 113a, a deadline temperature calculation unit 113b, a data set generation unit 113c, a second model generation unit 114, a deadline temperature prediction unit 115, and an output unit 116.

[0071] The acquisition unit 111 acquires various data or information from the plant management device 200, the data management device 210, or the user terminal 300 via the network 400. The acquisition unit 111 acquires, for example, at least one of operation data, operation record data, operation data, operation schedule data, equipment data, threshold data, a first model, a first reference model, and a second reference model. The data or information acquired by the acquisition unit 111 is not limited to the above examples. The acquisition unit 111 stores the acquired various data or information in the storage unit 120.

[0072] The acquiring unit 111 may acquire various data or information based on a period (time interval) that is predetermined depending on the type of data or information. Furthermore, the acquiring unit 111 may acquire various data or information based on an instruction from the user terminal 300.

[0073] (Generation of the first model) For example, when the first model cannot be acquired by the acquisition unit 111 or the first model is not stored in the storage unit 120, the first model generation unit 112 generates the first model based on the driving performance data. The first model generation unit 112 generates the first model by determining values ​​of deterioration contribution parameters included in the first reference model based on the driving performance data. For example, the first model generation unit 112 may fit the first reference model based on the driving performance data, or may perform machine learning using the driving performance data as training data.

[0074] For example, if the deterioration level is not included in the operating performance data acquired by the acquisition unit 111, the first model generation unit 112 calculates the deterioration level before generating the first model. The first model generation unit 112 calculates the deterioration level of the catalyst in the catalytic reaction device 500 for each time based on the operating performance data. An example of a method for calculating the deterioration level of the catalyst at any time t will be described below.

[0075] The first model generation unit 112 calculates the degree of deterioration based on the operational performance data using the equations (4-1), (4-2), and (5) described below. The equations (4-1) and (4-2) are equations for calculating the apparent reaction rate constant k from the sulfur concentration of the feed oil, the sulfur concentration of the product oil, and the feed oil throughput. n is the reaction order, which is determined in advance. [S] is the sulfur concentration of the product oil at the operating time t, and [S]0 is the sulfur concentration of the feed oil. LHSV is the liquid hourly space velocity at the operating time t, i.e., the feed oil throughput at the operating time t. The equation (4-1) is used when n≠1.

number

[0076] Equation (4-2) is used when n=1.

number

[0077] Equation (5) corresponds to the so-called Arrhenius equation.

number

[0078] The first model generation unit 112 calculates the apparent reaction rate constant k at time t based on equations (4-1) and (4-2) using the values ​​of the feedstock oil throughput, the sulfur concentration of the feedstock oil, and the sulfur concentration of the product oil at time t included in the operational history data. The first model generation unit 112 calculates the apparent frequency factor A based on equation (5) using the calculated apparent reaction rate constant k and the reaction temperature T at operation time t included in the operational history data. The calculated apparent frequency factor A corresponds to the apparent frequency factor At of the catalyst at operation time t.

[0079] The first model generation unit 112 calculates the degree of catalyst deterioration Φ at operating time t based on the ratio between the apparent frequency factor At at operating time t and the apparent frequency factor A0 at the start of operation (operating time t=0). Here, the apparent frequency factor A0 is given in advance or calculated in the same manner as the apparent frequency factor At. The first model generation unit 112 can calculate the degree of deterioration for each time in a predetermined period by repeating the above calculation for each time in the predetermined period.

[0080] When generating the first model, the first model generation unit 112 may further use operational history data of a catalytic reaction device (second catalytic reaction device) similar to the catalytic reaction device 500. Here, examples of the "catalytic reaction device similar to the catalytic reaction device 500" include an experimental device corresponding to the catalytic reaction device 500 and another catalytic reaction device having the same function as the catalytic reaction device 500.

[0081] Furthermore, when generating the first model, the first model generation unit 112 may use operational history data relating to the time after it is determined that the unstable period has ended. Here, the "unstable period" refers to a period in which the degree of catalyst degradation changes drastically, which occurs immediately after the start of feeding oil through the catalytic reactor 500. It is known that initial degradation, in which the catalyst activity rapidly decreases, occurs during an initial period after the catalytic reactor 500 starts operating and feedstock oil begins to be fed through the catalyst. After this period has elapsed, the change in catalyst activity becomes gradual, and the change in the degree of degradation stabilizes. The first model generation unit 112 may determine the end of the unstable period based on the time-series data included in the acquired operational history data. The first model generation unit 112 may determine the end of the unstable period based on the time (operating time) of the catalytic reactor 500 included in the operational history data. The user may, for example, determine in advance information relating to the length of the unstable period (e.g., operation time, cumulative value of feedstock oil throughput, amount of change in degradation level or rate of change in degradation level) based on past operating records of the catalytic reaction apparatus 500 or an apparatus similar to the catalytic reaction apparatus 500, and store the predetermined information relating to the length of the unstable period in the storage unit 120. In this case, the first model generation unit 112 can determine the end of the unstable period in the acquired operating record data by comparing the stored information relating to the length of the unstable period with corresponding information included in the acquired operating record data.

[0082] Furthermore, when new operating history data is acquired by the acquisition unit 111, the first model generation unit 112 may update (regenerate) the first model by redetermining the deterioration-contribution parameters based on the new operating history data. The new operating history data is, for example, data including values ​​of multiple parameters that indicate the past operating state of the catalytic reaction device 500 at a time later than the operating history data used to generate the first model. The first model generation unit 112 can update the first model based on the acquired new operating history data in the same manner as the above-described method for generating the first model. By updating the first model based on the new operating history data, it is possible to reflect a newer state of the catalytic reaction device 500 in the first model.

[0083] (Generation of driving data) The driving data generation unit 113a generates driving data, for example, when driving data cannot be acquired by the acquisition unit 111 or when driving data is not stored in the storage unit 120. The driving data generation unit 113a generates driving data based on driving performance data, for example.

[0084] When generating driving data based on driving performance data, the driving data generation unit 113a extracts a set of specific parameter values ​​from the driving performance data based on the values ​​of the parameters included in the driving performance data. Furthermore, the driving data generation unit 113a generates driving data based on the extracted set. Note that the set of specific parameter values ​​extracted by the driving data generation unit 113a may be single or multiple.

[0085] For example, when a predetermined first condition is satisfied for a value of a first parameter included in a set of values ​​of a plurality of parameters in the driving performance data, the driving data generating unit 113a may extract a set of values ​​of a plurality of parameters including the value of the first parameter that satisfies the first condition as a set of values ​​of a specific plurality of parameters. An example of extracting a set of values ​​of a specific plurality of parameters based on the first condition (first parameter) will be described below.

[0086] The driving data generation unit 113a may extract a specific set of parameter values ​​from the driving performance data based on, for example, the value of a first parameter included in the driving performance data and first and second thresholds predetermined for the first parameter. More specifically, when the value of the first parameter is equal to or greater than the first threshold and equal to or less than the second threshold, the driving data generation unit 113a extracts a set of parameter values ​​including the value of the first parameter as a specific set of parameter values. When the value of the first parameter is less than the first threshold or exceeds the second threshold, the driving data generation unit 113a does not extract a set of parameter values ​​including the value of the first parameter as a specific set of parameter values. The driving data generation unit 113a sequentially performs these processes on each set of parameter values ​​included in the driving performance data to extract the specific set of parameter values ​​from the driving performance data. Next, an example will be described using sets of parameter values ​​from time T1 to time T6 shown in FIG. 4. In this case, the operating data generating unit 113a extracts a set of parameter values ​​corresponding to time T1, time T2, and time T6 as a specific set of parameter values.

[0087] For example, when the value of a first parameter is not zero (0) and not null, the operational data generation unit 113a may extract a set of parameter values ​​including the value of the first parameter as a specific set of parameter values. When the value of the first parameter is zero (0) or null, the operational data generation unit 113a does not extract a set of parameter values ​​including the value of the first parameter as a specific set of parameter values. Next, an exemplary explanation will be given using the sets of parameter values ​​from time T1 to time T6 shown in FIG. 4. In this case, the operational data generation unit 113a extracts the sets of parameter values ​​corresponding to time T1, time T2, time T3, time T4, and time T6 as a specific set of parameter values.

[0088] The driving data generation unit 113a may extract a set of specific parameter values ​​from the driving performance data so as to include the most frequent value of the first parameter included in the driving performance data, for example. In this case, before extracting the set of specific parameter values, the driving data generation unit 113a may refer to the value of the first parameter included in the driving performance data and calculate the most frequent value of the first parameter. Furthermore, the most frequent value of the first parameter does not necessarily have to be a single value, but may have a range (value range) predetermined by the user. For example, when the values ​​of the first parameter included in the driving performance data are divided into predetermined ranges, the range to which the first parameter belongs in the largest number of times may be treated as the most frequently occurring value of the first parameter. Note that the predetermined range can be changed as appropriate by the user. Next, an example will be described using the set of parameter values ​​from time T1 to time T6 shown in FIG. 4. For example, when the mode is in a certain interval (25000 to 30000), the operating data generating unit 113a extracts a set of parameter values ​​corresponding to time T1 and time T6 as a specific set of parameter values.

[0089] The driving data generating unit 113a may extract a set of specific parameter values ​​from the driving performance data further based on, for example, a second parameter different from the first parameter. For example, when a predetermined second condition is satisfied for the value of a second parameter included in the set of parameter values ​​of the driving performance data, the driving data generating unit 113a may extract, as a specific set of parameter values, a set of parameter values ​​including the value of the second parameter that satisfies the second condition. For example, the driving data generating unit 113a may extract a set of parameter values ​​from the driving performance data based on the first parameter (first condition), and then extract a specific set of parameter values ​​from the extracted set based on the second parameter. An example of extracting a specific set of parameter values ​​based on the second condition (second parameter) will be described below.

[0090] The driving data generation unit 113a may extract a set of specific parameter values ​​based on, for example, the value of a second parameter included in the driving performance data and third and fourth thresholds predetermined for the second parameter. More specifically, when the value of the second parameter is equal to or greater than the third threshold and equal to or less than the fourth threshold, the driving data generation unit 113a extracts a set of parameter values ​​including the value of the second parameter as a set of specific parameter values. When the value of the second parameter is less than the third threshold or exceeds the fourth threshold, the driving data generation unit 113a does not extract a set of parameter values ​​including the value of the second parameter as a set of specific parameter values. Hereinafter, a description will be given using, as an example, the sets of parameter values ​​from time T1 to time T6 shown in FIG. 4. In this case, the driving data generation unit 113a compares the first parameter with the first and second thresholds and the second parameter with the third and fourth thresholds, thereby extracting a set of parameter values ​​corresponding to time T2 and time T6 as a set of specific parameter values.

[0091] The driving data generating unit 113a may extract a set of specific parameter values ​​from the driving performance data further based on, for example, a third parameter different from the first parameter and the second parameter. For example, when a predetermined third condition is satisfied for the value of a third parameter included in the set of parameter values ​​of the driving performance data, the driving data generating unit 113a may extract, as a specific set of parameter values, a set of parameter values ​​including the value of the third parameter that satisfies the third condition. For example, after extracting a set of parameter values ​​from the driving performance data based on the first parameter, the driving data generating unit 113a may extract a specific set of parameter values ​​from the extracted set further based on the third parameter. An example of extracting a specific set of parameter values ​​based on the third condition (third parameter) will be described below.

[0092] The operating data generation unit 113a may extract a set of specific parameter values ​​based on, for example, the value of a third parameter included in the operating performance data and fifth and sixth thresholds predetermined for the third parameter. More specifically, when the value of the third parameter is equal to or greater than the fifth threshold and equal to or less than the sixth threshold, the operating data generation unit 113a extracts a set of parameter values ​​including the value of the third parameter as a set of specific parameter values. When the value of the third parameter is less than the fifth threshold or exceeds the sixth threshold, the operating data generation unit 113a does not extract a set of parameter values ​​including the value of the third parameter as a set of specific parameter values. Hereinafter, a description will be given using, as an example, the sets of parameter values ​​from time T1 to time T6 shown in FIG. 4. In this case, the operating data generation unit 113a compares the first parameter with the first and second thresholds and the third parameter with the fifth and sixth thresholds to extract a set of parameter values ​​corresponding to time T1 and time T6 as a set of specific parameter values.

[0093] Furthermore, when generating the operating data, the operating data generating unit 113a may use not only the operating history data of the catalytic reaction device 500 (first catalytic reaction device) but also the operation data of the catalytic reaction device 500. Since the operating data includes time-series information on the operating state of the catalytic reaction device 500, the operating data generating unit 113a can compare the operating data with the operating history data to extract from the operating history data a set of specific multiple parameter values ​​that indicate that the catalytic reaction device is operating normally.

[0094] Furthermore, when generating the operating data, the operating data generating unit 113a may use not only the operating history data of the catalytic reaction device 500 (first catalytic reaction device), but also the operating history data of a catalytic reaction device similar to the catalytic reaction device 500 (second catalytic reaction device). Here, examples of the "catalytic reaction device similar to the catalytic reaction device 500" include an experimental device corresponding to the catalytic reaction device 500 and another catalytic reaction device having the same function as the catalytic reaction device 500. The operating history data of the second catalytic reaction device may be referred to as "other device operating history data" in the present disclosure. Note that the other device operating history data only needs to include at least a plurality of parameters included in the operating data to be generated, and does not need to include all of the multiple parameters included in the operating history data.

[0095] The deadline temperature calculation unit 113b calculates a deadline temperature from the operating data based on the first model. For example, the deadline temperature calculation unit 113b inputs a set of specific parameter values ​​included in the operating data into the first model, and calculates a deadline temperature corresponding to the set of parameter values.

[0096] The deadline temperature calculation unit 113b calculates the degree of catalyst deterioration according to time from the operating data based on, for example, a first model, and simulates the relationship between the catalyst temperature and time using the calculated degree of deterioration. As a result, the deadline temperature calculation unit 113b calculates the catalyst temperature (deadline temperature) at the operating deadline. An example of a method for calculating the deadline temperature by the deadline temperature calculation unit 113b will be described in more detail below. Note that in the exemplary description below, when calculating the degree of catalyst deterioration and catalyst temperature for a set of values ​​of a certain number of parameters (for example, the set with Case ID 1 in FIG. 3), if a specific process is repeated for each time, the values ​​of that set are repeatedly used at all times unless otherwise specified. In this case, a simulation is performed in which the same operating state continues during the operating period of the catalytic reaction device 500.

[0097] The deadline temperature calculation unit 113b sets the deterioration degree at the start point (time 0) of the catalytic reaction device 500 to a predetermined value (for example, 1). The deadline temperature calculation unit 113b inputs the values ​​of multiple parameters at time t into a first model and obtains the output value (dΦ / dt) of the first model. The deadline temperature calculation unit 113b obtains the deterioration degree at time t by subtracting the obtained output value from the deterioration degree at time t-1. Thereafter, by repeating the same process, the deadline temperature calculation unit 113b can sequentially calculate the deterioration degree up to the operation deadline.

[0098] FIG. 6 is a graph showing an example of the deterioration level and the operating period. The vertical axis of the graph indicates the magnitude of the deterioration level (remaining activity ratio). The horizontal axis of the graph indicates time (elapsed time). The vertical axis at the intersection of the vertical and horizontal axes indicates a deterioration level of 0. The horizontal axis at the intersection of the vertical and horizontal axes indicates time 0. In the example of FIG. 6, the deterioration level at time 0 is set to 1. Note that the unit of time on the horizontal axis of the graph is not particularly limited, but in the example of FIG. 6, days are used. A star symbol indicates the value of the deterioration level of the catalyst calculated at a certain time t. Note that the deadline temperature calculation unit 113b may, for example, derive a function indicating the correlation between the deterioration level and time by fitting using the calculated value of the deterioration level at time t. In this case, the deadline temperature calculation unit 113b may calculate the deterioration level at the operating deadline from the function obtained by fitting.

[0099] The deadline temperature calculation unit 113b may store in the storage unit 120, as catalyst deterioration prediction data, the correspondence relationship between the time and the deterioration degree calculated from the function obtained by fitting or the operating data.

[0100] The deadline temperature calculation unit 113b calculates the temperature of the catalyst at time t based on the calculated deterioration level at time t and the values ​​of multiple parameters used to calculate the deterioration level. More specifically, the deadline temperature calculation unit 113b calculates the apparent reaction rate constant k at time t from the above equations (4-1) and (4-2) based on the values ​​of multiple parameters at a certain time t. The deadline temperature calculation unit 113b calculates the apparent frequency factor A (A tThe deadline temperature calculation unit 113b calculates the apparent reaction rate constant k and the apparent frequency factor A t Based on this, the temperature T of the catalyst at the operating time t can be calculated from equation (5). Therefore, the deadline temperature calculation unit 113b can calculate the deadline temperature based on the degree of deterioration at a predetermined deadline and the values ​​of multiple parameters used to calculate the degree of deterioration. Note that the deadline temperature calculation unit 113b may derive a function indicating the correlation between the catalyst temperature and time by fitting, for example, using the calculated value of the catalyst temperature at time t. In this case, the deadline temperature calculation unit 113b may calculate the temperature of the catalyst at the operating deadline (deadline temperature) from the function obtained by fitting.

[0101] The deadline temperature calculation unit 113b may store in the storage unit 120, as temperature prediction data, the correspondence relationship between the catalyst temperature and time calculated from the function obtained by fitting or the operating data.

[0102] In the above-described example of the catalyst temperature calculation method by the deadline temperature calculation unit 113b, it is assumed that the operating data and the multiple parameters of the first model do not include the catalyst temperature. If the multiple parameters of the first model include the catalyst temperature, the deadline temperature calculation unit 113b may use a different calculation method. For example, the deadline temperature calculation unit 113b may simultaneously calculate the deterioration level and the catalyst temperature. Specifically, the deadline temperature calculation unit 113b calculates the catalyst temperature (reaction temperature) required for the reaction process at time t based on the deterioration level calculated for the operating time (time t-1) and multiple parameters included in the operating data for the next time t (e.g., the next day). Furthermore, the deadline temperature calculation unit 113b calculates the deterioration level at time t from the first model using the calculated reaction temperature at time t and the values ​​of multiple parameters (excluding the catalyst temperature) of the operating data at time t. Thereafter, the calculation of the reaction temperature and the deterioration level is repeated while increasing time t by a unit time, thereby calculating the deterioration level and reaction temperature for each time. In this case, the deadline temperature calculation unit 113b generates catalyst deterioration prediction data and temperature prediction data simultaneously in parallel.

[0103] FIG. 7 is a graph schematically illustrating an example of the catalyst temperature and operation period. The vertical axis of the graph represents the magnitude of the catalyst temperature. The horizontal axis of the graph represents time (elapsed time). The vertical axis at the intersection of the vertical and horizontal axes represents the catalyst temperature of 0°C. The horizontal axis at the intersection of the vertical and horizontal axes represents time 0. Note that the unit of time on the horizontal axis of the graph is not particularly limited, but in the example of FIG. 7, days are used. In the example of FIG. 7, the allowable temperature of the catalytic reaction device 500 is 395°C, and the operation deadline of the catalytic reaction device 500 is 365 days. In the example of FIG. 7, the deadline temperature calculation unit 113b calculates the deadline temperature to be 370°C based on the operation deadline and the temperature prediction data.

[0104] The data set generating unit 113c generates a data set by associating a set of values ​​of a plurality of parameters included in the operating data with a deadline temperature calculated based on the set. The data set generating unit 113c stores the generated data set in the storage unit 120.

[0105] The data set generating unit 113c may extract the deadline temperature calculated by the deadline temperature calculating unit 113b based on the allowable temperature of the catalytic reaction device 500. In this case, if the calculated deadline temperature is equal to or lower than the allowable temperature of the catalytic reaction device 500, the data set generating unit 113c determines that the deadline temperature is appropriate. If the calculated deadline temperature exceeds the allowable temperature of the catalytic reaction device 500, the data set generating unit 113c determines that the deadline temperature is inappropriate. The data set generating unit 113c may generate a data set by associating the deadline temperature determined to be appropriate with the values ​​of multiple parameters used in calculating the deadline temperature.

[0106] The second model generation unit 114 generates a second model based on the data set. For example, the second model generation unit 114 performs machine learning based on the data set and determines values ​​of temperature contribution parameters included in the second reference model to generate the second model.

[0107] The deadline temperature prediction unit 115 predicts the deadline temperature based on the second model. The deadline temperature prediction unit 115 can predict the deadline temperature according to the operation schedule data by inputting the values ​​of multiple parameters included in the operation schedule data into the second model.

[0108] The output unit 116 outputs the deadline temperature predicted by the deadline temperature prediction unit 115. The output unit 116 generates, for example, a display screen for showing the predicted deadline temperature to the user. The output unit 116 transmits information for displaying the display screen on the user terminal 300 to the user terminal 300 via the communication unit 130. The display screen includes, for example, the deadline temperature and operation schedule data (a set of values ​​of multiple parameters) used to predict the deadline temperature.

[0109] When the deadline temperature prediction unit 115 sequentially predicts deadline temperatures corresponding to each operation schedule data based on a plurality of operation schedule data (a set of values ​​of a plurality of parameters), the output unit 116 may generate a display screen for displaying each deadline temperature and the scheduled operation data corresponding to each deadline temperature together. In this case, the output unit 116 may generate a display screen for displaying sets of each deadline temperature and the scheduled operation data corresponding to each deadline temperature based on the order of magnitude of the deadline temperatures. The output unit 116 may generate a display screen for displaying sets of each deadline temperature and the scheduled operation data corresponding to each deadline temperature based on the order of magnitude of the value of a first parameter included in the operation schedule data.

[0110] <Processing flow> The following describes an example of the flow of processing executed by the information processing device 100. Note that the content and order of the steps described below are merely examples and can be changed as appropriate as long as they do not contradict the content of this disclosure.

[0111] 8 is a flowchart showing an example of the flow of a generation process for generating a first model. This generation process is executed, for example, when the information processing device 100 is started up or in response to a request from the user terminal 300.

[0112] (Step S100) The acquisition unit 111 acquires device data of the catalytic reaction device 500. The acquisition unit 111 acquires a first reference model corresponding to the type of catalyst included in the acquired device data. If a first model compatible with the catalytic reaction device 500 is present in the data management device 210, the acquisition unit 111 acquires the first model. The acquisition unit 111 also acquires threshold data. Finally, the acquisition unit 111 stores the acquired device data, first reference model, first model, and threshold data in the storage unit 120. Then, the process proceeds to step S101.

[0113] (Step S101) The first model generation unit 112 determines whether or not a first model exists in the storage unit 120. If the determination is affirmative, the process proceeds to step S110. If the determination is negative, the process proceeds to step S102.

[0114] (Step S102) If a negative determination is made in step S101, the acquisition unit 111 acquires driving performance data. The acquisition unit 111 stores the acquired driving performance data in the storage unit 120. Then, the process proceeds to step S103.

[0115] (Step S103) The first model generation unit 112 generates a first model based on the acquired driving performance data and the first reference model. Furthermore, if the acquired driving performance data does not include the deterioration level of the catalyst, the first model generation unit 112 calculates the deterioration level based on the acquired driving performance data and generates the first model using the calculated deterioration level. Finally, the first model generation unit 112 stores the generated first model in the storage unit 120. Then, the process proceeds to step S119.

[0116] (Step S110) If the determination in step S101 is affirmative, the acquisition unit 111 determines whether it is time to acquire driving performance data based on the period for acquiring driving performance data. If the determination is affirmative, the process proceeds to step S111. If the determination is negative, the process proceeds to step S119.

[0117] (Step S111) If a positive determination is made in step S110, the acquisition unit 111 acquires driving performance data. The acquisition unit 111 stores the acquired driving performance data in the storage unit 120. Then, the process proceeds to step S112.

[0118] (Step S112) The first model generation unit 112 determines whether the unstable period of the catalyst in the catalytic reaction device 500 has ended based on the acquired operating history data. If the determination is affirmative, the process proceeds to step S113. If the determination is negative, the process proceeds to step S119.

[0119] (Step S113) The first model generation unit 112 updates the first model based on the acquired driving performance data. Furthermore, if the acquired driving performance data does not include the deterioration level of the catalyst, the first model generation unit 112 calculates the deterioration level based on the acquired driving performance data, and updates the first model using the calculated deterioration level. Finally, the first model generation unit 112 stores the updated first model in the storage unit 120. Then, the process proceeds to step S119.

[0120] (Step S119) The processing unit 110 determines whether or not to terminate this process based on the termination condition. If the determination is affirmative, this process terminates. If the determination is negative, the process proceeds to step S101. Here, the termination condition may be, for example, when termination instruction data is received from the user terminal 300, when operation of the catalytic reaction device 500 has ended, or the like. The termination condition may also be other conditions.

[0121] 9 is a flowchart showing an example of the flow of a generation process for generating a second model. This generation process is executed, for example, when a predetermined program is executed in the information processing device 100, or in response to a request from the user terminal 300.

[0122] (Step S120) The processing unit 110 determines whether it is time to generate a second model based on a predetermined condition. If the determination is affirmative, the process proceeds to step S121. If the determination is negative, the process ends. Here, the predetermined condition may be, for example, when a request to generate a second model has been received from the user terminal 300 or the like, when a new first model has been generated or updated, when a second model is pre-set to be generated periodically and the period has arrived, or the like. Note that the predetermined condition may be other conditions.

[0123] (Step S121) If step S120 is judged to be positive, the acquisition unit 111 acquires device data of the catalytic reaction device 500. The acquisition unit 111 also acquires a first model corresponding to the catalytic reaction device 500. The acquisition unit 111 also acquires operating history data of the catalytic reaction device 500. The acquisition unit 111 also acquires threshold data. The acquisition unit 111 also acquires a second reference model. The acquisition unit 111 stores the acquired device data, first model, operating history data, threshold data, and second reference model in the storage unit 120. Then, the processing proceeds to step S122.

[0124] (Step S122) The driving data generation unit 113a generates driving data based on the driving performance data. The driving data generation unit 113a may generate driving data using threshold data in addition to the driving performance data. The driving data generation unit 113a stores the generated driving data in the storage unit 120. Then, the process proceeds to step S123.

[0125] (Step S123) The deadline temperature calculation unit 113b calculates deadline temperatures corresponding to each set of parameter values ​​included in the operating data based on the first model and the operating data. The deadline temperature calculation unit 113b stores the calculated deadline temperatures in the storage unit 120. Then, the process proceeds to step S124.

[0126] (Step S124) The data set generating unit 113c generates a data set by associating the calculated deadline temperature with the values ​​of the multiple parameters used to calculate the deadline temperature. The data set generating unit 113c stores the generated data set in the storage unit 120. Then, the process proceeds to step S125.

[0127] (Step S125) The second model generation unit 114 generates a second model based on the generated dataset and the acquired second reference model. The second model generation unit 114 stores the generated second model in the storage unit 120. If a second model already exists in the storage unit 120, the second model generation unit 114 stores the newly generated second model in the storage unit 120, and then the process ends.

[0128] 10 is a flowchart showing an example of the flow of a prediction process for predicting a deadline temperature. This prediction process is executed, for example, when a predetermined program is executed in the information processing device 100, or in response to a request from the user terminal 300. is executed.

[0129] (Step S130) The processing unit 110 determines whether it is time to predict the deadline temperature based on a predetermined condition. If the determination is affirmative, the process proceeds to step S132. If the determination is negative, the process ends. Here, the predetermined condition may be when a request to predict the deadline temperature has been received from the user terminal 300, when a new second model has been generated or updated, when the deadline temperature is preset to be predicted periodically and the period has arrived, etc. Note that the predetermined condition may be other conditions.

[0130] (Step S132) If the result of step S130 is affirmative, the acquisition unit 111 acquires a second model. The acquisition unit 111 also acquires apparatus data of the catalytic reaction device 500. The acquisition unit 111 also stores the acquired second model and apparatus data in the storage unit 120. Then, the process proceeds to step S134.

[0131] (Step S134) The acquisition unit 111 acquires the operation schedule data. The acquisition unit 111 stores the acquired operation schedule data in the storage unit 120. Then, the process proceeds to step S136.

[0132] (Step S136) The deadline temperature prediction unit 115 predicts the deadline temperature based on the acquired second model and the operation schedule data. The deadline temperature prediction unit 115 stores output data including the predicted deadline temperature in the storage unit 120. Then, the process proceeds to step S138.

[0133] (Step S138) The output unit 116 transmits the output data to the target user terminal 300 via the communication unit 130. Upon receiving the output data, the user terminal 300 displays the expiration temperature included in the output data on the display unit 310. Then, this process ends.

[0134] The order of the steps shown in Figures 8, 9, and 10 above is an example, and the order of the steps may be changed as long as no contradiction occurs in the operations. Also, some of the steps shown in Figures 8, 9, and 10 above may be deleted. Also, steps that perform processing other than the steps shown in Figures 8, 9, and 10 above may be added.

[0135] (Other variations) In the embodiment described above, the operating data generating unit 113a extracts a set of parameter values ​​based on a first parameter (first condition), and then extracts a specific set of parameter values ​​based on a second parameter (second condition). However, this is not limiting. For example, the operating data generating unit 113a may extract a set of parameter values ​​based on a second parameter (second condition), and then extract a specific set of parameter values ​​based on the first parameter (first condition). The same applies to the case where a specific set of parameter values ​​is extracted based on a third parameter (third condition). In other words, when extracting a specific set of parameter values ​​based on multiple conditions, the order in which the multiple conditions are used can be changed as appropriate.

[0136] In the embodiment described above, the operating data generating unit 113a uses a threshold value when extracting a set of specific parameter values ​​based on the second parameter (second condition) or the third parameter (third condition), but this is not limiting. For example, the operating data generating unit 113a may extract a set of parameters including the value of the second parameter as the specific parameter values ​​when the value of the second parameter is not zero (0) and not null, or when the value includes the most frequent value. The same applies when the operating data generating unit 113a extracts a set of specific parameter values ​​based on the third parameter (third condition).

[0137] In the embodiment described above, the operating data generating unit 113a uses the first threshold as the lower limit threshold and the second threshold as the upper limit threshold when extracting a set of specific parameter values ​​based on the first parameter (first condition), but is not limited to this. For example, when extracting a set of specific parameter values ​​based on the first parameter, the operating data generating unit 113a may use only the first threshold as the lower limit or may use only the first threshold as the upper limit. The same applies to the case where a set of specific parameter values ​​is extracted based on the second parameter (second condition) or the third parameter (third condition).

[0138] The operating data generating unit 113a may extract a set of specific parameter values ​​by imposing a plurality of first conditions on the first parameter. For example, the operating data generating unit 113a may extract a set of specific parameter values ​​based on a threshold value and also on the most frequent value of the first parameter. The same applies to the case where a set of specific parameter values ​​is extracted based on a second parameter (second condition) or a third parameter (third condition).

[0139] The operating data generating unit 113a may extract a set of values ​​of a specific plurality of parameters based on the first parameter (first condition), the second parameter (second condition), and the third parameter (third condition).

[0140] The information, parameters, etc. described in this disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or corresponding other information. Equations, etc. using these parameters may differ from those explicitly disclosed in this disclosure.

[0141] In this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0142] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0143] The terms "determining" and "determining" in this disclosure may encompass a wide variety of actions. Each of "determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, searching (e.g., searching in a table, database, or other data structure), ascertaining, and so forth. Also, each of "determining" and "determining" may include resolving, selecting, choosing, establishing, comparing, and so forth, and so forth. That is, each of "determining" and "determining" may include ascertaining, for example, some action.

[0144] In this disclosure, when expressions such as "using / using data as input / based on / according to / in response to" (including similar expressions) are used, unless otherwise specified, this includes cases where the data itself is used, or where data that has been processed in some way (e.g., data with noise added, normalized data, features extracted from data, intermediate representations of data, etc.) is used. Furthermore, when a statement is made that a result is obtained "using data as input / based on / according to / in response to" (including similar expressions), this includes cases where the result is obtained based solely on the data, or where the result is influenced by other data, factors, conditions, and / or states other than the data itself, unless otherwise specified. Furthermore, when a statement is made that "data is output" (including similar expressions), this includes cases where the data itself is used as output, or where data that has been processed in some way (e.g., data with noise added, normalized data, features extracted from data, intermediate representations of various data, etc.) is used as output, unless otherwise specified.

[0145] The present disclosure may be provided as an information processing method including processing steps performed in the information processing device 100. The present disclosure may also be provided as a program executed in the information processing device 100. The program may be provided in a form stored on a storage medium such as an optical disc, or may be provided in a form that allows the program to be downloaded to a computer via a network such as the Internet, installed, and made available.

[0146] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments and modifications described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0147] Several aspects of the present disclosure are described below.

[0148] The first aspect is an information processing device including: a deadline temperature calculation unit that calculates the deadline temperature of the catalyst from operating data including values ​​of multiple parameters based on a first model that indicates the correlation between multiple parameters indicating the operating state of a catalytic reactor that generates a refined oil by passing a feedstock oil through a catalyst and the deterioration level of the catalyst; and a second model generation unit that generates a second model that indicates the correlation between the deadline temperature and the multiple parameters based on the calculated deadline temperature and the values ​​of the multiple parameters used to calculate the deadline temperature. According to the first aspect, the second model is generated using the deadline temperature calculated based on the first model that indicates the correlation between multiple parameters and the deterioration level. Therefore, a second model that can accurately predict the deadline temperature can be generated. Ultimately, by directly or indirectly using the second model, a user can operate the catalytic reactor economically.

[0149] A second aspect is the information processing device according to the first aspect, further comprising a data set generation unit that extracts the calculated deadline temperature based on the allowable temperature of the catalytic reaction device, and the second model generation unit generates the second model based on the extracted deadline temperature and the values ​​of the multiple parameters corresponding to the deadline temperature. According to the second aspect, the second model is generated by selecting a set of the calculated deadline temperature and the values ​​of the multiple parameters corresponding to the deadline temperature based on the allowable temperature of the catalytic reaction device. This improves the prediction accuracy of the deadline temperature of the second model.

[0150] A third aspect is the information processing device according to the first aspect, wherein the plurality of parameters include at least one of a parameter related to the operating conditions of the catalytic reactor, a parameter related to the feedstock oil, and a parameter related to the refined oil. According to the third aspect, a second model is generated using a plurality of parameters including at least one of a parameter related to the hydrogen partial pressure of hydrogen supplied to the catalytic reactor, a parameter related to the feedstock oil, and a parameter related to the refined oil. This improves the prediction accuracy of the expiration temperature of the second model.

[0151] A fourth aspect is the information processing device according to the first aspect, wherein the feedstock oil contains M types of base oils from 1 to M (M is an integer of 2 or more), and the plurality of parameters include a parameter related to the throughput of the catalytic reaction device and a parameter related to the content ratio of Xth (X is any one integer from 1 to M) base oil. According to the fourth aspect, a second model is generated using a plurality of parameters including a parameter related to the base oil contained in the feedstock oil. This can improve the prediction accuracy of the expiration temperature of the second model.

[0152] A fifth aspect is the information processing device according to the first aspect, further comprising an acquisition unit that acquires operating history data including values ​​of multiple parameters indicating the past operating states of the catalytic reaction device, and an operating data generation unit that generates the operating data based on the acquired operating history data. According to the fifth aspect, the operating data is generated based on operating data including values ​​of multiple parameters indicating the past operating states of the catalytic reaction device. Therefore, the operating data used to generate the second model is generated based on values ​​that have been proven in the operation of the catalytic reaction device. Therefore, the operating environment of the catalytic reaction device can be reflected in the second model, thereby improving the prediction accuracy of the expiration temperature of the second model. Furthermore, the second model can be generated more efficiently.

[0153] A sixth aspect is the information processing device according to the fifth aspect, wherein the plurality of parameters in the operating history data include a first parameter, and the operating data generation unit extracts a set of specific parameter values ​​from the operating history data, the set including the value of the first parameter that satisfies a predetermined first condition, and generates the operating data based on the extracted set. According to the sixth aspect, a set of parameters included in the operating history data is extracted based on a first parameter focused on by a user. This allows for more appropriate generation of operating data, thereby improving the prediction accuracy of the expiration temperature of the second model. Furthermore, this allows for more efficient generation of operating data, thereby allowing for more efficient generation of the second model.

[0154] A seventh aspect is the information processing device according to the sixth aspect, wherein the acquisition unit further acquires a predetermined threshold value for the first parameter, and the operating data generation unit extracts a specific set of values ​​of the plurality of parameters from the operating history data by comparing the value of the first parameter with the threshold value, and generates the operating data based on the extracted set. According to the seventh aspect, a set of parameters included in the operating history data is extracted based on a first parameter focused on by a user. This allows for more appropriate generation of operating data, thereby improving the prediction accuracy of the expiration temperature of the second model. Furthermore, this allows for more efficient generation of operating data, thereby allowing for more efficient generation of the second model.

[0155] An eighth aspect is the information processing device according to the sixth aspect, wherein the operating data generation unit extracts a set of specific parameter values, including the most frequent value of the first parameter, from the operating history data by referring to the value of the first parameter, and generates the operating data based on the extracted set. According to the eighth aspect, a set of parameters included in the operating history data is extracted based on the first parameter focused on by the user. This allows for more appropriate generation of operating data, thereby improving the prediction accuracy of the expiration temperature of the second model. Furthermore, this allows for more efficient generation of operating data, thereby allowing for more efficient generation of the second model.

[0156] A ninth aspect is the information processing device according to the sixth aspect, wherein the plurality of parameters of the operating history data includes a second parameter different from the first parameter, and the operating data generation unit extracts a set of specific parameter values ​​from the operating history data, including a value of the second parameter that satisfies a predetermined second condition, and generates the operating data based on the extracted set. According to the ninth aspect, a set of parameters included in the operating history data is extracted based on a first parameter and a second parameter focused on by a user. This allows for more appropriate generation of operating data, thereby improving the prediction accuracy of the expiration temperature of the second model. Furthermore, this allows for more efficient generation of operating data, thereby allowing for more efficient generation of the second model.

[0157] A tenth aspect is the information processing device according to the ninth aspect, wherein the first parameter is a parameter related to the operating conditions of the catalytic reaction device, and the second parameter is a parameter related to the feedstock. According to the tenth aspect, a set of multiple parameters included in the operating history data is extracted based on parameters related to the operating conditions and parameters related to the feedstock that a user focuses on. The set of multiple parameters included in the operating history data is extracted from different perspectives of the operating conditions and the feedstock. This allows for more appropriate generation of operating data, thereby improving the prediction accuracy of the expiration temperature of the second model. Furthermore, since operating data can be generated more efficiently, the second model can be generated more efficiently.

[0158] In an eleventh aspect, the information processing device according to the ninth aspect is configured such that the plurality of parameters in the operating history data include a third parameter different from the first parameter and the second parameter, and the operating data generation unit extracts a set of specific parameter values ​​from the operating history data, including a value of the third parameter that satisfies a predetermined third condition, and generates the operating data based on the extracted set. According to the eleventh aspect, the set of parameters included in the operating history data is extracted based on a third parameter focused on by a user. Therefore, the set of parameters included in the operating history data is extracted based on parameters related to operating conditions, parameters related to the feedstock oil, and parameters related to the product oil other than the parameters focused on as the first parameter and the second parameter. Therefore, the operating data can be generated more appropriately, thereby improving the prediction accuracy of the expiration temperature of the second model. Furthermore, the operating data can be generated more efficiently, thereby enabling the second model to be generated more efficiently.

[0159] In a twelfth aspect, the information processing device according to the fifth aspect is configured such that the acquisition unit further acquires operational data including time-series information regarding the operating state of the catalytic reaction device, and the operational data generation unit compares the acquired operational data with the operational history data to extract from the operational history data a set of specific parameter values ​​that indicate that the catalytic reaction device is operating normally, and generates the operational data based on the extracted set. According to the twelfth aspect, a set of parameters included in the operational history data is extracted based on the operational data. This allows for more appropriate generation of operational data, thereby improving the prediction accuracy of the expiration temperature of the second model. Furthermore, this allows for more efficient generation of operational data, thereby allowing for more efficient generation of the second model.

[0160] In a thirteenth aspect, when the catalytic reaction device is a first catalytic reaction device, the acquisition unit further acquires other-device operating history data including values ​​of multiple parameters indicating the past operating states of a second catalytic reaction device that is different from the first catalytic reaction device but similar to the first catalytic reaction device, and the operating data generation unit generates the operating data further based on the other-device operating history data. According to the thirteenth aspect, the operating data is generated based also on the other-device operating history data of the second catalytic reaction device. Therefore, even if the number of data points in the operating history data of the first catalytic reaction device is limited, a second model capable of accurately predicting the expiration temperature can be generated.

[0161] A fourteenth aspect is the information processing device according to any one of the fifth to thirteenth aspects, further comprising a data set generation unit that extracts the calculated deadline temperature based on the allowable temperature of the catalytic reaction device, and the second model generation unit generates the second model based on the extracted deadline temperature and the values ​​of the plurality of parameters corresponding to the deadline temperature. According to the fourteenth aspect, the second model is generated by selecting a set of the calculated deadline temperature and the values ​​of the plurality of parameters corresponding to the deadline temperature based on the allowable temperature of the catalytic reaction device. This improves the prediction accuracy of the deadline temperature of the second model.

[0162] A fifteenth aspect is the information processing device according to the first aspect, further comprising a first model generation unit that generates the first model and an acquisition unit that acquires operating history data including values ​​of multiple parameters that indicate the past operating states of the catalytic reaction device, wherein the first model generation unit generates the first model based on the operating history data. According to the fifteenth aspect, the first model is generated based on operating history data including values ​​of multiple parameters that indicate the past operating states of the catalytic reaction device. Thus, information specific to the catalytic reaction device can be reflected in the first model. Therefore, the calculation accuracy of the deadline temperature used for learning the second model can be improved. Ultimately, the prediction accuracy of the deadline temperature of the second model can be improved.

[0163] A sixteenth aspect is the information processing device according to the fifteenth aspect, wherein the acquisition unit further acquires new operating history data including values ​​of a plurality of parameters indicating the past operating state of the catalytic reaction device at a time later than the operating history data, the first model generation unit updates the first model based on the acquired new operating history data, the deadline temperature calculation unit recalculates the deadline temperature from the operating data based on the updated first model, and the second model generation unit regenerates the second model using the recalculated deadline temperature and the values ​​of the plurality of parameters corresponding to the deadline temperature. According to the fifteenth aspect, the new operating history data can be further reflected in the first model. Therefore, newer information specific to the catalytic reaction device can be reflected in the first model. Therefore, the calculation accuracy of the deadline temperature used to train the second model can be improved. Ultimately, the prediction accuracy of the deadline temperature of the second model can be improved.

[0164] A seventeenth aspect is the information processing device according to the fifteenth aspect, in which, when a period in which the deterioration level changes drastically is defined as an unstable period, the first model generation unit determines the end of the unstable period based on the acquired operating data, and generates the first model based on the operating data relating to the time after it is determined that the unstable period has ended. According to the seventeenth aspect, the first model is generated based on the operating data after the unstable period has ended. This improves the calculation accuracy of the deadline temperature used in learning the second model. This in turn improves the prediction accuracy of the deadline temperature of the second model.

[0165] In an eighteenth aspect, when the catalytic reaction device is a first catalytic reaction device, the acquisition unit further acquires other-device operating history data including values ​​of multiple parameters indicating the past operating state of a second catalytic reaction device that is different from the first catalytic reaction device but similar to the first catalytic reaction device, and the first model generation unit generates the first model further based on the other-device operating history data. According to the eighteenth aspect, the first model is generated based also on the other-device operating history data of the second catalytic reaction device. Therefore, even if the operating history data of the first catalytic reaction device is limited, the calculation accuracy of the deadline temperature used to train the second model can be improved. Ultimately, the prediction accuracy of the deadline temperature of the second model can be improved.

[0166] A nineteenth aspect is the information processing device according to the first aspect, further comprising an acquisition unit that acquires operation schedule data including values ​​of a plurality of parameters that indicate the planned operating state of the catalytic reaction device, and a deadline temperature prediction unit that predicts the deadline temperature from the acquired operation schedule data based on the second model, wherein the operation schedule data is determined based on business information. According to the nineteenth aspect, the deadline temperature can be predicted using the operation schedule data determined based on the business information. Therefore, a user can search for operating conditions that will allow the catalytic reaction device to be operated more economically based on the predicted deadline temperature and the operation schedule data.

[0167] A twentieth aspect is an information processing method comprising the steps of: calculating a deadline temperature, which is the temperature of the catalyst at a predetermined deadline in the catalytic reactor, from operating data including values ​​of multiple parameters based on a first model that indicates the correlation between the degree of deterioration of the catalyst and multiple parameters that indicate the operating state of the catalytic reactor, in which feedstock oil is passed through a catalyst to obtain a refined oil; and generating a second model that indicates the correlation between the deadline temperature and the multiple parameters based on the calculated deadline temperature and the values ​​of the multiple parameters used to calculate the deadline temperature. According to the twentieth aspect, it is possible to generate a second model that can accurately predict the deadline temperature. Consequently, by directly or indirectly using the second model, a user can operate the catalytic reactor economically. [Explanation of symbols]

[0168] 1. Information Processing Systems 100 Information processing device 110 Processing section 111 Acquisition Department 112 First model generation unit 113a Operation data generation unit 113b Deadline temperature calculation section 113c Dataset Generation Unit 114 Second Model Generation Unit 115 Deadline temperature prediction unit 116 Output section 120 Storage section 130 Communications Department 200 Plant Management Device 210 Data management device 300 User Terminals 310 Display section 320 Input section 400 Network 500 catalytic reactor

Claims

1. a deadline temperature calculation unit that calculates a deadline temperature of the catalyst from operating data including values ​​of a plurality of parameters based on a first model that indicates a correlation between a plurality of parameters that indicate the operating state of a catalytic reaction device in which a feedstock oil is passed through a catalyst to obtain a refined oil and a deterioration degree of the catalyst; a second model generation unit that generates a second model indicating a correlation between the deadline temperature and the plurality of parameters based on the calculated deadline temperature and the values ​​of the plurality of parameters used in calculating the deadline temperature; An information processing device comprising:

2. Further, a data set generation unit extracts the calculated limit temperature based on the allowable temperature of the catalytic reaction device, The second model generation unit generating the second model based on the extracted deadline temperature and the values ​​of the plurality of parameters corresponding to the deadline temperature; The information processing device according to claim 1 .

3. The plurality of parameters are: Parameters relating to the operating conditions of the catalytic reactor; parameters related to the feedstock; and parameters relating to the product oil, The information processing device according to claim 1 .

4. The feedstock is Contains M types of base oils numbered 1 to M (M is an integer of 2 or more), The plurality of parameters are: A parameter related to the throughput of the catalytic reactor; and a parameter relating to the content ratio of the Xth base oil (X is any one integer from 1 to M), The information processing device according to claim 1 .

5. an acquisition unit that acquires operational performance data including values ​​of a plurality of parameters that indicate past operational states of the catalytic reaction device; and a driving data generation unit that generates the driving data based on the acquired driving performance data. The information processing device according to claim 1 .

6. the plurality of parameters of the driving performance data include a first parameter, The driving data generation unit extracting from the driving performance data a set of specific values ​​of the plurality of parameters including a value of the first parameter that satisfies a predetermined first condition; generating the driving data based on the extracted set; The information processing device according to claim 5 .

7. The acquisition unit further obtaining a predetermined threshold value for the first parameter; The driving data generation unit extracting a specific set of values ​​of the plurality of parameters from the driving performance data by comparing the value of the first parameter with the threshold value; generating the driving data based on the extracted set; The information processing device according to claim 6 .

8. The driving data generation unit extracting a set of specific parameter values ​​including a mode value of the first parameter from the operating performance data by referring to the value of the first parameter; generating the driving data based on the extracted set; The information processing device according to claim 6 .

9. the plurality of parameters of the driving performance data include a second parameter different from the first parameter, The driving data generation unit extracting from the driving performance data a set of specific values ​​of the plurality of parameters including a value of the second parameter that satisfies a predetermined second condition; generating the driving data based on the extracted set; The information processing device according to claim 6 .

10. the first parameter is a parameter related to an operating condition of the catalytic reaction device, The second parameter is a parameter related to the feedstock oil. The information processing device according to claim 9 .

11. the plurality of parameters of the driving performance data include a third parameter different from the first parameter and the second parameter, The driving data generation unit extracting from the driving performance data a set of specific values ​​of the plurality of parameters including a value of the third parameter that satisfies a predetermined third condition; generating the driving data based on the extracted set; The information processing device according to claim 9 .

12. The acquisition unit Further acquiring operational data including time-series information regarding the operational state of the catalytic reaction device; The driving data generation unit By comparing the acquired operation data with the operating history data, a set of specific values ​​of the plurality of parameters that are determined to indicate that the catalytic reaction device is operating normally is extracted from the operating history data; generating the driving data based on the extracted set; The information processing device according to claim 5 .

13. When the catalytic reaction device is a first catalytic reaction device, The acquisition unit Further acquiring other device operation history data including values ​​of a plurality of parameters indicating the past operating states of a second catalytic reaction device that is different from the first catalytic reaction device and similar to the first catalytic reaction device; The driving data generation unit generating the operation data further based on the other device operation performance data; The information processing device according to claim 5 .

14. Further, a data set generation unit extracts the calculated limit temperature based on the allowable temperature of the catalytic reaction device, The second model generation unit generating the second model based on the extracted deadline temperature and the values ​​of the plurality of parameters corresponding to the deadline temperature; The information processing device according to any one of claims 5 to 13.

15. a first model generation unit that generates the first model; an acquisition unit that acquires operating history data including values ​​of a plurality of parameters that indicate past operating states of the catalytic reaction device; The first model generation unit generating the first model based on the driving performance data; The information processing device according to claim 1 .

16. The acquisition unit Further acquiring new operating history data including values ​​of a plurality of parameters indicating past operating states of the catalytic reaction device at a time later than the operating history data; The first model generation unit updating the first model based on the acquired new operating performance data; The deadline temperature calculation unit recalculating the deadline temperature from the operating data based on the updated first model; the second model generation unit regenerates the second model using the recalculated deadline temperature and values ​​of the plurality of parameters corresponding to the deadline temperature. The information processing device according to claim 15.

17. When the period in which the deterioration degree changes drastically is defined as an unstable period, The first model generation unit determining the end of the unstable period based on the acquired operating performance data; generating the first model based on the driving performance data relating to a time after it is determined that the unstable period has ended; The information processing device according to claim 15.

18. When the catalytic reaction device is a first catalytic reaction device, The acquisition unit Further acquiring other device operation history data including values ​​of a plurality of parameters indicating the past operating states of a second catalytic reaction device that is different from the first catalytic reaction device and similar to the first catalytic reaction device; The first model generation unit generating the first model further based on the other device operation performance data; The information processing device according to claim 15.

19. an acquisition unit that acquires operation schedule data including values ​​of a plurality of parameters that indicate a scheduled operating state of the catalytic reaction device; a deadline temperature prediction unit that predicts the deadline temperature from the acquired operation schedule data based on the second model, The operation schedule data is determined based on business information. The information processing device according to claim 1 .

20. a step of calculating a time limit temperature, which is the temperature of the catalyst at a predetermined time limit in the catalytic reaction device, from operational data including values ​​of a plurality of parameters based on a first model that indicates a correlation between a plurality of parameters that indicate the operating state of the catalytic reaction device, which generates a refined oil by passing a feedstock oil through a catalyst, and a deterioration degree of the catalyst; generating a second model that indicates a correlation between the deadline temperature and the plurality of parameters based on the calculated deadline temperature and the values ​​of the plurality of parameters used in calculating the deadline temperature; An information processing method comprising:

Images