Information processing system, information processing method, and program

Abstract

To provide an information processing system or the like capable of properly estimating an event which may occur in a pulp manufacturing system.SOLUTION: A first step of cooking wood chips with white liquor, a second step of obtaining green liquor from black liquor produced in the first step, a third step of obtaining clarified green liquor from the green liquor, and a step of adding calcium oxide to the clarified green liquor to obtain white liquor and calcium carbonate; A fourth step of supplying white liquor to the first step and supplying calcium carbonate to the fifth step, and the fifth step of supplying calcium oxide obtained by calcination of calcium carbonate to the fourth step are combined, the parameter information acquisition unit acquires two or more parameters related to any of the first step to the fifth step as the parameter information, the relationship model information acquisition unit acquires relationship model information created in advance and indicating a relationship between an event or an index related to the event and two or more parameters, and the estimation unit estimates the event or the index related to the event based on the acquired parameter information and the relationship model information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing system, an information processing method, and a program. [Background technology]

[0002] Pulp is produced by adding cooking water containing sodium hydroxide (hereinafter also referred to as "caustic soda") to wood chips and cooking them, with white liquor being used as the cooking water. In the cooking process, chips are cooked with alkali (white liquor) to obtain pulp, and cooking chemicals and thermal energy are recovered from the pulp waste liquor (black liquor). In the pulp production process, chemicals are recovered from the cooking process, pulp washing process, black liquor concentration process, black liquor combustion process, green liquor treatment process, white liquor treatment process, slaking reaction process, causticization reaction process, lime burning process, etc., and the recovered chemicals are reused. In this regard, Patent Document 1 discloses a technology that facilitates operational management of green liquor treatment. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-12850 Summary of the Invention [Problem to be solved by the invention]

[0004] However, there is still room for improvement in the efficiency of the pulp manufacturing process. In particular, technology to appropriately manage events that may occur in the process of reusing chemicals such as those mentioned above is desired.

[0005] In view of the above circumstances, the present invention provides an information processing system and the like that can appropriately predict events that may occur in a pulp manufacturing system. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided an information processing system for predicting events that may occur in a pulp production system, the pulp production system including a first step of cooking wood chips with white liquor to obtain pulp, a second step of treating black liquor produced in the first step to obtain green liquor, a third step of treating the green liquor to obtain clarified green liquor, a fourth step of adding calcium oxide to the clarified green liquor to obtain white liquor and calcium carbonate, supplying the white liquor to the first step, and supplying the calcium carbonate to the subsequent fifth step, and a fourth step of calcining the calcium carbonate to obtain calcium oxide, supplying the calcium oxide to the fourth step. and a fifth step of supplying the parameter information to the first step. The information processing system includes a parameter information acquisition unit, a relationship model information acquisition unit, and an estimation unit, wherein the parameter information acquisition unit acquires two or more parameters related to any of the first step to the fifth step as parameter information, the relationship model information acquisition unit acquires relationship model information created in advance that indicates the relationship between an event or an index related to the event and the two or more parameters, and the estimation unit estimates the index related to the event based on the acquired parameter information and relationship model information.

[0007] According to the above aspect, an information processing system or the like is provided that can appropriately predict events that may occur in a pulp production system.

[0008] Furthermore, it may be provided in the following aspects.

[0009] (1) An information processing system for predicting events that may occur in a pulp manufacturing system, the pulp manufacturing system comprising: a first step of cooking wood chips with white liquor to obtain pulp; a second step of treating black liquor produced in the first step to obtain green liquor; a third step of treating the green liquor to obtain clarified green liquor; a fourth step of adding calcium oxide to the clarified green liquor to obtain white liquor and calcium carbonate, supplying the white liquor to the first step, and supplying the calcium carbonate to the subsequent fifth step; and a fourth step of calcining the calcium carbonate to obtain calcium oxide, supplying the calcium oxide to the fourth step. and a fifth step of combining the first step and the fifth step, the information processing system including a parameter information acquisition unit, a relationship model information acquisition unit, and an estimation unit, wherein the parameter information acquisition unit acquires two or more parameters related to any of the first step to the fifth step as parameter information, the relationship model information acquisition unit acquires relationship model information created in advance that indicates a relationship between the event or an index related to the event and the two or more parameters, and the estimation unit estimates the event or the index related to the event based on the acquired parameter information and relationship model information.

[0010] (2) In the information processing system described in (1) above, the parameter information acquisition unit acquires two or more parameters selected from the group consisting of water quality parameters, operational parameters, and result parameters as the parameter information.

[0011] (3) In the information processing system described in (2) above, the parameter information includes, as the water quality parameters, one or more parameters selected from the group consisting of pH, electrical conductivity, oxidation-reduction potential, zeta potential, turbidity, temperature, foam height, biochemical oxygen demand (BOD), chemical oxygen demand (COD), total organic carbon (TOC), inorganic carbon, absorbance, color, appearance, whiteness, transparency, particle size distribution, degree of aggregation, amount of foreign matter, suspended solids (SS), foam area on the water surface, area of ​​dirt in the water, amount of air bubbles, amount of organic acid, amount of active alkali, total amount of titratable alkali, amount of metal or metal ion, non-metal ion content, amount of calcium, amount of total chlorine, amount of free chlorine, amount of dissolved oxygen (DO), cation demand, amount of hydrogen sulfide, degree of sulfidation, amount of hydrogen peroxide, ash concentration, microbial respiration rate, viable cell count, spore count, and ATP of the fluid circulating through the pulp manufacturing system.

[0012] (4) In the information processing system described in (2) or (3) above, the parameter information includes, as the operation parameters, the type of the wood chips, the quality of the wood chips, the pulp production volume, the water consumption unit or water consumption amount in the pulp manufacturing system, the new water consumption unit or new water consumption amount in the pulp manufacturing system, the bleaching chemical consumption unit or bleaching chemical consumption amount, the white liquor addition rate in the first step, the steam consumption unit or steam consumption amount in the pulp manufacturing system, the flow rate of the fluid circulating in the pulp manufacturing system, the water consumption unit or water consumption amount ... the temperature of the fluid to be treated, the amount or unit consumption of cooking steam in the first step, the evaporation factor of the evaporator in the second step, the steam pressure of the evaporator in the second step, the amount of black liquor injected in the second step, the flow rate of diluted black liquor, the amount of dregs extracted from the green liquor, the amount or rate of green liquor flocculant added in the third step, the amount of lime mud extracted in the fourth step, the amount or unit consumption of calcium oxide added in the fourth step, the unit consumption or amount of causticizing chemical used in the fourth step, the temperature of the causticizing tank in the fourth step the temperature of the pulp production system, the amount of hot causticizing water or its consumption unit in the fourth step, the differential pressure of a white liquor filter that filters the white liquor produced in the fourth step, the extraction rate of calcium oxide produced in the fifth step, the amount of calcium oxide produced in the fifth step, the amount of sodium hydroxide added or its consumption unit different from that of white liquor in the first step, the temperature of the cyclone dryer in the fifth step, the amount of sodium sulfate added or its consumption unit to the pulp production system, the type of fuel used in the fifth step, the amount of kiln air in the fifth step, the temperature of the kiln heavy oil in the fifth step, the kiln drive current in the fifth step, the kiln exhaust heat temperature in the fifth step, the moisture content of calcium carbonate supplied to the fifth step, the particle size of calcium carbonate produced in the fourth step, the particle size of calcium carbonate supplied to the fifth step, the weather during operation, the amount of rainfall, the amount of white liquor coagulant used or its addition rate, the amount of water reducing agent used or its consumption unit, the rotation speed of a lime mud filter, the number of days of operation, and the amount of dead load due to inert alkali.

[0013] (5) In the information processing system described in any one of (2) to (4) above, the parameter information acquires a parameter other than the target of estimation as the result parameter, and the result parameter includes one or more parameters selected from the group consisting of the causticization rate in the fourth step, the amount of white liquor produced in the fourth step, the amount of active alkali in the fluid circulating in the pulp manufacturing system, the lime calcination rate in the fifth step, the amount of calcium oxide produced in the fifth step, the pulp yield in the first step, the steam consumption rate or amount of steam used in the pulp manufacturing system, the water consumption rate or amount of water used in the pulp manufacturing system, the bleaching chemical consumption rate or amount of bleaching chemicals used, the causticization chemical consumption rate or amount of causticization chemicals used in the fourth step, the amount of grit produced in the fourth step, the amount of fuel used in the fifth step, the brightness of the pulp obtained in the first step, and the kappa number of the pulp obtained in the first step.

[0014] (6) In the information processing system described in any one of (1) to (5) above, the third step of the pulp manufacturing system is a step of treating the green liquor to obtain dregs and the clarified green liquor, generating weak liquor from the obtained dregs and supplying it to the second step, and supplying the obtained clarified green liquor to the fourth step.

[0015] (7) In the information processing system described in any one of (1) to (6) above, the event or the index related to the event estimated by the estimation unit relates to an event in a predetermined process selected from any one of the first process to the fifth process, and the parameter information acquisition unit acquires parameters in a process other than the predetermined process among the first process to the fifth process.

[0016] (8) In the information processing system described in any one of (1) to (7) above, the event or the indicator related to the event inferred by the inference unit is related to the event in the fourth step or the fifth step.

[0017] (9) In the information processing system described in any one of (1) to (8) above, the relationship model information is a model obtained by regression analysis, time series analysis, decision tree, neural network, Bayesian, clustering, classification, or ensemble learning between a pre-check result corresponding to the event or an index related to the pre-check result and the two or more parameters.

[0018] (10) An information processing method executed by an information processing system, the method comprising a step of executing processing of each part of the information processing system described in any one of (1) to (9) above.

[0019] (11) A program for causing a computer to execute the processing of each part of the information processing system described in any one of (1) to (9) above. Of course, this is not the case. [Brief explanation of the drawings]

[0020] [Figure 1] 1 is a diagram showing the overall configuration of an information processing system 1. FIG. [Figure 2] FIG. 1 is a schematic diagram showing an example of the overall configuration of a pulp manufacturing system PM. [Figure 3] FIG. 2 is a diagram illustrating a hardware configuration of an information processing device 2. [Figure 4] FIG. 2 is a diagram showing the hardware configuration of a user terminal 3. [Figure 5] FIG. 2 is a functional block diagram showing functions of the information processing device 2. [Figure 6] 1 is an activity diagram showing the flow of information processing using the information processing device 2 and the like. [Figure 7] FIG. 10 is a diagram showing an example of a guess result presented to a user. [Figure 8] FIG. 10 is a diagram showing the results of a simulation when a change to parameter 1 is input. [Figure 9] FIG. 10 is a diagram showing the results of a simulation when a change to the expected outcome index is input. [Figure 10] FIG. 10 is an explanatory diagram showing an example of a method for calculating an influence degree using an index X as an index (expected result). [Figure 11] 10 is a graph schematically showing the degree of influence of each parameter on an event. [Figure 12] 1 is a schematic diagram showing the transition of the actual measured value (broken line) of parameter 1 and the degree of influence of parameter 1 on an event. [Figure 13] 1 is a graph showing the results of Example 2. [Figure 14] 1 is a graph showing the results of Example 3. DETAILED DESCRIPTION OF THE INVENTION

[0021] Hereinafter, embodiments of the present invention will be described. Note that various features shown in the following embodiments can be combined with each other.

[0022] That is, the information processing system of this embodiment is as follows. An information processing system for predicting events that may occur in a pulp manufacturing system, comprising: The pulp making system comprises: A first step of cooking wood chips with white liquor to obtain pulp; A second step of treating the black liquor produced in the first step to obtain green liquor; a third step of treating the green liquor to obtain a clarified green liquor; a fourth step in which calcium oxide is added to the clarified green liquor to obtain white liquor and calcium carbonate, the obtained white liquor is supplied to the first step, and the obtained calcium carbonate is supplied to the subsequent fifth step; a fifth step of calcining the calcium carbonate to obtain calcium oxide, and supplying the obtained calcium oxide to the fourth step; and The system includes a parameter information acquisition unit, a relationship model information acquisition unit, and an estimation unit, the parameter information acquisition unit acquires, as parameter information, two or more parameters related to any one of the first step to the fifth step; the relationship model information acquisition unit acquires relationship model information that is created in advance and indicates a relationship between the event or an index related to the event and the two or more parameters; The estimation unit estimates the event or an index related to the event based on the acquired parameter information and relationship model information.

[0023] Incidentally, the program for realizing the software appearing in one embodiment may be provided as a non-transitory computer-readable medium, or may be provided so that it can be downloaded from an external server, or may be provided so that the program is started on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0024] Furthermore, various information processing according to an embodiment may realize input and output corresponding to the input. Here, the form of information referenced in such information processing (hereinafter referred to as reference information) is not limited as long as an output is obtained as a result of the input. The reference information may be, for example, rule-based information such as a database, a lookup table, or a predetermined function (including a decision formula such as a regression formula constructed using a statistical method), a trained model that has previously trained the correlation between input and output, or a large-scale language model that can output a desired result by inputting a prompt.

[0025] In one embodiment, a "unit" may include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In one embodiment, various information is handled, and this information is represented, for example, by physical values ​​of signal values ​​representing voltage and current, high and low signal values ​​as a binary bit set consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculations can be performed on a circuit in the broad sense.

[0026] Furthermore, a circuit in the broad sense is a circuit realized by at least an appropriate combination of a circuit, circuitry, processor, memory, etc. The processor may be a general-purpose processor or a dedicated circuit. That is, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0027] 1. Hardware Configuration In this section, the hardware configuration of the information processing system 1 according to this embodiment will be described.

[0028] The information processing system 1 of this embodiment is a system used to predict events that may occur in a pulp production system. Here, the information processing system 1 of this embodiment is equipped with an information processing device 2 and a user terminal 3, which are connected via a communication line. Note that the communication line here includes the Internet, wireless, etc., and mediates the exchange of data between devices connected to the line. Furthermore, in the information processing system 1 of this embodiment, the information processing device 2 is configured to be able to measure various parameters related to the pulp manufacturing system PM. In a typical aspect, the pulp manufacturing system PM is equipped with various measuring devices, and the parameters measured by these measuring devices are configured to be able to be transmitted to the information processing device 2.

[0029] In this specification, a system exemplified as information processing system 1 is one that is made up of one or more devices or components. Therefore, even an information processing device 2 alone is an example of a system, and a system that also includes a user terminal 3 and a pulp manufacturing PM may also be called a system. Below, we will continue to explain each component that can make up information processing system 1.

[0030] [Pulp manufacturing PM] First, a manufacturing system (pulp manufacturing system PM) to which the information processing system 1 of this embodiment is applied will be described. FIG. 2 is a schematic diagram showing an example of the overall configuration of the pulp manufacturing system PM. Note that the various components shown in FIG. 2 are merely an example of a pulp manufacturing system PM to which the information processing system 1 of this embodiment can be applied. That is, in a pulp manufacturing system to which the present invention can be applied, various elements shown in FIG. 2 may be modified within the scope of the present invention. That is, in a pulp manufacturing system to which the present invention can be applied, some elements may be added or some elements may be deleted from the various elements shown in FIG. 2. For example, although not shown, a tank for storing a product may be provided between each element shown in FIG. 2.

[0031] As shown in FIG. 2, the pulp manufacturing system PM in this embodiment includes a first process Pr1, a second process Pr2, a third process Pr3, a fourth process Pr4, and a fifth process Pr5. Here, the first process Pr1 is a process of cooking wood chips with white liquor to obtain pulp. The second process Pr2 is a process of treating the black liquor produced in the first process Pr1 to obtain green liquor. The third process Pr3 is a process of treating the green liquor to obtain clarified green liquor. The fourth process Pr4 is a process of adding calcium oxide to the clarified green liquor to obtain white liquor and calcium carbonate, supplying the resulting white liquor to the first process Pr1, and supplying the resulting calcium carbonate to the fifth process Pr5. The fifth process Pr5 is a process of calcining calcium carbonate to obtain calcium oxide, and supplying the resulting calcium oxide to the fourth process Pr4. Specific aspects of each process are described below. Note that within and between each process, materials involved in pulp manufacturing are transported as fluids or powders. When a material is transported as a fluid, it is typically transported by a pump or the like, but the details of this are omitted in the example of FIG.

[0032] (1st process Pr1) The first process Pr1 is a process in which wood chips are digested with white liquor to obtain pulp. This first process Pr1 may also be referred to as a "digestion system." In this embodiment, the first process Pr1 is equipped with a digester 511. As shown in FIG. 2, wood chips and white liquor are fed into this digester 511 to produce pulp.

[0033] The wood chips may be appropriately selected in terms of species and size (particle size) depending on the pulp to be produced. The white liquor contains sodium hydroxide (caustic soda) and is supplied from the fifth step Pr5, which will be described later. When cooking in the first step Pr1, sodium hydroxide may be supplied separately from outside the pulp production system PM in addition to the white liquor supplied from the fifth step Pr5.

[0034] Although not shown in Fig. 2, the first process Pr1 may also include a screening process for screening the pulp obtained by cooking, a washing process for washing the pulp, a bleaching process for bleaching the pulp, etc. In a typical embodiment, a cyclone cleaner for washing the pulp may be provided downstream of the digester 511 of the first process Pr1. The pulp obtained in the first process Pr1 is subjected to a papermaking process or the like to produce paper.

[0035] The waste liquid generated in the first step Pr1 is also called "black liquor," and in this pulp manufacturing system PM, it is supplied to the second step Pr2 described below for sodium hydroxide recovery.

[0036] (2nd process Pr2) The second process Pr2 is a process for obtaining green liquor by processing the black liquor produced in the first process Pr1. Such a second process Pr2 may be referred to as a "black liquor processing system." In this embodiment, the second process Pr2 includes an evaporator 521, a boiler 522, and a dissolving tank 523.

[0037] The evaporator 521 is a device that concentrates the black liquor produced in the first process Pr1. The black liquor concentrated by the evaporator 521 is transferred to a boiler 522 (recovery boiler) and combusted therein. This melts the inorganic sodium salts contained in the black liquor, which is then discharged as smelt from the bottom of the boiler 522. Note that black liquor before concentration is sometimes referred to as "weak black liquor." The discharged smelt is transferred to a dissolving tank 523 and dissolved in water or the like. By dissolving the smelt in this manner, green liquor rich in sodium hydroxide and sodium carbonate is produced. Note that in a typical embodiment, weak liquor produced in the third process Pr3 or the fourth process Pr4 described below may also be introduced into the dissolving tank 523. Note that the green liquor obtained in the second process Pr2 may also be referred to as "crude green liquor."

[0038] A heat recovery system for recovering thermal energy may be provided in the boiler 522. As such a heat recovery system, a conventionally known system may be used (for example, see Japanese Patent Application Laid-Open No. 6-212586).

[0039] (3rd process Pr3) The third process Pr3 is a process for obtaining clarified green liquor by treating the green liquor. Such a third process Pr3 may also be referred to as a "green liquor treatment system." In this embodiment, the third process Pr3 includes a green liquor clarification device 531, a clarified green liquor tank 532, and a dregs treatment unit 533.

[0040] A conventionally known device can be used for the green liquor clarification device 531, and a gravity settling type device, a forced filtration type device, etc. A device also called a green liquor clarifier can also be applied to the green liquor clarification device 531. As the green liquor clarifier, a multi-stage clarifier, a unit clarifier, a storage tank combined type clarifier, a sedimentation concentration type clarifier, etc. can be selected.

[0041] In the third step Pr3, a green liquor treatment agent (green liquor flocculant) is added to the green liquor in the green liquor clarification device 531 or upstream thereof, and solid-liquid separation is performed in the green liquor clarification device 531 to remove impurities, such as undissolved components, from the crude green liquor (clarification process). This clarification process results in a clarified green liquor from which impurities have been removed. In this embodiment, the resulting clarified green liquor is transferred to the clarified green liquor tank 532. The green liquor treatment agent (green liquor flocculant) used in the third step Pr3 may be appropriately selected from known materials. For example, the green liquor treatment agent (green liquor flocculant) described in Japanese Patent No. 6901032 may be used.

[0042] Meanwhile, in the above-mentioned clarification treatment, slurry-like sludge (green liquor mud) containing impurities is generated and accumulated in the green liquor clarification device 531. For this reason, the sludge accumulated in the green liquor clarification device 531 is withdrawn at a certain rate (at regular intervals or when a certain amount is reached). This sludge may contain insoluble impurities (dregs) such as unburned carbon, calcium carbonate, aluminum hydroxide, iron oxide, and silicon dioxide, which are derived from smelt generated by burning black liquor.

[0043] The third process Pr3 shown in FIG. 2 is equipped with a dregs treatment unit 533 and is configured to treat the sludge (dregs) extracted from the green liquor clarification apparatus 531. The dregs treatment unit 533 is configured to treat the dregs to obtain a weak liquor that dissolves the smelt. That is, the illustrated third process Pr3 treats green liquor to obtain dregs and clarified green liquor. The resulting clarified green liquor is supplied to the fourth process Pr4, while a weak liquor is produced from the resulting dregs. The third process Pr3 then supplies the resulting weak liquor to the second process Pr2. The dregs can be treated by appropriately combining known techniques. For example, a combination of a mechanism for adding warm water to the dregs to disperse them (a dregs mixer), a mechanism for washing the dregs (a dregs washer), and a mechanism for filtering the dregs (a dregs filter) can be used. The weak liquid obtained by filtering out the dregs is transferred to the dissolution tank 523 of the second process Pr2, thereby enabling efficient dissolution of the smelt. Furthermore, although not limited thereto, the dregs washer here can use the filtrate obtained in the lime mud filter 551 described below as part of the washing liquid.

[0044] (4th process Pr4) The fourth process Pr4 is a process in which calcium oxide is added to clarified green liquor to obtain white liquor and calcium carbonate, the obtained white liquor is supplied to the first process Pr1, and the obtained calcium carbonate is supplied to the fifth process Pr5. Note that this fourth process Pr4 may also be referred to as a "slaking / causticizing system." In this embodiment, the fourth process Pr4 includes a slaker 541, multiple causticizing reaction tanks 542, a white liquor clarifier 543, a white liquor tank 544, and a lime mud washer 545.

[0045] The clarified green liquor obtained in the third step Pr3 is mixed with calcium oxide in a slaker 541. As a result, the calcium oxide is slaked with water to produce calcium hydroxide (slaked reaction step). Thereafter, in a causticizing reaction tank 542, the sodium carbonate in the clarified green liquor reacts with the calcium hydroxide to produce sodium hydroxide (caustic soda) and calcium carbonate (causticizing reaction step).

[0046] The reaction liquor obtained in the causticizing reaction tank 542 is transferred to a white liquor clarifier 543. In this white liquor clarifier 543, insoluble calcium carbonate is precipitated and separated, and the supernatant liquid is transferred as white liquor to a white liquor tank 544. The white liquor transferred to this white liquor tank 544 is eventually supplied to the first step Pr1 and used for cooking wood pulp. Note that a white liquor filter for removing insoluble matter from the white liquor may be provided at least upstream or downstream of this white liquor tank 544. This can improve the degree of purification of the white liquor supplied to the first step Pr1.

[0047] On the other hand, the separated calcium carbonate is transferred to a lime mud washer 545, where it is washed and then subjected to the fifth step Pr5. The washing conditions here can be set as appropriate. As an example, the filtrate obtained in a lime mud filter 551, which will be described later, can be used as the washing liquid. In addition, in this lime mud washer 545, the calcium carbonate that has settled after washing is recovered and transferred to the lime mud filter 551, and the supernatant liquid can be recovered as a weak liquid. This weak liquid can be transferred to a dissolving tank 523 in the second step Pr2 and used to dissolve the smelt.

[0048] (5th process Pr5) The fifth process Pr5 is a process in which calcium carbonate is calcined to obtain calcium oxide, and the obtained calcium oxide is supplied to the fourth process Pr4. Note that such a fifth process Pr5 may also be referred to as a "calcination system." In this embodiment, the fifth process Pr5 includes a lime mud filter 551 and a kiln 552.

[0049] The calcium carbonate produced in the fourth step Pr4 is transferred to a kiln 552 after a certain amount of moisture is removed in a lime mud filter 551. The calcium carbonate transferred to the kiln 552 is roasted and converted into calcium oxide. The calcium oxide thus converted is then fed into a slaker 541 in the fourth step Pr4.

[0050] As described above, the water (filtrate) removed by the lime mud filter 551 can be transferred as a weak liquid to the dissolution tank 523 of the second process Pr2. In addition, an element for further removing moisture from the calcium carbonate may be provided between the lime mud filter 551 and the kiln 552. As an example, a cyclone dryer for drying the calcium carbonate may be provided between the lime mud filter 551 and the kiln 552.

[0051] Each process may be provided with a measuring device capable of measuring various parameters in the pulp production system PM. As will be described later, in an exemplary aspect of this embodiment, a predetermined calculation process can be performed using two or more parameters selected from the group consisting of water quality parameters, operation parameters, and result parameters. The measuring device acquires the parameters that form the basis of this calculation.

[0052] The measuring device may be appropriately selected depending on the parameters to be measured. In a typical embodiment, various sensors can be selected as the measuring device. Examples of measuring devices that can be used include a pH meter, an electrical conductivity meter, an oxidation-reduction potential meter, a turbidity meter, a thermometer, a level meter for measuring bubble height, a COD meter, a UV meter, a particle size distribution meter, an aggregation sensor, a digital camera (or a digital video camera), an internal bubble sensor, an absorptiometer, a freeness meter, a dissolved oxygen meter, a zeta potential meter, a residual chlorine meter, a hydrogen sulfide meter, a retention / freeness meter, a color sensor, a hydrogen peroxide meter, and a five-sense sensor. The five-sense sensor here may include an image sensor, a light intensity sensor, an acoustic sensor, an ultrasonic sensor, a gas component sensor, an odor sensor, a liquid component sensor, a tactile sensor, a pressure sensor, a temperature sensor, a humidity sensor, a displacement sensor, and the like.

[0053] In addition, the operating parameters etc. that are directly input for controlling the equipment may be used as they are, and such data may be transmitted and received from the equipment via communication. In addition, such parameters may be recorded outside the equipment for the operator of the equipment to keep them for record purposes.

[0054] [Information processing device 2] 3 is a diagram showing the hardware configuration of the information processing device 2. The information processing device 2 has a communication unit 21, a storage unit 22, and a control unit 23, and is configured by electrically connecting these units via a communication bus 20. Each unit provided in the information processing device 2 will be described below.

[0055] (Communications Department 21) The communication unit 21 is configured to be able to transmit various electrical signals from the information processing device 2 to external components. The communication unit 21 is also configured to be able to receive various electrical signals from the external components to the information processing device 2. Note that the communication unit 21 may have a network communication function, thereby enabling communication of various information between the information processing device 2 and external devices via a communication line.

[0056] (Storage unit 22) The memory unit 22 stores various pieces of information defined above. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs and the like related to the information processing device 2 executed by the control unit 23, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the program operations. The memory unit 22 stores various programs, variables, etc. related to the information processing device 2 executed by the control unit 23.

[0057] (Control unit 23) The control unit 23 is, for example, a central processing unit (CPU) not shown. The control unit 23 realizes various functions related to the information processing device 2 by reading out predetermined programs stored in the storage unit 22. In other words, information processing by software stored in the storage unit 22 is specifically realized by the control unit 23, which is an example of hardware, and can be executed as each functional unit included in the control unit 23. These will be described in more detail in the next section. Note that the control unit 23 is not limited to being single, and multiple control units 23 may be provided for each function. A combination of these may also be used.

[0058] [User terminal 3] FIG. 4 is a diagram showing the hardware configuration of the user terminal 3. The user terminal 3 is typically a terminal used by a person who performs operations related to pulp manufacturing PM. In this specification, a person who performs such operations may be simply referred to as a "user." The user terminal 3 has a communication unit 31, a storage unit 32, a control unit 33, a display unit 34, and an input unit 35, and these components are electrically connected within the user terminal 3 via a communication bus 30. Descriptions of the communication unit 31, the storage unit 32, and the control unit 33 will be omitted as they are substantially the same as the communication unit 21, the storage unit 22, and the control unit 23 in the information processing device 2 described above.

[0059] (Display section 34) The display unit 34 may be, for example, included in the housing of the user terminal 3 or may be externally attached. The display unit 34 displays a graphical user interface (GUI) screen that can be operated by the user. This is preferably implemented by selectively using display devices such as a CRT display, a liquid crystal display, an organic EL display, and a plasma display depending on the type of the user terminal 3.

[0060] (Input unit 35) The input unit 35 may be included in the housing of the user terminal 3, or may be externally attached. For example, the input unit 35 may be implemented as a touch panel integrated with the display unit 34. A touch panel allows the user to input tapping, swiping, and the like. Of course, a switch button, a mouse, a QWERTY keyboard, or the like may be used instead of a touch panel. That is, the input unit 35 accepts an operation input made by the user. The input is transferred as a command signal to the control unit 33 via the communication bus 30, and the control unit 33 can execute predetermined control or calculation as necessary.

[0061] 2. Functional configuration In this section, the functional configuration of this embodiment will be described. Fig. 5 is a functional block diagram showing the functions of the information processing device 2. As described above, information processing by software (stored in the storage unit 22) is specifically realized by hardware (control unit 23), and can be executed as each functional unit included in the control unit 23.

[0062] Specifically, the information processing device 2 (control unit 23) may include, as its functional units, a parameter information acquisition unit 231, a relationship model information acquisition unit 232, an estimation unit 233, a simulation unit 234, a relationship model information creation unit 235, a dataset identification unit 236, an impact level identification unit 237, a countermeasure presentation unit 238, and a memory management unit 239. Note that these functional units may be increased, omitted, or integrated as appropriate depending on the application to which the information processing device 2 is applied, etc.

[0063] (Parameter information acquisition unit 231) The parameter information acquisition unit 231 is configured to be able to execute a parameter information acquisition step. In the parameter information acquisition step, the parameter information acquisition unit 231 acquires two or more parameters related to any of the first to fifth steps as parameter information. Note that the parameter information here may be various parameters in the pulp manufacturing system PM, but typically the parameter information acquisition unit 231 acquires two or more parameters selected from the group consisting of water quality parameters, operation parameters, and result parameters as parameter information. Note that, upon this acquisition, the parameter information acquisition unit 231 is configured, for example, to acquire various information via the communication unit 21 from a measurement device capable of measuring at least some of the parameters.

[0064] (Relationship model information acquisition unit 232) The relationship model information acquisition unit 232 is configured to be able to execute a relationship model information acquisition step. In the relationship model information acquisition step, the relationship model information acquisition unit 232 acquires relationship model information that indicates the relationship between an event or an index related to an event, and two or more parameters, which has been created in advance. Note that the "event" here may also be referred to as an "expected result," etc., since it is an object of estimation in the pulp manufacturing PM. Details of this model will be explained later.

[0065] (Guessing part 233) The estimation unit 233 is configured to be able to execute an estimation process. In the estimation process, the estimation unit 233 estimates an event or an index related to the event based on the acquired parameter information and relationship model information. The index estimated by the estimation unit 233 may also be referred to as a predicted result or a related index. The content estimated by the estimation unit 233 may be presented to the user as an estimation result. Here, the estimation result may be associated with each parameter included in the parameter information and presented to the user. The presented object (estimation result) here is typically configured to be recognizable by the user, etc. That is, the estimation unit 233 may create display information and control it so that it is visible to the user, etc. Such display information is typically displayed on the display unit 34 of the user terminal 3. The display information may be visual information itself, such as a screen, image, icon, text, etc., generated in a manner visible to the user, or may be rendering information for displaying visual information, such as a screen, image, icon, text, etc., on various devices or terminals. Details of information processing related to estimation will be described later.

[0066] (Simulation Section 234) The simulation unit 234 is configured to be able to execute a simulation step. In the simulation step, the simulation unit 234 receives from the user a change to at least one of the inference results and parameters presented by the estimation unit 233, and estimates fluctuations of the inference results and parameters for which no change was accepted from the user, based on the content of the accepted change and the relationship model information. Details of the information processing related to this simulation will be explained later.

[0067] (Relationship model information creation unit 235) The relationship model information creation unit 235 is configured to be able to execute a relationship model information creation step. In the relationship model information creation step, the relationship model information creation unit 235 creates or updates relationship model information used in the above-mentioned estimation step, etc.

[0068] (Dataset identification unit 236) The dataset specifying unit 236 is configured to be able to execute a dataset specifying step. In the dataset specifying step, the dataset specifying unit 236 specifies a dataset in which an index related to an event is associated with two or more parameters. This dataset may be any of various datasets in which the above-described index is associated with the above-described two or more parameters. However, typically, the dataset specified by the dataset specifying unit 236 specifies an index (expected result or related index) estimated by the estimation unit 233 and two or more parameters acquired by the parameter information acquisition unit 231. In other words, the dataset specifying unit 236 specifies an index (expected result or related index) estimated by the estimation unit 233 and two or more parameters associated with the index, acquired by the parameter information acquisition unit 231. The specified dataset can be used in the impact specification unit 237.

[0069] (Influence Identification Department 237) The influence identification unit 237 is configured to be able to execute an influence identification step. In the influence identification step, the influence identification unit 237 identifies the influence of each parameter associated in the dataset on an event by comparing the relationship model information with the dataset. Note that the influence refers to the influence of each parameter included in the dataset on an event. For example, when an event (e.g., a problem in a manufacturing process) occurs, if the influence of a certain parameter in the dataset is relatively high, it can be determined that the parameter is the main cause of the event (the aforementioned problem). Note that the influence identification unit 237 calculates (estimates or predicts) the influence of each parameter associated in the dataset by a predetermined calculation process. From this perspective, the influence identification unit 237 may also be referred to as an "influence estimation unit" or an "influence estimation unit."

[0070] (Countermeasure presentation unit 238) The countermeasure presentation unit 238 is configured to be able to execute a countermeasure presentation step. In the countermeasure presentation step, the countermeasure presentation unit 238 presents countermeasure information related to the corresponding parameter according to the impact level identified by the impact level identification unit 237. The impact level identification unit 237 identifies the impact level, allowing the user to understand the main factors causing the event, and the countermeasure presentation unit 238 presents the countermeasures to the user, further improving the usability of the system. The countermeasure information is presented, for example, by being output to the user terminal 3. The countermeasure information may be visual information itself generated in a manner that is visible to the user, such as characters, numerical values, diagrams, photos, videos, screens, images, icons, text, etc., or may be rendering information for displaying the visual information on various devices or terminals, for example.

[0071] (Memory Management Department 239) The memory management unit 239 is configured to be able to execute a memory management process. In the memory management process, the memory management unit 239 is configured to manage various pieces of information to be stored that are related to the information processing system 1 of this embodiment. Typically, the memory management unit 239 is configured to store information handled by the information processing device 2 in a memory area. This memory area is exemplified by the memory unit 22 of the information processing device 2 or the memory units of various devices and terminals, but this memory area does not necessarily have to be within the information processing system 1, and the memory management unit 239 can also manage various pieces of information to be stored in an external storage device or the like.

[0072] 3. Details of data processing In Section 3, an information processing method executed by the information processing device 2 etc. will be described with reference to an activity diagram etc. Fig. 6 is an activity diagram showing the flow of information processing using the information processing device 2 etc.

[0073] 6, in this embodiment, first, the parameter information acquisition unit 231 of the information processing device 2 acquires parameter information (activity A101). As described above, in a typical aspect, the parameter information acquisition unit 231 acquires, as parameter information, two or more parameters selected from the group consisting of water quality parameters, operation parameters, and result parameters.

[0074] That is, the parameter information is related to pulp manufacturing system PM and may include two or more parameters selected from the group consisting of water quality parameters, operational parameters, and result parameters. Note that if the process related to the water quality parameters, operational parameters, or result parameters is divided by tanks, etc., it is sufficient to use the water quality parameters, operational parameters, or result parameters for part of the process, or the water quality parameters, operational parameters, or result parameters for the entire process.

[0075] The water quality parameters are not particularly limited as long as they relate to the fluids circulating through the pulp manufacturing system PM. For example, in the aforementioned pulp manufacturing system PM, fluids such as white liquor, black liquor, green liquor, and weak liquor, as well as lime mud, circulate within the process, and these fluids usually contain water. In other words, the water quality parameters are parameters related to such fluids, and are not limited to liquid fluids, but may be parameters related to slurry fluids. Furthermore, the operational parameters are not particularly limited as long as they relate to the operating conditions related to the pulp manufacturing system PM, equipment related to the pulp manufacturing system PM, or raw materials added to the pulp manufacturing system PM. Furthermore, the result parameters are parameters that arise as a result of the operation of the pulp manufacturing system PM, but are not parameters that are subject to estimation.

[0076] Below, specific examples of water quality parameters, operation parameters, and result parameters in the pulp manufacturing system PM will be explained.

[0077] That is, the parameter information may include, as water quality parameters, one or more parameters selected from the group consisting of pH, electrical conductivity, oxidation-reduction potential, zeta potential, turbidity, temperature, foam height, biochemical oxygen demand (BOD), chemical oxygen demand (COD), total organic carbon (TOC), inorganic carbon, absorbance, color, appearance, whiteness, transparency, particle size distribution, degree of aggregation, amount of foreign matter, suspended solids (SS), foam area on the water surface, area of ​​dirt in the water, amount of air bubbles, amount of organic acid, amount of active alkali, total amount of titratable alkali, amount of metal or metal ion, non-metal ion content, amount of calcium, amount of total chlorine, amount of free chlorine, amount of dissolved oxygen (DO), cation demand, amount of hydrogen sulfide, sulfidity, amount of hydrogen peroxide, ash concentration, microbial respiration rate, viable cell count, spore count, and ATP.

[0078] Of the above water quality parameters, "appearance" may be obtained from an RGB color sensor or camera images. "Active alkali content" and "total titratable alkali content" may indicate the alkali content evaluated as sodium content, the alkali content evaluated as calcium content, or the total alkali content. Furthermore, the metal in the "metal or metal ion content" can include heavy metals such as iron (Fe), lead (Pb), gold (Au), platinum (Pt), silver (Ag), copper (Cu), chromium (Cr), cadmium (Cd), mercury (Hg), zinc (Zn), arsenic (As), manganese (Mn), cobalt (Co), nickel (Ni), molybdenum (Mo), tungsten (W), tin (Sn), bismuth (Bi), uranium (U), and plutonium (Pu); alkali metals such as sodium (Na) and potassium (K); alkaline earth metals such as calcium (Ca) and barium (Ba); and base metals such as magnesium (Mg) and aluminum (Al). The "metal or metal ion content" may refer to the content of a specific (one) metal or metal ion, or the content of multiple metals. Furthermore, "non-metal ions" can include ions containing heteroatoms such as silicon (Si), phosphorus (P), sulfur (S), and nitrogen (N) as constituent components, as well as halogen ions such as chlorine (Cl) and bromine (Br).

[0079] The parameter information includes, as operation parameters, the type of wood chips, the quality of wood chips, the amount of pulp produced, the water consumption unit or amount of water used in the pulp manufacturing system, the new water consumption unit or amount of new water used in the pulp manufacturing system, the bleaching chemical consumption unit or amount of bleaching chemicals used, the white liquor addition rate in the first process, the steam consumption unit or amount of steam used in the pulp manufacturing system, the flow rate of fluid circulating in the pulp manufacturing system, the temperature of fluid circulating in the pulp manufacturing system, the amount of cooking steam or consumption unit in the first process, the evaporation factor of the evaporator in the second process, the steam pressure of the evaporator in the second process, the amount of black liquor injection in the second process, the flow rate of diluted black liquor, the amount of dregs extracted from green liquor, the amount of green liquor flocculant added or addition rate in the third process, the amount of lime mud extracted in the fourth process, the amount of calcium oxide input or consumption unit in the fourth process, the amount of causticizing chemicals used or consumption unit in the fourth process, the causticizing tank temperature in the fourth process, and the amount of hot causticizing water in the fourth process. the amount or unit consumption of sodium hydroxide different from that of the white liquor in the first step, the differential pressure of a white liquor filter that filters the white liquor produced in the fourth step, the cutting speed of calcium oxide produced in the fifth step, the amount of calcium oxide produced in the fifth step, the amount or unit consumption of sodium hydroxide fed to the pulp production system, the temperature of the cyclone dryer in the fifth step, the amount or unit consumption of Glauber's salt fed to the pulp production system, the type of fuel used in the fifth step, the amount of kiln air in the fifth step, the temperature of the kiln heavy oil in the fifth step, the kiln drive current in the fifth step, the kiln exhaust heat temperature in the fifth step, the moisture content of calcium carbonate fed to the fifth step, the particle size of calcium carbonate produced in the fourth step, the particle size of calcium carbonate fed to the fifth step, the weather during operation, the amount of rainfall, the amount or addition rate of white liquor coagulant used, the amount or unit consumption of water-reducing agent used, the rotation speed of a lime mud filter, the number of days of operation, and the dead load amount due to an inert alkali.

[0080] The above-mentioned "bleaching chemicals" include caustic soda, chlorine dioxide, oxygen, and hydrogen peroxide. The above-mentioned "causticizing chemicals" include sodium sulfate, hydrated lime, caustic soda, and sodium sulfide. Regarding the "type of fuel used in the fifth step," the term "fuel" in this specification encompasses heavy oil, petroleum coke, and the like. Regarding the "temperature of the cyclone dryer in the fifth step," the "temperature" in this specification may be measured at any location within the device. For example, the temperature may be measured at the inlet, inside, or outlet of the device.

[0081] The parameter information may also include, as result parameters, one or more parameters selected from the group consisting of the causticization rate in the fourth step, the amount of white liquor produced in the fourth step, the amount of active alkali in the fluid circulating through the pulp manufacturing system, the lime calcination rate in the fifth step, the amount of calcium oxide produced in the fifth step, the pulp yield in the first step, the steam consumption rate or amount of steam used in the pulp manufacturing system, the water consumption rate or amount of water used in the pulp manufacturing system, the bleaching chemical consumption rate or amount of bleaching chemical used, the causticization chemical consumption rate or amount of use in the fourth step, the amount of grid produced in the fourth step, the amount of fuel used or consumption rate in the fifth step, the brightness of the pulp obtained in the first step, and the kappa number of the pulp obtained in the first step.

[0082] Although some parameters essentially indicate the same thing, they may be classified as two or more of water quality parameters, operational parameters, and result parameters depending on the purpose. For example, in a black liquor evaporator, black liquor is heated by indirect heat exchange with steam generated from a boiler, and as a result of the heating, process steam is generated from the black liquor. This process steam is used to heat (concentrate) the concentrated black liquor in the next process. The amount of process steam generated is a result parameter because it is generated from the black liquor, and is used as an operational parameter because it is used to heat (concentrate) the concentrated black liquor in the next process. Furthermore, the steam generated from the boiler to heat the black liquor is used as an operational parameter. Note that the two or more parameters acquired by the parameter information acquisition unit are not all substantially identical. For example, in the case where the entire amount of process steam generated from the black liquor is used to heat (concentrate) the concentrated black liquor in the next process, the use of the process steam generated from the black liquor as a result parameter and the amount of steam used to heat (concentrate) the concentrated black liquor as an operational parameter is excluded. In such a case, the process steam generated from the black liquor as a result parameter and the amount of steam used to heat (concentrate) the concentrated black liquor as an operation parameter are substantially the same. However, when a portion of the process steam generated from the black liquor is used to heat (concentrate) the concentrated black liquor in the next step, the process steam generated from the black liquor as a result parameter and the amount of steam used to heat (concentrate) the concentrated black liquor as an operation parameter can be used as two parameters. In such a case, the process steam generated from the black liquor as a result parameter and the amount of steam used to heat (concentrate) the concentrated black liquor as an operation parameter are not substantially the same.Furthermore, in the case where the entire amount of process steam generated from the black liquor described above is used to heat (concentrate) the concentrated black liquor in the next step, the two parameters used are the process steam generated from the black liquor as a result parameter and the amount of steam used to heat (concentrate) the concentrated black liquor as an operation parameter, and further, if other parameters such as the pH of the water system as a water quality parameter are combined, the multiple parameters may be substantially the same.

[0083] These parameters may be quantitative or qualitative. When qualitative parameters are used, they may be assigned numerical values ​​and treated as quantitative data.

[0084] Note that the water quality parameters, operational parameters, and result parameters each encompass multiple parameters. Two or more parameters included in the parameter information can be independently selected from the water quality parameters, operational parameters, and result parameters. Two or more parameters can be selected from only water quality parameters, operational parameters, and result parameters (e.g., water pH and temperature), or two or more parameters can be selected from a combination of two or three of water quality parameters, operational parameters, and result parameters (e.g., water pH, wood chip type, and causticization rate). However, identical parameters (e.g., the pH of water at point A and the pH of water at point A) should not be selected (however, for example, the pH of water at point A and the pH of water at point B, which are measured at different points, may be selected).

[0085] As described above, while acquiring parameter information, the relationship model information acquisition unit 232 of the information processing device 2 acquires relationship model information (activity A102). Note that the order in which activity A101 and activity A102 are performed is arbitrary; activity A101 can be performed before activity A102, activity A102 can be performed before activity A101, or both activities can be performed in parallel (simultaneously).

[0086] This relationship model information is created in advance and indicates the relationship between events that may occur in the pulp manufacturing system PM and two or more parameters. Note that "in advance" refers to before the events are estimated, and may be during actual operation of the pulp manufacturing system PM, before actual operation, or any other time before the events are estimated.

[0087] Furthermore, the "expected results" related to the relationship model information relate to various events related to the pulp manufacturing PM. The estimation unit 233 of the information processing device 2 of this embodiment estimates predetermined events, and the events related to the relationship model information also correspond to the results estimated by this estimation unit 233.

[0088] The events to be inferred can be set as appropriate, but typically may be the following:

[0089] That is, in this embodiment, the predicted event may be related to one or more parameters selected from the group consisting of the causticization rate in the fourth step, the amount of white liquor produced in the fourth step, the amount of active alkali in the fluid circulating through the pulp manufacturing system, the lime calcination rate in the fifth step, the amount of calcium oxide produced in the fifth step, the pulp yield in the first step, the steam consumption rate or amount of steam used in the pulp manufacturing system, the water consumption rate or amount of water used in the pulp manufacturing system, the bleaching chemical consumption rate or amount of bleaching chemical used, the causticization chemical consumption rate or amount of use in the fourth step, the amount of grid produced in the fourth step, the amount of fuel used or consumption rate in the fifth step, the brightness of the pulp obtained in the first step, and the kappa number of the pulp obtained in the first step.

[0090] That is, the estimation target in this embodiment may be the result parameter described above. In this case, the result parameter is not usually included in the parameter information (two or more parameters).

[0091] The events to be estimated are not limited to the above items themselves, but may be combinations of the above items or related items related to the above items. For example, the product of the causticization rate in the fourth step and the amount of white liquor generated in the fourth step may be used as an estimated event (for example, this product may be evaluated as a "causticization efficiency index"). Examples of related items include the amount of energy (amount of fuel used) required to achieve a predetermined causticization rate (causticization rate in the fourth step). In other words, the related items here may be items that have a certain relationship to the above items and are useful for operating a pulp manufacturing PM.

[0092] The relationship model information is not particularly limited, but may include, for example, a function showing the relationship between the event to be inferred and two or more parameters, a lookup table, or a trained model of the relationship between the event to be inferred and two or more parameters.

[0093] The relationship model information is created, for example, as follows: Prior to predicting a specific event, a pre-measurement indicator related to the specific event is measured. Furthermore, two or more parameters, each of which is a water quality parameter, an operational parameter, or a result parameter, are measured in the same water system. Multiple data sets of these pre-measurement indicators and parameters are prepared, for example, by changing the day or time of measurement, so that the pre-measurement indicators and parameters fluctuate. Next, the pre-measurement indicator is assumed to be a function of two or more parameters, and the function form and coefficients are determined by comparing it with the pre-measurement indicator, thereby constructing the relationship model information. Here, the relationship model information may be a model obtained by performing a predetermined process on a pre-confirmation result corresponding to the event or an indicator related to the pre-confirmation result, and two or more parameters. The processing methods that can be used here include regression analysis (linear model, generalized linear model, generalized linear mixed model, ridge regression, lasso regression, elastic net, support vector regression, projection pursuit regression, principal component regression, etc.), time series analysis (VAR model, SVAR model, ARIMAX model, SARIMAX model, state space model, HMM model, etc.), decision trees (decision tree, regression tree, random forest, XGBoost, Light GBM, etc.), neural networks (simple perceptron, multilayer perceptron, DNN, CNN, RNN, LSTM, GAN, VAE, etc.), Bayes (naive Bayes, Bayesian optimization, Bayesian network, etc.), clustering (k-means, k-means++, etc.), classification (k-nearest neighbor method, support vector machine, etc.), ensemble learning (Boosting, Adaboost, etc.), etc.

[0094] In one embodiment, the relationship model information is preferably a model obtained by regression analysis of a pre-check result corresponding to an event or an index related to the pre-check result with two or more parameters. Note that the number of sample sets used in the regression analysis is not particularly limited.

[0095] It is preferable to create the relationship model information in the same system as the system for which the event is to be inferred. Also, for example, even within the same device, if the system undergoes significant changes, it is preferable to create and use the relationship model information for the system after the changes.

[0096] From this perspective, during the operation of the pulp manufacturing system PM, events and two or more parameters may be measured on a regular or irregular basis, and relationship model information may be created each time, or data may be added to update the relationship model information.

[0097] Such relationship model information may be created and updated, for example, by the function of the relationship model information creation unit 235 included in the information processing device 2. That is, the relationship model information creation unit 235 can create relationship model information suitable for the information processing of this embodiment by performing predetermined arithmetic processing on the acquired pre-check result or an index related to the pre-check result and two or more parameters. Note that this relationship model information may also be created manually by, for example, an operator.

[0098] After acquiring the parameter information and the relationship model information in this manner, the inference unit 233 of the information processing device 2 infers an event or an index related to the event based on the acquired parameter information and relationship model information (activity A103). Note that the event or the index related to the event here may be presented to the user as an inference result. More specifically, the inference result may be presented to the user in association with each parameter included in the parameter information.

[0099] Such inference results can typically be output by inputting the acquired parameter information into relationship model information. That is, events or indicators related to events output by input processing of such relationship model information can be presented in a manner that is easy for the user to understand.

[0100] In an exemplary embodiment, the event or indicator related to the event estimated by the estimation unit 233 relates to an event in a predetermined process selected from any one of the first to fifth processes, and the parameter information acquisition unit preferably acquires parameters in a process other than the predetermined process among the first to fifth processes. As described above, in a pulp manufacturing system PM, various materials may circulate within the system, and acquiring parameter information outside the predetermined process and making estimations based on this may contribute to improving the accuracy of estimation.

[0101] Furthermore, although not limited thereto, the event or indicator related to the event inferred by the inferring unit 233 may be related to an event in the fourth or fifth step. The slaking / causticizing system and the calcining system are positioned as processes that require particularly strict management among the pulp manufacturing PM processes, also in consideration of pulp quality and energy efficiency. The information processing system 1 of this embodiment is suitably used to infer events related to such processes.

[0102] The information processing method of this embodiment may include the following steps.

[0103] (Simulation process) The simulation process in this embodiment involves accepting from the user a change to at least one of the inference results and parameters presented by the estimation unit 233, and estimating the fluctuations for the inference results and parameters for which no changes were accepted from the user based on the content of the accepted change and the relationship model information.

[0104] The above-described simulation process is typically triggered by the estimation unit 233 presenting the estimation result to the user. FIG. 7 is a diagram showing an example of the estimation result presented to the user. In FIG. 7, parameter information (parameters 1 to 5) used by the estimation unit 233 is associated with an expected result index and displayed on the display unit 34 of the user terminal 3. That is, a predetermined screen showing the estimation result may be displayed on the display unit 34 based on the function of the estimation unit 233. Furthermore, the screen shown in FIG. 7 includes forms F1 to F5 corresponding to each parameter and a form F100 corresponding to an expected result index (an index related to the expected result), and each form shows the parameters (measured values) used by the estimation unit 233 in the estimation process and the estimation result (estimated value).

[0105] That is, a user who comes across a screen such as that shown in Fig. 7 can input a change to at least one of the inference results and each parameter. In the example shown in Fig. 7, forms F1 to F5 and F100 are configured so that various numerical values ​​can be input, and the above-mentioned changes are accepted when the user inputs any numerical value into the form.

[0106] 8 is a diagram showing the results of a simulation when a change is input for parameter 1. That is, when the user inputs a value V10 for form F1, the value shown in form F100, which indicates the expected result index, is changed to an estimated value of V200. This estimated value (V200) shown in form F100 can be obtained by inputting the input value (V10) for parameter 1 and the measured values ​​(V2 to V5) for parameters 2 to 5 into the relationship model information described above.

[0107] 8 shows an example in which the parameters 2 to 5 are calculated without being changed from the values ​​corresponding to the parameter information. That is, in this embodiment, it is also possible to perform a simulation after fixing the measurement results and the values ​​of each parameter to the contents presented as the estimated results. The control over the change of such values ​​can be set arbitrarily by the user.

[0108] Of course, in the example shown in Fig. 8, it is also possible to accept changes to some or all of parameters 2 to 5. Even in this case, as described above, the estimated value of the expected result index is calculated based on the input value of each parameter.

[0109] Meanwhile, the simulation unit 234 may execute the following process. FIG. 9 illustrates the results of a simulation performed when a change to the expected result index is input. In the example illustrated in FIG. 9, when a user inputs the expected result index value V300 into form F100, combinations of values ​​that satisfy the expected result index value V300 are presented in forms F1 to F5 corresponding to parameters 1 to 5. The combinations of values ​​presented in forms F1 to F5 are derived based on the value V300 and the relationship model information. That is, such combinations of values ​​can be obtained by back-calculating from the expected result index value V300 based on the relationship model information. Note that, when multiple combinations of estimated values ​​V10, 20, 30, 40, and 50 are expected, all or some of the expected combinations may be presented, or the most feasible combination may be presented. Note that the feasibility may be evaluated based on the operation history of the pulp manufacturing PM, etc. For example, a highly feasible combination may be a combination that requires a low cost to achieve each estimated value. Also, in the example shown in Fig. 9, it is possible to perform a simulation by fixing some of the parameters 1 to 5 to the contents presented as the estimation results.

[0110] The manner in which the estimation results and each parameter are changed is not limited to the manner shown in Fig. 8 or 9 (inputting numerical values ​​into a form). For example, it is assumed that the estimation unit 233 displays the estimation results and at least a part of each parameter as a graph (such as a bar graph). In this case, the simulation unit 234 can accept changes to the estimation results and each parameter when the user operates to change the shape of the graph. In this case, the presentation of the estimated variation results may also be realized by changing the shape of the graph for the corresponding item.

[0111] The simulation step may also be implemented by calculation using shap. In an exemplary embodiment, a shap value (Shapley value) for each parameter of the relationship model information is calculated in advance, and the estimated results and each parameter can be calculated based on the shap value. For example, in the example of FIG. 8, when a user changes a parameter, the value of the expected result index can be calculated based on the shap value calculated in advance. On the other hand, in the example of FIG. 9, when a user changes the value of the expected result index, calculations may be performed based on the shap value to find a value that approximates the value to which the expected result index is changed.

[0112] Furthermore, the simulation unit 234 of the information processing device 2 may display the simulation results of parameters, indicators, etc. in the following manner.

[0113] That is, the estimation unit 233 may estimate a predetermined index based on each parameter, and then display to the user a scatter diagram (graph) of a simulation of a case where a value of a certain parameter is reduced by a certain percentage. In this scatter diagram (graph), the horizontal axis represents the value of the parameter before the change, and the vertical axis represents the amount of change in the predetermined index. Note that in such a scatter diagram (graph), the results of a simulation based on data accumulated as past relationship model information and the results of a simulation based on the latest data set (i.e., the most recent data set used by the estimation unit 233 for estimation) may be displayed in different forms. That is, a user who sees such a scatter diagram (graph) can intuitively grasp how events in the pulp manufacturing system PM will change when a predetermined amount is reduced for the current parameters.

[0114] (Impact level identification process) The influence specifying step in this embodiment specifies the influence of each parameter included in the dataset on the event by comparing the relationship model information with the dataset.

[0115] When such an influence degree specifying step is executed, first, the data set specifying unit 236 specifies a data set in which an index (expected result or related index) related to the event is associated with two or more parameters.

[0116] Here, the parameter is a parameter associated with the index, or in other words, may have a correlation with the value of the index. Note that the selection of parameters is made, for example, based on the knowledge of the user or through analysis by an arbitrary information processing device, and if this selection is appropriate, the correlation with the index will be appropriate accordingly, and it can be expected that the accuracy of the index and the accuracy of the influence degree described below will also be improved.

[0117] The dataset here is data in which an index related to an event and two or more parameters are paired. In an exemplary embodiment, the index and two or more parameters associated in the dataset are preferably obtained more recently than the index and two or more parameters associated in the relationship model information. In other words, the data constituting the dataset (the index and two or more parameters) may be new data that has not necessarily been used to create the relationship model information. That is, the dataset in this embodiment may be a dataset based on the most recently obtained parameter information and the corresponding index. The corresponding index here may typically be a value output by inputting the most recently obtained parameter information into the relationship model information. This ensures real-time calculation of the influence degree, which will be described later, and also improves the calculation accuracy of the influence degree.

[0118] However, the data set identified by the data set identifying unit 236 is not limited to this. For example, a dataset identified by the dataset identifying unit 236 may be used to create the relationship model information, and then this dataset may be used to calculate the degree of influence. That is, in an embodiment, the dataset identified by the dataset identifying unit 236 may be part of the datasets that make up the relationship model information, and does not necessarily need to be independent of the data in the relationship model information. Note that if the two are independent, it is expected that the accuracy of calculating the degree of influence will be improved.

[0119] Furthermore, in the present embodiment, the dataset is described as using an index related to an event estimated by the estimation unit 233, but the present invention is not limited to this. A statistical or machine learning method may be utilized to simulate the calculation of an index related to an event, and the simulated index may be identified as the dataset. For example, a method called Permutation Importance may be used to apply two or more new parameters to an arbitrary range of datasets used to create the relationship model information and simulatedly evaluate them to generate simulated indexes, and the simulated indexes may be identified by the dataset identification unit 236.

[0120] After identifying the dataset in this manner, the influence identification unit 237 compares the relationship model information acquired by the relationship model information acquisition unit 232 with the identified dataset, thereby identifying the influence of each parameter included in the dataset on the event. The influence level refers to the level of influence of each parameter included in the data set on an event. For example, when an event (such as a problem in a manufacturing process) occurs, if the influence level of a parameter in the data set is relatively high, it can be determined that the parameter is the main factor causing the event (the aforementioned problem).

[0121] Although various methods for identifying the degree of influence may be used, in a typical embodiment, the influence identification unit 237 identifies the degree of influence by performing a predetermined arithmetic process on each parameter. This predetermined arithmetic process includes at least one of differential processing, statistical processing, and processing using a trained model.

[0122] Here, a case where difference processing is used as the calculation process for calculating the degree of influence will be described as an example. Fig. 10 is an explanatory diagram showing an example of a method for calculating the degree of influence using an index X as an index (expected result). Fig. 11 is a graph schematically showing the degree of influence of each parameter on an event. In addition, in the description here, a case where the parameters of the data set are six (parameters P1 to P6) as shown in Fig. 10 will be described as an example.

[0123] In the formula representing the index X in Fig. 10, t0, t1, t2, t3, t4, t5, and t6 are predetermined. The formula relating to the index X shown in Fig. 10 and the values ​​of t0 and the like correspond to the relationship model information. Furthermore, a and b are constants that can be set appropriately.

[0124] Each influence V(n) of the parameter Pn (n=1 to 6) can be expressed as ID(p)-ID(n). In this way, the influence is calculated (specified) by the difference process related to the index X. FIG. 10 shows an example of calculation of the influence V(1), which is the value of the influence of the parameter P1.

[0125] ID(p) is calculated using parameters that are more recently obtained than the parameters included in the relationship model information. The newly obtained parameters are, for example, new parameters that are obtained separately from the parameters used to create the relevance model information by the relevance model information creation unit described above.

[0126] ID(p) is then obtained by substituting the parameter values ​​of the data set into the equation for the index X. Specifically, in the formula for ID(p), A(p1) is the newly obtained value for parameter P1, B(p2) is the newly obtained value for parameter P2, C(p3) is the newly obtained value for parameter P3, D(p4) is the newly obtained value for parameter P4, E(p5) is the newly obtained value for parameter P5, and F(p6) is the newly obtained value for parameter P6. These values ​​A(p1) to F(p6) are typically values ​​acquired at the same time, but in an exemplary embodiment, they may be values ​​acquired at different times. For example, an exemplary embodiment is one in which value A(p1) is a value acquired X hours ago, while value B(p2) is acquired as an average value for a time period from Y days ago to Z hours ago.

[0127] As shown in FIG. 10, ID(1) can be calculated based on the reference value A(s1) for parameter P1 and parameters (values ​​B(p2) to F(p6)) obtained more recently than the parameters included in the relationship model information. The reference value A(s1) can be set based on various perspectives, such as historical average values ​​during the relationship model creation period, target reference values, design values, and numerical values ​​from periods of good operation. The same applies to the reference values ​​B(s2) to F(s6) for the other parameters P2 to P6. In other words, the reference values ​​described here are based on the relationship model information. Note that the term ID(1) is the same as ID(p) except for the reference value A(s1), as indicated by the arrow Ar in FIG. 10.

[0128] Although not shown in FIG. 10, the influence V(2), which is the value of the influence of parameter P2, can be calculated by calculating ID(p)-ID(2). The value of ID(p) has been explained above, so it will not be repeated here, but for ID(2), the value of B(p2) becomes the reference value B(s2). Everything else is the same as ID(p). Note that the influence V(3) and subsequent values, which are the value of the influence of parameter P3, can be calculated in the same manner.

[0129] In this way, the degree of influence is identified by comparing the relationship model information that can be acquired by the relationship model information acquisition unit 232 with the dataset identified by the dataset identification unit 236. ID(p) is a value that takes into account the data set, but ID(n) takes into account not only the data set mentioned above but also the reference value, so relationship model information is also taken into account. In one example of an embodiment (differential processing), the influence V(n) of each parameter is given by ID(p)-ID(n), so it can be said that the influence is a value obtained by comparing the dataset with the relationship model.

[0130] In the above description, a case has been described as an example in which parameter values ​​(values ​​A(p1) to F(p6)) obtained more recently than the parameters included in the relationship model information are used to calculate ID(p) or ID(n). In other words, the newly obtained parameters (values ​​A(p1) to F(p6)) used to calculate ID(p) or ID(n) are the values ​​of parameters P1 to P6 themselves, but are not limited to this. For example, moving averages may be used instead of the values ​​themselves. Furthermore, a composite value of two or more parameters (composite parameter value) may be used as the parameter (values ​​A(p1) to F(p6)) used to calculate the index X described here. In this case, the composite parameter related to this composite value may be used to specify the degree of influence when calculating the degree of influence.

[0131] Although the above describes an example in which differential processing is used as the calculation processing, statistical processing and processing such as a trained model can also be used. For example, Shap, Permutation Importance, Feature Importance, an impulse response function, etc. may be used for this processing. These processings may be combined with the above-described differential processing to calculate the influence degree with higher reliability and robustness.

[0132] In the above description, only one reference value is set for each ID(n), but this is not limited to this. For example, when calculating the value of one ID(n), multiple reference values ​​such as reference value A(s1) and reference value B(s2) may be used. In this case, the influence of a combination of two or more parameters is calculated. In other words, it is possible to identify the influence related to the interaction of parameters.

[0133] When the influence degree identification unit 237 identifies the influence degree of each parameter as described above, the influence degree is shown to the user in various formats via the display unit 34 of the user terminal 3. That is, the influence degree identification unit 237 can output the calculated influence degree to the user terminal 3 as information (impact degree information) that allows the user to understand the calculated influence degree, and identify the influence degree. The format of the impact information is not particularly limited, and may be, for example, visual information itself generated in a visible form such as numerical values ​​or a graph as shown in Fig. 11, or rendering information for displaying the visual information. Also, instead of visual information, the impact information may be audio information, or both. In the example of FIG. 11, the user can visually understand that parameter 1 is the parameter with the greatest influence as a factor causing the event.

[0134] The system becomes easier for users to use if they can visually grasp the factors that cause events as a manufacturing flow chart in addition to the graph shown in Fig. 11. For example, the influence degree identification unit 237 can identify parameters with a high influence degree by highlighting the parameters on the manufacturing flow chart.

[0135] Note that "identification" does not necessarily include the output of numerical values ​​or graphs (output of visual information) or the output of audio (output of audio information). In other words, "identification" may include only the calculation of the impact degree through the arithmetic processing described in Fig. 10. For example, if there is no particular problem with the manufacturing process or product quality, it is not necessary to notify the user of the content, and also, there are cases where the user is not interested in the magnitude of the impact degree of the parameter for the event, but is interested in countermeasures for the event.

[0136] The timing at which the impact identification unit 237 identifies the impact may be regular or irregular. When identifying the impact periodically, for example, intervals of several seconds to several tens of minutes may be set. The impact identification unit 237 may also identify the impact based on a manual instruction from the user (an instruction from the user to identify the impact). Furthermore, when the value of the index calculated by the estimation unit 233 exceeds a preset threshold, the impact identification unit 237 may identify the impact of each parameter.

[0137] Furthermore, the influence degree identification unit 237 may output to the user terminal 3 a screen showing the actual measurement value and the influence degree over time, as shown in Fig. 12, for example. Fig. 12 is a schematic diagram showing the transition of the actual measurement value (broken line) of parameter 1 and the influence degree of parameter 1 on an event. This allows the user to grasp the change over time in the actual measurement value related to the parameter and the influence degree of that parameter, making the system easier for the user to use.

[0138] In this manner, in the embodiment, the degree of influence is determined for the parameters (parameters P1 to P6) related to the data set. This makes it possible to identify with a high degree of accuracy which of all parameters (all factors) is the most influential factor in a currently occurring event (for example, a problem in the manufacturing process), making the system easier for system users to use and facilitating the management of events involving pulp manufacturing PMs.

[0139] (Countermeasure presentation process) The countermeasure presentation step presents countermeasure information according to the impact level identified by the impact level identification unit 237. As described above, for example, if the above-mentioned parameter 1 has the greatest impact level on the event, countermeasure information for optimizing the situation of parameter 1 is presented.

[0140] The countermeasure information is, for example, stored in a database by the storage management unit 239 of the information processing device 2. The countermeasure information is associated with one or more countermeasures to be taken when the calculated impact level is high. That is, in an example embodiment, at least one countermeasure information to be presented when the impact level is high is associated with each parameter. The presented countermeasure information may be visual information itself generated in a manner visible to the user, such as characters, numbers, diagrams, photos, videos, screens, images, icons, text, etc., or may be rendering information for displaying the visual information on various devices or terminals. When there are multiple highly impactful parameters, the countermeasure information presented by the countermeasure presentation unit 238 may correspond to these multiple highly impactful parameters. Typically, when the impact levels of parameters P1 and P2 are high, one or more countermeasures that can effectively control both parameters P1 and P2 may be presented.

[0141] Furthermore, when the countermeasure presentation unit 238 is capable of presenting a plurality of pieces of countermeasure information, the display order may be based on the score, or the display order may be random, and only the score may be displayed. The score indicates the degree to which the countermeasure information is recommended. The score may be, for example, a score set in advance by the user. The score may also reflect the results and effects of the countermeasures taken by the user based on the countermeasure information. In this case, the countermeasure presentation unit 238 only needs to be able to receive feedback on the results and effects of the countermeasures taken by the user based on the countermeasure information. In other words, the user takes countermeasures based on the countermeasure information, and the countermeasure presentation unit 238 receives input of a score according to the results and effects of the countermeasures.

[0142] As described above, the information processing system 1 of this embodiment can appropriately predict events that may occur in a pulp production system.

[0143] 4. Variations In Section 4, a modified example of the information processing method of the information processing system 1 and the like described above will be described.

[0144] The above-described embodiment has been described as a configuration of the information processing system 1, but an information processing method executed by the information processing system may also be provided, which includes steps of executing processing of each unit of the information processing system. Also, a program for causing a computer to execute processing of each unit of the information processing system 1 may also be provided.

[0145] In the above-described embodiment, an information processing method using relevance model information is described, but the information associated when creating the relevance model information is not limited to the above. In other words, the relevance model information used in this embodiment may be associated with various other conditions, such as weather conditions, regional conditions, and conditions related to the age of the facility.

[0146] In the above embodiment, the information processing system 1 performs various storage and control operations, but multiple external devices may be used instead of the information processing system 1. That is, various types of information may be distributed and stored in multiple external devices using blockchain technology or the like.

[0147] In the above embodiment, the information processing device 2 and the user terminal 3 function as separate devices. However, the user terminal 3 itself may have various functions as the control unit 23 of the information processing device 2. However, the computer may also function as a standalone computer and perform processes such as acquiring various information, making predictions, simulating, and identifying the degree of impact. [Example]

[0148] The present invention will be explained in more detail below by showing examples, but the present invention is not limited to the following examples in any way.

[0149] Example 1 In the pulp manufacturing system PM shown in Figure 2, the kiln heavy oil consumption unit (amount of kiln heavy oil used) was set as the estimation target, and relationship model information was created. Specifically, in Example 1, the following various parameters were selected and used as parameter information. In creating the relationship model information, each parameter was weighted according to its importance.

[0150] Water quality parameters Iron content of green liquor Iron content of white liquor Operating parameters The pressure difference of the white liquor filter that filters the white liquor produced in the fourth process Kiln air volume in the fifth process Kiln heavy oil temperature in the fifth process Kiln drive current in the fifth process Evaporator evaporation rate in the second process Result parameters Causticization rate in the fourth process White liquor production volume in the fourth process

[0151] In this Example 1, when the estimation equation (relationship model information) was created using only the operational parameters and result parameters, the correlation coefficient was less than 0.7, but by including water quality parameters in the parameter information, the correlation coefficient exceeded 0.7.

[0152] Example 2 In the pulp manufacturing PM shown in Figure 2, two estimation targets were set: the causticization rate and the kiln heavy oil consumption unit (amount of kiln heavy oil used), and relationship model information was created. Specifically, in Example 2, the following various parameters were selected and used as parameter information. In creating the relationship model information corresponding to each estimation target, each parameter was weighted according to its importance.

[0153] Water quality parameters Active alkali content of white liquor Total titratable alkali content of white liquor Iron content of white liquor Amount of suspended solids in green liquor Total titratable alkali content of green liquor Operating parameters Amount of calcium oxide added in the fourth step The amount of sodium hydroxide added is different from that of white liquor in the first process. Steam consumption in the first process Black liquor injection amount in the recovery boiler in the second process Diluted black liquor flow rate Result parameters Calcium oxide production volume produced in the fifth process

[0154] As a result, an estimation formula was created with a correlation coefficient of 0.807 for the causticization rate and 0.579 for the kiln heavy oil consumption rate. Furthermore, in this Example 2, actual equipment tests were also conducted in a pulp manufacturing PM. Figure 13 is a graph showing the results of Example 2. Specifically, Figure 13A shows a trend graph for the causticization rate, and Figure 13B shows a trend graph for the kiln heavy oil consumption rate. Verification of the learning data (relationship model information) was carried out during the period on the left side of the graph, and test data from the actual equipment was obtained during the period on the right side of the graph. As can be seen from this graph, a correlation between the predicted values ​​and the actual measured values ​​when using the relationship model information has been confirmed.

[0155] Example 3 In the pulp manufacturing system PM shown in Figure 2, the activation efficiency index was set as the estimation target and relationship model information was created. Note that the activation efficiency index here is defined as the product of the causticization rate and the white liquor flow rate (production volume). Specifically, in Example 3, the following various parameters were selected and used as parameter information. Note that, in creating the relationship model information, each parameter was weighted according to its importance.

[0156] Water quality parameters White liquor sulfidity Operating parameters Crude green liquor flow rate Dregs withdrawal amount Amount of green liquor flocculant added in the third process Black liquor injection amount in the recovery boiler in the second process Cutting rate of calcium oxide produced in the fifth step Causticizing tank temperature in the fourth process Amount of hot causticizing water in the fourth process Inlet temperature of the cyclone dryer in the fifth process Result parameters Calcium oxide production volume produced in the fifth process

[0157] In Example 3, actual machine tests were also conducted in the pulp manufacturing PM. FIG. 14 is a graph showing the results of Example 3. Verification of the learning data (relationship model information) was performed during the period on the left side of the graph (measurement period), and test data was acquired using the actual machine during the period on the right side of the graph (operation period). As can be seen from this graph, a correlation was confirmed between the predicted values ​​and the actual measured values ​​when using the relationship model information. In Example 3, operational changes were made to factors that have a significant impact on the causticization index (specifically, the amount of dregs extracted and the rate at which calcium oxide is excavated in the fifth process). This resulted in an approximately 4% improvement in the causticization efficiency index. Furthermore, this also led to a 2% increase in pulp production in the pulp manufacturing PM.

[0158] Although the embodiments of the present invention have been described above, these are merely examples of the present invention, and various other configurations may be adopted. Furthermore, the present invention is not limited to the above-described embodiments, and modifications and improvements within the scope of achieving the object of the present invention are included in the present invention. [Explanation of symbols]

[0159] 1: Information processing system 2: Information processing equipment 3: User terminal 20: Communication bus 21: Communications Department 22: Storage section 23: Control section 30: Communication bus 31: Communications Department 32: Storage section 33: Control section 34:Display section 35: Input section 40: Estimated value 50: Estimated value 231: Parameter information acquisition unit 232: Relationship model information acquisition unit 233: Guessing part 234: Simulation Department 235: Relationship model information creation unit 236: Dataset identification part 237: Impact Identification Department 238: Countermeasure presentation section 239: Memory management department 511: Digester 521: Evaporator 522: Boiler 523: Dissolving tank 531: Green liquor clarification equipment 532: Clarified green liquor tank 533: Dregs Processing Unit 541: Surekha 542: Causticizing reactor 543: White liquor clarifier 544: White liquor tank 545: Lime Mud Washer 551: Lime Mud Filter 552: Kiln F1~F5, F100: Forms PM: Pulp manufacturing system Pr1: 1st step Pr2: 2nd process Pr3: 3rd process Pr4: 4th step Pr5: 5th step

Claims

1. An information processing system for predicting events that may occur in a pulp manufacturing system, comprising: The pulp making system comprises: A first step of cooking wood chips with white liquor to obtain pulp; A second step of treating the black liquor produced in the first step to obtain green liquor; a third step of treating the green liquor to obtain a clarified green liquor; a fourth step in which calcium oxide is added to the clarified green liquor to obtain white liquor and calcium carbonate, the obtained white liquor is supplied to the first step, and the obtained calcium carbonate is supplied to the subsequent fifth step; a fifth step of calcining the calcium carbonate to obtain calcium oxide, and supplying the obtained calcium oxide to the fourth step; and The system includes a parameter information acquisition unit, a relationship model information acquisition unit, and an estimation unit, the parameter information acquisition unit acquires, as parameter information, two or more parameters related to any one of the first step to the fifth step; the relationship model information acquisition unit acquires relationship model information that is created in advance and indicates a relationship between the event or an index related to the event and the two or more parameters; The estimation unit estimates the event or an index related to the event based on the acquired parameter information and relationship model information.

2. 2. The information processing system according to claim 1, An information processing system, wherein the parameter information acquisition unit acquires, as the parameter information, two or more parameters selected from the group consisting of water quality parameters, operation parameters, and result parameters.

3. 3. The information processing system according to claim 2, The parameter information includes, as the water quality parameters, one or more parameters selected from the group consisting of pH, electrical conductivity, oxidation-reduction potential, zeta potential, turbidity, temperature, foam height, biochemical oxygen demand (BOD), chemical oxygen demand (COD), total organic carbon (TOC), inorganic carbon, absorbance, color, appearance, whiteness, transparency, particle size distribution, degree of aggregation, amount of foreign matter, suspended solids (SS), foam area on the water surface, area of ​​dirt in the water, amount of air bubbles, amount of organic acid, amount of active alkali, total amount of titratable alkali, amount of metal or metal ion, non-metal ion content, amount of calcium, amount of total chlorine, amount of free chlorine, amount of dissolved oxygen (DO), cation demand, amount of hydrogen sulfide, sulfidity, amount of hydrogen peroxide, ash concentration, microbial respiration rate, viable cell count, spore count, and ATP of the fluid circulating through the pulp manufacturing system.

4. 3. The information processing system according to claim 2, The parameter information includes, as the operation parameters, the type of the wood chips, the quality of the wood chips, the pulp production volume, the water consumption unit or the amount of water used in the pulp manufacturing system, the new water consumption unit or the amount of new water used in the pulp manufacturing system, the bleaching chemical consumption unit or the amount of bleaching chemical used, the white liquor addition rate in the first step, the steam consumption unit or the amount of steam used in the pulp manufacturing system, the flow rate of the fluid circulating in the pulp manufacturing system, the temperature of the fluid circulating in the pulp manufacturing system, and the amount of cooking steam in the first step. or consumption unit, evaporation factor of the evaporator in the second step, steam pressure of the evaporator in the second step, black liquor injection amount in the second step, diluted black liquor flow rate, amount of dregs extracted from the green liquor, amount or rate of green liquor flocculant added in the third step, amount of lime mud extracted in the fourth step, amount or consumption unit of calcium oxide added in the fourth step, consumption unit or amount of causticizing chemical used in the fourth step, causticizing tank temperature in the fourth step, an information processing system including one or more parameters selected from the group consisting of an amount of hot water or a consumption unit, a differential pressure of a white liquor filter that filters the white liquor produced in the fourth step, a cutting rate of calcium oxide produced in the fifth step, an amount of calcium oxide produced in the fifth step, an amount of sodium hydroxide fed or a consumption unit different from that of the white liquor in the first step, a temperature of a cyclone dryer in the fifth step, an amount of sodium sulfate fed or a consumption unit to the pulp production system, a type of fuel used in the fifth step, an amount of kiln air in the fifth step, a temperature of kiln heavy oil in the fifth step, a kiln drive current in the fifth step, a kiln exhaust heat temperature in the fifth step, a moisture content of calcium carbonate fed to the fifth step, a particle size of calcium carbonate produced in the fourth step, a particle size of calcium carbonate fed to the fifth step, weather during operation, an amount of rainfall, an amount of white liquor coagulant used or an addition rate, an amount of water reducing agent used or a consumption unit, a rotation speed of a lime mud filter, a number of days of operation, and a dead load amount due to an inert alkali.

5. 3. The information processing system according to claim 2, the parameter information acquires a parameter different from the target parameter to be estimated as the result parameter, The result parameters include one or more parameters selected from the group consisting of the causticization rate in the fourth step, the amount of white liquor produced in the fourth step, the amount of active alkali in the fluid circulating through the pulp manufacturing system, the lime calcination rate in the fifth step, the amount of calcium oxide produced in the fifth step, the pulp yield in the first step, the steam consumption rate or amount of steam used in the pulp manufacturing system, the water consumption rate or amount of water used in the pulp manufacturing system, the bleaching chemical consumption rate or amount of bleaching chemicals used, the causticization chemical consumption rate or amount of causticization chemicals used in the fourth step, the amount of grit produced in the fourth step, the amount of fuel used or consumption rate, the brightness of the pulp obtained in the first step, and the kappa number of the pulp obtained in the first step.

6. 2. The information processing system according to claim 1, The third step of the pulp manufacturing system is a step of treating the green liquor to obtain dregs and the clarified green liquor, generating weak liquor from the obtained dregs and supplying it to the second step, and supplying the obtained clarified green liquor to the fourth step.

7. 2. The information processing system according to claim 1, the event or the index relating to the event inferred by the inferring unit relates to an event in a predetermined process selected from any one of the first process to the fifth process, The parameter information acquisition unit acquires parameters for a step other than the predetermined step among the first step to the fifth step.

8. 2. The information processing system according to claim 1, An information processing system, wherein the event or the indicator related to the event inferred by the inference unit is related to the event in the fourth step or the fifth step.

9. 2. The information processing system according to claim 1, an information processing system, wherein the relationship model information is a model obtained by regression analysis, time series analysis, decision tree analysis, neural network analysis, Bayesian analysis, clustering analysis, classification analysis, or ensemble learning between a pre-check result corresponding to the event or an index related to the pre-check result and the two or more parameters.

10. An information processing method executed by an information processing system, A method comprising the step of executing processing of each part of the information processing system according to any one of claims 1 to 9.

11. A program, A program for causing a computer to execute processing of each unit of the information processing system according to any one of claims 1 to 9.

Images