Prediction device, calculation device, manufacturing device, and manufacturing method

Abstract

To reduce variations in performance of a polymer to be manufactured.SOLUTION: A prediction device (10A) for predicting a performance value of a polymer in a polymerization tank after charging a raw material in manufacturing the polymer includes: an acquisition unit (111) for acquiring an observation value observed as a value related to manufacturing of the polymer in manufacturing of a current polymer as an observation value for prediction; and a prediction unit (112) for predicting the performance value at a predetermined timing of the polymer to be manufactured at present from the observation value for prediction acquired by the acquisition unit using a relation between the observation value obtained in the past manufacturing of a polymer of the same kind as the polymer and the performance value of the polymer at the predetermined timing of the past manufacturing.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to a prediction device, a calculation device, a production device, and a production method used in the production of a polymer. [Background technology]

[0002] Soft sensors have been used in various fields. Soft sensors estimate process variables that are relatively easy to measure, such as temperature and pressure, instead of process variables y1 that are difficult to measure and are not measured frequently, or process variables y2 that require time to measure. For example, Patent Document 1 discloses a polyolefin resin granulation system equipped with a soft sensor that estimates the melt flow rate. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Publication No. 2011-245742 Summary of the Invention [Problem to be solved by the invention]

[0004] The present disclosure provides a prediction device, a computing device, a manufacturing device, and a manufacturing method that can reduce the number of steps required in the manufacturing process to obtain a polymer having a specific performance value. [Means for solving the problem]

[0005] The prediction device of the present disclosure is a prediction device that predicts a performance value representing the performance of a polymer in a polymerization tank after raw materials are added, in the production of a polymer, and may include an acquisition unit that acquires, as prediction observation values, observation values ​​observed in a current production of the polymer as values ​​related to the production of the polymer, and a prediction unit that predicts the performance value of the polymer currently being produced at a predetermined timing from the prediction observation values ​​acquired by the acquisition unit, using a relationship between observation values ​​obtained in a past production of a polymer of the same type as the polymer and the performance values ​​of the polymer at a predetermined timing in the past production.

[0006] In the above prediction device, the prediction unit may predict the performance value of the polymer currently being produced at a specified timing using the prediction observation values ​​acquired by the acquisition unit, based on a trained model that has learned through machine learning the relationship between learning observation values ​​obtained in past production of a polymer of the same type as the polymer and a performance value of the polymer at a specified timing in the past production.

[0007] In the above prediction device, the acquisition unit may acquire the observation value together with the elapsed time since the start of the current production, and a set of the elapsed time and the observation value may be used as a prediction observation value, and the prediction unit may predict the performance value of the polymer currently being produced at the specified timing using a relationship between a learning observation value, which is a set of the observation value in a past production and the elapsed time since the start of the past production, and the performance value at a specified timing of the past production.

[0008] In the above prediction device, the acquisition unit may predict the performance value of the polymer at the specified timing using the trained model trained using at least one observation value or performance value suitable for predicting the performance value selected by a genetic algorithm from multiple types of observation values ​​obtained in past production and performance values ​​of the polymer obtained in past production.

[0009] In the above prediction device, the observed values ​​may include at least any of the stirring current value, stirring power value, and pressure value within the polymerization tank of a stirrer that stirs the reaction mixture containing the raw materials in the polymerization tank, the amount of any raw material fed from the start of production to the present time, and the amount of all raw materials fed from the start of production to the present time.

[0010] In the above prediction device, the performance value may be any one of Mooney viscosity, average molecular weight, specific gravity, hardness, elongation, Curast minimum value, Curast maximum value, Curast induction time, Curast optimum vulcanization time, tensile strength, 100% tensile stress, glass transition point, thermal decomposition onset temperature, and compression set rate.

[0011] In the above prediction device, the polymer may be rubber.

[0012] In the above prediction device, the predetermined timing may be a timing when an input amount of a predetermined raw material for the polymer to be produced reaches a predetermined value, or a timing when a predetermined time has elapsed since the start of production.

[0013] The arithmetic device of the present disclosure is a arithmetic device that, in the production of a polymer, calculates a target timing for a specific operation to be performed in a polymerization tank, and may include a receiving unit that receives a target performance value indicating a target performance of the polymer in current production and a performance value at a predetermined timing after raw materials for the polymer are added and before production is completed, and a arithmetic unit that calculates the target timing for the polymer currently being produced to reach the target performance value, using the performance value of the polymer at the predetermined timing in a past production of a polymer of the same type as the polymer, the performance value of the polymer obtained in the past production, and the relationship between the target timing of the past production, and the target performance value received by the receiving unit and the performance value at the predetermined timing.

[0014] In the above-mentioned calculation device, the calculation unit may use the target performance value and the performance value at the specified timing to determine the target timing at which the polymer currently being produced will reach the target performance value, using a second learned model that has learned by machine learning the relationship between a performance value of the polymer at a specified timing in past production of a polymer of the same type as the polymer, the performance value of the polymer obtained in the past production, and the target timing of the past production.

[0015] The above-mentioned calculation device may be connected to the above-mentioned prediction device, and the reception unit may receive the performance value predicted by the prediction device as the performance value at the predetermined timing.

[0016] Another arithmetic device of the present disclosure is a arithmetic device that calculates a target timing to be used in determining the end of production of a polymer, and may include a reception unit that accepts, as an observation value for calculation, an observation value observed in a current production as a value related to the production of the polymer, and accepts, as a target value, a target performance value that indicates a target performance of the polymer in the current production, and a calculation unit that calculates the target timing of the current production from the observation value for calculation accepted by the reception unit, using a relationship between an observation value obtained in a past production of a polymer of the same type as the polymer, the performance value of the polymer obtained in the past production, and the target timing of the past production.

[0017] In the above-mentioned calculation device, the calculation unit may determine the target timing from the calculation observation values ​​using a third trained model that has learned through machine learning the relationship between learning observation values ​​obtained in past production of a polymer of the same type as the polymer, a performance value of the polymer obtained in the past production, and the target timing of the past production.

[0018] In the computing device, the polymer may be rubber.

[0019] The manufacturing apparatus of the present disclosure may include a polymerization tank into which raw materials for a polymer are input; an acquisition unit that acquires, as prediction observation values, observation values ​​observed in a current production of the polymer as values ​​related to the production of the polymer; a prediction unit that predicts a performance value of the polymer currently being produced at a predetermined timing from the prediction observation values ​​acquired by the acquisition unit, using a relationship between observation values ​​obtained in a past production of a polymer of the same type as the polymer and a performance value of the polymer at a predetermined timing of the past production; a reception unit that accepts a target performance value representing a target performance of the polymer in the current production and the performance value at the predetermined timing predicted by the prediction unit; a calculation unit that calculates a target timing at which the polymer currently being produced will reach the target performance value, using the performance value of the polymer at the predetermined timing in a past production of a polymer of the same type as the polymer, the relationship between the performance value of the polymer obtained in the past production and the target timing of the past production, and the target performance value and the performance value at the predetermined timing accepted by the reception unit; and a control unit that terminates the current production using the target timing obtained by the calculation unit.

[0020] The manufacturing method of the present disclosure may include the steps of: charging raw materials for a polymer into a polymerization tank; acquiring, as a prediction observation value, an observation value observed in a current production of the polymer as a value related to the production of the polymer; predicting, from the acquired prediction observation value, a performance value of the polymer currently being produced at a predetermined timing, using a relationship between an observation value obtained in a past production of a polymer of the same type as the polymer and a performance value of the polymer at a predetermined timing of the past production; accepting a target performance value representing a target performance of the polymer in the current production and the predicted performance value at the predetermined timing; determining a target timing for the polymer currently being produced to reach the target performance value, using the performance value of the polymer at the predetermined timing in a past production of a polymer of the same type as the polymer, the performance value of the polymer obtained in the past production, and a relationship between the target timing of the past production, the accepted target performance value, and the performance value at the predetermined timing; and terminating the current production using the determined target timing.

[0021] These general and specific aspects may be realized by a system, a method, and a computer program, as well as combinations thereof. Effect of the Invention

[0022] According to the prediction device, the calculation device, the production device, and the production method of the present disclosure, it is possible to reduce the number of steps required in the production process of a polymer. [Brief description of the drawings]

[0023] [Figure 1] 1 is a schematic diagram showing a configuration of a manufacturing apparatus according to a first embodiment. [Diagram 2] FIG. 1 is a block diagram showing a configuration of a prediction device according to a first embodiment. [Diagram 3] 1 is a block diagram showing a configuration of a calculation device according to a first embodiment. [Figure 4] 4 is a flowchart illustrating a process in the manufacturing apparatus according to the first embodiment. [Figure 5A] FIG. 2 is a schematic diagram illustrating learning of a Mooney viscosity prediction model used by the prediction device of the first embodiment. [Figure 5B] FIG. 2 is a schematic diagram illustrating input and output of a Mooney viscosity prediction model used by the prediction device of the first embodiment. [Figure 6] FIG. 2 is a schematic diagram illustrating training data of a Mooney viscosity prediction model used by the prediction device of the first embodiment. [Figure 7A] 3 is a schematic diagram illustrating learning of a target timing calculation model used by the prediction device of the first embodiment. FIG. [Figure 7B] 3 is a schematic diagram illustrating input and output of a target timing calculation model used by the prediction device of the first embodiment. FIG. [Figure 8] FIG. 11 is a schematic diagram showing the configuration of a manufacturing apparatus according to a second embodiment. [Figure 9] FIG. 11 is a block diagram showing the configuration of a calculation device according to a second embodiment. [Figure 10] 11 is a flowchart illustrating a process in a manufacturing apparatus according to a second embodiment. [Figure 11A] FIG. 11 is a schematic diagram illustrating learning of a Mooney viscosity prediction model used by a prediction device according to a second embodiment. [Figure 11B] FIG. 11 is a schematic diagram illustrating the input and output of a Mooney viscosity prediction model used by the prediction device of the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0024] One example of a method for producing a polymer is to feed the raw materials of the polymer to be produced into a polymerization tank and obtain the polymer by a polymerization reaction in the polymerization tank. In this case, the raw materials are not always fed into the polymerization tank all at once, but may be fed during production. For example, the raw materials include monomers and initiators, and may be fed initially, intermittently, or continuously. In addition, different methods may be combined for each of the multiple raw materials used to produce a single polymer. Specifically, when a polymer is produced using raw materials A and B, raw material A may only be fed initially, but raw material B may be fed intermittently.

[0025] The production of such polymers is not always completed in the same production time, and even when the same polymer is produced, it may take 50 hours at one time and 70 hours at another time, and each step of the production cannot be determined only by time. For example, in the production process, when the input amount of a specific raw material reaches a predetermined amount, the process may proceed to the next step. In addition, for example, the process may proceed to the next step on the condition that the performance of the polymer in the production process reaches a predetermined value. For example, when the process proceeds to the next step according to the input amount of the raw material, this can be relatively easily achieved by observing the input amount of the raw material. On the other hand, when the performance of the polymer in the production process proceeds to the next step according to a predetermined value, it is difficult to observe the performance value of the polymer in the production process in real time. Therefore, it is difficult to grasp each situation in the production of a polymer, and the performance of the produced polymer tends to vary.

[0026] In order to observe the performance values ​​of the polymer during production, it is necessary to extract a portion of the polymer from the polymerization tank and measure the values. However, the operation of extracting the polymer from the polymerization tank requires a considerable amount of time.

[0027] By the way, in the production of polymers, many kinds of materials and many kinds of equipment are used. In addition, the time required for production is long. Therefore, there are many candidates of data that can be used by soft sensors. Therefore, it is unclear which data is preferable to use for the soft sensor, and it is difficult to use the soft sensor easily.

[0028] The prediction device, the calculation device, the manufacturing device, and the manufacturing method according to each embodiment described below with reference to the drawings are intended to reduce the number of steps required in the manufacturing process. The "prediction device" of the present disclosure predicts a "performance value" that specifies the performance of a polymer at a predetermined timing in the production of a polymer, using an observed value obtained as a value related to the production. By using the prediction device, it becomes possible to predict a performance value in the production of a polymer without actually removing the polymer from a polymerization tank and measuring it. Therefore, for example, it is possible to grasp the degree of progress of polymerization in the production of a polymer, without actually measuring the polymer.

[0029] The "arithmetic device" determines a "target timing" to be used for determining the end of polymer production by using the performance value of the polymer at a predetermined timing or the observed value obtained during the production. By using the arithmetic device, it becomes possible to determine the target timing in the production of a polymer without actually taking out the polymer from the polymerization tank and measuring its performance.

[0030] The "production method" and "production apparatus" are used to produce a polymer by utilizing predicted performance values ​​and desired target timings. In the following description, the same components are denoted by the same reference numerals and description thereof will be omitted.

[0031] The "polymer" to be manufactured in the manufacturing equipment is a compound obtained by polymerizing one or more types of monomers. In the following, the "polymer" is described as being "rubber", but is not limited to this. For example, the "rubber" can be "fluororubber" or "non-fluororubber", etc.

[0032] In one embodiment, the polymer is a fluororubber, especially a perfluororubber.

[0033] The glass transition temperature of the fluororubber is 25° C. or lower, preferably 0° C. or lower, more preferably −5° C. or lower, further preferably −10° C. or lower, and may be −20° C. or lower. Here, the glass transition temperature is determined by cooling to −75° C. and then raising the temperature at 20° C. / min to obtain a DSC curve using a differential scanning calorimeter (Hitachi Technoscience Corporation, X-DSC823e), and the glass transition temperature is determined as the temperature indicating the intersection point between an extension of the baseline before and after the secondary transition of the DSC curve and a tangent to the inflection point of the DSC curve.

[0034] Examples of the fluororubber include tetrafluoroethylene (TFE), vinylidene fluoride (VdF), and a fluororubber represented by the formula (1): CF 2 =CF-R f a (1) (In the formula, R f a -CF 3 -OR f b (R f b and the like)).

[0035] Examples of the fluororubber include perfluororubbers containing tetrafluoroethylene (TFE), such as tetrafluoroethylene (TFE) / perfluoroalkylvinyl ether-based fluororubbers, vinylidene fluoride (VdF)-based fluororubbers, TFE / propylene (Pr)-based fluororubbers, TFE / Pr / VdF-based fluororubbers, ethylene (Et) / hexafluoropropylene (HFP)-based fluororubbers, Et / HFP / VdF-based fluororubbers, Et / HFP / TFE-based fluororubbers, fluorosilicone-based fluororubbers, and fluorophosphazene-based fluororubbers.

[0036] The perfluororubber may be one made of TFE / PAVE, etc. The TFE / PAVE composition is preferably (50-90) / (50-10) (mol%), more preferably (50-80) / (50-20) (mol%), and even more preferably (55-75) / (45-25) (mol%).

[0037] In this case, examples of the PAVE include perfluoromethyl vinyl ether (PMVE) and perfluoropropyl vinyl ether (PPVE), and these can be used alone or in any combination.

[0038] The fluorine content of the fluororubber is preferably 50% by mass or more, more preferably 55% by mass or more, and even more preferably 60% by mass or more. The upper limit of the fluorine content is not particularly limited, but is preferably 71% by mass or less.

[0039] The above-mentioned fluororubbers are the main monomers, and copolymers of monomers that provide crosslinkable groups can also be used. The monomers that provide crosslinkable groups may be any monomers that can introduce appropriate crosslinkable groups depending on the manufacturing method and crosslinking system, and examples of such monomers include known polymerizable compounds containing iodine atoms, bromine atoms, carbon-carbon double bonds, cyano groups, carboxyl groups, hydroxyl groups, amino groups, and ester groups, and chain transfer agents.

[0040] Examples of the non-fluorinated rubber include diene rubbers such as acrylonitrile-butadiene rubber (NBR) or its hydrogenated product (HNBR), styrene-butadiene rubber (SBR), chloroprene rubber (CR), butadiene rubber (BR), natural rubber (NR), and isoprene rubber (IR), ethylene-propylene-termonomer copolymer rubber, silicone rubber, butyl rubber, epichlorohydrin rubber, acrylic rubber, chlorinated polyethylene (CPE), polyblends of acrylonitrile-butadiene rubber and vinyl chloride (PVC-NBR), and ethylene propylene diene rubber (EPDM).

[0041] In the following description, the "performance value" is assumed to be the "Mooney viscosity" of rubber, but is not limited thereto. Specifically, the performance value may be anything that represents the performance of the polymer. For example, the "performance value" may be any of the following: "average molecular weight", "specific gravity based on water at 4°C (hereinafter simply referred to as "specific gravity")", "hardness", "elongation", "minimum value of Cure-Last", "maximum value of Cure-Last", "Cure-Last induction time", "suitable vulcanization time of Cure-Last", "tensile strength", "100% tensile stress", "glass transition point", "thermal decomposition onset temperature", and "permanent compression set rate". The performance value may also be a value obtained by a function using a plurality of selected from these performance values.

[0042] The "target timing" is the timing at which a specific operation is performed to end the production, and is assumed to be the "timing at which a specific operation is performed to obtain the target performance value of the rubber at the end of the production". The specific operation for ending the production is, for example, stopping the input of raw materials, stopping stirring, lowering the tank pressure, starting cooling, etc. This "target timing" needs to be determined according to the situation. For example, the "target timing" can be determined according to the observed value observed as a value related to the production of the polymer. The "start" of the production is determined, for example, by the timing of the input of the first raw material. The "end" of the production is the timing at which the produced polymer can be removed or transported after the target timing is reached due to the reaching of a predetermined end condition. The "end condition" is, for example, when the polymerization substantially stops, when the temperature inside the polymerization tank reaches a predetermined value, when the pressure inside the polymerization tank reaches a predetermined value, when a predetermined time has passed since the final input, etc.

[0043] An "observation value" is a value observed in the manufacture of a polymer in the manufacture of rubber as a value related to the manufacture of the polymer, and is, for example, a measurement value measured by a sensor or the like installed in a manufacturing device, or a value (calculation result) obtained by a predetermined calculation formula using the measurement value. For example, when a temperature sensor or a pressure sensor is used, these measurement values ​​are also observed values. In addition, for example, "the total amount of a certain raw material input from the start to the present" and "the total amount of all raw materials input from the start to the present" are also observed values. Note that multiple types of observation values ​​may be used to predict performance values ​​and calculate target timing, and the number of such values ​​is not limited. Also, multiple different types of observation values ​​at the same time may be used, or a combination of these may be used.

[0044] [Embodiment 1] A manufacturing apparatus 1A according to the first embodiment will be described with reference to Figs. 1 to 7B. Fig. 1 is an example of the manufacturing apparatus 1A used for manufacturing rubber. The manufacturing apparatus 1A shown in Fig. 1 includes a prediction device 10A that predicts the Mooney viscosity, which is a performance value that specifies the performance of the rubber in the polymerization tank 3, using a soft sensor in the manufacturing of rubber manufactured by charging raw materials into the polymerization tank 3, and a calculation device 20A that determines the target timing of the manufacturing of the rubber in the polymerization tank 3 using the soft sensor. The manufacturing apparatus 1A also includes an operation unit 30 that performs a specific operation to end the current manufacturing using the target timing obtained by the calculation device 20A.

[0045] The raw materials fed into the production apparatus 1A include monomers, initiators, chain transfer agents, etc. The raw materials may be fed initially, intermittently, or continuously, but the production apparatus 1A according to the first embodiment will be described using the raw materials fed intermittently or continuously as examples.

[0046] Specifically, as shown in FIG. 1, the prediction device 10A predicts the "Mooney viscosity" which is a rubber performance value at a predetermined timing of production from the "observation value" using the Mooney viscosity prediction model M1 which is a first software sensor. The calculation device 20A obtains the "target timing" of rubber production from the "Mooney viscosity" at the predetermined timing using the target timing calculation model M2 which is a second software sensor. Then, the production device 1A can use the obtained target timing to stop the introduction of materials into the polymerization tank 3 and end the production of rubber. For example, after the target timing is reached, the production device 1A can stop the stirring in the polymerization tank 3 or stop the temperature adjustment, so that the rubber can be taken out.

[0047] The manufacturing apparatus 1A includes a polymerization tank 3 used for polymerizing rubber, and can output a control signal for controlling an agitator 31, and can receive the results of the control (e.g., the number of rotations of the agitator and the amount of current used for the rotation). The manufacturing apparatus 1A is also connected to storage tanks 41, 42 in which raw materials are stored, and can output a control signal for controlling the introduction of raw materials. The manufacturing apparatus 1A can use, for example, the pressure value in the polymerization tank 3 measured by a pressure sensor 33 as an observation value, and control the timing of introduction of raw materials from the storage tanks 41, 42 to the polymerization tank 3.

[0048] In the following, an example will be described in which a Mooney viscosity prediction model M1, which is a trained model, is used as the first soft sensor, and a target timing calculation model M2, which is a trained model, is used as the second soft sensor, but the present invention is not limited to this. The first soft sensor may simply be a function that inputs the necessary "observation value" and predicts the "Mooney viscosity" of rubber at a predetermined timing. The second soft sensor may also simply be a function that inputs the "Mooney viscosity" of rubber at a predetermined timing and the target "performance value" of the rubber to be manufactured, and calculates the "target timing".

[0049] Prediction Device As shown in FIG. 2, the prediction device 10A is an information processing device including a control unit 11, a storage unit 12, and a communication unit 13. The control unit 11 is a controller that controls the entire prediction device 10A. For example, the control unit 11 realizes processing as an acquisition unit 111 and a prediction unit 112 by reading and executing a prediction program P1 stored in the storage unit 12. In addition, the control unit 11 is not limited to a unit that realizes a predetermined function by cooperation between hardware and software, and may be a hardware circuit designed specifically to realize a predetermined function. In other words, the control unit 11 can be realized by various processors such as a CPU, an MPU, a GPU, an FPGA, a DSP, and an ASIC.

[0050] The storage unit 12 is a recording medium for recording various information. The storage unit 12 is realized, for example, by a RAM, a ROM, a flash memory, a solid state device (SSD), a hard disk, or other storage device, or by an appropriate combination of these. The storage unit 12 stores the prediction program P1 executed by the control unit 11, as well as various data used for learning and prediction. For example, the storage unit 12 stores a prediction observation value 121, an intermediate Mooney viscosity 122, a Mooney viscosity prediction model M1, and the prediction program P1. The Mooney viscosity prediction model M1 may be included in the prediction program P1.

[0051] The communication unit 13 is an interface circuit (module) for enabling data communication with an external device (not shown).

[0052] The prediction device 10A may include an input unit 14 and an output unit 15. The input unit 14 is an input means such as an operation button, a mouse, a keyboard, etc., used to input an operation signal or data. The output unit 15 is an output means such as a display, etc., used to output a processing result or data.

[0053] The acquisition unit 111 acquires an observation value observed as a value related to the production of rubber in the current production as an observation value for prediction 121. The acquisition unit 111 also causes the storage unit 12 to store the observation value for prediction 121.

[0054] At this time, the acquisition unit 111 may acquire the observation value together with time information related to the current production, and the set of the time information and the observation value may be used as the prediction observation value. The time information is typically the elapsed time from the start of the current production. Note that the time information may be time information other than the elapsed time. In other words, instead of the elapsed time, the time information at the start of production and the time information at which each observation value was observed may be used to determine the elapsed time from the start of production.

[0055] The prediction unit 112 predicts the Mooney viscosity of the rubber currently being produced at a predetermined timing from the prediction observation value acquired by the acquisition unit 111, using the relationship between the observation value obtained in the past production of the same type of rubber as the rubber currently being produced and the Mooney viscosity of the rubber at a predetermined timing in the past production. The "predetermined timing" is the timing after the raw materials are input and before the end of production, such as the timing when the input amount of a predetermined raw material reaches a predetermined value, or the timing when a predetermined time (e.g., 3 hours) has passed since the start of production. Note that this "Mooney viscosity at the predetermined timing" will be described below as the "mid-way Mooney viscosity" as necessary.

[0056] The prediction unit 112 stores the predicted mid-way Mooney viscosity 122 in the storage unit 12. Alternatively, the prediction unit 112 may output the mid-way Mooney viscosity 122 to the calculation device 20A.

[0057] Here, the prediction unit 112 can use the Mooney viscosity prediction model M1, which is a trained model trained by machine learning, to predict the mid-way Mooney viscosity 122. This Mooney viscosity prediction model M1 has learned the relationship between the learning observation values, which are observation values ​​obtained in past production of the same type of rubber as the rubber being produced, and the mid-way Mooney viscosity of the past production. Therefore, the Mooney viscosity prediction model M1 can predict the mid-way Mooney viscosity of the rubber being produced by inputting the prediction observation values ​​acquired by the acquisition unit 111. Machine learning will be described later with reference to FIG. 5A.

[0058] For example, when the Mooney viscosity prediction model M1 is a model using multiple regression analysis, the "intermediate Mooney viscosity" to be predicted becomes the "objective variable" of the regression analysis, and the "observation value" becomes the "explanatory variable" of the regression analysis. Moreover, the observation value 121 for prediction, which is the input data of the Mooney viscosity prediction model M1, may be one observation value or a combination of multiple observation values ​​selected by a genetic algorithm from multiple types of observation values ​​obtained in past production. Therefore, the observation value 121 for prediction selected by the genetic algorithm is an observation value suitable for predicting the Mooney viscosity. Specifically, the observation value is selected using a genetic algorithm so that the prediction performance of the Mooney viscosity prediction model M1 is improved when the Mooney viscosity prediction model M1 is constructed using the selected observation value.

[0059] For example, the prediction observation value 121 includes at least any one of the "agitation current value" and "agitation power value" of the agitator 31 that agitates the reaction mixture containing the raw materials in the polymerization tank 3, the "pressure value" inside the polymerization tank 3, the "input amount" of any raw material from the start of production to the present time, and the "input amount" of all raw materials from the start of production to the present time. In other words, the prediction observation value 121 may be one value selected from these multiple types, or may be a combination of multiple types of values.

[0060] The prediction observation value 121 may be a value calculated using the measurement values, in addition to the measurement values ​​actually measured by the sensors 32, 33 and the flow meters 43, 44. In this case, for example, the acquisition unit 111 calculates the prediction observation value 121 using the acquired measurement values ​​according to a predetermined calculation formula, and stores the prediction observation value 121 in the storage unit 12.

[0061] When the prediction observation value 121 includes the elapsed time along with the observation value, the prediction unit 112 predicts the mid-way Mooney viscosity of the rubber to be produced in the current production, using the relationship between the learning observation value, which is a set of the observation value in the past production and the elapsed time from the start of the past production, and the mid-way Mooney viscosity in the past production.

[0062] In this way, by predicting the in-process Mooney viscosity 122 using the prediction device 10A, it is possible to know the Mooney viscosity of the rubber being produced without going through a complicated process such as extracting the rubber from the polymerization tank 3 during production and measuring it. Since the end of rubber production can be determined using this in-process Mooney viscosity, the number of production steps can be reduced.

[0063] <Arithmetic device> As shown in Fig. 3, the calculation device 20A is an information processing device including a control unit 21, a storage unit 22, and a communication unit 23. The calculation device 20A may also include an input unit 24 and an output unit 25. For example, the control unit 21 realizes processing as the reception unit 211 and the calculation unit 212 by reading and executing a calculation program P2 stored in the storage unit 22. In addition, for example, the storage unit 22 stores the mid-way Mooney viscosity 122, the target value 221, the target timing 222, the target timing calculation model M2, and the calculation program P2. Note that the target timing calculation model M2 may be included in the calculation program P2.

[0064] The receiving unit 211 receives a performance value (intermediate Mooney viscosity) of rubber at a predetermined timing and a target Mooney viscosity of rubber in the current production. The "target Mooney viscosity" will be described below as a "target value" as necessary. For example, the intermediate Mooney viscosity 122 received by the receiving unit 211 may be predicted by the prediction device 10A. The receiving unit 211 also stores the received intermediate Mooney viscosity 122 and target value 221 in the memory unit 22.

[0065] Also, for example, when rubber with the same performance is manufactured multiple times, the calculation device 20A does not need to receive a new target value each time, but may read and use the target value 221 received in the past and stored in the memory unit 22.

[0066] The calculation unit 212 determines the target timing to be used for determining the end of the current rubber production, using the relationship between the mid-production Mooney viscosity of the same kind of rubber as the rubber being produced, the final Mooney viscosity of the rubber obtained in the past production, and the target timing of the rubber production, and the target value and mid-production Mooney viscosity received by the reception unit 211. The calculation unit 212 also outputs the determined target timing to the operation unit 30. The mid-production Mooney viscosity, final Mooney viscosity, and target timing of the past production are all actual measured values.

[0067] Here, the calculation unit 212 can use the target timing calculation model M2, which is a learned model that has been learned by machine learning, to calculate the target timing 222. This target timing calculation model M2 is obtained by learning the relationship between the past mid-way Mooney viscosity, the final Mooney viscosity, and the target timing of the same type of rubber as the rubber being manufactured by machine learning. Therefore, the target timing calculation model M2 can obtain the target timing to be used for determining the end of the manufacturing of the current rubber, in order to set the performance of the currently manufactured rubber to the target value, using the target value 221 and the mid-way Mooney viscosity 122 received by the reception unit 211. Machine learning will be described later with reference to FIG. 7A.

[0068] In this way, by calculating the target timing 222 using the calculation device 20A, it becomes possible to end the manufacturing process in a state where the Mooney viscosity of the rubber is the target. Therefore, by using the target timing 222 obtained as a result of the calculation, it is possible to reduce the variation in the Mooney viscosity of the manufactured rubber, compared to a conventional simple soft sensor. Note that even if the manufacturing is ended based on the target timing obtained using the target value by the calculation device 20A, the obtained Mooney viscosity of the rubber (final Mooney viscosity) does not necessarily match the target value, but falls within a desired range from the target value.

[0069] In the above description, an example has been given in which the receiving unit 211 receives the mid-way Mooney viscosity predicted by the prediction device 10A. However, in cases where it is possible to actually measure the rubber being produced by extracting it from the polymerization tank 3, the receiving unit 211 may receive the actually measured mid-way Mooney viscosity. In particular, in cases where an abnormality occurs in an instrument or the like that acquires observed values, and accurate observed values ​​cannot be acquired, and therefore the prediction device 10A is unable to accurately predict the mid-way Mooney viscosity, it is effective to stop using the prediction device 10A and use the mid-way Mooney viscosity of the rubber being produced that has been extracted from the polymerization tank 3.

[0070] 1, the prediction device 10A, the calculation device 20A, and the operation unit 30 are shown as separate entities, but a plurality of them may be configured by a single information processing device. For example, all may be configured by a single information processing device, or the prediction device 10A and the calculation device 20A, or the calculation device 20A and the operation unit 30 may be configured by a single information processing device.

[0071] <Manufacturing method> The rubber manufacturing process in the manufacturing apparatus 1A will be described with reference to the flowchart shown in Fig. 4. When the manufacturing apparatus 1A starts manufacturing rubber, the acquisition unit 111 of the prediction apparatus 10A acquires the prediction observation value 121 (S11). Note that the acquisition unit 111 may acquire the prediction observation value 121 by calculation using a value acquired from an external sensor or device.

[0072] The prediction unit 112 uses the prediction observation value 121 acquired in step S11 to obtain an in-process Mooney viscosity 122 of the rubber being manufactured (S12). This allows the manufacturing apparatus 1A to obtain an in-process Mooney viscosity without actually measuring it through a complicated process.

[0073] The receiving unit 211 of the calculation device 20A receives the mid-way Mooney viscosity 122 obtained in step S12 and the target value 221 of the rubber being manufactured (S13).

[0074] The calculation unit 212 uses the mid-way Mooney viscosity 122 received in step S13 and the target value 221 to determine the target timing 222 used to determine the end of the production of the rubber being produced (S14).

[0075] As a result, the manufacturing apparatus 1A continues manufacturing the rubber using the target timing 222 obtained in step S14 until the end condition is reached, and ends the manufacturing of the rubber when the condition is reached (S15).

[0076] As a result, the manufacturing apparatus 1A does not require sampling inspection, making manual inspection steps unnecessary, and therefore reducing the manufacturing process.

[0077] The above-mentioned steps S1 and S2 are executed by the prediction device 10A, and the steps S3 and S4 are executed by the calculation device 20B. If the manufacturing device 1A is capable of actually measuring the mid-way Mooney viscosity, step S3 may receive the mid-way Mooney viscosity actually measured by sampling the rubber being manufactured, and step S4 may use the actually measured mid-way Mooney viscosity to determine the target timing. In such a case, the sampled mid-way Mooney viscosity can be used to determine the target timing at which the target value is obtained from a soft sensor obtained from past experience.

[0078] Here, the manufacturing apparatus 1A may be realized by one computer, or may be realized by a combination of multiple computers connected via a network. For example, the prediction device 10A shown in FIG. 2 and the arithmetic device 20A shown in FIG. 3 do not need to be separate computers, and may be realized by the same computer. In that case, the control units 11, 21, the storage units 12, 22, the communication units 13, 23, the input units 14, 24, and the output units 15, 25 are the same. Also, for example, all or a part of the data stored in the storage unit 12 may be stored in an external recording medium connected via a network, and the prediction device 10A may be configured to use the data stored in the external recording medium.

[0079] Machine Learning 5A and 5B show an outline of the generation and use of a Mooney viscosity prediction model M1 using machine learning, and FIG. 7A and 7B show an outline of the generation and use of a target timing calculation model M2 using machine learning. "Machine learning" is a method of learning features contained in input data and generating a "model" that estimates a result corresponding to newly input data. Specifically, machine learning is performed by a "learner." A model generated in this manner is called a "learned model."

[0080] As shown in FIG. 5A, multiple sets of input data and correct answer data obtained in past rubber manufacturing are input to the "learning device". Specifically, when generating the Mooney viscosity prediction model M1, the "observation value" obtained in past rubber manufacturing is used as the input data, and the "intermediate Mooney viscosity" actually measured in past rubber manufacturing is used as the correct answer data. In this way, the learning device learns the relationship between the observation value and the intermediate Mooney viscosity, which is the relationship of the learning data set, and generates the Mooney viscosity prediction model M1, which is a learned model that represents the relationship between the observation value and the intermediate Mooney viscosity with a parameter. In addition, by using the generated Mooney viscosity prediction model M1, the desired output "intermediate Mooney viscosity" can be obtained for the new input "observation value" as shown in FIG. 5B. Therefore, the output obtained by the Mooney viscosity prediction model M1 is the "intermediate Mooney viscosity" as a predicted value, not an actual measurement value.

[0081] More specifically, in machine learning, as shown in FIG. 6, when generating a trained model, a "dataset" is used, which is formed of multiple pairs of "input data," which is an observation value obtained in past rubber production, and "ground truth data," which is the mid-way Mooney viscosity of rubber obtained in the corresponding production. At this time, a part of the "dataset" obtained in the past operation is used as a learning dataset for "learning," and the rest is used as an evaluation dataset for "evaluation," which is used to confirm the learning. The learning dataset is also called a training dataset. The evaluation dataset is also called, for example, a test dataset.

[0082] In addition, when dividing a "data set" into a "learning data set" and an "evaluation data set", it is preferable to use the older data set in the time series as the "learning data set" and the newer data set as the "evaluation data set". For example, the observed values ​​obtained in the production in the production apparatus 1A may change in the time series. For example, for observed values ​​affected by the aging of the equipment, multiple observed values ​​obtained in a close period may be more similar than observed values ​​obtained in a distant period. Therefore, newer data tends to be more similar to data obtained in the future production. In such a case, using newer observed values ​​for evaluation may enable the prediction model to be evaluated with observed values ​​similar to observed values ​​actually produced by the production apparatus 1A in the future. Therefore, for example, a certain percentage of old data obtained in the past production may be used as the learning data set and the remaining new data as the evaluation data set, thereby making it possible to evaluate the Mooney viscosity prediction model M1 with data similar to data obtained in the future production.

[0083] Also, as shown in FIG. 7A, when generating the target timing calculation model M2, the actually measured "mid-way Mooney viscosity" and "target timing" are used as input data, and the actually measured "final Mooney viscosity" is used as the correct answer data. In this way, the learning device learns the relationship between the mid-way Mooney viscosity, the target timing, and the final Mooney viscosity, which are the relationships of the learning data set, and generates the target timing calculation model M2, which is a learned model that expresses the relationship of this learning data set with parameters. As described above, since the final Mooney viscosity is the Mooney viscosity actually measured for rubber obtained in past production, it is possible to learn the relationship of what kind of performance rubber is produced in the case of each mid-way Mooney viscosity and target timing by using the learning data set shown in FIG. 7A. Then, the target timing calculation model M2 generated in this way can input the "mid-way Mooney viscosity" and the "target value" and determine the "target timing" such that the final Mooney viscosity becomes the target value, as shown in FIG. 7B. The "mid-way Mooney viscosity" input to the target timing calculation model M2 may be an actually measured value or a highly accurate predicted value. Therefore, the mid-way Mooney viscosity obtained by the Mooney viscosity prediction model M1 may be input to the target timing calculation model M2, or an actually measured mid-way Mooney viscosity may be used.

[0084] Although a description using illustrations is omitted, it is preferable that the data used to generate the target timing calculation model M2 is also selected such that a learning data set is selected from the older data and a test data set is selected from the newer data, as described above with reference to FIG.

[0085] Machine learning includes supervised learning, unsupervised learning, reinforcement learning, and the like, and the examples described above in FIG. 5A and FIG. 7A are supervised learning. The learning device can use, for example, the above-mentioned multiple regression analysis as machine learning. The learning device may also use a regression method other than multiple regression analysis (for example, Principal Component Regression (PCR), Partial Least Squares (PLS), Support Vector Regression (SVR), Decision Tree (DT), Random Forest (RF), Gaussian Process Regression (GPR), Neural Network (NN), Model Tree, etc.). The above algorithms can also be prefixed with Time Difference (TD), Just In Time (JIT), or Moving Window (MW). The learning device can also use Locally Weighted Partial Least Squares (LWPLS). The learning device may also use a combination of these methods.

[0086] [Embodiment 2] A manufacturing apparatus 1B according to the second embodiment will be described with reference to Figs. 8 to 11B. Fig. 8 is an example of a manufacturing apparatus 1B used for manufacturing rubber. The manufacturing apparatus 1B shown in Fig. 8 includes a calculation device 20B that uses a soft sensor to obtain a target timing for manufacturing rubber in the manufacturing of rubber produced by feeding raw materials into a polymerization tank 3. The manufacturing apparatus 1B also includes an operation unit 30 that performs a specific operation for ending the current manufacturing using the target timing obtained by the calculation device 20B. Note that, in the manufacturing apparatus 1B according to the second embodiment, the same configuration as the manufacturing apparatus 1A described above will be omitted by using the same drawings. Here, the manufacturing apparatus 1B will be described as one that feeds raw materials intermittently or continuously.

[0087] Specifically, as shown in Fig. 8, the calculation device 20B uses the second target timing calculation model M3, which is a third software sensor, to obtain the "target timing" for rubber production from the "observation value". Then, the production apparatus 1B can use the obtained target timing to stop feeding the materials into the polymerization tank 3 and end the production of rubber. Specifically, after the target timing is reached, the production apparatus 1B can stop stirring in the polymerization tank 3 and stop adjusting the temperature, making it possible to remove the rubber.

[0088] <Arithmetic device> As shown in Fig. 9, the calculation device 20B is an information processing device including a control unit 21, a storage unit 22, and a communication unit 23. The calculation device 20B may also include an input unit 24 and an output unit 25. For example, the control unit 21 realizes processing as the reception unit 213 and the calculation unit 214 by reading and executing the second calculation program P3 stored in the storage unit 22. For example, the storage unit 22 stores the calculation observation value 223, the target value 221, the target timing 222, the second target timing calculation model M3, and the second calculation program P3. The second target timing calculation model M3 may be included in the second calculation program P3.

[0089] The receiving unit 213 receives an observation value observed as a value related to the production of rubber in the current production as an observation value for calculation 223. Note that the observation value for calculation 223 may be the same as the above-mentioned observation value for prediction 121. The receiving unit 213 also receives a target value 221 for the current production. The receiving unit 213 also stores the received observation value for calculation 223 and target value 221 in the storage unit 22.

[0090] The calculation unit 214 uses the relationship between the observed values ​​obtained in past production of the same type of rubber as the rubber being produced, the final Mooney viscosity of the rubber produced in the past production, and the target timing of the past production to determine the target timing of the current production from the calculation observation values ​​223 and the target values ​​221 received by the reception unit 213. Note that the observed values, final Mooney viscosity, and target timing of the past production are all actual measured values.

[0091] Here, the calculation unit 214 can use the second target timing calculation model M3, which is a learned model that has been learned by machine learning, to calculate the target timing. This second target timing calculation model M3 is a model that has learned the relationship between the learning observation value, which is the observation value obtained in the past production of the same type of rubber as the rubber being produced, the final Mooney viscosity of the rubber obtained in the past production, and the target timing of the past production by machine learning. Therefore, the second target timing calculation model M3 can use the calculation observation value and the target value accepted by the acceptance unit 213 to determine the target timing to be used for determining the end of the production of the current rubber in order to set the performance of the currently produced rubber to the target value. Machine learning will be described later with reference to FIG. 11A.

[0092] In the example of FIG. 8, the arithmetic unit 20B and the operation unit 30 are shown as separate entities, but may be configured as a single information processing device.

[0093] In this way, by calculating the target timing 222 by the calculation device 20B, it becomes possible to end the production in a state where the Mooney viscosity of the rubber is the target. Therefore, by using the target timing 222 obtained as a calculation result, it is possible to reduce the process related to actual measurement. Note that even if the production is ended based on the target timing obtained by using the target value by the calculation device 20B, the obtained Mooney viscosity of the rubber (final Mooney viscosity) does not necessarily match the target value, but falls within a desired range from the target value. In addition, by using the second target timing calculation model M3, it is possible to reduce the variation in rubber quality compared to the conventional simple soft sensor.

[0094] Manufacturing process The rubber manufacturing process in the manufacturing apparatus 1B will be described with reference to the flowchart shown in Fig. 9. When the manufacturing apparatus 1B starts manufacturing rubber, the receiving unit 213 of the calculation device 20B acquires the observation value for calculation 223 and the target value 221 (S21). Note that the acquiring unit 111 may obtain the observation value for calculation 223 by calculation using a value received from an external sensor or device.

[0095] The calculation unit 214 uses the calculation observation value 223 received in step S21 and the target value 221 to determine the target timing 222 used to determine the end of the production of the rubber being produced (S22).

[0096] As a result, the manufacturing apparatus 1B continues manufacturing rubber using the calculation observation value 223 and the target timing 222 obtained in step S22 until the end condition is reached, and ends the manufacturing of rubber when the condition is reached (S5).

[0097] As a result, in the manufacturing apparatus 1B, it is possible to eliminate steps relating to actual measurement without performing sampling inspection, and it is possible to reduce variation in the quality of rubber through simple procedures.

[0098] Machine Learning 11A and 11B are used to show an outline of the generation and use of the second target timing calculation model M3 using machine learning. As shown in FIG. 11A, when the second target timing calculation model M3 is generated, the "observation value" obtained in the past rubber production and the "final Mooney viscosity" measured for the rubber obtained in the past production are used as input data, and the "target timing" measured for the past rubber production is used as the correct answer data. The learning device learns the relationship between the observation value, the final Mooney viscosity, and the target timing, which is the relationship of such a learning data set, and generates the second target timing calculation model M3, which is a trained model that expresses the relationship of this learning data set with parameters. As described above, since the final Mooney viscosity is the Mooney viscosity measured for the rubber obtained in the past production, the relationship of what kind of target timing was in the case of each observation value and the final Mooney viscosity can be expressed by using the learning data set shown in FIG. 11A. Then, the generated second target timing calculation model M3 can input the "observation value" and the "target value" and obtain the "target timing" such that the final Mooney viscosity becomes the target value, as shown in FIG. 11B.

[0099] <Effects and supplements> As described above, the above-mentioned embodiments have been described as examples of the technology disclosed in the present application. However, the technology in the present disclosure is not limited to these, and can be applied to embodiments in which modifications, substitutions, additions, omissions, etc. are appropriately made.

[0100] The prediction device, the computing device, the manufacturing device, and the manufacturing method described in all claims of the present disclosure are realized by cooperation with hardware resources, such as a processor, a memory, and a program. [Industrial Applicability]

[0101] The stain prediction device, the computing device, the manufacturing device, and the manufacturing method of the present disclosure are useful, for example, in the production of polymers. [Explanation of symbols]

[0102] 1A,1B manufacturing equipment 10A Prediction Device 20A,20B arithmetic unit 11,21 Control section 12,22 Storage section 13,23 Communications Department 14,24 Input section 15,25 Output section 111 Acquisition Department 112 Prediction Department 211,213 Reception Department 212,214 Arithmetic unit 121 Forecast Observations 122 Mooney viscosity 221 Target 222 Target Timing 223 Observation values ​​for calculation

Claims

1. A prediction device for predicting a performance value representing the performance of rubber in a polymerization tank at a predetermined timing after a raw material is charged and before the end of the production in a rubber production process, comprising: an acquisition unit that acquires, as prediction observation values, observed values ​​that are observed as values ​​related to the production of rubber in a current production of the rubber; a prediction unit that predicts a performance value of the rubber currently being manufactured at a predetermined timing from the prediction observation value acquired by the acquisition unit, using a relationship between an observation value obtained in a past production of a rubber of the same type as the rubber and a performance value of the rubber at a predetermined timing of the past production; Equipped with The performance value is any one of Mooney viscosity, hardness, elongation, Curest minimum value, Curest maximum value, Curest induction time, Curest proper vulcanization time, tensile strength, 100% tensile stress, glass transition point, thermal decomposition onset temperature, and compression set rate, The acquisition unit acquires the observed value together with an elapsed time from a start of the current production, and sets the elapsed time and the observed value as a prediction observed value; The prediction unit is a prediction device that predicts the performance value of the rubber currently being manufactured at the predetermined timing by using the prediction observation value acquired by the acquisition unit, utilizing a trained model that has been trained by machine learning on the relationship between the observation value in past production of the same type of rubber as the rubber and the learning observation value, which is a set of the elapsed time from the start of the past production, and the performance value at a predetermined timing of the past production, The trained model is generated by machine learning using older data in a time series among past observation values ​​and performance values ​​as a training data set and newer data in a time series as an evaluation data set for evaluating the results of training. Prediction device.

2. The prediction device described in claim 1, wherein the acquisition unit predicts the performance value of the rubber at the specified timing using the trained model trained using at least one observation value or performance value suitable for predicting the performance value selected by a genetic algorithm from multiple types of observation values ​​obtained in past production and performance values ​​of the rubber obtained in past production.

3. The observed values ​​include at least one of an agitation current value, an agitation power value, a pressure value in the polymerization tank, an amount of any of the raw materials introduced from the start of production to the present time, and an amount of all the raw materials introduced from the start of production to the present time, of the agitator that agitates the reaction mixture containing the raw materials in the polymerization tank. The prediction device according to claim 1 .

4. 4. The prediction device according to claim 1, wherein the predetermined timing is a timing when an input amount of a predetermined raw material for the rubber to be produced reaches a predetermined value, or a timing when a predetermined time has elapsed since the start of production.

Images