JP7263680B2 - Temperature information estimation method, temperature information estimation model generation method, apparatus, and program - Google Patents

Description

The present disclosure relates to a temperature information estimation method, a temperature information estimation model generation method, an apparatus, and a program.

Conventionally, a simulation device for a screw extruder is known (see Patent Literature 1, for example). This simulation device calculates the distribution of filling rate, pressure, temperature, solid phase occupancy, and residence time inside the extruder from the configuration and operating conditions of the extruder and the physical properties of the resin.

Also, there is known a simulation device that efficiently realizes low-dimensional flow analysis and high-dimensional flow analysis under the same operating conditions of the kneading device (see, for example, Patent Document 2). This simulation device is an extruder simulation device that analyzes the flow of materials. Perform low-dimensional flow analysis of materials in a field. In addition, after the low-dimensional flow analysis or prior to the low-dimensional flow analysis, this simulation apparatus accepts selection of a target area to be subjected to the high-dimensional flow analysis in the calculation target field, and from the low-dimensional flow analysis result , the physical quantity of the material in the target region is extracted, and high-dimensional flow analysis of the material in the target region is performed based on the extracted physical quantity and setting information.

JP 2011-173276 A JP 2016-88056 A

The techniques disclosed in Patent Literature 1 and Patent Literature 2 are techniques for calculating the temperature and the like of the material inside the extruder by simulation. However, the conditions for producing the resin composition in the screw extruder driven in the simulation may differ from the conditions for producing the resin composition in the screw extruder actually driven.

For example, when predicting the temperature inside a screw extruder, assume that a simulation program created assuming a screw manufactured by a certain manufacturing company is used. In this case, in a screw extruder that is actually driven, if a screw manufactured by a certain manufacturer is replaced with a screw manufactured by another company, the temperature inside the screw extruder that is actually driven cannot be accurately estimated. , there is a problem.

A problem of the present disclosure is a temperature information estimation method and temperature information estimation that can accurately estimate the temperature information when the resin composition is manufactured from the manufacturing condition information of the resin composition manufactured by the screw extruder. It is to provide a model generation method, apparatus, and program.

The temperature information estimation method of the present disclosure uses a screw extruder equipped with a screw to obtain manufacturing condition information for manufacturing a resin composition from a thermoplastic resin using a screw extruder equipped with a screw to convert the thermoplastic resin into a resin composition. input to a learned model for estimating temperature information when the resin composition is manufactured from manufacturing condition information for manufacturing a product, and the resin composition corresponding to the input manufacturing condition information It is a temperature information estimation method in which a computer executes processing for estimating temperature information.

Also, the manufacturing condition information of the present disclosure may include information on the screw configuration of the screw extruder.

Further, the information on the screw configuration of the present disclosure may include at least one of screw shape information and screw angle information.

In addition, the manufacturing condition information of the present disclosure includes at least one of information on the filler composition added to the resin composition, the discharge amount information of the screw extruder, and the screw rotation speed information of the screw extruder. can be

Further, the temperature information of the present disclosure may be temperatures of the resin composition at multiple locations in the screw extruder.

In addition, the learned model of the present disclosure includes manufacturing condition information of a learning resin composition manufactured from a thermoplastic resin using a screw extruder equipped with a screw, and the learning resin composition is manufactured. The model can be pre-learned based on the learning data representing the combination with the temperature information when the user is present.

Also, the trained model of the present disclosure can be a PLS (Partial Least Squares regression) model, a support vector machine model, a random forest model, a Gaussian process model, or a neural network model.

The temperature information estimation model generation method of the present disclosure includes manufacturing condition information of a learning resin composition manufactured from a thermoplastic resin using a screw extruder equipped with a screw, and when the learning resin composition is manufactured. The resin composition is produced from the production condition information of the resin composition produced from the thermoplastic resin using a screw extruder equipped with a screw based on the learning data representing the combination with the temperature information when the resin composition is produced. A temperature information estimation model generation method in which a computer executes processing for generating a trained model for estimating temperature information when the user is in the room.

The temperature information estimating device of the present disclosure uses a screw extruder equipped with a screw to obtain manufacturing condition information for manufacturing a resin composition from a thermoplastic resin using a screw extruder equipped with a screw to obtain a resin composition from a thermoplastic resin. input to a learned model for estimating temperature information when the resin composition is manufactured from manufacturing condition information for manufacturing a product, and the resin composition corresponding to the input manufacturing condition information A temperature information estimating device including an estimating unit for estimating temperature information.

The temperature information estimation model generation device of the present disclosure includes manufacturing condition information of a learning resin composition manufactured from a thermoplastic resin using a screw extruder equipped with a screw, and the learning resin composition is manufactured. The resin composition is produced from the production condition information of the resin composition produced from the thermoplastic resin using a screw extruder equipped with a screw based on the learning data representing the combination with the temperature information when the resin composition is produced. The temperature information estimation model generation device includes a generation unit that generates a trained model for estimating temperature information when the user is in the room.

The temperature information estimation program of the present disclosure uses a screw extruder equipped with a screw to obtain manufacturing condition information for manufacturing a resin composition from a thermoplastic resin using a screw extruder equipped with a screw to obtain a resin composition from a thermoplastic resin. input to a learned model for estimating temperature information when the resin composition is manufactured from manufacturing condition information for manufacturing a product, and the resin composition corresponding to the input manufacturing condition information It is a temperature information estimation program for causing a computer to execute processing for estimating temperature information.

The temperature information estimation model generation program of the present disclosure includes manufacturing condition information of a learning resin composition manufactured from a thermoplastic resin using a screw extruder equipped with a screw, and when the learning resin composition is manufactured. The resin composition is produced from the production condition information of the resin composition produced from the thermoplastic resin using a screw extruder equipped with a screw based on the learning data representing the combination with the temperature information when the resin composition is produced. A temperature information estimation model generation program for causing a computer to execute processing for generating a trained model for estimating temperature information when the user is in the room.

According to the temperature information estimation method, apparatus, and program of the present disclosure, temperature information when the resin composition is manufactured from the manufacturing condition information of the resin composition manufactured by the screw extruder can be accurately estimated. You can get the effect that

According to the temperature information estimation model generation method, apparatus, and program of the present disclosure, the temperature information when the resin composition is manufactured from the manufacturing condition information of the resin composition manufactured by the screw extruder can be accurately estimated. You can get the effect that you can get a trained model for doing.

It is a schematic diagram showing an example of composition of a temperature information presumption system of a 1st embodiment. 2 is a schematic block diagram of a computer functioning as a temperature information estimation device; FIG. It is an explanatory view for explaining a screw extruder. FIG. 3 is an explanatory diagram for explaining the temperatures of the resin composition at multiple locations in the screw extruder. FIG. 4 is an explanatory diagram for explaining learning data according to the embodiment; It is a figure which shows an example of the learning processing routine performed by a temperature information estimation apparatus. It is a figure which shows an example of the temperature information estimation processing routine performed by a temperature information estimation apparatus. It is a schematic diagram showing an example of composition of a temperature information presumption system of a 2nd embodiment. FIG. 2 shows the results of Example 1; FIG. 10 is a diagram showing the results of Example 2; FIG. 10 is a diagram showing the results of Example 3; FIG. 10 is a diagram showing the results of Example 4; It is a figure which shows the result of each Example.

Each embodiment will be described in detail below.

[First embodiment]

<System configuration of temperature information estimation system according to first embodiment>

FIG. 1 shows an example of the configuration of a temperature information estimation system 10 according to the first embodiment. The temperature information estimation system 10 of the first embodiment can be functionally represented by a configuration including an input device 12, a temperature information estimation device 14, and a display device 30, as shown in FIG. The temperature information estimation system 10 of this embodiment estimates the temperature of a resin composition produced from a thermoplastic resin by a screw extruder.

The input device 12 accepts information input from the outside. The input device 12 is implemented by, for example, a keyboard, a mouse, or an input/output device that receives input from an external device.

The temperature information estimation device 14 can be configured by a computer including a CPU, a RAM, and a ROM storing programs for executing each processing routine described later and various data.

For example, the temperature information estimation device 14 can be realized by the computer 50 shown in FIG. The computer 50 includes a CPU 51 , a memory 52 as a temporary storage area, and a non-volatile storage section 53 . The computer 50 also includes an input/output interface (I/F) 54 to which an input/output device (not shown) is connected, and a read/write (R/W) unit 55 for controlling reading and writing of data to and from a recording medium. Prepare. The computer 50 also has a network I/F 56 connected to a network such as the Internet. The CPU 51 , memory 52 , storage unit 53 , input/output I/F 54 , R/W unit 55 and network I/F 56 are connected to each other via a bus 57 .

The storage unit 53 can be implemented by a hard disk drive (HDD), solid state drive (SSD), flash memory, or the like. A program for causing the computer 50 to function is stored in the storage unit 53 as a storage medium. The CPU 51 reads out the program from the storage unit 53, develops it in the memory 52, and sequentially executes the processes of the program.

As shown in FIG. 1, the temperature information estimation device 14 functionally includes an information acquisition unit 16, a learning data storage unit 18, a generation unit 20, a trained model storage unit 22, and an estimation unit. 24.

Information output from the temperature information estimation device 14 is displayed on the display device 30 .

The temperature information estimating device 14 of the present embodiment estimates temperature information when the resin composition is being manufactured from the manufacturing condition information of the resin composition by the screw extruder.

FIG. 3 shows an explanatory diagram for explaining the screw extruder. As shown in FIG. 3, the screw extruder Se is charged with a thermoplastic resin, a filler, an additive, and the like to produce a resin composition. The thermoplastic resin, fillers, additives, and the like fed into the screw extruder Se are kneaded by screws Sc installed at various locations of the screw extruder Se to produce a resin composition. In addition, the term "resin composition" does not refer only to the resin composition itself, but also includes molded articles or moldings obtained from the resin composition.

The thermoplastic resins include polypropylene, polyethylene, polyoxymethylene, polyamide, polycarbonate, polyvinyl chloride, acrylonitrile-butadiene-styrene copolymer resin (ABS resin), acrylonitrile-styrene copolymer resin (AS resin), polyester, and one or more resins selected from the group consisting of thermoplastic elastomers and copolymer resins thereof.

For example, the screw Sc includes a segmented screw piece P and a screw shaft S, as shown in FIG. The screw configuration varies, and the temperature of the resin composition in the screw extruder varies depending on the combination of screws installed in the screw extruder, and the temperature affects the physical properties of the resin composition.

For example, as shown in Figure 4, the temperatures at locations 1, 2, 3, 4 of the screw extruder are T1, T2, T3, T4. Depending on the values of temperatures T1, T2, T3, and T4 at locations 1, 2, 3, and 4 of the screw extruder, the physical properties of the finally produced resin composition will differ. , 2, 3, 4 temperatures T1, T2, T3, T4 should be estimated accurately.

In this regard, a method of estimating the temperature of the resin composition being kneaded in the screw extruder by simulating a virtual drive of the screw extruder is known as a prior art.

However, for example, the manufacturing conditions of the screw extruder to be driven in the simulation may differ from the manufacturing conditions of the screw extruder to be actually driven.

For example, when analyzing the temperature inside a screw extruder, assume that a simulation program created assuming a screw manufactured by a certain manufacturing company is used. In this case, in a screw extruder that is actually driven, if a screw manufactured by a certain manufacturer is replaced with a screw manufactured by another company, the temperature inside the screw extruder that is actually driven cannot be accurately estimated. , there is a problem.

Therefore, it is necessary to create a new program for executing a simulation that reflects the configuration of the screw of the screw extruder that is actually driven. However, since the combinations of screw configurations are enormous, it is costly to create a simulation program for each screw configuration.

Therefore, the temperature information estimating device 14 of the present embodiment uses the manufacturing condition information for manufacturing a resin composition from a thermoplastic resin using a screw extruder equipped with a screw, and the temperature when the resin composition is manufactured. Generate a trained model to infer information. Then, the temperature information estimation device 14 of the present embodiment estimates temperature information when the resin composition is manufactured using the learned model. The temperature information is the temperature of the resin composition at multiple locations in the screw extruder.

In this embodiment, by including information about the configuration of the screw of the screw extruder in the manufacturing condition information of the resin composition, the temperature when the resin composition is manufactured when the screw configuration is It is possible to make an accurate guess as to what will happen.

A specific description will be given below.

The input device 12 receives input of learning data. The learning data of the present embodiment includes manufacturing condition information of a learning resin composition manufactured from a thermoplastic resin using a screw extruder equipped with a screw, and the learning resin composition is manufactured. It is data representing a combination of the temperature information and the time.

The manufacturing condition information of the resin composition for learning includes information on the filler composition added to the resin composition, information on the screw configuration of the screw extruder, information on the discharge amount of the screw extruder, and screw rotation speed of the screw extruder. Contains information. The information on the screw configuration of the screw extruder includes information on the shape of the screw and information on the angle of the screw. Information about the screw configuration is represented, for example, by a screw configuration Xi (i=1 to integer, screw shape and angle).

The input device 12 also receives manufacturing condition information of a resin composition for which temperature information is to be estimated (hereinafter simply referred to as "inferred target manufacturing condition information"). The production condition information to be inferred includes, in the resin composition to be inferred produced by the screw extruder, information on the configuration of the filler added to the resin composition, information on the screw configuration of the screw extruder, and discharge of the screw extruder. Quantity information and screw speed information of the screw extruder are included. The information on the screw configuration of the screw extruder includes information on the shape of the screw and information on the angle of the screw.

The information acquisition unit 16 of the temperature information estimation device 14 acquires learning data received by the input device 12 . The information acquisition unit 16 then stores the learning data in the learning data storage unit 18 .

The information acquisition unit 16 also acquires the manufacturing condition information to be inferred received by the input device 12 .

The learning data storage unit 18 stores the learning data acquired by the information acquisition unit 16 . FIG. 5 shows an example of learning data stored in the learning data storage unit 18. As shown in FIG. In the example shown in FIG. 5, multiple pieces of learning data are stored in a table format. For example, in the table shown in FIG. 5, the learning data with "ID" of "00001" has a filler configuration of "AAA1", a screw configuration of "BBB1", and a screw extruder discharge rate of "CCC1 ”, and the rotation speed of the screw extruder is “DDD1”, the temperature 1 at a certain point 1 is “t1”, the temperature 2 at another point 2 is “t2”, and another point The temperature 3 of 3 was "t3", and the temperature 4 of another location 4 was "t4". A learned model, which will be described later, is generated based on the plurality of pieces of learning data.

For example, the information listed in Table 1 below is used as the information on the filler composition. "Sample code" in the table below is identification information for identifying the filler.

When producing a resin composition by a screw extruder, in addition to talc and mica shown in Table 1, glass fiber, clay, silica, alumina, kaolin, quartz, graphite and the like are further used. good too.

Further, the shape of the filler is not particularly limited, and may be scale-like (layered), columnar, plate-like, spherical, or flat.

The aspect ratios of the fillers shown in Table 1 are specified by the following measuring methods.

[Particle size D50L (average particle size measured by laser diffraction scattering method)]

A water dispersion with a filler concentration of 0.1% by mass was prepared, and the particle size distribution (volumetric standard) was measured. In the obtained particle size distribution, the particle size at which the cumulative volume is 50% was defined as D50L.

[Particle size D50S (average particle size measured by liquid phase gravity sedimentation method)]

Prepare an aqueous dispersion with a filler concentration of 0.1% by mass, and use an X-ray transmission sedimentation particle size distribution analyzer (manufactured by Micromeritics Japan G.K., product name “SediGraphIII5120”) in accordance with ISO13317-3:2001. Particle size distribution (by volume) was measured. In the obtained particle size distribution, the particle size at which the cumulative volume is 50% was defined as D50S.

[aspect ratio]

The aspect ratio of the filler was calculated using the above D50L and D50S by the formula described in the following document (Pabst, W., Berthold, Ch., Part. Part. Syst. Char., 24, 458-463 ( 2007), Pabst, W., Berthold, Ch., Gregorova, E., J. Eur. Ceram. Soc., 27, 1759-1762 (2007)).

The generating unit 20 generates temperature information Y when the resin composition is manufactured from manufacturing condition information X for manufacturing the resin composition based on a plurality of learning data stored in the learning data storage unit 18. Generate a trained model for inference.

The generation unit 20 of the present embodiment estimates the temperature information Y when the resin composition is manufactured from the manufacturing condition information X of the resin composition by partial least squares regression (PLS: Partial Least Squares regression). A trained model for (hereinafter simply referred to as "trained PLS") is generated. Specifically, partial least squares regression provides parameters suitable for inferring temperature information. Then, the generation unit 20 stores the generated learned PLS in the learned model storage unit 22 . The learned PLS of the present embodiment is a combination of parameters obtained by partial least squares regression and a model formula by PLS.

The learned model storage unit 22 stores the learned PLS generated by the generation unit 20 .

The estimation unit 24 acquires the manufacturing condition information to be estimated acquired by the information acquisition unit 16 . Also, the estimation unit 24 reads the learned PLS stored in the learned model storage unit 22 . Then, the estimation unit 24 inputs the manufacturing condition information to be estimated to the learned PLS, and estimates the temperature information for the manufacturing condition information to be estimated.

Specifically, when the production condition information to be inferred is input to the PLS after being learned, the temperatures T1, T2, T3, and T4 at locations 1, 2, 3, and 4 of the screw extruder are output as temperature information. .

In this way, learning data in which manufacturing condition information for learning and temperature information for learning when manufacturing a resin composition by a screw extruder are associated is prepared, and learning is completed using the learning data. By generating the PLS, it is possible to obtain a model for estimating the temperature information of the resin composition when it is being manufactured by the screw extruder from the manufacturing condition information of the resin composition manufactured by the screw extruder. can.

This makes it possible to accurately estimate the temperature information during the production of the resin composition from the production condition information of the resin composition without performing a simulation according to the production condition information. For this reason, even if a program for executing a simulation according to manufacturing condition information (for example, information on the screw configuration) is not newly created, the resin composition is manufactured from the manufacturing condition information of the resin composition. Temperature information can be estimated with high accuracy.

The display device 30 displays the temperature information estimated by the estimation unit 24 as a result.

<Operation of temperature information estimation device>

Next, the operation of the temperature information estimation device 14 will be described. When each piece of learning data representing a combination of the learning manufacturing condition information and the learning temperature information is input to the temperature information estimation device 14, the information acquisition unit 16 stores the learning data in the learning data storage unit 18. store to Then, upon receiving the instruction signal for the learning process, the temperature information estimation device 14 executes the learning process routine shown in FIG.

<Learning processing routine>

In step S<b>100 , the generation unit 20 acquires each piece of learning data stored in the learning data storage unit 18 .

In step S102, the generation unit 20 generates a PLS model for estimating temperature information from manufacturing condition information based on each of the learning data acquired in step S100. Then, the generation unit 20 acquires the learned PLS.

In step S104, the generation unit 20 stores the learned PLS generated in step S102 in the learned model storage unit 22, and ends the learning processing routine.

Next, the temperature information estimation device 14 executes the temperature information estimation processing routine shown in FIG. 7 upon receiving the input of the manufacturing condition information to be estimated.

<Temperature information estimation processing routine>

In step S200, the information acquisition unit 16 acquires manufacturing condition information to be inferred.

In step S<b>202 , the estimation unit 24 reads the learned PLS stored in the learned model storage unit 22 .

In step S204, the estimation unit 24 inputs the manufacturing condition information to be estimated acquired in step S200 to the learned PLS read out in step S202 to estimate temperature information.

In step S206, the estimation unit 24 outputs the temperature information of the resin composition estimated in step S204 as a result.

As described above, the temperature information estimation device 14 according to the first embodiment uses a screw extruder equipped with a screw to obtain manufacturing condition information for manufacturing a resin composition from a thermoplastic resin using a screw extruder equipped with a screw. From the manufacturing condition information for manufacturing a resin composition from a thermoplastic resin using a machine, it is input to a learned model for estimating the temperature information when the resin composition is manufactured, and the input manufacturing conditions Infer the temperature information of the resin composition corresponding to the information. As a result, it is possible to accurately estimate the temperature information when the resin composition is being manufactured from the manufacturing condition information of the resin composition manufactured by the screw extruder. Moreover, temperature information during production of the resin composition can be accurately estimated from the production condition information of the resin composition without performing a simulation according to the production condition information.

In addition, the temperature information estimation device 14 according to the first embodiment includes manufacturing condition information of a learning resin composition manufactured from a thermoplastic resin using a screw extruder equipped with a screw, and the learning resin composition Based on the learning data representing the combination with the temperature information when is being manufactured, the resin composition from the manufacturing condition information of the resin composition manufactured from the thermoplastic resin using a screw extruder equipped with a screw Generate a trained model to infer temperature information when the is being manufactured. As a result, it is possible to obtain a learned model for estimating temperature information when the resin composition is being manufactured from the manufacturing condition information of the resin composition manufactured by a screw extruder equipped with a screw.

[Second embodiment]

Next, a second embodiment will be described. The temperature information estimation system of the second embodiment differs from that of the first embodiment in that it outputs manufacturing condition information with a small difference from target temperature information.

<System configuration of temperature information estimation system according to second embodiment>

FIG. 8 shows an example of the configuration of a temperature information estimation system 210 according to the second embodiment. The temperature information estimation system 210 of the second embodiment can be functionally represented by a configuration including the input device 12, the temperature information estimation device 214, and the display device 30, as shown in FIG.

The temperature information estimation device 214 further includes a manufacturing condition selection unit 226 in addition to the temperature information estimation device 14 of the first embodiment, as shown in FIG.

The estimating unit 24 of the second embodiment, when estimating the temperature information of the resin composition when manufactured by the screw extruder, calculates the temperature information of the resin composition for each of the plurality of pieces of manufacturing condition information. Infer.

The manufacturing condition selection unit 226 selects the temperature information corresponding to the temperature information whose difference from the target temperature information is smaller than a preset threshold among the temperature information for each of the plurality of pieces of manufacturing condition information estimated by the estimation unit 24. Output condition information. The target temperature information is preset by the user.

For example, the production condition selection unit 226 selects TG1, TG2, TG3, and TG4 as the target temperature information for certain locations 1, 2, 3, and 4 in the screw extruder, and selects the temperature information estimated by the estimation unit 24 as T1 ,T2,T3,T4, then |TG1-T1|+|TG2-T2|+|TG3-T3|+|TG4-T4| Output condition information. As a result, the manufacturing condition information that achieves the target temperature information set by the user is obtained. Furthermore, since such manufacturing condition information also includes information on the screw configuration of the screw extruder, it is possible to obtain what kind of screw configuration is used to achieve the desired temperature state.

As described above, the temperature information estimation device 214 according to the second embodiment, when estimating the temperature information of the resin composition to be manufactured, determines the temperature of the resin composition for each of the plurality of pieces of manufacturing condition information. Information is estimated, and out of the temperature information for each of the plurality of pieces of manufacturing condition information, the manufacturing condition information corresponding to temperature information whose difference from target temperature information is smaller than a preset threshold value is output. As a result, manufacturing condition information that achieves target temperature information is obtained.

Next, each example is shown. Four examples are described below.

[Example 1]

The results of Example 1 are shown in FIG. Among the results shown in FIG. 9, the dotted line represents the temperature information estimated by the learned PLS of this embodiment, and the solid line represents the measured values. The result shown in FIG. 9 is that the information “Screw” representing the screw configuration is “CACCBE” and the information “Filler” representing the filler configuration is “Filler1/Filler9/Filler10=23/3/4[w%]”. 1 to 4 at each location of the screw extruder when the information "Q" representing the discharge rate of the screw extruder is "20" and the information "Ns" representing the number of rotations of the screw is "400" Estimated and measured values of temperature information.

[Example 2]

The results of Example 2 are shown in FIG. In the results shown in FIG. 10, the information “Screw” representing the screw configuration is “CACCBE”, and the information “Filler” representing the filler configuration is “Filler1/Filler9/Filler10=22/4/4[w%]”. 1 to 4 at each location of the screw extruder when the information "Q" representing the discharge rate of the screw extruder is "25" and the information "Ns" representing the number of rotations of the screw is "300" Estimated and measured values of temperature information.

[Example 3]

The results of Example 3 are shown in FIG. In the results shown in FIG. 11, the information “Screw” representing the screw configuration is “AACCBE”, and the information “Filler” representing the filler configuration is “Filler1/Filler9/Filler10=24/3/3[w%]”. , and when the information "Q" representing the discharge rate of the screw extruder is "25" and the information "Ns" representing the number of rotations of the screw is "200", each location 1 to 4 of the screw extruder Estimated and measured values of temperature information.

[Example 4]

The results of Example 4 are shown in FIG. The result shown in FIG. 12 is that the information “Screw” representing the screw configuration is “AACCBE”, the information “Filler” representing the filler configuration is “Filler1/Filler9/Filler10=24/3/4 w%”, The temperature of each part 1 to 4 of the screw extruder when the information "Q" representing the discharge rate of the screw extruder is "20" and the information "Ns" representing the number of rotations of the screw is "400" Estimated values and measured values of information.

Next, FIG. 13 shows a graph evaluating the deviation between the measured values and the predicted values in Examples 1 to 4. In FIG. 13(a) corresponds to Example 1, FIG. 13(b) corresponds to Example 2, FIG. 13(c) corresponds to Example 3, and FIG. 13(d) corresponds to Example 4. do.

Table 2 below summarizes the above results.

As shown in Table 2, in any example, the correlation coefficient between the measured value and the predicted value is 0.9 or more. It can be seen that the temperature information during the production of the composition is estimated with high accuracy.

The present invention is not limited to the above-described embodiments, and various modifications and applications are possible without departing from the gist of the present invention.

For example, in the above-described embodiment, the case of estimating the temperature information of the resin composition from the manufacturing condition information of the resin composition using a model based on partial least squares regression has been described as an example, but it is not limited to this. do not have. Any model may be used as long as it is a trained model that estimates temperature information when a resin composition is being manufactured from information on the manufacturing conditions of the resin composition by a screw extruder. For example, using a support vector machine model, a random forest model, a Gaussian process model, or a neural network model, the temperature information of the resin composition is estimated from the manufacturing condition information of the resin composition manufactured by the screw extruder. can be

In principle, the number of screws provided in the screw extruder may be one, and as the installation location of the thermometer used when collecting learning data, one or more thermometers are optional at the installation location of the screw. is installed in Further, for example, when four screws are installed in the screw extruder, the number of thermometers may be one, but the tip is upstream from the direction in which the resin flows, and the resin comes out of the extruder. When the direction is set to the downstream side, it is better to install the thermometer on the upstream side, and it is preferable to install a plurality of thermometers.

Moreover, the resin composition produced by the screw extruder may further contain other components within a range that does not impair the effects of the present invention. Examples of other ingredients include antioxidants (phenols, amines, sulfurs, phosphorus, etc.), light stabilizers (benzotriazoles, triazines, benzophenones, benzoates, hindered amines, oxanilides, etc.). , other polymers (polyolefins, ethylene/propylene copolymers, olefin copolymers such as ethylene/1-butene copolymers, olefin copolymers such as propylene/1-butene copolymers, polystyrene, polyamides, Polycarbonate, polyacetal, polysulfone, polyphenylene oxide, fluorine resin, silicone resin, LCP, etc.), flame retardants (bromine-based, chlorine-based, phosphorus-based, antimony-based, inorganic-based, etc.), release agents, fluidity improvers, fluorescence Brighteners, plasticizers, thickeners, antistatic agents, pigments, crystal nucleating agents and the like are included.

Further, in the specification of the present application, an embodiment in which the program is pre-installed has been described, but it is also possible to store the program in a computer-readable recording medium and provide it.

10, 210 temperature information estimation system 12 input device 14, 214 temperature information estimation device 16 information acquisition unit 18 learning data storage unit 20 generation unit 22 trained model storage unit 24 estimation unit 30 display device 50 computer 226 manufacturing condition selection unit

Claims (11)

Production condition information for producing a resin composition from a thermoplastic resin using a screw extruder equipped with a screw, from production condition information for producing a resin composition from a thermoplastic resin using a screw extruder equipped with a screw, Inputting to a learned model for estimating temperature information when the resin composition is manufactured, and estimating temperature information of the resin composition corresponding to the input manufacturing condition information,
A temperature information estimation method in which a computer executes processing,
The temperature information is temperature information of the resin composition at a plurality of locations of the screw extruder,
By inputting each of the plurality of pieces of manufacturing condition information into the learned model, estimating the temperature information of the resin composition at a plurality of locations of the screw extruder for each piece of the manufacturing condition information,
The manufacturing conditions such that a sum of differences between target temperature information preset for each of the plurality of locations and the temperature information estimated for each of the plurality of locations is smaller than a preset threshold. output information,
Temperature information estimation method . The manufacturing condition information includes information on the screw configuration of the screw extruder,
The method for estimating temperature information according to claim 1. The information on the screw configuration includes at least one of screw shape information and screw angle information,
The method for estimating temperature information according to claim 2. The manufacturing condition information includes at least one of information on the filler composition added to the resin composition, information on the discharge amount of the screw extruder, and information on the screw rotation speed of the screw extruder.
The temperature information estimation method according to any one of claims 1 to 3. The learned model includes manufacturing condition information of a learning resin composition manufactured from a thermoplastic resin using a screw extruder equipped with a screw, and temperature information when the learning resin composition is manufactured. is a pre-learned model based on training data representing a combination of
The temperature information estimation method according to any one of claims 1 to 4 . The trained model is a PLS (Partial Least Squares regression) model, a support vector machine model, a random forest model, a Gaussian process model, or a neural network model,
The temperature information estimation method according to any one of claims 1 to 4 . Learning representing a combination of manufacturing condition information of a learning resin composition manufactured from a thermoplastic resin using a screw extruder equipped with a screw and temperature information when the learning resin composition is manufactured Learning to estimate temperature information when the resin composition is being manufactured from the manufacturing condition information of the resin composition manufactured from the thermoplastic resin using a screw extruder equipped with a screw based on the data for generate a finished model,
A temperature information estimation model generation method in which a computer executes processing,
The temperature information is temperature information of the resin composition at a plurality of locations of the screw extruder,
By inputting each of a plurality of pieces of manufacturing condition information into the learned model, the temperature information of the resin composition at a plurality of locations of the screw extruder is estimated for each of the plurality of pieces of manufacturing condition information. is,
The manufacturing conditions such that a sum of differences between target temperature information preset for each of the plurality of locations and the temperature information estimated for each of the plurality of locations is smaller than a preset threshold. generating the trained model that is used to output information;
Temperature information inference model generation method . Production condition information for producing a resin composition from a thermoplastic resin using a screw extruder equipped with a screw, from production condition information for producing a resin composition from a thermoplastic resin using a screw extruder equipped with a screw, an estimating unit for inputting temperature information when the resin composition is manufactured into a trained model for estimating temperature information and estimating temperature information of the resin composition corresponding to the input manufacturing condition information; ,
The temperature information is temperature information of the resin composition at a plurality of locations of the screw extruder,
The estimation unit
By inputting each of the plurality of pieces of manufacturing condition information into the learned model, estimating the temperature information of the resin composition at a plurality of locations of the screw extruder for each piece of the manufacturing condition information,
The manufacturing conditions such that a sum of differences between target temperature information preset for each of the plurality of locations and the temperature information estimated for each of the plurality of locations is smaller than a preset threshold. output information,
Temperature information guessing device. Learning representing a combination of manufacturing condition information of a learning resin composition manufactured from a thermoplastic resin using a screw extruder equipped with a screw and temperature information when the learning resin composition is manufactured Learning to estimate temperature information when the resin composition is being manufactured from the manufacturing condition information of the resin composition manufactured from the thermoplastic resin using a screw extruder equipped with a screw based on the data for a generator that generates a finished model ,
The temperature information is temperature information of the resin composition at a plurality of locations of the screw extruder,
The generating unit
By inputting each of a plurality of pieces of manufacturing condition information into the learned model, the temperature information of the resin composition at a plurality of locations of the screw extruder is estimated for each of the plurality of pieces of manufacturing condition information. is,
The manufacturing conditions such that a sum of differences between target temperature information preset for each of the plurality of locations and the temperature information estimated for each of the plurality of locations is smaller than a preset threshold. generating the trained model that is used to output information;
Temperature information inference model generator. Production condition information for producing a resin composition from a thermoplastic resin using a screw extruder equipped with a screw, from production condition information for producing a resin composition from a thermoplastic resin using a screw extruder equipped with a screw, Inputting to a learned model for estimating temperature information when the resin composition is manufactured, and estimating temperature information of the resin composition corresponding to the input manufacturing condition information,
A temperature information estimation program for causing a computer to execute processing,
The temperature information is temperature information of the resin composition at a plurality of locations of the screw extruder,
By inputting each of the plurality of pieces of manufacturing condition information into the learned model, estimating the temperature information of the resin composition at a plurality of locations of the screw extruder for each piece of the manufacturing condition information,
The manufacturing conditions such that a sum of differences between target temperature information preset for each of the plurality of locations and the temperature information estimated for each of the plurality of locations is smaller than a preset threshold. output information,
Temperature information guessing program . Learning representing a combination of manufacturing condition information of a learning resin composition manufactured from a thermoplastic resin using a screw extruder equipped with a screw and temperature information when the learning resin composition is manufactured Learning to estimate temperature information when the resin composition is being manufactured from the manufacturing condition information of the resin composition manufactured from the thermoplastic resin using a screw extruder equipped with a screw based on the data for generate a finished model,
A temperature information estimation model generation program for causing a computer to execute processing ,
The temperature information is temperature information of the resin composition at a plurality of locations of the screw extruder,
By inputting each of a plurality of pieces of manufacturing condition information into the learned model, the temperature information of the resin composition at a plurality of locations of the screw extruder is estimated for each of the plurality of pieces of manufacturing condition information. is,
The manufacturing conditions such that a sum of differences between target temperature information preset for each of the plurality of locations and the temperature information estimated for each of the plurality of locations is smaller than a preset threshold. generating the trained model that is used to output information;
Temperature information inference model generation program .

Images