Molding condition estimation method, program, estimation device, display device, and learning model generation method

Abstract

Provided are a molding condition estimation method and the like with which molding conditions can be appropriately estimated. The molding condition estimation method includes acquiring a film temperature required for a film molded by a film molding machine, and estimating a molding condition satisfying the acquired film temperature using an estimation model that estimates a molding condition for the film temperature. The estimation model is constructed on the basis of molding information during molding detected by a detection device and a film temperature predicted from the molding information, the molding information indicating the state of a film molding machine that performs extrusion molding or the state of a film molded by the film molding machine.

Description

Technical Field

[0001] The present invention relates to a method for estimating molding conditions, a program, an estimation device, a display device, and a method for generating a learning model. Background Art

[0002] There is known a film molding machine that forms a film by curing a molten resin extruded from an outlet of a mold. For the film molding machine, in order to make the formed film satisfy required specifications, it is necessary to perform a condition setting operation and adjust set values of various molding condition items to obtain molding conditions. The adjustment of these molding conditions is performed based on the experience of an operator, and in order to obtain appropriate molding conditions, trial and error is required. Thus, a technique for assisting the molding condition setting operation performed by the operator has been proposed.

[0003] For example, in Patent Document 1, an injection molding machine system is disclosed that can appropriately adjust molding conditions of an injection molding machine by a machine learning unit that learns via reinforcement learning.

[0004] Prior Art Documents

[0005] Patent Documents

[0006] Patent Document 1: Japanese Unexamined Patent Application Publication No. 2019-166702 Summary of the Invention

[0007] Problems to be Solved by the Invention

[0008] Regarding the learning model for adjusting molding conditions, sufficient research has not been conducted on the subject of considering molding information during molding.

[0009] An object of the present disclosure is to provide a molding condition estimation method and the like that can appropriately estimate molding conditions.

[0010] Means for Solving the Problems

[0011] A molding condition estimation method according to one aspect of the present disclosure is executed by a computer to perform the following processing: obtaining a required film temperature of a film formed by a film molding machine, and using an estimation model for estimating molding conditions for the film temperature to estimate molding conditions that satisfy the obtained film temperature, the estimation model being constructed based on molding information during molding detected by a detection device and a film temperature predicted from the molding information, the molding information indicating a state of the film molding machine that performs extrusion molding or a state of a film formed by the film molding machine.

[0012] A program according to an aspect of the present disclosure causes a computer to perform the following processes: obtaining a required film temperature of a film formed by a film forming machine, and using a estimation model for estimating forming conditions for the film temperature to estimate the forming conditions that satisfy the obtained film temperature, the estimation model being constructed based on forming information during forming detected by a detection device and a film temperature predicted based on the forming information, the forming information indicating the state of the film forming machine performing extrusion forming or the state of the film formed by the film forming machine.

[0013] An estimation device according to an aspect of the present disclosure includes: an obtaining unit that obtains a required film temperature of a film formed by a film forming machine; and an estimation unit that uses an estimation model for estimating forming conditions for the film temperature to estimate the forming conditions that satisfy the film temperature obtained by the obtaining unit, the estimation model being constructed based on forming information during forming detected by a detection device and a film temperature predicted based on the forming information, the forming information indicating the state of the film forming machine performing extrusion forming or the state of the film formed by the film forming machine.

[0014] A display device according to an aspect of the present disclosure includes: an obtaining unit that obtains a required film temperature of a film formed by a film forming machine; an estimation unit that uses an estimation model for estimating forming conditions for the film temperature to estimate the forming conditions that satisfy the film temperature obtained by the obtaining unit, the estimation model being constructed based on forming information during forming detected by a detection device and a film temperature predicted based on the forming information, the forming information indicating the state of the film forming machine performing extrusion forming or the state of the film formed by the film forming machine; and a display unit that displays information related to the estimated forming information.

[0015] A method for generating a learning model according to an aspect of the present disclosure obtains training data, the training data including forming information during forming detected by a detection device and a film temperature predicted based on the forming information, the forming information indicating the state of the film forming machine performing extrusion forming or the state of the film formed by the film forming machine; and generates a learning model that has been learned based on the obtained training data to output forming conditions when a film temperature is input.

[0016] According to the present disclosure, forming conditions can be appropriately estimated. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a schematic diagram of a forming machine system according to the first embodiment.

[0018] Figure 2 is a block diagram showing a structural example of a data collection device.

[0019] Figure 3 It is a block diagram showing a structural example of an information processing apparatus.

[0020] Figure 4 It is an explanatory diagram for explaining a prediction method of a temperature prediction model.

[0021] Figure 5 It is a schematic diagram showing an example of a setting screen of molding information of a temperature prediction model.

[0022] Figure 6 It is a schematic diagram showing an example of a setting screen of molding information of a temperature prediction model.

[0023] Figure 7 It is a schematic diagram showing an example of a setting screen of molding information of a temperature prediction model.

[0024] Figure 8 It is a schematic diagram showing an example of a screen representing a prediction result of a temperature prediction model.

[0025] Figure 9 It is a flowchart showing an example of processing steps executed by the information processing apparatus.

[0026] Figure 10 It is a block diagram showing a structural example of the information processing apparatus according to the second embodiment.

[0027] Figure 11 It is an explanatory diagram showing an outline of an estimation model.

[0028] Figure 12 It is a flowchart showing an example of processing steps for generating an estimation model.

[0029] Figure 13 It is a flowchart showing an example of processing steps for estimating molding conditions. Detailed Description of the Invention

[0030] The present disclosure will be specifically described with reference to the drawings showing the embodiments.

[0031] (First Embodiment)

[0032] Figure 1 It is a schematic diagram of a molding machine system 100 according to the first embodiment. The molding machine system 100 includes a film molding machine (hereinafter simply referred to as "molding machine") 1, a plurality of detection devices 2, a data collection device 3, an information processing device 4, and a display device 5.

[0033] <Molding Machine 1>

[0034] The molding machine 1 includes an extruder 11, a casting device 12, an MD stretching device 13, a TD stretching device 14, a winding machine 15, and a control device 16.

[0035] The extruder 11 is, for example, a single-screw extruder or a twin-screw extruder, etc., and includes: a cylinder 112 having a hopper 111 for inputting a resin raw material, a screw 113, and a die 114. The screw 113 is rotatably inserted into the hole of the cylinder 112, and conveys the resin raw material input into the hopper 111 in the extrusion direction ( Figure 1 the right direction in the figure), and melts and kneads it. The extruder 11 extrudes the molten resin raw material in a film shape from the narrow gap at the front end of the die 114.

[0036] The casting device 12 has a plurality of casting rolls 121, and the casting rolls 121 are used to cool and shape the high-temperature melt extruded from the die 114. The plurality of casting rolls 121 include a first roll 1211 and a second roll 1212. The first roll 1211 is, for example, a metal roll having a temperature adjustment part (not shown) for cooling the melt, and is shaft-supported below the die 114. The first roll 1211 sandwiches the film-shaped melt extruded from the die 114 between it and the second roll 1212, and together with the second roll 1212, cools the film-shaped melt in a short time and shapes it into a film (sheet) shape. The casting device 12 controls the film thickness within a specified range. In this way, an unstretched film is obtained. The temperature adjustment method of the first roll 1211 is not particularly limited, and examples thereof include methods based on heat media such as air, water, and oil, or methods based on electric heaters, dielectric heating, etc. In Figure 1 the example shown, the plurality of casting rolls 121 further include rolls for cooling or conveying the melt.

[0037] The MD stretching device 13 has a plurality of tension rolls 131, inserts the unstretched film conveyed from the casting device 12 between the tension rolls 131, and stretches it in the longitudinal direction (film feeding direction: MD). The plurality of tension rolls 131 include: a heating roll 1311 having a temperature adjustment part for heating the film, and a cooling roll 1312 having a temperature adjustment part for cooling the film. As the temperature adjustment method of the tension rolls 131, for example, the same method as that of the above-mentioned casting rolls 121 can be cited. The film is heated to a specified temperature range where it can be stretched while in contact with the heating roll 1311, and thereafter, stretching in the longitudinal direction is obtained by the rotational speed difference of the respective cooling rolls 1312. For example, the first cooling roll 1312 is used as the starting roll to perform the first stretching on the film, and then the second cooling roll 1312 is further used as the starting roll to perform the second stretching on the film. The stretching ratio in the MD direction can be adjusted by the speed ratio of the tension rolls 131. In addition, Figure 1 for a simple example, the number of the tension rolls 131 is not limited to Figure 1 the example shown.

[0038] The TD stretching device 14 laterally stretches the film that has been longitudinally stretched by the MD stretching device 13 in the width direction (film width direction: TD). The TD stretching device 14 is, for example, a stretching device of a tenter such as a clip tenter or a needle tenter, and has a heating device such as a hot air blowing device (not shown), heats the film to a range of a specified temperature at which it can be stretched, and performs lateral stretching. The TD stretching device 14 includes: a traveling mechanism including a track and a chain (not shown), and a plurality of clamps continuously mounted on the chain. The track is arranged to expand in the width direction (TD) toward the downstream direction of the film feeding direction (MD).

[0039] The clamps grip the film ends at the entrance of the TD stretching device 14, are guided by the track and travel on the track, thereby conveying the film in the film feeding direction (MD), and releasing the film at the exit of the TD stretching device 14. The film held at both ends by the clamps passes through the hot air blowing device toward the downstream direction of the film feeding direction. Through the hot air blowing devices provided on the upper side and the lower side of the traveling mechanism, heated air is blown to both sides of the film to stretch the film in the width direction. The stretching ratio in the TD direction can be adjusted by the amount of air. The film that has been stretched in the width direction is wound by a winder 15.

[0040] In this specification, the casting process refers to the process performed by the casting device 12 in the molding process performed by the molding machine 1. The MD stretching process refers to the process performed by the MD stretching device 13 in the molding process performed by the molding machine 1. The TD stretching process refers to the process performed by the TD stretching device 14 in the molding process performed by the molding machine 1.

[0041] The control device 16 is a computer that controls the operation of the molding machine 1, and includes a control unit such as a CPU (Central Processing Unit) (not shown), a transceiver unit that exchanges information with the data collection device 3, and a display unit. The control device 16 sends the operation data indicating the operation state of the molding machine 1 to the data collection device 3.

[0042] <Detection device 2>

[0043] The detection device 2 is a sensor that detects the state of the molding machine 1 and the film (resin) molded by the molding machine 1. The detection device 2 is connected to the data collection device 3 and directly or indirectly outputs the measured data obtained by detection to the data collection device 3. The measured data is data of sensor values in time series indicating the state of the molding machine 1 and the film molded by the molding machine 1 detected. The measured data can be data of at least one of the state of the molding machine 1 and the film. The detection device 2 can be pre-installed in the molding machine 1 or set later as a device necessary for the operation control of the molding machine 1.

[0044] As measurement data detected by the detection device 2, for example, temperature, length, thickness, image, weight, flow rate, position, speed, acceleration, current, voltage, pressure, time, torque, force, distortion, power consumption, etc. can be cited. These measurement data can be measured using a thermometer, an infrared sensor, a length measuring sensor, a laser sensor, an X-ray sensor, a camera, a weighing scale, a flowmeter, a position sensor, a speed sensor, an acceleration sensor, an ammeter, a voltmeter, a pressure gauge, a timer, a torque sensor, a power meter, etc.

[0045] The detection device 2 includes, for example: a first sensor 21 that detects the measurement data of the casting device 12, a second sensor 22 that detects the measurement data of the MD stretching device 13, and a third sensor 23 that detects the measurement data of the TD stretching device 14.

[0046] The first sensor 21 includes, for example, a laser sensor that detects the film width, a laser sensor that detects the film thickness, a contact thermometer or a non-contact thermal imaging camera that detects the film temperature, a contact thermometer or a non-contact thermal imaging camera that detects the temperature of the casting roll 121, a contact thermometer or a non-contact thermal imaging camera that detects the temperature of the heat medium in the temperature adjustment unit of the casting roll 121, a flowmeter that detects the flow rate of the above heat medium, etc.

[0047] The second sensor 22 includes, for example, a laser sensor that detects the film width, a laser sensor that detects the film thickness, a contact thermometer or a non-contact thermal imaging camera that detects the film temperature, a contact thermometer or a non-contact thermal imaging camera that detects the temperature of the tension roll 131, a contact thermometer or a non-contact thermal imaging camera that detects the temperature of the heat medium in the temperature adjustment unit of the tension roll 131, a flowmeter that detects the flow rate of the above heat medium, etc.

[0048] The third sensor 23 includes, for example, a laser sensor that detects the film width, a laser sensor that detects the film thickness, a contact thermometer or a non-contact thermal imaging camera that detects the film temperature, a contact thermometer or a non-contact thermal imaging camera that detects the temperature of the air blown out from the hot air blowing device, a speedometer that detects the speed of the above air, a tachometer that detects the rotational speed of the fan of the hot air blowing device, etc.

[0049] The detection device 2 is set at an appropriate position of the molding machine 1 in order to detect the measurement data at a desired passing position through the molding machine 1. In addition, the measurement data detected by the detection device 2 is not limited to the data of the sensor value directly detected by the detection device 2, and may also include the data of the calculated value indirectly calculated from the sensor value.

[0050] As measurement data detected by the detection device 2, for example, film width, film thickness, initial film temperature, temperature of the casting roll 121, heat transfer coefficient between the casting roll 121 and the film, temperature of the tension roll 131, heat transfer coefficient between the tension roll 131 and the film, temperature of the air blown out from the hot air blowing device, speed of the air blown out from the hot air blowing device, etc. are listed, but it is not limited thereto.

[0051] The above heat transfer coefficient is an example of a calculated value and can be calculated based on the temperature and flow rate of the heat medium (such as water) of the temperature adjustment parts of the casting roll 121 and the tension roll 131. Similarly, the speed of the air can be calculated based on the fan speed of the hot air blowing device.

[0052] <Data collection device 3>

[0053] Figure 2 It is a block diagram showing a structural example of the data collection device 3. The data collection device 3 is a computer and includes a control unit 31, a storage unit 32, a communication unit 33, and a data input unit 34. The storage unit 32, the communication unit 33, and the data input unit 34 are connected to the control unit 31. The data collection device 3 is, for example, a PLC (Programmable Logic Controller).

[0054] The control unit 31 includes arithmetic processing circuits such as a CPU (Central Processing Unit), a multi-core CPU, an ASIC (Application Specific Integrated Circuit), and an FPGA (Field-Programmable Gate Array), and internal storage devices such as a ROM (Read Only Memory) and a RAM (Random Access Memory). The control unit 31 collects molding information by executing the control program stored in the storage unit 32 described later, and executes the process of sending it to the information processing device 4. In addition, each functional part of the data collection device 3 can be implemented at the software level, can be implemented at the hardware level, or can be implemented by a combination thereof.

[0055] The storage unit 32 includes non-volatile memories such as a hard disk, an EEPROM (Electrically Erasable Programmable ROM), and a flash memory. The storage unit 32 stores a control program for causing a computer to perform the collection process of molding information.

[0056] The communication unit 33 is equipped with a communication module for communicating with external devices via communication networks such as LAN and the Internet. The control unit 31 can transmit and receive various information between the control device 16 and the information processing device 4 via the communication unit 33. The control unit 31 acquires the operation data of the molding machine 1 via the communication unit 33.

[0057] The data input unit 34 is an input interface for inputting the signal output from the detection device 2. The detection device 2 is connected to the data input unit 34. The control unit 31 acquires the measurement data output from the detection device 2 at any time via the data input unit 34. In addition, the data collection device 3 can also acquire the measurement data via the control device 16 and the communication unit 33.

[0058] <Information processing device 4>

[0059] Figure 3 It is a block diagram showing a structural example of the information processing device 4. The information processing device 4 corresponds to a prediction device for predicting the temperature of the film (film temperature) based on the molding information including the measurement data.

[0060] The information processing device 4 is a computer, and includes a control unit 41, a storage unit 42, a communication unit 43, a display unit 44, and an operation unit 45. The storage unit 42, the communication unit 43, the display unit 44, and the operation unit 45 are connected to the control unit 41. The information processing device 4 can be a server device connected to a network. The information processing device 4 is a local machine configured in the factory where the molding machine 1 is installed, and preferably can perform prediction processing within the factory. The information processing device 4 can be composed of multiple computers for distributed processing, can also be implemented by multiple virtual machines within a single server, or can be implemented using a cloud server.

[0061] The control unit 41 has arithmetic processing circuits such as a CPU, a multi-core CPU, an ASIC, and an FPGA, internal storage devices such as a ROM and a RAM, and I / O terminals. The control unit 41 functions as the information processing device 4 according to the present embodiment by executing the program 4P stored in the storage unit 42 described later. In addition, each functional unit of the information processing device 4 can be implemented at the software level, at the hardware level, or by a combination thereof.

[0062] The storage unit 42 includes, for example, non-volatile memories such as a hard disk, a flash memory, and an SSD (Solid State Drive). The storage unit 42 can also be an external storage device connected to the information processing device 4. The storage unit 42 stores various programs and data referred to by the control unit 41. In the present embodiment, the storage unit 42 stores the program 4P for causing the computer to execute processing related to the prediction of the film temperature, and the temperature prediction model 421 necessary for executing the program 4P.

[0063] A program (program product) including program 4P can be provided by a non-transitory recording medium 4A that records the program in a readable manner. The storage unit 42 stores the program read from the recording medium 4A by a reading device (not shown). The recording medium 4A is, for example, a magnetic disk, an optical disk, a semiconductor memory, or the like. In addition, the program can also be downloaded from an external server connected to a communication network and stored in the storage unit 42. Program 4P can be a single computer program or a program composed of multiple computer programs. In addition, it can be executed on a single computer or on multiple computers interconnected via a communication network.

[0064] The communication unit 43 includes a communication module for communicating with an external device via a network such as a LAN or the Internet. The control unit 41 can transmit and receive various information to and from the data collection device 3 via the communication unit 43.

[0065] The display unit 44 includes, for example, a display device such as a liquid crystal display or an organic EL (Electro Luminescence) display. The display unit 44 displays various information including information related to the predicted film temperature according to an instruction from the control unit 41.

[0066] The operation unit 45 is an interface for accepting user operations. The operation unit 45 includes, for example, a touch panel device built into a display, a keyboard, a mouse, a speaker, and a microphone. The operation unit 45 accepts operation inputs from the user and sends a control signal corresponding to the operation content to the control unit 41. In addition, the display unit 44 and the operation unit 45 can also be omitted.

[0067] The information processing device 4 and the data collection device 3 are not limited to independent devices. For example, the information processing device 4 can also be integrated into the data collection device 3. In addition, the control device 16 can also function as the information processing device 4.

[0068] <Display device 5>

[0069] The display device 5 predicts the film temperature based on the molding information and displays information related to the predicted film temperature. The display device 5 has the same hardware structure as the information processing device 4. Its detailed illustration and description are omitted. It is a computer and includes a control unit, a storage unit, a communication unit, a display unit, and an operation unit, etc. The storage unit includes a non-volatile memory and stores various programs and data including a control program for causing the computer to execute prediction and display processing of the film temperature. The display device 5 can be movable. In addition, the information processing device 4 can also function as the display device 5.

[0070] <Method for predicting film temperature>

[0071] In the film forming process of the information processing apparatus 4 according to the present embodiment, based on the measurement data acquired during the forming process, the predicted values of the film temperature are obtained during the forming process for the casting process, the MD stretching process, and the TD stretching process, respectively. That is, the information processing apparatus 4 predicts the film temperature during the operation of the forming machine 1.

[0072] The film temperature can be predicted for specific prediction points, but it is preferably to predict the change in the film temperature, for example. The change in the film temperature includes, for example, time change, position change, process change, etc. As the film at the starting position of each process moves in the flow direction as the process progresses, the transport time and the transport amount (the amount of position change) increase. The time change refers to the change in the film temperature as the transport time elapses from the starting time when passing through the starting position. The position change refers to the change in the film temperature due to the change in the transport amount from the starting position. The process change refers to the change in the film temperature as the degree of progress of the process. In the present embodiment, it is assumed that the time change of the film temperature is predicted.

[0073] The information processing apparatus 4 predicts the film temperature using the temperature prediction model 421 for predicting the film temperature based on the forming information including the measurement data. The temperature prediction model 421 is a model capable of predicting the film temperature corresponding to the calculation conditions of the set forming information through simulation. The temperature prediction model 421 can be, for example, CAE (Computer Aided Engineering) analysis software.

[0074] Figure 4 It is an explanatory diagram for explaining the prediction method of the temperature prediction model 421. As Figure 4 shown on the upper side, the temperature prediction model 421 unfolds the flow path in the forming machine 1 into a two-dimensional flat plate flow, and calculates the heat transfer amount and the energy balance of the heat generation amount flowing in and out between the elements by dividing the flow path between the flat plates into elements. The temperature prediction model 421 sets the initial film position of each process as the transport starting position, and predicts the film temperature at each element position by successively calculating the energy balance within each element along the transport direction.

[0075] In Figure 4 the lower side shows the i-th element. In the i-th element, since the heat generation amount accompanying the change in the film temperature is equal to the sum of the heat transfer amounts from the four directions of up, down, left, and right of the i-th element, the energy balance within the i-th element can be expressed by the following formula (1).

[0076] ΔTi(ρ×Cp×D×W×vΔt)=-h1(Ti-Ta1)-h2(Ti-Ta2)-h3(Ti-Ta3)-h4(Ti-Ta4)…(1)

[0077] Here, Ti represents the film temperature in the i-th element, ΔTi represents the change in film temperature, ρ represents the density of the film resin, Cp represents the specific heat of the film resin, D represents the thickness of the film, W represents the width of the film, v represents the velocity of the film, Δt represents the elapsed time, h1 represents the heat transfer coefficient on the left surface side of the element, Ta1 represents the temperature of the substance in contact with the left surface of the element, h2 represents the heat transfer coefficient on the right surface side of the element, Ta2 represents the temperature of the substance in contact with the right surface of the element, h3 represents the heat transfer coefficient on the lower surface side of the element, Ta3 represents the temperature of the substance in contact with the lower surface of the element, h4 represents the heat transfer coefficient on the upper surface side of the element, and Ta4 represents the temperature of the substance in contact with the upper surface of the element.

[0078] Each element can be further divided in the thickness direction of the film. For example, each element can be equally spaced and divided into three parts in the thickness direction for analysis to predict the film temperatures at the front, center, and back of the film.

[0079] In the temperature prediction model, the conveyance time at a specified passing position is calculated based on the molding information, and the time change of the film temperature is obtained by establishing a correspondence between the film temperature and the conveyance time. The temperature prediction model 421 is not limited to using the above analysis method, as long as it can predict the film temperature based on the molding information.

[0080] The information processing device 4 acquires the measurement data detected by the detection device 2 and provides the acquired measurement data as an input to the temperature prediction model 421.

[0081] The molding information that becomes the input of the temperature prediction model 421 may include the operation data of the molding machine 1. As the operation data included in the molding information, for example, the film velocity, the discharge amount of the film, the starting position coordinates of the film, the ending position coordinates of the film, the position coordinates of the casting roll 121, the position coordinates of the tension roll 131, the draw ratio, the draw angle, etc. are listed. The operation data may also include various setting data determined according to the design of the molding machine 1, or according to the measurement data and other operation data. In addition, the operation data may acquire the control value of the control device 16 or the sensor value of the actual operation status detected by the detection device 2. That is, the above examples of the operation data may also be included in the measurement data.

[0082] The molding information that becomes the input of the temperature prediction model 421 may further include resin physical properties. As the resin physical properties, for example, the thermal conductivity, specific heat, density, etc. of the resin are listed. The resin physical properties can be obtained, for example, by accepting the input from the user, or by obtaining from a specified physical property database that stores physical property information.

[0083] Figures 5 to 7It is a schematic diagram showing an example of a setting screen 440 for the molding information of the temperature prediction model 421. The setting screen 440 is a screen for setting the calculation conditions of the molding information input to the temperature prediction model 421. Using Figures 5 to 7 , the molding information for temperature prediction in each process will be specifically described.

[0084] Figure 5 An example of a setting screen for the molding information related to the temperature prediction in the casting process is shown. As Figure 5 shown, the molding information for predicting the film temperature in the casting process includes, for example, the film speed, the discharge amount of the film, the starting XY coordinates of the film (the outlet XY coordinates of the die 114), the ending XY coordinates of the film, and the operation data related to the XY coordinates of each casting roll 121, etc. The molding information also includes the measurement data related to the film width, film thickness, initial film temperature (the temperature near the starting position), the temperature of each casting roll 121, and the heat transfer coefficient between each casting roll 121 and the film.

[0085] The molding information may further include the setting data related to the air temperature during air transportation, the heat transfer coefficient of the air, the roll diameter of each casting roll 121, the holding state of the next casting roll 121, the ambient temperature on the opposite side of the roll, the heat transfer coefficient on the opposite side of the roll, etc., as well as the resin physical properties. In this specification, the roll surface refers to the surface of the film in contact with the roll, and the opposite side of the roll refers to the side of the film opposite to the above roll surface.

[0086] In Figure 5 , the black circles included in the diagram showing the equipment structure are the specified passing positions, and the film is transported through the passing positions in the order of the circle numbers. For the circle numbers, the transportation amount (the change amount of the position) from the starting position to the passing position and the transportation time elapsed until passing through the passing position are correspondingly displayed.

[0087] Figure 6 An example of a setting screen for the molding information related to the temperature prediction in the MD stretching process is shown. The molding information for predicting the film temperature in the MD stretching process includes, for example, the initial film speed (the speed near the starting position), the discharge amount of the film, the stretching ratio of the first stretching, the film speed after the first stretching, the stretching ratio of the second stretching, the film speed after the second stretching, and the operation data related to the XY coordinates of each tension roll 131, etc. The molding information also includes the measurement data related to the film width, the film thickness before MD stretching, the initial film temperature (the temperature near the starting position), the film thickness after MD stretching, the temperature of each tension roll 131, and the heat transfer coefficient between each tension roll 131 and the film.

[0088] The forming information further includes setting data related to the air temperature during air conveyance, the heat transfer coefficient of the air, the identification information of the tension roller 131 at which the first stretching and the second stretching start, the roller diameter of each tension roller 131, the holding state of the next tension roller 131, the ambient temperature on the opposite side of the roller, the heat transfer coefficient on the opposite side of the roller, the type of the temperature adjustment unit of each tension roller 131, etc., and resin physical properties.

[0089] Figure 7 An example of a setting screen of the forming information related to the temperature prediction of the TD stretching process is shown. The forming information for predicting the film temperature in the TD stretching process includes, for example, operation data related to the film speed (production line speed), the discharge amount of the film, the stretching angle, the stretching ratio, etc. The forming information also includes measurement data related to the film width, the film thickness before TD stretching, the initial film temperature, the film thickness after TD stretching, the temperature of the air blown out from the hot air blowing device, the speed of the above air, etc. The temperature and speed of the air include the temperature and speed on the upper side of the film and the temperature and speed on the lower side of the film. When the entire conveyance section of the film in the TD stretching process is divided at regular intervals in the film feeding direction, the temperature and speed of the air can be detected for each section respectively.

[0090] The forming information may further include setting data related to the film width after TD stretching, the stretching distance, the number of sections, the section distance, the passing time, the total passing time, the heat transfer coefficient on the upper and lower sides of the film, etc., and resin physical properties.

[0091] In addition, since the discharge amount of the film can be determined by the film speed, the film width, and the film thickness, the structure may be such that only three of the above four items are set as necessary input items. Further, instead of obtaining the operation data of the film speed after the first stretching, the film speed after the first stretching can be calculated by the initial film speed and the stretching ratio of the first stretching. The same applies to the film speed after the second stretching. Instead of obtaining the measurement data of the film thickness after MD stretching, the film thickness after MD stretching can be calculated by the initial film speed, the stretching ratio of the first stretching, and the stretching ratio of the second stretching. For the film thickness after TD stretching, it can also be calculated based on the film speed and the stretching ratio.

[0092] When the information processing device 4 acquires the sensor values during molding through the data collection device 3, in the setting screen 440, the acquired sensor values or the calculated values obtained from these sensor values are automatically input into the respective input fields of the measurement data items. The information processing device 4 also inputs the resin physical properties of the resin used during molding into the respective input fields of the resin physical property items. At the same time, the operation data acquired through the control device 16 and the setting data of the molding machine 1 are input into the respective input fields of the operation data items. The information processing device 4 can directly input the molding information into the temperature prediction model 421 without going through the setting screen 440. In the temperature prediction model 421, the film temperature is predicted based on the calculation conditions of the molding information input through the setting screen 440.

[0093] Figure 8 It is a schematic diagram showing an example of a screen 441 showing the prediction result of the temperature prediction model 421. Figure 8 It shows an example of the screen 441 showing the prediction result of the film temperature in the casting process. The temperature prediction model 421 outputs the predicted value of the film temperature corresponding to the conveying time. The screen 441 showing the prediction result includes a graph with the vertical axis representing the film temperature and the horizontal axis representing the conveying time, and displays the prediction result of the film temperature in time series.

[0094] The information processing device 4 generates a graph showing the film temperatures of the front, center, and back of the film in time series based on the prediction result of the temperature prediction model 421. In addition, the temperature prediction model 421 can also predict the film temperature of only any one of the front, center, and back. The information processing device 4 displays the screen containing the generated graph through the display unit 44. In addition, the prediction result of the temperature prediction model 421 can be the predicted value of the film temperature for the conveying amount (position change) from the starting position of the casting process. In addition, Figure 5 the setting screen 440 of Figure 6 the screen 441 showing the prediction result can be structured as follows: They are arranged and displayed within one screen and displayed simultaneously on the display unit 44.

[0095] In the case of the MD stretching process, the temperature prediction model 421 predicts the temporal changes in the film temperatures of the roll surface, center, and roll opposite side of the film in the MD stretching process. In the case of the TD stretching process, the temperature prediction model 421 predicts the temporal changes in the film temperatures of the surface, center, and back of the film in the TD stretching process.

[0096] If each process is completed, the information processing device 4 uses the measured value of the molding information obtained during molding to predict the film temperature in real time. The information processing device 4 can predict the film temperature during each process. When predicting during the process, the information processing device 4 can also use the measured value during molding for the molding information that has obtained the measured value during molding in the molding information to be set; and use the estimated value or the past measured value as a reference value for the molding information that has not obtained the measured value during molding. The user can grasp the predicted value of the film temperature corresponding to the actual molding information during the operation of the molding machine 1.

[0097] Figures 5 to 7 The setting screen 440 shown can be configured to be able to select molding information items as inputs of the temperature prediction model 421. The information processing device 4 uses the setting screen 440 to accept the designation of whether each molding information needs to be input based on the operation of the user's operating unit 45. The information processing device 4 only uses the actual measured values of the molding information designated as required to be input as the input of the temperature prediction model 421, thereby predicting the film temperature. For the molding information designated as not requiring input, for example, a reference value can be used, or the molding information designated as not requiring input can be not used to predict the film temperature. Through the above structure, the user can select data that should reflect the actual molding situation, thereby improving the customization in temperature prediction.

[0098] The information processing device 4 can generate proposal information related to the proposal of the molding conditions based on the predicted value of the obtained film temperature. The proposal information includes, for example, the type of molding information that should be adjusted in order to increase or decrease the predicted film temperature, the recommended value of the molding information, etc. The information processing device 4, for example, pre-stores the correspondence between the molding information and the film temperature obtained based on the actual molding results in the past, and can determine the proposal information based on the correspondence. When generating the proposal information, the information processing device 4 can obtain the film temperature band that should be satisfied, and determine the proposal information that satisfies the obtained film temperature band. The information processing device 4 can obtain the film temperature band that should be satisfied by accepting the operation of the user's operating unit 45.

[0099] In addition, the information processing device 4 can predict the film temperature at a timing before the molding information is changed by inputting the change value for a part of the molding information and the actual measured value during molding for the remaining molding information into the temperature prediction model 421. When the prediction result satisfies the prescribed condition, the information processing device 4 can send a change instruction of the molding information to the control device 16. The information processing device 4 can generate the above-mentioned proposal information based on the obtained prediction result.

[0100] In addition, the information processing device 4 is not limited to predicting the film temperature in each process, but can also predict the film temperature of the entire molding process obtained by integrating each process. The information processing device 4 can be configured to obtain the prediction result of the film temperature of a single molding process obtained by integrating each process through the temperature prediction model 421, or can be configured to integrate the prediction results of the temperature prediction models 421 obtained in each process to generate a prediction of the entire molding process.

[0101] Figure 9 FIG. is a flowchart showing an example of the processing steps executed by the information processing device 4. The control unit 41 of the information processing device 4 executes the following processing according to the program 4P stored in the storage unit 42. The following will be described taking the casting process as an example, but the control unit 41 can also execute the same processing for the MD stretching process and the TD stretching process. For example, during molding, after the casting process is completed or at an appropriate timing during the casting process, the control unit 41 starts the following processing. The control unit 41 can start the processing in response to receiving a prediction request via the operation unit 45.

[0102] The control unit 41 of the information processing device 4, for example, refers to the physical property database stored in the storage unit 42 to obtain the resin physical properties of the raw material resin used for molding (step S11).

[0103] The control unit 41 obtains the measurement data during molding detected by the detection device 2 and the operation data during molding sent from the control device 16 through the data collection device 3 (step S12). The operation data can include design data obtained through the control device 16 or based on known equipment structures, etc. The control unit 41 can collect and obtain various molding information, or can obtain the molding information separately at the timing when the molding information is detected.

[0104] The control unit 41 inputs the molding information including the obtained resin physical properties, measurement data, and operation data into the temperature prediction model 421 (step S13). Specifically, the control unit 41 automatically inputs the obtained molding information into Figure 5 the input item column shown in the setting screen 440 described above, thereby providing input data to the temperature prediction model 421. In this case, the control unit 41 can accept the designation of whether each molding information item needs to be input based on the operation of the user's operation unit 45, and input only the measured values of the molding information for which the designation of need to input has been accepted into the temperature prediction model 421.

[0105] The control unit 41 obtains the predicted value of the film temperature output from the temperature prediction model 421 (step S14). The control unit 41 generates a screen showing the prediction result of the film temperature based on the obtained predicted value of the film temperature, and causes the display unit 44 to display the generated screen showing the prediction result (step S15). For example, the control unit 41 generates a screen showing the temporal change of the film temperature in the form of a graph.

[0106] Based on the obtained predicted value of the film temperature, the control unit 41 generates proposal information related to the proposal of the molding conditions (step S16). The proposal information includes, for example, the type of molding information to be adjusted, the recommended value of the molding information, etc. The control unit 41 causes the display unit 44 to display the screen showing the generated proposal information (step S17). The control unit 41 may also cause the display unit 44 to display a screen that simultaneously displays the prediction result and the proposal information. The control unit 41 ends the process. The control unit 41 may return the process to step S12, obtain newly detected molding information, and use the obtained new molding information to predict the film temperature again. Steps S16 and S17 may also be omitted.

[0107] The example in which the information processing device 4 executes a series of processes has been described above, but the display device 5 may also execute the same processes to perform the prediction and display of the film temperature.

[0108] According to the present embodiment, by providing a plurality of detection devices 2 in the molding machine system 100, it is possible to obtain the molding information during molding in real time. By using the obtained molding information, it is possible to accurately predict the film temperature during molding. Instead of the pre-molding prediction based on a previously obtained reference value, it is possible to predict the film temperature in real time during the film molding process.

[0109] Since it is possible to reflect the actual molding situation in the prediction of the film temperature, the prediction accuracy is improved compared to the case where the film temperature is predicted using only past measured values or estimated values. In film molding, since the resin needs to be melted and molded, the state of the resin changes in various ways. In addition, it includes a plurality of processes. Therefore, at each molding, the actual molding information is likely to change corresponding to the molding machine 1 and the state of the resin, and there is a risk of not matching the predicted temperature change before molding. By performing the prediction during film molding, it is possible to more accurately grasp the film temperature during molding.

[0110] By predicting the change in the film temperature, it is possible to grasp the change in the film temperature moving in the flow path. Using the temperature prediction model 421, it is possible to efficiently and accurately predict the film temperature.

[0111] (Second Embodiment)

[0112] In the second embodiment, a structure for estimating molding conditions that satisfy a desired film temperature using an estimation model will be described. The following mainly describes the differences from the first embodiment, and the same reference numerals will be given to the same structures as in the first embodiment, and the detailed description will be omitted.

[0113] Figure 10 FIG. 4 is a block diagram showing a configuration example of the information processing apparatus 4 according to the second embodiment. The information processing apparatus 4 according to the second embodiment corresponds to an estimation apparatus that estimates the molding conditions of the molding machine 1 that satisfies the desired film temperature. The molding conditions refer to the molding information that can be an adjustment target of the condition setting operation in the molding information.

[0114] In the storage unit 42 of the information processing apparatus 4, in addition to the program 4P for causing the computer to execute processing related to the estimation of the molding conditions and the above-described temperature prediction model 421, an estimation model 422 and a molding DB (DataBase) 423 are also stored.

[0115] The molding DB 423 is a database that stores the molding information and the predicted results of the film temperature in the prediction process of the film temperature using the temperature prediction model 421. In the molding DB 423, for example, records associating various molding information with information such as the predicted film temperature value are stored.

[0116] The display device 5 according to the second embodiment also stores information corresponding to the estimation model 422 and the molding DB 423 in the storage unit.

[0117] Regarding the molding process performed under various conditions, the information processing apparatus 4 collects the predicted results of the film temperature obtained by performing the prediction process described in the first embodiment and the molding information that becomes the calculation conditions, and stores them in the molding DB 423. In addition, the information processing apparatus 4 according to the second embodiment can generate data by executing the prediction process of the film temperature after the molding process based on the molding information obtained during the molding, and store the information in the molding DB 423. The information processing apparatus 4 uses the information stored in the molding DB 423 as training data to generate the estimation model 422.

[0118] <Estimation model 422>

[0119] Figure 11 FIG. 23 is an explanatory diagram showing an outline of the estimation model 422. The estimation model 422 estimates the molding conditions of the molding machine 1 for the film temperature. The molding conditions estimated by the estimation model 422 include, for example, the molding conditions that should be set in advance before or during the operation of the molding machine 1. The items of the molding conditions estimated by the estimation model 422 are the items of the molding information that are the input of the above-described temperature prediction model 421, and include, for example, measurement data, operation data, and resin physical properties.

[0120] The estimation model 422 of the present embodiment is a model that outputs information representing the molding conditions of the molding machine 1 when the film temperature is input, and is a machine learning model that has learned a specified training data. The estimation model 422 is, for example, a model constructed by a deep learning method using a neural network. When acquiring time series data, the estimation model 422 can be an RNN (Recurrent Neural Network). The estimation model 422 is a machine learning model that has learned a specified training data. The estimation model 422 is contemplated to be used as a program module that constitutes a part of artificial intelligence software.

[0121] The estimation model 422 includes: an input layer for inputting the film temperature, an intermediate layer (hidden layer) for extracting the feature amount of the film temperature, and an output layer for outputting the molding conditions. The intermediate layer has a plurality of nodes for extracting the feature amount of the input data, and transmits the feature amount extracted using various parameters to the output layer. When the film temperature is input to the input layer, an operation is performed in the intermediate layer by the learned parameters, and information representing the molding conditions is output from the output layer.

[0122] The film temperature input to the input layer of the estimation model 422 can be the temperature at a specified conveyance time, or data representing the change in the film temperature for a specified conveyance time or the change in the film temperature for a specified conveyance amount, etc. The film temperature input to the input layer of the estimation model 422 can be the change amount of the film temperature. When the change in the film temperature is set as the input, the film temperature input to the input layer can be input as image data obtained by graphing time series temperature data.

[0123] The output layer of the estimation model 422 has a plurality of nodes corresponding to a plurality of items related to the molding conditions. The nodes corresponding to each molding condition item respectively output values representing the molding conditions. In addition, if the molding conditions to be estimated can be obtained, the structure of the output layer is not particularly limited.

[0124] In the present embodiment, as Figure 11 shown, a variety of molding information including the above measurement data, operation data, and resin physical properties is classified into estimated object conditions and non-estimated object conditions (molding conditions), and only the estimated object conditions are estimated by the estimation model 422. Other non-estimated object conditions are used as input data for the estimation model 422. By classifying a large amount of molding information according to whether it is estimated, an estimation model 422 that can efficiently and accurately estimate the desired molding conditions can be obtained. In addition, the estimation model 422 can be structured not to use the non-estimated object conditions as input data. The estimation model 422 can be structured to regard all of the above-mentioned various molding information as non-estimated object conditions.

[0125] The conditions to be estimated in the casting process include, for example, film speed, film discharge amount, initial film temperature, starting XY coordinates of the film, ending XY coordinates of the film, XY coordinates of each casting roll 121, and temperature of each casting roll 121. Assuming a constant film thickness, since the discharge amount is determined according to the film speed, the discharge amount can be omitted from the conditions to be estimated.

[0126] The conditions to be estimated in the MD stretching process include, for example, initial film speed, film discharge amount, XY coordinates of each tension roll 131, and temperature of each tension roll 131.

[0127] The conditions to be estimated in the TD stretching process include, for example, initial film speed, film discharge amount, air temperature, and air speed.

[0128] In addition, in Figures 5 to 7 , the molding information in the molding information item marked with a black asterisk in the molding information item name indicates that it is a condition to be estimated. The molding information not marked with a black asterisk corresponds to the conditions outside the object to be estimated.

[0129] In the present embodiment, the above-mentioned estimation model 422 is prepared for each process. In the storage unit 42 of the information processing device 4, an estimation model 422 for estimating the molding conditions related to the casting process, an estimation model 422 for estimating the molding conditions related to the MD stretching process, and an estimation model 422 for estimating the molding conditions related to the TD stretching process are stored.

[0130] The structure of the estimation model 422 is not limited to Figure 11 the example shown. The estimation model 422 only needs to be able to identify the molding conditions for the film temperature. The estimation model 422 can be, for example, a model based on other learning algorithms such as Transformer, CNN (Convolution Neural Network), LSTM (Long Short-Term Memory), SVM (Support Vector Machine), and decision tree. The estimation model 422 is not limited to a machine learning model, and can also be a rule-based method or a model that derives the molding conditions through a specific formula.

[0131] The estimation model 422 can be generated in the following way: Prepare training data that establishes a correspondence between the film temperature and the conditions outside the object to be estimated and the label representing the conditions to be estimated, and use this training data to perform machine learning on an untrained neural network.

[0132] Generally, in the condition setting operation, past measured values and estimated values are used as calculation conditions to predict the film temperature, and the molding conditions are adjusted in such a way that the predicted film temperature satisfies the desired temperature. However, in film molding, since the resin needs to be melted and molded, the state of the resin changes in various ways. In addition, it includes multiple processes. Therefore, in the actual molding process, it is very likely that the molding information deviates from the past measured values and estimated values. At present, the situation is that data that can appropriately grasp the state of the actual molding process has not been fully obtained.

[0133] In the present embodiment, by providing a plurality of detection devices 2 in the molding machine system 100, molding information including molding conditions in the molding process is acquired in real time. Then, the film temperature during molding is predicted using the acquired molding information. By learning the estimation model 422 using training data, an estimation model 422 that can appropriately estimate the molding conditions corresponding to the required film temperature (required film temperature) can be generated, where the training data is generated using the predicted film temperature (predicted film temperature) and molding conditions.

[0134] Figure 12 It is a flowchart showing an example of the generation processing steps of the estimation model 422. The control unit 41 of the information processing device 4 executes the following processing according to the program 4P stored in the storage unit 42.

[0135] The control unit 41 of the information processing device 4 acquires training data based on the information stored in the molding DB 423 (step S21). The training data is a data set in which the film temperature and conditions other than the estimation target are given the conditions of the estimation target. The control unit 41 acquires a plurality of data sets as training data.

[0136] The control unit 41 generates an estimation model 422 that outputs the conditions of the estimation target (molding conditions) when the film temperature and conditions other than the estimation target are input, based on the acquired training data (step S22).

[0137] Specifically, the control unit 41 inputs multiple film temperatures and conditions outside the object to be estimated included in the training data as input data into the estimation model 422, and obtains the condition of the object to be estimated output from the estimation model 422. The control unit 41 calculates the error between the output condition of the object to be estimated and the condition of the object to be estimated included in the training data, that is, the condition of the object to be estimated as the correct answer value, through a prescribed loss function. In order to optimize (minimize or maximize) the loss function, the control unit 41 adjusts parameters such as weights between nodes, for example, using the error backpropagation method. In the stage before the start of learning, an initial setting value is given to the definition information describing the estimation model 422. If learning is completed because the error and the number of learning times satisfy a prescribed criterion, optimized parameters are obtained. If learning ends, the control unit 41 stores the definition information related to the learned estimation model 422 as the learned estimation model 422 in the storage unit 42, and ends a series of processes.

[0138] The control unit 41 executes the above processing using training data including film temperatures and forming conditions respectively related to the casting process, the MD stretching process, and the TD stretching process. In this way, three estimation models 422 are constructed that appropriately estimate the forming conditions corresponding to the film temperature involved in the casting process, the forming conditions corresponding to the film temperature involved in the MD stretching process, and the forming conditions corresponding to the film temperature involved in the TD stretching process.

[0139] When the molding machine system 100 includes multiple molding machines 1, it is preferable to generate an estimation model 422 for each molding machine 1. The information processing device 4 generates an estimation model 422 corresponding to each molding machine 1 using training data including the forming conditions obtained for each molding machine 1.

[0140] The estimation model 422 is not limited to the model generated and learned by the information processing device 4. The estimation model 422 can be a model that has been learned on an external server (not shown), sent to the information processing device 4, and stored in the storage unit 42. The estimation model 422 can be generated on an external server and then learned in the information processing device 4.

[0141] In addition, the estimation model 422 is not limited to being constructed for each process, and can also be one estimation model 422 that estimates the forming conditions for the entire molding process obtained by integrating each process. In this case, the temperature prediction model 421 can predict the film temperature for the entire molding process obtained by integrating each process.

[0142] The information processing device 4 estimates the forming conditions using the above-mentioned estimation model 422. Figure 13 It is a flowchart showing an example of the steps of the estimation process of the forming conditions.

[0143] The control unit 41 of the information processing apparatus 4 obtains the required film temperature of the film formed by the molding machine 1 by accepting the operation of the operation unit 45 of the user (step S31). The required film temperature of the film is, for example, the film temperature set by the operator and serves as the target value for the temperature of the film formed by the molding machine 1. The film temperature can be, for example, the film temperature at a specific conveyance moment, the change in the film temperature within a specified conveyance time, or the change amount of the film temperature. The control unit 41 can obtain a chart showing the change in the film temperature.

[0144] The control unit 41 obtains conditions other than the estimation target including resin physical properties, measurement data, operation data, etc. (step S32). The conditions other than the estimation target can be obtained, for example, by accepting the operation of the operation unit 45 of the user, by obtaining from a physical property database storing the physical properties of various resins, or by communicating with an external device. In steps S31 and S32, the control unit 41 can, for example, display on the display unit 44 a reception screen for the estimation conditions and use this reception screen to accept the input from the user.

[0145] The control unit 41 inputs the obtained film temperature and conditions other than the estimation target to the estimation model 422 (step S33). The control unit 41 obtains the molding conditions output from the estimation model 422 (step S34). The molding conditions output from the estimation model 422 refer to the estimation target conditions. The control unit 41 estimates the molding conditions for each process by inputting the input data to the estimation model 422 corresponding to each process.

[0146] The control unit 41 causes the display unit 44 to display information related to the obtained molding conditions (step S35) and ends a series of processes. The control unit 41, for example, generates a screen that displays the correspondence between the estimation result of the molding conditions and the film temperature as the estimation conditions and causes the display unit 44 to display the generated screen.

[0147] According to this embodiment, by using the estimation model 422, since the molding conditions that satisfy the required film temperature can be appropriately estimated, the condition setting operation is made easy. The estimation model 422 learns by using training data including measured values of molding information during molding and predicted values of the film temperature, and thus can consider the molding information during molding and accurately estimate the molding conditions that match the state of the actual molding machine 1.

[0148] By using the estimation model 422 as a machine learning model, it is possible to easily optimize the molding conditions in the film molding process where various molding conditions interact with each other.

[0149] Regarding the construction of the high-precision estimation model 422, it is important to obtain a large amount of high-quality training data. By using the data obtained through the prediction process of the film temperature for the molding conditions, training data can be efficiently obtained.

[0150] Regarding the above-described embodiments, the following remarks are further disclosed.

[0151] (Remark 1)

[0152] A method for estimating molding conditions, which is executed by a computer to perform the following processes: obtaining the film temperature required for the film formed by a film molding machine (required film temperature), using an estimation model for estimating the molding conditions for the film temperature to estimate the molding conditions that satisfy the obtained film temperature (required film temperature), the estimation model being constructed based on the molding information during molding detected by a detection device and the film temperature predicted according to the molding information (predicted film temperature), and the molding information indicating the state of the film molding machine performing extrusion molding or the film formed by the film molding machine.

[0153] (Remark 2)

[0154] According to the method for estimating molding conditions described in Remark 1 above, wherein the molding conditions are estimated by inputting the obtained film temperature into the estimation model, and the estimation model has been learned in such a way that it outputs the molding conditions when the film temperature is input.

[0155] (Remark 3)

[0156] According to the method for estimating molding conditions described in Remark 1 or Remark 2 above, wherein a temperature prediction model for predicting the film temperature based on the molding conditions is used to predict the film temperature corresponding to the molding information.

[0157] (Remark 4)

[0158] According to the method for estimating molding conditions described in any one of Remarks 1 to 3 above, wherein the molding conditions that satisfy the film temperature in the casting process, the MD stretching process, or the TD stretching process are estimated.

[0159] (Remark 5)

[0160] According to the method for estimating molding conditions described in any one of Remarks 1 to 4 above, wherein the molding conditions including at least one of the film speed, discharge amount, film temperature, film position coordinates, roller position coordinates, and roller temperature in the casting process are estimated.

[0161] (Remark 6)

[0162] According to the molding condition estimation method described in any one of Supplementary Notes 1 to 5, wherein the molding conditions including at least one of the film speed, discharge amount, position coordinates of the roll, and roll temperature in the MD stretching process are estimated.

[0163] (Supplementary Note 7)

[0164] According to the molding condition estimation method described in any one of Supplementary Notes 1 to 6, wherein the molding conditions including at least one of the film speed, discharge amount, air temperature, and air speed in the TD stretching process are estimated.

[0165] The implementation methods disclosed herein should be regarded as examples in all aspects and not as restrictive content. The technical features described in each embodiment can be combined with each other, and the scope of the present invention is intended to include all changes within the scope of the claims and the scope equivalent to the claims. The processes shown in each embodiment are not restrictive content, and within the non - contradictory scope, the order of each processing step can be changed, or multiple processes can be executed in parallel. The execution subject of each process is not restrictive content, and within the non - contradictory scope, the processing of each device can be executed by other devices.

[0166] The content described in each embodiment can be combined with each other. In addition, the independent claims and dependent claims described in the claims can be combined with each other in all possible combinations regardless of the citation form. Further, although the claims adopt the form of citing two or more other claims (multiple claim form), it is not limited thereto. It can also be described in the form of citing at least one multiple claim to record multiple claims (multiple - citing - multiple claim form).

[0167] Explanation of reference numerals

[0168] 100 Molding machine system

[0169] 1 Film molding machine

[0170] 11 Extruder

[0171] 12 Casting device

[0172] 121 Casting roll

[0173] 13 MD stretching device

[0174] 131 Tension roll

[0175] 14 TD stretching device

[0176] 15 Winder

[0177] 16 Control device

[0178] 2 Detection device

[0179] 21 First sensor

[0180] 22 Second sensor

[0181] 23 Third sensor

[0182] 3 Data collection device

[0183] 31 Control unit

[0184] 32 Storage unit

[0185] 33 Communication unit

[0186] 34 Data input unit

[0187] 4 Information processing device (estimation device)

[0188] 41 Control unit

[0189] 42 Storage unit

[0190] 43 Communication unit

[0191] 44 Display unit

[0192] 45 Operation unit

[0193] 4A Recording medium

[0194] 4P Program

[0195] 421 Temperature prediction model

[0196] 422 Estimation model

[0197] 5 Display device

Claims

1. A method for estimating molding conditions, which is executed by a computer to perform the following processes: Obtain the required film temperature of a film formed by a film forming machine; Use an estimation model for estimating molding conditions for the film temperature to estimate the molding conditions that satisfy the obtained film temperature. The estimation model is constructed based on the molding information during molding detected by a detection device and the film temperature predicted according to the molding information. The molding information represents the state of the film forming machine performing extrusion molding or the state of the film formed by the film forming machine.

2. The method for estimating molding conditions according to claim 1, wherein: The molding conditions are estimated by inputting the obtained film temperature into the estimation model, and the estimation model has been learned to output molding conditions when the film temperature is input.

3. The method for estimating molding conditions according to claim 1 or 2, wherein: A temperature prediction model for predicting the film temperature based on the molding conditions is used to predict the film temperature corresponding to the molding information.

4. The method for estimating molding conditions according to claim 1 or 2, wherein: The molding conditions that satisfy the film temperature in the casting process, the MD stretching process, or the TD stretching process are estimated.

5. The method for estimating molding conditions according to claim 1 or 2, wherein: The molding conditions including at least one of the film speed, discharge amount, film temperature, film position coordinates, roller position coordinates, and roller temperature in the casting process are estimated.

6. The method for estimating molding conditions according to claim 1 or 2, wherein: The molding conditions including at least one of the film speed, discharge amount, roller position coordinates, and roller temperature in the MD stretching process are estimated.

7. The method for estimating molding conditions according to claim 1 or 2, wherein: The molding conditions including at least one of the film speed, discharge amount, air temperature, and air speed in the TD stretching process are estimated.

8. A program that causes a computer to perform the following processes: Obtain the required film temperature of a film formed by a film forming machine; Use an estimation model for estimating molding conditions for the film temperature to estimate the molding conditions that satisfy the obtained film temperature. The estimation model is constructed based on the molding information during molding detected by a detection device and the film temperature predicted according to the molding information. The molding information represents the state of the film forming machine performing extrusion molding or the state of the film formed by the film forming machine.

9. An estimation device, comprising: An acquisition unit that acquires the required film temperature of a film formed by a film forming machine; and An estimation unit that uses an estimation model for estimating molding conditions for the film temperature to estimate the molding conditions that satisfy the film temperature acquired by the acquisition unit. The estimation model is constructed based on the molding information during molding detected by a detection device and the film temperature predicted according to the molding information. The molding information represents the state of the film forming machine performing extrusion molding or the state of the film formed by the film forming machine.

10. A display device, comprising: An acquisition unit that acquires the required film temperature of a film formed by a film forming machine; A presumption unit that presumes molding conditions that satisfy the film temperature acquired by the acquisition unit, using a presumption model that presumes molding conditions for the film temperature. The presumption model is constructed based on molding information during molding detected by a detection device and the film temperature predicted according to the molding information. The molding information represents the state of a film molding machine performing extrusion molding or the state of a film molded by the film molding machine; and A display unit that displays information related to the presumed molding conditions.

11. A method for generating a learning model, wherein Training data is acquired, the training data including molding information during molding detected by a detection device and the film temperature predicted according to the molding information. The molding information represents the state of a film molding machine performing extrusion molding or the state of a film molded by the film molding machine; A learning model is generated, the learning model having been learned based on the acquired training data to output molding conditions when a film temperature is input.

Images