Estimation method, computer program, estimation device, and estimation system

Abstract

Provided are an estimation method and the like where the state of a film molding machine can be estimated.　In this estimation method, detection data pertaining to the state of a film molding machine as detected by a detector is acquired, and an abnormality or the life span of the film molding machine is estimated by inputting the acquired detection data into an estimation model that estimates an abnormality or the life span of the film molding machine when the detection data pertaining to the state of the film molding machine has been inputted.

Description

Estimation method, computer program, estimation device, and estimation system

[0001] The present invention relates to an estimation method, a computer program, an estimation device, and an estimation system.

[0002] BACKGROUND ART Film molding machines that form a film by solidifying molten resin extruded from a die outlet are widely used, and techniques relating to such molding machines have been proposed.

[0003] For example, Patent Document 1 discloses a film forming device that can determine whether or not there is an abnormality in the winding shape of a film roll body based on an axial change in the radius of the film roll body.

[0004] Japanese Patent Application Laid-Open No. 2019-177508

[0005] However, the technology described in Patent Document 1 is a technology related to determining the state of a molded body, and is not a technology for estimating the state of a film forming machine. A technology that can estimate the state of a film forming machine is desired.

[0006] An object of the present disclosure is to provide an estimation method and the like that can estimate the state of a film forming machine.

[0007] An estimation method according to one aspect of the present disclosure acquires detection data regarding the state of a film forming machine detected by a detector, and estimates an abnormality or lifespan of the film forming machine by inputting the acquired detection data into an estimation model that estimates an abnormality or lifespan of the film forming machine when detection data regarding the state of the film forming machine is input.

[0008] A computer program according to one aspect of the present disclosure acquires detection data regarding the state of a film forming machine detected by a detector, and inputs the acquired detection data into an estimation model that estimates an abnormality or lifespan of the film forming machine when detection data regarding the state of the film forming machine is input, thereby causing a computer to execute a process of estimating an abnormality or lifespan of the film forming machine.

[0009] An estimation device according to one aspect of the present disclosure includes an acquisition unit that acquires detection data regarding the state of a film forming machine detected by a detector, and an estimation unit that estimates an abnormality or lifespan of the film forming machine by inputting the acquired detection data into an estimation model that estimates an abnormality or lifespan of the film forming machine when the detection data regarding the state of the film forming machine is input.

[0010] An estimation system according to one aspect of the present disclosure includes a film forming machine, a detector, and an estimation device. The estimation device includes an acquisition unit that acquires detection data regarding the state of the film forming machine detected by the detector, and an estimation unit that estimates an abnormality or lifespan of the film forming machine by inputting the acquired detection data into an estimation model that estimates an abnormality or lifespan of the film forming machine when detection data regarding the state of the film forming machine is input.

[0011] According to the present disclosure, the state of a film forming machine can be estimated.

[0012] FIG. 1 is a schematic diagram of an estimation system according to a first embodiment; FIG. 2 is a block diagram showing an example of the configuration of a data collection device; FIG. 3 is a block diagram showing an example of the configuration of an estimation device; FIG. 4 is a diagram showing an example of the contents of information stored in a molding information DB; FIG. 5 is an explanatory diagram showing an overview of an estimation model; FIG. 6 is a flowchart showing an example of a processing procedure executed by the estimation device; FIG. 7 is a schematic diagram showing an example of a screen showing the estimation results of an abnormality and a lifespan displayed on a terminal device; and FIG. 8 is a flowchart showing an example of a processing procedure executed by the estimation device according to a second embodiment.

[0013] The present disclosure will be described in detail with reference to the drawings illustrating embodiments thereof. (First Embodiment) Fig. 1 is a schematic diagram of an estimation system 100 according to a first embodiment. The estimation system 100 includes a film forming machine 1, a plurality of detectors 2, and an estimation device 4 as main devices. The estimation device 4 is communicably connected to a data collection device 3 and terminal devices 5a and 5b via a network N1 such as the Internet.

[0014] 1 shows one film forming machine 1 and one data collection device 3, but a plurality of data collection devices 3 (not shown) are connected to the estimation device 4 via a network N1. One or more film forming machines 1 are connected to the data collection device 3. Each data collection device 3 and one or more film forming machines 1 connected to the data collection device 3 are installed, for example, in the same factory.

[0015] The estimation device 4 is a device capable of various information processing and information transmission and reception, such as a server computer, personal computer, or quantum computer. The estimation device 4 collects molding information from each of the multiple film molding machines 1 and estimates an abnormality or lifespan of each film molding machine 1 based on the collected molding information. The molding information includes operation data and detection data, which will be described later. The estimation device 4 transmits the estimated abnormality or lifespan to the terminal devices 5a and 5b.

[0016] Terminal devices 5a and 5b are information processing terminals having communication and display functions, such as personal computers, tablet terminals, and smartphones. Terminal device 5a is a terminal used by a user of film forming machine 1. Users of film forming machine 1 include organizations such as corporations that own film forming machine 1, and operators belonging to such organizations. Terminal device 5b is a terminal used by service providers such as sales staff and maintenance staff related to the user's film forming machine 1. The number of terminal devices 5a and 5b may be two or more.

[0017] <Film Forming Machine 1> The film forming machine 1 forms a thin resin film by extrusion molding. The film forming machine 1 includes an extruder 11, a casting device 12, an MD stretching device 13, a TD stretching device 14, a winder 15, and a control device 16.

[0018] The extruder 11 is, for example, a single-screw extruder or a twin-screw extruder, and includes a raw material supply section 111 into which the resin raw material is introduced, a cylinder 112, a screw 113, and a die 114. The raw material supply section 111 includes a hopper for storing the resin raw material and a feeder for introducing the resin raw material. The resin raw material introduced into the hopper is discharged from the feeder into the cylinder 112 at a constant flow rate. The screw 113 is rotatably inserted into the bore of the cylinder 112 and transports the resin raw material discharged from the raw material supply section 111 in the extrusion direction (to the right in FIG. 1 ), where it is melted and kneaded. The screw 113 rotates at a predetermined rotation speed by a driving force output from a drive unit 115, for example, including a motor and a reducer (not shown). The extruder 11 extrudes the molten resin raw material into a film form through a narrow gap (lip) at the tip of the die 114. The die 114 is, for example, a T-die.

[0019] The casting device 12 includes multiple casting rolls 121 for cooling and shaping the high-temperature molten material extruded from the die 114. The casting rolls 121 are rotated at a predetermined rotation speed by a driving force output from a driving device 122 including, for example, a motor and a reducer (not shown). The multiple casting rolls 121 include a first roll 121a and a second roll 121b.

[0020] The first roll 121a is, for example, a metal roll having a temperature control unit (not shown) for cooling the molten material, and is axially supported below the die 114. The first roll 121a sandwiches the film-like molten material extruded from the die 114 between itself and the second roll 121b, and together with the second roll 121b, forms the film-like molten material into a film (sheet) while cooling it in a short time. The casting device 12 controls the film thickness within a predetermined range, thereby obtaining an unstretched film. The temperature of the first roll 121a can be controlled by any suitable method, including, but not limited to, a heat medium such as air, water, or oil, or an electric heater or dielectric heating. In the example shown in FIG. 1 , the multiple casting rolls 121 further include a roll for cooling or transporting the molten material.

[0021] The MD stretching device 13 includes multiple tension rolls 131. The unstretched film transported from the casting device 12 is inserted between the tension rolls 131 and stretched in the MD direction. The MD direction is the direction along the film transport direction and is also referred to as the longitudinal direction. The tension rolls 131 rotate at a predetermined rotation speed by a driving force output from a driving device 132 including, for example, a motor and a reducer (not shown).

[0022] The multiple tension rolls 131 include a heating roll having a temperature adjustment unit for heating the film and a cooling roll having a temperature adjustment unit for cooling the film. The temperature of the tension rolls 131 can be adjusted by the same method as that for the cast roll 121 described above. The film is heated to a predetermined temperature range within which it can be stretched while in contact with the heating roll, and then stretched in the MD direction by utilizing the difference in rotation speed between the cooling rolls. The stretch ratio in the MD direction can be adjusted by the speed ratio of the tension rolls 131. Note that FIG. 1 is merely an example, and the number of tension rolls 131 is not limited to the example shown in FIG. 1.

[0023] The TD stretching device 14 stretches in the TD direction the film that has been longitudinally stretched by the MD stretching device 13. The TD direction is a direction (width direction of the film) that intersects with the conveying direction of the film, and is also called the transverse direction.

[0024] The TD stretching device 14 is, for example, a tenter stretching device, and has a heating device such as a hot air blower (not shown), which heats the film to a predetermined temperature range at which the film can be stretched, and stretches the film transversely.

[0025] The TD stretching device 14 includes an oven 141 equipped with a heating device such as a hot air blower, and the oven 141 is provided with a traveling mechanism including a pair of left and right rails 142 and multiple links 143 arranged on the rails 142. The rails 142 are arranged so as to widen in the TD direction toward the downstream direction in the MD direction. The multiple links 143 form an endless chain. The endless chain made up of the multiple links 143 travels on the rails 142 at a predetermined speed by a rotational driving force output from a link driving device 145 arranged outside the oven 141.

[0026] A clip 144, which is a film gripping device, is attached to each of the multiple links 143. The number of links 143 and the number of clips 144 provided on each of the left and right rails 142 are the same. That is, the TD stretching device 14 includes a pair of left and right links 143 and a pair of left and right clips 144. The pair of links 143 and the pair of clips 144 are arranged on the rails 142 so as to be located at both the left and right ends of the film, i.e., so as to be aligned in a row along the TD direction. The pair of left and right clips 144 are adjusted in advance by synchronizing the drive devices so that there is no phase difference between the clips 144, i.e., so that the conveyance periods are the same. The TD stretching device 14 may be of a bearing clip type or a slide clip type.

[0027] At the entrance of the TD stretching device 14, the film is gripped at both ends by clips 144. The clips 144, while gripping the film, are transported together with the links 143 in the film feed direction, traveling on rails 142 to transport the film in the film feed direction. Both sides of the film in the oven are heated by air blown from hot air blowers installed above and below the traveling mechanism, and the film is stretched in the width direction as the clips 144 gripping both ends of the film move. The stretch ratio in the TD direction can be adjusted by the TD width of the rails 142. The oven 141 is divided into, for example, multiple zones in the transport direction, and the set temperature or air volume can be adjusted for each zone. The zones include a preheating zone, a stretching zone, and a heat setting zone.

[0028] The clips 144 release the film at the exit of the TD stretching device 14. The film stretched in the width direction is taken up by the winder 15 via a take-up machine (not shown). The TD stretching device 14 is not limited to a clip tenter, and may be, for example, a pin tenter having pins as film gripping devices. The above description of the structure of each part of the TD stretching device 14 is an example, and the configurations of temperature adjustment, air volume adjustment, link 143 of rail 142, etc. are not particularly limited.

[0029] The film forming machine 1 normally operates continuously without stopping, except at specific times such as when an abnormality occurs in the device or during a preset stop period.

[0030] The control device 16 is a computer that controls the operation of the film forming machine 1. The control device 16 includes a control unit such as a central processing unit (CPU) (not shown), a storage unit such as a read only memory (ROM), a random access memory (RAM), or a hard disk, a communication unit that transmits and receives information to and from external devices via wire or wirelessly, a display unit such as a liquid crystal display or an organic electroluminescence (EL) display that displays various images to the user, an operation unit that accepts operations from the user, and the like.

[0031] The control device 16 is a computer that controls the operation of the film forming machine 1. The control device 16 accepts settings of molding condition parameters for the film forming machine 1 through an operation unit or a communication unit. The control device 16 also receives detection data detected by the detector 2 from the data collection device 3 through the communication unit. The control device 16 controls the operation of the film forming machine 1 based on the accepted molding condition parameters and detection data. The control device 16 also transmits operation data indicating the operating status of the film forming machine 1 to the data collection device 3 through the communication unit. The data collection device 3 transmits the accepted operation data to the estimation device 4. Note that the operation data may be transmitted to the estimation device 4 directly from devices such as motors and inverters in the film forming machine 1 without going through the collection device 3.

[0032] The film forming machine 1 is set with forming condition parameters that define the forming conditions, and operates in accordance with the forming condition parameters. Examples of molding condition parameters include the feeder supply amount in the extruder 11, the rotation speed or rotational speed of the screw 113, the rotation speed or rotational speed of the motor of the drive device 115, and the lip opening of the die 114, the rotation speed or rotational speed of the cast roll 121 in the casting device 12, the rotation speed or rotational speed of the motor of the drive device 122, and the film discharge amount, the rotation speed or rotational speed of the tension roll 131 in the MD stretching device 13, the rotation speed or rotational speed of the motor of the drive device 132, the stretching ratio, and the film discharge amount, as well as the line speed of the film conveying line in the TD stretching device 14, the temperature in the oven 141 (particularly for each zone), the pressure in the oven 141 (particularly for each zone), the air volume or wind speed at the entrance and exit of the oven 141 (particularly the air blowing nozzles of the hot air blowing device near the entrance and exit), the stretching angle, the stretching ratio, and the film discharge amount. Instead of the film discharge rate, the film speed, film width, and film thickness may be set. The optimal molding condition parameters change as needed during operation depending on the environment of the film molding machine 1 and the state of the molded product.

[0033] Examples of the operation data of the film forming machine 1 include the feeder supply amount in the extruder 11, the temperature of the cylinder 112, the rotation speed of the screw 113, the motor rotation speed, motor torque, and motor current, the rotation speed of the casting roll 121 in the casting device 12, the rotation speed of the motor, motor torque, and motor current, the rotation speed of the tension roll 131 in the MD stretching device 13, the motor rotation speed, motor torque, and motor current, and the line speed and line tension in the TD stretching device 14. The operation data corresponds to the set value of each item, i.e., the control value by the control device 16.

[0034] <Detector 2> Detector 2 is a sensor that detects, in a time series manner, physical quantities that indicate the state of the film forming machine 1. The state of the film forming machine 1 detected by detector 2 includes the state of the film forming machine 1 itself as well as the state of the film (resin) formed by the film forming machine 1. Detector 2 is connected to data collecting device 3 by wire or wirelessly, and outputs the detection data obtained by detection to data collecting device 3 directly or indirectly.

[0035] The estimation system 100 includes a plurality of detectors 2 that detect various types of detection data. Some of the plurality of detectors 2 are connected to a data collecting device 3, and the data collecting device 3 acquires the detection data from the detectors 2. Some of the plurality of detectors 2 are connected to a control device 16, and the data collecting device 3 acquires the detection data from the detectors 2 via the control device 16. Note that in FIG. 1 , connection lines between some of the detectors 2 and the data collecting device 3 or the control device 16 are not shown.

[0036] The detectors 2 include those provided for the purpose of detecting sensor values ​​necessary for controlling the operation of the film forming machine 1, and those provided for the purpose of detecting sensor values ​​necessary for carrying out abnormality estimation or lifespan estimation of the film forming machine 1 using this estimation method. The detectors 2 may be configured separately from the film forming machine 1, or may be configured to be incorporated into the film forming machine 1.

[0037] Examples of the detector 2 include an acceleration sensor, a speed sensor, a displacement sensor, an Acoustic Emission (AE) sensor, a viscometer, a gel counter, a strain sensor, a crystal orientation sensor, an anemometer, an air volume meter, a thermometer, a surface potential sensor, a laser sensor, an infrared sensor, an X-ray sensor, a position sensor, a tension sensor, a load cell, a torque sensor, an encoder, a current sensor, a tachometer, an angle sensor, a pressure gauge, a weight scale, a length measuring sensor, a photosensor (camera), a flow meter, a voltmeter, a timer, and a wattmeter.

[0038] Examples of the detection data detected by the detector 2 include acceleration, speed, displacement, viscosity, number of gels, strain, degree of crystalline orientation, wind speed, air volume, temperature, charge amount, position, phase difference, tension, torque, rotation speed, angle, pressure, weight, length, thickness, image, flow rate, current, voltage, time, force, power consumption, etc. In this specification, the detection data detected by the detector 2 is not limited to sensor values ​​directly detected by the detector 2, but also includes calculated values ​​indirectly calculated from the sensor values.

[0039] Examples of detection data related to the extruder 11 and the detector 2 for the detection data include an acceleration sensor that detects the acceleration (vibration) of the reducer, a tachometer that detects the rotation speed of the screw 113 or the motor, a tachometer that detects the rotation speed of the screw 113 or the motor, a torque sensor that detects the torque of the motor, a current sensor that detects the current of the motor, a viscometer that detects the resin viscosity (particularly the resin viscosity immediately after discharge from the die 114), a contact thermometer or a non-contact thermographic camera that detects the temperature inside the cylinder 112 or the resin (particularly the resin immediately after discharge from the die 114), a laser displacement sensor that detects the lip opening of the die 114, and a weight scale that detects the feeder supply amount.

[0040] Examples of detection data related to the casting device 12 and the detector 2 for the detection data include, for example, an acceleration sensor that detects the acceleration (vibration) of the bearing of the casting roll 121, a speed sensor that detects the rotational speed of the casting roll 121 or the motor, a tachometer that detects the rotational speed of the casting roll 121 or the motor, a torque sensor that detects the torque of the motor, a current sensor that detects the current of the motor, a thermometer or thermographic camera that detects the temperature of the casting roll 121 or the film, a laser sensor that detects the width of the film, a laser thickness sensor that detects the thickness of the film, and a gel counter that detects the number of gels in the film (particularly the film downstream of the casting roll 121).

[0041] Examples of detection data related to the MD stretching device 13 and the detector 2 for said detection data include an acceleration sensor that detects the acceleration (vibration) of the bearing of the tension roll 131, a tachometer that detects the rotation speed of the tension roll 131 or the motor, a speed sensor that detects the rotation speed of the tension roll 131 or the motor, a torque sensor that detects the torque of the motor, a current sensor that detects the current of the motor, a thermometer or thermographic camera that detects the temperature of the tension roll 131 or the film, a laser sensor that detects the width of the film, and a laser sensor that detects the thickness of the film.

[0042] Examples of the detection data related to the TD stretching device 14 and the detector 2 for the detection data include an acceleration sensor that detects the acceleration (vibration) of the TD stretching device 14 (particularly the rails 142 near the start and end points of the stretching zone in the oven 141), a velocity sensor that detects the velocity (vibration), a displacement sensor that detects the displacement (vibration), an AE sensor that detects elastic waves, a strain sensor that detects the distortion of the clips 144, a laser sensor that detects the phase difference (shift in the passing time of the reference position) between a pair of left and right clips 144, a photo sensor or a photoelectric sensor, a thermometer or a thermography camera that detects the temperature in the oven 141 (particularly for each zone), a pressure gauge that detects the pressure in the oven 141 (particularly for each zone), and a sensor that detects the air volume at the entrance and exit of the oven 141 (particularly for the air blowing nozzle of the hot air blowing device near the entrance and exit). Examples of such sensors include an air flow meter that detects the wind speed at the entrance and exit of the oven 141 (particularly the air blowing nozzles of the hot air blowing device near the entrance and exit), an anemometer that detects the wind speed at the entrance and exit of the oven 141 (particularly the air blowing nozzles of the hot air blowing device near the entrance and exit), a pressure gauge that detects the pressure at the entrance and exit of the oven 141 (particularly the air blowing nozzles of the hot air blowing device near the entrance and exit), a tachometer that detects the fan rotation speed in the hot air blowing device, a speed sensor that detects the line speed of the film transport line, a tension sensor that detects the tension of the film transport line or clip 144, a crystal orientation sensor that detects the degree of crystal orientation of the film (particularly the film at the most downstream of the TD stretching device 14), a gel counter that detects the number of gels in the film (particularly the film at the most downstream of the TD stretching device 14), a laser sensor that detects the width of the film, and a laser sensor that detects the thickness of the film.

[0043] The detection data relating to the winder 15 and the detector 2 for the detection data include, for example, a surface potential sensor that detects the amount of charge on the film.

[0044] Detector 2 is installed in an appropriate location on or near film forming machine 1 so as to detect the state of components and film at desired positions in film forming machine 1. Detector 2 preferably has heat resistance, water resistance, oil resistance, etc., depending on the installation location. Note that detector 2 and the contents of the detection data are not limited to the above-mentioned examples. Furthermore, the above-mentioned detection data is not limited to those detected by detector 2 in combination as exemplified, and detector 2 is not limited to those for detecting the detection data in combination as exemplified.

[0045] 2 is a block diagram showing an example of the configuration 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 programmable logic controller (PLC).

[0046] The control unit 31 includes an arithmetic processing circuit such as a CPU (Central Processing Unit), a multi-core CPU, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), an internal storage device such as a ROM (Read Only Memory) and a RAM (Random Access Memory), an I / O terminal, etc. The control unit 31 executes a control program stored in a storage unit 32 (described later) to collect forming information including detection data and operation data and transmit the information to the estimation device 4. Each functional unit of the data collection device 3 may be realized by software, hardware, or a combination thereof.

[0047] The storage unit 32 includes a nonvolatile memory such as a hard disk, an EEPROM (Electrically Erasable Programmable ROM), a flash memory, etc. The storage unit 32 stores a control program for causing a computer to execute a process for collecting molding information.

[0048] The communication unit 33 includes a communication device that realizes communication via the networks N1 and N2. The communication unit 33 is connected to the control device 16 via the network N2, such as a local area network (LAN). The control unit 31 can transmit and receive various information to and from the control device 16 via the communication unit 33. The communication unit 33 is also connected to the estimation device 4 on the cloud, which is the network N1, via a relay device (not shown). The relay device is, for example, a router, a gateway, or the like. The control unit 31 can transmit and receive various information to and from the estimation device 4 via the relay device and the communication unit 33.

[0049] The data input unit 34 is an input interface that receives signals output from the detector 2. The detector 2 is connected to the data input unit 34. The control unit 31 acquires the detection data output from the detector 2 via the data input unit 34 as needed.

[0050] The data collection device 3 and the control device 16 are not limited to being separate devices, but may be configured as a single common device.

[0051] 3 is a block diagram showing an example configuration of the estimation device 4. The estimation device 4 includes a control unit 41, a storage unit 42, and a communication unit 43. The storage unit 42 and the communication unit 43 are connected to the control unit 41. The estimation device 4 may be configured to perform distributed processing using multiple computers, may be realized by multiple virtual machines provided in a single server, or may be realized using a cloud server.

[0052] The control unit 41 includes an arithmetic processing circuit such as a CPU, a multi-core CPU, an ASIC, or an FPGA, an internal storage device such as a ROM or a RAM, an I / O terminal, etc. Each functional unit of the estimation device 4 may be realized by software, by hardware, or by a combination thereof.

[0053] The storage unit 42 includes a nonvolatile memory such as a hard disk, flash memory, or SSD (Solid State Drive). The storage unit 42 may be an external storage device connected to the estimation device 4. The storage unit 42 stores various computer programs and data referenced by the control unit 41. The storage unit 42 in this embodiment stores a program 4P for causing a computer to execute processing related to estimation of an abnormality or lifespan of the film forming machine 1, as well as a molding information DB (Database) 421 and an estimation model 422 required for executing the program 4P. The molding information DB 421 is a database that stores molding information received from each data collection device 3. The estimation model 422 is a learning model generated by machine learning. The estimation model 422 is expected to be used as a program module constituting part of artificial intelligence software.

[0054] A computer program (computer program product) including the program 4P may be provided by a non-transitory recording medium 4A on which the computer program is readably recorded. The storage unit 42 stores the computer program read from the recording medium 4A by a reading device (not shown). The recording medium 4A may be, for example, a magnetic disk, an optical disk, or a semiconductor memory. Alternatively, the computer program may be downloaded from an external server connected to a communications network and stored in the storage unit 42. The program 4P may be a single computer program or may be composed of multiple computer programs, and may be executed on a single computer or on multiple computers interconnected by a communications network.

[0055] The communication unit 43 includes a communication device that realizes communication via the network N1. The control unit 41 can transmit and receive various information between the data collection device 3 and the terminal devices 5a and 5b via the communication unit 43.

[0056] <Molding Information DB 421> Figure 4 is a diagram showing an example of the contents of information stored in the molding information DB 421. The molding information DB 421 stores records that link information such as an equipment ID, date and time, operating data, and detection data, using, for example, a data ID as a key. The equipment ID represents the equipment identifier of the film molding machine 1. The date and time represent the year, month, date and time when the operating data or detection data stored as a record was obtained. The operating data includes the multiple types of operating data described above. The detection data includes the multiple types of detection data described above. Each time the estimation device 4 receives operating data and detection data from the data collection device 3, it stores the data in chronological order in the molding information DB 421. The contents of the molding information DB 421 are updated as needed.

[0057] <Estimation Model 422> Figure 5 is an explanatory diagram showing an overview of the estimation model 422. Figure 5 illustrates, as an example, the estimation model 422 composed of a first estimation model 422a and a second estimation model 422b. The first estimation model 422a is a learning model that receives molding information, including detection data and operation data of the film forming machine 1, as input, and outputs abnormality presence / absence data indicating the presence or absence of an abnormality in the film forming machine 1. The second estimation model 422b is a learning model that receives molding information, including detection data and operation data of the film forming machine 1, as input, and outputs failure probability data indicating the failure probability of the film forming machine 1 at a predetermined time point. Because the first estimation model 422a and the second estimation model 422b have similar configurations, the configuration will be described below using the first estimation model 422a as an example.

[0058] The first estimation model 422a is, for example, a neural network. The first estimation model 422a includes an input layer to which shaping information is input, an output layer that outputs anomaly presence / absence data or failure probability data, and an intermediate layer (hidden layer) that extracts features. The intermediate layer may include a convolutional layer, a pooling layer, a fully connected layer, etc. The intermediate layer has multiple nodes that extract features of the input data and passes the extracted features using various parameters to the output layer. When shaping information is input to the input layer, calculations are performed in the intermediate layer using learned parameters, and output information indicating anomaly presence / absence data or failure probability data is output from the output layer.

[0059] The input layer of the first estimation model 422a receives the above-described multiple types of detection data and driving data. The detection data includes detection data detected by the detector 2 for state estimation. The detection data may further include detection data detected by the detector 2 for driving control.

[0060] In this embodiment, various feature quantities calculated from the detection data and operation data are input as input information to the first estimation model 422a. The detection data and operation data used to calculate the feature quantities include the various detection data and operation data described above. Each of the detection data and operation data input to the first estimation model 422a may be a combination of appropriate detection data and operation data selected from the detection data and operation data exemplified above. The detection data and operation data are, for example, time-series data for a portion of the entire period from the start of operation to the time of data acquisition, or for a predetermined number of detections. The number of pieces of detection data and operation data may correspond to one cycle of the film forming machine 1. Using a group of data at multiple points in time is expected to reduce noise and improve estimation accuracy.

[0061] In addition, by inputting the features of the detection data and driving data into the first estimation model 422a, the features of each data are reflected and the estimation accuracy of the model is expected to be improved, which is preferable, but the detection data and driving data themselves may also be input into the first estimation model 422a.

[0062] Examples of feature quantities obtained from the detection data and the driving data include feature quantities representing time-series features such as RMS (root mean square) of various data, RMS (root mean square) of the time-synchronous average of various data, and the energy ratio of the time-synchronous average of various data; feature quantities representing the characteristics of frequency components such as amplitude, intensity, frequency, and image data obtained by frequency analysis such as Fourier transform, fast Fourier transform, and Hilbert spectrum analysis of various data; and values ​​based on these feature quantities such as the time derivatives and differences of the feature quantities. Different feature quantities may be calculated for each of the detection data and the driving data. The estimation device 4 stores, in advance, in the storage unit 42, a table (not shown) that associates, for each feature quantity, a formula used to calculate the feature quantity with a data item used to calculate the feature quantity.

[0063] The output layer of the first estimation model 422a has a node that outputs anomaly presence / absence data indicating whether an anomaly is present or absent. Note that the estimation of an anomaly is not limited to being indicated by the presence or absence of an anomaly. The estimation model 422 may be configured to output, for example, an anomaly degree that indicates the degree of anomaly numerically, or an anomaly level that indicates the degree of anomaly at multiple levels.

[0064] The second estimation model 422b has the same configuration as the first estimation model 422a and receives as input various feature quantities calculated from the detection data and driving data. Note that the feature quantity items input to the first estimation model 422a may be the same as or different from the feature quantity items input to the second estimation model 422b. Furthermore, the detection data and driving data items used to calculate the feature quantities input to the first estimation model 422a may be the same as or different from the detection data and driving data items input to the second estimation model 422b. The second estimation model 422b may also be configured to receive anomaly presence / absence data estimated by the first estimation model 422a as an additional input element.

[0065] The output layer of the second estimation model 422b has a node that outputs failure probability data. The failure probability data represents the failure probability of the film forming machine 1 at a future time point a predetermined period from the present, such as the probability that the film forming machine 1 will break down in three months. The failure probability represents the lifespan of the film forming machine 1. Note that the estimation model 422 may output a numerical value indicating the remaining lifespan of the film forming machine 1 (how long it will take for the film forming machine 1 to break down) as an estimate of the lifespan.

[0066] The first estimation model 422a can be generated by preparing training data in which data indicating the presence or absence of an abnormality is labeled for feature quantities obtained from the detection data and operation data, and using the training data to perform machine learning on an untrained neural network. The estimation device 4 acquires training data including a data set in which detection data and operation data from past operations of the film forming machine 1 are associated with identification results that identify the actual presence or absence of an abnormality. It is preferable that the estimation device 4 collects a large amount of detection data and operation data from multiple film forming machines 1 as training data.

[0067] The estimation device 4 inputs feature quantities included in the training data into the input layer of the first estimation model 422a, undergoes arithmetic processing in the intermediate layer, and obtains an anomaly identification result output from the output layer. The estimation device 4 compares the anomaly identification result output from the output layer with the identification result included in the training data, and optimizes parameters such as weights (coupling coefficients) between neurons using, for example, backpropagation so that the identification result output from the output layer approaches a correct value. Before learning begins, initial settings are set in the definition information describing the first estimation model 422a. When learning is completed by satisfying predetermined criteria such as errors, the number of learning times, and the like, optimized parameters are obtained. Upon completion of learning, the estimation device 4 stores the definition information related to the trained first estimation model 422a in the storage unit 42 as the trained first estimation model 422a.

[0068] The second estimation model 422b can be generated in a similar manner. By the above-mentioned processing, the first estimation model 422a that has been trained to be able to appropriately identify the presence or absence of an abnormality based on the feature quantities of the molding information, and the second estimation model 422b that has been trained to be able to appropriately identify the failure probability based on the feature quantities of the molding information are constructed. Note that the first estimation model 422a and the second estimation model 422b are not limited to being configured in the same manner, and for example, the first estimation model 422a may be a binary classification model, and the second estimation model 422b may be a regression model that outputs continuous values.

[0069] The estimation model 422 is not limited to being generated and learned by the estimation device 4. The estimation model 422 may be a model that has been learned by an external server and transmitted to the estimation device 4 and stored in the storage unit 42. The estimation model 422 may be generated by an external server and learned by the estimation device 4.

[0070] The configuration of the first estimation model 422a and the second estimation model 422b is not limited as long as they can estimate an abnormality or a service life based on the detection data and the operating data. The first estimation model 422a and the second estimation model 422b may be models based on other learning algorithms, such as a recurrent neural network (RNN), a convolution neural network (CNN), a graph neural network (GNN), a transformer, a support vector machine, a decision tree, an eXtreme Gradient Boosting (XGBoost), a logistic regression, or a random forest. The first estimation model 422a and the second estimation model 422b may be models trained by unsupervised learning. The first estimation model 422a and the second estimation model 422b may include multiple models and be constructed by applying ensemble learning such as bagging, boosting, or stacking. The first estimation model 422a and the second estimation model 422b may estimate an abnormality or a service life using a rule-based method.

[0071] In this embodiment, the first estimation model 422a that estimates the presence or absence of an abnormality and the second estimation model 422b that estimates the failure probability are configured separately, but the estimation device 4 may be configured to estimate the presence or absence of an abnormality and the failure probability using a single learning model. Furthermore, the estimation device 4 may be provided with only either the first estimation model 422a or the second estimation model 422b and may estimate only either the presence or absence of an abnormality or the failure probability.

[0072] The estimation model 422 can accurately estimate abnormalities or lifespans by taking into account a variety of characteristics through input of a wide variety of detection data and operational data. For example, inputting mechanical vibrations indicated by acceleration is considered to be able to take into account the deterioration state of equipment components. Inputting resin viscosity is considered to be able to take into account changes in resin properties. Inputting gel count is considered to be able to take into account quality abnormalities due to the presence or absence of unmixed portions of the resin raw material or the presence or absence of foreign matter. Inputting clip strain is considered to be able to take into account the deterioration state of the equipment. Inputting crystalline orientation is considered to be able to take into account quality abnormalities. Inputting the air speed, air volume, or pressure in the oven 141 is considered to be able to take into account the environment within the oven 141. Inputting the temperatures of each detection location and detection target is considered to be able to take into account various temperature environments. Inputting the amount of film charge is considered to be able to take into account poor film winding and quality abnormalities around the winder 15. Inputting synchronization error indicated by the phase difference between the left and right clips is considered to be able to take into account sliding loads and quality changes due to equipment load and deterioration. It is believed that by inputting the line tension, it is possible to take into account the wear state of the rail. It is also believed that by inputting the motor torque, rotation number, and rotation speed of each detection point and detection target, it is possible to take into account the deterioration state of the drive unit.

[0073] 6 is a flowchart showing an example of a processing procedure executed by the estimation device 4. The control unit 41 of the estimation device 4 executes the following processing in accordance with a program 4P stored in the storage unit 42. The control unit 41 starts the following processing at predetermined or appropriate intervals.

[0074] The control unit 41 of the estimation device 4, functioning as an acquisition unit, acquires molding information including detection data and operation data during continuous operation through the data collection device 3, and stores the acquired molding information in the molding information DB 421 (step S10). The molding information is associated with the device ID of the film molding machine 1. The control unit 41 may acquire multiple pieces of detection data and operation data together, or may acquire each piece of detection data and operation data individually at the timing when it is detected. The timing to receive the molding information may be a time period when traffic on the network N2 is relatively low.

[0075] The control unit 41 determines whether or not to execute the estimation process (step S11). If it determines not to execute the estimation process because a preset start condition is not satisfied (S11: NO), the control unit 41 returns the process to step S11 and waits until the start condition is satisfied. The start condition may be that the detection data and the driving data are acquired a preset number of times, that a preset estimation timing is satisfied, or the like.

[0076] When it is determined that the estimation process is to be executed because a preset start condition is satisfied (YES in S11), the control unit 41 calculates various feature quantities based on the acquired time-series detection data and driving data (step S12). The control unit 41 identifies the calculation method to be used for calculating each feature quantity, and the detection data and driving data, for example, by referring to a table that associates formulas used for calculating the feature quantities with data items.

[0077] The control unit 41, functioning as an estimation unit, inputs the calculated feature quantities of the detection data and operation data to the first estimation model 422a (step S13), and acquires abnormality presence / absence data output from the first estimation model 422a (step S14). Through the processing of steps S13 and S14, an abnormality in the film forming machine 1 is estimated.

[0078] The control unit 41, functioning as an estimation unit, inputs the calculated feature quantities of the detection data and operation data to the second estimation model 422b (step S15), and acquires failure probability data output from the second estimation model 422b (step S16). Through the processes of steps S15 and S16, the life of the film forming machine 1 is estimated.

[0079] The control unit 41 determines whether to output an alert (step S17). For example, if the estimation result corresponds to at least one of the following: there is an abnormality and the failure probability is equal to or greater than a preset threshold, the control unit 41 determines to output an alert. If the estimation result does not correspond to an abnormality and the failure probability is less than a preset threshold, the control unit 41 determines not to output an alert.

[0080] If it is determined that an alert should not be output (S17: NO), the control unit 41 ends the processing. If it is determined that an alert should be output (S17: YES), the control unit 41 generates a screen showing the estimated results of the abnormality and lifespan of the film forming machine 1 (step S18). The screen showing the estimated results is an example of alert information that notifies of the abnormality and lifespan of the film forming machine 1. The control unit 41 transmits the generated screen showing the estimated results to the user terminal device 5a and the service provider terminal device 5b that correspond to the device ID of the film forming machine 1 (step S19). The control unit 41 may transmit the estimated results to the control device 16. The control unit 41 ends the series of processes.

[0081] The control unit 41 repeatedly executes the above-described process during continuous operation of the film forming machine 1. By estimating abnormalities and lifespan while the continuous operation is continued based on the detection data and operation data detected during the continuous operation, the estimation results can be fed back to the operation of the film forming machine 1.

[0082] Although the above describes an example in which the estimation device 4 executes a series of processes, the entity that executes each process is not limited. Each process in the flowchart may be executed by, for example, the control device 16, the data collection device 3, or the terminal device 5. The estimation model 422 may be deployed to the control device 16 or the data collection device 3, and the anomaly and lifespan estimation process may be executed on the control device 16 or the data collection device 3 side.

[0083] In the above process, the order of the abnormality estimation process in steps S13 and S14 and the life estimation process in steps S15 and S16 may be reversed or may be processed in parallel. Either the abnormality estimation process or the life estimation process may be omitted.

[0084] The estimation device 4 may re-learn the estimation model 422 based on the molding information obtained during continuous operation. The estimation device 4 receives, for example, from a service provider, the results of identifying an abnormality or end of life for the molding information obtained during a predetermined period. The estimation device 4 performs re-learning using information obtained by labeling the acquired results of identifying an abnormality or end of life for the molding information as training data, and updates the estimation model 422. The training data used for re-learning may include molding information obtained from multiple film molding machines 1.

[0085] The estimation device 4 may evaluate the accuracy of the estimation model 422 using an evaluation method such as cross-validation, and if the evaluation index satisfies a predetermined standard, may update the estimation model 422. The estimation device 4 may also receive a request from a service provider regarding whether or not the estimation model 422 needs to be updated. This allows the accuracy of estimating anomalies or lifespans to be improved through operation of this system.

[0086] 7 is a schematic diagram showing an example of a screen 70 showing the estimated results of an abnormality and lifespan displayed on the terminal devices 5 a and 5 b. The screen 70 has a result display section 701 that displays the estimated results of the presence or absence of an abnormality and the failure probability.

[0087] The estimation device 4 acquires the estimation result by the estimation model 422, and displays the acquired presence or absence of an abnormality and failure probability on the result display unit 701. The estimation device 4 also outputs alert information through the screen 70 by displaying on the screen 70 an alert display unit 702 that displays text or the like indicating that the estimation result of the abnormality or lifespan is abnormal.

[0088] The screen 70 also has a trend display section 703 that displays the trend of the feature. The trend display section 703 includes a reception section 704 that receives the period and type of feature for displaying the trend, and a trend graph display section 705 that displays a trend graph. The reception section 704 has, for example, a pull-down menu. The user or service provider can select any period and type of feature by opening the pull-down menu. The list of feature types in the pull-down includes each feature used in the input information of the estimation model 422.

[0089] When the estimation device 4 receives the selection of a period and a type of feature via the terminal devices 5a and 5b, it reads out the detection data and operation data for the selected period from the molding information DB 421. Based on the read detection data and operation data, the estimation device 4 generates a time series graph showing the trend of the selected feature, and displays it on the trend display unit 703. Note that the trend display unit 703 may display the trends of the detection data and operation data instead of or in addition to the feature.

[0090] Although the above describes an example in which alert information is output together with the estimation result, the estimation device 4 may output only alert information to the terminal devices 5a and 5b notifying of an abnormality in the film forming machine 1. The alert information may be in the form of, for example, a message, a voice, an alert sound, or the like.

[0091] 7 in response to a request from the terminal devices 5a and 5b, regardless of whether an abnormality is present or not. Each user or service provider can view and check the status of the film forming machine 1 owned by the user at any time by accessing the service provider site using, for example, a browser.

[0092] According to this embodiment, the state of the film forming machine 1, such as an abnormality or end of life of the film forming machine 1, can be accurately estimated based on various detection data obtained by the detector 2 that detects the state of the film forming machine 1. The estimation results make it possible to accurately grasp the state of the film forming machine 1. In conventional film forming machines, the detection data by the detector 2 is mainly used for operation control, and detection of the state of the film forming machine 1 during operation has not been taken into consideration when estimating an abnormality or end of life. In this embodiment, by installing the detector 2 for the purpose of maintaining the film forming machine 1, it is possible to collect more detection data than could be obtained with conventional film forming machines 1 and use this data for condition analysis.

[0093] By collecting detection data during continuous operation of the film forming machine 1 and estimating abnormalities or lifespan based on the collected data, the state of the film forming machine 1 can be grasped early, leading to smooth response. Because it is possible to respond before the condition deteriorates, it is possible to facilitate equipment maintenance and reduce production downtime.

[0094] By using the estimation model 422, it is possible to easily and accurately estimate an abnormality or the lifespan of the film forming machine 1. By using a plurality of detection data representing the state of the film forming machine 1 as input information for the estimation model 422, it is possible to improve the accuracy of estimating an abnormality or the lifespan. By performing preprocessing on the detection data and operation data to calculate feature quantities, it is possible to provide the estimation model 422 with information suitable for estimating an abnormality or the lifespan, thereby improving the estimation accuracy.

[0095] The estimation device 4 can accumulate a huge amount of data on the cloud and provide trends in the accumulated data and estimated results of abnormalities or lifespans based on the data to the terminal device 5. Users and service providers can visually and clearly recognize the status of the film forming machine 1 at any time.

[0096] Second Embodiment In the second embodiment, a configuration will be described that uses an estimation model 422 or feature amounts corresponding to the film forming machine 1. In the following embodiment, differences from the first embodiment will be mainly described, and components common to the first embodiment will be assigned the same reference numerals and detailed descriptions thereof will be omitted.

[0097] The estimation device 4 of the second embodiment stores multiple types of estimation models 422 generated by different algorithms in the storage unit 42. Prior to estimating an abnormality or lifespan according to the molding information, the estimation device 4 determines the estimation model 422 to be used for estimating the abnormality or lifespan based on the type of film forming machine 1 owned by the user and the molding information collected from the film forming machine 1. The estimation model 422 can be determined based on the estimation accuracy of each estimation model 422. For example, the accuracy of each estimation model 422 is evaluated by an evaluation method such as cross-validation based on the estimation results of each estimation model 422 for test data of the molding information of the film forming machine 1. The estimation model 422 is determined by selecting the estimation model 422 with the highest estimation accuracy from all of the prepared estimation models 422.

[0098] The estimation device 4 may select multiple estimation models 422 with high estimation accuracy and estimate the abnormality or lifespan using the selected multiple estimation models 422. The estimation device 4 estimates the abnormality or lifespan by, for example, combining the estimation results of the multiple types of estimation models 422 and integrating them by majority vote or weighting.

[0099] The estimation device 4 may generate an estimation model 422 specialized for estimating abnormalities or the lifespan of the film forming machine 1 owned by the user by fine-tuning a previously generated, trained estimation model 422.

[0100] The estimation device 4 may also select feature quantities to be used as input information to the estimation model 422 from among a plurality of preset feature quantities, depending on the type of film forming machine 1 owned by the user. The feature quantities to be used as input information can be determined, for example, based on the contribution of the feature quantities. For example, estimation is performed by the estimation model 422 using a plurality of preset feature quantities, and the contribution of the input data corresponding to each feature quantity is calculated using SHAP (Shapley Additive exPlanation), LIME (Local Interpretable Model-Agnostic Explanations), feature importance in a decision tree algorithm model, or the like. The estimation device 4 determines the feature quantities to be used as input information by, for example, selecting feature quantities whose calculated contribution quantities are equal to or greater than a predetermined value, or by selecting a predetermined number of feature quantities in descending order of contribution quantities.

[0101] The estimation device 4 stores in the memory unit 42 the equipment ID of the determined estimation model 422 and the type of feature used in the input information in association with the equipment ID of the film forming machine 1 to which the estimation model 422 and feature are applied.

[0102] FIG. 8 is a flowchart showing an example of a processing procedure executed by the estimation device 4 of the second embodiment.

[0103] The control unit 41 of the estimation device 4 acquires the detection data during continuous operation, molding information including operating data, and the equipment ID of the film molding machine 1 in association with each other, and stores the acquired molding information in the molding information DB 421 (step S21).

[0104] The control unit 41 determines whether to execute the estimation process (step S22). If it determines not to execute the estimation process because the preset start condition is not satisfied (S22: NO), the control unit 41 returns the process to step S22 and waits until the start condition is satisfied.

[0105] If it is determined that the estimation process is to be executed because the preset start condition is satisfied (S22: YES), the control unit 41 selects (step S23) an estimation model 422 associated with the acquired device ID of the film forming machine 1. In step S23, the control unit 41 identifies the estimation model 422 corresponding to the acquired device ID based on the pre-stored correspondence between the film forming machine 1 and the estimation model 422 to be applied.

[0106] The control unit 41 calculates various feature quantities based on the acquired time-series detection data and operation data (step S24). If feature quantities to be used are set for each type of film forming machine 1, the control unit 41 identifies feature quantities associated with the acquired device ID of the film forming machine 1 based on the correspondence between the film forming machine 1 and the feature quantities to be applied, which is stored in advance, and calculates the identified feature quantities.

[0107] Thereafter, the control unit 41 executes the same processing as in the first embodiment to estimate an abnormality and a lifespan using the selected estimation model 422 and feature amount.

[0108] According to this embodiment, the accuracy of estimating an abnormality or lifespan can be improved by using an estimation model 422 and feature values ​​that correspond to the type of film forming machine 1 owned by the user. The configuration of each film forming machine 1 often varies greatly. By setting the type of estimation model 422 and feature values ​​to be used according to the type of film forming machine 1, it is possible to accurately estimate an abnormality or lifespan in accordance with the state of the film forming machine 1.

[0109] The embodiments disclosed herein are illustrative in all respects and should not be considered limiting. 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 modifications within the scope of the claims and equivalents thereto. The sequences shown in each embodiment are not limited, and within the scope of no contradiction, each processing step may be executed in a different order, or multiple processes may be executed in parallel. The entity that performs each process is not limited, and within the scope of no contradiction, the process of each device may be executed by another device.

[0110] The matters described in each embodiment can be combined with each other. Furthermore, the independent claims and dependent claims described in the claims can be combined with each other in any and all combinations, regardless of the reference format. Furthermore, the claims use a format in which a claim references two or more other claims (multiple claim format), but this is not limited to this. A multiple claim (multi-multi claim) that references at least one other multiple claim may also be used.

[0111] The following supplementary notes are further disclosed with respect to the above embodiments. (Supplementary Note 1) An estimation method comprising: acquiring detection data relating to the state of a film forming machine detected by a detector; and estimating an abnormality or lifespan of the film forming machine by inputting the acquired detection data into an estimation model that estimates an abnormality or lifespan of the film forming machine when the detection data relating to the state of the film forming machine is input. (Supplementary Note 2) The estimation method according to Supplementary Note 1, acquiring the detection data during continuous operation of the film forming machine; and estimating an abnormality or lifespan of the film forming machine based on the detection data while the continuous operation continues. (Supplementary Note 3) The estimation method according to Supplementary Note 1 or Supplementary Note 2, deriving feature values ​​based on the detection data; and estimating an abnormality or lifespan of the film forming machine by inputting the derived feature values ​​into the estimation model that estimates an abnormality or lifespan of the film forming machine when the feature values ​​based on the detection data relating to the state of the film forming machine are input. (Supplementary Note 4) The estimation method according to any one of Supplements 1 to 3, transmitting information indicating the estimated abnormality or lifespan of the film forming machine to a terminal device. (Supplementary Note 5) The estimation method according to any one of Supplementary Notes 1 to 4, further comprising generating information indicating a trend of the detection data based on the detection data in time series, and transmitting the generated information indicating the trend of the detection data to a terminal device. (Supplementary Note 6) The estimation method according to any one of Supplementary Notes 1 to 5, wherein the film forming machine comprises an extruder, a casting device, an MD stretching device, a TD stretching device, and a winding device, and the detection data includes a physical quantity related to the extruder, a physical quantity related to the casting device, a physical quantity related to the MD stretching device, a physical quantity related to the TD stretching device, or a physical quantity related to the winding device.(Supplementary Note 7) The estimation method according to any one of Supplementary Notes 1 to 6, wherein the film forming machine includes an extruder, a casting device, an MD stretching device, a TD stretching device, and a winding device, and the detection data includes at least one of acceleration in the extruder, resin viscosity in the extruder, acceleration in the casting device, number of gels in the film in the casting device, acceleration in the MD stretching device, acceleration in the TD stretching device, air speed in the TD stretching device, air volume in the TD stretching device, distortion of film grippers in the TD stretching device, phase difference between a pair of left and right film grippers in the TD stretching device, degree of crystal orientation in the TD stretching device, number of gels in the film in the TD stretching device, and amount of electrostatic charge of the film in the winding device. (Supplementary Note 8) The estimation method according to any one of Supplementary Notes 1 to 7, wherein detection data selected from a plurality of types of preset detection data is input to the estimation model. (Supplementary Note 9) The estimation method according to any one of Supplementary Notes 1 to 8, wherein a plurality of types of estimation models generated by different algorithms are prepared, and an estimation model to be used is selected depending on the type of the film forming machine. (Supplementary Note 10) The estimation method according to any one of Supplementary Notes 1 to 9, wherein the estimation model includes a plurality of models, and an abnormality or lifespan of the film forming machine is estimated based on the output of each of the plurality of models.

[0112] 100 Estimation system 1 Film forming machine 11 Extruder 12 Casting device 13 MD stretching device 14 TD stretching device 15 Winder 16 Control device 2 Detector 3 Data collection device 31 Control unit 32 Memory unit 33 Communication unit 34 Data input unit 4 Estimation device 41 Control unit 42 Memory unit 43 Communication unit 4A Recording medium 4P Program 421 Forming information DB 422 Estimation model 5a, 5b Terminal device

Claims

1. An estimation method for estimating an abnormality or lifespan of a film forming machine by acquiring detection data relating to the state of a film forming machine detected by a detector, and inputting the acquired detection data into an estimation model that estimates an abnormality or lifespan of the film forming machine when the detection data relating to the state of the film forming machine is input.

2. The estimation method according to claim 1, further comprising acquiring the detection data during continuous operation of the film forming machine, and estimating an abnormality or lifespan of the film forming machine based on the detection data while the continuous operation is continued.

3. The estimation method according to claim 1 or claim 2, further comprising deriving a feature quantity based on the detection data, and inputting the derived feature quantity into the estimation model, which estimates an abnormality or lifespan of the film forming machine when a feature quantity based on detection data relating to the state of the film forming machine is input, thereby estimating an abnormality or lifespan of the film forming machine.

4. The estimation method according to any one of claims 1 to 3, further comprising transmitting information indicating the estimated abnormality or lifespan of the film forming machine to a terminal device.

5. The estimation method according to any one of claims 1 to 4, further comprising the steps of: generating information indicating a trend of the detection data based on the time-series detection data; and transmitting the generated information indicating the trend of the detection data to a terminal device.

6. The estimation method according to any one of claims 1 to 5, wherein the film forming machine is equipped with an extruder, a casting device, an MD stretching device, a TD stretching device and a winding device, and the detection data includes a physical quantity related to the extruder, a physical quantity related to the casting device, a physical quantity related to the MD stretching device, a physical quantity related to the TD stretching device or a physical quantity related to the winding device.

7. The method of estimating according to any one of claims 1 to 6, wherein the film forming machine is equipped with an extruder, a casting device, an MD stretching device, a TD stretching device, and a winding machine, and the detection data includes at least one of the following: acceleration in the extruder, resin viscosity in the extruder, acceleration in the casting device, number of gels in the film in the casting device, acceleration in the MD stretching device, acceleration in the TD stretching device, wind speed in the TD stretching device, air volume in the TD stretching device, distortion of a film gripper in the TD stretching device, phase difference between a pair of left and right film grippers in the TD stretching device, degree of crystal orientation in the TD stretching device, number of gels in the film in the TD stretching device, and amount of charge of the film in the winding machine.

8. The estimation method according to any one of claims 1 to 7, wherein detection data selected from a plurality of types of preset detection data is input to the estimation model.

9. The estimation method according to any one of claims 1 to 8, further comprising the steps of: preparing a plurality of types of estimation models generated by different algorithms; and selecting an estimation model to be used according to the type of the film forming machine.

10. The estimation method according to any one of claims 1 to 9, wherein the estimation model includes a plurality of models, and an abnormality or lifespan of the film forming machine is estimated based on the output of each of the plurality of models.

11. A computer program for causing a computer to execute a process of acquiring detection data relating to the state of a film forming machine detected by a detector, and estimating an abnormality or lifespan of the film forming machine by inputting the acquired detection data into an estimation model which estimates an abnormality or lifespan of the film forming machine when the detection data relating to the state of the film forming machine is input.

12. An estimation device comprising: an acquisition unit that acquires detection data concerning the state of a film forming machine detected by a detector; and an estimation unit that estimates an abnormality or lifespan of the film forming machine by inputting the acquired detection data into an estimation model that estimates an abnormality or lifespan of the film forming machine when detection data concerning the state of the film forming machine is input.

13. An estimation system comprising a film forming machine, a detector, and an estimation device, the estimation device comprising: an acquisition unit that acquires detection data relating to a state of the film forming machine detected by the detector; and an estimation unit that estimates an abnormality or lifespan of the film forming machine by inputting the acquired detection data into an estimation model that estimates an abnormality or lifespan of the film forming machine when the detection data relating to the state of the film forming machine is input.

Images