WO2023085283A1 - Dispositif de traitement d'informations, système de traitement d'informations, et programme - Google Patents

Dispositif de traitement d'informations, système de traitement d'informations, et programme Download PDF

Info

Publication number
WO2023085283A1
WO2023085283A1 PCT/JP2022/041605 JP2022041605W WO2023085283A1 WO 2023085283 A1 WO2023085283 A1 WO 2023085283A1 JP 2022041605 W JP2022041605 W JP 2022041605W WO 2023085283 A1 WO2023085283 A1 WO 2023085283A1
Authority
WO
WIPO (PCT)
Prior art keywords
molding
waveform data
setting condition
value
information processing
Prior art date
Application number
PCT/JP2022/041605
Other languages
English (en)
Japanese (ja)
Inventor
貴則 角屋
祐介 内山
宏樹 岡
Original Assignee
株式会社Mazin
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社Mazin filed Critical 株式会社Mazin
Priority to JP2023559646A priority Critical patent/JPWO2023085283A1/ja
Publication of WO2023085283A1 publication Critical patent/WO2023085283A1/fr

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B22—CASTING; POWDER METALLURGY
    • B22D—CASTING OF METALS; CASTING OF OTHER SUBSTANCES BY THE SAME PROCESSES OR DEVICES
    • B22D17/00—Pressure die casting or injection die casting, i.e. casting in which the metal is forced into a mould under high pressure
    • B22D17/20—Accessories: Details
    • B22D17/32—Controlling equipment
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C39/00—Shaping by casting, i.e. introducing the moulding material into a mould or between confining surfaces without significant moulding pressure; Apparatus therefor
    • B29C39/22—Component parts, details or accessories; Auxiliary operations
    • B29C39/44—Measuring, controlling or regulating
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C45/00—Injection moulding, i.e. forcing the required volume of moulding material through a nozzle into a closed mould; Apparatus therefor
    • B29C45/17—Component parts, details or accessories; Auxiliary operations
    • B29C45/76—Measuring, controlling or regulating
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C49/00—Blow-moulding, i.e. blowing a preform or parison to a desired shape within a mould; Apparatus therefor
    • B29C49/42—Component parts, details or accessories; Auxiliary operations
    • B29C49/78—Measuring, controlling or regulating

Definitions

  • the present invention relates to an information processing device, an information processing system, and a program, and more particularly to setting molding conditions for a molding machine.
  • a plurality of molding conditions are adjusted little by little to find the conditions that can mold a good product.
  • This condition adjustment occurs at the time of startup before the start of production first thing in the morning (starting with loose conditions at first) or when there is a change in the surrounding environment.
  • the state of the melted resin is very important, and the melted resin is affected by the surrounding environment (such as temperature and humidity). may be.
  • the physical properties of the resin vary depending on the resin lot, or if the mold used in the domestic factory is used in the overseas factory, it is necessary to adjust the molding conditions according to the environment and the original molding machine. .
  • Patent Document 1 a technique for calculating and outputting molding conditions to be adjusted and their adjustment amounts from physical quantity data at the time of molding using AI (artificial intelligence) machine learning is disclosed (see Patent Document 1).
  • the conditions are adjusted in consideration of the quality of the molded product.
  • a technique for adjusting the conditions (specifically, using the mold internal pressure) using only the information of the first model and the second model based on machine learning is disclosed (see Patent Document 2).
  • An object of one aspect of the present invention is to provide a technology that simplifies the AI processing procedure and supports the setting of molding conditions in a way that is easy for workers to understand.
  • a first molding condition determination support system includes: A molding condition determination support system in which a molding machine that molds a molded product by supplying a molten material to a mold cavity, and a sensor and a display device are connected, Acquire the data of the mold internal pressure waveform, which is the reference when molding the predetermined molded product, by the sensor, When there is a difference between the reference mold pressure waveform and the waveform for each shot, the information processing device sets the setting condition regarding the plurality of extraction intervals set for the mold pressure waveform in the case of what kind of reference waveform.
  • a learning model is generated by machine learning based on the learning data of how much the value of is changed to make the waveform for each shot approach the reference waveform
  • the information processing device uses a learning model to reduce the absolute value of the difference between the reference mold pressure waveform and the mold pressure waveform obtained by the sensor at each of multiple shots in the manufacturing stage. Calculating the setting conditions and their values, at that time, confirming the setting conditions one by one in a predetermined order from one of the sections, The display device arranges the setting conditions to be reset and their values on the screen in chronological order of forming of the extracted section.
  • a second molding condition determination support system includes: A molding condition determination support system in which a molding machine that molds a molded product by supplying a molten material to a mold cavity, and a sensor and a display device are connected, Acquiring data of a mold internal pressure waveform that serves as a reference during molding of the predetermined molded product by the sensor, When there is a difference between the waveform of the internal mold pressure that serves as a reference and the waveform of each shot acquired by the sensor, the information processing device determines at least (1) an injection speed, ( 2) Machine learning based on learning data about how much the values of the setting conditions of 2) VP switching position, (3) pressure retention, and (4) pressure retention time should be changed to bring the waveform for each shot closer to the reference waveform Generate a learning model by The information processing device uses the learning model to reduce the absolute value of the difference between the reference mold internal pressure waveform and the mold internal pressure waveform at each of a plurality of shots in the manufacturing stage acquired by the sensor.
  • (1) injection speed, (2) VP switching position, (3) holding pressure and (4) holding pressure time are determined in this order.
  • the display device displays the setting conditions to be reset and their values at the time of molding of the (1) injection speed, the (2) VP switching position, the (3) holding pressure, and the (4) holding pressure time. Arrange them in order and display them on the screen.
  • An information processing device is an information processing device that outputs information about setting conditions of a molding machine that molds a molded product by supplying a molten material to a mold cavity, at least one storage device storing at least one reference waveform data which is waveform data detected by a sensor provided in the molding machine or the mold when a non-defective product of the predetermined molded product is molded; obtaining reference waveform data by referring to the storage device; obtaining at least one waveform data in one shot during molding of the molded product from the sensor; Using a machine learning model that learns so that the difference between the waveform data at the time of molding and the reference waveform data becomes small with the waveform data at the time of molding as input, the value of at least one setting condition and the value of the setting condition a molding condition providing unit that outputs at least one value of a setting condition for the sensor to detect waveform data identical or similar to the reference waveform data by processing the waveform data at the time of molding; Prepare.
  • An information processing apparatus is the information processing apparatus according to the first aspect, wherein the molding condition provision unit includes a plurality of steps included in one shot during molding of the molded product or By determining the setting conditions for each process or section in a predetermined order among the sections, the values of the setting conditions for a plurality of processes or sections are output.
  • An information processing apparatus is the information processing apparatus according to the second aspect, wherein the forming condition providing unit converts the output setting condition value for each step or section into a forming Outputs information for arranging and displaying processes or sections in chronological order.
  • An information processing device is the information processing device according to any one of the first to third aspects, wherein the sensor is a pressure sensor and/or a temperature sensor.
  • An information processing device is the information processing device according to any one of the first to fourth aspects, wherein the storage device stores a plurality of the reference waveform data,
  • the molding condition providing unit specifies a plurality of setting condition ranges from a plurality of setting conditions corresponding to the plurality of reference waveform data, and selects one setting condition range from the specified plurality of setting condition ranges. Outputs the value of the setting condition based on the selected setting condition range.
  • An information processing apparatus is the information processing apparatus according to the fifth aspect, wherein the forming condition provision unit selects one setting condition range from the specified plural setting condition ranges. In this case, the setting condition range with the widest setting condition range is selected.
  • An information processing device is the information processing device according to any one of the first to sixth aspects, wherein the storage device stores a machine learning model for each resin type or resin characteristic. is stored, and the molding condition providing unit refers to the storage device to select a machine learning model corresponding to the type of resin or physical properties of the resin input by the user, and uses the selected machine learning model to output the value of the at least one setting condition.
  • An information processing device is the information processing device according to any one of the first to seventh aspects, wherein the storage device includes the type of resin or physical properties of the resin as an input parameter.
  • the molding condition providing unit inputs the type of resin or the properties of the resin into the machine learning model based on the type of resin or physical properties of the resin input by the user. , outputting the value of the at least one setting condition.
  • An information processing apparatus is an information processing system that outputs information about setting conditions of a molding machine that molds a molded product by supplying a molten material to a mold cavity, At least one reference waveform data, which is waveform data detected by a sensor provided in the molding machine or the mold when molding a predetermined molded product and is used as a reference, and controls the molding machine when molding a non-defective product.
  • At least one storage device storing at least one piece of reference operation data that is operation data of the controller and serves as a reference; Machine learning for learning so as to reduce the difference between the waveform data at the time of molding and the reference waveform data by using at least one setting condition value and the first difference and the second difference at the time of the setting condition value as input.
  • Machine learning for learning so as to reduce the difference between the waveform data at the time of molding and the reference waveform data by using at least one setting condition value and the first difference and the second difference at the time of the setting condition value as input.
  • waveform data identical or similar to the reference waveform data is obtained from the sensor.
  • a molding condition providing unit that outputs at least one setting condition value detected by Prepare.
  • An information processing device is the information processing device according to the ninth aspect, wherein the storage device stores a machine learning model for each physical property of the resin,
  • the molding condition providing unit estimates the physical properties of the resin in the molding machine using the characteristic values of the motor provided in the molding machine and/or the characteristic values of the motor stored in the controller. Using a machine learning model corresponding to the estimated physical properties of the resin, the value of the at least one setting condition is output.
  • An information processing device is the information processing device according to the ninth aspect, wherein the storage device stores a machine learning model including resin physical properties as input parameters,
  • the molding condition providing unit estimates the physical properties of the resin in the molding machine using the characteristic values of the motor provided in the molding machine and/or the characteristic values of the motor stored in the controller. Inputting the estimated physical property of the resin into the machine learning model, and outputting the value of the at least one setting condition.
  • An information processing apparatus is the information processing apparatus according to any one of the ninth to eleventh aspects, wherein the molding condition providing unit provides feedback to the molding machine so that the at least Output the value of one setting condition to the molding machine.
  • An information processing device is the information processing device according to any one of the first to twelfth aspects, wherein the machine learning model is Bayesian optimization.
  • An information processing apparatus is the information processing apparatus according to any one of the first to thirteenth aspects, wherein the at least one setting condition is injection speed, VP switching position, holding pressure and At least one of the dwell times.
  • An information processing system is an information processing system that outputs information regarding setting conditions of a molding machine that molds a molded product by supplying a molten material to a mold cavity, at least one storage device storing at least one reference waveform data which is waveform data detected by a sensor provided in the molding machine or the mold when a non-defective product of the predetermined molded product is molded; obtaining reference waveform data by referring to the storage device; obtaining at least one waveform data in one shot during molding of the molded product from the sensor; Using a machine learning model that learns so that the difference between the waveform data at the time of molding and the reference waveform data becomes small with the waveform data at the time of molding as input, the value of at least one setting condition and the value of the setting condition a molding condition providing unit that outputs at least one value of a setting condition for the sensor to detect waveform data identical or similar to the reference waveform data by processing the waveform data at the time of molding; Prepare.
  • An information processing system is an information processing system that outputs information about setting conditions of a molding machine that molds a molded product by supplying a molten material to a mold cavity, At least one reference waveform data, which is waveform data detected by a sensor provided in the molding machine or the mold when molding a predetermined molded product and is used as a reference, and controls the molding machine when molding a non-defective product.
  • At least one storage device storing at least one piece of reference operation data that is operation data of the controller and serves as a reference; Machine learning for learning so as to reduce the difference between the waveform data at the time of molding and the reference waveform data by using at least one setting condition value and the first difference and the second difference at the time of the setting condition value as input.
  • Machine learning for learning so as to reduce the difference between the waveform data at the time of molding and the reference waveform data by using at least one setting condition value and the first difference and the second difference at the time of the setting condition value as input.
  • waveform data identical or similar to the reference waveform data is obtained from the sensor.
  • a molding condition providing unit that outputs at least one setting condition value detected by Prepare.
  • a program stores at least one reference waveform data, which is waveform data detected by a sensor provided in a molding machine or a mold when a non-defective product is molded for a predetermined molded product. to a computer accessible to at least one storage device that obtaining reference waveform data by referring to the storage device; obtaining at least one waveform data in one shot during molding of the molded product from the sensor; Using a machine learning model that learns so that the difference between the waveform data at the time of molding and the reference waveform data becomes small with the waveform data at the time of molding as input, the value of at least one setting condition and the value of the setting condition a step of outputting at least one value of a setting condition for the sensor to detect waveform data identical or similar to the reference waveform data by processing the waveform data at the time of molding; It is a program for executing
  • the program according to the eighteenth aspect of the present invention includes at least one reference waveform data that is waveform data detected by a sensor provided in a molding machine or a mold when a non-defective product is molded of a predetermined molded product, and at least one reference waveform data that serves as a reference;
  • a computer capable of referencing at least one storage device storing at least one piece of reference operation data, which is operation data of a controller that controls the molding machine during molding and serves as a reference, Machine learning for learning so as to reduce the difference between the waveform data at the time of molding and the reference waveform data by using at least one setting condition value and the first difference and the second difference at the time of the setting condition value as input.
  • a model by processing the value of at least one setting condition and the first difference and the second difference at the value of the setting condition, waveform data identical or similar to the reference waveform data is obtained from the sensor.
  • a step of outputting at least one value of the setting condition detected by It is a program for executing
  • FIG. 1 is an external view of a molding machine of a molding condition determination support system according to an embodiment of the present invention
  • FIG. 1 is a schematic configuration diagram of part of a molding machine of a molding condition determination support system according to an embodiment of the present invention
  • FIG. 4 is a diagram showing a mold internal pressure waveform over time during one shot for molding one molded product in the embodiment of the present invention. It is a figure explaining the flow of processing of the molding condition determination support system in embodiment of this invention. It is a figure which shows the example of a display screen of the display apparatus of the molding condition determination support system in embodiment of this invention.
  • FIG. 1 is a functional block diagram of an information processing device of a molding condition determination support system according to an embodiment of the present invention
  • FIG. 4 is a flow chart showing the flow of processing of the information processing device of the molding condition determination support system according to the embodiment of the present invention
  • It is a figure which shows an example of the equipment configuration of the molding condition determination support system in 2nd Embodiment.
  • FIG. 10 is a functional block diagram of an information processing device of a molding condition determination support system according to a second embodiment; It is a schematic diagram showing the position of the sensor of the modification according to the second embodiment.
  • It is a figure which shows an example of the equipment configuration of the molding condition determination support system in 3rd Embodiment.
  • FIG. 11 is a functional block diagram of an information processing device of a molding condition determination support system according to a third embodiment
  • FIG. 5 is a diagram showing a plurality of examples of mold internal pressure waveforms with the lapse of time between one shot for molding one molded product; It is a figure which shows an example of the equipment configuration of the molding condition determination support system in 4th Embodiment.
  • FIG. 11 is a functional block diagram of an information processing device of a molding condition determination support system in a fourth embodiment; 4 is a schematic diagram showing an example of a machine learning model stored in a storage unit; FIG. FIG.
  • FIG. 11 is an external view of a molding machine of a molding condition determination support system according to a fifth embodiment; It is a figure which shows an example of the equipment configuration of the molding condition determination support system in 5th Embodiment.
  • FIG. 11 is a functional block diagram of an information processing device of a molding condition determination support system according to a fifth embodiment;
  • FIG. 11 is a schematic configuration diagram of a molding condition determination support system in a sixth embodiment;
  • the molding condition determination support system is applied to a method of molding a molded product by supplying a molten material to a mold of a molding machine.
  • Applicable molding methods include, for example, injection molding of resin or rubber, blow molding and extrusion molding, metal casting such as die casting, and the like. In the following, injection molding will be mainly described as an example of application.
  • FIG. 1 is an external view of a molding machine 1 of a molding condition determination support system 100 according to an embodiment of the present invention.
  • the molding machine 1 is an injection molding machine that makes various plastic products by pouring melted resin (plastic) into a mold, cooling it, solidifying it, and taking it out. It can be roughly divided into an injection unit 10 for melting a material such as resin with heat and injecting it into a mold, a mold clamping unit 20 for opening and closing the mold, and molding conditions (for example, the speed at which resin is injected into the mold). , pressure, temperature, etc.).
  • FIG. 2 is a schematic configuration diagram of part of a known general molding machine 1 as disclosed in the above-mentioned Patent Document 1 and Patent Document 2.
  • the injection unit 10 includes a hopper, heating cylinder, screw, nozzle, heater, driving device, and the like.
  • the hopper is an inlet for pellets (granulated material).
  • a heating cylinder is provided axially movably with respect to the bed.
  • the screw is arranged inside the heating cylinder and provided rotatably and axially movably.
  • the nozzle is an injection port provided at the tip of the heating cylinder, and the melted resin inside the heating cylinder is supplied to the mold cavity by axial movement of the screw.
  • the mold clamping unit 20 opens and closes the mounted mold, and when the mold is clamped, the mold does not open due to the pressure of the melted resin injected into the mold cavity (molded part). make it
  • the mold clamping unit 20 includes a stationary platen, a movable platen, tie bars, a driving device, and the like.
  • a fixed-side first mold is fixed to the fixed platen.
  • the stationary platen is capable of coming into contact with the nozzle, and guides the resin injected from the nozzle to the cavity of the mold.
  • a cavity is a region formed between the first mold and the second mold and corresponding to the shape of the product.
  • a second mold on the movable side is fixed to the movable platen, and can be moved toward and away from the fixed platen.
  • the tie bars support movement of the movable platen.
  • the drive device is composed of, for example, a cylinder device, and moves the movable platen.
  • the first mold has a supply channel between the nozzle and the cavity.
  • a three-plate mold or the like can also be applied in the same manner.
  • the ejector pin (ejection pin) 22 fixed to the ejector plate 21 protrudes when the mold is opened, so that the molded product (workpiece) can be removed from the mold.
  • a plurality of sensors 23 for acquiring in-mold data are provided in such a manner as to be embedded in the ejector plate 21 at positions corresponding to (opposed to) the ejector pins 22 (see also FIG. 5).
  • the sensor 23 is a pressure sensor that detects the pressure inside the mold received from the melted resin, and is, for example, a load cell.
  • the measuring mechanism via the ejector plate 21 and the ejector pin 22 is not essential, and the mounting position of the sensor 23 is not particularly limited as long as it is possible to acquire data inside the mold, regardless of whether it is inside or outside the mold. Optional.
  • the controller 30 controls the driving device of the injection unit 10 and the driving device of the mold clamping unit 20 based on command values (parameters) regarding molding conditions.
  • the molding machine 1 may be composed of a plurality of devices including a control device, a sensor, and the like.
  • a mold clamping force control device for driving mold opening/closing, screw rotation/reverse movement, injection unit forward/backward movement, etc.
  • a nozzle/cylinder for driving mold opening/closing, screw rotation/reverse movement, injection unit forward/backward movement, etc.
  • a nozzle/cylinder a hopper lower temperature control device
  • a pressure control device and the like.
  • a mold temperature control device there are, for example, a mold temperature control device, a hot runner temperature/nozzle opening/closing control device, a mold vibrating device, and the like.
  • Peripheral devices include, for example, a molded product take-out device controlled by a control device, an insert product insertion device, an insert insertion device, a molded product deburring device, a runner cutting device, a molded product weight scale, a molded product strength tester, Optical inspection equipment for molded products, imaging equipment for molded products, image processing equipment, robots for transporting molded products, etc.
  • a control device equipped with a sensor to perform closed-loop feedback control or feedforward control, or there may be a device having only a data output function.
  • the following general injection molding method is known.
  • the resin is stored between the tip of the heating cylinder and the nozzle while being melted by shear friction heat accompanying heating of the heater and rotation of the screw.
  • the amount of stored resin is measured from the retracted position of the screw that retracts as the amount of stored resin increases.
  • mold clamping is performed by moving the movable platen to match the first mold and the second mold.
  • the nozzle is connected to the stationary platen.
  • the injection-filling step with the screw stopped rotating, the screw is moved toward the nozzle at a predetermined injection speed and pushing force, thereby injecting and filling the resin into the mold cavity at high pressure.
  • the filled resin is further pushed into the cavity, and a holding pressure process is performed in which a predetermined holding pressure is applied to the resin in the cavity for a predetermined time.
  • a predetermined holding force is applied to the resin by applying a constant pressing force (holding force) to the screw.
  • the pressure generated in the resin inside the cavity varies depending on the position of the cavity.
  • the pressing of the resin is stopped to reduce the holding pressure, and the mold is further cooled to solidify the resin in the cavity.
  • the mold release process the first mold and the second mold are separated, and the ejector pin (ejection pin) 22 protrudes when the mold is opened, thereby removing (removing) the molded product from the mold. can be done.
  • FIG. 3 is a diagram showing an example of the equipment configuration of the molding condition determination support system 100 according to this embodiment.
  • a mold equipped with a sensor (load cell) 23 for acquiring in-mold data such as an internal pressure of the mold is installed.
  • the sensor 23 sends sensing data to the information processing device 4 via the instrumentation amplifier 2, the A/D converter 3, etc., which serve as a data acquisition unit.
  • the sensor 23 and the information processing device 4 may have a configuration such as a wireless connection.
  • the sensor (load cell) 23 is used, but any sensor capable of acquiring intra-cavity data such as the internal pressure of the mold can be used regardless of the type and data communication method, and can be installed at any position.
  • the information processing device 4 is, for example, an industrial PC (personal computer), and includes a CPU (Central Processing Unit), which is an arithmetic device as a control unit and a calculation unit, ROM (Read Only Memory), RAM (Random Access Memory), etc. and the like, and a predetermined storage device as a storage unit, such as an internal or external HDD.
  • a CPU Central Processing Unit
  • ROM Read Only Memory
  • RAM Random Access Memory
  • In-mold pressure data for one shot is displayed as a pressure waveform with the horizontal axis (time) and the vertical axis (pressure).
  • the mold internal pressure waveform can be analyzed by dividing it into a plurality of (here, three) sections along with the passage of time on the horizontal axis.
  • the first section a relates to the above (1) injection speed and (2) VP switching position
  • the second section b relates to the above (3) holding pressure
  • the third section c relates to the above ( 4) Analyze as related to dwell time.
  • the injection speed refers to how fast the screw is advanced toward the nozzle. Note that the number of steps may be set.
  • the VP switching position is a position where the control method is switched from V (injection speed) to P (holding pressure) in relation to forward movement of the screw.
  • the amount of resin to be injected is determined by the position of the screw.
  • the injection start position is called the metering position
  • the injection end position is called the VP switching position.
  • An image of the VP switching position is, for example, a position filled with about 95% resin. If the value of the VP switching position is made smaller, the short circuit of the molded product is gradually improved. As the numerical value of the VP switching position is decreased, more resin enters and the pressure inside the mold increases (increases).
  • Holding pressure is the amount of pressure that is applied after the mold cavity is filled with resin until the gate is sealed (the gate is solidified) with a certain force to prevent the resin from flowing back from the gate. Say things.
  • the unit is MPa or kgf/cm2. For example, 40 MPa for 2 seconds or the like is set after the end of injection. Note that the number of steps may be set.
  • Holding pressure time means the time during which holding pressure is maintained.
  • the display device 5 of the molding conditions (changed values) calculated using the AI of the information processing device 4 is, for example, a monitor, a tablet, or the like. may be fixed by a jig.
  • the display device 5 is connected to the information processing device 4 by wire or wirelessly.
  • FIG. 5 is a diagram for explaining the processing flow of the molding condition determination support system 100 according to this embodiment.
  • the waveform of the mold internal pressure in one shot for a given molded product is obtained by measuring it with a load cell 23 (pressure sensor) installed on the back of the ejector pin 22 of the mold. be done.
  • a load cell 23 pressure sensor
  • One is to acquire a reference waveform as a premise, and the other is to acquire a mold internal pressure waveform for each shot in the actual manufacturing stage.
  • a detailed description will be given including these two methods.
  • a load cell installed on the back of the ejector pin 22 of the mold 23 measures the pressure inside the mold, and the information processing device 4 acquires the reference waveform data. That is, molding is performed under conditions that produce a good product (in the operation condition determination work for calculating the optimum operation conditions of the molding machine 1, the operation conditions that serve as approximate standards based on experience are set and the molding operation is performed.
  • the operator refers to process monitoring data, molded product weight measurement values, etc., and visually checks the molded product to confirm the molding state.
  • the mold pressure at that time is stored as a reference waveform in a database table or the like in a predetermined storage unit 58 of the information processing device 4 .
  • the pressure for a good product differs from the pressure for a defective product (strength, dimensions, surface condition, etc.).
  • the pressure for a defective product differs from the pressure for a defective product (strength, dimensions, surface condition, etc.).
  • the pressure for a defective product there is For example, if there is less resin in the cavity, the pressure will be lower, and if there is more resin in the cavity, the pressure will be higher.
  • the difference in the tendency of the resin to cool due to variations in the resin temperature and the mold temperature also appears in the pressure.
  • the table or the like of the above database may store the reference waveform in association with each type of molded product.
  • the information processing device 4 generates a learning model by AI machine learning, that is, in advance, the above-described reference waveform for a predetermined molded product, the mold pressure waveform at each shot, and each parameter and the resulting mold pressure waveform, etc. are used as learning data (teacher data), and (1) injection speed, (2) VP switching position, ( 3) Hold pressure, (4) Hold pressure time, which parameter should be changed by what amount (value, width) to effectively and efficiently approach (ideally match) the reference waveform.
  • a learning model is generated by learning whether it can be corrected. However, this learning model is updated each time new learning data (teacher data) relating to the difference between the reference waveform and the mold internal pressure waveform at each shot is obtained. Note that parameters such as temperature may also be taken into consideration as (5).
  • the mold internal pressure waveform for each shot for a predetermined molded product was set on the back surface of the ejector pin 22 of the mold. Measurement is performed by the load cell 23 (pressure sensor), and the information processing device 4 acquires the mold internal pressure waveform data. Next, the information processing device 4 compares the mold internal pressure waveform in each shot with a reference waveform using a molding condition setting support application or the like equipped with AI, determines whether the difference exceeds a predetermined value, and determines if the difference exceeds a predetermined value. , it is determined that the condition needs to be reset because the difference is large (the deviation is large).
  • the molding conditions that minimize the difference between the most recent mold internal pressure waveform and the reference waveform (to match the target reference waveform) are set by AI (artificial intelligence). is calculated by the learning model generated above. That is, the most recent mold internal pressure waveform and the reference waveform are compared, and based on which part of the waveform there is a divergence (there are various deviation patterns such as inclination), etc., (1) injection speed, (2) Among the VP switching position, (3) holding pressure, and (4) holding pressure time, molding conditions to be adjusted and their values are determined (molding condition optimization). Note that the adjustment order of the molding conditions is fixed when calculating based on the learning model.
  • the information processing device 4 outputs the molding conditions calculated by the AI, displays them on the display device 5, and instructs the operator to change them (recommend that these parameters should be changed).
  • the operator inputs the conditions to the controller 30 of the molding machine 1 by pressing a button or the like, and the molding of a predetermined molded product is restarted.
  • FIG. 6 is a diagram showing an example of a display screen of the display device 5. As shown in FIG.
  • any condition may be determined first. For example, in the case of the order of (3), (4), (1), (2), etc., the conditions are displayed in that order from the top. It may be In addition, FIG. 6 shows an example in which the number of sensors is six and the number of graphs (the most recent mold internal pressure waveform and the reference waveform) corresponding to the number is displayed.
  • FIG. 7 is a functional block diagram of the information processing device 4 of the molding condition determination support system 100 according to this embodiment.
  • the information processing device 4 includes a communication unit 41, an acquisition unit 42, a calculation unit 43, a learning data storage unit 44, a model generation unit 45, a molding condition provision unit 46, and an output unit 47. , and a storage unit 48 .
  • Each unit may be implemented by a known input/output I/F, CPU, or the like, or by an HDD or the like.
  • Some functions of the information processing device 4 may be implemented as predetermined software, and the software may be implemented in the cloud.
  • the communication unit 41 has a function of communicating with each device connected to a predetermined network.
  • the acquisition unit 42 has a function of acquiring the internal pressure data of the mold actually measured from the sensor 23 via the communication unit 41, the instrumentation amplifier 2, the A/D converter 3, etc. in chronological order. are doing. As mentioned above, there are mainly two situations, one is to acquire the reference waveform as a premise, and the other is to acquire the mold internal pressure waveform at each shot in the actual manufacturing stage. be.
  • the calculation unit 43 calculates the deviation between the reference waveform (reference waveform data) stored in the storage unit 48 and the waveform acquired by the acquisition unit 42 for each shot, and based on the deviation amount (distance, etc.), the above ( It has a function of calculating how the waveform of the next shot changes when the parameters of the setting conditions of 1) to (4) are changed. Depending on the various patterns in which the waveform of the internal mold pressure deviates from the reference waveform, which parameter out of (1) injection speed, (2) VP switching position, (3) holding pressure, and (4) holding pressure time, and how much (value, width), effectively and efficiently calculate how close you are to the reference waveform when you change it.
  • the learning data storage unit 44 stores the parameters of the above setting conditions (1) to (4) based on the deviation between the reference waveform and the waveform for each shot for any reference waveform calculated by the calculation unit 43. is changed, data indicating how the waveform of the next one shot changed is linked and stored in the storage unit 48 as learning data (teaching data). It should be noted that data such as material such as resin may also be linked and stored.
  • the model generating unit 45 uses an AI (artificial intelligence) module to determine how much the parameters of the setting conditions (1) to (4) should be changed for any reference waveform.
  • AI artificial intelligence
  • a learning model of the relation of whether the waveform for each shot approaches the reference waveform is generated and stored in the storage unit 48 .
  • the model generating unit 45 determines how much the parameters of the setting conditions (1) to (4) are changed in the case of what kind of reference waveform, and how much the waveform for each shot changes. machine learning by regression analysis etc.
  • the regression method for example, a well-known method such as linear regression, polynomial regression, or logistic regression can be used, so detailed description is omitted.
  • the model generation unit 45 may perform machine learning by deep learning using a multi-layer neural network, or by other known machine learning or the like. may be to generate Note that parameters such as temperature may also be taken into consideration as (5).
  • the molding condition providing unit 46 compares the mold internal pressure waveform in each shot with the reference waveform and determines whether the difference exceeds a predetermined value.
  • a function to determine that resetting is necessary, and a molding condition that minimizes the difference between the most recent mold pressure waveform and the reference waveform (matches to the target reference waveform) when it is determined that the conditions need to be reset. is calculated based on the learning model and provided by calculating how much the parameters of the above setting conditions (1) to (4) should be changed.
  • the order of adjustment of the molding conditions is fixed during calculation based on the learning model. That is, when adjusting the molding conditions, instead of searching for all conditions at once, (1) injection speed, (2) VP switching position, (3) holding pressure, (4) holding pressure time in this order ( order).
  • the conditions (1) to (4) are not completely independent, and there are some parts that affect each other.
  • the optimization process can be performed with a small number of times, and the procedure is easy for the operator to understand (The adjustment values of the conditions (1) to (4) in chronological order can be easily visually confirmed.) can be adjusted with Here, the determination is made in order from (1).
  • This order information set in ) is retained and used for calculations based on the learning model.) For example, the order of (3), (4), (1), and (2).
  • a Bayesian optimization algorithm may be applied as the main AI algorithm used in calculating the molding conditions. This uses the concepts of exploitation (using data/information obtained in the past) and exploration (going to obtain data that has not yet been obtained) to derive the next action to be taken (points to be explored). It is an optimization method. Note that parameters such as temperature may also be taken into consideration as (5).
  • the output unit 47 has a function of outputting various data such as image data and audio data through a display mechanism such as a display and an audio output mechanism such as a speaker.
  • a display mechanism such as a display
  • an audio output mechanism such as a speaker.
  • the changed values and changed amounts of the parameters of the setting conditions (1) to (4) calculated by the AI are output to the display device 5 so as to be displayed.
  • the storage unit 48 has a function of storing programs and various data for making the information processing device 4 function.
  • the storage unit 48 may be realized as a storage unit encrypted by blockchain.
  • the database has a predetermined table or the like in which various types of data are linked and stored. Reference waveform data is stored in a table or the like of a predetermined database in association with each type of molded product.
  • FIG. 8 is a flow chart showing the main processing flow of the information processing device 4 of the molding condition determination support system according to the present embodiment.
  • the acquisition unit 42 of the information processing device 4 acquires the reference waveform of the internal pressure data of the mold actually measured from the sensor 23 via the communication unit 41, the instrumentation amplifier 2, the A/D converter 3, and the like. (step S801).
  • the model generating unit 45 uses an AI (artificial intelligence) module to calculate the above (1 ) to (4) are changed to change the waveform of the next shot. (stored in . Generate a learning model of the relationship (Step S802).
  • the acquisition unit 42 acquires the internal pressure data of the mold actually measured from the sensor 23 via the communication unit 41, the instrumentation amplifier 2, the A/D converter 3, etc. at each actual manufacturing stage. A waveform of the mold pressure in the shot is obtained (step S803).
  • the molding condition providing unit 46 compares the mold internal pressure waveform in each shot with the reference waveform, determines whether the difference is smaller than a predetermined value (step S804), and if it is not smaller (step S804/ No), it is determined that the condition needs to be reset because the difference is large (the deviation is large).
  • the learning model generated in S802 is updated by adding information on the difference between the latest intramold pressure waveform and the reference waveform as learning data (step S805), and based on the updated learning model, the above (1) How much the parameters of the setting conditions of (4) should be changed is calculated (step S806). As described above, the order of adjustment of the molding conditions is fixed in advance when calculating based on the learning model.
  • the output unit 47 outputs the change values and change amounts of the parameters for each of the setting conditions (1) to (4) calculated by the molding condition providing unit 46 so as to be displayed on the display device 5 (step S807).
  • molding is resumed under conditions reset according to the output result, and the waveform of the mold pressure is obtained for each shot (step S803), and whether or not the difference between the waveform of the mold pressure and the reference waveform is smaller than a predetermined value. Determination (step S804) is repeated until the difference becomes smaller than a predetermined value.
  • the changed values of the parameters of the molding conditions are displayed on the display device 5 in a time series of molding so that the operator can easily understand. Since it is displayed along the line, it is possible to support the setting of molding conditions.
  • the information processing device and the result display unit may be integrated. That is, the data output to the display device may be used by being displayed on a predetermined display unit (liquid crystal display or the like) only in the information processing device without being output to the display device.
  • a predetermined display unit liquid crystal display or the like
  • the molding machine 10 may be integrated with the information processing device 4 . It broadly includes aspects in which it is physically incorporated in the molding machine 10 or only its functions are realized in the molding machine 10 . In that case, the display device 5 may also be integrated, or the display device 5 may not be provided (in this case, parameter changes are fed back by automatic control).
  • the sensor in the first embodiment is a pressure sensor, whereas the sensor in the second embodiment is a temperature sensor.
  • a reference temperature waveform is acquired when a non-defective product is produced, and molding conditions related to temperature are adjusted so as to approach the reference temperature waveform.
  • FIG. 9 is a diagram showing an example of the equipment configuration of a molding condition determination support system according to the second embodiment.
  • the sensor 23 is changed to a sensor 23b as compared with the system according to the first embodiment shown in FIG.
  • a sensor 23b detects the temperature of the mold.
  • the sensor 23b may be embedded inside the mold, or the sensor 23b may be an ejector pin type temperature sensor in the form of an ejector pin (extrusion pin) 22 .
  • FIG. 10 is a functional block diagram of the information processing device of the molding condition determination support system in the second embodiment.
  • the same reference numerals are assigned to the same elements as in the first embodiment, and detailed description thereof will be omitted as appropriate.
  • the functions of the acquisition unit 42, the calculation unit 43b, the learning data storage unit 44b, the model generation unit 45b, the molding condition provision unit 46, and the output unit 47 are realized by the processor 40 reading programs from the storage unit 48 and executing them. may be Since the processing of each unit is the same as that of the first embodiment, details thereof will be omitted as appropriate.
  • the storage unit 48 is a storage device, and the storage unit 48 stores reference waveform data, which is waveform data detected by a sensor 23b provided in a molding machine or a mold when a non-defective product is molded for a predetermined molded product. At least one is stored.
  • the waveform data is data representing time-series changes in temperature.
  • the molding condition providing unit 46 acquires reference waveform data by referring to the storage unit 48, and obtains at least one sensor waveform data for one shot during molding of the molded product from the sensor 23b provided in the molding machine or the mold. get.
  • the molding condition providing unit 46 receives the value of at least one setting condition and the waveform data at the time of molding at the value of the setting condition, and learns so that the difference between the waveform data at the time of molding and the reference waveform data becomes small.
  • the sensor 23b detects waveform data identical or similar to the reference waveform data by processing the value of at least one setting condition and the waveform data at the time of molding at the value of the setting condition. Output at least one setting condition value.
  • the machine learning model receives at least one setting condition value and the waveform data at the time of molding when the value of the setting condition is the input, and calculates an evaluation value based on the difference between the waveform data at the time of molding and the reference waveform data.
  • It is a machine learning model (specifically, for example, Bayesian optimization) that aims to optimize a black-box function as an output.
  • the set conditions are, for example, (1) injection speed, (2) VP switching position, (3) holding pressure, and (4) holding pressure time.
  • the molding condition providing unit 46 for example, in a predetermined order of a plurality of processes (or sections) included in one shot when molding a molded product, one process (or section) at a time in the process (or section) By confirming the setting conditions, values of the setting conditions for a plurality of steps (or intervals) may be output.
  • the process corresponds to the section described above.
  • the first section a in FIG. and the third section c is the section of the cooling process described above.
  • the molding condition providing unit 46 converts the output setting condition values for each process (or section) into You may output the information for arranging and displaying in order.
  • the temperature measured by the sensor 23b is not limited to the temperature of the mold, and may be the temperature of the heater as shown in FIG. 11, for example.
  • FIG. 11 is a schematic diagram showing positions of sensors in a modification according to the second embodiment. As shown in FIG. 11, the heater 12 is provided so as to wrap around the outer surface of the nozzle 11, and the sensor 23b may be provided so as to contact the heater 12, for example.
  • the pressure sensor and the temperature sensor may be used together, and in this case, the molding conditions may be adjusted so that the pressure and temperature waveforms of one shot approach the reference waveforms of the pressure and temperature, respectively.
  • FIG. 12 is a diagram showing an example of the device configuration of a molding condition determination support system according to the third embodiment. As shown in FIG. 12, in a molding condition determination support system 100c according to the third embodiment, the information processing device 4 is changed to an information processing device 4c as compared with the system according to the first embodiment shown in FIG. It's becoming
  • FIG. 13 is a functional block diagram of the information processing device of the molding condition determination support system in the third embodiment. As shown in FIG. 13, in the information processing device 4c, the molding condition providing section 46 is changed to a molding condition providing section 46c as compared with the information processing device 4 of the first embodiment.
  • FIG. 14 is a diagram showing a plurality of examples of mold internal pressure waveforms with the passage of time during one shot for molding one molded product.
  • the vertical axis is the pressure inside the mold and the horizontal axis is the elapsed time.
  • FIG. 14 there are a plurality of waveforms that result in good molded products.
  • the information processing device 4c may acquire a plurality of pieces of reference waveform data that produce non-defective products and store them in the storage unit 48. In this way, a plurality of reference waveform data may be stored.
  • the calculation unit 43 selects one from a plurality of reference waveforms (reference waveform data) stored in the storage unit 48, and compares the selected reference waveform data with the waveform for each shot acquired by the acquisition unit 42. Calculate the shift, and based on the amount of shift (distance, etc.), calculate how the waveform of the next shot changes when the parameters of the setting conditions (1) to (4) above are changed. You may
  • the molding condition providing unit 46c may specify a plurality of setting condition ranges in which non-defective products are obtained from a plurality of setting conditions corresponding to a plurality of reference waveform data. Specifically, for example, by selecting two setting conditions from the setting conditions when each of the plurality of reference waveform data is obtained and extracting the range between the two selected setting conditions as the setting condition range, A plurality of setting condition ranges may be specified.
  • the molding condition providing unit 46c may select one setting condition range from the specified plural setting condition ranges. Specifically, for example, when selecting one setting condition range from a plurality of specified setting condition ranges, the molding condition providing unit 46c may select the setting condition range having the widest setting condition range. Then, the molding condition providing unit 46c may output the value of the setting condition based on the selected setting condition range. Specifically, for example, the molding condition providing unit 46c may select and output a setting condition from the selected setting condition range, or statistically process the setting condition range (for example, average, median calculation). Output the setting conditions obtained by Here, the setting conditions are, for example, (1) injection speed, (2) VP switching position, (3) holding pressure, and (4) holding pressure time.
  • the waveform of the sensor varies depending on the type of resin (eg, polypropylene, polystyrene, etc.) when the conditions are changed. Focusing on this fact, in the fourth embodiment, a machine learning model is provided for each resin type or resin characteristic (for example, resin viscosity).
  • resin eg, polypropylene, polystyrene, etc.
  • FIG. 15 is a diagram showing an example of the device configuration of a molding condition determination support system according to the fourth embodiment.
  • the information processing device 4 is changed to an information processing device 4d as compared with the system according to the first embodiment shown in FIG.
  • FIG. 16 is a functional block diagram of the information processing device of the molding condition determination support system in the fourth embodiment.
  • the model generating section 45 is changed to a model generating section 45d, and the molding condition providing section 46 is replaced with the molding condition providing section 46d, as compared with the one in the first embodiment shown in FIG. , and an input unit 49 is added.
  • the input unit 49 receives input from the user (for example, resin type or resin characteristics).
  • FIG. 17 is a schematic diagram illustrating an example of a machine learning model stored in a storage unit; As shown in FIG. 17, machine learning models 48-1, . . . , 48-N (N is an integer equal to or greater than 2) are stored.
  • the model generation unit 45d may generate a machine learning model for each resin type or resin characteristic (for example, resin viscosity) and store it in the storage unit 48 as shown in FIG.
  • the storage unit 48 may store a machine learning model for each resin type or resin characteristic (for example, resin viscosity).
  • the acquisition unit 42 may acquire the type of resin or the characteristics of the resin input by the user.
  • the molding condition providing unit 46d refers to the storage unit 48 to select a machine learning model corresponding to the type of resin or the physical properties of the resin input by the user, and uses the selected machine learning model to perform at least one You may output the value of one setting condition.
  • the model generation unit 45d may generate a machine learning model whose input parameters include the type of resin or physical properties of the resin. More specifically, the model generation unit 45d generates a waveform during molding by inputting the type of resin or physical properties of the resin in addition to the value of at least one setting condition and the waveform data during molding at the value of the setting condition.
  • a machine learning model may be generated that learns so that the difference between the data and the reference waveform data becomes smaller.
  • the storage unit 48 may store a machine learning model whose input parameters include the type of resin or physical properties of the resin.
  • the acquisition unit 42 may acquire the type of resin or the characteristics of the resin input by the user.
  • the molding condition providing unit 46d may output at least one setting condition value by inputting the resin type or resin characteristics input by the user into the machine learning model.
  • one storage unit stores, but it may be distributed and stored in a plurality of storage units.
  • the processing is described as being executed by one processor, but the processing may be executed by a plurality of processors.
  • the information processing apparatus provides information processing for outputting information regarding the setting conditions of a molding machine that molds a molded product by supplying a molten material to a cavity of a mold (for example, a mold). It is a device.
  • waveform data detected by a sensor provided in the molding machine (for example, a heater) or the mold during molding of a predetermined molded product is used as a reference.
  • at least one storage device storing at least one reference waveform data.
  • the information processing apparatus further acquires reference waveform data by referring to the storage device, and acquires at least one waveform data in one shot during molding of the molded product from the sensor.
  • At least one setting condition value and the waveform data at the time of molding at the value of the setting condition are input, and a machine learning model is used that learns so that the difference between the waveform data at the time of molding and the reference waveform data becomes small.
  • a machine learning model is used that learns so that the difference between the waveform data at the time of molding and the reference waveform data becomes small.
  • the operating data of the molding machine for each molding shot (e.g., motor current, motor torque, etc.) is monitored, and the waveform of the sensor during the molding shot is determined by adding the information of the operating data.
  • Condition adjustment is performed so that it approaches the reference waveform of the sensor.
  • the setting condition is a value specified on the molding machine side in order to operate the molding machine.
  • the operating data is a value representing the operation of the molding machine when the molding machine is operated under the set conditions, and the value changes with time.
  • FIG. 18 is an external view of a molding machine of a molding condition determination support system according to the fifth embodiment.
  • the molding machine 1 is provided with a motor 13 for driving the screw and a current sensor 14 for detecting the current of the motor 13 .
  • FIG. 19 is a diagram showing an example of the device configuration of a molding condition determination support system according to the fifth embodiment.
  • a molding condition determination support system 100e according to the fifth embodiment differs from that of the first embodiment shown in FIG. 3 in that the information processing device 4 is changed to an information processing device 4e.
  • FIG. 20 is a functional block diagram of the information processing device of the molding condition determination support system in the fifth embodiment.
  • the information processing device 4 e includes a communication unit 41 , an acquisition unit 42 , a storage unit 48 , a state estimator 51 and a condition adjustment unit 52 . Since the communication unit 41 and the acquisition unit 42 are the same as those in the first embodiment, description thereof will be omitted.
  • a learning model database (DB) 481 is constructed in the storage unit 48 .
  • the storage unit 48 stores at least one reference waveform data which is waveform data detected by a sensor provided in the molding machine 1 or the mold when a non-defective product is molded for a predetermined molded product, and which is used as a reference. At least one piece of reference operation data, which is the operation data of the controller 30 that controls 1 and serves as a reference, is stored.
  • the state estimator 51 acquires the current value of the motor 13 detected by the current sensor 14 (hereinafter also referred to as the motor current value) as data related to the extrusion torque of the molding machine 1 .
  • the state estimator 51 may obtain data on the extrusion torque of the molding machine 1 from parameters input to the molding machine 1 .
  • the state estimator 51 may acquire from the controller 30 the motor current value included in the molding machine data received by the controller 30 from the molding machine 1 as the data on the extrusion torque of the molding machine 1 .
  • the state estimator 51 acquires a parameter related to the viscosity of the resin to be poured into the mold (hereinafter referred to as a viscosity parameter) from the data related to the extrusion torque. In this way, the state estimator 51 can be used to obtain the characteristic values (eg, current or torque) of the motor 13 provided in the molding machine 1 and/or the characteristic values (eg, current or torque) of the motor 13 stored in the controller 30. ), the physical properties of the resin in the molding machine 1 are estimated.
  • a viscosity parameter a parameter related to the viscosity of the resin to be poured into the mold
  • the condition adjustment unit 52 has a condition adjustment AI 521 .
  • the learning model database 481 of the storage unit 48 stores, for example, a machine learning model (specifically, parameters of the machine learning model) for each physical property of resin.
  • the condition adjustment AI 521 can record and read machine learning models corresponding to resin physical properties (for example, viscosity parameters) from the learning model database 481 .
  • resin physical properties for example, viscosity parameters
  • condition adjustment unit 52 determines the molding conditions so as to approximate the reference waveform of the sensor.
  • condition adjustment unit 52 generates a first difference that is the difference between the waveform data at the time of molding and the reference waveform data.
  • the condition adjustment unit 52 also generates a second difference between the operating data of the molding machine and the reference operating data. These first difference and second difference are input to the condition adjustment AI 521 .
  • the condition adjustment AI 521 receives at least one setting condition value and a first difference and a second difference at the time of the setting condition value, and adjusts the difference between the waveform data at the time of molding and the reference waveform data to be small.
  • a waveform identical or similar to the reference waveform data by processing the value of at least one setting condition and the first difference and the second difference at the value of the setting condition using a machine learning model that learns to At least one value of the setting condition detected by the sensor 23 is output.
  • the condition adjustment AI 521 is a machine learning model (for example, Bayesian optimization) aimed at optimizing a black-box function that outputs an evaluation value based on the first difference and the second difference. is the same as the reference waveform data by processing the first difference and the second difference between the value of at least one setting condition and the value of the setting condition so as to optimize the evaluation value using Alternatively, it outputs the value of at least one setting condition for which the sensor detects similar waveform data.
  • a machine learning model for example, Bayesian optimization
  • condition adjustment unit 52 adjusts the characteristic value (eg current or torque) of the motor provided in the molding machine 1 and/or the characteristic value (eg current or torque) of the motor stored in the controller 30 ) may be used to estimate the physical properties of the resin in the molding machine 1, and a machine learning model corresponding to the estimated physical properties of the resin may be used to output the value of at least one set condition.
  • characteristic value eg current or torque
  • the characteristic value eg current or torque
  • the storage unit 48 may store a machine learning model that includes resin physical properties as input parameters.
  • the condition adjustment unit 52 adjusts the characteristic value (eg current or torque) of the motor 13 provided in the molding machine 1 and/or the characteristic value (eg current or torque) of the motor 13 stored in the controller 30 ) to estimate the physical properties of the resin in the molding machine 1, input the estimated physical properties of the resin into the machine learning model, and output the value of at least one set condition.
  • condition adjusting unit 52 directly feeds back the value of the setting condition determined by the condition adjustment AI 521 to the molding machine 1.
  • the value may be output to the molding machine 1.
  • one storage unit stores, but it may be distributed and stored in a plurality of storage units.
  • the processing is described as being executed by one processor, but the processing may be executed by a plurality of processors.
  • the information processing device in the fifth embodiment is an information processing device that outputs information about the setting conditions of a molding machine that molds a molded product by supplying a molten material to a cavity of a mold (for example, a mold).
  • the information processing apparatus according to the fifth embodiment includes at least one reference waveform data which is waveform data detected by a sensor provided in the molding machine or the mold during molding of the predetermined molded product and serves as a reference. and at least one storage device storing at least one reference operation data which is operation data of a controller for controlling the molding machine during molding of a non-defective product and serves as a reference.
  • the information processing apparatus in the fifth embodiment further inputs at least one setting condition value and a first difference and a second difference at the time of the setting condition value, waveform data at the time of molding and the reference waveform
  • the reference It comprises at least one processor that outputs at least one value of a setting condition for the sensor to detect waveform data that is the same as or similar to the waveform data.
  • At least one set condition to be output is at least one of injection speed, VP switching position, holding pressure, and holding pressure time, for example.
  • the sixth embodiment is different in that an information processing system having the functions of any one of the first to fifth information processing devices is connected via a communication network to the terminal device 6 in which the molding machine 1 is installed. ing.
  • FIG. 21 is a schematic configuration diagram of a molding condition determination support system in the sixth embodiment.
  • the molding condition determination support system 100f is provided with a terminal device 6 connected to the output of the A/D converter 3, and the information processing device 4 is different from that of the first embodiment. It has been changed to System 4f.
  • the information processing system 4f has the functions of any one of the first to fifth information processing devices, and is configured by, for example, one or a plurality of information devices.
  • the information processing system 4f can communicate with the terminal device 6 via the communication network CN.
  • the information processing system 4f can receive various data (for example, sensor waveform data, operation data, setting conditions, etc.) from the terminal device 6 .
  • the information processing system 4 f also transmits the value of the setting condition obtained by the processing to the terminal device 6 .
  • the terminal device 6 is connected to the display device 5 and controls the display device to display information including the setting condition values received from the information processing system 4f.
  • the information processing system 4f may be built remotely (for example, in the cloud). As a result, for example, by remotely constructing the information processing system 4f, for a plurality of molding machines 1 installed at a plurality of locations, the values of setting conditions for molding non-defective products can be determined, and the users of the plurality of molding machines 1 can The value of this setting condition can be transmitted to the terminal device 6 used by .
  • At least part of the information processing apparatuses 4, 4b, 4c, 4d, and 4e or the information processing system 4f described in the above-described embodiments may be configured by hardware or may be configured by software.
  • a program for realizing at least part of the function of each device/system is read into each device/system and executed, thereby performing processing for realizing at least part of the function of each device/system. good too.
  • the program is transmitted to other computer systems by transmission waves via computer-readable recording media such as CD-ROMs or magneto-optical disks, or via transmission media such as the Internet and telephone lines. good too.
  • the recording medium is not limited to a removable medium such as a magnetic disk or an optical disk, and may be a fixed type recording medium such as a hard disk device or memory. Also, some systems may be implemented through human actions.
  • the information processing devices 4, 4b, 4c, 4d, and 4e may be implemented as an information processing system having one or more information devices.
  • the information processing devices 4, 4b, 4c, 4d, 4e or the information processing system 4f have a plurality of information devices, at least one of them is a computer, and the computer executes a predetermined program, whereby the information processing device 4 , 4b, 4c, 4d, 4e or the information processing system 4f.
  • the present invention is not limited to the above-described embodiments as they are, and can be embodied by modifying the constituent elements without departing from the gist of the present invention at the implementation stage. Further, various inventions can be formed by appropriate combinations of the plurality of constituent elements disclosed in the above embodiments. For example, some components may be omitted from all components shown in the embodiments. Furthermore, components across different embodiments may be combined as appropriate.
  • Reference Signs List 1 molding machine 2 instrumentation amplifier 3 A/D converter 4, 4b, 4c, 4d, 4e information processing device 4f information processing system 5 display device 6 terminal device 10 injection unit 20 mold clamping unit 21 ejector plate 22 ejector pin 23 sensor 30 Controller 40 Display device 41 Cable 100, 100b, 100c, 100d, 100e, 100f Molding condition determination support system

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Manufacturing & Machinery (AREA)
  • Injection Moulding Of Plastics Or The Like (AREA)

Abstract

Le dispositif de traitement d'informations selon l'invention produit des informations se rapportant à des conditions de réglage pour une machine de moulage servant à introduire un matériau fondu dans la cavité d'une matrice pour mouler un article moulé, le dispositif de traitement d'informations comprenant : au moins un dispositif de stockage qui mémorise au moins une donnée de forme d'onde de référence qui est une donnée de forme d'onde détectée par un capteur fournies à la machine de moulage ou à la matrice au moment du moulage non défectueux d'un article moulé prescrit et qui sert de référence ; et une unité de fourniture de condition de moulage qui référence le dispositif de stockage et qui acquiert des données de forme d'onde de référence, qui acquiert au moins une donnée de forme d'onde pour un tir pendant le moulage de l'article moulé en provenance du capteur, qui utilise un modèle d'apprentissage automatique dans lequel sont introduites au moins une valeur de condition de réglage et des données de forme d'onde correspondant au moment où le moulage est effectué à ladite valeur de condition de réglage, le modèle d'apprentissage machine effectuant un apprentissage de façon à faire diminuer la différence entre les données de forme d'onde correspondant au moment où le moulage est effectué et les données de forme d'onde de référence, qui traite au moins une valeur de condition de réglage et des données de forme d'onde correspondant au moment où le moulage est effectué à ladite valeur de condition de réglage, et qui produit ainsi au moins une valeur de condition de réglage à laquelle le capteur détecte des données de forme d'onde qui sont identiques ou similaires aux données de forme d'onde de référence.
PCT/JP2022/041605 2021-11-09 2022-11-08 Dispositif de traitement d'informations, système de traitement d'informations, et programme WO2023085283A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2023559646A JPWO2023085283A1 (fr) 2021-11-09 2022-11-08

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2021-182728 2021-11-09
JP2021182728 2021-11-09

Publications (1)

Publication Number Publication Date
WO2023085283A1 true WO2023085283A1 (fr) 2023-05-19

Family

ID=86336105

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/041605 WO2023085283A1 (fr) 2021-11-09 2022-11-08 Dispositif de traitement d'informations, système de traitement d'informations, et programme

Country Status (2)

Country Link
JP (1) JPWO2023085283A1 (fr)
WO (1) WO2023085283A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH07205230A (ja) * 1994-01-26 1995-08-08 Fanuc Ltd 射出成形機におけるリザーバ内圧調整方法
US20160158985A1 (en) * 2014-12-04 2016-06-09 Extrude To Fill, LLC Control system for injection molding
JP2019014187A (ja) * 2017-07-10 2019-01-31 株式会社日本製鋼所 計算機と複数台の射出成形機とからなる射出成形機システム
JP2020062848A (ja) * 2018-10-19 2020-04-23 株式会社Ｉｂｕｋｉ 情報処理装置、情報処理方法、及びプログラム
WO2021091191A1 (fr) * 2019-11-08 2021-05-14 엘에스엠트론 주식회사 Système de moulage par injection basé sur l'intelligence artificielle et procédé pour la création de conditions de moulage

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH07205230A (ja) * 1994-01-26 1995-08-08 Fanuc Ltd 射出成形機におけるリザーバ内圧調整方法
US20160158985A1 (en) * 2014-12-04 2016-06-09 Extrude To Fill, LLC Control system for injection molding
JP2019014187A (ja) * 2017-07-10 2019-01-31 株式会社日本製鋼所 計算機と複数台の射出成形機とからなる射出成形機システム
JP2020062848A (ja) * 2018-10-19 2020-04-23 株式会社Ｉｂｕｋｉ 情報処理装置、情報処理方法、及びプログラム
WO2021091191A1 (fr) * 2019-11-08 2021-05-14 엘에스엠트론 주식회사 Système de moulage par injection basé sur l'intelligence artificielle et procédé pour la création de conditions de moulage

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
HATAKEYAMA-SATO, KEN: "Machine Learning for Material Science", THE BRAIN & NEURAL NETWORKS, vol. 28, no. 1, 5 March 2021 (2021-03-05), pages 20 - 27, XP093067074 *

Also Published As

Publication number Publication date
JPWO2023085283A1 (fr) 2023-05-19

Similar Documents

Publication Publication Date Title
US6258303B1 (en) Apparatus and method of monitoring injection molding operation wherein sprue gate closing point of time is indicated together with displayed parameter waveforms
US9724863B2 (en) Injection molding machine
US20200198201A1 (en) Injection molding system
JP7205225B2 (ja) 成形条件決定支援装置および射出成形機
US11440229B2 (en) Injection molding system, molding condition correction system, and injection molding method
US20200086542A1 (en) Methods for controlling injection molding processes based on actual plastic melt pressure or cavity pressure
CN110948810A (zh) 成型条件决定辅助装置以及注塑成型机
JP2020052821A (ja) 劣化判定装置および劣化判定システム
JP2020163825A (ja) 射出成形システム、成形条件補正システムおよび射出成形方法
JP2015066700A (ja) 粘度測定機能を有する射出成形機および射出成形機を用いた粘度測定方法
US11537945B2 (en) Machine learning device and machine learning method
JP2021062504A (ja) 射出成形機管理支援装置及び射出成形機
US11745403B2 (en) Injection molding system, molding condition correction system, and injection molding method
JP2020108947A (ja) 品質予測システム及び成形機
US20090051064A1 (en) Molding Machine Monitoring Apparatus, Method, and Program
WO2023085283A1 (fr) Dispositif de traitement d'informations, système de traitement d'informations, et programme
US20200206998A1 (en) Quality prediction system and molding machine
EP3552796B1 (fr) Appareil de moulage par injection et procédé de moulage par injection
JP5653599B2 (ja) 成形条件設定画面、成形条件設定装置及び成形条件設定方法
JP2010158841A (ja) 設定画面、射出成形機及び設定画面の表示方法
JP7481048B1 (ja) 情報処理システム、情報処理方法及びプログラム
US20200094461A1 (en) Device for assisting molding condition determination and injection molding apparatus
JP2021527584A (ja) 射出成形機を制御するためのシステムおよびアプローチ
JP2021066057A (ja) 射出成形機管理装置及び射出成形機
JP2020185779A (ja) バルブゲート制御装置および射出成形機

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22892781

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023559646

Country of ref document: JP