[go: up one dir, main page]

WO2021220719A1 - Système de moulage, dispositif de prédiction d'irrégularité, procédé de prédiction d'irrégularité, programme et modèle entraîné - Google Patents

Système de moulage, dispositif de prédiction d'irrégularité, procédé de prédiction d'irrégularité, programme et modèle entraîné Download PDF

Info

Publication number
WO2021220719A1
WO2021220719A1 PCT/JP2021/014311 JP2021014311W WO2021220719A1 WO 2021220719 A1 WO2021220719 A1 WO 2021220719A1 JP 2021014311 W JP2021014311 W JP 2021014311W WO 2021220719 A1 WO2021220719 A1 WO 2021220719A1
Authority
WO
WIPO (PCT)
Prior art keywords
pressure
gate
molding
evaluation value
cavity
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/JP2021/014311
Other languages
English (en)
Japanese (ja)
Inventor
紀行 馬場
幸治 木村
慎太郎 辻
智也 足立
勇佐 大久保
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
JTEKT Corp
Original Assignee
JTEKT Corp
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 JTEKT Corp filed Critical JTEKT Corp
Publication of WO2021220719A1 publication Critical patent/WO2021220719A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

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
    • 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

Definitions

  • This disclosure relates to molding systems, anomaly predictors, anomaly prediction methods, programs and trained models.
  • Patent Document 1 discloses an injection molding apparatus that injects a molding material into a mold.
  • Patent Document 1 as a countermeasure against molding defects (gas residual defects) caused by gas remaining in the cavity, molding is performed so that the forward position of the screw is retracted by a predetermined amount when a gas residual defect is confirmed by a quality check. Change the condition settings. As described above, Patent Document 1 discloses a technique for changing the molding conditions so that the gas discharge capacity is superior to the filling amount of the resin in the cavity.
  • the mold wears as the number of moldings increases. Since the wear of the mold affects the quality of the molded product, at present, the time when the mold is replaced at a certain number of times of molding or determined by intuition and tips based on the skill level of the operator who performs injection molding. I am exchanging molds at. For this reason, if the timing of mold replacement is incorrect, the molded product may be defective or the man-hours may be increased due to wasteful mold replacement.
  • the quality of the molded product is checked, and it is confirmed that the molded product has a defect or a tendency to become defective due to the wear of the mold. After determining, decide to replace the mold. Since the quality check is performed by a visual inspection of the worker or the like, the accuracy of the quality check largely depends on the skill level of the worker. In addition, since man-hours are required for workers, the burden of inspection is large. Therefore, there is a demand for a technique for automatically determining an appropriate mold replacement timing regardless of the skill level of the operator.
  • an object of the present disclosure is to provide a molding system for predicting a wear state of a gate, an abnormality prediction device, an abnormality prediction method, a program, and a trained model.
  • the present disclosure is a molding system including a molding device for molding a molded product and an abnormality predicting device for predicting an abnormality of the molding device.
  • the molding device forms a cavity inside and is described as described above.
  • a mold portion having a gate that opens on the cavity side, a filling operation of filling the cavity with a molten molding material via the gate, and holding the pressure of the molding material filled in the cavity.
  • the abnormality predictor has an injection unit that performs a pressure operation and a pressure release operation for releasing the pressure holding of the molding material, and a pressure sensor that detects the pressure of the molding material in the cavity.
  • a molding system having an abnormality prediction unit for acquiring prediction information for predicting a wear state of a gate.
  • the molding system acquires prediction information for predicting the wear state of the gate based on the maximum value of the pressure of the molding material in the cavity between the pressure holding operation and the pressure releasing operation. .. This makes it possible to predict the wear state of the gate from the information acquired by the pressure sensor provided in the molding apparatus.
  • the present disclosure is the molding system according to the above (1), and the abnormality prediction unit is generated based on the first evaluation value acquired when the wear state of the gate is normal.
  • the first evaluation value acquired at the time of molding the molded product to be predicted becomes larger than the 1 reference value
  • the molding indicating that the gate is worn is acquired.
  • a system may be provided. With this configuration, the wear state of the gate can be easily predicted by comparing the first reference value and the first evaluation value.
  • the present disclosure is the molding system according to the above (2), in which the abnormality prediction unit molds a plurality of the molded products to be predicted by the molding apparatus and continuously over a predetermined plurality of times. Even if a molding system is provided that obtains the prediction information indicating that the gate is worn when the acquired first evaluation value is larger than the first reference value. good. With such a configuration, it is possible to exclude the influence of sudden disturbance and more accurately predict the wear state of the gate.
  • the present disclosure is the molding system according to the above (1), in which the injection portion stores the molded material in a molten state and is inserted into the cylinder and a cylinder connected to the mold portion.
  • the molding apparatus has a screw that pushes the molded material in a molten state toward the mold portion, and the molding apparatus detects the pressure of the molding material in the cylinder or the pressure that the screw receives from the molding material.
  • the data acquisition unit further has a second pressure sensor, and the data acquisition unit is based on the maximum value of the pressure detected by the second pressure sensor between the pressure holding operation and the pressure releasing operation.
  • the abnormality prediction unit may provide a molding system that acquires the value and acquires the prediction information based on the difference or ratio between the first evaluation value and the first reference value.
  • both the first reference value and the first evaluation value are acquired when the molded product to be predicted is molded once, regardless of whether the wear state of the gate is normal or not. be able to. Therefore, for example, even if the molding conditions (pressurization, mold clamping force, type of molding material, etc.) are changed while using the same mold portion, the first reference can be easily obtained after the change. It is possible to get the value.
  • the present disclosure is the molding system according to (1) above, and the abnormality prediction unit uses a trained model in which the correlation between the first evaluation value and the wear state of the gate is machine-learned.
  • the prediction information is acquired, the explanatory variable of the trained model includes the first evaluation value, and the objective variable of the trained model is the inner diameter of the gate or the inner diameter of the gate.
  • a molding system may be provided that includes the amount of wear of the gate. With this configuration, the wear state of the gate can be predicted more accurately even when the molding conditions vary.
  • the present disclosure is the molding system according to any one of (1) to (5) above, and the data acquisition unit is based on the time-series data of the pressure detected by the pressure sensor.
  • the second evaluation value regarding the change in the pressure of the molding material after the holding pressure release operation is acquired, and the abnormality prediction unit obtains one or more of the prediction information based on the first evaluation value and the second evaluation value. May provide a molding system to obtain.
  • the molding system according to the present disclosure has both a first evaluation value based on the maximum pressure during the pressure holding process and a second evaluation value based on a change in the pressure of the molding material in the cavity after the pressure holding release operation. Based on, the prediction information for predicting the wear state of the gate is acquired. This makes it possible to more accurately predict the wear state of the gate from the information acquired by the pressure sensor provided in the molding apparatus.
  • the present disclosure is an abnormality predicting device for predicting an abnormality of a molding device for molding a molded product, in which the molding device has a mold portion having a cavity formed inside and a gate opening on the cavity side.
  • the abnormality predicting device has the injection portion for performing the pressure holding release operation, and the pressure sensor for detecting the pressure of the molding material in the cavity, and the abnormality predicting device releases the pressure holding from the pressure holding operation.
  • a data acquisition unit that acquires the maximum value of the pressure detected by the pressure sensor as the first evaluation value until the operation, and prediction information for predicting the wear state of the gate based on the first evaluation value.
  • an abnormality prediction device including an abnormality prediction unit for acquiring the above.
  • the abnormality prediction device acquires prediction information for predicting the wear state of the gate based on the maximum value of the pressure of the molding material in the cavity from the pressure holding operation to the pressure releasing operation. This makes it possible to predict the wear state of the gate from the information acquired by the pressure sensor provided in the molding apparatus.
  • the present disclosure comprises a mold portion having a gate that forms a cavity inside and opens on the cavity side, and a filling operation that fills the cavity with a molten molding material via the gate.
  • a molding apparatus for molding a molded product having an injection portion for performing a pressure holding operation for holding the pressure of the molding material filled in the cavity and a pressure holding release operation for releasing the pressure holding of the molding material.
  • the maximum value of the pressure detected by the pressure sensor that detects the pressure of the molding material in the cavity between the pressure holding operation and the pressure releasing operation is the first, which is an abnormality prediction method for predicting the abnormality.
  • an abnormality prediction method including a data acquisition step of acquiring as one evaluation value and an abnormality prediction step of acquiring prediction information for predicting a wear state of the gate based on the first evaluation value.
  • the abnormality prediction method acquires prediction information for predicting the wear state of the gate based on the maximum value of the pressure of the molding material in the cavity between the pressure holding operation and the pressure releasing operation. This makes it possible to predict the wear state of the gate from the information acquired by the pressure sensor provided in the molding apparatus.
  • the present disclosure includes a mold portion having a gate that forms a cavity inside and opens on the cavity side, and a filling operation that fills the cavity with a molten molding material via the gate.
  • a molding apparatus for molding a molded product having an injection portion for performing a pressure holding operation for holding the pressure of the molding material filled in the cavity and a pressure holding release operation for releasing the pressure holding of the molding material.
  • the maximum value of the pressure detected by the pressure sensor that detects the pressure of the molding material in the cavity during the period from the pressure holding operation to the pressure releasing operation is the program for predicting the abnormality of the above.
  • the program according to the present disclosure is a computer that acquires prediction information for predicting the wear state of a gate based on the maximum value of the pressure of the molding material in the cavity between the pressure holding operation and the pressure releasing operation. Let the device do it. This makes it possible to predict the wear state of the gate from the information acquired by the pressure sensor provided in the molding apparatus.
  • the present disclosure comprises a mold portion having a gate that forms a cavity inside and opens on the cavity side, and a filling operation that fills the cavity with a molten molding material via the gate.
  • a molding apparatus for molding a molded product having an injection portion for performing a pressure holding operation for holding the pressure of the molding material filled in the cavity and a pressure holding release operation for releasing the pressure holding of the molding material.
  • the explanatory variables are detected by a pressure sensor that detects the pressure of the molding material in the cavity between the pressure holding operation and the pressure releasing operation.
  • a trained model is provided that includes a first evaluation value obtained based on the maximum pressure value, and the objective variable includes the inner diameter of the gate or the amount of wear of the gate.
  • the explanatory variable is the first evaluation value regarding the maximum value of the pressure of the molding material in the cavity between the pressure holding operation and the pressure releasing operation
  • the objective variable is the inner diameter of the gate or the gate. Since it is the amount of wear, if the first evaluation value is input to the trained model, the predicted wear state of the gate is output. Thereby, the wear state of the gate can be predicted by the first evaluation value acquired based on the detected value of the pressure sensor.
  • FIG. 1 is a block diagram schematically showing a molding system according to the first embodiment.
  • FIG. 2 is an explanatory diagram conceptually showing the molding apparatus according to FIG. 1.
  • FIG. 3 is an explanatory diagram conceptually showing the molding apparatus according to FIG. 1.
  • FIG. 4 is a cross-sectional view of a mold portion schematically showing a state at the end of the filling process.
  • FIG. 5 is a cross-sectional view showing a mold portion cut by the cutting line indicated by the arrow V in FIG.
  • FIG. 6 is a cross-sectional view showing a mold portion cut by the cutting line of the arrow VI of FIG.
  • FIG. 7 is an example of a graph showing time series data of pressure.
  • FIG. 8 (a) and 8 (b) are explanatory views schematically showing the state at the start and end of the pressure holding process when the gate is normal.
  • 9 (a) and 9 (b) are explanatory views schematically showing the state at the start and end of the pressure holding process when the gate is abnormal.
  • FIG. 10 is a block diagram showing a functional configuration of the learning device according to the first embodiment.
  • 11 (a) and 11 (b) are graphs schematically explaining the evaluation values according to the first embodiment.
  • FIG. 12 is a block diagram showing a functional configuration of the abnormality prediction device according to the first embodiment.
  • FIG. 13 is a block diagram schematically showing the molding system according to the second embodiment.
  • FIG. 14 is a block diagram showing a functional configuration of the abnormality prediction device according to the second embodiment.
  • 15 (a) and 15 (b) are graphs schematically explaining a method for determining an abnormality according to a modified example.
  • FIG. 1 is a block diagram schematically showing a molding system 10 according to the first embodiment.
  • the molding system 10 includes a plurality of molding devices 20, a learning device 30, an abnormality prediction device 40, an input unit 50, and a display unit 60.
  • the molding device 20, the learning device 30, the abnormality prediction device 40, the input unit 50, and the display unit 60 are each provided so as to be able to communicate wirelessly or by wire.
  • the learning device 30 and the abnormality prediction device 40 are composed of an information processing device (computer device) having a calculation unit (for example, CPU, GPU, etc.) and a storage unit (for example, HDD, SSD, etc.).
  • the learning device 30 and the abnormality prediction device 40 may be configured by the same information processing device or may be configured by separate information processing devices.
  • a plurality of molding devices 20 are connected to one learning device 30 and one abnormality prediction device 40, and the learning device 30 and the abnormality prediction device 40 are used for various data transmitted from the plurality of molding devices 20. Based on this, learning and abnormality prediction are performed.
  • the molding device 20 may have a one-to-one correspondence with the learning device 30 and the abnormality prediction device 40. That is, in the molding system 10, the molding device 20 may be one, or a plurality of learning devices 30 and abnormality prediction devices 40 may be provided.
  • the input unit 50 is, for example, a keyboard or a mouse, and receives various inputs from the operator.
  • the display unit 60 is, for example, a display or a speaker, and displays various information in the molding system 10.
  • the input unit 50 and the display unit 60 may be integrated, for example, a touch panel. Further, the input unit 50 and the display unit 60 may be provided as a portable terminal device so as to be movable to a place away from the molding device 20, the learning device 30, and the abnormality prediction device 40.
  • FIGS. 2 and 3 are explanatory views conceptually showing the molding apparatus 20.
  • the molding apparatus 20 includes a bed 21, an injection portion 22, a mold clamping portion 23, a mold portion 24, a pressure sensor 25, a temperature sensor 26, and a control panel 27.
  • FIG. 2 shows a molding apparatus 20 in a state where the mold portion 24 is open
  • FIG. 3 shows a molding apparatus 20 in a state where the mold portion 24 is combined.
  • the molding apparatus 20 is an apparatus for performing mold-fastening injection molding.
  • the control panel 27 has a control unit 271 and a communication unit 272.
  • the control unit 271 is electrically connected to each drive unit (motor 237, etc.) of the molding apparatus 20 and outputs an operation command to each drive unit. Further, the control unit 271 is electrically connected to each sensor (pressure sensor 25 or the like) of the molding apparatus 20, and the signal detected by each sensor is input to the control unit 271.
  • the control unit 271 is composed of an information processing device having a calculation unit (for example, CPU, GPU, etc.) and a storage unit (for example, HDD, SSD, etc.).
  • the communication unit 272 communicates with each other unit (learning device 30, etc.) of the molding system 10.
  • the communication unit 272 transmits, for example, the signal detected by each of the sensors to the learning device 30 or the abnormality prediction device 40. Further, the communication unit 272 receives the determination information and the prediction information described later from the abnormality prediction device 40.
  • the mold clamping portion 23 includes a fixed plate 231, a movable plate 232, a tie bar 233, a ball screw 234, a support plate 235, a mold clamping force sensor 236, and a motor 237.
  • the fixing plate 231 and the supporting plate 235 are fixed to the bed 21.
  • the support board 235 supports the ball screw 234.
  • the ball screw 234 is connected to the motor 237. When the motor 237 is rotated by the operation command of the control unit 271, the ball screw 234 moves.
  • a movable platen 232 is fixed to the end of the ball screw 234 opposite to the end connected to the motor 237.
  • the direction in which the ball screw 234 moves is referred to as an "axial direction".
  • the side where the motor 237 is located with respect to the ball screw 234 is referred to as the "one side” in the axial direction
  • the side where the movable platen 232 is located with respect to the ball screw 234 is referred to as the “other side” in the axial direction.
  • the movable board 232 moves in the axial direction as the ball screw 234 moves.
  • the movable platen 232 is formed with a through hole 232a penetrating in the axial direction.
  • the end of the tie bar 233 on one side in the axial direction is fixed to the support plate 235, and the end on the other side in the axial direction is fixed to the fixing plate 231.
  • the tie bar 233 is inserted into the through hole 232a of the movable platen 232. As a result, the tie bar 233 guides the axial movement of the movable platen 232.
  • the mold clamping force sensor 236 detects the pressure (reaction force of the mold clamping force) applied to the support plate 235 from the ball screw 234.
  • the mold clamping force sensor 236 outputs a pressure detection signal to the control unit 271.
  • the mold clamping force sensor 236 may be installed at another position as long as it can detect the mold clamping force in the mold portion 24 described later.
  • the fixing plate 231 is formed with a through hole 231a having a diameter widened on the other side in the axial direction. A cylinder 222, which will be described later, is inserted into the through hole 231a.
  • the mold unit 24 has a plurality of molds 241 and 242.
  • the mold 241 is fixed to the movable platen 232.
  • the mold 241 moves in the axial direction together with the movable platen 232. That is, the mold 241 is a movable mold.
  • the mold 242 is fixed to the fixing plate 231. That is, the mold 242 is a fixed mold.
  • a flow path 243 is formed in the mold 242.
  • the cavity C1 of the present embodiment is an annular space filled with a molding material.
  • the injection unit 22 includes a hopper 221, a cylinder 222, a screw 223, a ball screw 225, a motor 226, a pressurization sensor 227, a pressure sensor 227a, a movement amount sensor 228, and a heater 229.
  • the hopper 221 is connected to the cylinder 222 and supplies the molding material into the cylinder 222.
  • the cylinder 222 is a member having a hollow cylindrical shape extending in the axial direction. The diameter of the one-sided end portion of the cylinder 222 in the axial direction becomes narrower as it approaches the one-sided end in the radial direction, and the nozzle 224 is provided at the one-sided end in the axial direction of the cylinder 222.
  • the nozzle 224 is connected to the flow path 243 of the mold 242.
  • the screw 223 is inserted into the cylinder 222 from the end on the other side in the axial direction of the cylinder 222.
  • a ball screw 225 is connected to the other side of the screw 223 in the axial direction, and a motor 226 is connected to the other side of the ball screw 225 in the axial direction.
  • the motor 226 is rotated by the operation command of the control unit 271
  • the ball screw 225 moves in the axial direction.
  • the screw 223 also moves in the axial direction.
  • the screw 223 rotates in the circumferential direction with the axial direction as the central axis.
  • the pressurization sensor 227 detects the pressure applied from the ball screw 225 to the motor 226 (the reaction force of the pushing force of the screw 223). That is, the pressurization sensor 227 detects the pressure that the screw 223 receives from the molding material L1.
  • the pressurization sensor 227 outputs a detection signal related to pressure to the control unit 271.
  • the pressurization sensor 227 may be installed at another position as long as it can detect the pushing force of the screw 223.
  • the pressure sensor 227a is installed on the inner peripheral surface of the cylinder 222 and detects the pressure received by the cylinder 222 from the molding material L1.
  • the pressure sensor 227a outputs a pressure detection signal to the control unit 271.
  • At least one of the pressurization sensor 227 and the pressure sensor 227a functions as the "second pressure sensor" of the present disclosure.
  • the movement amount sensor 228 detects the movement amount of the ball screw 225 in the axial direction.
  • the movement amount sensor 228 outputs a detection signal related to the movement amount to the control unit 271.
  • the movement amount sensor 228 may be installed at another position as long as it can detect the movement amount of the ball screw 225 in the axial direction.
  • the heater 229 is, for example, a resistance heating heater in which a resistance wire is wound in a coil shape.
  • the heater 229 heats the inside of the cylinder 222 by the resistance heat when a current is passed through the resistance wire by the operation command of the control unit 271.
  • the pressure sensor 25 (“pressure sensor” of the present disclosure) is installed on the surface of the molds 241 and 242 exposed to the cavity C1. More specifically, the pressure sensor 25 is installed on a surface of the surface exposed to the cavity C1 that is close to the gate 243b (FIG. 4) described later.
  • the pressure sensor 25 detects the pressure in the cavity C1.
  • the pressure sensor 25 detects the pressure of the molding material (melted state or solidified state, or a state in which the molten state and the solidified state are mixed) supplied into the cavity C1.
  • the pressure sensor 25 outputs a detection signal related to pressure to the control unit 271.
  • one pressure sensor 25 is installed in the mold 242. However, a plurality of pressure sensors 25 may be installed in both the molds 241 and 242, respectively.
  • the temperature sensor 26 is built in the mold 241 and detects the temperature of the mold 241.
  • the temperature sensor 26 outputs a detection signal related to temperature to the control unit 271.
  • the temperature sensor 26 may be installed in a region of the mold 241 facing the cavity C1 or may be installed in the mold 242. Further, the temperature sensor 26 may be installed in the cylinder 222. That is, the temperature sensor 26 may be able to directly or indirectly detect the temperature of the molding material supplied into the cavity C1.
  • a method of manufacturing a molded product by the molding apparatus 20 will be described with reference to FIGS. 2 to 5 as appropriate.
  • the pre-process ST1, the mold clamping process ST2, the filling process ST3, the pressure holding process ST4, the pressure holding release process ST5, and the mold release process ST6 are performed in this order. Will be executed.
  • the molded product is a resin cage used for rolling bearings.
  • this is an example of a molded product, and the molded product molded by the molding apparatus according to the present disclosure may be a molded product having another shape and use.
  • the pre-process ST1 is executed.
  • the screw 223 is rotated by the motor 226, and the pellets of the molding material are supplied from the hopper 221 into the cylinder 222 while the inside of the cylinder 222 is heated by the heater 229.
  • the pellets of the molding material are melted in the cylinder 222 by the frictional heat accompanying the rotation of the screw 223 and the heating by the heater 229, and become the molding material L1 in the molten state.
  • the previous step ST1 is completed.
  • the ball screw 234 is moved to the other side in the axial direction by the operation command of the control unit 271, and the mold is as shown in FIG.
  • the 241 is brought into contact with the mold 242.
  • the ball screw 234 further presses the mold 241 against the mold 242 toward the other side in the axial direction by a predetermined mold tightening force. That is, the plurality of molds 241 and 242 are tightened.
  • an annular cavity C1 is formed between the plurality of molds 241 and 242.
  • the mold clamping force is one of the molding conditions, and is determined according to other molding conditions such as the shape of the molds 241 and 242.
  • the mold clamping force is detected by the mold clamping force sensor 236.
  • the ball screw 225 moves to one side in the axial direction while maintaining the above-mentioned mold clamping force.
  • the screw 223 pushes the molding material L1 to one side in the axial direction, and the molten molding material L1 is ejected from the nozzle 224 of the cylinder 222 to the cavity C1 via the flow path 243 of the mold 242 (filling operation). ..
  • FIG. 4 is a cross-sectional view of the mold portion 24 schematically showing the state at the end of the filling step ST3.
  • FIG. 5 is a cross-sectional view of the mold portion 24 cut by the cutting line indicated by the arrow V in FIG.
  • FIG. 6 is a cross-sectional view of the mold portion 24 cut by the cutting line of the arrow VI of FIG.
  • the flow path 243 has a first opening 243a that opens on the nozzle 224 side and a second opening 243b that opens on the cavity C1 side. Since the second opening 243b functions as a gate for supplying the molding material L1 from the flow path 243 into the cavity C1, it is hereinafter referred to as “gate 243b”.
  • the cavity C1 is formed in an annular shape.
  • the pressure sensor 25 is installed so as to face the region of the cavity C1 closest to the gate 243b.
  • the pressure sensor 25 is installed close to the direction in which the gate 243b faces (in the present embodiment, the radial direction of the cavity C1) when the cavity C1 is viewed in the axial direction as shown in FIG.
  • the gate 243b has a circular inner peripheral surface. Further, the gate 243b has an inner diameter smaller than the inner diameter of other parts of the flow path 243. With such a configuration, it is possible to realize a good gate cut (cutting the connection between the molded product of the cavity C1 portion and the runner of the flow path 243 portion) when the molded product is molded. On the other hand, the gate 243b has a characteristic that it is easily worn because the inner diameter of the gate 243b is smaller than that of other parts of the flow path 243. Since the wear of the gate 243b particularly affects the quality of the molded product, when the gate 243b is worn to some extent, it becomes necessary to replace the mold portion 24.
  • the filling step ST3 ends.
  • the molten molding material L1 is supplied into the cavity C1 while gradually solidifying from the vicinity of the surface of the molds 241 and 242.
  • the screw 223 further pushes the molding material L1 to one side in the axial direction, and the molding material L1 is further injected from the nozzle 224 of the cylinder 222 into the cavity C1.
  • a predetermined pressure for example, several tens to several hundreds of MPa
  • the screw 223 continues to apply a predetermined pressure to the molding material L1 for a predetermined time (for example, several seconds) (pressure holding operation).
  • the pressure (pressurization) at which the screw 223 pushes the molding material L1 into the cavity C1 is detected by the pressurization sensor 227 and the pressure sensor 227a.
  • the screw 223 moves to the other side in the axial direction to release the pressure holding of the molding material L1 (pressure holding release operation).
  • the holding pressure releasing step ST5 ends.
  • the mold release step ST6 the mold portion 24 is cooled, so that the molding material L1 in the cavity C1 is solidified to form a molded product.
  • the ball screw 234 moves to one side in the axial direction, and the mold 241 separates from the mold 242, so that the molded product is taken out.
  • the cooling of the mold portion 24 may be started at the same time as the pressure holding release step ST5.
  • FIG. 7 is an example of a graph showing time-series data of the pressure detected by each sensor of the molding apparatus 20 in the filling process ST3, the pressure holding process ST4, and the pressure holding release step ST5.
  • the vertical axis is the pressure P and the horizontal axis is the time t.
  • the graph line F0 is time-series data of the pressure detected by the pressurization sensor 227 (“second time-series data” of the present disclosure).
  • Graph lines F1 and F2 are time-series data of pressure detected by the pressure sensor 25 (“time-series data” of the present disclosure).
  • the graph line F1 is a pressure sensor when the gate 243b is not worn, or when the wear is such that the quality of the molded product is not adversely affected even if the gate 243b is worn (hereinafter, appropriately referred to as “when the gate is normal”). It is the time series data of the pressure detected by 25.
  • the graph line F1 is time-series data of the pressure detected when molding is performed for the first time by the mold portion 24.
  • the graph line F2 is time series data of the pressure detected by the pressure sensor 25 when the gate 243b has abnormal wear (more specifically, there is wear to the extent that it adversely affects the quality of the molded product).
  • the graph line F0 tends to obtain substantially the same graph if the molding conditions (molding force, pressurization, holding time, etc.) are the same regardless of whether the gate 243b is normal or abnormal.
  • the graph line F0 rises to the pressure Ps1 in the filling step ST3.
  • the pressure Ps1 is the "set pressure" of the pressure holding step ST4. That is, during the pressurization step ST4, the control unit 271 feedback-controls the motor 226 so that the pressure detected by the pressurization sensor 227 is maintained at Ps1. Therefore, during the pressurization step ST4, the pressure detected by the pressurization sensor 227 becomes substantially constant at Ps1.
  • the pressure holding step ST4 starts at time point X1 and ends at time point X2. That is, the holding time is (X2-X1). After that, the pressure drops in the pressure holding release step ST5.
  • the holding pressure release step ST5 is started from the time point X2. That is, the holding pressure release operation is executed at the time point X2.
  • the graph line F1 rises after the graph line F0 rises in the filling step ST3, the pressure rises to the maximum pressure Pt1 in the pressure holding step ST4, then the pressure decreases, and the pressure suddenly increases in the pressure releasing step ST5. descend.
  • the graph line F2 rises after the graph line F0 rises in the filling step ST3, the pressure rises to the maximum pressure Pt2 in the pressure holding step ST4, then the pressure decreases, and the pressure suddenly increases in the pressure holding release step ST5. descend.
  • the graph line F1 when the gate is normal
  • the graph line F2 when the gate is abnormal
  • the first point is the maximum pressure in the pressure holding step ST4.
  • the maximum pressure Pt2 on the graph line F2 tends to be larger than the maximum pressure Pt1 on the graph line F1.
  • the maximum pressure increases as a result of the lack of attenuation. That is, the maximum pressure of the molding material L1 in the cavity C1 in the pressure holding step ST4 increases as the inner diameter of the gate 243b increases (that is, as the gate 243b wears).
  • the second point is the degree of pressure change (that is, the slope of the pressure) after the pressure holding release operation (that is, after the time point X2).
  • the slope of the pressure after the pressure release operation of the graph line F1 tends to be larger in the negative direction than the slope of the pressure after the pressure release operation of the graph line F1. This cause will be described with reference to FIGS. 8 (a) and 8 (b) and FIGS. 9 (a) and 9 (b).
  • FIG. 8A shows a state at the time when the filling step ST3 is completed and the pressure holding step ST4 is started.
  • the inner diameter d1 of the gate 243b is a normal inner diameter that does not affect the quality of the molded product.
  • FIG. 8B shows a state at the time when the holding pressure holding step ST4 is completed and the holding pressure releasing step ST5 is started.
  • the pressure holding step ST4 heat is taken from the molding material L1 by the mold 242, so that a part of the molding material L1 solidifies at the edge portion of the flow path 243 to become a solidified body S1.
  • the solidified body S1 covers the entire gate 243b, and as shown in FIG. 8B, the cavity C1 and the flow path 243 are cut off by the solidified body S1 in a “gate seal” state. It becomes.
  • the holding pressure release operation is performed, so that the molding material L1 in the cavity C1 solidifies and shrinks while remaining in the cavity C1.
  • the pressure of the molding material L1 in the cavity C1 after the pressure holding release operation sharply decreases as shown in the graph line F1 of FIG.
  • FIG. 9A shows a state at the time when the filling step ST3 is completed and the pressure holding step ST4 is started.
  • the inner diameter d2 of the gate 243b is larger than the normal inner diameter d1 and is an abnormal inner diameter that affects the quality of the molded product.
  • FIG. 9B shows a state at the time when the holding pressure holding step ST4 is completed and the holding pressure releasing step ST5 is started.
  • the pressure holding step ST4 heat is taken from the molding material L1 by the mold 242, so that a part of the molding material L1 solidifies at the edge portion of the flow path 243 to become a solidified body S1.
  • the diameter d2 is larger than that in the normal state, the solidified body S1 cannot completely cover the gate 243b by the end of the pressure holding step ST4. Therefore, as shown in FIG. 9B, the gap G1 remains in the solid body S1 of the gate 243b, and the cavity C1 and the flow path 243 are not cut off by the solid body S1.
  • Such a state is referred to as a "gate seal unfinished state”.
  • the holding pressure release operation is performed while the gate seal is not completed, so that the molding material L1 in the cavity C1 flows back to the flow path 243 (that is, in the direction of the arrow AR1). Further, the molding material L1 remaining in the cavity C1 solidifies and shrinks.
  • the pressure of the molding material L1 in the cavity C1 after the pressure holding release operation is the graph line F1 due to the backflow of the molding material L1 into the flow path 243 as shown in the graph line F2 of FIG. Decreases more rapidly than.
  • the filling amount of the molding material in the cavity C1 is reduced by the amount of backflow of the molding material L1 into the flow path 243.
  • the adverse effect is that the size, weight, and quality (for example, strength) of the product vary widely.
  • the filling amount of the molding material decreases, the molded product has voids (unintentional space generated inside the molded product), sink marks (unintentional dents generated on the outer surface of the molded product), warpage (unintentional deformation of the molded product), and the like. There is a possibility that such a defect may occur. Therefore, a technique capable of sensing the abnormality of the gate 243b in the molding apparatus 20 and automatically determining the abnormality is important.
  • the inventors found that the maximum pressure of the molding material L1 in the cavity C1 during the pressure holding step ST4 is larger when the gate is abnormal than when the gate is normal (Pt1 ⁇ . Pt2) was discovered. That is, focusing on the maximum value of the pressure of the molding material L1 in the cavity C1 during the pressure holding step ST4 (hereinafter, appropriately referred to as “first evaluation value R1”), an abnormality due to wear of the gate, and eventually due to the abnormality. It was discovered that abnormalities in molded products (for example, voids, sink marks, warpage, dimensional differences, etc.) can be predicted.
  • the inventors have found that the degree of change in pressure (pressure gradient) of the molding material L1 in the cavity C1 after the pressure holding release operation is more negative when the gate is abnormal than when the gate is normal. I found that it grows in the direction. That is, focusing on the inclination of the pressure of the molding material L1 in the cavity C1 after the pressure holding release operation (hereinafter, appropriately referred to as “second evaluation value R2”), an abnormality due to wear of the gate, and eventually an abnormality caused by the abnormality occurs. It was discovered that abnormalities in the molded product (for example, voids, sink marks, warpage, dimensional difference, etc.) can be predicted.
  • the learning device 30 generates a trained model Tm1 in which the correlation between the first evaluation value R1 and the second evaluation value R2 and the wear state of the gate 243b is learned.
  • the abnormality prediction device 40 acquires prediction information for predicting the wear state of the gate 243b based on the learned model Tm1 and the first evaluation value R1 and the second evaluation value R2.
  • the learning device 30 and the abnormality prediction device 40 will be described.
  • FIG. 10 is a block diagram showing a functional configuration of the learning device 30 according to the present embodiment.
  • the learning device 30 includes a training data acquisition unit 31, a learning calculation unit 32, a molding information storage unit 33, and a learned model storage unit 34. Each of these units is realized by a computer device having a calculation unit such as a CPU and a storage unit such as an HDD.
  • the molding information is, for example, table-type information in which various types of first information and second information are associated with each other.
  • first information is the type of the mold
  • second information includes various dimensions of the mold and the volume of the cavity C1.
  • the first information is the type or lot number of the molding material
  • the second information includes the physical properties (viscosity, moisture content, etc.) of the molding material.
  • the training data acquisition unit 31 acquires information on the training data from each unit of the molding system 10.
  • the training data includes a first evaluation value R1, a second evaluation value R2, a third evaluation value R3, molding information, and wear information of the gate 243b, which will be described later.
  • the training data is acquired based on the data detected in each part of the molding system 10 (for example, the pressure sensor 25) when, for example, the molded product to be learned is molded.
  • the training data acquisition unit 31 sets the maximum pressure of the molding material L1 in the cavity C1 during the pressure holding step ST4 as the first evaluation value R1 based on the pressures detected by the pressure sensor 25 and the pressurization sensor 227, respectively. get. Specifically, based on the pressure detected by the pressurization sensor 227 being the set pressure Ps1, the start time point X1 and the end time point X2 of the pressure holding step ST4 are acquired. Then, the maximum value Ptn of the pressure detected by the pressure sensor 25 is acquired as the first evaluation value R1 between the time point X1 (holding pressure operation time point) and the time point X2 (holding pressure release operation time point).
  • the training data acquisition unit 31 makes a second evaluation regarding the change (inclination) of the pressure of the molding material L1 after the time point X2 (the time of the holding pressure release operation) based on the time series data of the pressure detected by the pressure sensor 25. Get the value R2.
  • FIG. 11A and 11 (b) are graphs schematically explaining the second evaluation value R2 according to the present embodiment.
  • FIG. 11A is an enlarged graph showing graph lines F1 and F2 after the time point X2 in FIG. 7.
  • the time point is divided from X2 every T1 for a predetermined time.
  • the time point X3 is the time point at which X2 + T1 is reached
  • the time point X4 is the time point at which X3 + T1 is reached.
  • it is divided into four time points X3 to X6, but it may be divided into more time points (for example, 10 points).
  • the rate of change of the graph lines F1 and F2 from the time point X2 to the time point X3 is acquired as the slope of each pressure.
  • the pressure at the time point X2 is Pa1
  • the pressure at the time point X3 is Pa2
  • the pressure slope dPa1 is (Pa2-Pa1) / ( It becomes X3-X2).
  • FIG. 11B is a graph plotting the slope of the pressure acquired at predetermined time intervals on the graph lines F1 and F2.
  • the vertical axis of the graph is the slope of pressure, and the horizontal axis is time.
  • the slope of the pressure acquired from the graph line F1 is plotted by the black circle
  • the slope of the pressure acquired from the graph line F2 is plotted by the white circle.
  • FIG. 11A since it is divided into four time points after the time point X2, four pressure slopes are acquired at each of the graph lines F1 and F2. For example, the pressure slope dPa1 on the graph line F1 from time point X2 to time point X3 is plotted on time point X2 in FIG. 11B.
  • the average value (or median value) of the slopes of these plurality of pressures is acquired as the second evaluation value R2.
  • the time series data of the pressure detected by the pressure sensor 25 when the molded product to be learned is molded is the graph line F1
  • dPv1 is acquired as the second evaluation value R2.
  • the time-series data of the pressure detected by the pressure sensor 25 when the molded product to be learned is molded is the graph F2
  • dPv2 is acquired as the second evaluation value R2.
  • the pressure time series data is displayed as a curve in FIGS. 11A and 7, the pressure time series data is actually composed of a plurality of points. Then, "spike noise" may occur in which a point at a predetermined time point has a value extremely different from that of other adjacent points. Therefore, if the second evaluation value R2 is acquired based only on the pressure value at the time when the spike noise is generated, an accurate value cannot be acquired.
  • a plurality of pressure slopes are acquired at predetermined time intervals, and the average value or the median value of the plurality of pressure slopes is set as the second evaluation value R2. Therefore, the influence of spike noise can be reduced.
  • the second evaluation value R2 may be acquired by a method other than the above as long as it is a value indicating a change in pressure after the holding pressure release operation.
  • the second evaluation value R2 may be obtained by deriving a function of the approximate curve from the time series data of the pressure composed of a plurality of points and differentiating the function.
  • the amount of change in the pressure may be acquired as the second evaluation value R2.
  • the amount of change in pressure (Pa2-Pa1) between the pressure holding release operation (time point X2) and the predetermined time T1 may be acquired as the second evaluation value R2.
  • the training data acquisition unit 31 acquires wear information indicating the wear state of the gate 243b.
  • the wear state of the gate 243b is, for example, the inner diameter of the gate 243b or the wear amount of the gate 243b.
  • the operator confirms the mold portion 24 with a ruler, for example, and measures the inner diameter of the gate 243b. Then, the measured inner diameter of the gate 243b is input to the input unit 50. As a result, the training data acquisition unit 31 acquires the inner diameter of the gate 243b as wear information.
  • the inner diameter (initial inner diameter) of the gate 243b in the initial state of the mold portion 24 is measured.
  • the operator measures the inner diameter of the gate 243b with a ruler and subtracts the initial inner diameter of the gate 243b from the inner diameter.
  • the amount of wear from the initial inner diameter of the gate 243b is acquired.
  • the operator inputs the calculated wear amount of the gate 243b to the input unit 50.
  • the training data acquisition unit 31 acquires the amount of wear of the gate 243b as wear information.
  • the training data acquisition unit 31 stores the initial inner diameter of the gate 243b in a storage unit (not shown), and based on the inner diameter of the gate 243b input by the operator to the input unit 50 and the initial inner diameter, the training data acquisition unit 31 May be configured to calculate the amount of wear on the gate 243b.
  • the training data acquisition unit 31 acquires a plurality of third evaluation values R3.
  • the third evaluation value R3 includes, for example, a value related to the temperature detected by the temperature sensor 26, a value related to the surrounding environment and the internal environment of the molding apparatus 20 detected by another sensor (for example, a humidity sensor) (not shown). including.
  • the training data acquisition unit 31 acquires molding information based on the information input by the operator to the input unit 50 and the molding information storage unit 33. For example, when molding a molded product to be learned, the operator inputs a lot number of a molding material related to the molded product. The training data acquisition unit 31 acquires molding information regarding the physical properties (for example, viscosity) of the molding material corresponding to the lot number from the molding information storage unit 33.
  • a set of training data (first evaluation value R1, second evaluation value R2 acquired at the time of molding the molded product, The third evaluation value R3, a set of molding information and wear information) is acquired.
  • first evaluation value R1, second evaluation value R2 acquired at the time of molding the molded product, The third evaluation value R3, a set of molding information and wear information) is acquired.
  • the learning calculation unit 32 generates a trained model Tm1 that models the correlation between the first evaluation value R1 and wear information by performing supervised machine learning based on a plurality of sets of training data. do. Further, the learning calculation unit 32 performs a supervised machine learning calculation based on a plurality of sets of training data, so that the learned model Tm2 models the correlation between the second evaluation value R2 and the wear information. To generate. That is, in this embodiment, two trained models Tm1 and Tm2 are generated.
  • a convolutional neural network (CCN) is used as the machine learning model, but other models may be used.
  • CCN convolutional neural network
  • it may be a regression tree model that is a model for grouping data.
  • the first evaluation value R1, the third evaluation value R3, and the molding information (these three types of information are collectively referred to as "first evaluation information") will be described.
  • the variable and the wear information as the objective variable, the correlation between the first evaluation information and the wear information is modeled.
  • the second evaluation value R2, the third evaluation value R3, and the molding information (these three types of information are collectively referred to as "second evaluation information") are used as explanatory variables.
  • the wear information as the objective variable, the correlation between the second evaluation information and the wear information is modeled.
  • the learned models Tm1 and Tm2 generated by the learning calculation unit 32 are stored in the learned model storage unit 34.
  • the trained models Tm1 and Tm2 stored in the trained model storage unit 34 when new information is input to the learning device 30 and new training data is acquired by the training data acquisition unit 31, the content of the training data is obtained. It will be updated accordingly.
  • the learned models Tm1 and Tm2 are transmitted from the learning device 30 to the abnormality prediction device 40 described later, and are also stored in the learned model storage unit 45 of the abnormality prediction device 40.
  • the trained model Tm1 and / or the trained model Tm2 of the present embodiment may be stored and provided in an arbitrary storage medium such as a non-transitory computer-readable medium.
  • the first evaluation value R1 regarding the maximum pressure value and the second evaluation value R2 regarding the slope of the pressure are separated, and the trained models Tm1 and Tm2 are generated, respectively.
  • the first evaluation value R1, the second evaluation value R2, the third evaluation value R3, and the molding information are used as explanatory variables, and the wear information is used as the objective variable. Therefore, the trained model Tm3 that models the correlation between the third evaluation information and the wear information may be generated. Further, in the present embodiment, two trained models Tm1 and Tm2 are generated, but only one of the trained models may be generated.
  • the method of generating the trained models Tm1 and Tm2 includes a training data acquisition step and a learning calculation step.
  • the training data acquisition unit 31 acquires a plurality of sets of training data.
  • the first evaluation value R1 and the second evaluation value R2 are acquired based on the time series data of the pressure detected by the pressure sensor 25.
  • the wear information is acquired by the worker actually inspecting the mold portion 24 obtained by molding the molded product from which the first evaluation value R1 and the second evaluation value R2 have been acquired.
  • the learning calculation unit 32 generates the trained models Tm1 and Tm2 based on a plurality of sets of training data.
  • FIG. 12 is a block diagram showing a functional configuration of the abnormality prediction device 40 according to the present embodiment.
  • the abnormality prediction device 40 includes a data acquisition unit 41, an abnormality prediction unit 42, an output unit 43, a molding information storage unit 44, and a learned model storage unit 45.
  • Each of these units is realized by a computer device having a calculation unit such as a CPU and a storage unit such as an HDD.
  • the arithmetic unit executes the data acquisition process and the abnormality prediction process described later based on the program stored in the storage unit.
  • the program of the present embodiment may be stored and provided on an arbitrary storage medium such as a non-transitory computer-readable medium.
  • the molding information storage unit 44 stores table-type molding information in which various first information and the second information are associated with each other.
  • the learned model storage unit 45 stores the learned models Tm1 and Tm2 generated by the learning device 30.
  • the molding information storage unit 44 and the learned model storage unit 45 may be realized by the same storage area as the molding information storage unit 33 and the learned model storage unit 34 of the learning device 30 among the computer devices, or may be different storage. It may be realized by the area. That is, the learning device 30 and the abnormality prediction device 40 may be configured to share the same molding information storage unit 33 and the learned model storage unit 34, or the learning device 30 and the abnormality prediction device 40 may be independently molded. It may be configured to have information storage units 33, 44 and trained model storage units 34, 45.
  • the data acquisition unit 41 executes a data acquisition process for acquiring information for performing abnormality prediction from each unit of the molding system 10.
  • the information for performing the abnormality prediction is, for example, a set of first evaluation value R1, second evaluation value R2, third evaluation value R3, and molding information acquired when the molded product to be predicted is molded.
  • the abnormality prediction unit 42 inputs a set of first evaluation value R1, third evaluation value R3, and molding information acquired by the data acquisition unit 41 into the trained model Tm1.
  • the trained model Tm1 outputs prediction information D1 for predicting the wear state of the gate 243b based on these inputs.
  • the abnormality prediction unit 42 inputs a set of the second evaluation value R2, the third evaluation value R3, and the molding information acquired by the data acquisition unit 41 into the trained model Tm2.
  • the trained model Tm2 outputs prediction information D2 for predicting the wear state of the gate 243b based on these inputs.
  • the prediction information D1 and D2 are information corresponding to the objective variables used when the trained models Tm1 and Tm2 are generated.
  • the prediction information D1 is information including the probability predicted for the wear amount of the gate 243b. More specifically, the prediction information D1 includes, for example, a first probability of 1 mm or less, a second probability of being longer than 1 mm and 3 mm or less, and a third probability of greater than 3 mm for the amount of wear of the gate 243b.
  • the trained model Tm1 when a set of first evaluation value R1, third evaluation value R3 and molding information are input to the trained model Tm1, the trained model Tm1 has a first probability of 10%, a second probability of 10%, and a third.
  • the prediction information D1 having a probability of 80% is output.
  • the prediction information D2 is also output in the same manner.
  • the output unit 43 determines whether the wear state of the gate 243b is normal or abnormal based on the prediction information D1 and D2 acquired by the abnormality prediction unit 42.
  • the output unit 43 acquires the first preliminary determination information PD1 of the gate 243b based on, for example, a predetermined threshold value and the prediction information D1.
  • the predetermined threshold value is, for example, the maximum allowable wear amount (or the maximum allowable inner diameter). For example, when the maximum allowable wear amount is 3 mm, the output unit 43 indicates that the wear state of the gate 243b is abnormal when the third probability is the highest among the first to third probabilities described above.
  • the first preliminary determination information PD1 is acquired based on the prediction information D1.
  • the prediction information D1 is acquired from the first evaluation value R1 acquired based on the maximum pressure in the pressure holding step ST4 and the trained model Tm1.
  • the second preliminary determination information PD2 is acquired based on the prediction information D2.
  • the prediction information D2 is acquired from the second evaluation value R2 acquired based on the slope of the pressure after the pressure holding release operation and the trained model Tm2.
  • the first preliminary judgment information PD1 and the second preliminary judgment information PD2 are two pieces of information focusing on different points in the time series data of the pressure obtained when the molded product to be predicted is molded. It is acquired based on the first evaluation value R1 and the second evaluation value R2), respectively. Therefore, only when both the first preliminary judgment information PD1 and the second preliminary judgment information PD2 show an abnormality, it is determined that the wear state of the gate 243b is abnormal, so that the wear state of the gate 243b is more reliable. It is possible to extract only when it is abnormal. As a result, the frequency of inspection and replacement of the mold portion 24 can be reduced.
  • the wear state of the gate 243b is abnormal. It may be configured to determine. With this configuration, it is possible to extract the case where the wear state of the gate 243b becomes abnormal without omission. As a result, it becomes possible to quickly respond to an abnormality in the mold portion 24, and it is possible to improve the yield of the molded product.
  • the output unit 43 outputs the determination information and the prediction information D1 and D2 to the display unit 60 and the control unit 271. Judgment information and prediction information D1 and D2 are displayed on the display unit 60. In particular, when it is determined that the wear state of the gate 243b is abnormal, the determination information is displayed in a highlighted color such as red on the display of the display unit 60, and an alert is issued on the speaker. May be good.
  • the operation command of the control unit 271 causes the molding apparatus 20 including the gate 243b determined to be abnormal to be stopped with the mold portion 24 open. It may be configured as follows. In this case, the operator inspects the mold unit 24 based on an alert or the like from the display unit 60, and replaces the mold unit 24 as necessary.
  • the prediction information D1 and D2 obtained by the abnormality prediction unit 42 may be displayed as they are on the display unit 60 without providing the output unit 43.
  • the operator may determine whether the wear state of the gate 243b is normal or abnormal based on the prediction information D1 and D2 displayed on the display unit 60.
  • the abnormality prediction method includes a data acquisition step and an abnormality prediction step.
  • the data acquisition unit 41 sets the first evaluation value R1, the second evaluation value R2, the third evaluation value R3, and the molding, which are acquired when the molded product to be predicted is molded. Get information. With the above, the data acquisition process is completed.
  • the abnormality prediction unit 42 first inputs a set of first evaluation value R1, third evaluation value R3, and molding information to the trained model Tm1 to predict information. Acquire D1. Further, the abnormality prediction unit 42 acquires the prediction information D2 by inputting a set of the second evaluation value R2, the third evaluation value R3, and the molding information into the trained model Tm2.
  • the output unit 43 acquires the first and second preliminary determination information PD1 and PD2 from the prediction information D1 and D2. Then, the output unit 43 acquires the determination information based on the first and second preliminary determination information PD1 and PD2. Finally, the output unit 43 outputs the determination information and the prediction information D1 and D2 to the display unit 60 and the control unit 271. As a result, the abnormality prediction process is completed.
  • the molding system 10 has a maximum value (first evaluation value R1) of the pressure of the molding material L1 in the cavity C1 between the pressure holding operation (time point X1) and the pressure holding release operation (time point X2). Based on this, the prediction information for predicting the wear state of the gate 243b is acquired. Further, the molding system 10 according to the present embodiment predicts the wear state of the gate 243b based on the value (second evaluation value R2) relating to the change in the pressure of the molding material L1 in the cavity C1 after the pressure holding release operation. Get forecast information for.
  • the molding system 10 acquires the prediction information D1 by inputting the first evaluation value R1 into the trained model Tm1 in which the correlation between the first evaluation value R1 and the wear information is machine-learned. do.
  • the explanatory variable of the trained model Tm1 includes the first evaluation value R1
  • the objective variable of the trained model Tm1 includes the inner diameter of the gate 243b or the wear amount of the gate 243b.
  • the molding system 10 acquires the prediction information D2 by inputting the second evaluation value R2 into the trained model Tm2 in which the correlation between the second evaluation value R2 and the wear information is machine-learned. do.
  • the explanatory variable of the trained model Tm2 includes the second evaluation value R2
  • the objective variable of the trained model Tm2 includes the inner diameter of the gate 243b or the wear amount of the gate 243b.
  • the pressure sensor 25 is provided on the surface of the cavity C1 close to the gate 243b.
  • the pressure sensor 25 can more easily detect the pressure change due to the backflow of the molding material L1 from the cavity C1 to the flow path 243 as shown in FIG. 9B, so that the gate 243b is worn out. It is possible to more accurately detect a more rapid decrease in pressure after the pressure holding release operation due to the operation. As a result, the second evaluation value R2 can be acquired more accurately.
  • the first evaluation value R1 and the second evaluation value R2 also depend on the temperature of the molding material L1.
  • the molding system 10 according to the present embodiment can use the trained models Tm1 and Tm2 as models incorporating the above correlation by including the third evaluation value R3 regarding the temperature of the molding material L1 as an explanatory variable. Therefore, the wear state of the gate 243b can be predicted more accurately.
  • FIG. 13 is a block diagram schematically showing the molding system 11 according to the second embodiment.
  • the molding system 11 includes a plurality of molding devices 20, an abnormality prediction device 40a, an input unit 50, and a display unit 60.
  • the abnormality prediction device 40a of the molding system 11 acquires prediction information D3 for predicting the wear state of the gate 243b based on the first evaluation value R1 and the predetermined first reference value Rf1. That is, the molding system 11 relates to the molding system according to the first embodiment in that the wear state of the gate 243b is predicted by comparing the first evaluation value R1 and the first reference value Rf1 without using the trained model Tm1. Different from 10.
  • the abnormality prediction device 40a of the molding system 11 acquires prediction information D4 for predicting the wear state of the gate 243b based on the second evaluation value R2 and the predetermined second reference value Rf2. do. That is, the molding system 11 relates to the molding system according to the first embodiment in that the wear state of the gate 243b is predicted by comparing the second evaluation value R2 and the second reference value Rf2 without using the trained model Tm2. Different from 10.
  • FIG. 14 is a block diagram showing a functional configuration of the abnormality prediction device 40a according to the present embodiment.
  • the abnormality prediction device 40a includes a data acquisition unit 41, an abnormality prediction unit 42a, an output unit 43a, a molding information storage unit 44, and a reference value storage unit 46. Each of these units is realized by a computer device having a calculation unit such as a CPU and a storage unit such as an HDD.
  • the data acquisition unit 41 acquires evaluation information in the same manner as the data acquisition unit 41 according to the first embodiment.
  • the reference value storage unit 46 stores the first reference value Rf1 and the second reference value Rf2.
  • the first reference value Rf1 is a value generated based on the first evaluation value R1 (maximum value of pressure) obtained when a molded product is molded using the gate 243b in which the wear state is normal.
  • the first reference value Rf1 is, for example, a predetermined margin on the average value or the median value of the plurality of first evaluation values R1 obtained when a plurality of molded products are molded using the gate 243b in which the wear state is normal. It is a value that takes into account.
  • the predetermined margin is determined by the maximum amount of wear (or maximum allowable inner diameter) allowed at the gate 243b.
  • the second reference value Rf2 is a value generated based on the second evaluation value R2 (value based on the change in pressure) obtained when the molded product is molded using the gate 243b in which the wear state is normal. Is.
  • the second reference value Rf2 is, for example, a predetermined margin on the average value or the median value of the plurality of second evaluation values R2 obtained when a plurality of molded products are molded using the gate 243b in which the wear state is normal. It is a value that takes into account.
  • the predetermined margin is determined by the maximum amount of wear (or maximum allowable inner diameter) allowed at the gate 243b.
  • the abnormality prediction unit 42a acquires the first evaluation value R1 acquired by the data acquisition unit 41 and the first reference value Rf1 stored in the reference value storage unit 46. Then, the abnormality prediction unit 42a acquires the prediction information D1 by comparing the first evaluation value R1 and the first reference value Rf1.
  • the prediction information D1 is, for example, the difference or ratio between the first evaluation value R1 and the first reference value Rf1.
  • the prediction information D1 indicates whether or not the gate 243b is worn.
  • the abnormality prediction unit 42a acquires the second evaluation value R2 acquired by the data acquisition unit 41 and the second reference value Rf2 stored in the reference value storage unit 46. Then, the abnormality prediction unit 42a acquires the prediction information D2 by comparing the second evaluation value R2 with the second reference value Rf2.
  • the prediction information D2 is, for example, the difference or ratio between the second evaluation value R2 and the second reference value Rf2.
  • the second evaluation value R2 regarding the pressure change after the pressure holding release operation tends to be smaller (that is, larger in the negative direction) than the second reference value Rf2 regarding the pressure change when the gate 243b is normal. .. Therefore, when the second evaluation value R2 is smaller than the second reference value Rf2, it is predicted that the gate 243b is worn. Therefore, the prediction information D2 indicates whether or not the gate 243b is worn.
  • the output unit 43a determines whether or not the wear state of the gate 243b is abnormal based on the prediction information D1 and D2 acquired by the abnormality prediction unit 42a.
  • the prediction information D1 is the difference between the first evaluation value R1 and the first reference value Rf1 (R1-Rf1)
  • the prediction information D2 is the difference between the second evaluation value R2 and the second reference value Rf2 (R2-Rf2).
  • the output unit 43a determines that the wear state of the gate 243b is abnormal when the prediction information D1 has a positive value and the prediction information D2 has a negative value.
  • the output unit 43a determines that the wear state of the gate 243b is abnormal when either the case where the prediction information D1 has a positive value or the case where the prediction information D2 has a negative value is satisfied. You may try to do it.
  • the output unit 43a outputs the determination information regarding the determination result of the wear state of the gate 243b and the prediction information D1 and D2 to the display unit 60 and the control unit 271.
  • the display unit 60 and the control unit 271 perform the same operations as in the first embodiment based on the determination information and the prediction information D1 and D2.
  • the prediction information D1 and D2 obtained by the abnormality prediction unit 42a may be displayed as they are on the display unit 60 without providing the output unit 43a.
  • the operator may determine the state of the mold unit 24 based on the prediction information D1 and D2 displayed on the display unit 60.
  • the wear state of the gate 243b is determined by comparing the first evaluation value R1 and the first reference value Rf1 and the second evaluation value R2 and the second reference value Rf2. It can be easily predicted. In the present embodiment, both the first evaluation value R1 and the second evaluation value R2 are used to predict the wear state of the gate 243b, but only one of the evaluation values is used to predict the wear state of the gate 243b. You may.
  • the first reference value Rf1 is based on the first evaluation value R1 (maximum pressure value) obtained when a molded product is molded using the gate 243b in which the wear state is normal. Will be generated.
  • the implementation of this disclosure is not limited to this.
  • the first reference value Rf1 may be generated based on the maximum value of the pressure detected by the pressurization sensor 227 during the pressurization step ST4.
  • the first reference value Rf1 may be generated based on the maximum value of the pressure detected by the pressure sensor 227a during the pressure holding step ST4.
  • the pressures detected by the pressurization sensor 227 and the pressure sensor 227a are the pressures of the molding material before passing through the flow path 243, they are not affected by the flow path resistance by the flow path 243. Since the flow path 243 has a flow path resistance equal to or higher than a predetermined value when the gate 243b is normal, the maximum value of the pressure detected during the pressure holding step ST4 by the pressure sensor 25 is detected by the pressure sensor 227 and the pressure sensor 227a, respectively. The predetermined value Th1 or more is lower than the maximum value of the pressure to be applied.
  • the flow path resistance of the flow path 243 becomes less than a predetermined value, and the maximum value of the pressure detected during the pressure holding step ST4 by the pressure sensor 25 and the pressure sensor 227 and the pressure sensor 227a respectively detect the maximum value.
  • the difference from the maximum value of the pressure to be applied is less than the predetermined value Th1.
  • the data acquisition unit 41 acquires the maximum value of the pressure detected by the pressurization sensor 227 and the pressure sensor 227a as the first reference value Rf1, and the abnormality prediction unit 42a acquires the first reference value Rf1 and the first evaluation value.
  • the difference from R1 (Rf1-R1) is acquired as prediction information, and when the difference (Rf1-R1) is smaller than the predetermined value Th1, the output unit 43a determines that the wear state of the gate 243b is abnormal. It may be configured.
  • the abnormality prediction unit 42a acquires the ratio of the first reference value Rf1 and the first evaluation value R1 as prediction information, and the output unit 43a determines whether or not the wear state of the gate 243b is abnormal based on the ratio. It may be configured to determine.
  • both the first reference value Rf1 and the first evaluation value R1 are formed. Can be obtained. Therefore, for example, even if the molding conditions (pressurization, mold clamping force, type of molding material, etc.) are changed while using the same mold portion 24, the first step is easily performed after the change. It becomes possible to acquire the reference value Rf1.
  • the pressure sensor 227 and the pressure are applied to at least one of the first reference value Rf1 and the first evaluation value R1.
  • a correction value related to calibration between the sensor 227a and the pressure sensor 25 may be added.
  • the output unit 43a determines the wear state of the gate 243b based on the prediction information D1 and D2 acquired in one molding.
  • the output unit 43a may determine the wear state of the gate 243b based on the information acquired in the plurality of moldings.
  • FIG. 15A is a graph showing a plurality of first evaluation values R1 for each number of moldings.
  • the vertical axis of the graph is the pressure, and the horizontal axis is the number of moldings.
  • a plurality of molded products to be predicted are molded by the molding apparatus 20, and a plurality of first evaluation values R1 are acquired.
  • the first evaluation value R1 of the first molding is “Pta”.
  • the first reference value Rf1 is a value Pth obtained by adding a margin Th2 to the first evaluation value R1 of the first molding (that is, in a state where the gate 243b is not worn).
  • Molding is repeated in the molding apparatus 20, and the data acquisition unit 41 acquires the first evaluation value R1 each time. Then, when the plurality of (for example, three) first evaluation values R1 continuously acquired over a predetermined plurality of times (for example, three times) are all larger than the first reference value Rf1, the gate Prediction information D1 indicating that wear has occurred in 243b is acquired.
  • the first evaluation value R1 of the N4th time is equal to or higher than the first reference value Rf1 and the first evaluation value R1 of the N2 and N3 times is also equal to or higher than the first reference value Rf1, the first evaluation is performed three times in a row.
  • the value R1 becomes larger than the first reference value Rf1.
  • FIG. 15B is a graph showing a plurality of second evaluation values R2 for each number of moldings.
  • the vertical axis of the graph is the slope of pressure, and the horizontal axis is the number of moldings.
  • a plurality of molded products to be predicted are molded by the molding apparatus 20, and a plurality of second evaluation values R2 are acquired.
  • the second evaluation value R2 of the first molding is “dPva”.
  • the second reference value Rf2 is a value dPth obtained by subtracting the margin Th3 from the second evaluation value R2 of the first molding (that is, in a state where the gate 243b is not worn).
  • Molding is repeated in the molding apparatus 20, and the data acquisition unit 41 acquires the second evaluation value R2 each time.
  • the gate It is configured to acquire the prediction information D2 indicating that the 243b is worn.
  • the gate 243b When a disturbance (for example, vibration) is suddenly applied to the molding apparatus 20, the gate 243b has no abnormality, but the first evaluation value R1 or the second evaluation value R2, which are abnormal values in a single shot, are acquired. There is. As described above, by monitoring the first evaluation value R1 and the second evaluation value R2 multiple times, it is possible to exclude the influence of such disturbances and more accurately predict the wear state of the gate 243b. Become.
  • Molding system 20 Molding equipment 21 Bed 22 Injection part 221 Hopper 222 Cylinder 223 Screw 225 Ball screw 226 Motor 227 Pressure sensor 227a Pressure sensor 228 Movement amount sensor 229 Heater 224 Nozzle 23 Type tightening part 231 Fixed plate 231a Through hole 232 Movable board 232a Through hole 233 Tie bar 234 Ball screw 235 Support board 236 Force sensor 237 Motor 24 Mold part 241 Mold 242 Mold 243 Flow path 243a 1st opening 243b 2nd opening (gate) 25 Pressure sensor 26 Temperature sensor 27 Control panel 271 Control unit 272 Communication unit 30 Learning device 31 Training data acquisition unit 32 Learning calculation unit 33 Molding information storage unit 34 Learned model storage unit 40, 40a Abnormality prediction device 41 Data acquisition unit 42, 42a Abnormality prediction unit 43, 43a Output unit 44 Molding information storage unit 45 Learned model storage unit 46 Reference value storage unit 50 Input unit 60 Display unit C1 Cavity L1 Molding material F0, F1, F2 Graph line F Ps1 Pressure (set

Landscapes

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

Abstract

L'invention concerne un système de moulage (10) qui comprend un dispositif de moulage (20) et un dispositif de prédiction d'irrégularité (40). Le dispositif de prédiction d'irrégularité (40) acquiert, en tant que première valeur d'évaluation, la valeur maximale de la pression d'un matériau de moulage à l'intérieur d'une cavité du dispositif de moulage (20) détectée à partir d'une opération de maintien de pression jusqu'à une opération de libération du maintien de pression par le dispositif de moulage (20), et acquiert des informations de prédiction pour prédire l'état d'usure d'une entrée d'une partie de matrice du dispositif de moulage (20) sur la base de la première valeur d'évaluation.
PCT/JP2021/014311 2020-04-27 2021-04-02 Système de moulage, dispositif de prédiction d'irrégularité, procédé de prédiction d'irrégularité, programme et modèle entraîné Ceased WO2021220719A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2020078313A JP7424191B2 (ja) 2020-04-27 2020-04-27 成形システム、異常予測装置、異常予測方法、プログラム及び学習済みモデル
JP2020-078313 2020-04-27

Publications (1)

Publication Number Publication Date
WO2021220719A1 true WO2021220719A1 (fr) 2021-11-04

Family

ID=78278856

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/014311 Ceased WO2021220719A1 (fr) 2020-04-27 2021-04-02 Système de moulage, dispositif de prédiction d'irrégularité, procédé de prédiction d'irrégularité, programme et modèle entraîné

Country Status (2)

Country Link
JP (1) JP7424191B2 (fr)
WO (1) WO2021220719A1 (fr)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7605014B2 (ja) * 2021-05-14 2024-12-24 株式会社ジェイテクト 射出成形装置
EP4190462A1 (fr) * 2021-12-03 2023-06-07 Siemens Aktiengesellschaft Procédé et composant d'évaluation de surveillance d'un procédé de production de coulée sous pression ou de moulage par injection d'un composant mécanique avec une machine de production correspondante

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2020052821A (ja) * 2018-09-27 2020-04-02 株式会社ジェイテクト 劣化判定装置および劣化判定システム

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2020052821A (ja) * 2018-09-27 2020-04-02 株式会社ジェイテクト 劣化判定装置および劣化判定システム

Also Published As

Publication number Publication date
JP2021172029A (ja) 2021-11-01
JP7424191B2 (ja) 2024-01-30

Similar Documents

Publication Publication Date Title
JP7571485B2 (ja) 異常予測システム、異常予測装置、異常予測方法及びプログラム
US20200103862A1 (en) Deterioration determining apparatus and deterioration determining system
US20080099943A1 (en) Injection molding control method
US11358317B2 (en) Systems and methods for controlling injection molding using predicted cavity pressure
JP5770060B2 (ja) 射出成形機の成形監視装置
WO2021220719A1 (fr) Système de moulage, dispositif de prédiction d'irrégularité, procédé de prédiction d'irrégularité, programme et modèle entraîné
US20230367304A1 (en) State determination device and state determination method
WO2021206017A1 (fr) Système de moulage, dispositif de prédiction d'irrégularité, procédé de prédiction d'irrégularité, programme et modèle entraîné
WO2021215222A1 (fr) Système de moulage, dispositif de prédiction d'anomalie, procédé de prédiction d'anomalie, programme et modèle entraîné
WO2014189083A1 (fr) Dispositif de diagnostic de moulage
US20240342972A1 (en) Injection molding machine pass/fail determination system
JP7424192B2 (ja) 成形システム、異常予測装置、異常予測方法、プログラム及び学習済みモデル
JP7495513B2 (ja) 状態判定装置及び状態判定方法
KR101919242B1 (ko) 사출금형의 진단시스템
JP2021066057A (ja) 射出成形機管理装置及び射出成形機
US20240009905A1 (en) State determination device and state determination method
JP2007098756A (ja) 加硫制御方法及び制御システム
JP2015033793A (ja) 射出成形機
JP7683210B2 (ja) 検出システム、検出装置、検出方法、プログラム及び学習済みモデル
JP7585748B2 (ja) 異常検出システム、異常検出装置、異常検出方法、プログラム及び学習済みモデル
JP2007112100A (ja) 成形状態監視システム
JP5426043B1 (ja) 樹脂射出成形不具合判定方法及び樹脂射出成形不具合判定装置
US20250353232A1 (en) Injection molding machine pass/fail determination system
JP7367511B2 (ja) 金型異常判定装置、プログラムおよび金型異常判定方法
JP7481048B1 (ja) 情報処理システム、情報処理方法及びプログラム

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: 21797701

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21797701

Country of ref document: EP

Kind code of ref document: A1