Detection system, detection device, detection method, program, and learned model

Abstract

To detect completion of a gate seal more accurately.SOLUTION: A detection system comprises: a molding apparatus that molds a molded product; and a detection device that detects a state of the molding apparatus. The molding apparatus includes: a die section in which a flow channel and a cavity communicating with the flow channel through a gate are formed; an injection section that performs a charging operation that charges a molding material in a molten state into the cavity from the flow channel, a pressure retaining operation that retains a pressure of the molding material charged into the cavity, and a pressure retaining release operation that releases the retention of the pressure of the molding material; and a pressure sensor that detects the pressure of the molding material in the flow channel. The detection device includes: a data acquiring section that acquires time series data on pressures detected by the pressure sensor; and a detection section that detects, after the pressure retaining operation, whether or not sealing of the gate is completed based on the time series data before the pressure retaining release operation.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a detection system, a detection device, a detection method, a program, and a trained model. [Background technology]

[0002] There is known an injection molding apparatus that molds a molded product by supplying a molten liquid of a molding material to a cavity formed between a plurality of molds. Injection molding involves a filling process in which the mold is filled with the molding material, a pressure holding process in which the molding material in the mold is held at a predetermined pressure, and a pressure release process in which the pressure of the molding material in the mold is released. Here, the pressure release process must be performed after the gate in the mold is sealed with the solidified molding material (i.e., after the gate is sealed). This is because releasing the pressure holding process when the gate seal is incomplete may cause the molding material in the cavity to flow back toward the gate, resulting in sink marks or voids in the molded product.

[0003] For example, Patent Document 1 discloses a technology for detecting whether gate sealing is complete. In Patent Document 1, when gate sealing is completed, the volume of compressible resin decreases by the volume of the cavity, and the forward speed of the screw that compresses the resin and moves forward slows down significantly as gate sealing is completed. This is utilized to sequentially detect the forward speed of the screw and compare it with a set value, and the point in time when the forward speed falls below the set value is detected as the point in time when gate sealing is completed. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 5-286008 Summary of the Invention [Problem to be solved by the invention]

[0005] For example, when the cavity volume is relatively small (for example, when the cavity volume is approximately the same as the volume of the flow passage upstream of the cavity), the reduction in the forward speed of the screw caused by the completion of gate sealing is also small. Therefore, in the technology of Patent Document 1, the accuracy of detecting the completion of gate sealing becomes lower as the cavity volume becomes smaller.

[0006] In addition, the forward speed of the screw varies depending on the variation between lots of molding materials (e.g., variation in viscosity) and the surrounding environment (e.g., temperature, humidity), etc. For this reason, the forward speed is likely to be a different value each time molding is performed, and even if such a forward speed is compared with a previously stored set value, it is difficult to accurately detect the completion of gate sealing.

[0007] Therefore, an object of the present invention is to provide a detection system, a detection device, a detection method, a program, and a trained model that can more accurately detect the completion of gate sealing. [Means for solving the problem]

[0008] (1) A detection system according to the present disclosure includes a molding apparatus that molds a molded product, and a detection device that detects a state of the molding apparatus. The molding apparatus includes a mold section having a flow path and a cavity that is connected to the flow path via a gate formed therein, an injection section that performs a filling operation of filling molten molding material from the flow path into the cavity, a pressure holding operation of holding the pressure of the molding material filled in the cavity, and a pressure release operation of releasing the pressure holding of the molding material, and a pressure sensor that detects the pressure of the molding material in the flow path. The detection device includes a data acquisition section that acquires time series data of the pressure detected by the pressure sensor, and a detection section that detects whether sealing of the gate has been completed based on the time series data after the pressure holding operation and before the pressure release operation.

[0009] If the sealing of the gate is completed after the pressure holding operation and before the pressure holding release operation, a temporary pressure increase (or a temporary relaxation of the pressure decrease) occurs in the time series data of the pressure detected by the pressure sensor. The detection unit focuses on such a change and detects whether the sealing of the gate is completed. This makes it possible to more accurately detect whether the sealing of the gate is completed.

[0010] (2) Preferably, the detection unit detects that the sealing of the gate is complete when the second time-series data of the pressure gradient after the pressure-holding operation and before the pressure-holding release operation, which is calculated based on the time-series data, includes an upwardly convex area. By using the time-series data of the pressure gradient, the difference between a case where the gate is completely sealed and a case where the gate is not completely sealed becomes clearer. Therefore, the accuracy of detecting whether the gate sealing is complete or not can be improved.

[0011] (3) Preferably, the detection unit detects whether sealing of the gate has been completed by inputting input information to a trained model, and the explanatory variables of the trained model and the input information include the time series data, a value relating to the change in pressure after the pressure holding operation and before the pressure release operation calculated based on the time series data, or second time series data of the slope of the pressure after the pressure holding operation and before the pressure release operation calculated based on the time series data, and the objective variable of the trained model includes a state value relating to the sealing of the gate.

[0012] By using a trained model, it is possible to more accurately detect whether or not the gate has been sealed, even when there is variation in molding conditions.

[0013] (4) Preferably, the injection unit has a cylinder in which a nozzle communicating with the flow path is formed, and a screw inserted into the cylinder, and prior to the filling operation, while the flow path and the nozzle are in communication, the injection unit further performs a metering operation in which the molding material is introduced into the cylinder while moving the screw in a direction away from the nozzle, and the molding material to be used for molding the molded product is metered, and after the metering operation, the detection unit further detects whether sealing of the nozzle has been completed based on the time-series data prior to the filling operation.

[0014] If the sealing of the nozzle is not completed after the metering operation and before the filling operation, a temporary increase in pressure (or a temporary slackening in the pressure decrease) occurs in the time series data of the pressure detected by the pressure sensor. The detection unit focuses on such a change and detects whether the sealing of the nozzle is completed. This makes it possible to further detect whether the sealing of the nozzle is completed.

[0015] (5) Preferably, the detection unit detects that sealing of the nozzle is not complete when third time-series data of the pressure gradient after the metering operation and before the filling operation, which is calculated based on the time-series data, includes an upwardly convex area. By using the time-series data of the pressure gradient, the difference between a case where the nozzle is completely sealed and a case where the nozzle is not completely sealed becomes clearer. Therefore, it is possible to improve the accuracy of detecting whether or not the nozzle is completely sealed.

[0016] (6) Preferably, the pressure sensor is provided on the opposite side of the flow path to an ejector pin exposed to the flow path, and is pressed by the ejector pin to indirectly detect the pressure of the molding material in the flow path. With this configuration, the pressure sensor can detect the pressure in the flow path while preventing the pressure sensor from affecting the flow of the molding material.

[0017] (7) A detection device according to the present disclosure is a detection device that detects the state of a molding device that molds a molded product, the molding device having a mold section having a flow path and a cavity connected to the flow path via a gate formed therein, an injection section that performs a filling operation of filling molten molding material from the flow path into the cavity, a pressure holding operation of maintaining the pressure of the molding material filled in the cavity, and a pressure release operation of releasing the maintenance of the pressure of the molding material, and a pressure sensor that detects the pressure of the molding material in the flow path, the detection device having a data acquisition section that acquires time series data of the pressure detected by the pressure sensor, and a detection section that detects whether sealing of the gate has been completed based on the time series data after the pressure holding operation and before the pressure release operation.

[0018] (8) A detection method according to the present disclosure is a detection method for detecting a state of a molding apparatus including a mold section having a flow path and a cavity connected to the flow path via a gate formed therein, and an injection section which performs a filling operation of filling molten molding material from the flow path into the cavity, a pressure holding operation of maintaining the pressure of the molding material filled in the cavity, and a pressure holding release operation of releasing the maintenance of the pressure of the molding material, the detection method including a data acquisition step of acquiring time series data of pressure detected by a pressure sensor which detects the pressure of the molding material in the flow path, and a detection step of detecting whether sealing of the gate has been completed based on the time series data after the pressure holding operation and before the pressure holding release operation.

[0019] (9) A program according to the present disclosure is a program for detecting the state of a molding apparatus including a mold section having a flow path and a cavity connected to the flow path via a gate formed therein, and an injection section that performs a filling operation of filling molten molding material from the flow path into the cavity, a pressure holding operation of maintaining the pressure of the molding material filled in the cavity, and a pressure holding release operation of releasing the pressure holding of the molding material, the program causing a computer device to execute a data acquisition process of acquiring time series data of pressure detected by a pressure sensor that detects the pressure of the molding material in the flow path, and a detection process of detecting whether sealing of the gate has been completed based on the time series data after the pressure holding operation and before the pressure holding release operation.

[0020] (10) A trained model according to the present disclosure is a trained model for detecting whether sealing of the gate has been completed in a molding apparatus including a mold section having a flow path and a cavity connected to the flow path via a gate formed therein, and an injection section that performs a filling operation of filling molten molding material from the flow path into the cavity, a holding pressure operation of maintaining the pressure of the molding material filled in the cavity, and a holding pressure release operation of releasing the maintenance of the pressure of the molding material, wherein explanatory variables include time series data of pressure detected by a pressure sensor that detects the pressure of the molding material in the flow path, a value related to the change in pressure after the holding pressure operation and before the holding pressure release operation calculated based on the time series data, or second time series data of the slope of the pressure after the holding pressure operation and before the holding pressure release operation calculated based on the time series data, and a target variable includes a state value related to the sealing of the gate. Effect of the Invention

[0021] According to the present invention, the completion of gate sealing can be detected more accurately. [Brief description of the drawings]

[0022] [Figure 1] FIG. 1 is a block diagram illustrating a detection system according to a first embodiment. [Diagram 2] FIG. 2 is an explanatory diagram conceptually showing the molding device in FIG. [Diagram 3] FIG. 2 is an explanatory diagram conceptually showing the molding device in FIG. [Figure 4] FIG. 4 is a cross-sectional view showing the mold part of FIG. [Diagram 5] 5 is a cross-sectional view showing a mold part cut along the cutting line of arrow V in FIG. 4. [Figure 6] 1 is an example of a graph showing time series data of pressure. [Figure 7] FIG. 1 is a diagram illustrating a gate seal and pressure in a flow channel. [Figure 8] 13 is a diagram illustrating an example in which a pressure sensor is provided in the cavity C1. FIG. [Figure 9] 1 is an example of a graph showing time series data of pressure. [Figure 10] FIG. 13 is a diagram illustrating a nozzle seal. [Figure 11] 1 is an example of a graph showing time series data of pressure. [Figure 12] 1 is a block diagram showing a functional configuration of a learning device according to a first embodiment. [Figure 13] FIG. 13 is a diagram illustrating time series data of pressure gradient. [Figure 14] 1 is a block diagram showing a functional configuration of a detection device according to a first embodiment. [Figure 15] FIG. 11 is a block diagram illustrating a detection system according to a second embodiment. [Figure 16] FIG. 11 is a block diagram showing the functional configuration of a detection device according to a second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0023] First Embodiment A first embodiment of the present invention will now be described with reference to the drawings.

[0024] <Overall configuration of anomaly detection system> 1 is a block diagram showing a schematic diagram of a detection system 10 according to a first embodiment. The detection system 10 includes a plurality of molding devices 20, a learning device 30, a detection device 40, an input unit 50, and a display unit 60. The detection system 10 is a system that detects whether sealing of a gate 246 is completed or not based on time series data of pressure detected by a pressure sensor 25 described later. The detection system 10 is also a system that detects whether sealing of a nozzle 224 is completed or not based on time series data of pressure detected by a pressure sensor 25 described later.

[0025] The molding device 20, the learning device 30, the detection device 40, the input unit 50, and the display unit 60 are each provided so as to be able to communicate wirelessly or wired. The learning device 30 and the detection device 40 are configured by an information processing device (computer device) having a calculation unit (e.g., CPU, GPU, etc.) and a storage unit (e.g., HDD, SSD, etc.). The learning device 30 and the detection device 40 may be configured by the same information processing device, or may be configured by separate information processing devices.

[0026] In this embodiment, a plurality of molding devices 20 are connected to one learning device 30 and one detection device 40, and the learning device 30 and the detection device 40 perform learning and detection based on various data transmitted from the plurality of molding devices 20. Note that the molding devices 20 may correspond one-to-one to the learning devices 30 and the detection devices 40. That is, the detection system 10 may include one molding device 20, or may include a plurality of learning devices 30 and detection devices 40.

[0027] The input unit 50 is, for example, a keyboard or a mouse, and receives various inputs from an operator. The display unit 60 is, for example, a display or a speaker, and displays various information in the detection system 10. The input unit 50 and the display unit 60 may be integrated, for example, as a touch panel. Furthermore, the input unit 50 and the display unit 60 may be provided as a portable terminal device that can be moved to a location away from the molding device 20, the learning device 30, and the detection device 40.

[0028] <Outline of molding device configuration> 2 and 3 are explanatory diagrams conceptually showing molding apparatus 20. In Fig. 2 and Fig. 3, the parts shown as cross sections are hatched. Molding apparatus 20 has a bed 21, an injection section 22, a mold clamping section 23, a mold section 24, a pressure sensor 25, a temperature sensor 26, and a control panel 27. Fig. 2 shows molding apparatus 20 in a state where mold section 24 is open, and Fig. 3 shows molding apparatus 20 in a state where mold section 24 is assembled. Molding apparatus 20 is an apparatus that performs mold clamping type injection molding.

[0029] 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 device 20, and outputs operation commands to each drive unit. The control unit 271 is also electrically connected to each sensor (pressure sensor 25, etc.) of the molding device 20, and signals detected by each sensor are input to the control unit 271. The control unit 271 is configured by an information processing device having a calculation unit (e.g., CPU, GPU, etc.) and a storage unit (e.g., HDD, SSD, etc.).

[0030] The communication unit 272 communicates with other units (such as the learning device 30) of the detection system 10. For example, the communication unit 272 transmits signals detected by the sensors to the learning device 30 or the detection device 40. The communication unit 272 also receives detection information, which will be described later, from the detection device 40.

[0031] The mold clamping unit 23 has a fixed platen 231, a movable platen 232, tie bars 233, a ball screw 234, a support platen 235, a mold clamping force sensor 236, and a motor 237. The fixed platen 231 and the support platen 235 are fixed to the bed 21. The support platen 235 supports a ball screw 234. The ball screw 234 is connected to a motor 237. When the motor 237 is rotated by an operation command from the control unit 271, the ball screw 234 moves. The movable platen 232 is fixed to the end of the ball screw 234 opposite to the end connected to the motor 237.

[0032] Here, in the molding apparatus 20, the direction in which the ball screw 234 moves is referred to as the "axial direction." The side on which the motor 237 is located relative to the ball screw 234 is referred to as "one side" in the axial direction, and the side on which the movable platen 232 is located relative to the ball screw 234 is referred to as "the other side" in the axial direction.

[0033] The movable platen 232 moves in the axial direction in accordance with the movement of the ball screw 234. A through hole 232a penetrating in the axial direction is formed in the movable platen 232. One axial end of the tie bar 233 is fixed to the support platen 235, and the other axial end is fixed to the fixed platen 231. The tie bar 233 is inserted into the through hole 232a of the movable platen 232. In this way, the tie bar 233 guides the axial movement of the movable platen 232.

[0034] The mold clamping force sensor 236 detects pressure (reaction force of the mold clamping force) applied to the support platen 235 from the ball screw 234. The mold clamping force sensor 236 outputs a detection signal related to the pressure to the control unit 271. The mold clamping force sensor 236 may be installed at another position as long as it is a position where the mold clamping force in the mold unit 24 described later can be detected. The fixed platen 231 is formed with a through hole 231a whose diameter expands on the other axial side. A cylinder 222 described later is inserted into the through hole 231a.

[0035] The mold section 24 has a plurality of molds 241, 242. The mold 241 is fixed to a movable platen 232. When the ball screw 234 moves in the axial direction, the mold 241 also 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 fixed platen 231. That is, the mold 242 is a fixed mold.

[0036] Please refer to Fig. 3. When the mold 241 moves to the other axial direction by the ball screw 234 and comes into contact with the mold 242 (i.e., when the multiple molds 241, 242 are combined), a cavity C1 is formed between the molds 241, 242. The cavity C1 in this embodiment is an annular space into which the molding material is filled.

[0037] Fig. 4 is an enlarged cross-sectional view of the mold part 24 shown in Fig. 3. When the mold 241 and the mold 242 are combined, a flow path 243, a gate 246, and a cavity C1 are formed inside the mold part 24. The flow path 243 is formed inside the mold 242, and includes a spool 244 and a plurality of runners 245 (four in this embodiment) branching off from the spool 244.

[0038] The gate 246 is formed inside the mold 242 and is located between the flow path 243 and the cavity C1. The cavity C1 communicates with the flow path 243 via the gate 246. More specifically, the multiple gates 246 (four in this embodiment) are connected to the multiple runners 245, respectively. Note that, although multiple runners 245 and multiple gates 246 are shown in FIG. 4 as an example, the numbers of the runners 245 and the gates 246 are not limited. For example, there may be only one each of the runner 245 and the gate 246.

[0039] The spool 244 is a passage through which the molding material injected from the injection section 22 into the mold section 24 first flows. An end 244a of the spool 244 on the injection section 22 side opens so as to communicate with a nozzle 224 described below. The inner diameter of the spool 244 is smallest at the end 244a, and increases from the end 244a to the runner 245.

[0040] The runners 245 branch off slightly toward the end 244a from the end 244b on the cavity C1 side of the spool 244 (i.e., the opposite side of the end 244a). The space on the end 244b side of the spool 244 from the position where the runners 245 branch off is a resin reservoir for storing cold slug, and is also called a "cold slug well". The end 244b opens at one end of the mold 242 in the axial direction (the cut surface with the mold 241). An ejector pin 247 is built into the mold 241 at a position corresponding to the opening of the end 244b. The ejector pin 247 is a pin for removing a molded product such as cold slug stored in the end 244b from the mold 242, and is provided axially movable.

[0041] FIG. 5 is a cross-sectional view showing the mold part 24 taken along the cutting line indicated by the arrow V in FIG. The gates 246 correspond one-to-one to the runners 245. Furthermore, the inner diameter of the gates 246 decreases as it approaches the cavity C1.

[0042] Please refer to Fig. 4. The pressure sensor 25 is provided on one axial side of the ejector pin 247 of the mold 241 (i.e., the side opposite to the flow path 243 of the ejector pin 247), and detects the pressure of the molding material (in a molten state or a solidified state, or a state in which the molten state and the solidified state are mixed) in the spool 244 via the ejector pin 247. That is, when the molding material is supplied to the spool 244, the molding material presses the ejector pin 247 to one axial side, and the ejector pin 247 presses the pressure sensor 25 to one axial side. In this way, the pressure sensor 25 indirectly detects the pressure of the molding material in the spool 244.

[0043] By placing the pressure sensor 25 in this position, the pressure sensor 25 is not directly exposed to the spool 244, so that the pressure sensor 25 can detect the pressure inside the spool 244 while preventing the pressure sensor 25 from affecting the flow of molding material from the spool 244 to the gate 246.

[0044] The position of the pressure sensor 25 is not limited to this. For example, the pressure sensor 25 may be provided at another position on the spool 244, or on any of the multiple runners 245. That is, the pressure sensor 25 detects the pressure of the molding material in the flow path 243. In other words, the pressure sensor 25 detects the pressure of the molding material downstream of a nozzle 224 described below and upstream of a gate 246. The pressure sensor 25 outputs a detection signal related to the pressure to the control unit 271.

[0045] The number of pressure sensors 25 is not limited. In this embodiment, an example in which there is one pressure sensor 25 will be described, but there may be two or more pressure sensors 25. For example, one pressure sensor 25 may be provided for each runner 245, resulting in a total of four pressure sensors 25. In this case, the time series data of pressure described later may be acquired as time series data of the average value of the pressures detected by each of the four pressure sensors 25.

[0046] The temperature sensor 26 is built into the mold 242 and detects the temperature of the mold 242. The temperature sensor 26 outputs a detection signal related to the temperature to the control unit 271. The temperature sensor 26 may be installed in the mold 241. The temperature sensor 26 may also be installed in the cylinder 222. That is, it is only necessary for the temperature sensor 26 to be able to directly or indirectly detect the temperature of the molding material supplied into the cavity C1.

[0047] 2. The injection section 22 has a hopper 221, a cylinder 222, a screw 223, a ball screw 225, a motor 226, a pressure sensor 227, a movement amount sensor 228, and a heater 229. The hopper 221 is connected to the cylinder 222 and supplies 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 end on one axial side of the cylinder 222 narrows as it approaches the extreme end on one radial side, and a nozzle 224 is provided at the extreme end on one axial side of the cylinder 222. The nozzle 224 is connected to a spool 244 of a mold 242.

[0048] The screw 223 is inserted into the cylinder 222 from the other axial end of the cylinder 222. A ball screw 225 is connected to the other axial end of the screw 223, and a motor 226 is connected to the other axial end of the ball screw 225. When the motor 226 rotates in response to an operation command from the control unit 271, the ball screw 225 moves in the axial direction. Accordingly, the screw 223 also moves in the axial direction. At this time, the screw 223 rotates in a circumferential direction with the axial direction as the central axis.

[0049] The pressure sensor 227 detects the pressure (reaction force of the pushing force of the screw 223) applied from the ball screw 225 to the motor 226. That is, the pressure sensor 227 detects the pressure that the screw 223 receives from the molding material. The pressure sensor 227 outputs a detection signal related to the pressure to the control unit 271. Note that the pressure sensor 227 may be installed in another position as long as it is a position where the pushing force of the screw 223 can be detected.

[0050] The movement amount sensor 228 detects the amount of movement in the axial direction of the ball screw 225. The movement amount sensor 228 outputs a detection signal related to the amount of movement to the control unit 271. Note that the movement amount sensor 228 may be installed in another position as long as the movement amount in the axial direction of the ball screw 225 can be detected.

[0051] The heater 229 is, for example, a resistance heater formed by winding a resistance wire into a coil shape. When a current flows through the resistance wire in response to an operation command from the control unit 271, the heater 229 heats the inside of the cylinder 222 by resistance heat.

[0052] <Manufacturing method using molding equipment> 2 and 3, a method for manufacturing a molded product using the molding apparatus 20 will be described. In the method for manufacturing a molded product using the molding apparatus 20, a pre-process ST1, a mold clamping process ST2, a filling process ST3, a pressure holding process ST4, a pressure releasing process ST5, and a demolding process ST6 are performed in this order. In this embodiment, the molded product is a resin cage used for a rolling bearing. However, this is only one example of a molded product, and the molded product molded by the molding apparatus according to the present invention may be a molded product of other shapes and applications.

[0053] Please refer to Fig. 2. First, a pre-process ST1 is performed. In the pre-process ST1, the screw 223 is rotated by the motor 226, and 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 caused by the rotation of the screw 223 and the heating by the heater 229, and become a molten molding material (melting operation).

[0054] Next, the screw 223 moves to the other axial side while rotating, so that a predetermined amount of molding material is stored in the cylinder 222 on one axial side of the screw 223 (metering operation). With the above, the pre-step ST1 is completed.

[0055] Next, when the mold clamping step ST2 is started, in the molding apparatus 20 in the state shown in FIG. 2, the ball screw 234 moves to the other axial side in response to an operation command from the control unit 271, and the mold 241 is brought into contact with the mold 242 as shown in FIG. 3. With the mold 241 and the mold 242 combined in this manner, the ball screw 234 further presses the mold 241 against the mold 242 in the other axial direction with a predetermined mold clamping force. That is, the multiple molds 241, 242 are clamped together. As a result, an annular cavity C1 is formed between the multiple molds 241, 242. With the above, the mold clamping step ST2 is completed.

[0056] Here, the mold clamping force is one of the molding conditions, and is determined according to other molding conditions such as the shapes of the molds 241 and 242. The mold clamping force is detected by a mold clamping force sensor 236.

[0057] Next, when the filling step ST3 is started, the ball screw 225 moves to one axial side while maintaining the above-mentioned mold clamping force. This causes the screw 223 to push the molding material to one axial side, and the molten molding material is injected from the nozzle 224 of the cylinder 222 through the spool 244, the multiple runners 245, and the multiple gates 246 into the cavity C1 (filling operation).

[0058] When the molding material is filled into the cavity C1, the filling step ST3 is completed. In the filling step ST3, the molten molding material is supplied to the cavity C1 from the vicinity of the surfaces of the metal molds 241 and 242 while gradually solidifying.

[0059] Next, when the pressure holding step ST4 is started, the screw 223 further pushes the molding material toward one side in the axial direction, and the molding material is further injected from the nozzle 224 of the cylinder 222 into the cavity C1. As a result, a predetermined pressure (e.g., several tens to several hundreds of MPa) is applied to the molding material filled in the cavity C1. Then, the screw 223 maintains this state for a predetermined time, thereby continuing to apply the predetermined pressure to the molding material for a predetermined time (e.g., several seconds) (pressure holding operation). The pressure (pressure) with which the screw 223 pushes out the molding material into the cavity C1 is detected by the pressure sensor 227.

[0060] Next, when the pressure-removing step ST5 is started, the screw 223 moves to the other axial side and releases the pressure of the molding material (pressure-removing operation). After the pressure-removing operation, a predetermined time has elapsed and the pressure of the molding material in the cavity C1 falls below a predetermined value, and the pressure-removing step ST5 ends. Thereafter, when the mold release step ST6 is started, the mold part 24 is cooled, so that the molding material in the cavity C1 solidifies and a molded product is formed. Then, the ball screw 234 moves to one axial side, and the mold 241 is separated from the mold 242, and the molded product is removed. Note that cooling of the mold part 24 may be started simultaneously with the pressure-removing step ST5.

[0061] In the molding device 20, molding of molded products is performed continuously. For example, the pressure release step ST5 and demolding step ST6 of the nth molded product and the pre-step ST1 of the n+1th molded product are performed in parallel. That is, when the screw 223 is moved to the other radial side as the pressure release operation of the nth molded product, a metering operation of the molding material for molding the next n+1th molded product may be performed at the same time. By configuring in this way, the cycle time for molding the molded products can be shortened.

[0062] <About the gate seal> Next, the seal of the gate 246 to be detected in this embodiment will be described. Fig. 6 is an example of a graph showing time series data of pressure detected by the pressurization sensor 227 and the pressure sensor 25 in the filling step ST3, the pressure holding step ST4, and the pressure holding release step ST5. Fig. 6(a) shows the time series data of pressure detected by the pressurization sensor 227, and Fig. 6(b) shows the time series data of pressure detected by the pressure sensor 25. In Figs. 6(a) and 6(b), the horizontal axis represents time, and the vertical axis represents pressure.

[0063] In this embodiment, the origin of time (t=0) is the time when the control unit 271 issues an operation command to the motor 226 to move the screw 223 to one side in the axial direction. In other words, it is the time when the injection unit 22 starts to supply the molding material to the mold unit 24 in the filling process ST3. Note that the origin of time (t=0) is not limited to this, and may be the time when the pressurization sensor 227 detects a predetermined pressure, or the time when the movement amount sensor 228 detects a predetermined movement amount.

[0064] First, referring to Fig. 6(a), the pressure detected by the pressure sensor 227 will be described. Graph lines Fi1 to Fi3 in Fig. 6(a) are time-series data of pressure obtained when a molded product is molded under the following molding conditions 1 to 3, which have different pressure dwell times (time of the pressure dwell process ST4).

[0065] Molding condition 1: Execution of the dwelling process ST4 from time X1 to time X2 (gate sealing not completed) Molding condition 2: Execution of the dwelling process ST4 from time X1 to time X3 (gate sealing not completed) Molding condition 3: Execution of the pressure holding process ST4 from time X1 to time X4 (gate sealing completed)

[0066] That is, in the case of graph line Fi1, the pressure retention time is (X2-X1), in the case of graph line Fi2, the pressure retention time is (X3-X2), and in the case of graph line Fi3, the pressure retention time is (X4-X2). Of the three graph lines Fi1 to Fi3, the pressure retention time of graph line Fi1 is the shortest, and the pressure retention time of graph line Fi3 is the longest.

[0067] In the example of Figure 6, molding conditions 1 and 2 are conditions under which the pressure retention release operation is performed before the gate 246 is completely sealed because the pressure retention time is short (gate sealing incomplete), and molding condition 3 is a condition under which the pressure retention release operation is performed with the gate 246 completely sealed (gate sealing completed).

[0068] For example, under molding condition 1, the filling step ST3 is started before time X1, and at time X1, the space in the mold section 24 (the flow path 243, the gate 246, and the cavity C1) is filled with the molding material. Therefore, until time X1, the graph line Fi1 is almost constant at pressure Pi1. Then, from time X1, the pressure holding step ST4 is started, and additional pressure is applied to the space in the mold section 24 filled with the molding material until the pressure reaches Pi2. Therefore, the graph line Fi1 rises from time X1. Thereafter, at time X2, a pressure holding release operation is performed, and the pressure of the graph line Fi1 decreases from time X2.

[0069] The trends of the graph lines Fi2 and Fi3 are similar to the trend of the graph line Fi1 described above. That is, the pressure Pi1 is maintained until the time point X1, the pressure increases to the pressure Pi2 at the time points X3 and X4, and the pressure decreases from the time points X3 and X4.

[0070] For example, the screw 223 is feedback-controlled by the control unit 271 so that the pressure detected by the pressurizing sensor 227 becomes a predetermined pressure (for example, pressures Pi1 and Pi2). For this reason, the time-series data (graph lines Fi1 to Fi3) of the pressure detected by the pressurizing sensor 227 does not easily show any change due to the completion of sealing of the gate 246. In other words, it is difficult to detect whether or not sealing of the gate 246 has been completed based on the time-series data of the pressure detected by the pressurizing sensor 227.

[0071] Graph lines F1 to F3 in FIG. 6(b) are time series data of pressure obtained by pressure sensor 25 when molding products under molding conditions 1 to 3 described above, respectively. The shapes of graph lines F1 to F3 up to time X1 are almost the same as each other. Graph line F1 monotonically decreases from time X1 to time X2 when the holding pressure release operation is performed, and decreases more rapidly after time X2. Graph line F2 has almost the same tendency as graph line F1. That is, graph line F2 monotonically decreases from time X1 to time X3 when the holding pressure release operation is performed, and decreases more rapidly after time X3.

[0072] Graph line F3 has a different tendency from graph lines F1 and F2. Graph line F3 decreases from time X1, but has an inflection point where the pressure changes from decreasing to increasing at a time point (near time point X3) before time point X4 when the pressure holding release operation is performed, and then has a maximum pressure value. After the maximum pressure value, the pressure decreases more rapidly. In this way, under molding condition 3 in which gate 246 is completely sealed during pressure holding step ST4, a temporary increase in pressure is detected in pressure holding step ST4, as shown by graph line F3. The reason for this will be explained with reference to FIG. 7.

[0073] Fig. 7 is a diagram for explaining the sealing of the gate 246 and the pressure in the flow path 243. Fig. 7(a) is a diagram showing the state at time X1 under molding condition 3. Note that the state at time X1 under molding conditions 1 and 2 is similar to Fig. 7(a).

[0074] Here, the factors of the increase and decrease in the pressure in the flow path 243 at time X1 will be described. The pressure in the flow path 243 increases by the amount of molding material L1 flowing from the injection section 22 into the flow path 243. This increase is called "inflow pressure AR1". In addition, since the temperature of the mold section 24 is lower than that of the molding material L1 heated by the heater 229, the molding material L1 is cooled by heat taken by the mold section 24. This causes the molding material L1 to contract, and the pressure in the flow path 243 decreases by the amount of contraction. This decrease is called "contraction pressure AR2". In addition, the pressure in the flow path 243 decreases by the amount of molding material L1 flowing out from the flow path 243 to the cavity C1. This decrease is called "outflow pressure AR3". As shown in FIG. 7(a), the pressure detected by the pressure sensor 25 at time X1 can be expressed as (inflow pressure AR1-contraction pressure AR2-outflow pressure AR3) when broken down into factors of increase and decrease.

[0075] In the example of FIG. 6, the graph lines F1 to F3 decrease monotonically after time X1, because the sum of the contraction pressure AR2 and the outflow pressure AR3 is greater than the inflow pressure AR1 (inflow pressure AR1<contraction pressure AR2+outflow pressure AR3). Under conditions where the inflow pressure AR1 is greater than the sum of the contraction pressure AR2 and the outflow pressure AR3 (inflow pressure AR1>contraction pressure AR2+outflow pressure AR3), the graph lines F1 to F3 increase monotonically after time X1. For example, when the temperature of the mold section 24 is high and the contraction speed of the molding material L1 is relatively slow, the contraction pressure AR2 decreases. Also, when the inner diameter of the gate 246 is small and the outflow speed of the molding material L1 is relatively slow, the outflow pressure AR3 decreases. In such cases, the graph lines F1 to F3 tend to increase monotonically after time X1.

[0076] FIG. 7(b) is a diagram showing the state at time X4 under molding condition 3. FIG. 7(b) shows an enlarged view of the area including the gate 246 on the right side of FIG. 7(a). During the pressure-holding step ST4, the molding material L1 in the molten state is partially solidified at the edge of the gate 246 by the heat being taken away by the mold 242, and becomes a solidified body S1. When the solidified body S1 completely covers the gate 246 by the time the pressure-holding step ST4 is completed, the cavity C1 and the flow path 243 are cut off by the solidified body S1, as shown in FIG. 7(b), resulting in a gate-sealed state. In this way, the state in which the gate 246 is completely sealed by the time the pressure-holding step ST4 is completed is the normal state.

[0077] When the gate 246 is completely sealed, the outflow pressure AR3 becomes zero. Therefore, the pressure detected by the pressure sensor 25 after the gate 246 is sealed can be expressed as (inflow pressure AR1-contraction pressure AR2) when broken down into factors of increase and decrease. In other words, the only factor that reduces the pressure in the flow path 243 is the contraction pressure AR2. As a result, as shown by the graph line F3 in FIG. 6(b), a pressure increase is detected in the pressure holding step ST4.

[0078] In other words, the moment the gate 246 is sealed, the molding material L1 that has flowed from the injection section 22 into the flow path 243 loses its escape route, that is, the cavity C1, and the density of the molding material L1 inside the flow path 243 increases. This causes the pressure of the graph line F3 to increase.

[0079] Thereafter, the pressure of the graph line F3 decreases as the molding material L1 of not only the gate 246 but also the runner 245 and the spool 244 solidifies and shrinks. Therefore, the pressure increase of the graph line F3 caused by the sealing of the gate 246 occurs only temporarily, and the graph line F3 reaches a maximum value before the pressure holding release operation (time point X4).

[0080] In the example of FIG. 6(b), the following condition 1 is satisfied, so that a temporary increase in pressure is detected in the pressure maintaining step ST4. Condition 1: Inlet pressure AR1 < Contraction pressure AR2 + Outlet pressure AR3 Inlet pressure AR1>Contraction pressure AR2

[0081] In contrast, when the following condition 2 is satisfied, the temporary increase in pressure is not detected in the pressure holding step ST4. However, the rate at which the pressure decreases temporarily slows down because the outflow pressure AR3 becomes zero when the gate 246 is sealed. Condition 2: Inlet pressure AR1 < Contraction pressure AR2

[0082] Finally, as a result of the pressure-holding release operation being performed, the inflow pressure AR1 also becomes zero, and the only factor causing an increase or decrease in the pressure detected by the pressure sensor 25 is the contraction pressure AR2. For this reason, after time point X4, the graph line F3 decreases monotonically.

[0083] FIG. 7(c) is a diagram showing the state at time X2 under molding condition 1. Note that time X3 under molding condition 2 is also similar to FIG. 7(c). FIG. 7(c) shows an enlarged view of the area including the gate 246 on the right side of FIG. 7(a). Since the dwell time under molding condition 1 is short, as shown in FIG. 7(c), the gate 246 is not completely sealed at time X2 when the dwell release operation is performed (gate sealing is not completed). In this way, the state in which the gate 246 is not completely sealed by the time the dwell step ST4 is completed is an abnormal state. In this case, the cavity C1 and the flow path 243 are not cut off by the solidified body S1 during the dwell step ST4, and the molding material L1 continues to flow into the cavity C1 until the dwell release operation is performed. Therefore, the outflow pressure AR3 does not become zero until the end of the dwell step ST4.

[0084] That is, from the beginning to the end of the pressure maintaining step ST4, the pressure detected by the pressure sensor 25 is broken down into factors of increase and decrease as (inflow pressure AR1-contraction pressure AR2-outflow pressure AR3). As a result, as shown by the graph line F1 in Fig. 6(b), no inflection point such as an increase in pressure is detected in the pressure maintaining step ST4, and the pressure decreases monotonically (or increases monotonically). The graph line F2 also has a similar tendency.

[0085] In the above, incomplete gate sealing due to a short dwell time has been described, but incomplete gate sealing can also occur due to other reasons. For example, incomplete gate sealing is more likely to occur when the molding material L1 is more difficult to solidify than normal. If the viscosity of the molding material L1 is low or the temperature of the molding material L1 is high, the molding material L1 tends to be more difficult to solidify. In addition, if the gate 246 wears down over time and the inner diameter of the gate 246 becomes wider than normal, more molding material L1 needs to solidify to seal the gate 246, which makes incomplete gate sealing more likely to occur.

[0086] If the holding pressure release operation is performed without completing the gate sealing, the molding material L1 flows back from the cavity C1 to the flow path 243, and the amount of molding material L1 filled in the cavity C1 decreases, which has the adverse effect of increasing the variation in the dimensions, weight, and quality (e.g., strength) of the molded product. In addition, if the amount of molding material filled decreases, there is a risk of defects such as voids (unintended spaces occurring inside the molded product), sink marks (unintended dents occurring on the outer surface of the molded product), and warpage (unintended deformation of the molded product) occurring in the molded product. For this reason, it is important to have a technology that senses the state of the molding device 20 and automatically detects whether sealing of the gate 246 has been completed.

[0087] Then, as a result of intensive research, the inventors discovered that when the pressure sensor 25 is installed in the flow path 243 as in this embodiment, a temporary increase in pressure (or a temporary weakening of the pressure drop) is detected the moment the gate 246 is sealed. In other words, by focusing on whether or not a temporary increase in pressure (or a temporary weakening of the pressure drop) is detected during the pressure retention step ST4, it is possible to detect whether or not sealing of the gate 246 has been completed.

[0088] <Issues with detecting pressure inside a cavity> As described above, in this embodiment, whether or not sealing of the gate 246 has been completed is detected based on the time-series pressure data of the pressure sensor 25 installed in the flow path 243. Here, as another method for detecting whether or not sealing of the gate 246 has been completed, it is also possible to install multiple pressure sensors 25a, 25b in the cavity C1.

[0089] 8 is a diagram illustrating an example in which two pressure sensors 25a, 25b are installed in the mold 241 so as to face the cavity C1. The pressure sensor 25a is provided at a position closer to the gate 246 than the pressure sensor 25b.

[0090] Fig. 9 is an example of a graph of time series data of pressure detected by pressure sensors 25a and 25b. In the graph of Fig. 9, pressure holding step ST4 is performed from time X1 to time X5, and pressure holding release operation is started at time X5. Figs. 8(b) and (c) are enlarged views of an area including gate 246 closest to pressure sensor 25a in Fig. 8(a). Fig. 8(b) shows the state at time X5 when sealing of gate 246 is completed in pressure holding step ST4, and Fig. 8(c) shows the state at time X5 when sealing of gate 246 is not completed in pressure holding step ST4.

[0091] As shown in Fig. 8(b), when the pressure-holding release operation is performed with the gate 246 completely sealed, the cavity C1 and the flow path 243 are cut off by the solidified body S1, so the molding material L1 contracts and solidifies while remaining in the cavity C1. Therefore, as shown in Fig. 9(a), there is almost no difference between the graph line Fa1 of the pressure detected by the pressure sensor 25a and the graph line Fb1 of the pressure detected by the pressure sensor 25b.

[0092] In contrast, as shown in FIG. 8(c), if the hold pressure release operation is performed with the gate 246 incompletely sealed, the molding material L1 flows back from the cavity C1 to the flow path 243 as indicated by the arrow AR4. Therefore, the pressure detected by the pressure sensor 25a close to the gate 246 rapidly decreases by the amount of the backflow of the molding material L1 after time point X5, as indicated by the graph line Fa2. The pressure sensor 25b is located away from the gate 246 and is therefore less susceptible to the backflow. Therefore, the graph line Fb2 does not decrease as rapidly as the graph line Fa2 after time point X5. As a result, a difference occurs between the graph line Fa2 and the graph line Fb2 in the tendency of the pressure decrease after the hold pressure release operation.

[0093] That is, it is possible to detect whether or not the gate 246 has been sealed by paying attention to the difference in time series data of the pressure after the pressure-holding release operation detected by the multiple pressure sensors 25a, 25b at different distances from the gate 246. For example, when the difference in pressure between the graph line Fa2 and the graph line Fb2 at a predetermined time point after the time point X5 exceeds a predetermined value, it is possible to detect that "sealing of the gate 246 has not been completed."

[0094] As described above, the sealing of the gate 246 can also be detected by installing multiple pressure sensors 25a, 25b in the cavity C1. However, since the cavity C1 is an area where a molded product is formed, when installing the pressure sensors 25a, 25b, it is necessary to devise a way to avoid affecting the shape of the molded product. If no measures are taken, the pressure sensors 25a, 25b will leave marks on the outer surface of the molded product. For this reason, when installing the pressure sensors 25a, 25b, it is necessary to install them at positions that allow marks to remain on the outer surface of the molded product, or to install them so as to leave as few marks as possible, which results in various restrictions on installation.

[0095] In contrast, in this embodiment, the pressure sensor 25 is installed in the flow path 243. Since the flow path 243 is not an area where a molded product is formed, there is no problem even if a trace of the pressure sensor 25 remains after molding. In this way, by installing the pressure sensor 25 in the flow path 243, it is possible to detect the sealing of the gate 246 while suppressing any influence on the molded product.

[0096] <Detection of nozzle seal abnormalities> By installing the pressure sensor 25 in the flow path 243, it is also possible to detect phenomena other than gate sealing. For example, it is possible to detect whether or not sealing of the nozzle 224 has been completed based on time-series data of the pressure detected by the pressure sensor 25. This will be described with reference to Figs. 10 and 11.

[0097] Figures 10(a) and (b) are enlarged views showing an area including the nozzle 224 of the cylinder 222 and the mold portion 24. Figures 10(a) and (b) show the state immediately after time point Xa1 when the metering operation is started in the pre-process ST1 for molding the (n+1)th molded product. Figure 10(a) shows the state under normal conditions, and Figure 10(b) shows the state under abnormal conditions.

[0098] As described above, in the molding apparatus 20, the pre-process ST1 for molding the n+1th molded product is performed in parallel with the pressure release process ST5 and the demolding process ST6 for molding the nth molded product. Therefore, as shown in Figs. 10(a) and 10(b), the nth molded product is present inside the mold section 24 before demolding. Note that, although Fig. 10 illustrates an example in which the demolding process ST6 is performed after time Xa1, the demolding process ST6 may be performed before time Xa1. In this case, the nth molded product is not present inside the mold section 24, and the insides of the flow path 243, the gate 246, and the cavity C1 are hollow.

[0099] Refer to FIG. 10(a). When the pre-process ST1 is performed, the tip of the cylinder 222 on the nozzle 224 side is in contact with the mold 242 (nozzle touch), and the nozzle 224 and the flow path 243 are in communication with each other. The inside of the cylinder 222 is heated by the heater 229 (FIG. 2), so that the molding material L1 in a molten state is present. However, since the mold 242 is at a lower temperature than the inside of the cylinder 222, the molding material L1 near the nozzle 224 of the cylinder 222 is cooled by the mold 242 and solidifies to become a solidified body S1. Then, after the nozzle 224 is blocked by this solidified body S1 (i.e., after the nozzle 224 is sealed), a metering operation of the molding material L1 is performed in the cylinder 222. During the metering operation, the state in which the nozzle 224 is sealed is the normal state.

[0100] 10(b) is referred to. If the molding material L1 becomes harder to solidify than normal for some reason, the metering operation may be performed with the nozzle 224 incompletely sealed by the solidified body S1. For example, if the viscosity of the molding material L1 is lower than normal due to moisture being mixed into the molding material L1, or if the temperature of the mold portion 24 is higher than normal, the molding material L1 becomes harder to solidify.

[0101] Furthermore, even if the nozzle 224 is once sealed, if a stronger impact than normal is applied to the solidified body S1 before or during the metering operation, a hole may be formed in the solidified body S1 during the metering operation, and the inside of the cylinder 222 may communicate with the flow path 243 via the nozzle 224 (i.e., the seal of the nozzle 224 may be broken). For example, when the pressure inside the cylinder 222 is higher than normal or when the strength of the solidified body S1 is lower than normal, the seal of the nozzle 224 may be easily broken. Such a case is also included in the state where the seal of the nozzle 224 is incomplete.

[0102] 10(b), if the metering operation is performed while the nozzle 224 is incompletely sealed, the molding material L1 that was originally intended to be used to mold the (n+1)th molded product will leak into the flow path 243. As a result, the molding material L1 cannot be accurately metered in the cylinder 222 (specifically, the amount will be less than the amount set), and there is a risk that the (n+1)th molded product will have dimensional abnormalities, sink marks, voids, or other abnormalities. For this reason, a technology for sensing the state of the molding apparatus 20 and automatically detecting whether or not sealing of the nozzle 224 has been completed becomes important.

[0103] Fig. 11(a) is a graph showing an example of time series data of pressure detected by pressure sensor 25 in the pressure release process ST5 and demolding process ST6 for the nth molded product, and the pre-process ST1 for the n+1th molded product. In Fig. 11(a), the horizontal axis is time and the vertical axis is pressure. Fig. 11(b) is a graph showing time series data of pressure gradient calculated based on the time series data of pressure in Fig. 11(a). In Fig. 11(b), the horizontal axis is time and the vertical axis is pressure gradient. At time point Xa1, the metering operation for the n+1th molded product is started.

[0104] Graph line F4 in Fig. 11(a) is time-series data of the pressure detected by pressure sensor 25 when nozzle 224 is sealed (normal) during the metering operation as shown in Fig. 10(a). Around time Xa1, the nth molded product shrinks and solidifies in flow path 243, so graph line F4 decreases monotonically.

[0105] Graph line dF4 in Fig. 11(b) is time series data of the pressure gradient calculated based on graph line F4. As time passes, the shrinkage and solidification of the molded product in flow path 243 is completed, so graph line dF4 increases monotonically while taking negative values.

[0106] Graph line F5 in Fig. 11(a) is time-series data of the pressure detected by the pressure sensor 25 when the sealing of the nozzle 224 is incomplete (abnormal) during the metering operation as shown in Fig. 10(b). At time point Xa1 (or immediately after time point Xa1), molding material L1 flows from the cylinder 222 into the flow path 243, and the flowing molding material L1 presses the pressure sensor 25 through the n-th molded product, so that graph line F5 temporarily rises immediately after time point Xa1 (or, even if it does not rise, the degree of pressure decrease becomes gradual).

[0107] Graph line dF5 in FIG. 11(b) is time series data of the pressure gradient calculated based on graph line F5. Graph line F5 has a region where the pressure temporarily rises (or the degree of pressure decrease becomes gentle) immediately after time point Xa1, so graph line dF5 has a region (maximum region) that is upwardly convex immediately after time point Xa1. When graph line F5 temporarily rises, the maximum value of the upwardly convex region of graph line dF5 is a positive value. When pressure does not rise immediately after time point Xa1 in graph line F5 and the degree of pressure decrease becomes gentle, the maximum value of the upwardly convex region of graph line dF5 is a negative value.

[0108] 11 also appears when the demolding step ST6 of the n-th molded product has already been completed at time Xa1. That is, since the flow path 243 is hollow at time Xa1, if the nozzle 224 is not completely sealed, the flowing molding material L1 directly presses against the pressure sensor 25, and the graph line F5 temporarily rises immediately after time Xa1.

[0109] Here, when the filling operation starts, the screw 223 moves to one side in the axial direction, so that the solidified material S1 in the nozzle 224 is pressed more strongly toward the flow passage 243, and the seal of the nozzle 224 is broken. Therefore, in order to detect whether the sealing of the nozzle 224 is completed or not, in this embodiment, attention is paid to the time series data of the pressure after the time point Xa1 and before the filling operation. The solidified material S1 in the nozzle 224 becomes a cold slug and is stored in the cold slug well.

[0110] In this way, the inventors discovered that a difference occurs after time Xa1 and before the filling operation between the graph line F4 (or graph line dF4) when sealing of the nozzle 224 is complete (normal) and the graph line F5 (or graph line dF5) when sealing of the nozzle 224 is not complete (abnormal). Then, the inventors came up with the idea that by focusing on this difference, it is possible to detect whether sealing of the nozzle 224 is complete or not.

[0111] Therefore, the detection system 10 according to this embodiment detects the following two states (1) and (2). Note that, although an example of detecting the following two states will be described in this embodiment, the detection system 10 may be a system that detects only one of the following two states. (1) After the pressure-holding operation, whether or not sealing of the gate 246 has been completed is detected based on the time-series data of the pressure detected by the pressure sensor 25 before the pressure-holding release operation. (2) After the metering operation, whether or not sealing of the nozzle 224 has been completed is detected based on the time-series data of the pressure detected by the pressure sensor 25 before the filling operation.

[0112] Specifically, the learning device 30 generates a trained model Tm1 that has learned the correlation between the time series data of the pressure detected by the pressure sensor 25 and the sealing state of the gate 246, and a trained model Tm2 that has learned the correlation between the time series data of the pressure detected by the pressure sensor 25 and the sealing state of the nozzle 224. Then, the detection device 40 detects whether or not sealing of the gate 246 has been completed, and whether or not sealing of the nozzle 224 has been completed, based on the trained models Tm1 and Tm2 and the time series data of the pressure detected by the pressure sensor 25. The learning device 30 and the detection device 40 will be described below.

[0113] <Explanation of the learning device> 12 is a block diagram showing the functional configuration of a learning device 30 according to this embodiment. The learning device 30 has 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 a HDD.

[0114] Various molding information is stored in the molding information storage unit 33. The molding information is, for example, information in a table format in which various first information and second information are associated with each other. For example, when the first information is the type of mold, the second information includes various dimensions of the mold and the volume of the cavity C1. When the first information is the type or lot number of the molding material, the second information includes the physical properties of the molding material (viscosity, moisture content, etc.).

[0115] The training data acquisition unit 31 acquires information about training data from each part of the detection system 10. The training data includes a state value SV1 related to the sealing of the gate 246, and time series data of molding information, environmental values, and pressure corresponding to the state value SV1. The training data further includes a state value SV2 related to the sealing of the nozzle 224, and time series data of molding information, environmental values, and pressure corresponding to the state value SV2. The training data is acquired based on data detected by each part of the detection system 10 (e.g., the pressure sensor 25) when, for example, a molded product to be learned is molded.

[0116] The state value SV1 is a value obtained by quantifying the state of sealing of the gate 246 after the holding pressure operation and before the holding pressure release operation. For example, a state in which the gate 246 is completely sealed is quantified as "1," and a state in which the gate 246 is incompletely sealed is quantified as "0." The training data acquisition unit 31 acquires the state value SV1 through input by an operator. For example, in order to train the learning device 30, an operator artificially molds a molded product with the gate 246 in an incompletely sealed state, and inputs the state value SV1 as "0" to the input unit 50. In this way, the training data acquisition unit 31 acquires the state value SV1.

[0117] The status value SV1 is not limited to a value that directly indicates the sealing status of the gate 246 as described above. For example, a molded product molded with the gate 246 imperfectly sealed may have a certain dimension smaller than a normal molded product, or may have voids. The sealing status of the gate 246 may be indirectly indicated by the status of such a molded product. For example, the status value SV1 may be "1" when the molded product has voids, and "0" when the molded product has no voids.

[0118] The state value SV2 is a value obtained by quantifying the state of sealing of the nozzle 224 after the metering operation and before the filling operation. For example, a state in which the nozzle 224 is completely sealed is quantified as "1," and a state in which the nozzle 224 is incompletely sealed is quantified as "0." The training data acquisition unit 31 acquires the state value SV2 through input by an operator. For example, in order to train the learning device 30, the operator artificially molds a molded product with the nozzle 224 in an incompletely sealed state, and inputs the state value SV2 as "0" to the input unit 50. In this way, the training data acquisition unit 31 acquires the state value SV2.

[0119] Furthermore, the training data acquisition unit 31 acquires molding information based on information input by an 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 the lot number of a molding material related to the molded product. The training data acquisition unit 31 acquires molding information related to the physical properties (e.g., viscosity) of the molding material corresponding to the lot number from the molding information storage unit 33.

[0120] The training data acquisition unit 31 further acquires a plurality of environmental values ​​as training data. The environmental values ​​are, for example, values ​​related to temperature detected by the temperature sensor 26 when the molded article to be learned is molded. The environmental values ​​may further include values ​​related to the environment around and inside the molding apparatus 20 detected by the pressure sensor 227, the mold clamping force sensor 236, and other sensors (e.g., humidity sensors) not shown when the molded article to be learned is molded.

[0121] The molding device 20 molds the molded product to be learned multiple times. Then, the training data acquisition unit 31 acquires one set of training data (a set of time-series data of the state value SV1, state value SV2, molding information, environmental value, and pressure acquired during molding of the molded product) each time a molded product to be learned is molded. In this way, the training data acquisition unit 31 acquires multiple sets of training data.

[0122] The learning calculation unit 32 performs supervised machine learning based on multiple sets of training data to generate a learned model Tm1 that models the correlation between the time series data of molding information, environmental values, and pressure, and the state value SV1. The learning calculation unit 32 also performs supervised machine learning based on multiple sets of training data to generate a learned model Tm2 that models the correlation between the time series data of molding information, environmental values, and pressure, and the state value SV2.

[0123] In this embodiment, a convolutional neural network (CCN) is used as the machine learning model, but other models may be used, such as a regression tree model that is a model related to data grouping.

[0124] Specifically, when generating the trained model Tm1, the molding information, environmental values, and pressure time-series data (collectively referred to as "input information") are used as explanatory variables, and the state value SV1 is used as the objective variable, thereby modeling the correlation between the input information and the state value SV1. That is, the learning calculation unit 32 generates the trained model Tm1 that constitutes an intermediate layer for outputting the state value SV1 corresponding to the input information from the output layer when the input information is input.

[0125] Specifically, when generating the trained model Tm2, ​​the input information is used as an explanatory variable and the state value SV2 is used as a target variable to model the correlation between the input information and the state value SV2. That is, the learning calculation unit 32 generates the trained model Tm2 that configures an intermediate layer for outputting the state value SV2 corresponding to the input information from the output layer when the input information is input.

[0126] Here, the tendency of the trained model Tm1 will be described. For example, when the time series data of pressure input to the input layer has an area that is convex upward after the pressure holding operation and before the pressure holding release operation as shown by the graph line F3 in FIG. 6(b), the output layer has a high probability of the state value SV1 ("1" in the above example) indicating that the gate 246 is completely sealed. Also, when the time series data of pressure input to the input layer does not have an area that is convex upward after the pressure holding operation and before the pressure holding release operation as shown by the graph lines F1 and F2 in FIG. 6(b), the output layer has a high probability of the state value SV1 ("0" in the above example) indicating that the gate 246 is not completely sealed.

[0127] When generating the trained model Tm1, time series data of the "slope" of the pressure after the pressure-holding operation and before the pressure-holding release operation may be used as input information instead of time series data of the pressure. FIG. 13 is a diagram for explaining time series data of the pressure gradient obtained based on the graph line F3. FIG. 13(a) shows an enlarged view of the region (maximum region) of the graph line F3 that is convex upward, and FIG. 13(b) shows a graph line dF3 that is time series data of the pressure gradient calculated based on the graph line F3. In FIG. 13(b), the horizontal axis is time, and the vertical axis is the pressure gradient. In addition, FIG. 13(a) also shows a graph line F31, and FIG. 13(b) also shows a graph line dF31. The graph line F31 shows another pattern of time series data of the pressure detected by the pressure sensor 25 when sealing of the gate 246 is completed. In the graph line F31, the pressure does not rise at the moment sealing of the gate 246 is completed, and the pressure only decreases gradually. The graph line dF31 is time series data of the pressure gradient calculated based on the graph line F31.

[0128] Refer to Fig. 13(a). If there is a clear maximum region like the graph line F3, the difference from the other graph lines F1 and F2 (Fig. 6) is also clear, so it is easy to detect that sealing of the gate 246 is complete. However, in reality, even if sealing of the gate 246 is complete, a graph line without a maximum region like the graph line F31 may be obtained. In this case, the difference from the graph lines F1 and F2 is visually unclear, and even if a trained model Tm1 is generated, the state value SV1 may not be appropriately classified.

[0129] In contrast, if time series data of the pressure gradient is used as in FIG. 13(b), the graph line dF31 calculated based on the graph line F31 also includes an upwardly convex area. Note that even if the time series data of the pressure gradient is calculated based on the graph lines F1 and F2, no upwardly convex area is included. For this reason, when generating the trained model Tm1, if the time series data of the pressure gradient is used instead of the time series data of the pressure as input information, the difference from the case where the sealing of the gate 246 is incomplete becomes clearer, and the estimation accuracy of the trained model Tm1 can be improved.

[0130] In addition, when generating the trained model Tm1, a value related to the change in pressure after the pressure-holding operation and before the pressure-holding release operation may be used as input information instead of the time series data of pressure. If the time series data of pressure (or the time series data of the pressure gradient) is used as input information, the amount of data increases, and processing time is likely to be long. For this reason, for example, a value related to the change in pressure at a predetermined time point is calculated based on the time series data of pressure (or the time series data of the pressure gradient), and the value is used as input information, thereby reducing the amount of data required. Examples of the value related to the change in pressure include the gradient of pressure, the amount of change in pressure, and the amount of pressure gradient that is convex upward. For example, the maximum value m2 of the graph line dF3 in FIG. 13(b) may be used as the value related to the change in pressure, or the difference (m2-m1, or m2-m3) between the gradient m1 before the inflection point of the graph line dF3 (or the gradient m3 after the inflection point) and the maximum value m2 may be used as the value related to the change in pressure.

[0131] When generating the trained model Tm1, the input information only needs to include time series data of pressure, time series data of pressure gradient, or values ​​related to pressure change after the pressure holding operation and before the pressure holding release operation, and does not need to include molding information and environmental values. However, when the environmental values ​​and molding information vary greatly or when the variation has a large effect on the sealing of the gate 246, it is preferable to include the environmental values ​​and molding information in the input information when generating the trained model Tm1 in order to more accurately predict the state value SV1 corresponding to the input information.

[0132] Next, the tendency of the trained model Tm2 will be described. For example, when the time series data of the pressure input to the input layer has an area that is convex upward after the metering operation and before the filling operation as shown by the graph line F5 in FIG. 11(a), the output layer has a high probability of the state value SV2 ("0" in the above example) indicating that the nozzle 224 is incompletely sealed. Also, when the time series data of the pressure input to the input layer does not have an area that is convex upward after the metering operation and before the filling operation as shown by the graph line F4 in FIG. 11(a), the output layer has a high probability of the state value SV2 ("1" in the above example) indicating that the nozzle 224 is completely sealed.

[0133] When generating the trained model Tm2, ​​time series data of the "slope" of the pressure after the metering operation and before the filling operation (for example, graph line dF5 in FIG. 11) may be used as input information instead of time series data of the pressure (for example, graph line F5 in FIG. 11). In this case, when there is an area that is convex upward after the metering operation and before the filling operation as shown in graph line dF5, the output layer has a high probability of the state value SV2 ("0" in the above example) indicating that the nozzle 224 is incompletely sealed. Also, when the time series data of the pressure input to the input layer does not have an area that is convex upward after the metering operation and before the filling operation as shown in graph line dF4, the output layer has a high probability of the state value SV2 ("1" in the above example) indicating that the nozzle 224 is completely sealed.

[0134] By using the time series data of the pressure gradient, an upwardly convex region is more likely to occur when the nozzle 224 is incompletely sealed than when the time series data of the pressure is used, and the difference in data based on whether the nozzle 224 is completely sealed or not becomes clearer. Therefore, by using the time series data of the pressure gradient as input information, the estimation accuracy of the trained model Tm2 can be improved.

[0135] The trained models Tm1 and Tm2 generated by the learning calculation unit 32 are 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 trained models Tm1 and Tm2 stored in the trained model storage unit 34 are updated as appropriate according to the contents of the training data. In addition, the trained models Tm1 and Tm2 are transmitted from the learning device 30 to the detection device 40 described below, and are also stored in the trained model storage unit 45 of the detection device 40.

[0136] <How to generate a trained model> Next, a method for generating the trained models Tm1 and Tm2 by the learning device 30 will be described. The method for generating the trained models Tm1 and Tm2 includes a training data acquisition step and a learning calculation step. These steps are realized by a computer device constituting the learning device 30 executing a predetermined program.

[0137] First, when the training data acquisition process is started, the training data acquisition unit 31 acquires multiple sets of training data. For example, an operator artificially performs molding in a state where the sealing of the gate 246 and the nozzle 224 is incomplete, and inputs state values ​​SV1 and SV2 to that effect into the input unit 50, whereby the training data acquisition unit 31 acquires the state values ​​SV1 and SV2. Then, time-series data of the pressure detected by the pressure sensor 25 when a molded product is molded using the gate 246 and the nozzle 224 is acquired. This completes the training data acquisition process.

[0138] Next, when the learning calculation process is started, the learning calculation unit 32 learns the correspondence between the input information and the state value SV1 based on multiple sets of training data, and generates a learned model Tm1. The learning calculation unit 32 also learns the correspondence between the input information and the state value SV2 based on multiple sets of training data, and generates a learned model Tm2. The learned models Tm1 and Tm2 are stored in the learned model storage units 34 and 45. This completes the learning calculation process.

[0139] <Description of the detection device> 14 is a block diagram showing the functional configuration of the detection device 40 according to this embodiment. The detection device 40 has a data acquisition unit 41, a detection unit 42, an output unit 43, a molding information storage unit 44, and a trained 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 a HDD. The calculation unit executes data acquisition processing and detection processing, which will be described later, based on a program stored in the storage unit.

[0140] The molding information storage unit 44 stores molding information in a table format in which various first information and second information are associated with each other, similar to the molding information storage unit 33. The trained model storage unit 45 stores trained models Tm1 and Tm2 generated by the learning device 30.

[0141] The molding information storage unit 44 and the trained model storage unit 45 may be realized in the same storage area as the molding information storage unit 33 and the trained model storage unit 34 of the learning device 30 in the computer device, or may be realized in a different storage area. That is, the learning device 30 and the detection device 40 may be configured to share the same molding information storage unit 33 and trained model storage unit 34, or the learning device 30 and the detection device 40 may be configured to have independent molding information storage units 33, 44 and trained model storage units 34, 45, respectively.

[0142] The data acquisition unit 41 executes a data acquisition process to acquire information for performing anomaly detection from each part of the detection system 10. The information for performing detection is, for example, time series data of pressure from a set of pressure sensors 25 acquired when a molded product to be detected is molded, environmental values, and molding information (hereinafter, these pieces of information are collectively referred to as a "detection data set").

[0143] The detection unit 42 inputs the detection data set acquired by the data acquisition unit 41 to the trained models Tm1 and Tm2. Based on these inputs, the trained model Tm1 outputs detection information D1 for detecting that sealing of the gate 246 has been completed, and the trained model Tm2 outputs detection information D2 for detecting that sealing of the nozzle 224 has been completed.

[0144] The detection information D1 is information including the accuracy of each value of the state value SV1. Specifically, the detection information D1 includes a first accuracy (accuracy that SV1=1) which is the accuracy that the sealing of the gate 246 is complete, and a second accuracy (accuracy that SV1=0) which is the accuracy that the sealing of the gate 246 is incomplete. As an example, when a detection dataset is input to the trained model Tm1, the trained model Tm1 outputs detection information D1 with a first accuracy of 90% and a second accuracy of 10%.

[0145] The detection information D2 is information including the accuracy of each value of the state value SV2. Specifically, the detection information D2 includes a first accuracy (accuracy that SV2=1) which is the accuracy that sealing of the nozzle 224 is complete, and a second accuracy (accuracy that SV2=0) which is the accuracy that sealing of the nozzle 224 is incomplete. As an example, when a detection dataset is input to the trained model Tm2, ​​the trained model Tm2 outputs detection information D2 with a first accuracy of 90% and a second accuracy of 10%.

[0146] The output unit 43 detects whether the seal of the gate 246 is completed based on the detection information D1 acquired by the detection unit 42. For example, when the first probability is the highest among the detection information D1, the output unit 43 detects that the seal of the gate 246 is completed. Then, the output unit 43 outputs the detection result to the display unit 60 and the control unit 271. The detection result is displayed on the display unit 60. When it is detected that the seal of the gate 246 is not completed, the detection result may be displayed in an emphasized color such as red on the display of the display unit 60, and an alert may be reported by the speaker.

[0147] Also, when it is detected that the seal of the gate 246 has not been completed continuously over multiple moldings, there is a high possibility that some abnormality (for example, wear of the gate 246) has occurred in the molding apparatus 20 or the molding material L1. Therefore, when it is detected that the seal of the gate 246 has not been completed continuously for a predetermined number of times, the molding apparatus 20 including the gate 246 with an incomplete seal may be configured to be stopped with the mold part 24 open by an operation command of the control unit 271. In this case, the operator inspects the mold part 24 based on an alert or the like from the display unit 60, and repairs or replaces the mold part 24 as necessary.

[0148] The output unit 43 also detects whether the seal of the nozzle 224 is completed based on the detection information D2 acquired by the detection unit 42. For example, when the first probability is the highest among the detection information D2, the output unit 43 detects that the seal of the nozzle 224 is completed. Then, the output unit 43 outputs the detection result to the display unit 60 and the control unit 271. The detection result is displayed on the display unit 60. When it is detected that the seal of the nozzle 224 is not completed, the detection result may be displayed in an emphasized color such as red on the display of the display unit 60, and an alert may be reported by the speaker.

[0149] Furthermore, if it is detected that sealing of the nozzle 224 has not been completed consecutively over multiple moldings, there is a high possibility that some abnormality (e.g., wear of the nozzle 224) has occurred in the molding device 20 or the molding material L1. For this reason, if it is detected that sealing of the nozzle 224 has not been completed a predetermined number of times consecutively, the molding device 20 including the incompletely sealed nozzle 224 may be stopped by an operation command from the control unit 271. In this case, the operator inspects the nozzle 224 based on an alert from the display unit 60, and repairs or replaces the nozzle 224 as necessary.

[0150] In this embodiment, the output unit 43 may not be provided, and the detection information D1, D2 obtained by the detection unit 42 may be displayed directly on the display unit 60. In this case, the operator may check for abnormalities based on the detection information D1, D2 displayed on the display unit 60.

[0151] <Detection method using a detection device> Next, a description will be given of a detection method using the detection device 40. The detection method includes a data acquisition step and a detection step. These steps are realized by a computer device constituting the detection device 40 executing a predetermined program.

[0152] When the data acquisition process is started, the data acquisition unit 41 acquires a detection data set that is acquired when the molded product to be detected is molded. This completes the data acquisition process. Next, when the detection process is started, the detection unit 42 inputs the detection data set into the trained models Tm1 and Tm2 to acquire detection information D1 and D2. Next, the output unit 43 acquires detection results regarding whether or not sealing of the gate 246 and the nozzle 224 has been completed based on the detection information D1 and D2. Finally, the output unit 43 outputs the detection results to the display unit 60 and the control unit 271. This completes the detection process.

[0153] <Actions and Effects of the Detection System> As described above, the detection system 10 of this embodiment includes the molding device 20 that molds a molded product, and the detection device 40 that detects the state of the molding device 20.

[0154] The molding apparatus 20 has a mold section 24 formed therein with a flow path 243 and a cavity C1 connected to the flow path 243 via a gate 246, an injection section 22 that performs a filling operation to fill molten molding material L1 from the flow path 243 into the cavity C1, a pressure holding operation to hold the pressure of the molding material L1 filled in the cavity C1, and a pressure release operation to release the pressure of the molding material L1, and a pressure sensor 25 that detects the pressure of the molding material L1 in the flow path 243.

[0155] The detection device 40 has a data acquisition unit 41 that acquires time series data of the pressure detected by the pressure sensor 25 (e.g., graph line F3), and a detection unit 42 that detects whether sealing of the gate 246 has been completed based on the time series data after the pressure retention operation and before the pressure retention release operation.

[0156] If sealing of the gate 246 is completed after the pressure holding operation but before the pressure holding release operation, a temporary pressure increase (or a temporary slackening of the pressure decrease) occurs in the time series data of the pressure detected by the pressure sensor 25. The detection unit 42 focuses on such a change and detects whether sealing of the gate 246 is completed or not. This makes it possible to detect sealing of the gate 246, which could not be detected accurately in the past.

[0157] If sealing of the nozzle 224 is not completed after the metering operation and before the filling operation, a temporary increase in pressure (or a temporary slackening in the pressure decrease) occurs in the time series data of the pressure detected by the pressure sensor 25. The detection unit 42 focuses on such a change and detects whether sealing of the nozzle 224 is completed or not. This makes it possible to further detect the sealing of the nozzle 224.

[0158] Furthermore, the detection unit 42 detects whether sealing of the gate 246 is complete by inputting the time series data of the pressure, the time series data of the pressure gradient, or the value related to the change in pressure detected by the pressure sensor 25 to the trained model Tm1. With this configuration, once the trained model Tm1 is generated, it becomes possible to detect whether sealing of the gate 246 is complete from the time series data of the pressure, the time series data of the pressure gradient, or the value related to the change in pressure detected by the pressure sensor 25. By using the trained model Tm1, it is possible to more accurately detect whether sealing of the gate 246 is complete even when there is variation in molding conditions.

[0159] <Second embodiment> The detection system according to the first embodiment has been described above. However, the implementation of the present invention is not limited to this, and various modifications can be made. Below, a detection system 11 according to a second embodiment of the present invention will be described. In the following description, the same reference numerals are used for parts that are not changed from the first embodiment, and the description will be omitted.

[0160] 15 is a block diagram showing a schematic diagram of a detection system 11 according to the second embodiment. The detection system 11 includes a plurality of molding devices 20, a detection device 40a, an input unit 50, and a display unit 60.

[0161] In this embodiment, the detection device 40a of the detection system 11 detects that sealing of the gate 246 has been completed when time series data of the pressure gradient after the pressure-holding operation and before the pressure-holding release operation (for example, graph line dF3) calculated based on time series data of the pressure detected by the pressure sensor 25 includes an area that exceeds the reference value Ref1 and is upwardly convex. That is, the detection system 11 differs from the detection system 10 according to the first embodiment in that it detects whether sealing of the gate 246 has been completed by comparing the upwardly convex area with the reference value Ref1 without using the learned model Tm1.

[0162] Furthermore, in this embodiment, the detection device 40a of the detection system 11 detects that sealing of the nozzle 224 is not complete when time-series data of the pressure gradient after the metering operation and before the filling operation (e.g., graph line dF5) calculated based on time-series data of the pressure detected by the pressure sensor 25 includes an area that exceeds the reference value Ref2 and is convex upward. That is, the detection system 11 differs from the detection system 10 according to the first embodiment in that it detects whether sealing of the nozzle 224 is complete by comparing the upward convex area with the reference value Ref2 without using the trained model Tm2.

[0163] 16 is a block diagram showing the functional configuration of a detection device 40a according to this embodiment. The detection device 40a has a data acquisition unit 41, a detection 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 a HDD. The data acquisition unit 41 acquires time series data (e.g., graph lines F3 and F5) of the pressure detected by the pressure sensor 25, similar to the data acquisition unit 41 according to the first embodiment.

[0164] The reference value storage unit 46 stores reference values ​​Ref1 and Ref2. The reference value Ref1 is a value obtained by subtracting a predetermined margin Mg1 from an upward convex amount UP1 (e.g., UP1=m2-m1) in time-series data (e.g., graph line dF3) of the pressure gradient after the pressure-holding operation and before the pressure-holding release operation when the sealing of the gate 246 is completed, as shown in FIG. 13(b) (Ref1=UP1-Mg1). The reference value Ref1 may be a value obtained by subtracting a predetermined margin Mg1 from an average value Ave(UP1) of the upward convex amount obtained as a result of performing molding multiple times under the condition that the sealing of the gate 246 is completed. The predetermined margin Mg1 is, for example, a predetermined % (e.g., 50%) of the upward convex amount UP1.

[0165] As shown in FIG. 11(b), the reference value Ref2 is a value obtained by subtracting a predetermined margin Mg2 from the upward convex amount UP2 (e.g., UP2=m5-m4) in the time series data of the pressure gradient (e.g., graph line dF5) after the metering operation and before the filling operation when the sealing of the nozzle 224 is not completed (Ref2=UP2-Mg2). Here, m5 is the maximum value of the graph line dF5, and m4 is the pressure gradient before the inflection point of the graph line dF5. The reference value Ref2 may be a value obtained by subtracting a predetermined margin Mg2 from the average value Ave(UP2) of the upward convex amount obtained as a result of performing molding multiple times under the condition that the sealing of the nozzle 224 is not completed. The predetermined margin Mg2 is, for example, a predetermined % (e.g., 50%) of the upward convex amount UP2.

[0166] The data acquisition unit 41 acquires time series data of the pressure detected by the pressure sensor 25 when the molded product to be detected is molded. The detection unit 42a calculates the upward convex amounts UP1 and UP2 based on the time series data of the pressure. The detection unit 42a then compares the upward convex amount UP1 with a reference value Ref1 stored in the reference value storage unit 46 to acquire detection information D3 for detecting whether sealing of the gate 246 is complete. In this embodiment, the detection information D3 is the difference (UP1-Ref1) between the upward convex amount UP1 and the reference value Ref1. The detection information D3 may also be the ratio (UP1 / Ref1) of the upward convex amount UP1 to the reference value Ref1.

[0167] Furthermore, the detection unit 42a obtains detection information D4 for detecting whether sealing of the nozzle 224 is complete by comparing the amount UP2 of the upward convexity with a reference value Ref2 stored in the reference value storage unit 46. In this embodiment, the detection information D4 is the difference (UP2-Ref2) between the amount UP2 of the upward convexity and the reference value Ref2. Note that the detection information D4 may also be the ratio (UP2 / Ref2) between the amount UP2 of the upward convexity and the reference value Ref2.

[0168] The output unit 43a detects whether or not sealing of the gate 246 is complete based on the detection information D3 acquired by the detection unit 42a. For example, the output unit 43a detects that sealing of the gate 246 is complete when the detection information D3 is a positive value (i.e., when the amount UP1 of upward convexity is equal to or greater than the reference value Ref1).

[0169] Furthermore, the output unit 43a detects whether or not sealing of the nozzle 224 is complete based on the detection information D4 acquired by the detection unit 42a. For example, the output unit 43a detects that sealing of the nozzle 224 is not complete when the detection information D4 is a positive value (i.e., when the amount UP2 of upward convexity is equal to or greater than the reference value Ref2). Finally, the output unit 43a outputs these detection results to the display unit 60 and the control unit 271.

[0170] In this embodiment, the output unit 43a may not be provided, and the detection information D3, D4 obtained by the detection unit 42a may be directly displayed on the display unit 60. In this case, based on the detection information D3, D4 displayed on the display unit 60, the operator may determine whether or not sealing of the gate 246 and whether or not sealing of the nozzle 224 has been completed.

[0171] According to the detection system 11 of this embodiment, by comparing a characteristic value (e.g., the amount of upward convexity UP1, UP2) obtained based on the time series data of pressure with the reference values ​​Ref1, Ref2, it is possible to easily detect whether sealing of the gate 246 and whether sealing of the nozzle 224 are completed.

[0172] <Other> The embodiments disclosed above are illustrative in all respects and are not restrictive. That is, the detection system of the present invention is not limited to the illustrated forms, and may have other forms within the scope of the present invention. [Explanation of symbols]

[0173] 10 Detection system 11 Detection system 20 Molding device 21 bed 22 ejection section 221 hopper 222 Cylinder 223 Screw 224 Nozzle 225 Ball screw 226 Motor 227 Pressure sensor 228 Movement sensor 229 Heater 23 Mold clamping section 231 Fixed plate 231a Through hole 232 Movable plate 232a through hole 233 tie bar 234 ball screw 235 Support plate 236 Clamping force sensor 237 Motor 24 Mold section 241 Mold 242 Mold 243 flow passage 244 spool 244a end 244b End 245 Runner 246 Gate 25 Pressure sensor 25a Pressure sensor 25b 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 Detector 40a Detector 41 Data acquisition unit 42 detection unit 42a detection unit 43 output unit 43a Output unit 44 Molding information storage unit 45 Trained model storage unit 46 Reference value storage section 50 Input section 60 Display section C1 Cavity L1 Molding material S1 Solidified body AR1 Inlet pressure AR2 Contraction pressure AR3 Outlet pressure SV1 State value SV2 State value Tm1 Trained model Tm2 Trained model D1 Detection information D2 Detection information D3 Detection information D4 Detection information Ref1 Reference value Ref2 Reference value UP1 Amount that is convex upwards UP2 Amount that is convex upwards

Claims

1. A detection system comprising a molding device for molding a molded product and a detection device for detecting the state of the molding device, wherein the molding device has a mold part formed therein with a flow path and a cavity communicated with the flow path via a gate, and an injection part having a cylinder in which a nozzle communicated with the flow path is formed and a screw inserted into the cylinder, and performing a filling operation of filling the cavity with a molten molding material from the flow path, a pressure holding operation of holding the pressure of the molding material filled in the cavity, a pressure holding release operation of releasing the holding of the pressure of the molding material, and a metering operation of introducing the molding material into the cylinder while moving the screw in a direction away from the nozzle in a state where the flow path and the nozzle are communicated before the filling operation to meter the molding material used for molding the molded product, and a pressure sensor for detecting the pressure of the molding material in the flow path, and the detection device has a data acquisition part for acquiring time-series data of the pressure detected by the pressure sensor, and a detection part for detecting whether the sealing of the nozzle is completed based on the time-series data after the metering operation and before the filling operation, and detecting whether the sealing of the gate is completed based on the time-series data after the pressure holding operation and before the pressure holding release operation. A detection system having the above.

2. The detection part according to claim 1, wherein when the third time-series data of the slope of the pressure after the metering operation and before the filling operation calculated based on the time-series data includes a region that is convex upward, it is detected that the sealing of the nozzle is not completed. The detection system according to claim 1.

3. The detection system according to claim 1 or claim 2, wherein the detection part detects that the sealing of the gate is completed when the second time-series data of the slope of the pressure after the pressure holding operation and before the pressure holding release operation calculated based on the time-series data includes a region that is convex upward.

4. The detection part inputs input information into a learned model to detect whether the sealing of the gate is completed, and the explanatory variables of the learned model and the input information are the time-series data, a value related to the change in pressure after the pressure holding operation and before the pressure holding release operation calculated based on the time-series data, or Second time-series data of the slope of the pressure after the pressure holding operation and before the pressure release operation, calculated based on the time-series data. The target variable of the learned model includes a state value related to the seal of the gate. The detection system according to any one of claims 1 to 3.

5. The pressure sensor is provided on the side opposite to the flow path of the ejector pin exposed in the flow path, and indirectly detects the pressure of the molding material in the flow path by being pressed by the ejector pin. The detection system according to any one of claims 1 to 4.

6. A detection device for detecting the state of a molding device for molding a molded product, The molding device includes: A mold part having a flow path and a cavity communicated with the flow path through a gate formed inside; An injection part having a cylinder in which a nozzle communicating with the flow path is formed, and a screw inserted into the cylinder, and performing a filling operation of filling the cavity with a molten molding material from the flow path, a pressure holding operation of holding the pressure of the molding material filled in the cavity, a pressure release operation of releasing the holding of the pressure of the molding material, and a metering operation of introducing the molding material into the cylinder while moving the screw away from the nozzle in a state where the flow path and the nozzle are communicated before the filling operation to meter the molding material used for molding the molded product. A pressure sensor for detecting the pressure of the molding material in the flow path; And having The detection device includes: A data acquisition unit for acquiring time-series data of the pressure detected by the pressure sensor; A detection unit for detecting whether the seal of the nozzle is completed based on the time-series data after the metering operation and before the filling operation, and detecting whether the seal of the gate is completed based on the time-series data after the pressure holding operation and before the pressure release operation. A detection device having.

7. A mold part having a flow path and a cavity communicated with the flow path through a gate formed therein, a cylinder having a nozzle communicated with the flow path formed therein, and a screw inserted into the cylinder, and performing a filling operation of filling the cavity with a molten molding material from the flow path, a pressure holding operation of holding the pressure of the molding material filled in the cavity, a pressure release operation of releasing the holding of the pressure of the molding material, and a metering operation of introducing the molding material into the cylinder while moving the screw in a direction away from the nozzle in a state where the flow path and the nozzle are communicated before the filling operation to meter the molding material used for molding a molded product, and an injection unit, a detection method for detecting the state of the molding apparatus, A data acquisition step of acquiring time-series data of the pressure detected by a pressure sensor that detects the pressure of the molding material in the flow path; A detection step of detecting whether the sealing of the nozzle is completed based on the time-series data after the metering operation and before the filling operation, and detecting whether the sealing of the gate is completed based on the time-series data after the pressure holding operation and before the pressure release operation; A detection method comprising the above.

8. A program for detecting the state of a molding apparatus having a flow path, a mold part having a cavity communicated with the flow path through a gate formed therein, a cylinder having a nozzle communicated with the flow path formed therein, and a screw inserted into the cylinder, and performing a filling operation of filling the cavity with a molten molding material from the flow path, a pressure holding operation of holding the pressure of the molding material filled in the cavity, a pressure release operation of releasing the holding of the pressure of the molding material, and a metering operation of introducing the molding material into the cylinder while moving the screw in a direction away from the nozzle in a state where the flow path and the nozzle are communicated before the filling operation to meter the molding material used for molding a molded product, and an injection unit, A data acquisition step of acquiring time-series data of the pressure detected by a pressure sensor that detects the pressure of the molding material in the flow path; After the metering operation and before the filling operation, based on the time-series data, detecting whether the seal of the nozzle is completed, and after the pressure-holding operation and before the pressure-release operation, based on the time-series data, detecting whether the seal of the gate is completed; a detection step A program for causing a computer device to execute. **Claim 9** An injection molding apparatus comprising: a mold part having a flow path and a cavity communicated with the flow path through a gate formed therein; a cylinder having a nozzle communicated with the flow path formed therein; and a screw inserted into the cylinder, the injection molding apparatus performing: a filling operation of filling a molten molding material from the flow path into the cavity; a pressure-holding operation of holding the pressure of the molding material filled in the cavity; a pressure-release operation of releasing the holding of the pressure of the molding material; and a metering operation of introducing the molding material into the cylinder while moving the screw away from the nozzle in a state where the flow path and the nozzle are in communication with each other before the filling operation, and measuring the molding material used for molding a molded product. A learned model for detecting whether the seal of the gate is completed, Time-series data of the pressure detected by a pressure sensor that detects the pressure of the molding material in the flow path A value related to the change in pressure after the pressure-holding operation and before the pressure-release operation calculated based on the time-series data, or Second time-series data of the slope of the pressure after the pressure-holding operation and before the pressure-release operation calculated based on the time-series data, the first explanatory variable including the above is input, Causing a computer to function so as to output a first target variable including a state value related to the seal of the gate Time-series data of the pressure detected by a pressure sensor that detects the pressure of the molding material in the flow path, or Third time-series data of the slope of the pressure after the metering operation and before the filling operation calculated based on the time-series data, the second explanatory variable including the above is input, A learned model for causing a computer to function so as to output a second target variable including a state value related to the seal of the nozzle.

Images