Control device and display device for an injection molding machine

Abstract

The present invention reduces the burden of settings for injection molding. A control device of an injection molding machine according to an embodiment of the present invention includes a reception unit that receives setting information indicating settings for performing injection molding, an acquisition unit that acquires measurement information measured during injection molding performed using the setting information, and a storage unit that stores a learned model for outputting corrected setting information in which the settings indicated by the setting information are corrected, based on the measurement information acquired by the acquisition unit.

Description

Technical Field

[0001] This application claims priority based on Japanese Patent Application No. 2021-200913, filed on December 10, 2021. The entire contents of that Japanese application are incorporated herein by reference.

[0002] This invention relates to a control device and a display device for an injection molding machine. Background Technology

[0003] An injection molding machine has a cylinder into which resin particles, the molding material, are supplied, and a heater that heats the cylinder to melt the resin particles. The injection molding machine manufactures molded products by melting the resin particles inside the cylinder and filling the cavity space within a mold assembly with the molten resin.

[0004] Previously, in injection molding machines, settings for injection molding were required to produce molded parts. These settings involved verifying the molded parts produced using those settings and repeatedly readjusting them to arrive at the appropriate configuration. Therefore, this setting process required time and effort from technicians.

[0005] Patent Document 1: Japanese Patent Application Publication No. 2020-49929

[0006] In contrast, in recent years, with the improvement of computer processing power, there has been a trend towards the development of artificial intelligence. For example, Patent Document 1 proposes a technology that uses machine learning to determine the injection molding settings based on the quality of the molded product. However, the technology described in Patent Document 1 requires the measurement of the quality of the molded product, thus incurring a heavy workload. Summary of the Invention

[0007] Therefore, in view of the above-mentioned problems, the object of the present invention is to provide a technique for deriving molding settings based on information measured during injection molding, thereby reducing the burden of setting settings for injection molding.

[0008] To achieve the above objectives, a control device for an injection molding machine according to an embodiment of the present invention includes: a receiving unit for receiving setting information indicating settings for performing injection molding; an acquiring unit for acquiring measurement information measured during injection molding with the setting information; and a storage unit for storing a learned model that outputs corrected setting information that corrects the settings indicated by the setting information by inputting the measurement information acquired by the acquiring unit.

[0009] Invention Effects

[0010] According to the above embodiments, the aim is to provide a technique that reduces the burden of setting up for injection molding. Attached Figure Description

[0011] Figure 1 This is a diagram showing the state of the injection molding machine at the end of the mold opening process according to the embodiment.

[0012] Figure 2 This is a diagram showing the state of the injection molding machine during mold closing according to the embodiment.

[0013] Figure 3 This is a diagram illustrating the structure of the machine learning system for the injection molding machine according to an illustrative embodiment.

[0014] Figure 4 This is a diagram illustrating an example of the hardware and functional structure of the learning device involved in the implementation method.

[0015] Figure 5 This is a diagram illustrating multiple waveform data acquired by the data acquisition unit according to the embodiment.

[0016] Figure 6 This is a graph showing the degree of deviation between the mold clamping force correction value output by the learned model involved in the implementation method and the mold clamping force setting value for the appropriate molded product.

[0017] Figure 7 This is a graph showing the degree of deviation between the mold clamping force correction value output by the learned model involved in the implementation method and the mold clamping force setting value for the appropriate molded product.

[0018] Figure 8 This is a schematic diagram illustrating the process flow between the test injection molding machine and the learning device involved in the embodiment.

[0019] Figure 9 This is a diagram that uses function blocks to represent the constituent elements of the control device involved in the implementation method.

[0020] Figure 10 This is a diagram illustrating the change in the clamping force setting value caused by the correction of the learned model using the control device involved in the implementation method.

[0021] Figure 11 This diagram illustrates an example of a display screen shown by the display control unit according to the embodiment.

[0022] Figure 12 This is a flowchart illustrating the steps for adjusting the clamping force setting value in the control device involved in the implementation method.

[0023] In the diagram: 10 - Injection molding machine, 700 - Control device, 702 - Storage medium, 711 - Input receiving unit, 712 - Condition calculation unit, 713 - Action control unit, 714 - Acquisition unit, 715 - Information generation unit, 716 - Correction unit, 717 - Display control unit, LM - Model after learning, 722 - Reliability coefficient. Detailed Implementation

[0024] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. Furthermore, in the drawings, the same or corresponding structures are sometimes labeled with the same or corresponding symbols, and descriptions are omitted.

[0025] Figure 1 This is a diagram showing the state of the injection molding machine at the end of the mold opening process according to the embodiment. Figure 2 This diagram illustrates the state of the injection molding machine during mold closing according to the embodiment. In this specification, the X-axis, Y-axis, and Z-axis are mutually perpendicular directions. The X-axis and Y-axis represent horizontal directions, and the Z-axis represents vertical directions. When the mold closing device 100 is horizontal, the X-axis is the mold opening and closing direction, and the Y-axis is the width direction of the injection molding machine 10. The negative side of the Y-axis is referred to as the operating side, and the positive side of the Y-axis is referred to as the opposite side of the operating side.

[0026] like Figures 1-2 As shown, the injection molding machine 10 includes: a mold clamping device 100, a mold opening and closing device 800; an ejection device 200 for ejecting the molded article formed by the mold device 800; an injection device 300 for injecting molding material into the mold device 800; a moving device 400 for moving the injection device 300 forward and backward relative to the mold device 800; a control device 700 for controlling each component of the injection molding machine 10; and a frame 900 for supporting each component of the injection molding machine 10. The frame 900 includes: a mold clamping device frame 910 for supporting the mold clamping device 100; and an injection device frame 920 for supporting the injection device 300. The mold clamping device frame 910 and the injection device frame 920 are respectively mounted on the base plate 2 via horizontal adjusting casters 930. The control device 700 is arranged in the internal space of the injection device frame 920. The components of the injection molding machine 10 will be described below.

[0027] (Mold closing device)

[0028] In the description of the mold closing device 100, the moving direction of the movable pressure plate 120 when the mold is closed (e.g., the positive X-axis direction) is set to forward, and the moving direction of the movable pressure plate 120 when the mold is opened (e.g., the negative X-axis direction) is set to rearward.

[0029] The mold closing device 100 performs mold closing, pressurization, mold closing, depressurization, and mold opening of the mold device 800. The mold device 800 includes a fixed mold 810 and a moving mold 820.

[0030] The mold closing device 100 is, for example, horizontal, and the mold opening and closing direction is horizontal. The mold closing device 100 has a fixed pressure plate 110 for mounting the fixed mold 810, a movable pressure plate 120 for mounting the moving mold 820, and a moving mechanism 102 for moving the movable pressure plate 120 relative to the fixed pressure plate 110 in the mold opening and closing direction.

[0031] The fixed pressure plate 110 is fixed relative to the mold closing device frame 910. The fixed mold 810 is installed on the surface of the fixed pressure plate 110 opposite to the movable pressure plate 120.

[0032] The movable pressure plate 120 is configured to move freely relative to the mold clamping device frame 910 in the mold opening and closing direction. A guide member 101 for guiding the movable pressure plate 120 is laid on the mold clamping device frame 910. A moving mold 820 is mounted on the surface of the movable pressure plate 120 opposite to the fixed pressure plate 110.

[0033] The moving mechanism 102 performs mold closing, pressurization, mold clamping, demolding, and mold opening of the mold device 800 by moving the movable pressure plate 120 forward and backward relative to the fixed pressure plate 110. The moving mechanism 102 includes an toggle seat 130 spaced apart from the fixed pressure plate 110, a connecting rod 140 connecting the fixed pressure plate 110 and the toggle seat 130, an toggle mechanism 150 that moves the movable pressure plate 120 relative to the toggle seat 130 in the mold opening and closing direction, a mold clamping motor 160 that operates the toggle mechanism 150, a motion conversion mechanism 170 that converts the rotational motion of the mold clamping motor 160 into linear motion, and a mold thickness adjustment mechanism 180 that adjusts the distance between the fixed pressure plate 110 and the toggle seat 130.

[0034] The toggle seat 130 is spaced apart from the fixed pressure plate 110 and is mounted on the mold clamping device frame 910 so as to move freely in the mold opening and closing direction. Furthermore, the toggle seat 130 can be configured to move freely along a guide laid on the mold clamping device frame 910. The guide of the toggle seat 130 can be interchangeable with the guide 101 of the movable pressure plate 120.

[0035] In addition, in this embodiment, the fixed pressure plate 110 is fixed relative to the mold clamping device frame 910, and the toggle seat 130 is configured to move freely relative to the mold clamping device frame 910 in the mold opening and closing direction. However, it is also possible that the toggle seat 130 is fixed relative to the mold clamping device frame 910, and the fixed pressure plate 110 is configured to move freely relative to the mold clamping device frame 910 in the mold opening and closing direction.

[0036] Connecting rods 140 connect the fixed pressure plate 110 and the toggle seat 130 at a distance L in the mold opening and closing direction. Multiple connecting rods 140 can be used (e.g., four). The multiple connecting rods 140 are configured parallel to the mold opening and closing direction and extend according to the clamping force. A connecting rod strain detector 141 for detecting the strain of the connecting rod 140 can be installed on at least one connecting rod 140. The connecting rod strain detector 141 sends a signal indicating its detection result to the control device 700. The detection result of the connecting rod strain detector 141 is used for detecting the clamping force, etc.

[0037] In this embodiment, a connecting rod strain gauge 141 is used as the clamping force detector for detecting the clamping force, but the present invention is not limited to this. The clamping force detector is not limited to a strain gauge and may also be piezoelectric, capacitive, hydraulic, or electromagnetic, etc., and its installation position is not limited to the connecting rod 140.

[0038] A toggle mechanism 150 is positioned between a movable pressure plate 120 and a toggle seat 130, allowing the movable pressure plate 120 to move relative to the toggle seat 130 in the mold opening and closing direction. The toggle mechanism 150 has a crosshead 151 that moves in the mold opening and closing direction and a pair of linkages that extend and retract with the movement of the crosshead 151. Each linkage has a first linkage 152 and a second linkage 153 connected by pins or the like, allowing for free extension and retraction. The first linkage 152 is mounted by pins or the like to allow for free oscillation relative to the movable pressure plate 120. The second linkage 153 is mounted by pins or the like to allow for free oscillation relative to the toggle seat 130. The second linkage 153 is mounted to the crosshead 151 via a third linkage 154. When the crosshead 151 moves forward or backward relative to the toggle seat 130, the first linkage 152 and the second linkage 153 extend and retract, causing the movable pressure plate 120 to move forward or backward relative to the toggle seat 130.

[0039] Furthermore, the structure of the toggle mechanism 150 is not limited to... Figure 1 and Figure 2 The structure shown. For example, in Figure 1 and Figure 2 In this configuration, each link group has 5 nodes, but it can have 4 nodes, or it can be the node where one end of the third link 154 is connected to the first link 152 and the second link 153.

[0040] The clamping motor 160 is mounted on the toggle seat 130 and operates the toggle mechanism 150. The clamping motor 160 moves the crosshead 151 forward and backward relative to the toggle seat 130, causing the first link 152 and the second link 153 to extend and retract, thereby moving the movable pressure plate 120 forward and backward relative to the toggle seat 130. The clamping motor 160 is directly connected to the motion conversion mechanism 170, but can also be connected to the motion conversion mechanism 170 via a belt and pulleys.

[0041] The motion conversion mechanism 170 converts the rotary motion of the mold clamping motor 160 into the linear motion of the crosshead 151. The motion conversion mechanism 170 includes a lead screw shaft and a lead screw nut screwed to the lead screw shaft. Balls or rollers may be located between the lead screw shaft and the lead screw nut.

[0042] Under the control of the control device 700, the mold closing device 100 performs the mold closing process, the pressure raising process, the mold closing process, the pressure release process, and the mold opening process.

[0043] In the mold closing process, the mold closing motor 160 is driven to advance the crosshead 151 to the mold closing end position at a set speed, causing the movable pressure plate 120 to advance so that the moving mold 820 contacts the fixed mold 810. For example, a mold closing motor encoder 161 is used to detect the position and speed of the crosshead 151. The mold closing motor encoder 161 detects the rotation of the mold closing motor 160 and sends a signal indicating its detection result to the control device 700.

[0044] Furthermore, the crosshead position detector for detecting the position of the crosshead 151 and the crosshead movement speed detector for detecting the movement speed of the crosshead 151 are not limited to the mold clamping motor encoder 161; conventional detectors can be used. Similarly, the movable platen position detector for detecting the position of the movable platen 120 and the movable platen movement speed detector for detecting the movement speed of the movable platen 120 are not limited to the mold clamping motor encoder 161; conventional detectors can be used.

[0045] In the pressurization process, the mold clamping motor 160 is further driven to advance the crosshead 151 from the mold closing end position to the mold closing position, thereby generating a mold clamping force.

[0046] During the mold closing process, the mold closing motor 160 is driven to maintain the position of the crosshead 151 in the mold closing position. During the mold closing process, the mold closing force generated during the pressurization process is maintained. During the mold closing process, a cavity space 801 (see reference) is formed between the moving mold 820 and the fixed mold 810. Figure 2 The injection unit 300 fills the cavity space 801 with liquid molding material. The filled molding material is then cured to obtain a molded product.

[0047] The number of cavity spaces 801 can be one or more. In the latter case, multiple molded articles can be obtained simultaneously. An insert can be configured in a part of the cavity space 801, and the other part of the cavity space 801 can be filled with molding material. A molded article in which the insert and the molding material are integrated can be obtained.

[0048] During the depressurization process, the crosshead 151 is retracted from the mold-closing position to the mold-opening start position by driving the mold-closing motor 160, thereby causing the movable pressure plate 120 to retract and reducing the mold-closing force. The mold-opening start position and the mold-closing end position can be the same position.

[0049] In the mold opening process, the crosshead 151 is retracted from the mold opening start position to the mold opening end position at a set moving speed by driving the mold closing motor 160, causing the movable pressure plate 120 to retract, so that the moving mold 820 separates from the fixed mold 810. Then, the ejector device 200 ejects the molded product from the moving mold 820.

[0050] The setting conditions in the mold closing process, the pressure raising process, and the mold closing process are set uniformly as a series of setting conditions. For example, the moving speed, position (including the mold closing start position, moving speed switching position, mold closing end position, and mold closing position) and mold closing force of the crosshead 151 in the mold closing process and the pressure raising process are set uniformly as a series of setting conditions. The mold closing start position, moving speed switching position, mold closing end position, and mold closing position are arranged sequentially from back to front, and represent the start and end points of the range for setting the moving speed. The moving speed is set for each range. There can be one or more moving speed switching positions. The moving speed switching position can be omitted. Only the mold closing position and the mold closing force can be set.

[0051] The settings for the depressurization and mold opening processes are also set in the same way. For example, the moving speed and position (mold opening start position, moving speed switching position, and mold opening end position) of the crosshead 151 in the depressurization and mold opening processes are set uniformly as a series of settings. The mold opening start position, moving speed switching position, and mold opening end position are arranged sequentially from front to back, and represent the start and end points of the range for setting the moving speed. The moving speed is set for each range. There can be one or more moving speed switching positions. A moving speed switching position may not be set. The mold opening start position and the mold closing end position can be the same position. Furthermore, the mold opening end position and the mold closing start position can be the same position.

[0052] In addition, the moving speed and position of the movable pressure plate 120 can be set instead of the moving speed and position of the crosshead 151. Furthermore, the clamping force can be set instead of the position of the crosshead (e.g., the mold closing position) and the position of the movable pressure plate.

[0053] However, the toggle mechanism 150 amplifies the driving force of the clamping motor 160 and transmits it to the movable pressure plate 120. This amplification factor is also known as the toggle ratio. The toggle ratio varies depending on the angle θ (hereinafter also referred to as "link angle θ") formed by the first link 152 and the second link 153. The link angle θ is determined by the position of the crosshead 151. The toggle ratio reaches its maximum when the link angle θ is 180°.

[0054] When the thickness of the mold assembly 800 changes due to replacement of the mold assembly 800, temperature changes of the mold assembly 800, etc., mold thickness adjustment is performed to obtain the specified mold closing force during mold closing. In mold thickness adjustment, for example, the distance L between the fixed pressure plate 110 and the toggle seat 130 is adjusted so that the linkage angle θ of the toggle mechanism 150 becomes the specified angle at the moment when the moving mold 820 contacts the fixed mold 810.

[0055] The mold clamping device 100 includes a mold thickness adjustment mechanism 180. The mold thickness adjustment mechanism 180 adjusts the distance L between the fixed pressure plate 110 and the toggle seat 130, thereby adjusting the mold thickness. Furthermore, the timing of the mold thickness adjustment is performed, for example, during the period from the end of the molding cycle to the start of the next molding cycle. The mold thickness adjustment mechanism 180 includes, for example: a lead screw shaft 181 formed at the rear end of the connecting rod 140; a lead screw nut 182 held in the toggle seat 130 for free rotation and immobility; and a mold thickness adjustment motor 183 that rotates the lead screw nut 182 screwed to the lead screw shaft 181.

[0056] Each connecting rod 140 is provided with a lead screw shaft 181 and a lead screw nut 182. The rotational driving force of the die thickness adjustment motor 183 can be transmitted to multiple lead screw nuts 182 via the rotational driving force transmission unit 185. Multiple lead screw nuts 182 can be rotated synchronously. In addition, by changing the transmission path of the rotational driving force transmission unit 185, multiple lead screw nuts 182 can also be rotated individually.

[0057] The rotary drive force transmission unit 185 is composed of, for example, gears. In this case, driven gears are formed on the outer periphery of each lead screw nut 182, drive gears are mounted on the output shaft of the die thickness adjustment motor 183, and intermediate gears that mesh with multiple driven gears and drive gears are kept rotatably in the center of the toggle seat 130. Alternatively, instead of gears, the rotary drive force transmission unit 185 may also be composed of belts and pulleys.

[0058] The operation of the die thickness adjustment mechanism 180 is controlled by the control device 700. The control device 700 drives the die thickness adjustment motor 183 to rotate the lead screw nut 182. As a result, the position of the toggle seat 130 relative to the connecting rod 140 is adjusted, and the distance L between the fixed pressure plate 110 and the toggle seat 130 is adjusted. Alternatively, multiple die thickness adjustment mechanisms can be used in combination.

[0059] The die thickness adjustment motor encoder 184 is used to detect the interval L. The die thickness adjustment motor encoder 184 detects the rotation amount and direction of the die thickness adjustment motor 183 and sends a signal indicating the detection result to the control device 700. The detection result of the die thickness adjustment motor encoder 184 is used to monitor and control the position and interval L of the toggle seat 130. However, the toggle seat position detector for detecting the position of the toggle seat 130 and the interval detector for detecting the interval L are not limited to the die thickness adjustment motor encoder 184; conventional detectors can be used.

[0060] The mold clamping device 100 may have a mold temperature regulator for adjusting the temperature of the mold assembly 800. The mold assembly 800 has a flow path for a temperature regulating medium inside it. The mold temperature regulator adjusts the temperature of the temperature regulating medium supplied to the flow path of the mold assembly 800, thereby regulating the temperature of the mold assembly 800.

[0061] In addition, the mold closing device 100 in this embodiment is a horizontal type with the mold opening and closing direction in the horizontal direction, but it can also be a vertical type with the mold opening and closing direction in the vertical direction.

[0062] Furthermore, the mold clamping device 100 of this embodiment includes a mold clamping motor 160 as a drive unit, but a hydraulic cylinder may be used instead of the mold clamping motor 160. Also, the mold clamping device 100 may include a linear motor for mold opening and closing, or it may include an electromagnet for mold clamping.

[0063] (Ejection device)

[0064] In the description of the ejector device 200, similar to the description of the mold closing device 100, the moving direction of the movable pressure plate 120 when the mold is closed (e.g., the positive X-axis direction) is set to forward, and the moving direction of the movable pressure plate 120 when the mold is opened (e.g., the negative X-axis direction) is set to rearward.

[0065] Ejection device 200 is mounted on movable pressure plate 120 and moves forward and backward together with movable pressure plate 120. Ejection device 200 includes: ejection rod 210 for ejecting molded article from mold device 800; and drive mechanism 220 for moving ejection rod 210 along the moving direction (X-axis direction) of movable pressure plate 120.

[0066] Ejector rod 210 is configured to move freely in and out of the through hole in movable pressure plate 120. The front end of ejector rod 210 contacts ejector plate 826 of moving mold 820. The front end of ejector rod 210 may or may not be connected to ejector plate 826.

[0067] The drive mechanism 220 includes, for example, an ejector motor and a motion conversion mechanism that converts the rotational motion of the ejector motor into the linear motion of the ejector rod 210. The motion conversion mechanism includes a lead screw and a lead screw nut screwed to the lead screw. Balls or rollers may be located between the lead screw and the lead screw nut.

[0068] The ejection device 200 performs the ejection process under the control of the control device 700. In the ejection process, the ejector rod 210 is moved forward from the standby position to the ejection position at a set speed, causing the ejector plate 826 to move forward and eject the molded product. Then, the ejection motor is driven to move the ejector rod 210 backward at a set speed, causing the ejector plate 826 to return to the original standby position.

[0069] For example, an ejector motor encoder is used to detect the position and speed of the ejector rod 210. The ejector motor encoder detects the rotation of the ejector motor and sends a signal indicating its detection result to the control device 700. In addition, the ejector rod position detector for detecting the position of the ejector rod 210 and the ejector rod speed detector for detecting the speed of the ejector rod 210 are not limited to the ejector motor encoder, and conventional detectors can be used.

[0070] (Injection device)

[0071] In the description of the injection device 300, unlike the description of the mold clamping device 100 and the description of the ejection device 200, the direction of movement of the screw 330 during filling (e.g., the negative X-axis direction) is set to forward, and the direction of movement of the screw 330 during metering (e.g., the positive X-axis direction) is set to rearward.

[0072] An injection unit 300 is mounted on a sliding base 301, which is configured to move freely forward and backward relative to the injection unit frame 920. The injection unit 300 is also configured to move freely forward and backward relative to the mold assembly 800. The injection unit 300 contacts the mold assembly 800 and fills the cavity space 801 within the mold assembly 800 with molding material metered in the cylinder 310. The injection unit 300 includes, for example, a cylinder 310 for heating the molding material, a nozzle 320 located at the front end of the cylinder 310, a screw 330 configured to move freely forward and backward and rotate freely within the cylinder 310, a metering motor 340 for rotating the screw 330, an injection motor 350 for moving the screw 330 forward and backward, and a load detector 360 for detecting the load transmitted between the injection motor 350 and the screw 330.

[0073] The cylinder body 310 heats the molding material supplied to it from the supply port 311. The molding material includes, for example, resin. The molding material is formed in granular form and supplied to the supply port 311 in a solid state. The supply port 311 is formed at the rear of the cylinder body 310. A cooler 312, such as a water-cooled cylinder, is provided on the outer periphery of the rear of the cylinder body 310. A heater 313, such as a belt heater, and a temperature detector 314 are provided on the outer periphery of the cylinder body 310, further forward than the cooler 312.

[0074] The cylinder block 310 is divided into multiple regions along its axial direction (e.g., the X-axis direction). A heater (an example of a heating element) 313 and a temperature detector (an example of a detection element) 314 are respectively provided in each of the multiple regions. A set temperature is set for each of the multiple regions, and the control device 700 controls the heater 313 so that the temperature detected by the temperature detector 314 becomes the set temperature.

[0075] The nozzle 320 is located at the front end of the cylinder 310 and presses against the mold assembly 800. A heater 313 and a temperature detector 314 are provided on the outer periphery of the nozzle 320. The control device 700 controls the heater 313 so that the detected temperature of the nozzle 320 becomes the set temperature.

[0076] The screw 330 is configured to rotate freely and move forward and backward within the cylinder 310. When the screw 330 is rotated, molding material is conveyed forward along the spiral grooves of the screw 330. As the molding material is conveyed forward, it is gradually melted by heat from the cylinder 310. As the liquid molding material is conveyed forward and accumulates at the front of the cylinder 310, the screw 330 retracts. Then, when the screw 330 is moved forward, the liquid molding material accumulated at the front of the screw 330 is injected from the nozzle 320 and fills the mold assembly 800.

[0077] The check ring 331 is installed at the front of the screw 330 so that it can move freely forward and backward. The check ring 331 acts as a check valve to prevent the molding material from flowing backward from the front of the screw 330 when the screw 330 is pushed forward.

[0078] When the screw 330 is advanced, the check ring 331 is pushed backward by the pressure of the molding material in front of the screw 330, and retracts relative to the screw 330 to a closed position that blocks the flow path of the molding material (see reference). Figure 2 This prevents the molding material accumulated in front of the screw 330 from flowing backward.

[0079] On the other hand, when the screw 330 is rotated, the check ring 331 is pushed forward by the pressure of the molding material being conveyed forward along the spiral groove of the screw 330, and advances relative to the screw 330 to the open position where the flow path of the molding material is opened (see reference). Figure 1 Thus, the molding material is conveyed to the front of the screw 330.

[0080] The check ring 331 can be either a cotransformer that rotates with the screw 330 or a non-cotransformer that does not rotate with the screw 330.

[0081] Additionally, the injection device 300 may have a drive source that moves the check ring 331 back and forth relative to the screw 330 between an open position and a closed position.

[0082] The metering motor 340 rotates the screw 330. The drive source for rotating the screw 330 is not limited to the metering motor 340; for example, it could be a hydraulic pump.

[0083] The injection motor 350 moves the screw 330 forward and backward. A motion conversion mechanism is provided between the injection motor 350 and the screw 330 to convert the rotational motion of the injection motor 350 into the linear motion of the screw 330. This motion conversion mechanism may include, for example, a lead screw shaft and a lead screw nut screwed to the lead screw shaft. Ball bearings, rollers, etc., may be provided between the lead screw shaft and the lead screw nut. The drive source for moving the screw 330 forward and backward is not limited to the injection motor 350; for example, it may be a hydraulic cylinder.

[0084] Load detector 360 detects the load transmitted between injection motor 350 and screw 330. The detected load is converted into pressure by control device 700. Load detector 360 is positioned along the load transmission path between injection motor 350 and screw 330, and detects the load acting on load detector 360.

[0085] The load detector 360 sends the detected load signal to the control device 700. The load detected by the load detector 360 is converted into the pressure acting between the screw 330 and the molding material, and is used to control and monitor the pressure on the screw 330 from the molding material, the back pressure on the screw 330, and the pressure acting on the molding material from the screw 330.

[0086] Furthermore, the pressure detector for detecting the pressure of the molding material is not limited to the load detector 360; conventional detectors can be used. For example, a nozzle pressure sensor or a mold pressure sensor can be used. The nozzle pressure sensor is located at the nozzle 320. The mold pressure sensor is located inside the mold assembly 800.

[0087] The injection unit 300 performs metering, filling, and pressure holding processes under the control of the control unit 700. The filling and pressure holding processes can be collectively referred to as the injection process.

[0088] In the metering process, the metering motor 340 drives the screw 330 to rotate at a set speed, conveying the molding material forward along the spiral grooves of the screw 330. As a result, the molding material is gradually melted. As the molten molding material is conveyed forward of the screw 330 and accumulates at the front of the cylinder 310, the screw 330 retracts. For example, a metering motor encoder 341 is used to detect the rotational speed of the screw 330. The metering motor encoder 341 detects the rotation of the metering motor 340 and sends a signal indicating its detection result to the control device 700. However, the screw speed detector for detecting the rotational speed of the screw 330 is not limited to the metering motor encoder 341; conventional detectors can be used.

[0089] In the metering process, to limit the screw 330 from retracting too rapidly, the injection motor 350 can be driven to apply a set back pressure to the screw 330. For example, a load detector 360 can be used to detect the back pressure on the screw 330. If the screw 330 retracts to the metering end position and a predetermined amount of molding material accumulates in front of the screw 330, the metering process ends.

[0090] The position and speed of the screw 330 in the metering process are uniformly set as a series of preset conditions. For example, the metering start position, speed switching position, and metering end position are set. These positions are arranged sequentially from front to back and represent the start and end points of the set speed interval. The speed is set for each interval. There can be one or more speed switching positions. Alternatively, no speed switching position can be set. Furthermore, the back pressure is set for each interval.

[0091] In the filling process, the injection motor 350 is driven to advance the screw 330 at a set speed, filling the cavity space 801 within the mold assembly 800 with the liquid molding material accumulated in front of the screw 330. For example, an injection motor encoder 351 is used to detect the position and speed of the screw 330. The injection motor encoder 351 detects the rotation of the injection motor 350 and sends a signal indicating its detection result to the control device 700. If the screw 330 reaches the set position, a switch is made from the filling process to the holding pressure process (so-called V / P switching). The position where the V / P switching occurs is also called the V / P switching position. The set speed of the screw 330 can be changed according to the position of the screw 330, time, etc.

[0092] The position and moving speed of the screw 330 in the filling process are uniformly set as a series of preset conditions. For example, the filling start position (also called the "injection start position"), the moving speed switching position, and the V / P switching position are set. These positions are arranged sequentially from back to front and represent the start and end points of the set moving speed interval. The moving speed is set for each interval. There can be one or more moving speed switching positions. It is also possible not to set any moving speed switching positions.

[0093] The upper limit of the pressure of the screw 330 is set for each range of the screw 330's moving speed. The pressure of the screw 330 is detected by the load detector 360. When the pressure of the screw 330 is below the set pressure, the screw 330 moves forward at the set moving speed. On the other hand, when the pressure of the screw 330 exceeds the set pressure, in order to protect the mold, the screw 330 moves forward at a slower moving speed than the set moving speed, so that the pressure of the screw 330 falls below the set pressure.

[0094] Furthermore, during the filling process, after the screw 330 reaches the V / P switching position, it can be paused at the V / P switching position before the V / P switch is performed. Instead of stopping the screw 330 immediately before the V / P switch, the screw 330 can be moved forward or backward at a slight speed. Moreover, the screw position detector for detecting the position of the screw 330 and the screw speed detector for detecting the movement speed of the screw 330 are not limited to the injection motor encoder 351; conventional detectors can be used.

[0095] During the holding pressure process, the injection motor 350 pushes the screw 330 forward, maintaining the pressure of the molding material at the front end of the screw 330 (hereinafter also referred to as "holding pressure") at a set pressure, and pushing the remaining molding material in the cylinder 310 towards the mold assembly 800. This replenishes any insufficient molding material in the mold assembly 800 due to cooling shrinkage. For example, a load detector 360 is used to detect the holding pressure. The set value of the holding pressure can be changed according to the elapsed time since the start of the holding pressure process. The holding pressure and the holding time for each of the multiple holding pressure processes can be set separately, or they can be set uniformly as a series of setting conditions.

[0096] During the holding pressure process, the molding material in the cavity space 801 within the mold assembly 800 is gradually cooled. At the end of the holding pressure process, the inlet of the cavity space 801 is blocked by the solidified molding material. This state is called gate sealing, which prevents the backflow of molding material from the cavity space 801. After the holding pressure process, the cooling process begins. During the cooling process, the molding material within the cavity space 801 solidifies. To shorten the molding cycle time, a metering process can be performed during the cooling process.

[0097] Furthermore, the injection device 300 in this embodiment is a coaxial screw type, but it can also be a pre-plasticizing type, etc. In a pre-plasticizing type injection device, molten molding material in a plasticizing cylinder is supplied to the injection cylinder, and the molding material is injected from the injection cylinder into the mold device. In the plasticizing cylinder, the screw is configured to rotate freely but not retract, or the screw is configured to rotate freely and retract freely. On the other hand, in the injection cylinder, the plunger is configured to retract freely.

[0098] Furthermore, the injection device 300 in this embodiment is horizontal with the cylinder 310's axis in the horizontal direction, but it can also be vertical with the cylinder 310's axis in the vertical direction. The mold clamping device combined with the vertical injection device 300 can be either vertical or horizontal. Similarly, the mold clamping device combined with the horizontal injection device 300 can be either horizontal or vertical.

[0099] (Mobile device)

[0100] In the description of the moving device 400, similarly to the description of the injection device 300, the direction of movement of the screw 330 during filling (e.g., the negative X-axis direction) is set to forward, and the direction of movement of the screw 330 during metering (e.g., the positive X-axis direction) is set to rearward.

[0101] The moving device 400 causes the injection device 300 to move forward and backward relative to the mold device 800. Furthermore, the moving device 400 presses the nozzle 320 relative to the mold device 800 to generate nozzle contact pressure. The moving device 400 includes a hydraulic pump 410, a motor 420 as a drive source, and a hydraulic cylinder 430 as a hydraulic actuator.

[0102] The hydraulic pump 410 has a first port 411 and a second port 412. The hydraulic pump 410 is a bidirectional rotating pump, generating hydraulic pressure by switching the rotation direction of the motor 420, drawing in working fluid (e.g., oil) from either the first port 411 or the second port 412 and discharging it from the other port. Alternatively, the hydraulic pump 410 can also draw working fluid from a tank and discharge working fluid from either the first port 411 or the second port 412.

[0103] Motor 420 operates hydraulic pump 410. Motor 420 drives hydraulic pump 410 by means of rotational direction and rotational torque corresponding to control signals from control device 700. Motor 420 can be an electric motor or an electric servo motor.

[0104] The hydraulic cylinder 430 has a cylinder body 431, a piston 432, and a piston rod 433. The cylinder body 431 is fixed relative to the injection device 300. The piston 432 divides the interior of the cylinder body 431 into a front chamber 435, which serves as a first chamber, and a rear chamber 436, which serves as a second chamber. The piston rod 433 is fixed relative to the fixed pressure plate 110.

[0105] The front chamber 435 of the hydraulic cylinder 430 is connected to the first port 411 of the hydraulic pump 410 via a first flow path 401. Working fluid ejected from the first port 411 is supplied to the front chamber 435 via the first flow path 401, thereby propelling the injection device 300 forward. As the injection device 300 advances, the nozzle 320 is pressed against the fixed mold 810. The front chamber 435 functions as a pressure chamber, generating the nozzle contact pressure of the nozzle 320 through the pressure of the working fluid supplied from the hydraulic pump 410.

[0106] On the other hand, the rear chamber 436 of the hydraulic cylinder 430 is connected to the second port 412 of the hydraulic pump 410 via the second flow path 402. The working fluid ejected from the second port 412 is supplied to the rear chamber 436 of the hydraulic cylinder 430 via the second flow path 402, thereby pushing the injection device 300 backward. The injection device 300 retracts and the nozzle 320 separates from the fixed mold 810.

[0107] In addition, in this embodiment, the moving device 400 includes a hydraulic cylinder 430, but the present invention is not limited thereto. For example, instead of the hydraulic cylinder 430, an electric motor and a motion conversion mechanism that converts the rotational motion of the electric motor into the linear motion of the injection device 300 may also be used.

[0108] (Control device)

[0109] The control device 700 is, for example, composed of a computer, such as Figures 1-2 As shown, the device includes a CPU (Central Processing Unit) 701, a storage medium 702 such as a memory, an input interface 703, and an output interface 704. The control device 700 performs various controls by causing the CPU 701 to execute programs stored in the storage medium 702. Furthermore, the control device 700 receives signals from external sources through the input interface 703 and sends signals to external sources through the output interface 704.

[0110] The control device 700 repeatedly manufactures molded products by performing metering, mold closing, pressurization, mold closing, filling, pressure holding, cooling, depressurization, mold opening, and ejection processes. The series of actions used to obtain the molded product, such as the actions from the start of the metering process to the start of the next metering process, is also called "material injection" or "molding cycle." Furthermore, the time required for one material injection is also called "molding cycle time" or "cycle time."

[0111] A typical molding cycle may include, for example, the following steps in sequence: metering, mold closing, pressure increase, mold closing, filling, pressure holding, cooling, pressure release, mold opening, and ejection. This sequence refers to the order in which each step begins. The filling, pressure holding, and cooling steps occur during the mold closing step. Alternatively, the start of the mold closing step can coincide with the start of the filling step. The end of the pressure release step can coincide with the start of the mold opening step.

[0112] Furthermore, to shorten the molding cycle time, multiple processes can be performed simultaneously. For example, the metering process can be performed during the cooling process of the previous molding cycle or during the mold closing process. In this case, the mold closing process can be set to be performed at the very beginning of the molding cycle. The filling process can also begin during the mold closing process. The ejection process can begin during the mold opening process. When an on / off valve is provided for the flow path of the nozzle 320, the mold opening process can begin during the metering process. This is because even if the mold opening process begins during the metering process, as long as the on / off valve closes the flow path of the nozzle 320, the molding material will not leak from the nozzle 320.

[0113] In addition, a single molding cycle can include processes other than metering, mold closing, pressurization, mold closing, filling, pressure holding, cooling, depressurization, mold opening, and ejection.

[0114] For example, a pre-metering backfeeding process can be performed after the pressure holding process ends and before the metering process begins, causing the screw 330 to retract to a pre-set metering start position. This reduces the pressure of the molding material accumulated in front of the screw 330 before the metering process begins, preventing the screw 330 from retracting abruptly at the start of the metering process.

[0115] Furthermore, a post-metering backflow process can be performed after the metering process is completed and before the filling process begins, retracting the screw 330 to a pre-set filling start position (also known as the "injection start position"). This reduces the pressure of the molding material accumulated in front of the screw 330 before the filling process begins, preventing leakage of the molding material from the nozzle 320 before the filling process begins.

[0116] The control device 700 is connected to the operation device 750, which receives user input, and the display device 760, which displays a screen. The operation device 750 and the display device 760 are, for example, composed of a touch panel 770, and can be integrated. The touch panel 770, as the display device 760, displays a screen under the control of the control device 700. Information such as the settings of the injection molding machine 10 and the current status of the injection molding machine 10 can be displayed on the screen of the touch panel 770. Furthermore, operation sections such as buttons and input fields for receiving user input can be displayed on the screen of the touch panel 770. The touch panel 770, as the operation device 750, detects user input on the screen and outputs a signal corresponding to the input operation to the control device 700. Thus, for example, the user can simultaneously check the information displayed on the screen and operate the operation sections on the screen to set the injection molding machine 10 (including inputting setting values). Furthermore, by operating the operation sections on the screen, the user can cause the injection molding machine 10 corresponding to the operation sections to operate. Furthermore, the operation of the injection molding machine 10 can include, for example, the operation (including stopping) of the mold clamping device 100, the ejection device 200, the injection device 300, the moving device 400, etc. Also, the operation of the injection molding machine 10 can include switching the screen displayed on the touch panel 770, which is a display device 760.

[0117] Furthermore, while the operation device 750 and display device 760 of this embodiment are integrated into a touch panel 770, they can also be provided independently. Additionally, multiple operation devices 750 can be provided. The operation device 750 and display device 760 are disposed on the operation side (negative Y-axis direction) of the mold clamping device 100 (more specifically, the fixed pressure plate 110).

[0118] [Concepts of Machine Learning Systems]

[0119] Figure 3 This is a diagram illustrating the structure of the machine learning system SYS of the injection molding machine according to this embodiment. Figure 3 As shown, the machine learning system SYS consists of a learning device 1300, a test injection molding machine 1350, and an injection molding machine 10.

[0120] The test injection molding machine 1350 is a conventionally installed injection molding machine used for machine learning in the factory. The structure of the test injection molding machine 1350 is the same as that of the injection molding machine 10, so the description is omitted.

[0121] The test injection molding machine 1350 of this embodiment manufactures molded articles according to the settings of the operators in the factory. Furthermore, the test injection molding machine 1350 outputs setting information set during injection molding of the molded article and measurement information measured during injection molding with that setting information to the learning device 1300. The setting information and measurement information are configured for machine learning.

[0122] Furthermore, the learning device 1300 can be, for example, a local server located in a factory or the like, or a cloud server. Moreover, the learning device 1300 can also be a fixed terminal device or a portable terminal device (mobile terminal) configured in a factory or the like. Fixed terminal devices can include, for example, a desktop PC (Personal Computer). Mobile terminal devices can include, for example, smartphones, tablets, laptops, etc.

[0123] The learning device 1300 generates training data based on the setting information and measurement information input from the test injection molding machine 1350, and uses the training data to perform machine learning, thereby generating a learned model LM.

[0124] The setting information refers to the settings used for injection molding, and is information derived by repeatedly performing injection molding to obtain the optimal settings. In this embodiment, the case where the setting information is a clamping force setting value is described, but this embodiment does not limit the setting information to a clamping force setting value.

[0125] The setting information is used for injection molding settings, and is particularly preferred to be information that needs to be adjusted according to the conditions and environment of injection molding. For example, the setting information can include VP switching position, holding pressure setting, filling speed setting, filling pressure, and back pressure setting. Furthermore, the metering-related setting information can include metering speed, metering delay, and metering end position. Moreover, the mold closing-related setting information, in addition to the mold closing force setting value, can also include pressurization timing, mold opening and closing speed, and mold opening position. Furthermore, the ejection device 200-related setting information can include ejection position, ejection pressure, ejection speed, and ejection compression timing. Finally, the temperature-related setting information within the injection molding machine 10 can include cylinder temperature setting, nozzle temperature setting, water cooling temperature, and mold temperature.

[0126] The measurement information is the information measured during injection molding using parameters set according to the setting information. In this embodiment, waveform data representing the actual value that changes during injection molding is used as the measurement information. When the setting information is a clamping force setting value, the actual value of the waveform data is the clamping force measured as the detection result of the connecting rod strain detector 141 (an example of a detection unit).

[0127] The learned model LM is a machine learning model that takes in the clamping force setpoint and waveform data representing the change in clamping force and performs machine learning on the learned model. Furthermore, when waveform data is input, the learned model LM outputs information correcting the clamping force setpoint (hereinafter also referred to as the clamping force correction value). The specific generation method and usage of the learned model LM will be described later.

[0128] The learning device 1300 can output the generated learned model LM to the test injection molding machine 1350. By repeatedly performing injection molding using the clamping force setting value corrected by the learned model LM in the test injection molding machine 1350, the reliability of the correction setting information output by the learned model LM can be measured.

[0129] Furthermore, the learning device 1300 records the generated learned model LM and the reliability coefficient based on the measured reliability level in the storage medium 702 of the control device 700 of the injection molding machine 10. The reliability coefficient will be described later.

[0130] The injection molding machine 10 is shipped from the factory with the learned model LM and other information registered. Therefore, when the injection molding machine 10 is used at the destination, the clamping force setting value (an example of setting information) can be adjusted without machine learning, thus reducing the workload of the operators.

[0131] [An example of the hardware and functional structure of a learning device]

[0132] Next, refer to Figure 4 An example of the functional structure used by the learning device 1300 to generate the learned model LM will be explained.

[0133] Figure 4 This diagram illustrates an example of the hardware and functional structure of the learning device 1300 according to this embodiment.

[0134] The functions of the learning device 1300 are implemented through any hardware or any combination of hardware and software. For example, such as Figure 4 As shown, the learning device 1300 includes an input device 1301, an auxiliary storage device 1302, a memory device 1303, a display device 1304, a communication interface 1305, an external interface 1306, and a CPU 1307 connected via a bus 1308.

[0135] Input device 1301 receives various inputs from the user. Input device 1301 includes, for example, an operation input device that receives mechanical operation inputs from the user. Furthermore, the operation input device includes, for example, a touch panel mounted on display device 1304, a touchpad separately provided with display device 1304, etc.

[0136] Auxiliary storage device 1302 stores various installed programs and files, data, etc., required for various processes. Auxiliary storage device 1302 may include, for example, HDD (Hard Disc Drive), SSD (Solid State Drive), flash memory, etc.

[0137] When a program start instruction is present, memory device 1303 reads the program from auxiliary storage device 1302 and stores it. Memory device 1303 may include, for example, DRAM (Dynamic Random Access Memory) or SRAM (Static Random Access Memory).

[0138] Display device 1304 displays information screens and operation screens to the user. For example, display device 1304 includes a remote operation display device. Display device 1304 is, for example, a liquid crystal display or an organic EL (Electroluminescence) display.

[0139] The communication interface 1305 serves as an interface for communicating with external devices. Thus, the learning device 1300 can communicate with external devices such as the injection molding machine 10 via the communication interface 1305. Furthermore, the communication interface 1305 can have various communication interfaces depending on the communication method with the connected device.

[0140] External interface 1306 functions as an interface for reading data from and writing data to a recording medium (not shown). Recording media include, for example, floppy disks, CDs (Compact Discs), DVDs (Digital Versatile Discs), BDs (Blu-ray Discs), SD cards, and USB storage devices. Thus, the learning device 1300 can read various types of data used in processing from the recording medium and store them in the auxiliary storage device 1302, or install programs that implement various functions.

[0141] CPU 1307 executes various programs loaded from auxiliary storage device 1302 into memory device 1303, and implements various functions related to learning device 1300 according to the programs.

[0142] The CPU 1307 of the learning device 1300 executes the program stored in the auxiliary storage device 1302. Thus, the CPU 1307, as a functional unit, includes a data acquisition unit 1311, a setting unit 1312, a learning unit 1313, a test output unit 1314, a test result acquisition unit 1315, a coefficient calculation unit 1316, and an output unit 1317.

[0143] The data acquisition unit 1311 acquires a combination of multiple clamping force setting values ​​(an example of setting information) used in machine learning and waveform data (an example of measurement information) representing changes in clamping force from the test injection molding machine 1350. There is no particular limitation on the number of clamping force setting values ​​and waveform data acquired, as long as it is sufficient to generate a number of learned models (LMs).

[0144] The setting unit 1312 generates training data by combining the clamping force setting value acquired by the data acquisition unit 1311 with waveform data. In this embodiment, the setting unit 1312 displays multiple waveform data on the display device 1304. The operator sets the correct interpretation conditions for the displayed waveform data.

[0145] The forward condition refers to the waveform data measured when generating an appropriate molded product from multiple waveform data. One or more waveform data can be set to define the forward condition.

[0146] Figure 5 This is a diagram illustrating multiple waveform data acquired by the data acquisition unit 1311. Figure 5 In the example shown, the vertical axis represents the actual values, and the horizontal axis represents the time axis. Figure 5 In the example shown, waveform data 1601–1606 are displayed. The actual value is set to the actual measured clamping force.

[0147] like Figure 5 As shown, waveform data 1601 to 1606 are examples where the actual value of the clamping force differs from the set clamping force value. The degree of change of the actual value of waveform data 1601 to 1606 from time t0 is different. The waveform data measured when a suitable molded product is produced is waveform data 1603. The shape of the waveform data when a suitable molded product is produced tends to become the shape represented by waveform data 1603. Therefore, the operator sets waveform data 1603, which is judged to have an appropriate degree of change, as the positive condition, and sets other waveform data 1601, 1602, and 1604 to 1606 as negative conditions.

[0148] Return to Figure 4 The setting unit 1312 generates data for training purposes, which sets a flag indicating whether the combination of the clamping force setting value and waveform data acquired by the data acquisition unit 1311 according to the operator's operation.

[0149] The learning unit 1313 performs machine learning based on multiple training data output from the setting unit 1312, thereby generating a learned model LM. Specifically, the learning unit 1313 reads the clamping force setting value, waveform data, and markers indicating whether a condition is correct from each training data set, performs machine learning, and generates the learned model LM. The generated learned model LM, by inputting waveform data measured in the injection molding machine 10, can output a corrected clamping force value (information correcting the clamping force setting value) that represents the measurable correct condition, i.e., the waveform data.

[0150] The learned model LM is generated by applying supervised learning to the basic learning model. Specifically, the learning unit 1313 performs machine learning on a set of training data (training data set) consisting of a combination of waveform data as input and the positive solution (clamping force correction value) as output, thereby generating the learned model LM.

[0151] Furthermore, a learned model (LM) can be updated by adding a training dataset to an existing learned model (LM).

[0152] Machine learning used in generating a learned model (LM) includes, for example, machine learning that uses a deep neural network (DNN), also known as deep learning.

[0153] The test output unit 1314 outputs the learned model LM generated by the learning unit 1313 to the control device 700 of the test injection molding machine 1350. The method of outputting the learned model LM to the control device 700 of the test injection molding machine 1350 can be any method, for example, it can be sent to the control device 700 of the test injection molding machine 1350 through a predetermined communication line set in the factory.

[0154] The test result acquisition unit 1315 acquires the test results from the test injection molding machine 1350 when injection molding is performed using the learned model LM. As the test results, it acquires the clamping force correction value (information on the corrected clamping force setting value) output by the learned model LM and the waveform data when injection molding is performed using the clamping force correction value.

[0155] In the test injection molding machine 1350, waveform data measured by injection molding with an initial clamping force setting is input to the learned model LM. The learned model LM then outputs a clamping force correction value. The test injection molding machine 1350 then uses this clamping force correction value as the clamping force setting value for injection molding. The test injection molding machine 1350 then acquires waveform data measured during injection molding using the clamping force correction value. By repeating this process, the test injection molding machine 1350 acquires a combination of the clamping force correction value and waveform data as a test result, and outputs this test result to the learning device 1300.

[0156] The coefficient calculation unit 1316 calculates the reliability coefficient, which represents the reliability of the learned model LM, and outputs it to the test injection molding machine 1350 based on the test results input from the test injection molding machine 1350.

[0157] The reliability factor is set as the gain of reliability based on the clamping force correction value output by the learned model LM, with the clamping force setting value of the appropriate molded part (i.e., the positive solution) as the benchmark. (Reference) Figure 6 and Figure 7 The reliability of the clamping force correction value output by the learned model LM is explained.

[0158] Figure 6 and Figure 7 This is a graph representing the degree of deviation of the clamping force correction value output by the learned model LM based on the clamping force setting value of the appropriate molded product (i.e., the correct solution). Figure 6 and Figure 7 The degree of deviation of the clamping force correction values ​​output by different learned LM models is shown.

[0159] Figure 6 and Figure 7The vertical axis shows the amount of correction of the clamping force correction value relative to the clamping force setting value (clamping force correction value - clamping force setting value). The clamping force correction value is set as the value output by the learned model LM when waveform data measured in injection molding using this clamping force setting value is input to the learned model LM. The horizontal axis shows the amount of correction of the clamping force correction value that becomes the correct solution relative to the preset clamping force setting value (clamping force correction value that becomes the correct solution - clamping force setting value). Figure 6 and Figure 7 This shows the case where the correction amount relative to the preset clamping force setting is within the range of "0%" to "100%".

[0160] exist Figure 6 In the first learned model LM shown, with the baseline 1701 as the reference, the deviation between the correction amount of the first learned model LM and the correction amount of the correct solution falls within the range between the lower limit 1703 and the upper limit 1702.

[0161] In contrast, Figure 7 In the second learned model LM shown, with the baseline 1801 as the reference, the deviation between the correction amount of the second learned model LM and the correction amount of the correct solution falls within the range between the lower limit 1803 and the upper limit 1802.

[0162] Right now, Figure 6 The correction value of the clamping force output by the first learned model LM is shown as... Figure 7 Compared to the correction value of the clamping force output by the second learned model LM, the deviation is small.

[0163] Furthermore, the coefficient calculation unit 1316 calculates the reliability coefficient based on the deviation for each learned model LM.

[0164] The reliability coefficient involved in this embodiment is, for example, the gain relative to the correction amount of the clamping force correction value output from the learned model LM, and is a value between '0' and '1'. The higher the reliability of the learned model LM, the larger the reliability coefficient.

[0165] exist Figure 6 In the example shown, the coefficient calculation unit 1316 calculates the reliability coefficient based on the difference 1704 between the lower limit 1703 and the upper limit 1702. Similarly, in Figure 7 In the example shown, the coefficient calculation unit 1316 calculates the reliability coefficient based on the difference 1804 between the lower limit 1803 and the upper limit 1802. The smaller the difference between the upper and lower limits, the larger the value set by the coefficient calculation unit 1316 as the reliability coefficient. Thus, the reliability coefficient corresponding to the deviation is calculated.

[0166] Return to Figure 4The output unit 1317 outputs the learned model LM generated by the learning unit 1313 and the reliability coefficients calculated by the coefficient calculation unit 1316 to the control device 700 of the injection molding machine 10. The method for outputting the learned model LM and reliability coefficients to the control device 700 of the injection molding machine 10 can be any method, and can be transmitted to the control device 700 of the injection molding machine 10 via a predetermined communication line installed in the factory. Furthermore, the output unit 1317 can write the learned model LM and reliability coefficients to a predetermined recording medium. Thus, the learned model LM can be registered in the control device 700 of the injection molding machine 10 via a predetermined storage medium. Therefore, the registration of the learned model LM and reliability coefficients by the injection molding machine 10 to the control device 700 is performed in the factory or the like before the injection molding machine 10 leaves the factory. However, the registration of the learned model LM and reliability coefficients is not limited to before leaving the factory; for example, it can be performed after leaving the factory using a shared communication line or the like.

[0167] Figure 8 This is a schematic diagram illustrating the process flow between the test injection molding machine 1350 and the learning device 1300 involved in this embodiment.

[0168] like Figure 8 As shown, the test injection molding machine 1350 outputs the combination of the first setting information (clamping force setting value) and the first waveform data, the combination of the second setting information (clamping force setting value) and the second waveform data, and the combination of the third setting information (clamping force setting value) and the third waveform data to the learning device 1300 (step S1501). Furthermore, the combination of setting information and waveform data output from the test injection molding machine 1350 to the learning device 1300 is not limited to three; the number input is the number required to generate the learned model LM.

[0169] The setting unit 1312 generates training data by setting whether each combination of the input setting information and waveform data is a correct solution condition. (Step S1502)

[0170] The learning unit 1313 generates a learned model LM by performing machine learning on the model IM based on multiple training data output from the setting unit 1312 (step S1503).

[0171] The test output unit 1314 outputs the learned model LM along with the test request to the test injection molding machine 1350 (step S1504). The test injection molding machine 1350 then performs an injection molding test using the learned model LM.

[0172] Then, the test injection molding machine 1350 outputs the test results of molding using the learned model LM to the learning device 1300 (step S1505).

[0173] Then, the coefficient calculation unit 1316 of the learning device 1300 calculates the reliability coefficient of the learned model LM based on the test results (step S1506). The method for calculating the reliability coefficient is as described above, so the explanation is omitted.

[0174] Then, the output unit 1317 outputs the learned model LM and reliability coefficient to the injection molding machine 10.

[0175] After performing the above-mentioned processing, the learning device 1300 and the test injection molding machine 1350 register the learned model LM and reliability coefficient in the control device 700 of the injection molding machine 10.

[0176] [Functional Structure of the Control Device of an Injection Molding Machine]

[0177] Figure 9 This is a diagram showing the components of the control device 700 involved in this embodiment using function blocks. Figure 9 The functional blocks illustrated are conceptual and do not necessarily need to be physically configured as shown. All or part of each functional block can be functionally or physically distributed / integrated in any unit. All or any part of the processing functions performed in each functional block are implemented through a program executed by the CPU701. Alternatively, each functional block can be implemented as hardware based on wiring logic. Figure 9 As shown, the control device 700 includes an input receiving unit 711, a condition calculation unit 712, an action control unit 713, an acquisition unit 714, an information generation unit 715, a correction unit 716, and a display control unit 717.

[0178] Furthermore, the learned model LM and reliability coefficient 722 are stored in the storage medium 702 of the control device 700. The learned model LM and reliability coefficient 722 are information registered in the learning device 1300 before the injection molding machine 10 leaves the factory. As described above, the learned model LM has completed learning at the stage when the injection molding machine 10 leaves the factory.

[0179] The input receiving unit 711 receives input operations from the user of the operating device 750 via the input interface 703.

[0180] The input receiving unit 711 receives setting information related to the conditions used by the injection molding machine 10 for injection molding as an input operation. In this embodiment, the received setting information is assumed to be a clamping force setting value.

[0181] The condition calculation unit 712 is used to calculate the parameters for injection molding based on the input setting information. For example, the condition calculation unit 712 calculates the position of the crosshead 151 so that when a clamping force setting value is input, it outputs the clamping force represented by the clamping force setting value.

[0182] The motion control unit 713 controls the operation of the injection molding machine 10 according to the parameters calculated by the condition calculation unit 712. For example, the motion control unit 713 uses the parameters calculated by the condition calculation unit 712 to perform metering process, mold closing process, pressure increase process, mold closing process, filling process, pressure holding process, cooling process, pressure release process, mold opening process, and ejection process to manufacture molded products.

[0183] The acquisition unit 714 acquires waveform data (an example of measurement information) representing the actual value of the clamping force measured during the manufacturing of the molded article by the motion control unit 713.

[0184] The information generation unit 715 uses the waveform data acquired by the learning model LM input acquisition unit 714 to generate a clamping force correction value (an example of correcting setting information). The output clamping force correction value is a clamping force setting value corrected to the waveform data with the correct solution condition set at output.

[0185] The correction unit 716 uses the reliability coefficient 722 corresponding to the learned model LM to correct the clamping force correction value generated by the information generation unit 715.

[0186] In this embodiment, the correction unit 716 multiplies the correction amount (clamping force correction value - clamping force set value) included in the clamping force correction value by a reliability coefficient 722, and then adds the clamping force set value to the correction amount multiplied by the reliability coefficient 722. Through this calculation, the clamping force correction value is adjusted according to the reliability of the learned model LM. In other words, the correction unit 716 can generate a clamping force correction value corrected according to the reliability coefficient 722.

[0187] Furthermore, this embodiment describes a method of multiplying the correction amount by the reliability coefficient 722 as a correction of the clamping force correction value using the reliability coefficient 722. However, any correction method can be used as long as the correction setting information using the reliability coefficient 722 is used.

[0188] Then, the condition calculation unit 712 sets the clamping force correction value corrected according to the reliability coefficient 722 as the clamping force setting value, and calculates the position (parameter) of the crosshead 151 to output the clamping force shown in the clamping force setting value.

[0189] The motion control unit 713 controls the operation of the injection molding machine 10 according to the parameters calculated by the condition calculation unit 712. Subsequent processing is a repetition of the above process.

[0190] That is, the control device 700 of this embodiment repeatedly performs the following processes: 1) calculation of parameters based on the clamping force correction value; 2) motion control based on the parameters; 3) acquisition of waveform data measured during the motion; 4) inputting the waveform data into the learned model LM and outputting the clamping force correction value; 5) correcting the clamping force correction value according to the reliability coefficient 722. Through this repetition, the clamping force correction value after correction by the correction unit 716 is adjusted to an appropriate clamping force setting value for outputting the molded product.

[0191] The display control unit 717 controls the display device 760 to display a display screen. Furthermore, this embodiment describes an example of outputting display screens, etc., to the display device 760, but the output destination of the display screen is not limited to the display device 760. For example, the display control unit 717 can output display screens, etc., to an information processing device connected via a network.

[0192] The display control unit 717 displays a screen on the display device 760 that includes a field for inputting the clamping force setting value required for the initial molding. Furthermore, at least one of waveform data and clamping force correction values ​​can be displayed on the screen shown by the display control unit 717. Specific display screens will be described later.

[0193] [Example of changes in clamping force setting]

[0194] Figure 10 This is a diagram illustrating the change in the clamping force setting value (setting information) caused by the correction of the learned model LM involved in the control device 700 according to this embodiment.

[0195] exist Figure 10 In the example shown, the clamping force setting value is input by the input receiving unit 711 during the first injection (step S1). Then, the control device 700 calculates a clamping force correction value (an example of correcting the setting information) based on waveform data measured during molding of the molded article according to the clamping force setting value set in the first injection (step S1). Then, the control device 700 sets the calculated clamping force correction value as the clamping force setting value for the second injection (step S2).

[0196] By repeating this process, the clamping force setting converges to the specified value 2003. The specified value 2003 is the appropriate clamping force setting for outputting the molded product (the correct clamping force setting).

[0197] For example, the correction unit 716 determines whether the difference between the clamping force correction value generated as the (n+1)th injection (step Sn+1) (used as the clamping setting value for the (n+2)th injection) and the clamping force correction value generated in the nth injection (step Sn) (used as the clamping setting value for the (n+1)th injection) is less than a preset stability detection range. If it is determined that the difference is greater than the stability detection range, the above process is repeated. On the other hand, if it is determined that the difference is less than the stability detection range, the generated clamping force correction value is considered as the appropriate clamping force setting value for the molded product (the correct clamping force setting value) and the above process ends. In addition, the stability detection range is a range preset as a condition for ending the generation of the clamping force correction value.

[0198] exist Figure 10 In the example shown, the correction unit 716 determines that the difference between the mold clamping force correction value generated as the 6th injection (step S6) and the mold clamping force correction value of the 5th injection (step S5) is less than a preset stable detection range. Therefore, the adjustment period 2001 ends, and the process proceeds to the correction end period 2002.

[0199] Then, after the sixth injection (step S6), the clamping force correction value generated in the sixth injection (step S6) is used as the clamping force setting value to control the operation of the injection molding machine 10. Afterwards, it is possible to manufacture molded articles using appropriate clamping force settings. This improves the quality of the molded articles.

[0200] [Example of a display screen]

[0201] Figure 11 This diagram illustrates an example of a display screen displayed by the display control unit 717 according to this embodiment. (Example:) Figure 11 As shown, the display screen 2100 shows the following: automatic condition setting bar 2101, initial setting value bar 2102, correction value bar 2103, actual measured value bar 2104, waveform data bar 2105, setting value change display bar 2107, stable detection range setting bar 2110, stable detection injection quantity setting bar 2111, adjustment end display bar 2112, model version upgrade bar 2113, reference button 2114, and execution button 2115.

[0202] The Automatic Condition Setting section 2101 is set to determine whether automatic correction of the clamping force setting value is performed. When "In" is set, correction of the clamping force setting value using the learned model LM is performed. When "Cut" is set, correction of the clamping force setting value is not performed.

[0203] The initial setting value field 2102 is set as the input field for the clamping force setting value used in the initial molding.

[0204] Waveform data 2105 displays waveform data 2106 measured during each injection molding process at the currently set clamping force setting. The vertical axis represents the actual value of the clamping force, and the horizontal axis represents time.

[0205] The correction value column 2103 is set to display the clamping force correction value after correction by the correction unit 716. For example, the clamping force correction value generated by the above calculation is displayed using the waveform data displayed in the waveform data column 2105.

[0206] The actual measured value column 2104 is set to display the actual value measured during injection molding at the currently set clamping force setting value (clamping force correction value). The actual value displayed in the actual measured value column 2104 can be the average value of the waveform data 2106 or the peak value of the waveform data 2106. That is, the condition calculation unit 712 sets the parameters of the injection molding machine 10 according to the clamping force correction value displayed in the correction value column 2103, so that the actual value shown in the actual measured value column 2104 is close to the clamping force correction value displayed in the correction value column 2103.

[0207] The stability detection range setting column 2110 and the stability detection injection quantity setting column 2111 show the conditions for ending the correction process of the clamping force setting value.

[0208] The stability detection range setting field 2110 is a setting field for comparing the difference between the clamping force correction value generated for the (n+1)th injection (step Sn+1) and the clamping force setting value for the nth injection (step Sn). The method of using this stability detection range is as described above, so the explanation is omitted.

[0209] The Stable Detection Pour Count Setting field 2111 is set to adjust the stable detection pour count for adjusting the clamping force correction value. When the number of pours performed to correct the clamping force correction value becomes the same as the stable detection pour count, the correction of the clamping force correction value ends.

[0210] The adjustment end display bar 2112 shows the remaining amount of material to be dispensed before the correction ends, indicating that a stable number of dispensing tests have been completed. Additionally, display screen 2100 explains an example where a dispensing quantity is set as the condition for the correction to end. However, the condition for the correction to end is not limited to the dispensing quantity; time (e.g., minutes) and the percentage achieved before the end can also be displayed.

[0211] The setting change display bar 2107 shows the mold clamping force setting value that changes over time. Figure 11In the setting change display bar 2107 shown, for ease of explanation, all the clamping force setting values ​​generated from the initial clamping force setting value 2108 to the appropriate clamping force setting value 2109 are plotted. However, in practice, only the clamping force setting values ​​generated so far are plotted.

[0212] The Model Version Upgrade bar 2113, Reference button 2114, and Execute button 2115 are set up to update the learned Model (LM).

[0213] For example, the input receiving unit 711 receives the press of the reference button 2114, thereby displaying the selection screen of the learned model LM on the display control unit 717.

[0214] Then, the learned model LM selected through this selection screen is displayed in the model version upgrade column 2113.

[0215] Then, in the model version upgrade section 2113, when the learned model LM is displayed, the input receiving unit 711 presses the receive execution button 2115, thereby registering the learned model LM to be used in the storage medium 702. For subsequent processing, the registered learned model LM will be used.

[0216] [Reliability coefficient update]

[0217] This implementation does not limit the update target to the learned model (LM). For example, the reliability coefficients can be updated.

[0218] For example, when calibrating the clamping force setting value using the learned model LM after the injection molding machine 10 leaves the factory, if it takes time to derive the appropriate clamping force setting value, sometimes the time to derive the appropriate clamping force setting value can be shortened by changing only the reliability coefficient without changing the learned model LM.

[0219] Therefore, the control device 700 according to this embodiment can update its reliability coefficient as needed. Any method can be used to update the reliability coefficient. For example, it can be done using methods such as... Figure 11 The display screen shown has an input field for inputting reliability coefficients. Then, when the input receiving unit 711 inputs a reliability coefficient in the input field, the control device 700 updates the reliability coefficient stored in the storage medium 702. Furthermore, when the control device 700 receives an updated reliability coefficient from the learning device 1300, it can also update the reliability coefficient.

[0220] Thus, after the injection molding machine 10 leaves the factory, the reliability coefficient is changed without changing the learned model LM, thereby improving stability and allowing for the adjustment of the time required to correct the clamping force setting value.

[0221] Furthermore, this embodiment is not limited to the method of updating only the reliability coefficients without updating the learned model LM; the reliability coefficients can be updated simultaneously when updating the learned model LM.

[0222] [Processing steps for correcting configuration information]

[0223] Figure 12 This is a flowchart illustrating the adjustment steps of the clamping force setting value (setting information) in the control device 700 according to this embodiment. In this embodiment, the display control unit 717 continuously displays as shown in the flowchart. Figure 11 The display screen is as shown.

[0224] First, the input receiving unit 711 receives the input of the clamping force setting value used in the initial (injection) molding of the initial setting value column 2102 of the display screen 2100 (step S2201).

[0225] Next, the condition calculation unit 712 calculates the parameters for (injection) molding according to the received clamping force setting value (step S2202).

[0226] The motion control unit 713 controls the motion of the injection molding machine 10 according to the calculated parameters to manufacture the molded product (step S2203).

[0227] The acquisition unit 714 acquires waveform data (an example of measurement information) representing the actual value of the clamping force measured during the manufacturing of the molded article by the motion control unit 713 (step S2204). The acquired waveform data is displayed in the waveform data column 2105 of the display screen 2100. Furthermore, the actual measured value column 2104 of the display screen 2100 displays the actual value based on the waveform data.

[0228] The information generation unit 715 generates a clamping force correction value by inputting waveform data from the learned model LM (step S2205).

[0229] The calibration unit 716 calibrates the clamping force correction value based on the reliability coefficient 722 (step S2206). The calibrated clamping force correction value is displayed in the correction value column 2103 of the display screen 2100. In the setting value change display column 2107, the calibrated clamping force correction value is plotted as the new clamping force setting value.

[0230] Then, the correction unit 716 determines whether the difference between the previous mold clamping force correction value and the current mold clamping force correction value is greater than the stable detection range (step S2207). When it is determined that the difference is less than the stable detection range (step S2207: "No"), the process ends.

[0231] On the other hand, when it is determined that the difference is greater than the stable detection range (step S2207: "Yes"), the correction unit 716 determines whether the number of injections used to derive the correction value of this clamping force is greater than or equal to the stable detection injection number (step S2208). When it is determined that the number of injections this time is greater than or equal to the stable detection injection number (step S2208: "Yes"), the process ends.

[0232] When the correction unit 716 determines that the number of injections this time is less than the number of injections detected in the stable test (step S2208: "No"), the condition calculation unit 712 sets the clamping force correction value corrected in step S2206 as the clamping force setting value, and calculates the parameters for injection molding according to the clamping force setting value (step S2202).

[0233] The control device 700 according to this embodiment can easily adjust the clamping force setting value for manufacturing a suitable molded article by performing the above processing steps.

[0234] In the above embodiments, an example using waveform data as measurement information was described. However, the measurement information is not limited to waveform data; any information measured during the injection molding of the molded article is acceptable. For example, it could be detection information detected by a sensor (an example of a detection unit) provided on the injection molding machine 10 during the injection molding of the molded article. Furthermore, it could be a voltage signal used for controlling the injection molding machine 10 during the injection molding of the molded article. Moreover, it could be communication data received from an external device that performs measurements on the injection molding machine 10 during the injection molding of the molded article.

[0235] Furthermore, in this embodiment, the measurement information is not limited to one piece, and multiple pieces of information can be combined. For example, at least two of the following can be combined: waveform data, detection information detected by a sensor (an example of a detection unit), voltage signal, and communication data.

[0236] Furthermore, this embodiment describes the case where there is only one setting information (clamping force setting value). However, this embodiment is not limited to the case where there is only one setting information (clamping force setting value), and machine learning can also be performed on combinations of multiple setting information.

[0237] [effect]

[0238] Conventionally, the conditions for injection molding were adjusted by observing the molded product. In contrast, in this embodiment, machine learning is used to perform a correlation between measurement information (e.g., waveform data) and setting information (e.g., clamping force setting value). Therefore, the control device 700 according to this embodiment can adjust the clamping force setting value based on the waveform data using the learned model LM. Thus, there is no need for technicians to adjust the setting information, thereby reducing the burden of setting adjustments required for manufacturing molded products.

[0239] Furthermore, adjusting settings using the learned model LM becomes easy, thus reducing the effort required for adjustments and the frequency of maintenance.

[0240] Furthermore, the learned model LM, which is machine learning through the learning device 1300, is registered on the injection molding machine 10, thus reducing the burden of machine learning at the destination of shipment.

[0241] The control device 700 of this embodiment corrects the setting information using a reliability coefficient corresponding to the reliability level of the learned model LM, thus suppressing over-correction of the setting information based on the learned model LM. Furthermore, by utilizing the reliability coefficient, the responsiveness and stability can be adjusted regarding the correction of the setting information.

[0242] Furthermore, when the amount of setting information correction is within the specified range compared to the previous setting, the control device 700 according to this embodiment ends the setting information correction, thus achieving a balance between the accuracy of the setting information and the time until the setting information is exported.

[0243] When the number of times the setting information is corrected reaches a predetermined number, the control device 700 according to this embodiment ends the correction of the setting information, thus suppressing the time delay until the setting information is exported.

[0244] The embodiments have been described in detail above, but the present invention is not limited to this specific embodiment and various modifications and alterations can be made within the scope of the spirit described in the technical solution.

Claims

1. A control device for an injection molding machine, comprising: The receiving unit receives setting information indicating settings for injection molding. The acquisition unit acquires measurement information measured during injection molding with the set information. The storage unit stores a learned model that is used to input the measurement information acquired by the acquisition unit and output corrected setting information that is modified according to the setting information; and The correction unit uses a reliability coefficient preset based on the reliability of the learned model to correct the correction setting information output by the learned model.

2. The control device for the injection molding machine according to claim 1, wherein, The learned model stored in the storage unit has completed its learning process at the stage when the injection molding machine leaves the factory.

3. The control device for the injection molding machine according to claim 1, wherein, The storage unit stores the reliability coefficient at the stage when the injection molding machine leaves the factory. The control device of the injection molding machine also includes a control unit for changing the reliability coefficient stored in the storage unit.

4. The control device for the injection molding machine according to any one of claims 1 to 3, wherein, The measurement information is any one or more of the following: the detection results detected by the detection unit during molding, the voltage signal used to control molding, and the communication data received from an external device.

5. A display device for an injection molding machine, comprising: The display control unit displays a screen that includes a column for inputting setting information for injection molding. The acquisition unit acquires measurement information measured during molding using the setting information input into the field. The storage unit stores a learned model that is modified by the setting information represented by the setting information and is used to input the measurement information acquired by the acquisition unit and output the modified setting information. and The correction unit uses a reliability coefficient pre-set based on the reliability of the learned model to correct the correction setting information output by the learned model. The display screen shown on the display control unit displays at least one of the measurement information and the correction setting information.

Images