Method for generating molding conditions for an injection molding system, injection molding system, and molding condition generation support program for an injection molding system

Abstract

To provide a method for generating molding conditions for an injection molding system, an injection molding system, and a molding condition generation support program for an injection molding system that can generate molding conditions during injection compression molding or core back molding relatively more easily than before.SOLUTION: An injection molding machine 11 is provided with a molding die 41 in which a cavity C is formed between a fixed mold 15 and a movable mold 17, a mold clamping device 13 to which the molding die 41 is attached, and an injection device 14 that injects into the cavity C. A learning model for injection compression molding or core-back molding generates molding conditions for injection compression molding or core-back molding from information about the injection molding machine 11, information about the molding die 41, and information about the resin material supplied to the injection device 14.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a method for generating molding conditions for an injection molding system equipped with an injection molding machine that moves a movable mold relative to a fixed mold during injection compression molding or core-back molding, an injection molding system, and a molding condition generation support program for an injection molding system. [Background technology]

[0002] Conventionally, methods relating to setting molding conditions for injection compression molding are known, such as those described in Patent Documents 1 and 2. Patent Document 1 describes correcting the injection filling amount in injection compression molding when the mold position when the mold clamping pressure is removed deviates from an arbitrary setting value set with respect to a reference point. Patent Document 1 also describes determining the reference point in advance based on the product shape, etc. Patent Document 2 describes determining, during a test injection, molding conditions that allow molding of a good product between the injection speed of the molten resin and the speed in the direction of increasing the cavity volume of the mold, and then performing molding under conditions that meet the molding conditions. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 8-174616 [Patent Document 2] Japanese Patent Application Publication No. 4-246523 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the injection compression molding conditions set in Patent Documents 1 and 2 do not take into account the type of resin material. In actual injection compression molding, the temperature of the heating cylinder varies depending on the type of resin material, which in turn leads to differences in the fluidity and other behavior of the molten resin material in the cavity. Therefore, injection compression molding conditions cannot be generally determined. Although Patent Document 1 suggests that the product shape should be reflected in the molding conditions, setting actual injection compression molding conditions almost always requires information about the mold used to shape the product. Therefore, even if the molding conditions are set to reflect the product shape, the injection compression molding conditions cannot be generally determined. Therefore, the injection compression molding conditions are still set by skilled operators through repeated trial and error. Similarly, the core-back molding process is still performed by skilled operators through repeated trial and error.

[0005] Therefore, an object of the present invention is to provide a method for generating molding conditions for an injection molding system, an injection molding system, and a molding condition generation support program for an injection molding system, which can generate molding conditions for injection compression molding or core-back molding relatively easily compared to conventional methods. Other objects and novel features will become apparent from the description of this specification and the accompanying drawings. [Means for solving the problem]

[0006] The method for generating molding conditions for an injection molding system according to claim 1 of the present invention is a method for generating molding conditions for an injection molding system equipped with an injection molding machine that moves a movable mold relative to a fixed mold during injection compression molding or core-back molding, and is a method for generating molding conditions for an injection molding system equipped with an injection molding machine that moves a movable mold relative to a fixed mold during injection compression molding or core-back molding, and is equipped with an injection molding machine having a molding mold in which a cavity is formed between the fixed mold and the movable mold, a mold clamping device to which the molding mold is attached, and an injection device that injects into the cavity, and a learning model for injection compression molding or core-back molding generates molding conditions for injection compression molding or core-back molding from at least information about the injection molding machine, information about the molding mold, and information about the resin material supplied to the injection device. [Effects of the Invention]

[0007] The method for generating molding conditions for an injection molding system of the present invention is a method for generating molding conditions for an injection molding system equipped with an injection molding machine that moves a movable mold relative to a fixed mold during injection compression molding or core-back molding, and is equipped with an injection molding machine having a molding mold in which a cavity is formed between the fixed mold and the movable mold, a mold clamping device to which the molding mold is attached, and an injection device that injects into the cavity, and a learning model for injection compression molding or core-back molding generates molding conditions for injection compression molding or core-back molding from at least information about the injection molding machine, information about the molding mold, and information about the resin material supplied to the injection device, so that molding conditions for injection compression molding or core-back molding can be generated relatively easily than before. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a schematic explanatory diagram of an injection molding machine of an injection molding system according to an embodiment of the present invention. [Figure 2] 1 is an enlarged view of a main part of a mold clamping device and a molding mold of an injection molding machine according to an embodiment of the present invention, showing a mold open state. FIG. [Figure 3]1 is an enlarged view of a main part of a mold clamping device and a molding die of an injection molding machine according to an embodiment of the present invention, showing a state at the start of injection compression molding. FIG. [Figure 4] 1 is an enlarged view of a main part of a mold clamping device and a molding die of an injection molding machine according to an embodiment of the present invention, showing the state at the end of injection compression molding. FIG. [Figure 5] FIG. 3 is a view taken along the line AA in FIG. 2. [Figure 6] FIG. 2 is a block diagram of a machine learning device of the injection molding system of the present embodiment. [Figure 7] FIG. 10 is a schematic diagram of a screen for inputting information about a molding die in an input device of the injection molding machine of the injection molding system of the present embodiment. [Figure 8] FIG. 10 is a schematic diagram of a screen for inputting information about molding defects in the input device of the injection molding machine of the injection molding system of the present embodiment. [Figure 9] FIG. 10 is a diagram showing a neural network of a learning model of the machine learning device of the injection molding system of the present embodiment. [Figure 10] FIG. 10 is a flowchart illustrating the generation of molding conditions using a learning model of the machine learning device of the injection molding system of this embodiment and the correction of the learning model.

[0009] Specific embodiments will be described in detail below with reference to the drawings. However, the present invention is not limited to the following embodiments. In addition, the following description and drawings have been simplified as appropriate for clarity of explanation. In addition, hatching has been omitted in some parts to avoid cluttering the drawings.

[0010] <Injection molding machine> An injection molding system 1 equipped with an injection molding machine 11 of this embodiment will be described with reference to Figures 1 to 5. First, the injection molding machine 11, which moves a movable mold relative to a fixed mold during injection compression molding or core-back molding, will be described with reference to Figure 1. The injection molding machine 11 is equipped with a mold clamping unit 13 and an injection unit 14 on a bed 12. To explain the mold clamping unit 13 first, the mold clamping unit 13 is equipped with two mold opening and closing mechanisms 19 that move a movable platen 18, on which a movable mold 17 is attached, relative to a fixed platen 16, on which a fixed mold 15 is attached, and mold clamping cylinders 21 of four mold clamping mechanisms 20 that clamp the fixed mold 15 and the movable mold 17 together (however, only the mold opening and closing mechanism 19 and mold clamping mechanism 20 on the near side are shown in Figure 1).

[0011] A funnel-shaped portion 23 for inserting a nozzle 22 of the injection unit 14 is provided in the center of the side of the fixed platen 16 opposite the mold mounting surface, which is fixed on the bed 12. A hole is provided in the center of the funnel-shaped portion 23 for connecting the nozzle 22 to the fixed mold 15. Clamping cylinders 21 of the mold clamping mechanism 20 are provided near each of the four corners inside the fixed platen 16. The rod on the forward side of the piston 24 of the clamping cylinder 21 forms a tie bar 25. The clamping cylinder 21 is a double-acting cylinder equipped with a clamping oil chamber on the forward side of the piston 24 and a mold-opening oil chamber on the backward side of the piston 24. The clamping cylinder 21 is connected to a hydraulic system 26 equipped with valves, sensors, a pump, a tank, etc. In the present invention, the clamping cylinder 21 is controlled by a valve capable of closed-loop control, such as a servo valve or a flow control valve.

[0012] A plurality of engagement grooves 25a are formed near the tip end of the outer periphery of each tie bar 25 over a predetermined length in the mold opening / closing direction. Each tie bar 25 is inserted into an insertion hole 29 provided near the four corners of the movable platen 18. Half nuts 30 serving as an engagement mechanism are disposed near the insertion holes 29 on the surface of the movable platen 18 opposite the mold mounting surface. Engagement teeth 31 of the half nuts 30 can be advanced and retreated toward the engagement grooves 25a of the tie bars 25 by a drive mechanism 28 such as a cylinder. When the engagement teeth 31 advance, the half nuts 30 can engage the movable platen 18 with the tie bars 25. The movable platen 18 is also equipped with an ejector mechanism (not shown) and the like.

[0013] Two mold opening and closing mechanisms 19 are arranged on the bed 2 to move the movable platen 18 toward or away from the fixed platen 16. The mold opening and closing mechanisms 19 use a servo motor 27 and a ball screw mechanism 32. A rotary encoder (not shown) of the servo motor 27 measures the distance of the movable platen 18 from the fixed platen 16 (the distance of the movable mold 17 from the fixed mold 15). Note that the distance of the movable platen 18 from the fixed platen 16 may also be measured by a position detection mechanism such as a linear scale other than the rotary encoder.

[0014] The mold clamping unit 13 is equipped with four tie bar movement mechanisms 33, which are separate from the mold clamping cylinders 21 and move the tie bars 25 a certain distance, corresponding to the number of tie bars 25 (however, only two are shown in FIG. 1). The tie bar movement mechanisms 33 are equipped with two hydraulic cylinders 34 per tie bar 25, and the rods of the hydraulic cylinders 34 and the rods 35 protruding from the pistons 24 of the mold clamping cylinders 21 toward the side opposite the mold mounting surface are connected by a connecting plate 36. The hydraulic cylinders 34 are controlled by closed-loop controllable valves 37 provided in the hydraulic device 26. In addition, a position detection mechanism 38 is attached to the fixed platen 16 to detect the movement position of the tie bars 25. The tie bar movement mechanisms 33 may be operated by a servo motor.

[0015] The mold clamping device is not limited to the one shown in FIG. 1 and may be one using a toggle mechanism, etc. Although illustration of a toggle mechanism is omitted, a pressure platen is provided on the back of the movable platen, and each toggle link of the toggle mechanism is provided connecting the movable platen and the pressure platen. A mold clamping mechanism such as a servo motor is provided on the back side of the pressure platen, and is capable of rotating a ball screw journaled on the pressure platen. The ball screw is inserted into a ball screw nut, and the ball screw nut is fixed to a crosshead. A toggle link is rotatably attached to the crosshead. In such a toggle mechanism, the movement amount of the movable platen near the completion of mold closing is small compared to the movement amount of the crosshead, and the movement control of the movable platen by the servo motor can be performed with high precision.

[0016] Next, the molding die 41 attached to the mold clamping unit 13 will be described with reference to FIGS. 2 to 5. The molding die 41 is used for injection compression molding, and a cavity C is formed between the fixed die 15 and the movable die 17. The fixed die 15 is a cavity type, and has a cavity surface 42 formed by a recess and a sliding surface 43 with the movable die 17, which will be described later. The outer periphery of the sliding surface 43 forms a parting surface 44 that faces the movable die 17. The fixed die 15 also has a flow path 45 through which molten resin flows during injection (injection filling), and a gate 46 is formed in the cavity surface 42. The flow path 45 may be a hot runner or a cold runner. The fixed die 15 also has a temperature control flow path 47 inside through which a temperature control medium flows.

[0017] The movable mold 17 is a core mold, and the tip surface of the convex portion forms a cavity surface 48. The side surface of the convex portion forms a sliding surface 49 that faces the sliding surface 43 of the fixed mold 15 with a very small gap between them when the molds are closed. The outer periphery of the sliding surface 49 that faces the fixed mold 15 forms a parting surface 50. However, the parting surface 44 of the fixed mold 15 and the parting surface 50 of the movable mold 17 do not necessarily abut upon completion of molding. The movable mold 17 is also equipped with a temperature control flow path 51 through which a temperature control medium flows and an ejector 52 that ejects the molded product P. Figure 5, which is a view along the arrow AA in Figure 2, shows the cavity surface 48 of the movable mold 17. The injection pressure exerted on the movable mold 17 and the movable platen 18 during injection depends on the area of ​​the cavity surface 48.

[0018] The molding die 41 is also called a spigot die due to its structure. Figure 3 shows the state of the molding die 41 at the start of injection compression molding. Figure 4 shows the state of the molding die 41 at the end of injection compression molding. As can be seen from Figures 3 and 4, when the movable die 17 is moved in the mold closing direction relative to the fixed die 15, the volume of the cavity C is reduced and the molten resin inside is compressed. It is rare for the molding die 41 to be used both as an injection compression molding die and a core-back molding die, but the basic structure is the same even when the molding die is a core-back molding die. That is, in the case of a core-back molding die, injection begins in the state shown in Figure 4, and the molten resin in the cavity foams, expanding the cavity volume and completing the molding in the state shown in Figure 3.

[0019] Next, the injection unit 14 will be described. The injection unit 14 is equipped with a screw and the like (not shown) inside the heating cylinder 54, and a nozzle 22 is attached to the front of the heating cylinder 54. The injection unit 14 is also equipped with a drive mechanism 55 on the rear side, which rotates the screw and moves the heating cylinder 54 back and forth in the axial direction. Furthermore, a material supply mechanism 53 equipped with a hopper and the like is provided on a block or plate (not shown) to which the heating cylinder 54 of the injection unit 14 is attached. The injection unit 14 can be moved back and forth as a whole by a nozzle touch device (not shown), and when it moves forward, the tip of the nozzle 22 touches the fixed mold 15. The structure and number of the injection unit 14 are not particularly limited.

[0020] <Control device and Detection Device Peripheral devices such as Next, the control device 61 of this embodiment will be described mainly with reference to the block diagram of Figure 6. The injection molding machine 11 is equipped with the control device 61. The control device 61 controls the injection molding machine 11, and is equipped with a calculation unit, a memory unit, an input unit, an output unit, etc., which are not shown. The control device 61 is connected to the hydraulic device 26 of the injection molding machine 11, a servo amplifier 62 of the servo motor 27 of the mold opening and closing mechanism 19, a servo amplifier 63 of the injection servo motor and metering servo motor, not shown, of the injection unit 14, and an input device 64. The control device 61 is also connected to each sensor of the injection molding machine 11. The control device 61 is also connected to the control device of the temperature adjustment device 65, Detection Device It is also connected to peripheral devices such as a control device for a material supply device (not shown) connected to the material supply mechanism 53, a molded product removal device 67, and the control devices thereof.

[0021] Detection Device The device 66 is provided with a camera 68 such as a CCD camera, which can read information about the molded product P. Here, the position where the camera 68 of the molded product removal device 67 reads the molded product P may be a position where the molded product P is held by the molded product removal device 67, or may be another position such as on a conveyor. Detection Device66 may be a weight measuring instrument for measuring the weight of the molded product P, a color measuring instrument for measuring the surface condition of the molded product, a tension measuring instrument for measuring the strength of the molded product, a load measuring instrument, etc. In addition, a position sensor for detecting the position of the screw at the completion of dwelling pressure, or a position sensor for detecting the position of the movable platen 18 or the movable mold 17 at the end of cooling in injection compression molding, etc. are also complementary. Detection Device Used as 66.

[0022] <Machine learning device> In addition, in the injection molding system 1 of this embodiment, a control device 71 equipped with a machine learning device 70 that constitutes the molding condition generation support program is provided separately from the control device 61 of the injection molding machine 11. The control device 71 may be a central control device for a factory connected to multiple injection molding machines 11, or it may be provided in another structure outside the factory within the same company, or in the injection molding machine manufacturer or management company. In these cases, the injection molding machine 11 and the control device 71 may be connected either wired or wirelessly. The machine learning device 70, which is the molding condition generation support program, may be provided in the control device 61 of the injection molding machine 11.

[0023] The control device 71 that controls the multiple injection molding machines 11 is provided with an input unit 72. The input unit 72 is connected to the control device 61 of the injection molding machine 11 and Detection Device 66, etc., and the injection molding machine 11 and Detection Device 66 is input. The control device 71 also has a machine learning device 70. The machine learning device 70 has a learning model unit 73. The learning model unit 73 includes an estimation unit 74, a learning model generation / correction unit 75, and a learning model storage unit 76. The estimation unit 74 generates molding conditions for injection compression molding using a neural network. The learning model generation / correction unit 75 also corrects the learning model by backpropagation or the like when the molded product produced under the generated molding conditions is not optimal and the molding conditions are corrected. The learning model storage unit 76 stores the generated or corrected molding conditions.

[0024] The learning model unit 73 of the machine learning device 70 is also connected to a molding condition storage unit 77, an injection molding machine information storage unit 78, a molding die information storage unit 79, and a resin material information storage unit 80. The molding condition storage unit 77 stores basic pattern molding conditions used for injection compression molding or core-back molding when the machine is shipped or when the control device is installed. It also stores newly generated molding conditions for each molding die 41. The injection molding machine information storage unit 78 stores information necessary to generate molding conditions for all injection molding machines 11 connected to the control device 71. Specifically, this information includes information (specification information) about the clamping mechanism of the clamping device 13, information (specification information) about the injection mechanism including the injection servomotor of the injection device 14 and the drive unit of the metering mechanism including the metering servomotor, information (specification information) about the screw of the injection device 14, and information (specification information) about the heater and cylinder inner diameter of the heating cylinder 54. The molding die information storage unit 79 stores information about each molding die 41 installed in the injection molding machine 11. Furthermore, the resin material information storage unit 80 stores information about basic resin materials and information about resin materials that have been used in the injection molding machine 11 in the past.

[0025] The machine learning device 70 is also provided with a molding condition confirmation / correction unit 81, which is connected to the learning model unit 73 and the molding condition storage unit 77. When an operator presses a defect type button 124 based on the molding results, the molding condition confirmation / correction unit 81 of the machine learning device 70 corrects the molding conditions. Alternatively, the operator may directly correct at least one of the molding condition items generated by the estimation unit 74 of the learning model unit 73 by manual input or the like. The machine learning device 70 is also connected to an output unit 82. The output unit 82 is connected to the control device 61 of the injection molding machine 11.

[0026] <Input device and input screen> Next, the input device 64 for setting the injection molding machine 11 and its input screen 91 will be described with reference to Figures 7 and 8. The input device 64, which is provided on the side of the fixed platen 16 of the injection molding machine 11, is used by the operator to set and input molding conditions and displays the operating status of the injection molding machine 11, and is composed of a touch panel or the like. The input device 64 allows the operator to input setting values ​​for molding conditions related to the injection molding machine 11 by switching between pages, and can also display actual measured values ​​during molding by the injection molding machine 11 and production information. It is also possible for the injection molding system 1 to provide a handheld input device that the operator can hold and use around the injection molding machine 11, separate from the input device 64 fixed to the injection molding machine 11, and such an input device is also included in the input device of the present invention.

[0027] The input device 64 has a general screen (not shown) for setting and inputting the various molding conditions described above, as well as an input screen 91 for inputting information about the molding die 41 and information about the resin material to be supplied to the injection unit 14, as shown in Fig. 7. The input screen 91 displays information about the molding die 41, including the molded product P, including an input section 92 for inputting the cavity projected area (cavity surface 48 in Fig. 5), an input section 93 for inputting the cavity volume at the end of molding, an input section 94 for inputting the longest cavity flow length (the flow length from the gate to the end farthest from the gate), an input section 95 for inputting the molded product weight, an input section 96 for inputting the molded product volume, an input section 97 for inputting the type of molded product, an input section 98 for inputting the number of molded products (number of parts), and an input section 99 for inputting whether or not there will be any merger within the cavity at the time of injection (this indicates whether the flows of resin injected into the cavity merge along the way, and is necessary for preventing welds).

[0028] 7 for inputting the average thickness A of the molded product, an input section 101 for inputting the thickness of the thick-walled portion of the molded product, an input section 102 for selecting and inputting the shape of the molded product, and an input section 103 for inputting the compression stroke B during injection compression molding. Also, with regard to the runner portion through which the injected molten resin is sent to the cavity, there is an input section 104 for inputting the length of the runner R, an input section 105 for inputting the cross-sectional area (narrowest part) of the runner R, an input section 106 for inputting the type of runner R (hot runner or cold runner), an input section 107 for inputting the number of gates G, an input section 108 for inputting the position of the gate G (center, end, or midway between the center and end), and an input section 109 for inputting the cross-sectional area of ​​the gate G. Furthermore, the input screen 91 is provided with an input section 110 for inputting the mold weight, an input section 111 for inputting the mold type (such as a spigot mold for injection compression molding or a flat mold for injection compression molding as shown in FIG. 11) or a heating / cooling mold, and an input section 112 for inputting the estimated cooling time.

[0029] In this embodiment, the input screen 91 includes an input section 113 for selecting and inputting a resin type such as polypropylene, polycarbonate, acrylic (PMMA), etc., for inputting information about the resin material to be supplied to the injection device, an input section 114 for selecting and inputting the grade of the resin material (if the same resin material needs to be further subdivided and input), an input section 115 for inputting composite materials such as glass fiber or carbon fiber, an input section 116 for inputting the ratio (weight %) of the composite material, etc. Furthermore, if the resin manufacturer's recommended injection or mold temperature is included in the resin material grade section, it may be possible to input this information.

[0030] The information about the molding die 41 that is input from the input screen 91 must include either the cavity projected area or the molded product area, either the cavity volume or the molded product weight or the molded product volume, and the number of molded products if there are two or more molded products. The type of resin is also a required input item.

[0031] Note that in FIG. 7, the input section for information regarding the molding die 41 including the molded product P and the input section for information regarding the resin material supplied to the injection unit 14 are merely examples, and the number of items may be increased or decreased. Furthermore, molding conditions can be generated even if all of the input fields are left blank. Also, in the input screen 91 of FIG. 7, information regarding the molding die including the molded product and information regarding the resin material supplied to the injection unit are input from the same input screen 91, but they may also be input from separate input screens. Furthermore, the information regarding the molding die 41 and the resin material may be read via wired or wireless communication means, QR code (registered trademark), barcode, or the like. In this case, the items regarding the molding die 41 including the molded product and the resin material may be the same as the information input from the input screen 91, or the number of items may be increased or decreased.

[0032] In this embodiment, information about the injection molding machine 11 is sent from the injection molding machine 11 to the injection molding machine information storage unit 78 of the control device 71 and stored therein. However, if the injection unit 14 or other mechanisms used by the injection molding machine 11 are changed depending on the molding die 41, information about the injection molding machine 11 may be input from the input screen 91.

[0033] Although not shown, a separate screen may be provided for inputting information about core-back molding, in which the movable mold retracts during foam molding. In this case, the input section 95 for the compression stroke B in FIG. 7 becomes the input section for the core-back amount (foam expansion stroke). An input section for inputting whether the foam is chemical or physical is also provided. In the case of chemical foaming, the input section 107 for the composite material becomes the input section for the type of foaming agent and the foaming agent ratio (weight %). In the case of physical foaming, an input section is provided for inputting the position of the gas supply section, the type of gas, the gas pressure, etc., when supplying foaming gas to the heating cylinder of the injection unit or the mold cavity.

[0034] The input device also has a molded product status input screen 121 for inputting information about the molded product P molded by injection compression molding. Fig. 8 shows an example of the molded product status input screen 121. If the molded product P is a good product, the operator can input that it is a good product by pressing a good product button 122 and then pressing a confirm button 123. If the molded product P is defective, the operator can input that it is a defect and the type of defect by pressing a defect type button 124 that indicates the type of defect for each molded product P and then pressing the confirm button 123. The defect type buttons 124 on the molded product status input screen 121 include input buttons for short shot (underweight), overpack (overweight), weight variation, burrs, sink marks, deformation (including warpage), burns, flow marks, voids, silver streaks, cracks, welds, other surface defects, contamination, gate defects, ejector marks, other surface defects, etc.

[0035] Therefore, if the operator determines that the molded product P is a good product, he or she can input information that the molded product P is a good product by pressing the good product button 122 and the confirm button 123 in that order. If the operator determines that the molded product P has a short shot, he or she can input information that the molded product P has a short shot by pressing the short shot button, which is a defect type button 124, and the confirm button 123 in that order. If the molded product P has two or more types of defects, he or she can press multiple defect type buttons 124 and then the confirm button 123. Furthermore, regarding the degree of the defect, by pressing a defect type button (the same button) such as a short shot multiple times, the color of the defect type button 124 will change, and then the confirm button 123 can be pressed to input the degree of the defect.

[0036] The degree of defect may be input using separately provided numeric buttons. Furthermore, larger buttons may be used for defect types with high defect frequency, such as short shot (underweight), overpack (overweight), weight variation, burrs, sink marks, and deformation (including warpage). Conversely, for defect types with low defect frequency, an "Other" button may be pressed to move to a separate input screen for defect types with low defect frequency. Furthermore, the defect type buttons 124 may be displayed on the input screen 121 in descending order of frequency of pressing. Then, by an operator viewing the molded product P and pressing one of the defect type buttons 124 and the confirm button 123 in sequence on the input screen 121 for the molded product status, information on the defect type of the molded product P can be sent to the molding condition confirmation / correction unit 81 of the machine learning device 70.

[0037] <Molding condition generation support program for injection molding systems> In this embodiment, a support program for generating molding conditions for an injection molding system is stored in an external control device 71, which is remote from the injection molding machine 11. More specifically, the control device 71 includes a machine learning device 70, and a learning model (generation support program) for injection compression molding or core-back molding is stored in a learning model unit 73 of the machine learning device 70. As shown in FIG. 9 , the learning model of this embodiment uses a neural network 131 having one or more intermediate layers 133 (hidden layers). When at least information about the injection molding machine 11, information about the molding die 41, and information about the resin material supplied to the injection device 14 is input from an input layer 132, the neural network 131 of the learning model adds a bias b as necessary in the intermediate layer 133 using a function equation to which a weight w is assigned, and obtains molding conditions as output y in an output layer 134. Note that FIG. 9 shows the intermediate layer 133 only schematically; in reality, more complex function equations, weights w, and bias b are used. 9 shows only one intermediate layer 133, deep learning may be performed by providing two or more intermediate layers 133. Furthermore, the neural network 131 may be one that uses a convolutional neural network as at least a part thereof.

[0038] The learning model may be stored in the learning model unit 73 of the initial machine learning device 70 by downloading it via the Internet or installing it via a mobile device. In this embodiment, the initial learning model for injection compression molding was created by an injection molding machine manufacturer. The molding condition storage unit 77 stores a large number of molding conditions that have produced conforming products, linked to combinations of past data on specific injection molding machines, specific molding molds, and specific resin materials. The injection molding machine information storage unit 78 pre-stores information on the injection molding machine 11, the molding mold information storage unit 79 pre-stores information on the molding mold 41, and the resin material information storage unit 80 pre-stores information on the resin material. The information on the injection molding machine 11 and the molding mold 41 may be stored in the control device 61 of the injection molding machine 11 and transmitted via communication when the control device 71 of the central processing unit generates molding conditions using the learning model.

[0039] <Generation or modification of molding conditions using a learning model for injection compression molding> The generation of molding conditions using the learning model of the machine learning device 70 of the injection molding system 1 will be described using the flowchart in Figure 10. The flowchart in Figure 10 does not only show the control of the control devices 61, 71, but also includes the work performed by the operator. Information about the injection molding machine 11 is initially stored in the injection molding machine information storage unit 78 of the control device 71. Then, first, information about the molding die 41 to be used for injection compression molding and information about the resin material are input from the input device 64 connected to the control device 61 or an input device (not shown) connected to the control device 71 (s1).

[0040] Next, it is determined whether molding conditions related to injection compression molding have been stored in the molding condition memory unit 77 from the beginning (s2). If the molding conditions are stored (s2=Y), the estimation unit 74 of the learning model unit 73 inputs information about the injection molding machine 11, information about the molding die 41, and information about the resin material supplied to the injection device into the stored molding conditions from the input layer 132 of the neural network 131 stored in the learning model memory unit 76 of the learning model unit 73 of the machine learning device 70, and outputs output values ​​y1 and y2 to the output layer 134 via the intermediate layer 133 using function equations to which weights w1 to w12 and biases b1 and b2 have been assigned, thereby generating molding conditions (s3).

[0041] Specifically, the molding condition storage unit 77 stores molding conditions for performing injection compression molding using the injection molding machine 11, linked to information about the injection molding machine 11, information about the molding die 41, and information about the resin material. Here, the molding conditions refer to various setting values ​​for performing injection compression molding using the injection molding machine 11 to obtain a good molded product. As described above, if past molding conditions with similar information about the injection molding machine 11, information about the molding die 41, and information about the resin material have been saved, these past molding conditions are also input from the input layer. Regarding similar past molding conditions, multiple similar molding conditions may be extracted according to prioritized items, or a machine learning device may extract similar molding conditions using techniques such as clustering or supervised learning. Furthermore, when similar molding conditions from the past are not used, molding conditions for injection compression molding are generated using information on the injection molding machine 11 stored in the injection molding machine information storage unit 78, information on the molding mold 41 stored in the molding mold information storage unit 79 or information on the molding mold 41 entered from the input device 64, and information on the resin material stored in the resin material information storage unit 80 or information on the resin material entered from the input screen 91 of the input device 64.

[0042] At this stage, it is not easy to determine from the outside what function formulas and weightings the learning model used in the estimation unit 74 of the learning model unit 73 of the machine learning device 70 uses to perform calculations from the input layer 132 to the intermediate layer 133 and from the intermediate layer 133 to the output layer 134. However, the following is a rough guideline. First, the injection amount is roughly determined from the molded product weight or volume (cavity volume), number of molded products, and the length and cross-sectional area of ​​the runner (if the flow path 45 is a cold runner, the runner). The injection stroke (from the metering end position (injection start position) to the hold pressure end position, or from the injection start position to the hold pressure switch position) is then determined from the screw diameter (or heating cylinder inner diameter), which is information from the injection molding machine 11. Next, the injection speed and injection pressure are determined from the molded product shape (cavity shape), runner shape, gate shape, and resin material used. The temperature of the heating cylinder 54 varies depending on the resin material used, and as a result, the rheological properties of the molten resin also vary, as well as the injection speed at which burning occurs, which has a significant impact on the injection speed and injection pressure. Furthermore, if the molded product shape (cavity shape) is thin or the resin material has poor fluidity when molten, these may be the reasons for adopting injection compression molding, and these will affect the injection speed and injection pressure.

[0043] Once the resin material, injection speed, and injection pressure are determined, the clamping unit's holding force during injection, the position of the movable platen (movable mold), and the pressure (force) or compression speed (moving speed of the movable mold) of the compression molding performed after injection are determined accordingly. If the molded product shape (cavity shape) is thin or the resin material has poor fluidity when molten, the position of the movable platen 18 (or movable mold 17) relative to the fixed platen 16 (or fixed mold 15) at the start of compression is set to a position thicker than the actual thickness of the molded product P and retracted to a predetermined position. In other words, a molding process called an injection press is performed in which the cavity volume at the start of molding is larger than the cavity volume at the end of molding. As described above, in the case of injection compression molding, there is a causal relationship between the molding conditions on the clamping unit 13 and the molding conditions on the injection unit 14. Changing one setting often necessitates changing the other setting as well. Therefore, generating molding conditions by an operator requires skill, and even an experienced operator will need time. To solve this problem, it is useful to use a machine learning device 70 and its learning model that can memorize and reflect the quality of past molding conditions. Because the mutual causal relationships in the learning model of injection compression molding are complex, a learning model that adjusts the interrelationships, such as mathematical programming, may be incorporated.

[0044] Furthermore, since the molding conditions on the mold clamping unit 13 side and the molding conditions on the injection unit 14 side are closely related, the learning model may set or correct the molding conditions on the injection unit 14 side based on the molding conditions on the mold clamping unit 13 side input or selected by the operator. Alternatively, the learning model may set or correct the molding conditions on the mold clamping unit 13 side based on the molding conditions on the injection unit 14 side input or selected by the operator. As an example, in the case of optical molded products with thick walls, such as lens molding, the injection speed or injection pressure is set relatively low to prevent deterioration of the resin material, such as burning. In response, the mold clamping unit 13 compresses the molten resin in the cavity C at a speed higher than a predetermined value to spread the molten resin within the cavity C. The estimated cooling time is set in relation to the temperature of the molding mold (temperature control medium temperature). The corresponding temperature of the molding mold (temperature control medium temperature) is determined to some extent by the type of resin material, but is also affected by the mold shape and cavity shape. The cooling temperature may be initially input in the form of an estimated cooling temperature, but the cooling time may also be generated (estimated) as part of the molding conditions based on the mold shape, cavity shape, and type of resin material.

[0045] Furthermore, in the present invention, initial molding conditions can be generated even if no molding conditions are saved. However, it can be said that it is rare for injection compression molding or other molding to produce a good product under the initial molding conditions. In other words, if molding conditions are not saved, the learning model generates molding conditions in the estimation unit 74 of the learning model unit 73 using only the injection molding machine information saved in the injection molding machine information storage unit 78, the input information about the molding mold, and the information about the resin material (s4). For example, when at least one piece of information about the molding mold, such as the cavity projected area, cavity volume (molded product volume), or molded product weight, and information about the resin material are entered on the input screen 91, the initial molding conditions are generated (estimated) using the learning model.

[0046] <Modification of learning model for injection compression molding> Next, we will explain the process of operating the injection molding machine 11 to actually perform injection compression molding to obtain information about the molded product P and then modifying the learning model for injection compression molding or core-back molding. Continuing with the flowchart in Figure 10, whether the molding conditions are saved and generated in the estimation unit 74 of the learning model unit 73 (s3) or not saved and generated (s4), the injection molding machine 11 is then operated manually or semi-automatically (other than continuous automatic molding) to mold the molded product P (s5). In injection compression molding, after molten resin is injected from the injection unit 14 into the cavity C, the movable mold 17 is moved relative to the fixed mold 15 to compress the molten resin within the cavity C. At this time, molding conditions with a smaller injection amount than the injection amount set under the previously set molding conditions are automatically generated, and short-shot molding is performed under these molding conditions with a smaller injection amount. The operator then ejects the molded product P with the ejector 52, removes it from the movable mold 17, etc., and visually checks it himself. If it is a short shot, he presses the defect type button 124 for "short shot (insufficient weight)" on the input screen, and then presses the confirm button 123, which changes the molding conditions and increases the injection amount. In this case, the injection amount is not increased by a uniform fixed amount, but rather by a predetermined ratio relative to the previous injection amount, molded product weight, etc.

[0047] Once the short shot is resolved, the operator inspects the removed molded product P and determines whether it is a good product or a defective product (s6). It is unlikely that a good product can be molded from the start, and if the operator inspects the removed molded product P and determines that it has a "sink mark," "burn," "flow mark," "silver streak," or other defect (s6=N), he or she presses the corresponding defect type button 124 on the input screen 91 of the input device 64 (s7), and then presses the confirm button 123 to improve the molding conditions. At this time, the corresponding defect type button 124 may be pressed multiple times depending on the severity of the defect.

[0048] The learning model storage unit 76 stores information on which molding conditions to modify and by how much when one of the defect type buttons 124 is pressed once, based on information about the injection molding machine, the molding mold, and the resin material. Specifically, when the "Sink" button is pressed, the molding condition checking / modifying unit 81 modifies the molding conditions for both the mold clamping unit 13 and the injection unit 14 (s8), for example, by increasing the compression amount on the mold clamping unit 13 side and increasing the dwell pressure during dwelling on the injection unit 14 side. When the "Burn" button is pressed, the molding conditions are modified, for example, by reducing the injection speed on the injection unit 14 side. As described above, the modification of the molding conditions may be performed on at least one of the mold clamping unit 13 side and the injection unit 14 side.

[0049] The operator then manually or semi-automatically molds the molded product P again. At this time, it is desirable to display the molding conditions estimated by the learning model on the display device, have the operator check them, and, if he or she determines that the molding conditions are satisfactory, press the molding start button for manual or semi-automatic molding to begin molding. Furthermore, if the operator determines that the molding conditions are not satisfactory after checking them, the operator may manually correct the molding conditions. However, once the learning model of the machine learning device 70 has repeatedly learned and is able to consistently generate satisfactory molding conditions (including minor corrections), the molding conditions generated by the learning model may be left on the display device and the next injection molding may begin. This process repeats steps (s7) and (s8) until the operator confirms that the molded product P is a good product.

[0050] If the molding conditions are improved by pressing the defect type button 124 and good products can be obtained (s6=Y), the operator presses the good product button 122 (s9) and then presses the confirm button 123. This confirms that the molding conditions were correct in the molding condition confirmation / correction unit 81 of the machine learning device 70, and the molding conditions at that time are saved in the learning model storage unit 76 without correcting the learning model in the learning model generation / correction unit. Then, when the start button to start automatic molding (continuous molding) is pressed, continuous molding begins (s10).

[0051] In the machine learning device 70, the learning model generation / correction unit 75 corrects the learning model (s11) assuming that the countermeasure is a favorable correction of molding conditions. Note that the start of continuous operation (s10) and the correction of the learning model (s11) may occur either first or simultaneously. In this embodiment, the correction of the learning model is performed using backpropagation (also called backpropagation). Specifically, the weights w and biases b of the neural network 131 shown in FIG. 9 are improved from the output layer 134 to the intermediate layer 133 and input layer 132, moving from the output side to the input side. Specifically, the output solution estimated by the learning model is verified, and the weights w and biases b of the neural network are adjusted to reduce the error from the correct answer. As an example, the value of the weight w of the neural network is changed by differentiating the error function using gradient descent. In other words, the error can be reduced by increasing or decreasing the weight w relative to the slope of the error function.

[0052] The learning model that generated the molding conditions when the molded product P was a non-defective product is then treated in the learning model generation / correction unit 75 of the learning model unit 73 as being correct, and the weight w of the function formula is increased. The corrected neural network 131 of the learning model is then stored in the learning model storage unit 76. In this way, the learning model of the molding conditions when the information on the molding die and the information on the resin material are stored, and Even when the information is about similar molding dies and resin materials, the ratio of good molding conditions being estimated is increased.

[0053] At the same time, the correction range (or correction ratio) of each molding condition to be corrected by each press of the defect type button 124 is also corrected by the learning model generation / correction unit 75 of the learning model unit 73 and stored in the learning model storage unit 76. Naturally, this correction range is not uniform, depending on the information about the injection molding machine, the molding mold, and the resin material. Each press of the defect type button 124 optimizes the correction range (or correction ratio) of each molding condition, allowing the operator to appropriately correct the molding conditions without having to enter values ​​on the input screen. For example, pressing the defect type button 124 once can result in a minor correction, pressing it three times can result in a standard correction, and pressing it five times can result in a major correction. The degree of correction per press is adjusted by re-learning the learning model. As mentioned above, if the correction range is large, the operator must confirm the corrected molding condition values ​​before starting the next molding. The molding conditions can also be corrected after the machine enters fully automatic operation.

[0054] <Method of correcting learning model according to another embodiment> The learning model for injection compression molding may be modified by reinforcement learning. When reinforcement learning is performed, the defect type button 124 is pressed for a defect, and the molding conditions corresponding to the defect type button 124 are modified. If the molded product P is a good product in the next or subsequent moldings, the good product button 122 and the confirm button 123 are pressed, and a positive reward is given to the modified molding conditions (or the numerical modification range or modification ratio of the modified item), and a negative reward is given to the molding conditions before modification (or the modified item). Furthermore, if the defect type button 124 is pressed for a defect in the molded product P but the molded product P is not a good product in the next or subsequent moldings, the number of times the defect type button 124 is pressed is increased. If the molded product P is still not a good product, a negative reward is given to the modified molding conditions (or the numerical modification range or modification ratio of the modified item). Furthermore, if a good product cannot be molded using only the learning model of the machine learning device 70, the operator directly inputs and modifies the molding conditions to those that will allow a good product to be molded. Even in the case where the operator directly inputs the settings, the range of settings to be input is smaller than when the operator inputs all molding conditions from the beginning, and the occurrence of basic major errors is reduced, which often contributes to improving molding conditions.

[0055] <Core-back molding> Next, we will describe the generation and modification of molding conditions using a learning model for core-back molding (foam molding). Core-back molding is a molding method in which a resin material containing a foaming material or foaming gas is injected from an injection device into a cavity formed between the fixed and movable molds of a molding die when the clamping device 13 is clamped. The foaming material or foaming gas contained in the resin material then expands within the cavity to produce a molded product with internal bubbles. In foam molding, it is important to appropriately retract the movable mold in response to the expansion of the molded product. Therefore, injection compression molding and core-back molding have something in common in that molding is performed while the volume of the cavity of the molding die 41 is changed.

[0056] During core-back molding, if the retraction speed of the movable mold is too fast, it can result in sink marks or skin defects on the surface of the molded product, or in a thicker-than-expected molded product. Conversely, if the retraction speed of the movable mold is too slow, it can result in a thinner-than-expected molded product due to insufficient foam expansion. Therefore, the operator inspects the foam-molded molded product and, if sink marks or other defects are detected, corrects the molding conditions by pressing the "Sink Mark" button or the "Over Thickness" button, which is specifically for core-back molding. Specifically, pressing the "Sink Mark" button or the "Over Thickness" button, which is specifically for core-back molding, modifies the molding conditions by reducing the retraction speed of the movable mold by a specified amount or by shifting the retraction stop position of the movable mold forward by a specified amount (toward a narrower cavity C). Alternatively, the operator can directly set molding conditions such as the retraction speed of the movable mold, the cavity pressure during retraction, and the retraction time from a separate input screen. If the molded product is too thin, the operator can also modify the molding conditions by pressing the "Insufficient Foam Expansion" button, which is specifically for core-back molding. Specifically, when the foam expansion deficiency button, which is specifically for core-back molding, is pressed, the molding conditions are corrected, such as increasing the retraction speed of the movable mold by a predetermined speed or changing the retraction stop position of the movable mold a predetermined amount backward (in the direction that widens the cavity C). Alternatively, the numerical values ​​of the molding conditions, such as the retraction speed of the movable mold, the pressure inside the cavity during retraction, and the retraction time, can be directly reset from another screen.

[0057] If the molding conditions are corrected by pressing the sink mark button, the core-back molding-specific overthickness button, or the insufficient foam expansion button, and a non-defective product is molded, the learning model uses backpropagation to improve the weights w and biases b from the output layer 134 to the middle layer 133 and input layer 132. Alternatively, a positive reward is awarded for the molding conditions or the extent of the molding condition corrections made through reinforcement learning. This increases the probability that the molding condition generation unit will generate molding conditions that will produce a non-defective product the first time, even in cases where similar information about the injection molding machine, mold, and resin material is used. When generating and correcting molding conditions for core-back molding, as with the learning model for injection-compression molding, the causal relationships between the clamping unit 13 and the injection unit 14 are complex. Therefore, incorporating a learning model that can memorize and correct past molding conditions is more useful than manual adjustments by an operator. <When not using the defect type button>

[0058] The method for obtaining information about molded products in the above-mentioned injection compression molding or core-back molding and correcting the learning model for the injection compression molding or core-back molding involves the operator directly removing the molded product from the mold during manual or semi-automatic molding, and if the molded product is defective, entering the type by pressing the defect type button 124 on the input screen 91 of the input device 64 of the injection molding machine 11. This method is easy to use even for operators who have been molding for a long time, and does not require investment in equipment such as a separate inspection device. It is also possible to correct molding conditions without using a central control device 71 by installing a machine learning device 70 in the control device 61 of the injection molding machine 11.

[0059] However, in the present invention, it is not essential to modify the molding conditions from the defect type button 124 on the input screen 121. It is also possible to have the defect type button 124 not provided on the input screen 121, and to not use an inspection device, and for the operator who sees a defective product to simply modify at least one element of the individual molding conditions by manually inputting it on the input screen.

[0060] Information about molded products in injection compression molding and core-back molding may be detected by a detection device such as a CCD camera, photoelectric tube, weight scale, or colorimeter. When a detection device is used, if the molded product is good, the machine learning device is first made to learn in a supervised manner that it is a good product. If the molded product is defective, the shape of the defect is linked to the type of defect, and the machine learning device is made to learn in a supervised manner.

[0061] If the detection device inspects the molded product and determines that a specific type of defect exists, the learning model is modified by changing the weighting through backpropagation or by providing a reward through reinforcement learning, just as when the operator presses the defect type button 124. The molding conditions generated by the learning model are then modified using the information initially set for the injection molding machine 11, the mold 41, and the resin material supplied to the injection unit 14. It is preferable to retain some of the operator's input for minor adjustments to the molding conditions. Therefore, an inspection device may be used to monitor molded products after the start of fully automatic operation. When the defect rate of molded products increases slightly, a message suggesting a corrective measure is displayed on the display screen of the injection molding machine 11 or on the display screen of the central control device 71 that oversees multiple injection molding machines 11. If the operator sees the message and believes the corrective measure is correct, they can adjust the molding conditions by making minor adjustments to the numerical values ​​via the input device 64 of the injection molding machine 11 or the input device that oversees the multiple injection molding machines 11.

[0062] Although the present invention will not be listed one by one, it goes without saying that the present invention is not limited to the above-described embodiment, and can be applied to combinations of the respective embodiments and to modifications made by those skilled in the art based on the spirit of the present invention. For example, the above-described embodiment can also be applied to general injection molding other than injection compression molding and core-back molding. In particular, the method in which an operator who has judged the condition of a molded product selects and presses a defect type button on an input device to correct molding conditions and eliminate defects in molded products molded using the corrected molding conditions can be applied to any molding. [Explanation of symbols]

[0063] 1. Injection molding system 11 Injection molding machine 13 Mold clamping device 14 Injection device 15 Fixed mold 17 Movable mold 61,71 Control device 64 Input Devices 70 Machine Learning Device 73 Learning Model Section 74 Estimation part 75 Learning model generation and correction section 76 Learning model memory unit 77 Molding condition memory section 81 Molding condition confirmation / correction section 91,121 input screens 131 Neural Networks 132 Input Layer 133 Middle Class 134 Output Layer C cavity P Molded product b bias w weight y output value

Claims

1. A method for generating molding conditions for an injection molding system equipped with an injection molding machine that moves a movable mold relative to a fixed mold during injection compression molding or core-back molding, comprising: a molding die in which a cavity is formed between a fixed die and a movable die; an injection molding machine having a mold clamping device to which the molding die is attached and an injection device that injects into the cavity; The input device of the injection molding machine requires input of information about the injection molding machine, information about either the cavity projected area or the molded product area from among the information about the molding die, information about either the cavity volume, the molded product weight, or the molded product volume, information about the number of molded pieces, and information about the type of resin material to be supplied to the injection device, but it is possible to generate molding conditions without inputting all of the items, A method for generating molding conditions for an injection molding system, in which a learning model for injection compression molding or core-back molding generates molding conditions for injection compression molding or core-back molding from information input from the input device.

2. Using the learning model, injection compression molding or core-back molding is performed to form a molded product; 2. A method for generating molding conditions for an injection molding system according to claim 1, wherein information about the molded product is obtained by reading the molded product with a detection device or by an operator inputting the state of the molded product, and the learning model for the injection compression molding or core-back molding is corrected.

3. In an injection molding system having an injection molding machine that moves a movable mold relative to a fixed mold during injection compression molding or core-back molding, a molding die in which a cavity is formed between a fixed die and a movable die; an injection molding machine having a mold clamping device to which the molding die is attached and an injection device that injects into the cavity; a storage device that stores molding conditions; a learning device having a learning model that generates molding conditions for injection compression molding or core-back molding from at least information about the injection molding machine, information about the molding die, and information about the resin material supplied to the injection device; an input device that allows an operator to input the state of a molded product obtained by injection compression molding or core-back molding; The input device further includes a non-defective button and a defective type button for indicating the type of defective product, The learning model is corrected by pressing the defect type button of the input device at least during manual molding or semi-automatic molding. Injection molding system.

4. In an injection molding system having an injection molding machine that moves a movable mold relative to a fixed mold during injection compression molding or core-back molding, a molding die in which a cavity is formed between a fixed die and a movable die; an injection molding machine having a mold clamping device to which the molding die is attached and an injection device that injects into the cavity; a storage device that stores molding conditions; a learning device having a learning model that generates molding conditions for injection compression molding or core-back molding from at least information about the injection molding machine, information about the molding die, and information about the resin material supplied to the injection device; an input device that allows an operator to input the state of a molded product obtained by injection compression molding or core-back molding; a detection device that detects the state of a molded product molded by injection compression molding or core-back molding using the learning model related to injection compression molding or core-back molding, During fully automatic molding, the learning model and molding conditions are corrected based on the detection results of the molded product state by the detection device, or a message suggesting a solution is displayed. Injection molding system.

5. In an injection molding system having an injection molding machine that moves a movable mold relative to a fixed mold during injection compression molding or core-back molding, a molding die in which a cavity is formed between a fixed die and a movable die; an injection molding machine having a mold clamping device to which the molding die is attached and an injection device that injects into the cavity; a storage device that stores molding conditions; a learning device having a learning model that generates molding conditions for core-back molding from at least information about the injection molding machine, information about the molding die, and information about the resin material supplied to the injection device; and an input device that allows an operator to input the state of the core-back molded product, The input device further includes an input section for inputting at least the amount of core back for inputting the foam expansion stroke and a button for inputting the thickness of the molded product. At least during manual molding or semi-automatic molding, when the button related to the plate thickness over is pressed, the molding conditions or the learning model are corrected. Injection molding system.

6. 6. A molding condition generation support program for an injection molding system, which is installed in the injection molding system according to at least one of claims 3 to 5.

Images