Information processing system, information processing method, and program

The information processing system uses pressure time series data and machine learning to enhance defect detection in molded products by calculating pressure increase rates, effectively identifying issues like silver streaks and improving product quality assessment.

JP2024163639AActive Publication Date: 2024-11-22MAZIN INC

Patent Information

Application Number
JP2023079422
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-12
Publication Date
2024-11-22
Estimated Expiration
2043-05-12

AI Technical Summary

Technical Problem

Conventional methods for detecting defects in injection-molded products, particularly poor appearance, are inadequate as they rely solely on peak value differences in pressure waveforms, failing to capture other types of defects and issues like silver streaks.

Method used

An information processing system that utilizes pressure time series data from a mold-equipped pressure sensor to calculate the pressure increase rate during a specified period, employing machine learning models to determine the quality of the molded product's appearance by analyzing features such as the center of gravity of pressure increase rates.

Benefits of technology

Enhances the detection of defects in molded product appearance by accurately identifying issues like silver streaks, improving the overall quality assessment of injection-molded parts.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024163639000001_ABST
    Figure 2024163639000001_ABST
Patent Text Reader

Abstract

To assist in detecting a visual defect in a molded product that is subject to pass / fail judgment.SOLUTION: An information processing system that determines a quality or non-quality of an appearance of a molded product that is molded by injecting resin into a mold equipped with a pressure sensor includes: an acquisition part that acquires pressure time series data detected by the pressure sensor during injection molding of the molded product to be judged as pass / fail; a calculation part that calculates a pressure increase rate at least at one time using data from the acquired pressure time series data during a target period from a pressure rise time to a time based on a V-P switching time; and an output part that outputs information indicating whether the appearance of the molded product to be determined is good or bad or information indicating a presence or absence of a defect based on a feature amount based on the calculated pressure increase rate and / or performs processing to reject the molded product. The V-P switching time is a timing for switching from a velocity control period to a pressure control period.SELECTED DRAWING: Figure 6
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to an information processing system, an information processing method, and a program. [Background technology]

[0002] Conventionally, molded products are produced by injecting resin into a metal mold (see, for example, Patent Document 1). Even if the parameters (e.g., injection pressure) of the molding machine that injects resin into the metal mold for molding are monitored, defective products may still be produced due to factors such as temperature, even if the parameters of the molding machine are the same. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2004-209814 A Summary of the Invention [Problem to be solved by the invention]

[0004] In response to this, it is conceivable to provide a pressure sensor in the mold and judge quality based on the difference between a reference pressure waveform when a good product is produced and the acquired pressure waveform. The pressure waveform measured by the pressure sensor represents the state of the resin in the mold, so that quality can be judged more accurately. An example of the difference between the reference pressure waveform and the acquired pressure waveform is the difference in peak value. The peak value is a feature value that represents a change in physical quantity such as thermal expansion or volume change when transitioning from a liquid to a solid.

[0005] However, there are many types of defects in injection molding other than burrs and shorts, and not all of them show up as differences in peak values, so defective products can be produced even if the peak values ​​are the same. In particular, there is a problem with appearance defects, which are difficult to show up as differences in peak values.

[0006] The present invention has been made in consideration of the above problems, and aims to provide an information processing system, an information processing method, and a program that can assist in detecting appearance defects in molded products that are being judged as pass / fail. [Means for solving the problem]

[0007] An information processing system according to a first aspect of the present invention is an information processing system for judging the quality or non-quality of the appearance of a molded product molded by injecting resin into a mold provided with a pressure sensor, and includes an acquisition unit that acquires pressure time series data detected by the pressure sensor during injection molding of the molded product to be judged as quality or non-quality, a calculation unit that calculates a pressure increase rate at least one time using data from the acquired pressure time series data during a target period from the pressure rise time to a time based on a VP switching time, and an output unit that executes outputting information indicating the quality or non-quality of the appearance of the molded product to be judged as quality or non-quality or information indicating the presence or absence of a defect based on a feature based on the calculated pressure increase rate and / or performing processing to reject the molded product, wherein the VP switching time is the timing for switching from a speed control period to a pressure control period.

[0008] An information processing system according to a second aspect of the present invention is the information processing system according to the first aspect, further comprising a memory unit in which a machine learning model is stored that has been trained to output information indicating the pass / fail of injection molding by using at least a feature value based on a pressure increase rate calculated using data during a target period from the pressure rise time to a time based on the VP switching time, out of reference time series data, which is time series data of pressure when a good product is molded, as an input value, and the output unit inputs the feature value based on the calculated pressure increase rate into the machine learning model, thereby outputting information indicating the pass / fail appearance of the molded product to be judged as pass / fail or information indicating the presence or absence of a defect and / or performing processing to reject the molded product.

[0009] An information processing system according to a third aspect of the present invention is the information processing system according to the second aspect, wherein the machine learning model calculates the distance between the center of gravity of a feature vector based on a pressure increase rate calculated using data for a target period from among reference time series data and a feature vector based on a pressure increase rate calculated using data for the target period from among the pressure time series data of the object to be judged as good or bad, and based on the calculated distance, outputs information indicating the quality of the appearance of the molded product to be judged as good or bad or information indicating the presence or absence of defects and / or performs processing to reject the molded product.

[0010] An information processing system according to a fourth aspect of the present invention is the information processing system according to any one of the first to third aspects, wherein the information indicating the quality of the appearance of the injection molding includes information indicating the presence or absence of silver streaks.

[0011] An information processing system according to a fifth aspect of the present invention is the information processing system according to any one of the first to fourth aspects, further comprising a determination unit that determines a VP switching time using an injection pressure detected by a pressure sensor provided at an end of a screw of a molding machine that molds a molded product, the end being opposite to an end that pushes in a resin, The calculation unit calculates a pressure increase rate at least at one time using the identified VP switching time.

[0012] An information processing system according to a sixth aspect of the present invention is the information processing system according to any one of the first to fifth aspects, further comprising a determination unit that determines a VP switching time by using a current value or torque of a motor for pushing resin into a screw of a molding machine that molds a molded product; The calculation unit calculates a pressure increase rate at least at one time using the identified VP switching time.

[0013] An information processing method according to a seventh aspect of the present invention is an information processing method for judging the quality or non-quality of the appearance of a molded product molded by injecting resin into a mold provided with a pressure sensor, and includes the steps of acquiring pressure time series data detected by the pressure sensor during injection molding of the molded product to be judged as quality or non-quality, calculating a pressure increase rate at at least one time using data from the acquired pressure time series data during a target period from the pressure rise time to a time based on a VP switching time, and outputting information indicating the quality or non-quality of the appearance of the molded product to be judged as quality or non-quality or information indicating the presence or absence of a defect based on a feature based on the calculated pressure increase rate and / or performing processing to reject the molded product, wherein the VP switching time is the timing for switching from a speed control period to a pressure control period.

[0014] A program according to an eighth aspect of the present invention is a program for judging the quality or non-quality of the appearance of a molded product molded by injecting resin into a mold provided with a pressure sensor, and causes a computer to execute the following steps: acquiring pressure time series data detected by the pressure sensor during injection molding of the molded product to be judged as quality or non-quality; calculating a pressure increase rate at at least one time using data from the acquired pressure time series data during a target period from the pressure rise time to a time based on the VP switching time; and outputting information indicating the quality or non-quality of the appearance of the molded product to be judged as quality or non-quality or information indicating the presence or absence of a defect based on a feature based on the calculated pressure increase rate and / or performing processing to reject the molded product, wherein the VP switching time is the timing for switching from a speed control period to a pressure control period. Effect of the Invention

[0015] According to one aspect of the present invention, information indicating whether the appearance of a molded product that is being judged as good or bad can be obtained, or information indicating the presence or absence of a defect can be obtained, and if the molded product is defective, the molded product can be rejected, thereby assisting in the detection of defects in the appearance of a molded product that is being judged as good or bad. [Brief description of the drawings]

[0016] [Figure 1] FIG. 13 is a diagram for explaining the pressure increase rate from the pressure rise time to the VP switching time. [Diagram 2] FIG. 2 is an external view of a molding machine according to the present embodiment. [Diagram 3] 1 is a schematic configuration diagram of a part of a molding machine 1 according to the present embodiment. [Figure 4] 1 is a diagram showing an example of the configuration of a mold clamping unit in the present embodiment and an example of the device configuration of a molding condition determination support system 100. FIG. [Diagram 5] 2 is a block diagram showing a schematic configuration of an information processing system 4. FIG. [Figure 6] 13 is a diagram illustrating an example of a distance between the center of gravity of a feature amount vector based on reference time series data and a feature amount vector based on a pressure increase rate. FIG. [Figure 7] 1 is a graph showing an example of pressure time series data. [Figure 8] 1 is a graph showing an example of time-series data of mold internal pressure and injection pressure on the molding machine side. [Figure 9] 1 is a graph showing an example of time-series data of the mold internal pressure and the injection pressure on the molding machine side in a case where the time at which the injection pressure peaks is not fixed at a single point. [Figure 10] 11 is a graph showing an example of time-series data of the injection pressure and the motor current value in a case where the peaks of the injection pressure and the motor current value coincide with each other. [Figure 11] FIG. 13 is a schematic configuration diagram of a molding condition determination support system according to a modified example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] Hereinafter, each embodiment will be described with reference to the drawings. However, more detailed description than necessary may be omitted. For example, detailed description of already well-known matters or duplicate description of substantially the same configuration may be omitted. This is to avoid the following description becoming unnecessarily redundant and to facilitate understanding by those skilled in the art.

[0018] The inventors of this application have focused on the fact that appearance defects appear due to changes in the flow state of the resin. The rate of pressure increase from the rise of the mold pressure waveform to the peak value may be used as a feature value that represents the flow behavior of the resin. In injection molding, there is a speed control period in which resin is injected into the mold at a certain speed, and after the speed control period, there is a pressure control period in which a certain pressure is applied to hold the resin inside the mold, and the timing of switching from the speed control period to the pressure control period is called the VP switching time.

[0019] Therefore, the inventors of the present application came up with the idea of ​​using a feature based on the pressure increase rate from the pressure rise time to a time based on the VP switching time (for example, the VP switching time, or a time determined based on the VP switching time, specifically, for example, a time X seconds after or X seconds before the VP switching time).

[0020] Fig. 1 is a diagram for explaining the pressure increase rate from the pressure rise time to the VP switching time. In Fig. 1, the vertical axis is pressure and the horizontal axis is elapsed time, and an example of the mold internal pressure waveform with the passage of time during one shot for molding one molded product is shown. The mold internal pressure waveform is detected by, for example, pressure sensor 23, and is the pressure inside the mold from the molten resin. As shown in Fig. 1, time t0 is the pressure rise time, and time t1 is the VP switching time. If the sampling time between time t0 and time t1 is Δt, there are (t1-t0) / Δt sampling points, and since the pressure increase rate can be calculated at each sampling point, (t1-t0) / Δt pressure increase rates can be calculated. In this way, since multiple pressure increase rates are obtained, the feature value based on the pressure increase rate may be a statistic of these multiple pressure increase rates (e.g., maximum value, minimum value, average value, median value, etc.) or a representative value of these multiple pressure increase rates.

[0021] 2 is an external view of a molding machine in this embodiment. The molding machine 1 in this embodiment is an injection molding machine that produces various plastic products by pouring molten resin (plastic) into a mold, cooling and solidifying it, and removing it. The molding machine 1 has an injection unit 10 that uses heat to melt the resin material and inject it into the mold, a mold clamping unit 20 that opens and closes the mold, and a controller 30 that controls molding conditions (e.g., speed, pressure, temperature, etc. when injecting the resin into the mold).

[0022] Fig. 3 is a schematic diagram of a part of the molding machine 1 in this embodiment. As shown in Fig. 3, the injection unit 10 includes a hopper, a heating cylinder, a screw 12, a nozzle, a heater, a driving device, and the like. The hopper is an inlet for pellets (granular molding material). The heating cylinder is provided so as to be movable in the axial direction relative to the bed. The screw 12 is disposed inside the heating cylinder and is provided so as to be rotatable and movable in the axial direction. The nozzle is an injection port provided at the tip of the heating cylinder, and supplies the molten resin inside the heating cylinder to the cavity of the mold by the axial movement of the screw 12.

[0023] 3, the molding machine 1 is provided with a motor 13 that drives the screw 12, and a current sensor 14 that detects the current of the motor 13. The molding machine 1 also is provided with a load cell 15, which is an example of a pressure sensor that detects the injection pressure, on the end side of the screw 12.

[0024] The clamping unit 20 performs opening and closing operations of the attached mold, and prevents the mold from opening due to the pressure of the molten resin injected into the mold cavity (molded product portion) when the mold is clamped. The clamping unit 20 includes a fixed platen, a movable platen, tie bars, a drive unit, and the like. A first mold on the fixed side is fixed to the fixed platen. The fixed platen can abut against the nozzle and guides the resin injected from the nozzle to the mold cavity. The cavity is an area formed between the first mold and the second mold and corresponds to the product shape. A second mold on the movable side is fixed to the movable platen and can be moved toward and away from the fixed platen. The tie bars support the movement of the movable platen. The drive unit is, for example, a cylinder device, and moves the movable platen. The first mold has a supply path between the nozzle and the cavity. A three-plate mold or the like can be similarly applied.

[0025] FIG. 4 is a diagram showing an example of the configuration of a mold clamping unit and an example of the device configuration of the molding condition determination support system 100 in this embodiment.

[0026] As shown in FIG. 4, ejector pins (extrusion pins) 22 fixed to an ejector plate 21 are pushed out when the mold is opened, so that a molded product (workpiece) can be removed from the mold after molding. A plurality of pressure sensors 23 for acquiring data inside the mold are provided in a manner such that they are embedded in the ejector plate 21 at positions corresponding (opposite) the positions of the ejector pins 22. The pressure sensors 23 are pressure sensors for detecting the pressure inside the mold received from the molten resin, and are, for example, load cells. Note that a measurement mechanism via the ejector plate 21 and the ejector pins 22 is not essential, and the mounting position of the pressure sensors 23 is not particularly limited as long as it is possible to acquire data inside the mold, and may be any position, whether inside or outside the mold.

[0027] The controller 30 shown in FIG. 3 controls the drive device of the injection unit 10 and the drive device of the mold clamping unit 20 based on command values ​​(parameters) related to molding conditions. The molding machine 1 may be composed of a plurality of devices each equipped with a control device, a sensor, and the like.

[0028] 4, a mold equipped with a sensor (load cell) 23 for acquiring data inside the mold such as mold pressure is installed in the mold clamping unit 20 of the molding machine 1. The pressure sensor 23 transmits sensing data to an information processing system 4 via an instrumentation amplifier 2, an A / D converter 3, etc., which serve as a data acquisition unit.

[0029] The pressure sensor 23 and the information processing system 4 may be connected wirelessly or the like. Here, the pressure sensor (load cell) 23 is used, but any type or data communication method may be used as long as the sensor can acquire data inside the cavity such as the mold pressure, and the installation position may be arbitrary. For example, when the mold is manufactured, if a sensor is embedded in the mold itself or the sensor is provided in such a manner that it touches the cavity, data inside the cavity such as the mold pressure can be acquired.

[0030] The information processing system 4 judges whether the appearance of a molded product formed by injecting resin into a mold provided with a pressure sensor 23 is good or bad. The information processing system 4 is, for example, an industrial PC (personal computer) and includes a processor (for example, CPU: Central Processing Unit) which is an arithmetic device serving as a control unit and calculation unit, known input / output means such as ROM (Read Only Memory) and RAM (Random Access Memory), and includes a predetermined storage device as a built-in or external HDD or the like serving as a storage unit. The information processing system 4 controls the display device 5 to display information.

[0031] Fig. 5 is a block diagram showing a schematic configuration of the information processing system 4. As shown in Fig. 5, the information processing system 4 includes a processor 40, an input unit 41, an output unit 42, a storage unit 43, and a communication unit 44. The input unit 41, for example, accepts an input from a user. The output unit 42, for example, outputs a video signal to the display device 5. The storage unit 43 stores a program that is read and executed by the processor 40. The communication unit 44 communicates, for example, by wire or wirelessly.

[0032] The processor 40 functions as an acquisition unit 45, an identification unit 46, a calculation unit 47, and an output unit 48 by reading and executing a program from the storage unit 43. The acquisition unit 45 acquires pressure time series data detected by the pressure sensor 23 during injection molding of a molded product to be judged as pass / fail. The determination unit 46 determines the VP switching time. The process of the determination unit 46 will be described later. The calculation unit 47 calculates a pressure increase rate at least at one time by using data from the acquired pressure time series data during a target period from the pressure rise time to a time based on the VP switching time.

[0033] The output unit 48 outputs information indicating whether the appearance of the molded product to be judged is good or bad, or information indicating the presence or absence of a defect, based on the feature amount based on the calculated pressure increase rate, and / or executes processing to reject the molded product. Here, the information indicating the quality of the injection molded product's appearance includes, for example, information indicating the presence or absence of silver streaks.

[0034] <Specific example 1 of the process of the output unit 48> In this case, as an example, the output unit 48 may compare the pressure increase rate during the period from the pressure rise time to the VP switching time in the pressure time series data with the pressure increase rate during the same period in the reference time series data, which is the time series data of the pressure when a good product is molded, and determine that the molded product is defective when the difference in the pressure increase rate is equal to or greater than a predetermined threshold value.

[0035] <Specific example 2 of the process of the output unit 48> Another specific example of the processing of the output unit 48 will be described. For example, the storage unit 43 stores a machine learning model that has been trained to output information representing the pass / fail of injection molding using at least a feature value based on the pressure increase rate as an input value. Here, the feature value based on the pressure increase rate may be calculated using data during a target period from the pressure rise time to a time based on the VP switching time among reference time series data, which is time series data of pressure when a non-defective product is molded. The time based on the VP switching time may be the VP switching time itself, may be a time a predetermined time later (or earlier) than the VP switching time, or may be a time obtained by multiplying the VP switching time by a predetermined factor (for example, 1.1). In addition, the feature value may be, for example, a representative value of the pressure increase rate from the pressure rise time to the time based on the VP switching time, an average value or a median value of the pressure increase rate from the pressure rise time to the time based on the VP switching time, or the like. In this case, the output unit 48 outputs information representing the pass / fail of the appearance of the molded product to be judged, for example, by inputting the feature value based on the calculated pressure increase rate into the machine learning model.

[0036] Here, the machine learning model, for example, calculates the distance between the center of gravity of a feature vector based on the pressure increase rate calculated using data for a target period from the reference time series data, and a feature vector based on the pressure increase rate calculated using data for the target period from the pressure time series data of the object to be judged as pass / fail, and outputs information indicating the pass / fail appearance of the molded product to be judged as pass / fail based on the calculated distance.

[0037] Fig. 6 is a diagram showing an example of the distance between the center of gravity of a feature vector based on reference time series data and a feature vector based on a pressure increase rate (hereinafter also referred to as the distance from the center of gravity). As shown in region R1 in Fig. 6, in the case of a non-defective molded product (i.e., a molded product without defects), the distance from the center of gravity is within a predetermined threshold value (e.g., 2). On the other hand, in the case of the occurrence of silver streaks, which is an example of an appearance abnormality, the distance from the center of gravity exceeds the predetermined threshold value, as shown by points P1 to P4. In this way, the machine learning model may, for example, determine that an item is a non-defective item when the distance from the center of gravity falls within a predetermined threshold, and determine that an item has a visual abnormality when the distance from the center of gravity exceeds the predetermined threshold.

[0038] Next, an embodiment of the process of the determination unit 46 that determines the VP switching time from the pressure time series data (also called internal mold pressure waveform data) will be described. <Example 1> Fig. 7 is a graph showing an example of pressure time series data. In the mold pressure waveform shown in the graph of Fig. 7, it is difficult to determine at what timing the mold pressure waveform in the dashed frame R2 of Fig. 7 has a peak. In other words, it is difficult to determine at what timing the VP is switched from the mold pressure waveform data, and it is difficult to specify the VP switching time.

[0039] Therefore, the time series data of the injection pressure on the molding machine side is obtained from the load cell 15 and synchronized in time with the mold internal pressure waveform data. FIG. 8 is a graph showing an example of the time series data of the mold internal pressure and the molding machine injection pressure. As shown by the arrow A1 in FIG. 8, the injection pressure on the molding machine side has a sharp peak. Since the time when this injection pressure peaks is the VP switching time, the corresponding time in the mold internal pressure waveform data indicates the VP switching time. This makes it possible to obtain the pressure increase rate up to the VP switching time from the mold internal pressure waveform data.

[0040] At this time, the determination unit 46 determines the VP switching time using, for example, the injection pressure detected by the load cell 15 provided at the end opposite to the end of the screw 12 of the molding machine that molds the molded product, which pushes in the resin. Specifically, for example, the determination unit 46 may detect the timing of the peak of the injection pressure as the VP switching time. As a result, the calculation unit 47 calculates the pressure increase rate at least at one time using the determined VP switching time.

[0041] <Example 2> FIG. 9 is a graph showing an example of time series data of the mold cavity pressure and the injection pressure on the molding machine side in the case where the time when the injection pressure reaches its peak is not fixed to one point. In the above-mentioned Example 1, the VP switching time was obtained using the peak of the injection pressure, but when the maximum value of the injection pressure is equal to or less than the holding pressure while holding pressure is applied (the maximum value of the injection pressure while holding pressure is applied≦holding pressure), the time when the injection pressure reaches its peak is not fixed to one point as shown in FIG. 9. The maximum value of the injection pressure here means a momentary peak of the waveform that should appear but is buried and does not appear. Here, the holding pressure is, as an example, the pressure measured by the load cell 15. In FIG. 9, the waveform becomes flat at the maximum value of the injection pressure, indicating that the momentary peak that should appear is buried because the pressure due to the holding pressure is higher.

[0042] Therefore, the torque of the extrusion motor of the molding machine or the current value of the motor, which is correlated with the torque, is monitored. Figure 10 is a graph showing an example of time-series data of the injection pressure and the current value of the motor when the peaks of the injection pressure and the current value of the motor coincide. As shown in Figure 10, the torque or current value of the motor peaks at the peak of the injection pressure, so the time when the torque or current value peaks is the time when the injection pressure peaks, and this time corresponds to the VP switching time.

[0043] In this case, the determination unit 46 may determine the VP switching time using a current value or torque of a motor for pushing resin into a screw of a molding machine that molds the molded product. Specifically, for example, the determination unit 46 may determine the time when the current value or torque of the motor reaches a peak (maximum value) as the VP switching time. In this case, the calculation unit 47 may calculate the pressure increase rate at least at one time using the determined VP switching time.

[0044] As described above, the information processing system 4 according to this embodiment is an information processing system relating to a molded product that is molded by injecting resin into a mold in which a pressure sensor is provided, and includes an acquisition unit 45 that acquires pressure time series data detected by the pressure sensor during injection molding of a molded product to be judged as pass / fail. The information processing system 4 further includes a calculation unit 47 that calculates a pressure increase rate at least at one time using data from the acquired pressure time series data during a target period from the pressure rise time to a time based on the VP switching time. Furthermore, the information processing system 4 includes an output unit 48 that executes outputting information indicating whether the appearance of the molded product to be judged is good or bad, or information indicating the presence or absence of a defect, and / or executing processing to reject the molded product, based on the feature amount based on the calculated pressure increase rate. For example, the output unit 48 may output information such as "a defective appearance will occur," or may output information that some kind of defect has occurred without specifying the type of defect. Furthermore, when it is determined that a defect has occurred, the output unit 48 may execute processing to reject the molded product. Here, the processing may, for example, control the molded product to be moved to another location (for example, control the lane through which the molded product flows after molding), or may mark the molded product in which a defect has occurred.

[0045] According to this configuration, information indicating whether the appearance of the molded product being judged as good or bad can be obtained, or information indicating whether or not it is defective can be obtained, and if it is defective, the molded product can be rejected, thereby assisting in the detection of defects in the appearance of the molded product being judged as good or bad.

[0046] Fig. 11 is a schematic diagram of a molding condition determination support system in a modified example. As shown in Fig. 11, the molding condition determination support system 100b is different from that of this embodiment in that a terminal device 6 connected to the output of the A / D converter 3 is provided, and the information processing system 4 is communicably connected to the terminal device 6 via a communication circuit network CN. The information processing system 4 can receive various data (e.g., waveform data of a sensor, operation data, setting conditions, etc.) from the terminal device 6. The information processing system 4 also transmits information indicating the quality of the appearance of the molded product to be judged, obtained by processing, to the terminal device 6.

[0047] The terminal device 6 is connected to the display device 5, and controls the display device to display the information received from the information processing system 4. The information processing system 4 may be constructed remotely (for example, in the cloud). Thus, for example, by constructing the information processing system 4 remotely, it is possible to determine information indicating the quality of the appearance of a molded product that is the subject of quality judgment for a plurality of molding machines 1 installed in a plurality of locations, and to transmit this information to the terminal devices 6 used by users of the plurality of molding machines 1.

[0048] At least a part of the information processing system 4 described in the above embodiment may be configured with hardware or software. When configured with software, a program that realizes at least a part of the functions of the information processing system 4 may be stored in a computer-readable recording medium and read and executed by a computer. The recording medium is not limited to a removable one such as a magnetic disk or an optical disk, but may be a fixed recording medium such as a hard disk device or a memory.

[0049] In addition, a program that realizes at least a part of the functions of the information processing system 4 may be distributed via a communication line (including wireless communication) such as the Internet. Furthermore, the program may be encrypted, modulated, or compressed and distributed via a wired line or wireless line such as the Internet, or stored in a recording medium.

[0050] Furthermore, the information processing system 4 may be operated by one or more information devices. When multiple information devices are used, one of the devices may be a computer, and the computer may execute a predetermined program to realize the function as at least one of the means of the information processing system 4.

[0051] In the method invention, all the steps may be realized by automatic control using a computer. Alternatively, each step may be performed by a computer while the progress between steps is controlled manually. Furthermore, at least some of the steps may be performed manually.

[0052] As described above, the present invention is not limited to the above-described embodiment as it is, and in the implementation stage, the components can be modified and embodied without departing from the gist of the invention. In addition, various inventions can be formed by appropriately combining the multiple components disclosed in the above-described embodiment. For example, some components may be deleted from all the components shown in the embodiment. Furthermore, components from different embodiments may be appropriately combined. [Explanation of symbols]

[0053] 1 Molding machine 10. Injection Unit 12 Screw 13 Motor 14 Current Sensor 15 Load Cell 100, 100b Molding condition decision support system 2. Instrumentation Amplifier 20 Mold clamping unit 3. A / D Converter 30 Controller 4. Information Processing Systems 40 processors 41 Input section 42 Output section 43 Storage section 44 Communications Department 45 Acquisition Department 46 Specific part 47 Calculation section 48 Output section 5 Display device 6 Terminal Equipment 10. Injection Unit 20 Mold clamping unit 21 Ejector plate 22 Ejector pin 23 Pressure Sensor 30 Controller

Claims

1. An information processing system for a molded product that is molded by injecting resin into a mold having a pressure sensor, an acquisition unit that acquires pressure time series data detected by the pressure sensor during injection molding of a molded product to be judged as pass / fail; A calculation unit that calculates a pressure increase rate at at least one time by using data from the acquired pressure time series data during a target period from a pressure rise time to a time based on a VP switching time; an output unit that outputs information indicating whether the appearance of the molded product to be judged is good or bad, or information indicating the presence or absence of a defect, based on the feature amount based on the calculated pressure increase rate, and / or performs processing to reject the molded product; Equipped with The VP switching time is a timing for switching from a velocity control period to a pressure control period.

2. The machine learning model is trained to output information indicating the quality of the injection molding by using, as an input value, at least a feature value based on a pressure increase rate calculated using data during a target period from a pressure rise time to a time based on a V-P switching time, out of reference time series data which is time series data of pressure when a non-defective product is molded, and a storage unit is stored in the machine learning model. The output unit inputs a feature based on the calculated pressure increase rate into the machine learning model, thereby outputting information indicating whether the appearance of the molded product to be judged is good or bad, or information indicating the presence or absence of a defect, and / or performing a process to reject the molded product. The information processing system according to claim 1 .

3. 3. The information processing system according to claim 2, wherein the machine learning model calculates a distance between a center of gravity of a feature vector based on a pressure increase rate calculated using data for a target period from among reference time series data, and a feature vector based on a pressure increase rate calculated using data for the target period from among the pressure time series data of the object to be judged good or bad, and outputs information indicating whether the appearance of the molded product to be judged good or bad or information indicating the presence or absence of a defect and / or performs processing to reject the molded product based on the calculated distance.

4. The information indicating the quality of the appearance of the injection molding includes information indicating the presence or absence of silver streaks.

3. The information processing system according to claim 1 or 2.

5. The present invention further includes a determination unit that determines a VP switching time by using an injection pressure detected by a pressure sensor provided at an end of a screw of a molding machine that molds a molded product, the end being opposite to an end into which a resin is pushed in, The calculation unit calculates a pressure increase rate at least at one time using the specified VP switching time. The information processing system according to claim 1 .

6. The present invention further includes a determination unit that determines a VP switching time by using a current value or torque of a motor for pushing resin into a screw of a molding machine that molds a molded product, The calculation unit calculates a pressure increase rate at least at one time using the specified VP switching time. The information processing system according to claim 1 .

7. 1. An information processing method for a molded product that is molded by injecting resin into a mold having a pressure sensor, comprising: A step of acquiring pressure time series data detected by the pressure sensor during injection molding of a molded product to be judged pass / fail; A step of calculating a pressure increase rate at at least one time using data during a target period from a pressure rise time to a time based on a VP switching time among the acquired pressure time series data; a step of outputting information showing the quality of the appearance of the molded product to be judged as pass / fail or information showing the presence or absence of a defect based on the feature amount based on the calculated pressure increase rate, and / or executing control to reject the molded product; having The information processing method, wherein the VP switching time is a timing for switching from a velocity control period to a pressure control period.

8. A program for evaluating the quality of the appearance of a molded product produced by injecting resin into a mold having a pressure sensor, the program being programmed on a computer: A step of acquiring pressure time series data detected by the pressure sensor during injection molding of a molded product to be judged as pass / fail; A step of calculating a pressure increase rate at at least one time using data during a target period from a pressure rise time to a time based on a VP switching time among the acquired pressure time series data; a step of outputting information showing the quality of the appearance of the molded product to be subjected to pass / fail judgment or information showing the presence or absence of a defect based on the feature amount based on the calculated pressure increase rate, and / or performing a process for rejecting the molded product; A program for executing The VP switching time is a timing for switching from a velocity control period to a pressure control period.

Citation Information

Patent Citations

  • Method for judging quality of molded product in injection molding

    JP1991099821A

  • Injection molding device and controlling method thereof

    JP1999138611A

  • Method for molding plastic molded product and plastic molded product

    JP2002086504A

  • Injection molder

    JP2016083775A

  • Injection molding machine

    JP2004209814A

Cited By

  • Semiconductor device

    CN121729107A