Apparatus, method, learning device and inference device for manufacturing resin molded products

Abstract

To detect a molding failure in a resin molded article and identify its cause.SOLUTION: A device for producing a resin molded article includes a die 103 for pouring resin, first and second pressure sensors 207, first and second die temperature sensors 208, and first and second resin temperature sensors 209. The first pressure sensor 207, first die temperature sensor 208, and first resin temperature sensor 209 are provided near the gate of a die 103. The second pressure sensor 207, second die temperature sensor 208, and second resin temperature sensor 209 are provided near the end of the molding section within a cavity. The device for producing a resin molded article further includes a determination unit 221 that detects a molding failure in resin and determines its cause on the basis of the output values of the first and second pressure sensors 207, the output values of the first and second die temperature sensors 208, and the output values of the first and second resin temperature sensors 209.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to a manufacturing apparatus for a resin molded product, and more particularly to detection of molding defects in a resin molded product and estimation of the cause thereof. [Background technology]

[0002] Injection molding is a well-known method for manufacturing resin molded products, in which heated and molten resin is injected into a mold and cooled to produce a resin molded product. During the injection molding process, resin molded products can suffer from short shots and sink marks, which are areas where the resin is not filled, and burrs, which are when resin leaks from the parting surface of the mold. Resin molded products with short shots, sink marks, or burrs are deemed defective. Therefore, there is a need for technology to detect these resin molding defects and adjust the molding conditions to produce quality products.

[0003] Regarding technology for determining the quality of resin molded products, for example, Japanese Patent Application Laid-Open No. 2009-298033 (Patent Document 1) discloses a molded product determination system that "includes a pressure sensor that detects the pressure of molding material injected into a mold cavity of an injection molding device, a temperature sensor that detects the temperature of the molding material injected into the mold cavity, and a control unit that determines the quality of a molded product made from the molding material based on the pressure of the molding material detected by the pressure sensor and the temperature of the molding material detected by the temperature sensor" (see [Abstract]). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2009-298033 Summary of the Invention [Problem to be solved by the invention]

[0005] According to the technology disclosed in Patent Document 1, a pressure sensor and a resin temperature sensor are used in the mold to improve the accuracy of detecting short shots. However, the technology disclosed in Patent Document 1 cannot identify the cause of molding defects caused by temperature differences between different locations in the mold or between different locations in the cavity. Therefore, there is a need for a technology that can more accurately detect molding defects in resin molded products and identify the cause.

[0006] The present disclosure has been made in view of the above-described background, and an object of one aspect is to provide a technique for detecting molding defects in resin molded products and identifying the causes thereof. [Means for solving the problem]

[0007] According to one embodiment, there is provided an apparatus for manufacturing a resin molded product. The manufacturing apparatus includes a mold for pouring resin, first and second pressure sensors, first and second mold temperature sensors, and first and second resin temperature sensors. The first pressure sensor, the first mold temperature sensor, and the first resin temperature sensor are provided near a gate of the mold. The second pressure sensor, the second mold temperature sensor, and the second resin temperature sensor are provided near an end of the molded product portion in the cavity. The manufacturing apparatus further includes a determination unit that detects resin molding defects and determines the cause of the defects based on output values ​​of the first and second pressure sensors, output values ​​of the first and second mold temperature sensors, and output values ​​of the first and second resin temperature sensors. [Effects of the Invention]

[0008] According to one embodiment, it is possible to detect molding defects in a resin molded product and identify the cause of the defects.

[0009] The above and other objects, features, aspects and advantages of the present disclosure will become apparent from the following detailed description of the disclosure taken in conjunction with the accompanying drawings. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram showing an example of the appearance of a manufacturing apparatus 100 according to an embodiment. [Figure 2] An example of the main configuration of the manufacturing apparatus 100 related to the detection of molding defects and the improvement of molding conditions will be shown. [Figure 3] FIG. 2 is a diagram showing an example of the configuration of a pressure sensor 207 and its surroundings. [Figure 4] 2 is a diagram illustrating an example of a circuit configuration of a determination unit 221. FIG. [Figure 5] FIG. 10 is a diagram showing an example of a waveform of pressure measured by a pressure sensor 207. [Figure 6] FIG. 10 is a diagram showing an example of a procedure of a determination unit 221. [Figure 7] FIG. 7 shows an example of the configuration of a manufacturing apparatus 700 according to an embodiment. [Figure 8] FIG. 8 shows an example of the configuration of a manufacturing apparatus 800 according to an embodiment. [Figure 9] FIG. 4 shows an example of the configuration of a learning device 420 for generating a model for detecting molding defects in a manufacturing apparatus according to an embodiment. [Figure 10] 10 is a flowchart showing an example of a procedure for a learning process performed by a learning device 420. [Figure 11] FIG. 4 is a diagram showing an example of the configuration of an inference device 430 for detecting molding defects using a trained model in a molding process of a manufacturing apparatus according to an embodiment. [Figure 12] 10 is a flowchart showing an example of the procedure of inference processing by the inference device 430. [Figure 13] FIG. 4 is a diagram illustrating an example of a neural network model used by a learning device 420. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments of the technical concept according to the present disclosure will be described with reference to the drawings. In the following description, the same components are denoted by the same reference numerals. The names and functions of the components are also the same. Therefore, detailed descriptions thereof will not be repeated.

[0012] <Configuration of the resin molded product manufacturing apparatus> First, referring to FIGS. 1 to 3, the configuration of the resin molded product manufacturing apparatus according to the present embodiment will be described. The resin molded product manufacturing apparatus according to the present embodiment manufactures a resin molded product by injection molding. Further, the resin molded product manufacturing apparatus according to the present embodiment can analyze the output values of various sensors to detect molding defects, estimate or identify the causes, and present or automatically execute improvements to the manufacturing process (such as adjustment of the resin injection speed, mold temperature, resin temperature, etc.).

[0013] FIG. 1 is a diagram showing an example of the appearance of the manufacturing apparatus 100 according to the present embodiment. Referring to FIG. 1, the configuration of the manufacturing apparatus 100 and the procedure of injection molding will be described. The manufacturing apparatus 100 mainly includes a mold 103 and an injection unit 110. The mold 103 includes a movable mold 104 and a fixed mold 105. The movable mold 104 is driven by a motor 112. The injection unit 110 includes a hopper 101, a cylinder 102, and a motor 111.

[0014] The injection unit 110 melts the resin and pours the melted resin into the mold 103. The hopper 101 is set with a resin material. The resin material is, for example, resin pellets or the like. In a certain aspect, the hopper 101 may be manually replenished with resin or may be provided with a mechanism for automatically replenishing resin from an external tank or the like.

[0015] The cylinder 102 is connected to the hopper 101 and serves as a passage for transporting the resin flowing in from the hopper 101 to the mold 103. More specifically, a screw 216 (see FIG. 2) is provided inside the cylinder 102, and as the screw 216 rotates, the resin inside the cylinder 102 is transported to the mold 103. The cylinder 102 is provided with a heater 214 (see FIG. 2) for heating the resin so that the resin does not solidify.

[0016] The mold 103 is a mold into which resin is poured and deforms the resin into the shape of the product. The movable mold 104 is a mold driven by a motor 112, and the mold 103 opens and closes as the movable mold 104 moves. The movable mold 104 is provided with an ejector pin 206 (see FIG. 2). When the mold 103 opens (when the movable mold 104 moves), the ejector pin 206 pushes out the resin molded product attached to the mold 103 (movable mold 104). The fixed mold 105 is connected to the cylinder 102. For example, the resin flows from the fixed mold 105 through a sprue, a runner, and a gate into the cavity 205 (see FIG. 2). In this specification, the term "cavity 205" encompasses the gap formed between the movable mold 104 and the fixed mold 105 and the concave mold (usually the fixed mold 105). The convex mold (usually the movable mold 104) is sometimes called a core.

[0017] Motor 111 drives screw 216. In one aspect, manufacturing apparatus 100 may include motor 111 and a motor driver (not shown) that controls motor 111. In another aspect, manufacturing apparatus 100 may include motor 111 but not a motor driver. In this case, manufacturing apparatus 100 may be connected to an external motor driver.

[0018] The motor 112 drives the movable mold 104 via a power transmission component. In one aspect, the manufacturing apparatus 100 may include the motor 112 and a motor driver (not shown) that controls the motor 112. In another aspect, the manufacturing apparatus 100 may include the motor 112 but not the motor driver. In this case, the manufacturing apparatus 100 may be connected to an external motor driver.

[0019] Next, the procedure for resin molding will be described. First, the injection unit 110 pours heated molten resin (hereinafter, also referred to as "molten resin") into the mold 103. More specifically, the injection unit 110 heats and melts the resin material (pellets, etc.) in the hopper 101. The molten resin flows from the hopper 101 into the cylinder 102. The molten resin that has flowed into the cylinder 102 is poured into the fixed mold 105 by a screw 216 inside the cylinder 102. The screw 216 is rotated by a motor 111.

[0020] The molten resin injected into the fixed mold 105 passes through the sprue 203 (see FIG. 2). The molten resin that has passed through the sprue 203 flows into a cavity 205 formed by the fixed mold 105 and the movable mold 104.

[0021] The cavity 205 is divided into a runner, a gate, and a molded product section, and the molten resin is filled in this order: runner, gate, and molded product section. The molded product section is a gap in the shape of the product to be molded from the resin. The runner is the path for the molten resin from the sprue 203 to the molded product section. The gate is located between the runner and the molded product section and serves as the entrance for the resin to the molded product section. The gate may also have the role of adjusting the inflow pressure, inflow speed, temperature, etc. of the resin, and preventing backflow.

[0022] After the cavity 205 is filled with molten resin, the molten resin comes into contact with the surfaces of the mold 103 (the movable mold 104 and the fixed mold 105), whereby the resin is cooled and solidified, and a molded product is formed in the cavity 205. After the resin has solidified, the movable mold 104 is driven by the motor 112 to separate from the fixed mold 105, and the mold 103 opens. At this time, the molded product generally adheres to the movable mold 104. An ejector pin 206 (see FIG. 2) provided on the movable mold 104 pushes the molded product in the direction (closing direction) opposite to the operating direction (opening direction) of the movable mold 104, thereby peeling the molded product from the movable mold 104. The peeling of the molded product from the movable mold 104 is also referred to as demolding.

[0023] 2 shows an example of the main components related to the detection of molding defects and the improvement of molding conditions of the manufacturing apparatus 100. The manufacturing apparatus 100 is equipped with a pressure sensor 207, a mold temperature sensor 208, and a resin temperature sensor 209 on the mold 103 as main components related to the detection of molding defects and the improvement of molding conditions. The manufacturing apparatus 100 also includes, internally or externally, a control unit 260, an amplifier 220, a determination unit 221, and a display device 222.

[0024] The pressure sensor 207 is disposed between the ejector pin 206 and the ejector plate 303 (see FIG. 3). The pressure sensor 207 detects the pressure that the ejector pin 206 receives from inside the cavity. As an example, the pressure sensor 207 is preferably disposed in two locations: near the gate (or near the sprue 203 or runner) and near the end of the molded product. This is because the vicinity of the gate (or near the sprue 203 or runner) and the end of the molded product are locations where molding defects are most likely to occur. The manufacturing apparatus 100 can detect the presence or absence of molding defects and estimate their causes by comparing and analyzing the signals obtained from the pressure sensors 207 disposed in these locations. The end of the molded product may be, for example, the end of the molded product located farthest from the gate, near a location in the molded product corresponding to a thin portion of the resin in the molded product, or near a location in the molded product corresponding to a narrow portion of the molded product's shape.

[0025] In some aspects, the pressure sensors 207 may be placed in more locations in addition to near the gate (or near the sprue 203 or runner) and near the end of the molded product. In this case, the manufacturing apparatus 100 can estimate the presence or absence of molding defects and their causes based on a combination of analysis results of the output values ​​of the pressure sensors 207 placed in three or more locations.

[0026] The mold temperature sensor 208 measures the temperature of the mold 103 (the fixed mold 105 or the movable mold 104) and outputs a signal indicating the temperature of the mold 103. As an example, like the pressure sensor 207, the mold temperature sensor 208 is preferably provided in two locations: near the gate (or near the sprue 203 or runner) and near the end of the molded product portion. This is because the manufacturing apparatus 100 can calculate the temperature change of the mold during the resin filling process by acquiring the temperatures of the mold at two locations: near the gate and near the end of the molded product portion, where the temperature difference between the resin and the mold is greatest, and can identify the cause of molding defects from the temperature change. Furthermore, the manufacturing apparatus 100 can improve molding conditions based on the identified cause of molding defects.

[0027] 2, the mold temperature sensor 208 is provided in the fixed mold 105, but the arrangement of the mold temperature sensor 208 is not limited to this. In one aspect, the mold temperature sensor 208 may be provided in the movable mold 104.

[0028] In another aspect, the mold temperature sensors 208 may be placed in more locations in addition to near the gate (or near the sprue 203 or runner) and near the end of the molded product. In this case, the manufacturing apparatus 100 can estimate the presence or absence of molding defects and their causes based on a combination of analysis results of the output values ​​of the mold temperature sensors 208 placed in three or more locations.

[0029] The resin temperature sensor 209 measures the temperature of the resin (molten resin) inside the mold and outputs a signal indicating the temperature of the resin. As an example, like the pressure sensor 207, the resin temperature sensor 209 is preferably provided in two locations: near the gate (or near the sprue 203 or runner) and near the end of the molded product. This is because the manufacturing apparatus 100 can calculate the temperature change of the resin during the resin filling process by acquiring the resin temperatures at two locations, near the gate and near the end of the molded product, where the temperature difference between the resin and the mold is greatest, and can identify the cause of molding defects from the temperature change. Furthermore, the manufacturing apparatus 100 can improve molding conditions based on the identified cause of molding defects.

[0030] 2, the resin temperature sensor 209 is provided in the fixed mold 105, but the location of the resin temperature sensor 209 is not limited to this. In one aspect, the resin temperature sensor 209 may be provided in the movable mold 104.

[0031] In another aspect, the resin temperature sensors 209 may be placed in more locations in addition to near the gate (or near the sprue 203 or runner) and near the end of the molded product. In this case, the manufacturing apparatus 100 can estimate the presence or absence of molding defects and their causes based on a combination of analysis results of the output values ​​of the resin temperature sensors 209 placed in three or more locations.

[0032] The vicinity of the gate (or the vicinity of the sprue 203 or runner) is a position where it is easy to accurately measure the resin temperature at the beginning of the resin filling process. The vicinity of the end of the molded product is also the position where the resin is most likely to cool. Therefore, there is likely to be a difference in both the resin temperature and the mold temperature between the vicinity of the gate (or the vicinity of the sprue 203 or runner) and the vicinity of the end of the molded product, making this a suitable place to place a sensor.

[0033] The amplifier 220 amplifies the signals from the pressure sensor 207, the mold temperature sensor 208, and the resin temperature sensor 209, and outputs the amplified signals to the determination unit 221. As an example, the amplifier 220 may be realized by an operational amplifier element and its peripheral circuitry, etc.

[0034] The determination unit 221 acquires the output values ​​(signals) of each sensor received from the amplifier and analyzes the output values ​​of each sensor to determine whether or not there is a molding defect, identify the cause of the molding defect, and generate information for improving the molding conditions (at least some or all of the mold temperature adjustment information, resin temperature adjustment information, resin injection speed adjustment information, etc.). Details of the analysis procedure of the output values ​​of each sensor by the determination unit 221 will be described later with reference to FIG. 5. The determination unit 221 outputs information including some or all of the information for determining whether or not there is a molding defect, identify the cause of the molding defect, and improve the molding conditions to the display device 222.

[0035] Display device 222 displays the information acquired from determination unit 221. In one aspect, determination unit 221 may be a PC, and display device 222 may be a display. In another aspect, determination unit 221 may be a device equipped with a microcomputer, an SoC (System on Chip), or the like. In this case, display device 222 may be any device, such as a display, tablet, or PC, that can receive and display information or video from determination unit 221.

[0036] In one aspect, some or all of amplifier 220, determination unit 221, and display device 222 may be realized as separate devices or components, or may be realized as an integrated device. In another aspect, some or all of amplifier 220, determination unit 221, and display device 222 may be incorporated into manufacturing apparatus 100.

[0037] The control unit 260 controls a series of operations of the manufacturing apparatus 100, such as melting the resin, injecting the resin, and controlling the mold. In one aspect, the control unit 260 may be provided as a control unit inside the manufacturing apparatus 100. In another aspect, the control unit 260 may be provided outside the manufacturing apparatus 100. In this case, a PC (Personal Computer) or the like may be used as the control unit 260, or a dedicated device may be used as the control unit 260.

[0038] FIG. 3 is a diagram showing an example of the configuration of the pressure sensor 207 and its surroundings. The pressure sensor 207 is disposed between the ejector pin 206 and the ejector plate 303. When resin flows into the mold 103, the ejector pin 206 moves due to the flow of the resin. That is, the ejector pin 206 is pushed by the resin. The pressure sensor 207 can detect the pressure inside the mold 103 by being pushed by the ejector pin 206. By disposing the pressure sensor 207 at the base of the ejector pin 206, no trace of the pressure sensor 207 remains on the molded product. However, there may be cases where a trace of the pressure sensor 207 may remain on the molded product, such as when examining the pressure inside the resin case. Therefore, in some aspects, the pressure sensor 207 may be provided directly on the inner wall surface of the mold.

[0039] <B. Circuit Configuration> FIG. 4 is a diagram showing an example of the circuit configuration of the determination unit 221. Referring to FIG. 4, the circuit configuration of the determination unit 221 will be described. The determination unit 221 includes a processor 401, a memory 402, a storage 403, an external device IF (Interface) 404, an input IF 405, an output IF 406, and a communication IF 407. These circuits are interconnected by a bus 408. Note that the determination units 721 (see FIG. 7), 821 (see FIG. 8), etc. also have the same circuit configuration and functions as the determination unit 221.

[0040] The processor 401 can execute a program for realizing various functions of the determination unit 221. The processor 401 is constituted by, for example, at least one integrated circuit. The integrated circuit may be constituted by, for example, at least one CPU (Central Processing Unit), at least one GPU (Graphics Processing Unit), at least one FPGA (Field Programmable Gate Array), at least one ASIC (Application Specific Integrated Circuit), or a combination thereof, etc.

[0041] Memory 402 stores programs executed by processor 401 and data referenced by processor 401. In one aspect, memory 402 may be realized by a dynamic random access memory (DRAM), a static random access memory (SRAM), or the like.

[0042] Storage 403 is a non-volatile memory and may store programs executed by processor 401 and data referenced by processor 401. In this case, processor 401 executes programs read from storage 403 to memory 402 and references data read from storage 403 to memory 402. In one aspect, storage 403 may be realized by a hard disk drive (HDD), a solid state drive (SSD), an erasable programmable read only memory (EPROM), an electrically erasable programmable read only memory (EEPROM), a flash memory, or the like.

[0043] The external device IF 404 can be connected to any external device. The external device IF 404 is connected to the amplifier 220 and receives the output values ​​of each sensor via the amplifier 220. The external device IF 404 writes the received output values ​​of each sensor into the memory 402 or the storage 403. In one aspect, the external device IF 404 may be realized by a USB (Universal Serial Bus) terminal or the like.

[0044] The input IF 405 may be connected to any input device, such as a keyboard, mouse, touchpad, or gamepad. In one aspect, a user may input an on / off command for the molding defect monitoring function to the determination unit 221 via the input device 410 connected to the input IF 405. In another aspect, the user may select one or more improvements to the molding conditions displayed on the display device 222 or input an instruction to execute the improvements to the determination unit 221 via the input device 410. In this case, the determination unit 221 may output parameters (feedback signals) of the selected improvements to the control unit 260 of the manufacturing apparatus 100. The control unit 260 may adjust the molding conditions based on the parameters (feedback signals). In one aspect, the input IF 405 may be implemented by a USB terminal, a PS / 2 terminal, a Bluetooth (registered trademark) module, or the like.

[0045] Output IF 406 may be connected to any output device such as a cathode ray tube display, a liquid crystal display, or an organic electroluminescence (EL) display. Output IF 406 is connected to display device 222. Output IF 406 outputs information including the presence or absence of a molding defect, the cause of the molding defect, and some or all of the remedial measures for the molding defect to display device 222. In one aspect, output IF 406 may be implemented by a USB terminal, a D-sub terminal, a DVI (Digital Visual Interface) terminal, an HDMI (registered trademark) (High-Definition Multimedia Interface) terminal, or the like. In one aspect, when display device 222 is a PC or the like, determination unit 221 may be connected to display device 222 via external device IF 404 or communication IF 407.

[0046] The communication IF407 is connected to a wired or wireless network device. The communication IF407 can be connected to an external learning device 420 and an inference device 430. In a certain aspect, the communication IF407 may be implemented by a wired LAN (Local Area Network) port, a Wi-Fi (registered trademark) (Wireless Fidelity) module, etc. In other aspects, the communication IF407 may transmit and receive data using communication protocols such as TCP / IP (Transmission Control Protocol / Internet Protocol) and UDP (User Datagram Protocol).

[0047] The learning device 420 takes in the output values of each pre-prepared sensor and the determination result of molding defects as learning data, and generates a learned model for determining molding defects by machine learning. In a certain aspect, the determination unit 221 may transmit the determination result of molding defects to the learning device 420 as learning data via the communication IF407.

[0048] The inference device 430 outputs the presence or absence of molding defects, the causes of molding defects, and improvement measures for molding defects based on the output values of each sensor obtained from the determination unit 221 using the learned model. In this case, the determination unit 221 may receive the presence or absence of molding defects, the causes of molding defects, and improvement measures for molding defects from the inference device 430 via the communication IF407, and display this information on the display device 222. In a certain aspect, the determination unit 221 may transfer the signal obtained from the amplifier 220 to the inference device 430 instead of analyzing it by itself, and receive the presence or absence of molding defects, the causes of molding defects, and improvement measures for molding defects from the inference device 430. In other aspects, the determination unit 221 may output the presence or absence of molding defects, the causes of molding defects, and improvement measures for molding defects using the learned model received from the learning device 420.

[0049] <C.Molding Defect Determination Method> Next, the procedure for determining the presence or absence of molding defects using each sensor and for identifying the causes of the molding defect determination will be described.

[0050] (a. Types of molding defects) First, we will explain the types of molding defects detected by the manufacturing apparatus 100. The main molding defects detected by the manufacturing apparatus 100 are short shots, sink marks, and burrs.

[0051] A short shot is a phenomenon in which resin is not filled in a part of the product, resulting in a chipped part of the molded product. A sink mark is a phenomenon in which the surface of a molded product becomes indented due to resin shrinkage, resulting in a poor appearance. A flash is a phenomenon in which resin leaks from gaps in the parting surfaces of the mold (the mating surfaces of the movable mold 104 and the fixed mold 105), and the leaked resin solidifies, resulting in a poor appearance of the molded product. To detect the presence or absence of these molding defects, the manufacturing apparatus 100 uses the output values ​​of pressure sensors 207 installed at least in two locations: near the gate (or near the sprue 203 or runner) and near the end of the molded product.

[0052] (b. Detection of short shots and sink marks) 5 is a diagram showing an example of a waveform of pressure measured by the pressure sensor 207. Graph 500 shows the change in pressure inside the mold 103 measured by the pressure sensor 207. According to graph 500, the pressure inside the mold 103 gradually increases and reaches a peak pressure. Thereafter, the pressure inside the mold gradually decreases. This is because the pressure inside the mold 103 increases as the mold 103 is filled with resin, and then decreases as the mold 103 opens.

[0053] Short shots and sink marks occur when insufficient pressure is transmitted to the resin filling the mold 103, causing the resin to harden before reaching the end of the molded product, leaving part of the molded product unfilled. Therefore, when short shots or sink marks occur, the pressure inside the mold 103 decreases. Therefore, the determination unit 221 is configured to be able to set a pressure value P1 that serves as a predetermined lower threshold (lower limit reference) for detecting short shots and sink marks. The determination unit 221 can detect short shots and sink marks based on whether the pressure inside the mold 103 falls below the pressure value P1. This is because when the pressure inside the mold 103 falls below the pressure value P1, it means that sufficient pressure is not being transmitted to the resin.

[0054] It should be noted that a common pressure value P1 may be used for detecting short shots and sink marks. However, there may be cases where separate predetermined lower thresholds (lower limit references) are required for detecting short shots and sink marks. In this case, the determination unit 221 may be configured to be able to set, for example, a pressure value P1(X) that serves as the predetermined lower limit threshold (lower limit reference) for short shots and a pressure value P1(Y) that serves as the predetermined lower limit threshold (lower limit reference) for sink marks.

[0055] Furthermore, the pressure value P1 can be set separately for each of the pressure sensors 207 disposed near the gate and near the end of the molded product portion. Hereinafter, the pressure sensor 207 disposed near the gate will be referred to as the first pressure sensor, and the pressure sensor 207 disposed near the end of the molded product portion will be referred to as the second pressure sensor. Furthermore, the predetermined lower threshold value (lower limit reference) corresponding to the first pressure sensor will be referred to as the first pressure value P1A. Furthermore, the predetermined lower threshold value (lower limit reference) corresponding to the second pressure sensor will be referred to as the second pressure value P1B.

[0056] When separate predetermined lower thresholds (lower limit standards) are required for detecting short shots and sink marks, the first pressure value P1A is divided into a first pressure value P1A(X) for short shots and a first pressure value P1A(Y) for sink marks. Similarly, the second pressure value P1B is divided into a second pressure value P1B(X) for short shots and a second pressure value P1B(Y) for sink marks. Hereinafter, an example will be described in which the same first pressure value P1A and second pressure value P1B can be used for detecting short shots and sink marks.

[0057] The determination unit 221 determines whether the output value of the first pressure sensor near the gate is below a first pressure value P1A, and determines whether the output value of the second pressure sensor near the end of the molded product is below a second pressure value P1B. Based on a combination of the determination results of the output value of the first pressure sensor and the determination results of the output value of the second pressure sensor, the determination unit 221 can not only detect molding defects (short shots or sink marks), but also narrow down the causes of the molding defects. Narrowing down the causes of molding defects will be described later.

[0058] (c. Checking for burrs) Burrs are generated when excessive pressure is applied to the resin filled in the mold 103, causing the resin to leak from the gap between the movable mold 104 and the fixed mold 105. Therefore, when burrs occur, the pressure inside the mold 103 increases. Therefore, the determination unit 221 is configured to be able to set a pressure value P2 that serves as a predetermined upper limit threshold (upper limit reference) for detecting burrs. The determination unit 221 can detect burrs based on whether the pressure inside the mold 103 exceeds the pressure value P2. This is because when the pressure inside the mold 103 exceeds the pressure value P2, excessive pressure is being applied to the resin.

[0059] Like pressure value P1, pressure value P2 can be set individually for the first and second pressure sensors located near the gate and near the end of the molded product. Hereinafter, the predetermined upper threshold (upper limit reference) corresponding to the first pressure sensor will be referred to as the first pressure value P2A. Also, the predetermined threshold (lower limit reference) corresponding to the second pressure sensor will be referred to as the second pressure value P2B.

[0060] The determination unit 221 determines whether the output value of the first pressure sensor near the gate exceeds a first pressure value P2A, and determines whether the output value of the second pressure sensor near the end of the molded product portion exceeds a second pressure value P2B. Based on a combination of the determination results of the output values ​​of the first pressure sensor and the second pressure sensor, the determination unit 221 can not only detect molding defects (burrs), but also narrow down the causes of the molding defects.

[0061] (d. Narrowing down the causes of molding defects) As described above, the determination unit 221 determines whether the output value of the first pressure sensor near the gate is within the range (first range) between the first pressure value P1A and the first pressure value P2A. Similarly, the determination unit 221 determines whether the output value of the second pressure sensor near the end of the molded product portion is within the range (second range) between the second pressure value P1B and the second pressure value P2B. The determination unit 221 can narrow down the causes of molding defects based on a combination of the determination results of the output value of the first pressure sensor and the output value of the second pressure sensor.

[0062] (Pattern 1) Output value of the first pressure sensor = within the first range (within the reference range) Output value of the second pressure sensor = Within the second range (within the standard) In the case of pattern 1, the pressure applied to the resin is normal both near the gate and near the end of the molded product, and no molding defects occur. Pattern 1 refers to a state in which the output value of pressure sensor 207 is within the range from pressure value P1 to pressure value P2, as in the example of Figure 5.

[0063] (Pattern 2) Output value of the first pressure sensor = within the first range (within the reference range) Output value of the second pressure sensor = Second out of range (out of standard) (When the output value of the second pressure sensor is lower than the second range (reference)) While sufficient pressure is being applied to the resin near the gate, the pressure is not reaching the resin at the end of the molded product. In other words, it is assumed that a larger-than-expected pressure drop is occurring during the resin filling process. In this case, the likely cause is low resin or mold temperature. (When the output value of the second pressure sensor is higher than the second range (reference)) If the output value of the second pressure sensor is higher than the second range (reference), excessive pressure is being applied to the resin at the end of the molded product. In other words, it is assumed that the resin temperature or mold temperature has become higher than expected, which has improved the resin's fluidity during the resin filling process.

[0064] (Pattern 3) Output value of the first pressure sensor = Within the first range (outside the standard) Output value of the second pressure sensor = Outside the second range (within the standard) (When the output value of the first pressure sensor is lower than the first range (reference)) As in the case where the output value of the second pressure sensor is higher than the second range (standard), it is assumed that the resin temperature or mold temperature in part of the mold became higher than expected, causing the pressure near the end of the molded product to fall within the standard range despite the pressure near the gate being low. (When the output value of the first pressure sensor is higher than the first range (reference)) It is assumed that excessive pressure is occurring near the gate, to the point that flash is occurring, while the pressure drop near the end of the molded product is large. In this case, it is necessary to reduce the pressure near the gate and suppress the pressure drop during the resin filling process.

[0065] (Pattern 4) Output value of the first pressure sensor = Within the first range (outside the standard) Output value of the second pressure sensor = Second out of range (out of standard) (When the output values ​​of the first and second pressure sensors are lower than the first and second ranges (reference values), respectively) The pressure is too low both near the gate and near the end of the molded part, so it is necessary to adjust the injection speed, resin temperature, and / or mold temperature to increase the pressure on the resin and prevent pressure drop. (When the output values ​​of the first and second pressure sensors are higher than the first and second ranges (reference values), respectively) The pressure is too high both near the gate and near the end of the molded part, so you need to adjust the injection speed, resin temperature, and / or mold temperature to reduce the pressure on the resin.

[0066] As described above, the determination unit 221 can narrow down the causes of molding defects based on a combination of the determination results of the output value of the first pressure sensor and the determination results of the output value of the second pressure sensor. Furthermore, the determination unit 221 can determine whether the output value of an arbitrary temperature sensor is within a reference range, and can identify or narrow down in detail the causes of molding defects based on a combination of the determination results of the arbitrary temperature sensors.

[0067] (e. Identifying or narrowing down the cause of molding defects) The determination unit 221 identifies or narrows down the cause of molding defects based on the determination results of the output values ​​of each temperature sensor. More specifically, the determination unit 221 determines whether the mold temperature sensor 208 (first mold temperature sensor) near the gate has a value within a predetermined third range. The determination unit 221 also determines whether the mold temperature sensor 208 (second mold temperature sensor) near the end of the molded product has a value within a predetermined fourth range. The determination unit 221 also determines whether the resin temperature sensor 209 (first resin temperature sensor) near the gate has a value within a predetermined fifth range. The determination unit 221 also determines whether the resin temperature sensor 209 (second resin temperature sensor) near the end of the molded product has a value within a predetermined sixth range. The judgment unit 221 can identify or narrow down the cause of molding defects based on a combination of some or all of the judgment results of the output value of the first mold temperature sensor, the judgment results of the output value of the second mold temperature sensor, the judgment results of the output value of the first resin temperature sensor, and the judgment results of the output value of the second resin temperature sensor.

[0068] As an example, the judgment unit 221 can identify or further narrow down the cause of the molding defect based on a combination of the judgment results of the mold temperatures near the gate and near the end of the molded product portion, a combination of the judgment results of the resin temperatures near the gate and near the end of the molded product portion, a combination of the judgment results of the mold temperature near the gate and the resin temperature near the gate, a combination of the judgment results of the mold temperature near the end of the molded product portion and the mold temperature near the end of the molded product portion, or a combination of these. An example of identifying or narrowing down the cause of the molding defect will be described below.

[0069] (e1: Combination of the mold temperature sensor and resin temperature sensor judgment results) As a first example, we will explain how to identify or narrow down the cause of molding defects based on a combination of the results of determining whether the output value of mold temperature sensor 208 is within a reference range and the results of determining whether the output value of resin temperature sensor 209 is within a reference range. Determination unit 221 can make the following combinations of determinations both near the gate and near the end of the molded product. Note that the determination of whether the output value of each sensor is within the reference range may also be made based on whether the output value of each sensor exceeds the upper reference value of each sensor and whether the output value of each sensor is below the lower reference value of each sensor.

[0070] (Pattern 1) Mold temperature sensor 208 output value: Within range (within standard) Resin temperature sensor 209 output value: Within range (within standard) In this case, there is no problem with either the mold 103 or the resin. If there is an abnormality in the output value of any of the pressure sensors 207 in this state, the determination unit 221 may determine, for example, that there is a problem with the resin injection speed. In this case, the determination unit 221 outputs information to the display device 222 including the estimated cause and a solution such as a parameter for the resin injection speed or an instruction to change the injection speed.

[0071] (Pattern 2) Mold temperature sensor: Within range (within standard) Resin temperature sensor: Out of range (out of standard) In this case, the determination unit 221 determines that there is a problem with the resin temperature. Therefore, for example, the determination unit 221 outputs information including the estimated cause (resin temperature) and solutions such as adjustment parameters for the resin temperature and instructions to change the resin temperature to the display device 222. For example, the solutions may include instructions to adjust the temperature of the heater of the cylinder 102 and the temperature to be set.

[0072] (Pattern 3) Mold temperature sensor: Out of range (out of standard) Resin temperature sensor: Within range (within standard) In this case, the determination unit 221 determines that there is a problem with the mold temperature. Therefore, for example, the determination unit 221 outputs information including the estimated cause (resin temperature) and solutions such as resin temperature adjustment parameters and instructions to change the resin temperature to the display device 222. For example, the solutions may include instructions to adjust the temperature of the heater and / or cooling device of the mold 103, the temperature to be set, etc.

[0073] (Pattern 4) Mold temperature sensor: Out of range (out of standard) Resin temperature sensor: Out of range (out of standard) In this case, the determination unit 221 determines that there is a problem with the mold temperature and resin temperature. Therefore, for example, the determination unit 221 outputs information including the estimated cause (mold temperature and resin temperature) and solutions such as instructions to change the adjustment parameters for the mold temperature and resin temperature and the resin temperature to the display device 222. For example, the solutions may include instructions to adjust the temperature of the heater of the cylinder 102 and the temperature to be set, and instructions to adjust the temperature of the heater and / or cooling device of the mold 103 and the temperature to be set, etc.

[0074] Note that the determination unit 221 may also determine whether or not there is a problem with the resin injection speed based on how much each sensor deviates from its reference range, even in the cases of patterns 2 to 4. When the determination unit 221 determines that there is a problem with the resin injection speed, the information output to the display device 222 may include information indicating that there is a problem with the resin injection speed, and information such as parameters for the resin injection speed and instructions to change the injection speed.

[0075] Because the resin and the mold come into contact during the resin molding process, the resin temperature and the mold temperature are proportional to each other. However, the effects of the resin temperature on the mold and the mold temperature on the resin vary depending on various factors, such as the type of resin and the shape of the mold. Therefore, it is difficult to determine the cause of a molding defect (whether the problem is with the mold temperature or the resin temperature) using only either the mold temperature sensor 208 or the resin temperature sensor 209. By providing both the mold temperature sensor 208 and the resin temperature sensor 209, the determination unit 221 can estimate or identify the cause of a molding defect based on a combination of the determination results of whether the output values ​​of each sensor are within a reference range.

[0076] (e2: Combination of the judgment results of the sensors near the gate and the end of the molded product) As a second example, we will explain how to identify or narrow down the cause of molding defects based on a combination of the judgment result of whether the output value of the first mold temperature sensor is within the third reference range and the judgment result of whether the output value of the second mold temperature sensor is within the fourth reference range, and a combination of the judgment result of whether the output value of the first resin temperature sensor is within the fifth reference range and the judgment result of whether the output value of the second resin temperature sensor is within the sixth reference range.

[0077] When temperature sensors (mold temperature sensor 208 and resin temperature sensor 209) are located both near the gate and near the end of the molded product, judgment unit 221 can determine whether the temperature abnormality is occurring throughout the entire mold 103 or in only a part of the mold 103. Hereinafter, mold temperature sensor 208 and resin temperature sensor 209 will be collectively referred to as temperature sensors.

[0078] For example, suppose that the output value of the temperature sensor near the gate and the output value of the temperature sensor near the end of the molding section are both outside their reference ranges. In this case, the cause may lie in either the resin temperature or the mold temperature. Therefore, the determination unit 221 can identify or narrow down the cause of the molding defect based on whether the output values ​​of the mold temperature sensor 208 and the resin temperature sensor 209, which are installed near the gate and the end of the molding section, are within their respective reference ranges.

[0079] For example, suppose the output value of a temperature sensor near the gate is within a reference range, but the output value of a temperature sensor near the end of the molding section is outside the reference range. In this case, since the possibility of such an abnormal temperature distribution occurring in the resin temperature is low, it is more likely that there is a problem with the mold temperature. Therefore, the judgment unit 221 can identify or narrow down the cause of molding defects based on whether the output values ​​of the mold temperature sensors 208 installed near the gate and near the end of the molding section are within their respective reference ranges.

[0080] The determination unit 221 can acquire information on the temperature distribution of the resin and the temperature distribution of the mold by referring to the output values ​​of each sensor provided at multiple locations on the mold 103. Based on the information on the temperature distribution of the resin and the temperature distribution of the mold, the determination unit 221 can generate instruction information for a solution, such as adjusting the temperature of a heater at an arbitrary location on the mold 103, and parameters therefor, and output the generated information to the display device 222.

[0081] In the above example, the determination unit 221 identifies the cause of molding defects based on the output values ​​of sensors installed near the gate and near the end of the molded product and the determination results of whether the output values ​​are within the reference range. However, application examples of the technology disclosed herein are not limited to this. In some aspects, the determination unit 221 may identify the cause of molding defects based on the output values ​​of sensors installed in three or more locations and the determination results of whether the output values ​​of each sensor are within the reference range of each sensor. The mold 103 may be equipped with multiple temperature adjustment units such as heaters. The determination unit 221 can adjust the temperatures of only some of the temperature adjustment units by obtaining temperature distribution information of the mold 103.

[0082] Furthermore, in the above example, the determination unit 221 uses the peak value of the pressure value as an indicator for detecting the occurrence of a molding defect, but application examples of the technology of the present disclosure are not limited to this. In certain aspects, the determination unit 221 may use an integral value obtained by time integration of the pressure value generated during molding as an indicator for detecting the occurrence of a molding defect. Similarly, the determination unit 221 may use the mold temperature and resin temperature at the time when the peak value of the pressure value is measured as indicators. Furthermore, the determination unit 221 may use an integral value obtained by time integration of the mold temperature generated during molding and an integral value obtained by time integration of the resin temperature as indicators for detecting the occurrence of a molding defect.

[0083] In another aspect, the determination unit 221 may receive the threshold value of each sensor in advance via the input IF 405 or the communication IF 407. The determination unit 221 stores the threshold value of each sensor in the storage 403. The processor 401 may refer to the threshold value of each sensor read from the storage 403 to the memory 402.

[0084] <D.フローチャート> 6 is a diagram showing an example of a procedure of determination unit 221. In one aspect, processor 401 may load a program for performing the processing of FIG. 6 from storage 403 into memory 402 and execute the program. In another aspect, some or all of the processing may be realized as a combination of circuit elements configured to perform the processing.

[0085] In step S605, the determination unit 221 acquires the output value of the pressure sensor 207 near the gate. In step S610, the determination unit 221 acquires the output value of the pressure sensor 207 near the end of the molded product portion.

[0086] In step S615, determination unit 221 compares the pressure values ​​detected near the gate and near the end of the molded product portion with the reference pressure values ​​for each location. The processing in this step corresponds to the processing described with reference to Figure 5, in which the output value of the first pressure sensor near the gate is determined to be within the range (first range) between first pressure value P1A and first pressure value P2A, and the processing in which the output value of the second pressure sensor near the end of the molded product portion is determined to be within the range (second range) between second pressure value P1B and second pressure value P2B.

[0087] In step S620, determination unit 221 determines whether the pressure values ​​are normal. As an example, determination unit 221 determines whether the output value of the first pressure sensor is within a first range (within a reference range) and whether the output value of the second pressure sensor is within a second range (within a reference range). If determination unit 221 determines that the pressure values ​​are normal (YES in step S620), it completes the process. That is, determination unit 221 determines that no molding defect has occurred and does not execute the response process when a molding defect occurs. If not (NO in step S620), determination unit 221 transfers control to step S625.

[0088] In step S625, the determination unit 221 determines that the molded product has an abnormality (molding defect). In one aspect, in addition to detecting the molding defect, the determination unit 221 may narrow down potential causes of the molding defect based on a combination of the determination results of the output value of the first pressure sensor and the determination results of the output value of the second pressure sensor. In this case, the determination unit 221 may perform the processes from step S635 onwards in an order that prioritizes investigation of factors that are likely to be the cause of the molding defect. For example, if there is a high possibility that there is an abnormality in the resin temperature, the determination unit 221 may prioritize execution of the processes of steps S650 to S670 over the processes of steps S630 to S645. In another aspect, the determination unit 221 may detect the presence or absence of a molding defect and narrow down potential causes of the molding defect based on a combination of determination results of the output values ​​of the pressure sensors 207 at three or more locations.

[0089] In step S630, the determination unit 221 acquires the output value of the mold temperature sensor 208 near the gate. In step S635, the determination unit 221 acquires the output value of the mold temperature sensor 208 near the end of the molded product portion.

[0090] In step S640, the determination unit 221 determines whether the mold temperature is normal. The processing in this step corresponds to the processing described with reference to FIG. 5 for determining whether the output value of the first mold temperature sensor near the gate is within a predetermined third range and the processing for determining whether the output value of the second mold temperature sensor near the end of the molded product portion is within a predetermined fourth range. If the determination unit 221 determines that the mold temperature is normal (YES in step S640), it transfers control to step S650. If not (NO in step S640), the determination unit 221 transfers control to step S645.

[0091] In step S645, the determination unit 221 adjusts the mold temperature. In one aspect, the determination unit 221 may output the mold temperature adjustment instruction and parameters to the display device 222. In this case, the user can manually adjust (improve) the molding conditions by referring to the screen of the display device 222. In another aspect, the determination unit 221 may output the mold temperature adjustment instruction and parameters to the control unit 260 of the manufacturing apparatus 100 as a feedback signal. In this case, the manufacturing apparatus 100 can automatically adjust (improve) the molding conditions based on the feedback signal.

[0092] In step S650, the determination unit 221 acquires the output value of the resin temperature sensor 209 near the gate. In step S655, the determination unit 221 acquires the output value of the resin temperature sensor 209 near the end of the molded product portion.

[0093] In step S660, the determination unit 221 determines whether the resin temperature is normal. The processing in this step corresponds to the processing described with reference to FIG. 5 for determining whether the output value of the first resin temperature sensor near the gate is within a predetermined fifth range and the processing for determining whether the output value of the second resin temperature sensor near the end of the molded product portion is within a predetermined sixth range. If the determination unit 221 determines that the resin temperature is normal (YES in step S660), it transfers control to step S670. If not (NO in step S660), the determination unit 221 transfers control to step S665.

[0094] In step S665, the determination unit 221 adjusts the resin temperature. In one aspect, the determination unit 221 may output the resin temperature adjustment instruction and parameters to the display device 222. In this case, the user may manually adjust (improve) the molding conditions by referring to the screen of the display device 222. In another aspect, the determination unit 221 may output the resin temperature adjustment instruction and parameters to the control unit 260 of the manufacturing apparatus 100 as a feedback signal. In this case, the manufacturing apparatus 100 may automatically adjust (improve) the molding conditions based on the feedback signal.

[0095] In step S670, the determination unit 221 calculates the resin filling time from the difference in the time it takes for the pressure to reach its peak near the gate and near the end of the molded product. In step S675, the determination unit 221 adjusts the resin injection speed based on the resin filling time calculated in step S675. As an example, the determination unit 221 may adjust the resin injection speed when the pressure value is outside the normal range even though both the mold temperature and resin temperature are within the normal range.

[0096] In step S680, determination unit 221 checks the operation after the molding conditions have been adjusted. In one aspect, determination unit 221 may check the operation after the molding conditions have been adjusted by repeating the processes of steps S605 to S680.

[0097] The above flowchart is an example of the internal processing of the determination unit 221, and the processing procedure of the determination unit 221 is not limited to this. In a certain aspect, the execution order of each step may be changed as necessary. Also, in other aspects, the determination unit 221 may not execute some of the processes from step S605 to S680. For example, when the determination unit 221 determines from the determination result of the pressure value that there is a problem with the mold temperature, it may not execute the acquisition and adjustment processes of the resin temperature.

[0098] Also, in the above flowchart, the determination unit 221 separately performs the abnormal determination and adjustment process of the mold temperature, the abnormal determination and adjustment process of the resin temperature, and the adjustment process of the injection speed. However, the determination unit 221 may perform these simultaneously. As an example, the determination unit 221 may perform all or part of the adjustment of the mold temperature, the adjustment of the resin temperature, and the adjustment of the injection speed of the resin based on the combination of the determination results of the pressure values near the gate and near the end of the molded product part, the determination results of the mold temperatures near the gate and near the end of the molded product part, and the determination results of the resin temperatures near the gate and near the end of the molded product part. In this case, the determination unit 221 may, as an example, have a table or the like of adjustment parameters for the molding conditions associated with the combination of the determination results of the pressure values near the gate and near the end of the molded product part, the determination results of the mold temperatures near the gate and near the end of the molded product part, and the determination results of the resin temperatures near the gate and near the end of the molded product part. Alternatively, the determination unit 221 may, as an example, have a learned model that analyzes the output values of each sensor and outputs the detection result of molding defects.

[0099] <E. Variations of the manufacturing apparatus> Next, referring to FIGS. 7 and 8, variations of the manufacturing apparatus according to the present embodiment will be described.

[0100] FIG. 7 is a diagram showing a configuration example of a manufacturing apparatus 700 according to the present embodiment. The manufacturing apparatus 700 is different from the manufacturing apparatus 100 in that it includes a mold clamping detection sensor 710.

[0101] The mold 703 includes a movable mold 704 and a fixed mold 705. The movable mold 704 and / or the fixed mold 705 include a mold clamping detection sensor 710. When the mold 703 moves and the movable mold 704 and the fixed mold 705 come into contact with each other, the mold clamping detection sensor 710 outputs a mold clamping detection signal 723, or the mold clamping detection signal 723 changes. The determination unit 721 acquires the mold clamping detection signal 723 directly or via the amplifier 720. By acquiring the mold clamping detection signal 723, the determination unit 721 can easily detect the timing when the mold 703 is clamped. As a result, manufacturing apparatus 700 does not need to perform the molding defect detection process in all states during injection molding, including the injection molding measurement process, mold clamping process, injection process, cooling process, molded product removal process, and mold opening process, but can perform the molding defect detection process for, for example, a fixed time (such as only during the injection process) after obtaining mold clamping detection signal 723. That is, determination unit 721 can take in the output values ​​of the first and second pressure sensors, the first and second mold temperature sensors, and the first and second resin temperature sensors based on mold clamping detection signal 723.

[0102] Furthermore, the manufacturing apparatus 700 can divide the manufacturing process of continuous molded products into shots (one production of molded products) using the mold clamping detection signal 723, and acquire and analyze the output values ​​of each sensor for each shot. This allows the manufacturing apparatus 700 to analyze each shot and analyze differences between shots, etc. The determination unit 721 outputs the detection results of molding defects and various analysis results to the display device 722.

[0103] FIG. 8 is a diagram showing an example of the configuration of a manufacturing apparatus 800 according to this embodiment. The manufacturing apparatus 800 differs from the manufacturing apparatus 100 in that a control unit 860 (or an injection unit) has a function of outputting an injection start signal 824. The control unit 860 (or an injection unit) outputs the injection start signal 824 when resin is injected from the cylinder 102. The determination unit 821 acquires the injection start signal 824 directly or via the amplifier 820. By acquiring the injection start signal 824, the determination unit 821 can easily detect the timing at which the resin is injected. As a result, the manufacturing apparatus 800 does not need to perform molding defect detection processing in all states during injection molding, including the measurement process, mold clamping process, injection process, cooling process, molded product removal process, and mold opening process. For example, the manufacturing apparatus 800 can perform molding defect detection processing only for a certain period of time (such as only during the injection process) after acquiring the injection start signal 824. That is, the determination unit 821 can take in the output values ​​of the first and second pressure sensors, the first and second mold temperature sensors, and the first and second resin temperature sensors based on the injection start signal 824.

[0104] Furthermore, manufacturing apparatus 800 can divide the manufacturing process of continuous molded products into shots (one production of a molded product) using injection start signal 824, and acquire and analyze the output values ​​of each sensor for each shot. This allows manufacturing apparatus 800 to analyze each shot and analyze differences between shots.

[0105] In one aspect, manufacturing apparatus 800 may include a molding machine operation panel 823. A user can input a command to adjust molding conditions to manufacturing apparatus 800 (control unit 860) from molding machine operation panel 823 while referring to the screen of display device 822. Manufacturing apparatuses 100 and 700 may also include a molding machine operation panel.

[0106] In other situations, the determination unit 821 may output a feedback signal 826 including an adjustment command for the molding conditions and parameters therefor to the manufacturing apparatus 800 (control unit 860). In this case, the manufacturing apparatus 800 (control unit 860) can automatically adjust the molding conditions. Similarly, each of the determination units 221 and 721 of the manufacturing apparatuses 100 and 700 may also automatically output a feedback signal 826 including an adjustment command for the molding conditions and parameters therefor to each of the manufacturing apparatuses 100 and 700 (control unit 860).

[0107] Note that the respective configurations and functions of the manufacturing apparatuses 100, 700, and 800 may be used in combination. For example, the manufacturing apparatus according to the present embodiment may include a mold clamping detection sensor 710 and a molding machine operation panel 823, and may have a function of generating and outputting an injection start signal 824 and a feedback signal 826. Further, the manufacturing apparatus according to the present embodiment may implement a part of the functions of the manufacturing apparatuses 100, 700, and 800 using a learning apparatus 420 and an inference apparatus 430.

[0108] <F. Application Using Machine Learning> Next, referring to FIGS. 9 to 13, an example of incorporating machine learning into the manufacturing apparatus according to the present embodiment to detect molding defects and improve molding conditions will be described. Machine learning can be applied to any of the manufacturing apparatuses 100, 700, and 800. In the following description, when collectively referring to the manufacturing apparatuses 100, 700, and 800, they will simply be referred to as the manufacturing apparatus. Also, when collectively referring to the determination units 221, 721, and 821, they will simply be referred to as the determination unit.

[0109] 9 is a diagram showing an example of the configuration of a learning device 420 for generating a model for detecting molding defects in the manufacturing apparatus according to the present embodiment. The learning device 420 mainly includes a data acquisition unit 910, a model generation unit 920, and a trained model storage unit 930. In some aspects, some or all of the data acquisition unit 910, the model generation unit 920, and the trained model storage unit 930 may be realized as programs. In this case, for example, the learning device 420 may include a processor (not shown), a memory (not shown), and a storage (not shown), and may execute the program on these pieces of hardware.

[0110] The data acquisition unit 910 acquires, as learning data, information associating molding conditions, output values ​​of each sensor, and information (solutions) on the occurrence of molding defects. The output values ​​of each sensor refer to the output values ​​of the pressure sensor 207, mold temperature sensor 208, and resin temperature sensor 209 attached to multiple locations on the mold (near the gate, near the end of the molded product, etc.). The occurrence of molding defects also includes the occurrence of short shots, sink marks, and burrs.

[0111] The model generation unit 920 uses the learning data output from the data acquisition unit 910 to determine whether or not a molding defect exists based on the output values ​​of each sensor, estimate (identify) the cause of the molding defect, and learn how to adjust molding conditions when a molding defect occurs. More specifically, the model generation unit 920 learns how to determine whether or not a molding defect such as a short shot, sink mark, or flash has occurred based on a combination of output values ​​from the pressure sensor 207, mold temperature sensor 208, and resin temperature sensor 209 attached to multiple locations on the mold (near the gate, near the end of the molded product, etc.). The model generation unit 920 also learns how to estimate the cause of the molding defect and adjust molding conditions (mold temperature, resin temperature, resin injection speed, etc.) based on a combination of output values ​​from the mold temperature sensor 208 and resin temperature sensor 209.

[0112] In one aspect, a user may input learning data via a medium or a network to learning device 420. In another aspect, learning device 420 may receive, as learning data, data used in determining the presence or absence of a past molding defect from a determination unit via a network.

[0113] In another aspect, learning device 420 may be realized in any form, such as a server, a virtual machine in a cloud environment, a container, an application, etc. In another aspect, learning device 420 may be realized as an integrated unit with a manufacturing device or a determination unit.

[0114] The model generation unit 920 may use any algorithm such as supervised learning, unsupervised learning, reinforcement learning, etc. Upon completion of learning, the model generation unit 920 outputs a trained model and stores the trained model in the trained model storage unit 930.

[0115] Fig. 10 is a flowchart showing an example of the procedure of the learning process by the learning device 420. The procedure of the learning process by the learning device 420 will be described with reference to Fig. 10. In one aspect, the processor of the learning device 420 may read a program for executing the process shown in Fig. 10 from storage onto a memory, and execute the program.

[0116] In step S1010, the learning device 420 acquires learning data. The learning data is, for example, information that associates molding conditions, output values ​​of each sensor, and information (solution) on whether or not a molding defect has occurred. The learning device 420 may input the learning data from a user via a medium or a network, or may receive data used in determining the presence or absence of a molding defect from the manufacturing apparatuses 100, 700, and 800 as learning data.

[0117] In step S1020, the learning device 420 executes a learning process using the learning data by the model generation unit 920. When the learning is completed, the model generation unit 920 outputs the learned model.

[0118] In step S1030, learning device 420 stores the trained model in trained model storage unit 930. In one aspect, when learning device 420 generates a new trained model, it may transmit the trained model to inference device 430. In another aspect, learning device 420 may transmit the trained model to inference device 430 based on receiving a request from inference device 430.

[0119] 11 is a diagram showing an example of the configuration of an inference device 430 for detecting molding defects using a trained model in the molding process of the manufacturing apparatus according to this embodiment. The inference device 430 mainly comprises a data acquisition unit 1110, an inference unit 1120, and a trained model storage unit 1130. In some aspects, some or all of the data acquisition unit 1110, the inference unit 1120, and the trained model storage unit 1130 may be realized as programs. In this case, for example, the inference device 430 may include a processor (not shown), a memory (not shown), and a storage (not shown), and may execute the program on this hardware.

[0120] The data acquisition unit 1110 acquires the output values ​​of each sensor as input for inference. In other words, the data acquisition unit 1110 acquires data similar to the data acquired by the determination unit. The data acquisition unit 1110 may also acquire information on molding conditions from the manufacturing equipment in order to adjust the molding conditions.

[0121] The inference unit 1120 inputs the data transferred from the data acquisition unit 1110 to the trained model generated by the model generation unit 920. The trained model outputs an inference result based on the input data. The inference result may be a determination result of whether or not there is a molding defect, an estimation result of the cause of the molding defect, adjustment information for molding conditions, etc. The inference unit 1120 outputs the inference result to the determination unit.

[0122] 5 and other figures, the determination unit compares the output value of each sensor with a threshold value, but the inference unit 1120 uses the output value of each sensor as an input to the trained model. Therefore, if the determination unit has an inference device 430 built in or requests an external inference device 430 to perform the determination process, the determination unit does not need to store various threshold values.

[0123] The trained model storage unit 1130 stores the trained model. In one aspect, the inference device 430 may periodically or irregularly receive the trained model from the learning device 420 and store the trained model in the trained model storage unit 1130. In another aspect, the trained model storage unit 1130 may be the same storage unit as the trained model storage unit 930.

[0124] In one aspect, learning device 420 and inference device 430 may be the same device. In another aspect, inference device 430 may be implemented in any form, such as a server, a virtual machine in a cloud environment, a container, or an application. In another aspect, inference device 430 may be implemented as an integrated unit with a manufacturing device or a determination unit.

[0125] Fig. 12 is a flowchart showing an example of the procedure of inference processing by inference device 430. The procedure of inference processing by inference device 430 will be described with reference to Fig. 12. In one aspect, the processor of inference device 430 may read a program for executing the processing shown in Fig. 12 from storage onto a memory, and execute the program.

[0126] In step S1210, inference device 430 acquires information used to detect molding defects and identify the causes of the molding defects. This information is the same as the information used by the determination unit to detect molding defects and identify the causes of the molding defects. In one aspect, inference device 430 may acquire information (output values ​​of each sensor provided in the manufacturing apparatus) directly or via an amplifier. In another aspect, inference device 430 may acquire information (output values ​​of each sensor provided in the manufacturing apparatus) from the determination unit.

[0127] In step S1220, the inference device 430 inputs information used to detect molding defects and identify the causes of molding defects into the trained model.

[0128] In step S1230, inference device 430 outputs data (inference results). The data (inference results) may include the results of detecting molding defects, the results of identifying the causes of molding defects, parameters for improving molding conditions, and the like.

[0129] In step S1240, inference device 430 detects the occurrence of a molding defect by referring to the inference result. In one aspect, inference device 430 may transmit the inference result to the determination unit. In another aspect, inference device 430 may transmit a notification of the occurrence of a molding defect to the determination unit by referring to the inference result. Note that the determination unit may have the functionality of the inference device. In this case, the determination unit executes the processing procedure shown in FIG. 12 by using a trained model instead of making a determination using a threshold value.

[0130] FIG. 13 is a diagram showing an example of a neural network model used by the learning device 420. The neural network model is used for supervised learning. Supervised learning is a technique in which a learning device is provided with a set of input and result (label) data, and the device learns the features of the learning data and infers the result from the input. Note that the learning device 420 may perform learning using any technique other than a neural network.

[0131] A neural network consists of an input layer consisting of multiple neurons, an intermediate layer (hidden layer) consisting of multiple neurons, and an output layer consisting of multiple neurons. The intermediate layer may be one layer, or two or more layers.

[0132] For example, in a three-layer neural network as shown in FIG. 13, when multiple inputs are input as training data to the input layer (X1-X3), the values ​​of the training data are multiplied by weight W1 (w11-w16) and input to the intermediate layer (Y1-Y2), and the result is further multiplied by weight W2 (w21-w26) and output from the output layer (Z1-Z3). This output result varies depending on the values ​​of weights W1 and W2. The learning device 420 according to this embodiment inputs molding conditions, output values ​​of each sensor, etc. to the neural network as training data and repeatedly executes the learning process.

[0133] As described above, the manufacturing apparatus according to this embodiment can detect the presence or absence of molding defects in the resin molded product by analyzing the output values ​​of various sensors (pressure sensor, mold temperature sensor, resin temperature sensor) provided at least near the gate and near the end of the molded product portion.

[0134] Furthermore, the manufacturing device according to this embodiment can identify or narrow down the cause of molding defects by analyzing the output values ​​of various sensors (pressure sensor, mold temperature sensor, resin temperature sensor) installed at least near the gate and near the end of the molded product portion, and can generate and output instructions for improving molding conditions and parameters for that purpose.In addition, the technology disclosed herein can be applied to, for example, metal casting using a mold by die casting.

[0135] The embodiments disclosed herein should be considered to be illustrative in all respects and not restrictive. The scope of the present disclosure is defined by the claims, not by the above description, and is intended to include all modifications within the meaning and scope equivalent to the claims. Furthermore, the disclosures described in the embodiments and each modification are intended to be implemented, as far as possible, either alone or in combination. [Explanation of symbols]

[0136] 100,700,800 Manufacturing equipment, 101 Hopper, 102 Cylinder, 103,703 Mold, 104,704 Movable side mold, 105,705 Fixed side mold, 110 Injection unit, 111,112 Motor, 203 Sprue, 205 Cavity, 206 Ejector pin, 207 Pressure sensor, 208 Mold temperature sensor, 209 Resin temperature sensor, 214 Heater, 216 Screw, 220,720,820 Amplifier, 221,721,821 Judgment unit, 222,722,822 Display device, 260,860 Control unit, 303 Ejector plate, 401 Processor, 402 Memory, 403 Storage, 404 External device IF, 405 Input IF, 406 Output IF, 407 Communication IF, 408 bus, s420 learning device, 430 inference device, 500 graph, 710 mold clamping detection sensor, 723 mold clamping detection signal, 823 molding machine operation panel, 824 injection start signal, 826 feedback signal, 910, 1110 data acquisition unit, 920 model generation unit, 930, 1130 learned model memory unit, 1120 inference unit.

Claims

1. A mold for pouring resin, first and second pressure sensors; first and second mold temperature sensors; first and second resin temperature sensors; the first pressure sensor, the first mold temperature sensor, and the first resin temperature sensor are provided near a gate of the mold, the second pressure sensor, the second mold temperature sensor, and the second resin temperature sensor are provided near an end of a molded product portion in the cavity, a determination unit that detects a molding defect of the resin and determines the cause of the molding defect based on the output values ​​of the first and second pressure sensors, the output values ​​of the first and second mold temperature sensors, and the output values ​​of the first and second resin temperature sensors; Detecting a molding defect of the resin and determining the cause thereof based on the output values ​​of the first and second pressure sensors, the output values ​​of the first and second mold temperature sensors, and the output values ​​of the first and second resin temperature sensors, Determining whether an output value of the first pressure sensor is within a predetermined first range and whether an output value of the second pressure sensor is within a predetermined second range; and detecting molding defects based on a combination of a determination result of the output value of the first pressure sensor and a determination result of the output value of the second pressure sensor.

2. A mold for pouring resin; first and second pressure sensors; first and second mold temperature sensors; first and second resin temperature sensors; the first pressure sensor, the first mold temperature sensor, and the first resin temperature sensor are provided near a gate of the mold, the second pressure sensor, the second mold temperature sensor, and the second resin temperature sensor are provided near an end of a molded product portion in the cavity, a determination unit that detects a molding defect of the resin and determines the cause of the molding defect based on the output values ​​of the first and second pressure sensors, the output values ​​of the first and second mold temperature sensors, and the output values ​​of the first and second resin temperature sensors; The judgment unit outputs a feedback signal to a resin molding control device of the manufacturing device to adjust at least one parameter of the mold temperature, the resin temperature, and the resin injection speed based on a combination of judgment results of the output values ​​of the first and second mold temperature sensors and a combination of judgment results of the output values ​​of the first and second resin temperature sensors.

3. The determination unit determining whether the output value of the first mold temperature sensor is within a predetermined third range and whether the output value of the second mold temperature sensor is within a predetermined fourth range; determining whether the output value of the first resin temperature sensor is within a predetermined fifth range and whether the output value of the second resin temperature sensor is within a predetermined sixth range; 2. The apparatus for manufacturing a resin molded product according to claim 1, wherein the cause of a molding defect is identified based on the determination result of the output value of the first mold temperature sensor, the determination result of the output value of the second mold temperature sensor, the determination result of the output value of the first resin temperature sensor, and the determination result of the output value of the second resin temperature sensor.

4. a display unit that outputs the detection result of the resin molding defect and the cause thereof; The manufacturing device for resin molded products according to any one of claims 1 to 3, wherein the judgment unit outputs to the display unit information for adjusting at least one parameter of the mold temperature, the resin temperature, and the resin injection speed based on a combination of judgment results of the output values ​​of the first and second mold temperature sensors and a combination of judgment results of the output values ​​of the first and second resin temperature sensors.

5. Further provided with a mold clamping detection sensor, The determination unit Referring to the mold clamping detection signal of the mold clamping detection sensor, The manufacturing apparatus according to any one of claims 1 to 3, wherein output values ​​of the first and second pressure sensors, the first and second mold temperature sensors, and the first and second resin temperature sensors are taken in based on the mold clamping detection signal.

6. Further comprising an injection device for the resin, The determination unit Refer to the injection start signal of the injection device, 2. The manufacturing apparatus according to claim 1, wherein output values ​​of the first and second pressure sensors, the first and second mold temperature sensors, and the first and second resin temperature sensors are acquired based on the injection start signal.

7. A method for detecting molding defects in a manufacturing apparatus for resin molded products, comprising: acquiring output values ​​from a first pressure sensor, a first mold temperature sensor, and a first resin temperature sensor provided near a gate of a mold of the manufacturing apparatus; acquiring output values ​​from a second pressure sensor, a second mold temperature sensor, and a second resin temperature sensor provided near an end of a molded product portion in a cavity of the mold; detecting molding defects in the resin molded product and determining the cause thereof based on output values ​​of the first and second pressure sensors, output values ​​of the first and second mold temperature sensors, and output values ​​of the first and second resin temperature sensors; The step of detecting molding defects in the resin molded product and determining the cause thereof based on the output values ​​of the first and second pressure sensors, the output values ​​of the first and second mold temperature sensors, and the output values ​​of the first and second resin temperature sensors includes: determining whether an output value of the first pressure sensor is within a predetermined first range and whether an output value of the second pressure sensor is within a predetermined second range; The method includes a step of detecting molding defects in the resin molded product and determining the cause thereof based on a combination of the determination results of the output value of the first pressure sensor and the determination results of the output value of the second pressure sensor.

8. A method for detecting molding defects in a manufacturing device for resin molded products, comprising: acquiring output values ​​from a first pressure sensor, a first mold temperature sensor, and a first resin temperature sensor provided near a gate of a mold of the manufacturing apparatus; acquiring output values ​​from a second pressure sensor, a second mold temperature sensor, and a second resin temperature sensor provided near an end of a molded product portion in a cavity of the mold; detecting a molding defect in the resin molded product and determining the cause thereof based on the output values ​​of the first and second pressure sensors, the output values ​​of the first and second mold temperature sensors, and the output values ​​of the first and second resin temperature sensors; and outputting a feedback signal to a resin molding control device of the manufacturing apparatus for adjusting at least one parameter of the mold temperature, the resin temperature, or the resin injection speed based on a combination of the determination results of the output values ​​of the first and second mold temperature sensors and a combination of the determination results of the output values ​​of the first and second resin temperature sensors.

9. a data acquisition unit that acquires, as learning data, output values ​​of a first pressure sensor, a first mold temperature sensor, and a first resin temperature sensor provided near the gate of a mold of a manufacturing device for resin molded products, output values ​​of a second pressure sensor, a second mold temperature sensor, and a second resin temperature sensor provided near the end of a molded product portion in a cavity of the mold, and a judgment result of molding defects of the resin molded product; a model generation unit that uses the learning data to determine whether the output value of the first pressure sensor is within a predetermined first range and whether the output value of the second pressure sensor is within a predetermined second range, and generates a trained model for inferring the molding conditions of the resin molded product and the presence or absence of molding defects based on a combination of the determination results of the output value of the first pressure sensor and the determination results of the output value of the second pressure sensor.

10. a data acquisition unit that acquires, as input data from the manufacturing device, output values ​​of the first pressure sensor, the first mold temperature sensor, and the first resin temperature sensor that are provided near the gate of the mold, and output values ​​of the second pressure sensor, the second mold temperature sensor, and the second resin temperature sensor that are provided near an end of a molded product portion in the cavity of the mold; An inference device comprising: an inference unit that inputs the input data into the trained model described in claim 9 and outputs information on the presence or absence of molding defects in the resin molded product and information for adjusting at least one parameter of the mold temperature, the resin temperature, and the resin injection speed.

Images