Estimation device, estimation system, estimation method and program

Abstract

To provide an estimation device, estimation system, estimation method, and program that can easily estimate the cause of molding defects in injection molding machines.SOLUTION: An estimation device 4 is equipped with an acquisition unit 41 for acquiring, for each of a plurality of sensors 1 installed in an injection molding machine, a state indicating normality or abnormality determined based on sensing data of the sensor 1, an estimation unit 42 for estimating, using the acquired plurality of states, the type and cause of a molding defect in the injection molding machine, and an output unit 43 that outputs the type and cause of the estimated molding defect.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Injection molding using thermoplastic resins is used in a wide range of fields as a manufacturing method that can mass-produce parts with complex shapes. Technology for detecting abnormalities in injection molding machines is being researched (Patent Documents 1 and 2). Technology for determining defects in molded products molded by injection molding machines is also being researched (Patent Documents 3 and 4). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-122955 [Patent Document 2] International Publication No. 2019 / 188665 [Patent Document 3] JP 2023-68058 A [Patent Document 4] Patent No. 7250072 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventionally, a skilled engineer estimates the cause of molding defects in an injection molding machine based on many years of experience, intuition, or knowledge. Specifically, a skilled engineer estimates the cause of molding defects by listening to the sound and vibrations output by the injection molding machine and by visually inspecting the condition of the parts of the injection molding machine.

[0005] However, for an inexperienced technician, it is difficult to deduce the cause of the molding defect, and it takes a long time to identify the cause of the molding defect.

[0006] The present invention has been made in consideration of the above problems, and an object of the present invention is to easily estimate the cause of molding defects in an injection molding machine. [Means for solving the problem]

[0007] In order to achieve the above-mentioned object, one aspect of the present invention is an estimation device that includes an acquisition unit that acquires, for each of a plurality of sensors installed in an injection molding machine, a state indicating normal or abnormal determined based on sensing data of the sensor, an estimation unit that estimates a type and cause of a molding defect in the injection molding machine using the acquired plurality of states, and an output unit that outputs the estimated type and cause of the molding defect.

[0008] One aspect of the present invention is an estimation system comprising: a plurality of sensors installed in an injection molding machine and outputting sensing data; a multiplexer that acquires the sensing data from each of the plurality of sensors and outputs the acquired sensing data in a predetermined order; a microcomputer that determines whether each piece of sensing data output by the multiplexer is normal or abnormal and outputs status data in which the determined statuses are arranged in the predetermined order; and an estimation device, wherein the estimation device comprises an acquisition unit that acquires the status data from the microcomputer, an estimation unit that uses the status data to estimate a type and cause of a molding defect in the injection molding machine, and an output unit that outputs the estimated type and cause of the molding defect.

[0009] One aspect of the present invention is an estimation method performed by an estimation device, which includes the steps of acquiring, for each of a plurality of sensors installed in an injection molding machine, a state indicating normal or abnormal determined based on sensing data of the sensor, estimating the type and cause of a molding defect in the injection molding machine using the acquired plurality of states, and outputting the estimated type and cause of the molding defect.

[0010] One aspect of the present invention is a program for causing a computer to function as the estimation device. Effect of the Invention

[0011] According to the present invention, the cause of molding defects in an injection molding machine can be easily detected. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram showing the overall configuration of an estimation system according to an embodiment. [Diagram 2] FIG. 2 is an example of a table in which pattern data is associated with causes of molding defects. [Diagram 3] FIG. 3 is a schematic diagram showing an outline of an injection molding machine. [Figure 4] FIG. 4 is an explanatory diagram for explaining an outline of a method for estimating the cause of a molding defect. [Diagram 5] FIG. 5 is a flowchart showing a method for estimating the cause of molding defects. [Figure 6] FIG. 6 is a diagram showing an example of the output screen. [Figure 7] FIG. 7 shows an example of a hardware configuration. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0014] 1 is a schematic diagram of an estimation system according to an embodiment of the present invention. The estimation system shown in the figure includes a plurality of sensors 1 arranged in an injection molding machine 9, a multiplexer 2, a microcomputer 3, and an estimation device 4, and estimates the type (phenomenon) of molding defects in the injection molding machine 9 and the cause of the molding defects.

[0015] Each sensor 1 is installed at a certain position on the injection molding machine 9 and outputs sensing data for detecting an abnormality in the injection molding (parts) that occurs at that position. Each sensor 1 may be a different type of sensor. Furthermore, each sensor 1 is installed at a predetermined position on the corresponding injection molding machine 9 according to its type.

[0016] The multiplexer 2 acquires sensing data from each of the multiple sensors 1 and outputs the acquired sensing data in a predetermined order. For example, when one injection molding is completed, the multiplexer 2 inquires of each sensor 1 in a predetermined order and acquires sensing data during injection molding. Note that the sensing data is assumed to include identification information of the sensor 1. The multiplexer 2 outputs sensing data obtained by combining the multiple sensing data in the acquired order to the microcomputer 3.

[0017] The microcomputer 3 judges whether each piece of sensing data output by the multiplexer 2 is normal or abnormal, and outputs status data in which the judged statuses are arranged in the predetermined order. Specifically, the microcomputer 3 converts the format of the sensing data of each sensor 1 in the order output by the multiplexer 2, and judges whether the converted sensing data indicates a normal status or an abnormal status. For example, the microcomputer 3 may judge whether the sensing data is normal or abnormal using a predetermined threshold value, peak value, etc. set for each sensor 1 (sensing data). Then, the microcomputer 3 outputs to the estimation device 4 the status data in which the statuses (normal / abnormal) judged for each piece of sensing data are arranged in the above-mentioned order. The microcomputer 3 is connected to the sensor 1 and the estimation device 4 using, for example, a USB cable or the like.

[0018] For example, a microcomputer board such as Arduino can be used as the microcomputer 3. A program that specifies the operation of the microcomputer 3 is created by the estimation device 4, and the compiled program can be installed in the microcomputer 3 via a USB cable or the like.

[0019] The estimation device 4 estimates the type and cause of molding defects in the injection molding machine 9 using the status data acquired from the microcomputer 3. A computer such as a server or a personal computer can be used as the estimation device 4. The illustrated estimation device 4 includes an acquisition unit 41, an estimation unit 42, an output unit 43, and a storage unit 44. Each of the units 41 to 44 of the estimation device 4 may be developed using a flow-based programming tool such as Node-RED.

[0020] The acquiring unit 41 acquires, for each of the multiple sensors 1 installed in the injection molding machine 9, a state indicating normality or abnormality determined based on sensing data of the sensor 1. The acquiring unit 41 may acquire, from a microcomputer, state data in which the states indicated by the multiple sensors 1 are arranged in a predetermined order.

[0021] The estimation unit 42 estimates the type and cause of the molding defect in the injection molding machine 9 using the acquired multiple states. Specifically, the estimation unit 42 estimates the type and cause of the molding defect in the injection molding machine 9 using the state data. The estimation unit 42 may estimate, as the type and cause of the molding defect in the injection molding machine 9, the type and cause of the molding defect associated with the pattern data in the table stored in the storage unit 44 that matches the acquired multiple states. Types of molding defects include burrs, short shots, jetting, silver marks, etc.

[0022] The output unit 43 outputs to a display (not shown) the type and cause of the molding defect estimated by the estimation unit 42. When the estimation unit 42 estimates that there is no molding defect, it outputs to the display that the molding is normal.

[0023] The storage unit 44 includes a plurality of pattern data combining the states of a plurality of sensors 1, and a table in which the type and cause of molding defects are associated with each of the pattern data.

[0024] 2 is an example of a table stored in the storage unit 44. In the illustrated table, a plurality of pattern data 201 combining the states of a plurality of sensors 1 is set for each type (phenomenon) and cause of molding defects. Here, normal is represented by "0" and abnormal is represented by "1". In the table, for each pattern data 201, measures for eliminating the cause of the corresponding molding defect may be set.

[0025] 3 is a schematic diagram showing an overview of an injection molding machine 9. The injection molding machine 9 melts a molding material (such as a resin) with heat, performs injection molding, and injects the molten resin into a mold to produce a molded product. The injection molding machine 9 has a mold clamping unit 7, a mold 5, and an injection unit 6. The injection unit 6 melts the molding material with heat and injects it into the mold 5. The injection unit 6 shown in the figure includes a nozzle 60, a cylinder 61, a check valve 62, a heater 63, a screw 64, a hopper 65, a motor 66, and the like.

[0026] The mold 5 includes tie bars 51, a fixed mold 52, and a movable mold 53. The mold clamping unit 7 brings the movable mold 53 of the mold 5 close to the fixed mold 52, and performs mold clamping to close the mold 5. The mold clamping unit 7 includes a crosshead 71, an ejector mechanism 72, and the like.

[0027] In this embodiment, a plurality of sensors 1 are newly attached to a commercially available injection molding machine 9, and sensing data measured by each sensor 1 is used to estimate the type and cause of molding defects in the injection molding machine 9. Examples of the sensors 1 attached to the mold clamping unit 7 and mold 5 include a mold opening sensor, a tie bar sensor, a mold pressure sensor, a mold temperature sensor, and a resin temperature sensor. Examples of the sensors attached to the injection unit 6 include a gas concentration detection sensor, an IR spectrum sensor, and a sound sensor. In addition, a plurality of different types of sensors 1 are used as the sensors 1 attached to the injection molding machine 9.

[0028] Fig. 4 is an explanatory diagram for explaining an outline of a method for estimating the type and cause of molding defects in this embodiment. In the example shown in Fig. 4, for ease of explanation, the explanation is limited to a case where the type of molding defect is estimated to be "burr". Here, a mold opening sensor, a tie bar sensor, an internal mold pressure sensor, and other sensors (not shown) attached to the mold 5 are used. When the type of molding defect is "burr", a burr detector, an AI camera, etc. can be used as the other sensors.

[0029] In this case, the multiplexer 2 acquires sensing data from each sensor in a predetermined order (here, the order is the mold opening sensor, tie bar sensor, mold pressure sensor, and other sensors), combines the sensing data in the acquired order, and outputs the combined sensing data to the microcomputer 3. It is assumed that identification information of each sensor 1 is added to each sensing data.

[0030] The microcomputer 3 judges whether each piece of sensing data output by the multiplexer 2 is normal or abnormal, and outputs status data in which the judged status is arranged in the predetermined order. Here, the microcomputer 3 sets the status to "0" if it judges it to be normal, and to "1" if it judges it to be abnormal. For example, if the mold opening sensor is normal (0), the tie bar sensor is normal (0), the mold pressure sensor is normal (0), and other sensors are abnormal (1), the status data generated by the microcomputer 3 will be "0001".

[0031] When the estimation device 4 acquires the status data, it estimates the type and cause of the molding defect using the status data. Here, it is assumed that a table 301 as shown in the figure is stored in the storage unit 44 of the estimation device 4. The table 301 is a simplified version of the table shown in Fig. 2 for ease of explanation. In this case, the estimation device 4 identifies the type (phenomenon) and cause of the defect corresponding to the status data.

[0032] For example, if the status data is "0001", the type of production defect is estimated to be "burrs" and the cause of the production defect is estimated to be "gaps in the mold". If the status data is "1001", the type of production defect is estimated to be "burrs" and the cause of the production defect is estimated to be "mold deformation". If the status data is "1101", the type of production defect is estimated to be "burrs" and the cause of the production defect is estimated to be "insufficient mold clamping force". If the status data is "1111", the type of production defect is estimated to be "burrs" and the cause of the production defect is estimated to be "abnormal molding conditions".

[0033] FIG. 5 is a flowchart showing the flow of processing in this embodiment.

[0034] The multiplexer 2 acquires sensing data from the multiple sensors 1 in a predetermined order, combines the sensing data in the acquired order, and outputs the combined data to the microcomputer 3 (S11). For example, the multiplexer 2 may acquire sensing data from each sensor 1 at the timing when one injection molding is completed. Note that the sensing data is assumed to have identification information of the sensor 1 added thereto.

[0035] The microcomputer 3 determines whether each piece of sensing data output by the multiplexer 2 is normal or abnormal, and outputs state data in which the determined states (normal: 0, abnormal: 1) are arranged in the predetermined order to the estimation device 4 (S12).

[0036] The estimation device 4 acquires status data including a plurality of statuses from the microcomputer 3 (S13), and estimates the cause of the molding defect using the status data (S14). Specifically, the estimation device 4 estimates the type and cause of the molding defect associated with the pattern data in the table of the storage unit 44, which matches the acquired status data, as the type and cause of the molding defect in the injection molding machine 9. The estimation device 4 may also acquire measures associated with the pattern data matching the status data, by referring to the table.

[0037] Then, the estimation device 4 displays the estimated type and cause of the molding defect on a display (not shown) (S15). Furthermore, if a countermeasure is also acquired in S14, the estimation device 4 may display the countermeasure on the display together with the type and cause of the molding defect.

[0038] 6 is a diagram showing an example of an output screen displayed on the display. In the example shown in the figure, there is a first display section 601 showing the state (normal, abnormal) of each sensor 1, and a second display section 602 showing the type, cause and countermeasure of the molding defect.

[0039] The estimation device 4 of the present embodiment described above includes an acquisition unit 41 that acquires, for each of a plurality of sensors 1 installed in the injection molding machine 9, a state indicating normality or abnormality determined based on sensing data of the sensor 1, an estimation unit 42 that estimates the type and cause of a molding defect in the injection molding machine 9 using the acquired plurality of states, and an output unit 43 that outputs the estimated type and cause of the molding defect.

[0040] The estimation system of this embodiment is provided with a plurality of sensors 1 that are installed in the injection molding machine 9 and output sensing data, a multiplexer 2 that acquires the sensing data from the plurality of sensors and outputs the acquired sensing data in a predetermined order, a microcomputer 3 that judges whether each piece of sensing data output by the multiplexer 2 is normal or abnormal and outputs status data in which the judged statuses are arranged in the predetermined order, and an estimation device 4. The estimation device 4 is provided with an acquisition unit 41 that acquires status data from the microcomputer 3, an estimation unit 42 that estimates the type and cause of a molding defect in the injection molding machine 9 using the status data, and an output unit 43 that outputs the estimated type and cause of the molding defect.

[0041] Until now, skilled technicians have estimated the cause of molding defects in injection molding machines based on their many years of experience, intuition, or knowledge. However, according to this embodiment, the cause of molding defects in injection molding machine 9 can be easily estimated using sensing data output by multiple sensors 1.

[0042] The above-described estimation device 4 may use, for example, a general-purpose computer system as shown in Fig. 7. The computer system shown in the figure includes a CPU (Central Processing Unit, processor) 901, a memory 902, a storage 903 (HDD: Hard Disk Drive, SSD: Solid State Drive), a communication device 904, an input device 905, and an output device 906. The memory 902 and the storage 903 are storage devices. In this computer system, the CPU 901 executes a predetermined program loaded on the memory 902, thereby realizing each function of the estimation device 4.

[0043] The estimation device 4 may be implemented in one computer or in multiple computers. The estimation device 4 may be a virtual machine implemented in a computer. The program of the estimation device 4 may be stored in a computer-readable recording medium such as a HDD, SSD, a Universal Serial Bus (USB) memory, a Compact Disc (CD), or a Digital Versatile Disc (DVD), or may be distributed via a network. The computer-readable recording medium is, for example, a non-transitory recording medium.

[0044] The present invention is not limited to the above-described embodiment, and various modifications are possible within the scope of the present invention. [Explanation of symbols]

[0045] 1: Sensor 2: Multiplexer 3: Microcomputer 4: Estimation device 41: Acquisition Department 42:Estimation part 43: Output section 44: Storage part

Claims

1. an acquisition unit that acquires, for each of a plurality of sensors installed in the injection molding machine, a state indicating normality or abnormality determined based on sensing data of the corresponding sensor; an estimation unit that estimates a type and a cause of a molding defect in the injection molding machine using the acquired multiple states; and an output unit that outputs the type and cause of the estimated molding defect. Estimation device.

2. A table in which a plurality of pattern data combining the states of the plurality of sensors and a type and a cause of molding defects are associated with each of the pattern data, The estimation unit estimates, as a type and a cause of a molding defect in the injection molding machine, a type and a cause of the molding defect that correspond to pattern data in the table and that match the acquired multiple states. The estimation device according to claim 1 .

3. The pattern data and countermeasures are set in the table in association with each other, The estimation unit identifies a countermeasure associated with pattern data in the table that matches the acquired multiple states, and The output unit outputs the identified measures. The estimation device according to claim 2 .

4. A plurality of sensors are installed in the injection molding machine and output sensing data; a multiplexer that acquires the sensing data from each of the plurality of sensors and outputs the acquired sensing data in a predetermined order; a microcomputer that determines whether each piece of sensing data output by the multiplexer is normal or abnormal, and outputs status data in which the determined status is arranged in the predetermined order; An estimation device, The estimation device includes: an acquisition unit that acquires the status data from the microcomputer; an estimation unit that estimates a type and a cause of a molding defect in the injection molding machine using the status data; and an output unit that outputs the type and cause of the estimated molding defect. Estimation system.

5. An estimation method performed by an estimation device, acquiring, for each of a plurality of sensors installed in the injection molding machine, a state indicating normality or abnormality determined based on sensing data of the sensor; A step of estimating a type and a cause of a molding defect in the injection molding machine using the acquired multiple states; and outputting the type and cause of the estimated molding defect. Estimation device.

6. A program causing a computer to function as the estimation device according to any one of claims 1 to 3.

Images