WO2022075181A1 - 状態判定装置及び状態判定方法 - Google Patents
状態判定装置及び状態判定方法 Download PDFInfo
- Publication number
- WO2022075181A1 WO2022075181A1 PCT/JP2021/036167 JP2021036167W WO2022075181A1 WO 2022075181 A1 WO2022075181 A1 WO 2022075181A1 JP 2021036167 W JP2021036167 W JP 2021036167W WO 2022075181 A1 WO2022075181 A1 WO 2022075181A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- statistical
- state
- data
- injection molding
- molding machine
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 48
- 238000001746 injection moulding Methods 0.000 claims abstract description 82
- 238000004364 calculation method Methods 0.000 claims abstract description 42
- 238000003860 storage Methods 0.000 claims description 38
- 230000006870 function Effects 0.000 claims description 24
- 238000013500 data storage Methods 0.000 claims description 18
- 238000007619 statistical method Methods 0.000 claims description 13
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 2
- 230000002787 reinforcement Effects 0.000 claims description 2
- 230000001174 ascending effect Effects 0.000 claims 1
- 230000003247 decreasing effect Effects 0.000 claims 1
- 238000002347 injection Methods 0.000 description 43
- 239000007924 injection Substances 0.000 description 43
- 238000000465 moulding Methods 0.000 description 37
- 230000008569 process Effects 0.000 description 34
- 238000005259 measurement Methods 0.000 description 23
- 230000005856 abnormality Effects 0.000 description 21
- 238000004519 manufacturing process Methods 0.000 description 14
- 239000011347 resin Substances 0.000 description 14
- 229920005989 resin Polymers 0.000 description 14
- 238000010586 diagram Methods 0.000 description 11
- 238000010801 machine learning Methods 0.000 description 11
- 238000005303 weighing Methods 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000012423 maintenance Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000007547 defect Effects 0.000 description 5
- 230000002950 deficient Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000011109 contamination Methods 0.000 description 2
- 230000006866 deterioration Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000004519 grease Substances 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000003449 preventive effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C45/00—Injection moulding, i.e. forcing the required volume of moulding material through a nozzle into a closed mould; Apparatus therefor
- B29C45/17—Component parts, details or accessories; Auxiliary operations
- B29C45/76—Measuring, controlling or regulating
- B29C45/768—Detecting defective moulding conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C2945/00—Indexing scheme relating to injection moulding, i.e. forcing the required volume of moulding material through a nozzle into a closed mould
- B29C2945/76—Measuring, controlling or regulating
- B29C2945/76003—Measured parameter
Definitions
- the present invention relates to a state determination device and a state determination method related to an injection molding machine, and more particularly to a state determination device and a state determination method that assist in determining the quality of a molded product molded by the injection molding machine.
- the discrimination conditions related to molding are set in advance, and the quality of the molded products molded using these discrimination conditions is determined. For example, when the production lot of the resin that is the material of the molded product is switched, the plasticized state of the resin in the injection cylinder fluctuates, which may cause a defect in the molded product. In addition, the molded product may be defective due to wear of parts such as a screw or running out of grease on moving parts. Therefore, the state of the injection molding machine, which fluctuates due to changes over time and changes in the environment, is determined based on changes in the injection time and peak pressure of the injection process in the molding cycle, the measurement time of the measurement process, and the changes in the feature quantities such as the measurement position. ing.
- Patent Document 1 discloses that a quality determination is made based on the maximum value and the minimum value of the measurement data detected for each molding cycle.
- feature quantities eg, actual values / operation data such as injection time, peak pressure, measurement position, etc.
- reference values and reference values related to the calculated feature quantities are calculated. It is shown that normal (good product) or abnormal (defective product) is judged based on the allowable range such as deviation, average value, standard deviation, etc., and notified as an alarm (possibility that an abnormality has occurred in the product). There is.
- Japanese Unexamined Patent Publication No. 02-106315 Japanese Unexamined Patent Publication No. 06-231327 Japanese Unexamined Patent Publication No. 2002-079560 Japanese Patent Application Laid-Open No. 2003-039519
- the feature amount calculated from the measurement data fluctuates due to the influence of environmental changes such as temperature and changes over time. It varies. Conventionally, for abnormalities related to sudden or short-term factors, the measured values acquired for each molding cycle, or the upper and lower limit values determined in advance for the feature quantities and statistics calculated from the measured values, etc. It was possible to determine the molding state by setting a threshold value.
- the state determination device is based on the time-series data (eg, pressure, current, speed, etc.) related to the molding operation of the injection molding machine, and the feature amount of the time-series data (peak value in the molding process) for each molding process. Etc.), and the statistics are calculated using the statistical function for the calculated features. Subsequently, the molding state of the injection molding machine is determined based on the fluctuations of the calculated plurality of statistics.
- time-series data eg, pressure, current, speed, etc.
- feature amount of the time-series data peak value in the molding process
- one aspect of the present invention is a state determination device for determining the state of the injection molding machine, which is a data acquisition unit for acquiring data related to a predetermined physical quantity as data indicating the state of the injection molding machine, and the above-mentioned.
- a feature amount calculation unit that calculates a feature amount that indicates the characteristics of the state of the injection molding machine based on data related to the physical amount, a feature amount storage unit that stores the feature amount, and a predetermined statistic from a predetermined feature amount.
- the statistical condition storage unit that stores statistical conditions including at least a statistical function for calculating, and the statistical condition stored in the statistical condition storage unit based on the feature amount stored in the feature amount storage unit.
- a statistical data calculation unit that calculates statistics as statistical data, a statistical data storage unit that stores the statistical data, and a plurality of continuous statistical data among the statistical data stored in the statistical data storage unit. It is a state determination device including a state determination unit for determining the state of the injection molding machine based on the fluctuation.
- Another aspect of the present invention is a state determination method for determining the state of an injection molding machine, which comprises a step of acquiring data relating to a predetermined physical quantity as data indicating a state relating to the injection molding machine, and a step relating to the physical quantity. At least a step of calculating a feature amount indicating the characteristics of the state of the injection molding machine based on the data and a statistical function for calculating a predetermined statistic from the predetermined feature amount based on the calculated feature amount. A step of calculating the statistic as statistical data according to the included statistical conditions and a step of determining the state of the injection molding machine based on the fluctuation of a plurality of consecutive statistical data in the calculated statistical data are executed. This is a state determination method.
- FIG. 1 is a schematic hardware configuration diagram showing a main part of a state determination device according to an embodiment of the present invention.
- the state determination device 1 according to the present embodiment can be implemented as a control device that controls the injection molding machine 4 based on, for example, a control program.
- the state determination device 1 according to the present embodiment is a personal computer attached to the control device that controls the injection molding machine 4 based on the control program, or a personal computer connected to the control device via a wired / wireless network. It can be mounted on a higher-level device such as a cell computer, a fog computer 6, or a cloud server 7.
- a higher-level device such as a cell computer, a fog computer 6, or a cloud server 7.
- FIG. 1 is a schematic hardware configuration diagram showing a main part of a state determination device according to an embodiment of the present invention.
- the state determination device 1 according to the present embodiment can be implemented as a control device that controls the injection molding machine 4 based on, for example, a control program.
- the CPU 11 included in the state determination device 1 is a processor that controls the state determination device 1 as a whole.
- the CPU 11 reads the system program stored in the ROM 12 via the bus 22 and controls the entire state determination device 1 according to the system program. Temporary calculation data, display data, various data input from the outside, and the like are temporarily stored in the RAM 13.
- the non-volatile memory 14 is composed of, for example, a memory backed up by a battery (not shown), an SSD (Solid State Drive), or the like, and the storage state is maintained even when the power of the state determination device 1 is turned off.
- the non-volatile memory 14 has data read from the external device 72 via the interface 15, data input from the input device 71 via the interface 18, data acquired from the injection molding machine 4 via the network 9, and the like. Is memorized.
- the stored data includes, for example, the motor current, voltage, torque, position, speed, acceleration, and in-mold pressure of the drive unit detected by various sensors 5 attached to the injection molding machine 4 controlled by the control device 3.
- Data related to physical quantities such as the temperature of the injection cylinder, the flow rate of the resin, the flow velocity of the resin, the vibration and sound of the drive unit may be included.
- the data stored in the non-volatile memory 14 may be expanded in the RAM 13 at the time of execution / use. Further, various system programs such as a known analysis program are written in the ROM 12 in advance.
- the interface 15 is an interface for connecting the CPU 11 of the state determination device 1 and an external device 72 such as an external storage medium.
- an external device 72 such as an external storage medium.
- a system program, a program related to the operation of the injection molding machine 4, parameters, and the like can be read.
- the data or the like created / edited on the state determination device 1 side can be stored in an external storage medium such as a CF card or a USB memory (not shown) via the external device 72.
- the interface 20 is an interface for connecting the CPU of the state determination device 1 and the wired or wireless network 9.
- the network 9 communicates using technologies such as serial communication such as RS-485, Ethernet (registered trademark) communication, optical communication, wireless LAN, Wi-Fi (registered trademark), and Bluetooth (registered trademark). It may be there.
- a control device 3 for controlling the injection molding machine 4, a fog computer 6, a cloud server 7, and the like are connected to the network 9, and data is exchanged with each other with the state determination device 1.
- each data read on the memory, data obtained as a result of executing the program, etc. are output and displayed via the interface 17.
- the input device 71 composed of a keyboard, a pointing device, and the like passes commands, data, and the like based on operations by the operator to the CPU 11 via the interface 18.
- FIG. 2 is a schematic configuration diagram of the injection molding machine 4.
- the injection molding machine 4 is mainly composed of a mold clamping unit 401 and an injection unit 402.
- the mold clamping unit 401 is provided with a movable platen 416 and a fixed platen 414. Further, a movable side mold 412 is attached to the movable platen 416, and a fixed side mold 411 is attached to the fixed platen 414.
- the injection unit 402 includes an injection cylinder 426, a hopper 436 for storing the resin material to be supplied to the injection cylinder 426, and a nozzle 440 provided at the tip of the injection cylinder 426.
- the mold clamping unit 401 performs the mold closing / mold clamping operation by moving the movable platen 416, and the injection unit 402 presses the nozzle 440 against the fixed side mold 411. Inject the resin into the mold. These operations are controlled by commands from the control device 3.
- sensors 5 are attached to each part of the injection molding machine 4, and the motor current, voltage, torque, position, speed, acceleration, mold internal pressure, temperature of the injection cylinder 426, resin flow rate, and resin of the drive unit are attached. Physical quantities such as the flow velocity, vibration and sound of the driving unit are detected and sent to the control device 3.
- each detected physical quantity is stored in a RAM, a non-volatile memory, or the like (not shown), and is transmitted to the state determination device 1 via the network 9 as needed.
- FIG. 3 shows as a schematic block diagram the functions included in the state determination device 1 according to the first embodiment of the present invention.
- Each function of the state determination device 1 according to the present embodiment is realized by the CPU 11 included in the state determination device 1 shown in FIG. 1 executing a system program and controlling the operation of each part of the state determination device 1. ..
- the state determination device 1 of the present embodiment includes a data acquisition unit 100, a feature amount calculation unit 110, a statistical data calculation unit 120, and a state determination unit 140. Further, in the RAM 13 to the non-volatile memory 14 of the state determination device 1, the acquisition data storage unit 300 and the feature amount calculation unit 110 as an area for storing the data acquired by the data acquisition unit 100 from the control device 3 or the like are calculated. Statistical data calculated by the feature amount storage unit 310 as an area for storing the stored feature amount, the statistical condition storage unit 320 for storing statistical conditions in the calculation of statistical data by the statistical data calculation unit 120 in advance, and the statistical data calculation unit 120. A statistical data storage unit 330 is prepared in advance as an area for storing the data.
- the data acquisition unit 100 executes a system program read from the ROM 12 by the CPU 11 included in the state determination device 1 shown in FIG. 1, mainly performs arithmetic processing using the RAM 13 and the non-volatile memory 14 by the CPU 11, and the interfaces 15 and 18. Alternatively, it is realized by performing the input control process according to 20.
- the data acquisition unit 100 includes the motor current, voltage, torque, position, speed, acceleration, mold internal pressure, temperature of the injection cylinder 426, and resin flow rate of the drive unit detected by the sensor 5 attached to the injection molding machine 4. , Acquires data related to physical quantities such as resin flow velocity, drive unit vibration and sound.
- the data related to the physical quantity acquired by the data acquisition unit 100 may be so-called time-series data indicating the value of the physical quantity for each predetermined cycle.
- the data acquisition unit 100 acquires the data related to the physical quantity
- the data acquisition unit 100 also acquires the production number (the number of shots) when the physical quantity is detected.
- This production number (shot number) may be the production number (shot number) since the previous maintenance.
- the data acquisition unit 100 may acquire data directly from the control device 3 that controls the injection molding machine 4 via the network 9.
- the data acquisition unit 100 may acquire data acquired and stored by the external device 72, the fog computer 6, the cloud server 7, and the like.
- the data acquisition unit 100 may acquire data related to physical quantities for each step constituting one molding cycle by the injection molding machine 4.
- FIG. 4 is a diagram illustrating a molding cycle for manufacturing one molded product.
- the mold closing step, the mold opening step, and the protrusion step which are the steps of the shaded frame, are performed by the operation of the mold clamping unit 401.
- the injection step, the pressure holding step, the measuring step, the depressurizing step, and the cooling step which are the steps of the white frame, are performed by the operation of the injection unit 402.
- the data acquisition unit 100 acquires data related to physical quantities so that each of these steps can be distinguished.
- the data related to the physical quantity acquired by the data acquisition unit 100 is stored in the acquisition data storage unit 300 in association with the number of production (number of shots) produced by the injection molding machine 4.
- the feature amount calculation unit 110 executes a system program read from the ROM 12 by the CPU 11 included in the state determination device 1 shown in FIG. 1, and mainly performs arithmetic processing using the RAM 13 and the non-volatile memory 14 by the CPU 11. It will be realized.
- the feature amount calculation unit 110 is based on the data related to the physical amount indicating the state of the injection molding machine 4 acquired by the data acquisition unit 100, and the feature of the data related to the physical amount is for each step constituting the molding cycle of the injection molding machine 4.
- the amount is calculated.
- the feature amount calculated by the feature amount calculation unit 110 indicates the characteristics of the state of the injection molding machine 4 for each process.
- FIG. 5 is a graph showing changes in pressure during the injection process.
- t1 indicates the start time point of the injection process
- t3 indicates the end time point of the injection process.
- the pressure starts to rise with the operation of injecting the resin in the injection cylinder into the mold, and then is controlled by the control device 3 of the injection molding machine 4 so as to reach a predetermined target pressure P1.
- the predetermined target pressure P1 is manually set in advance by operating the input device 71 by the operator visually confirming the operation screen displayed on the display device 70 as a command based on the operation of the operator. As shown in FIG.
- the feature amount calculation unit 110 calculates the peak value of the time-series data indicating the pressure acquired in the injection step, and uses this as the feature amount of the peak pressure in the injection step.
- FIG. 6 is a graph showing changes in pressure and changes in screw position in the injection process. As shown in FIG. 6, the feature amount calculation unit 110 calculates the peak pressure in the injection process, then calculates the screw position at the peak pressure arrival time t2 when the peak pressure is reached, and uses this as the peak pressure in the injection process. It is a feature amount of the arrival position. In this way, the feature quantity calculated by the feature quantity calculation unit 110 is calculated based on the data related to the predetermined physical quantity in the predetermined process, or is calculated from the data related to a plurality of physical quantities in the predetermined process. There is. The feature amount calculated by the feature amount calculation unit 110 is stored in the feature amount storage unit 310 in association with the number of production (number of shots) produced by the injection molding machine 4.
- the statistical data calculation unit 120 executes a system program read from the ROM 12 by the CPU 11 included in the state determination device 1 shown in FIG. 1, and mainly performs arithmetic processing using the RAM 13 and the non-volatile memory 14 by the CPU 11. It will be realized.
- the statistical data calculation unit 120 calculates statistical data, which is a statistic of the feature amount, based on the feature amount indicating the feature of the state of the injection molding machine 4 calculated by the feature amount calculation unit 110.
- the statistical data calculation unit 120 refers to the statistical conditions stored in the statistical condition storage unit 320 when calculating the statistical data.
- the statistical condition stored in the statistical condition storage unit 320 defines the condition for calculating the statistic (example: average value, variance, etc.) from the feature amount.
- FIG. 7 is an example of statistical conditions stored in the statistical condition storage unit 320. As illustrated in FIG. 7, the statistical condition associates a feature amount with a statistical function for calculating a statistic from the feature amount. As shown in FIG. 7, the statistical conditions may be defined for each molding step constituting the molding cycle to which the feature amount belongs. Further, as shown in FIG. 7, the statistical condition may include the number of sample of the feature amount when calculating the statistic.
- the statistical functions included in the statistical conditions are, for example, weighted mean, arithmetic mean, weighted harmonic mean, harmonic mean, pruned mean, log mean, squared sum mean square root, minimum, maximum, median, weighted median, mode. It may be a value or the like.
- the injection molding machine 4 is subjected to a test operation in advance, and the correlation between the molding state of the molded product by the injection molding machine 4 and each statistic calculated from the feature amount is analyzed, and the analysis result is obtained. It is advisable to select an appropriate one based on.
- the maximum value of a predetermined feature amount when the maximum value of a predetermined feature amount changes as the molding state of the molded product by the injection molding machine 4 changes, the maximum value as a statistical function for calculating the statistic of the feature amount. Should be selected. Further, for example, when an outlier that greatly deviates from the average value of the features is included in a plurality of features, the weighted median value or the mode value that is not easily affected by the outliers is used as a statistical function. You should select it. Further, for example, when the value of a predetermined feature amount varies as the molding state of the molded product by the injection molding machine 4 changes, as a statistical function for calculating the statistic of the feature amount. The standard deviation should be selected.
- the statistical function when the value of the feature amount varies is not limited to the standard deviation, but may be a variance, an average deviation, a coefficient of variation, or the like. As described above, it is desirable to select a statistical function useful for determining the change in the state of the injection molding machine 4 as the statistical condition relating to the predetermined feature amount.
- the statistical conditions may be set and updated manually by the operator operating the input device 71 from the operation screen displayed on the display device 70.
- FIG. 14 is a table when the operator selects the weighted average as the statistical function for calculating the statistic from the injection time of the feature and the standard deviation as the statistical function for calculating the statistic from the peak pressure arrival position of the feature. An example is shown. Further, the number of samples used by the statistical function for calculating the statistic indicates that the injection time of the feature amount is 30 shots and the peak pressure arrival position of the feature amount is 10 shots.
- the number of samples As a method of determining the number of samples, if the value of the feature quantity changes with a small number of shots such as the injection time in the injection process or the peak pressure arrival position, select a small value as the number of samples and the mold opening time in the mold opening process. If the feature quantity value is stable and changes little in each molding cycle, such as, or if the feature quantity changes slowly after a large number of shots, such as the temperature of an injection cylinder, the number of samples is large, such as 90 shots. You should select a value. As described above, the number of samples may be appropriately selected depending on how the feature amount changes for each molding cycle (for each shot).
- the statistical data calculation unit 120 refers to the statistical conditions stored in the statistical condition storage unit 320, and refers to the statistical data of the feature amount based on the feature amount stored in the feature amount storage unit 310 at a predetermined timing predetermined.
- the statistical data is calculated.
- the statistical data calculation unit 120 may calculate statistical data for each predetermined molding cycle (every 1 shot, every 10 shots, every number of samples set in the statistical conditions, etc.).
- 8A and 8B show an example of statistical data of the peak pressure arrival position.
- FIG. 8A is a graph in which the feature amount for each shot is plotted
- FIG. 8B is a graph in which statistical data calculated from the feature amount is plotted.
- the statistical condition (statistical condition No.
- the statistical data calculation unit 120 divides the feature amount of the peak pressure arrival position calculated for each shot into 10 shots and calculates the standard deviation, and uses the result as the statistical data of the peak pressure arrival position.
- the injection process is defined as the molding process to which the feature amount belongs. Therefore, the timing at which the statistical data calculation unit 120 calculates the statistical data should not overlap with the injection process, that is, the statistical data should be calculated in the mold opening process, the ejection process, etc., which are the processes after the injection process is completed. It is good to set it to. (See FIG.
- the statistical data calculation unit 120 stores the statistical data calculated in this way in the statistical data storage unit 330.
- the operator visually confirms the dispersion state of the feature amount plotted in FIG. 8A and appropriately selects the statistical function.
- FIG. 9 shows an example of statistical data stored in the statistical data storage unit 330.
- the count numbers 1 to n correspond to the number of times the statistical data is calculated. That is, in the example of FIG. 9, n statistical data are stored after the statistical data is calculated and stored. In addition, each statistical data is arranged so as to have a large count number in the statistical data calculated later.
- the statistical data storage unit 330 can grasp the calculation order of the statistical data calculated by the statistical data calculation unit 120, that is, the time order in which the data related to the physical quantity on which the calculation is based is acquired. It is desirable to be remembered. By storing the statistical data so that the order can be grasped, it is possible to execute a predetermined process on a plurality of consecutive statistical data.
- the state determination unit 140 is realized by executing a system program read from the ROM 12 by the CPU 11 included in the state determination device 1 shown in FIG. 1 and performing arithmetic processing mainly by the CPU 11 using the RAM 13 and the non-volatile memory 14. Will be done.
- the state determination unit 140 determines the state of the injection molding machine 4 based on the fluctuation of a plurality of continuous statistical data in the statistical data stored in the statistical data storage unit 330.
- the state determination unit 140 determines the state of the injection molding machine 4 according to the fluctuation of the five most recent statistical data of, for example, the injection time, the weighing time, the mold closing time, and the mold opening time. judge.
- the state determination unit 140 is an injection molding machine depending on how the five most recent statistical data of the measurement pressure peak value, the measurement torque peak value, or the measurement end position fluctuate. The state of 4 is determined.
- the state determination unit 140 may determine fluctuations by performing statistical analysis on a plurality of consecutive statistical data stored in the statistical data storage unit 330.
- FIG. 10 is a schematic block diagram showing the functions provided by the state determination unit 140 in the case of performing statistical analysis.
- the state determination unit 140 that performs statistical analysis includes a statistical analysis unit 141 and a determination condition storage unit 142.
- the statistical analysis unit 141 performs statistical analysis on a plurality of consecutive statistical data based on the determination conditions stored in the determination condition storage unit 142.
- FIG. 11 shows an example of the determination condition stored in the determination condition storage unit 142.
- the determination condition can be defined as a set of the fluctuation condition of the statistical data and the determination result when the condition is satisfied for each determination state.
- the judgment condition (judgment condition No. 1) for judging the "state of time related to the molding process" is the latest one of "injection time, weighing time, mold closing time, and mold opening time”.
- the statistical analysis unit 141 obtains the latest statistical data for each of the injection time, the weighing time, the mold closing time, and the mold opening time each time the statistical data is newly calculated. Five pieces are acquired, and it is determined whether the statistical data included in the acquired statistical data is monotonically increasing. Then, when any one of the injection time, the weighing time, the mold closing time, and the mold opening time is monotonically increased, the state determination unit 140 determines that the molding time is abnormal.
- the determination condition (determination condition No. 3) for determining the “state of the weighing process” is the nearest one of the “measurement pressure peak value, the measurement torque peak value, and the measurement end position”.
- the statistical analysis unit 141 obtains the latest statistical data for each of the measured pressure peak value, the measured torque peak value, and the measurement end position each time new statistical data is calculated. Five pieces are acquired, and it is determined whether the total increase amount between the statistical data included in the acquired statistical data is 10% or more. Then, when any one of the measurement pressure peak value, the measurement torque peak value, and the measurement end position is increased by 10% or more in total, the state determination unit 140 determines that there is an abnormality in the measurement process.
- the determination result by the state determination unit 140 may be displayed and output to the display device 70. Further, the state determination unit 140 may transmit and output the determination result to a higher-level device such as the control device 3 of the injection molding machine 4, the fog computer 6, or the cloud server 7 via the network 9. Further, when the state determination unit 140 determines that the condition is abnormal, the operation of the injection molding machine 4 is stopped or decelerated, or the drive torque of the prime mover for driving the drive unit of the injection molding machine 4 is limited. May be good. As a result, the operation of the injection molding machine 4 can be stopped before the number of molding defects increases, or a safe standby state can be set to prevent the injection molding machine 4 from being damaged.
- the state determination device 1 can determine a molding state that changes slowly over a long period of time, and can further predict future changes in the state. For example, when a sudden impact is applied to the sensor 5 or noise is added to the physical quantity detected by the sensor 5, the feature quantity calculated by the feature quantity calculation unit 110 may include an outlier.
- the statistical data calculated by using the statistical conditions for the feature quantity including this outlier is a value in which the influence of the feature quantity outlier is reduced or a value in which the feature quantity outlier is removed.
- the changing molding state can be accurately determined.
- the state determination device 1 it is possible to grasp the transition of the molding state that gradually changes over time by making a judgment using the change state of the statistic obtained from a plurality of molding cycles. Therefore, it is possible to grasp the sign of the abnormality and notify the operator of the sign of the abnormality before the abnormality (alarm) occurs. That is, it is possible to notify before the injection molding machine is broken and before a defect of the molded product occurs, that is, to realize abnormality detection / preventive maintenance. Since it is possible to grasp the presence or absence of an abnormality before the production is stopped due to an abnormality, the operation rate is improved, the cost is reduced, and the work efficiency is improved.
- the operator can grasp the presence or absence of an abnormality, prepare maintenance parts before the corresponding member breaks, or use the relevant member as a maintenance part. It is possible to carry out maintenance work such as replacement. This realizes a stable determination based on numerical information and a reproducible determination, instead of determining the presence or absence of an abnormality based on the operator's experience and intuition.
- the state determination unit 140 determines fluctuations in a plurality of consecutive statistical data stored in the statistical data storage unit 330 by using a machine learning technique. You may try to do it.
- FIG. 12 is a schematic block diagram showing the functions provided by the state determination unit 140 when the fluctuation is determined based on the estimation result using the machine learning technique.
- the state determination unit 140 that makes a determination by machine learning includes an estimation unit 143 and a learning model storage unit 144.
- the estimation unit 143 uses the learning model stored in the learning model storage unit 144 to estimate the state based on a plurality of consecutive statistical data.
- FIG. 13 shows an example of a learning model stored in the learning model storage unit 144.
- the learning model stored in the learning model storage unit 144 uses statistical data calculated based on data acquired from the injection molding machine 4 that is operating normally in advance and the injection molding machine 4 that shows an abnormality. I learned from it.
- the learning model may be, for example, one learned by known supervised learning. In this case, as the machine learning algorithm, known ones such as a multi-layer perceptron, a recurrent neural network, and a convolutional neural network can be used.
- the learning model (learning model No. 1) for "estimating the state of time related to the molding process” is the “injection time, weighing time, mold closing time, mold” acquired from the injection molding machine 4 in advance. Learning using teacher data with "5 most recent statistical data of opening time” as input data and output data (label data) with the ratio of the increase (0 to 100%) to the normal value of the time related to the manufacture of the molded product as the output data (label data). It is a learning model.
- the estimation unit 143 acquires the five most recent continuous statistical data for each of the injection time, the weighing time, the mold closing time, and the mold opening time, and obtains the acquired statistical data as described above.
- the output (estimated value of the degree of anomaly) is acquired by inputting to the training model.
- the state determination unit 140 determines that there is an abnormality in the molding time.
- the learning model (learning model No. 3) of "for estimating the state of the weighing process" is the latest statistics of the "measured pressure peak value and the measured torque peak value" acquired from the injection molding machine 4 in advance.
- the learning model may be, for example, a known unsupervised learning.
- a known algorithm such as an autoencoder or a k-means method can be used.
- the learning model may be, for example, a known reinforcement learning.
- the machine learning algorithm a known one such as Q-learning can be used.
- the learning model may be stored in the learning model storage unit 144 in a compressed state, and may be decompressed and used at the time of estimation processing. By doing so, the storage memory of the state determination device can be used efficiently, and since it can be handled with a small amount of storage memory, there is a merit of cost reduction.
- the learning model may be encrypted and stored in the learning model storage unit 144, and may be combined and used at the time of estimation processing. By doing so, the state determination device 1 is strong against security and information confidentiality.
- the learning model can create a learning model with different characteristics depending on the type of learning data and the difference in the learning algorithm. Different learning models may be prepared and used appropriately in consideration of features and differences such as calculation load (calculation time), accuracy of estimated value, and robustness to time series data (stability, robustness). In this case, a plurality of different learning models are created in advance for the state to be determined. For example, when the calculation load of the state determination device 1 is high, a learning model having a low calculation load is selected, or the accuracy of the estimated value is obtained. If this is the case, a learning model with high estimation accuracy may be selected even if the calculation load is high, and an appropriate learning model may be used according to the situation.
- the state determination device 1 using the machine learning technique can determine the molding state that changes slowly over a long period of time, and can further predict future changes in the state.
- machine learning technology unlike the method by statistical analysis, the correlation between statistical data and state changes is learned in advance as a learning model, so the cost of analyzing the relationship between the two in advance can be reduced. ..
- the present invention is not limited to the examples of the above-described embodiments, and can be implemented in various embodiments by making appropriate changes.
- a plurality of injection molding machines 4 are connected to each other via a network 9
- data is acquired from the plurality of injection molding machines and the state of each injection molding machine is determined by one state determination device 1.
- the state determination device 1 may be arranged on each control device included in the plurality of injection molding machines, and the state of each injection molding machine may be determined by the injection molding machine. It may be judged by.
Landscapes
- Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Mechanical Engineering (AREA)
- Injection Moulding Of Plastics Or The Like (AREA)
Abstract
Description
即ち、機械が壊れる前に知らせること、成形品に不良が生じる前にその状態を知らせること、稼働率を向上させる予防保全が望まれている。
図1は本発明の一実施形態による状態判定装置の要部を示す概略的なハードウェア構成図である。本実施形態による状態判定装置1は、例えば制御用プログラムに基づいて射出成形機4を制御する制御装置として実装することができる。また、本実施形態による状態判定装置1は、制御用プログラムに基づいて射出成形機4を制御する制御装置に併設されたパソコンや、有線/無線のネットワークを介して制御装置と接続されたパソコン、セルコンピュータ、フォグコンピュータ6、クラウドサーバ7等の上位装置に実装することができる。本実施形態では、状態判定装置1を、ネットワーク9を介して制御装置3と接続されたパソコンの上に実装した例を示す。
例えば、複数の射出成形機4がネットワーク9を介して相互に接続されている場合、複数の射出成形機からデータを取得して其々の射出成形機の状態を1つの状態判定装置1で判定してもよいし、複数の射出成形機が備える其々の制御装置上に状態判定装置1を配置して、其々の射出成形機の状態を該射出成形機が備える其々の状態判定装置で判定してもよい。
2 機械学習装置
3 制御装置
4 射出成形機
5 センサ
6 フォグコンピュータ
7 クラウドサーバ
9 ネットワーク
11 CPU
12 ROM
13 RAM
14 不揮発性メモリ
15,17,18,20 インタフェース
22 バス
70 表示装置
71 入力装置
72 外部機器
100 データ取得部
110 特徴量算出部
120 統計データ算出部
140 状態判定部
141 統計解析部
142 判定条件記憶部
143 推定部
144 学習モデル記憶部
300 取得データ記憶部
310 特徴量記憶部
320 統計条件記憶部
330 統計データ記憶部
Claims (11)
- 射出成形機の状態を判定する状態判定装置であって、
前記射出成形機に係る状態を示すデータとして所定の物理量に係るデータを取得するデータ取得部と、
前記物理量に係るデータに基づいて、前記射出成形機の状態の特徴を示す特徴量を算出する特徴量算出部と、
前記特徴量を記憶する特徴量記憶部と、
所定の特徴量から所定の統計量を算出するための統計関数を少なくとも含む統計条件を記憶する統計条件記憶部と、
前記特徴量記憶部に記憶された前記特徴量に基づいて、前記統計条件記憶部に記憶された統計条件を参照して統計量を統計データとして算出する統計データ算出部と、
前記統計データを記憶する統計データ記憶部と、
前記統計データ記憶部に記憶された前記統計データの内で連続する複数の統計データの変動に基づいて、前記射出成形機の状態を判定する状態判定部と、
を備えた状態判定装置。 - 前記状態判定部は、
前記射出成形機の状態を判定するための判定条件を記憶した判定条件記憶部と、
前記統計データ記憶部に記憶した連続する複数の統計データが、前記判定条件記憶部に記憶された判定条件を満足するか否かを統計的に解析する統計解析部と、
を備え、
前記統計解析部の解析結果に基づいて前記射出成形機の状態を判定する、
請求項1に記載の状態判定装置。 - 前記判定条件は、連続する複数の統計データの単調増加する回数、単調減少する回数、上昇率、下降率のいずれか1つに係る条件を定義したものである、
請求項2に記載の状態判定装置。 - 前記状態判定部は、
前記統計データ算出部により算出された統計データの内で連続する複数の統計データと、該統計データが算出されたときの前記射出成形機の状態との相関性を学習した学習モデルを記憶した学習モデル記憶部と、
前記統計データ記憶部に記憶した連続する複数の統計データに基づいて、前記学習モデルを用いた前記射出成形機の状態の推定をする推定部と、
を備えた請求項1に記載の状態判定装置。 - 前記学習モデルは、教師あり学習、教師なし学習、及び強化学習のうち少なくとも1つの学習方法で学習したものである、
請求項4に記載の状態判定装置。 - 前記統計関数は、分散、標準偏差、平均偏差、変動係数、加重平均、重み付き調和平均、刈り込み平均、二乗和平均平方根、最小値、最大値、最頻値、加重中央値のいずれかである、
請求項1に記載の状態判定装置。 - 前記状態判定部による判定の結果は、表示装置に対して表示出力される、
請求項1に記載の状態判定装置。 - 前記状態判定部が前記射出成形機の状態が異常であると判定した場合、前記射出成形機の運転を停止、減速、または前記射出成形機を駆動する原動機の駆動トルクを制限する信号のうち少なくともいずれかを出力する、
請求項1に記載の状態判定装置。 - 前記データ取得部は、有線または無線のネットワークを介して接続され複数の射出成形機からデータを取得する、
請求項1に記載の状態判定装置。 - 前記射出成形機と有線又は無線のネットワークを介して接続された上位装置上に実装されている、
請求項1に記載の状態判定装置。 - 射出成形機の状態を判定する状態判定方法であって、
前記射出成形機に係る状態を示すデータとして所定の物理量に係るデータを取得するステップと、
前記物理量に係るデータに基づいて、前記射出成形機の状態の特徴を示す特徴量を算出するステップと、
算出した前記特徴量に基づいて、所定の特徴量から所定の統計量を算出するための統計関数を少なくとも含む統計条件に従い統計量を統計データとして算出するステップと、
算出した前記統計データの内で連続する複数の統計データの変動に基づいて、前記射出成形機の状態を判定するステップと、
を実行する状態判定方法。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE112021005248.9T DE112021005248T5 (de) | 2020-10-05 | 2021-09-30 | Zustandsbestimmungsvorrichtung und zustandsbestimmungsverfahren |
CN202180066813.9A CN116234651A (zh) | 2020-10-05 | 2021-09-30 | 状态判定装置及状态判定方法 |
JP2022555420A JP7525631B2 (ja) | 2020-10-05 | 2021-09-30 | 状態判定装置及び状態判定方法 |
US18/245,897 US20240009905A1 (en) | 2020-10-05 | 2021-09-30 | State determination device and state determination method |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2020-168771 | 2020-10-05 | ||
JP2020168771 | 2020-10-05 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022075181A1 true WO2022075181A1 (ja) | 2022-04-14 |
Family
ID=81126853
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/036167 WO2022075181A1 (ja) | 2020-10-05 | 2021-09-30 | 状態判定装置及び状態判定方法 |
Country Status (5)
Country | Link |
---|---|
US (1) | US20240009905A1 (ja) |
JP (1) | JP7525631B2 (ja) |
CN (1) | CN116234651A (ja) |
DE (1) | DE112021005248T5 (ja) |
WO (1) | WO2022075181A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023209988A1 (ja) * | 2022-04-28 | 2023-11-02 | ファナック株式会社 | 判定装置および判定方法 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080111264A1 (en) * | 2006-11-15 | 2008-05-15 | Husky Injection Molding Systems Ltd. | Vibration Based Injection Molding Machine Damage Detection and Health Monitoring |
JP2012076454A (ja) * | 2010-09-07 | 2012-04-19 | Sumitomo Heavy Ind Ltd | 射出成形機及び電力用半導体素子消耗度監視システム |
JP2017207822A (ja) * | 2016-05-16 | 2017-11-24 | ファナック株式会社 | 加工セル及び加工セル管理システム |
JP2019046311A (ja) * | 2017-09-05 | 2019-03-22 | オムロン株式会社 | 情報処理装置および情報処理方法 |
JP2020044836A (ja) * | 2018-09-14 | 2020-03-26 | 株式会社名機製作所 | 射出成形機、射出成形機の状態報知システム、射出成形機の状態報知方法 |
JP2020128014A (ja) * | 2019-02-07 | 2020-08-27 | ファナック株式会社 | 状態判定装置及び状態判定方法 |
JP2020142431A (ja) * | 2019-03-06 | 2020-09-10 | ファナック株式会社 | 射出成形機の管理システム及び射出成形機の集中管理システム |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2862881B2 (ja) | 1988-10-14 | 1999-03-03 | ファナック株式会社 | 成形品の良否判別基準値自動設定方法及び装置 |
JPH06231327A (ja) | 1993-01-28 | 1994-08-19 | Konica Corp | 成形不良自動判別装置 |
JP3546951B2 (ja) | 2000-09-08 | 2004-07-28 | 住友重機械工業株式会社 | 射出成形機の製品良否判別方法 |
JP2003039519A (ja) | 2001-05-25 | 2003-02-13 | Toshiba Mach Co Ltd | 射出成形機におけるモニタリング方法 |
-
2021
- 2021-09-30 DE DE112021005248.9T patent/DE112021005248T5/de not_active Withdrawn
- 2021-09-30 CN CN202180066813.9A patent/CN116234651A/zh active Pending
- 2021-09-30 WO PCT/JP2021/036167 patent/WO2022075181A1/ja active Application Filing
- 2021-09-30 JP JP2022555420A patent/JP7525631B2/ja active Active
- 2021-09-30 US US18/245,897 patent/US20240009905A1/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080111264A1 (en) * | 2006-11-15 | 2008-05-15 | Husky Injection Molding Systems Ltd. | Vibration Based Injection Molding Machine Damage Detection and Health Monitoring |
JP2012076454A (ja) * | 2010-09-07 | 2012-04-19 | Sumitomo Heavy Ind Ltd | 射出成形機及び電力用半導体素子消耗度監視システム |
JP2017207822A (ja) * | 2016-05-16 | 2017-11-24 | ファナック株式会社 | 加工セル及び加工セル管理システム |
JP2019046311A (ja) * | 2017-09-05 | 2019-03-22 | オムロン株式会社 | 情報処理装置および情報処理方法 |
JP2020044836A (ja) * | 2018-09-14 | 2020-03-26 | 株式会社名機製作所 | 射出成形機、射出成形機の状態報知システム、射出成形機の状態報知方法 |
JP2020128014A (ja) * | 2019-02-07 | 2020-08-27 | ファナック株式会社 | 状態判定装置及び状態判定方法 |
JP2020142431A (ja) * | 2019-03-06 | 2020-09-10 | ファナック株式会社 | 射出成形機の管理システム及び射出成形機の集中管理システム |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023209988A1 (ja) * | 2022-04-28 | 2023-11-02 | ファナック株式会社 | 判定装置および判定方法 |
Also Published As
Publication number | Publication date |
---|---|
JP7525631B2 (ja) | 2024-07-30 |
CN116234651A (zh) | 2023-06-06 |
US20240009905A1 (en) | 2024-01-11 |
DE112021005248T5 (de) | 2023-07-20 |
JPWO2022075181A1 (ja) | 2022-04-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6787971B2 (ja) | 状態判定装置及び状態判定方法 | |
US10981315B2 (en) | State determination device | |
JP6975188B2 (ja) | 状態判定装置及び状態判定方法 | |
JP7010861B2 (ja) | 状態判定装置及び状態判定方法 | |
CN110920009B (zh) | 状态判定装置以及状态判定方法 | |
WO2022075224A1 (ja) | 状態判定装置及び状態判定方法 | |
WO2022075242A1 (ja) | 状態判定装置及び状態判定方法 | |
WO2022075181A1 (ja) | 状態判定装置及び状態判定方法 | |
CN110962315B (zh) | 状态判定装置以及状态判定方法 | |
WO2022075244A1 (ja) | 状態判定装置及び状態判定方法 | |
CN117795308A (zh) | 控制装置以及控制方法 | |
WO2022054782A1 (ja) | 状態判定装置及び状態判定方法 | |
WO2023026416A1 (ja) | 状態判定装置及び状態判定方法 | |
WO2023026411A1 (ja) | 状態判定装置及び状態判定方法 | |
JP7184997B2 (ja) | 状態判定装置及び状態判定方法 | |
WO2024089851A1 (ja) | 判定装置及び判定方法 | |
WO2024057461A1 (ja) | 判定装置及び判定方法 | |
WO2024004106A1 (ja) | 判定システム及び方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21877482 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2022555420 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18245897 Country of ref document: US |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21877482 Country of ref document: EP Kind code of ref document: A1 |