WO2022210170A1 - 加工条件推定装置 - Google Patents
加工条件推定装置 Download PDFInfo
- Publication number
- WO2022210170A1 WO2022210170A1 PCT/JP2022/013554 JP2022013554W WO2022210170A1 WO 2022210170 A1 WO2022210170 A1 WO 2022210170A1 JP 2022013554 W JP2022013554 W JP 2022013554W WO 2022210170 A1 WO2022210170 A1 WO 2022210170A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- machining
- processing
- unit
- condition
- conditions
- Prior art date
Links
- 238000012545 processing Methods 0.000 claims abstract description 115
- 238000004088 simulation Methods 0.000 claims abstract description 39
- 238000011156 evaluation Methods 0.000 claims abstract description 29
- 238000003754 machining Methods 0.000 claims description 241
- 238000010801 machine learning Methods 0.000 claims description 29
- 238000009795 derivation Methods 0.000 claims description 19
- 238000010586 diagram Methods 0.000 description 9
- 238000000034 method Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 239000012530 fluid Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003746 surface roughness Effects 0.000 description 2
- KNMAVSAGTYIFJF-UHFFFAOYSA-N 1-[2-[(2-hydroxy-3-phenoxypropyl)amino]ethylamino]-3-phenoxypropan-2-ol;dihydrochloride Chemical compound Cl.Cl.C=1C=CC=CC=1OCC(O)CNCCNCC(O)COC1=CC=CC=C1 KNMAVSAGTYIFJF-UHFFFAOYSA-N 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000009760 electrical discharge machining Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23H—WORKING OF METAL BY THE ACTION OF A HIGH CONCENTRATION OF ELECTRIC CURRENT ON A WORKPIECE USING AN ELECTRODE WHICH TAKES THE PLACE OF A TOOL; SUCH WORKING COMBINED WITH OTHER FORMS OF WORKING OF METAL
- B23H7/00—Processes or apparatus applicable to both electrical discharge machining and electrochemical machining
- B23H7/02—Wire-cutting
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23H—WORKING OF METAL BY THE ACTION OF A HIGH CONCENTRATION OF ELECTRIC CURRENT ON A WORKPIECE USING AN ELECTRODE WHICH TAKES THE PLACE OF A TOOL; SUCH WORKING COMBINED WITH OTHER FORMS OF WORKING OF METAL
- B23H7/00—Processes or apparatus applicable to both electrical discharge machining and electrochemical machining
- B23H7/14—Electric circuits specially adapted therefor, e.g. power supply
- B23H7/20—Electric circuits specially adapted therefor, e.g. power supply for programme-control, e.g. adaptive
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
- G05B19/182—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by the machine tool function, e.g. thread cutting, cam making, tool direction control
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
- G05B19/4093—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by part programming, e.g. entry of geometrical information as taken from a technical drawing, combining this with machining and material information to obtain control information, named part programme, for the NC machine
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/45—Nc applications
- G05B2219/45043—EDM machine, wire cutting
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/45—Nc applications
- G05B2219/45221—Edm, electrical discharge machining, electroerosion, ecm, chemical
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Definitions
- the present invention relates to a machining condition estimating device, and more particularly to a machining condition estimating device for searching for machining conditions of a wire electric discharge machine.
- processing details workpiece material, work plate thickness, processing shape, step, surrounding environment, etc.
- required specifications processing speed, disconnection frequency, straightness accuracy, surface roughness, shape error, etc.
- the manufacturer performs actual machining many times while changing the machining conditions of the wire electric discharge machine, searches for machining conditions that are considered appropriate for each combination of machining content and required specifications, and creates a machining condition list. create it. It is necessary for a skilled worker to spend a lot of time searching for such processing conditions.
- the user selects and uses machining conditions that satisfy the desired machining contents and required specifications from the machining condition list prepared in advance by the manufacturer.
- Patent Document 1 describes a database of relationships between set machining conditions and machining results when actual machining is performed. Techniques for predicting machining conditions that satisfy required specifications have been disclosed. In the technique of Patent Document 1, machining is actually performed under the predicted machining conditions, the database is updated with the results obtained therefrom, and machining conditions to be tried next are predicted and presented repeatedly. This allows workers to find more suitable processing conditions faster than they can manually.
- the machining condition estimating device solves the above problems by using simulation technology to evaluate the machining conditions predicted by the search when searching for the machining conditions.
- simulation technology it is possible to evaluate machining conditions without actually machining, and it is possible to acquire more data in a shorter period of time than with actual machining.
- one aspect of the present invention is a machining condition estimating apparatus for estimating machining conditions in a wire electric discharge machine, which satisfies the machining contents and the required specifications with respect to the data related to the machining contents and the required specifications. Based on a processing information database storing processing information data associated with data related to processing conditions to be processed, and the processing information data stored in the processing information database, it is estimated that the desired processing content and required specifications are satisfied.
- a machining condition derivation unit that derives at least one machining condition
- a simulation unit that performs simulation of a wire electric discharge machine based on the machining conditions derived by the machining condition derivation unit
- a machining condition estimating device comprising: a machining condition evaluation unit for evaluating the machining conditions; and a database update unit for updating the machining information database based on the evaluation result of the machining condition evaluation unit.
- FIG. 2 is a schematic hardware configuration diagram of a control device according to the first embodiment;
- FIG. 2 is a schematic block diagram showing functions of the control device according to the first embodiment;
- FIG. 4 is a diagram showing an example of processing information data stored in a processing information database;
- FIG. 5 is a schematic hardware configuration diagram of a control device according to a second embodiment;
- FIG. 5 is a schematic block diagram showing functions of a control device according to a second embodiment;
- FIG. 1 is a schematic hardware configuration diagram showing essential parts of a machining condition estimation device according to a first embodiment of the present invention.
- the machining condition estimation device 1 of the present invention can be implemented, for example, as a control device that controls the wire electric discharge machine 8, or can be implemented as a personal computer attached to the control device. 6. It can also be implemented as a computer such as a cloud server 7 or the like.
- a machining condition estimating apparatus 1 according to the present embodiment is implemented as a computer connected to (a control apparatus for controlling) a wire electric discharge machine 8 via a wired/wireless network 5 .
- the CPU 11 provided in the machining condition estimation device 1 is a processor that controls the machining condition estimation 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 machining condition estimating apparatus 1 according to the system program.
- the RAM 13 temporarily stores calculation data, display data, various data input from the outside, and the like.
- 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 retains the storage state even when the machining condition estimating device 1 is powered off.
- the non-volatile memory 14 stores programs and data read from the external device 72 via the interface 15, programs and data input from the input device 71 via the interface 18, and the fog computer 6 and cloud server via the network 5. Programs, data, and the like obtained from other devices such as 7 are stored.
- the data stored in the non-volatile memory 14 are, for example, data related to the details of machining in the wire electric discharge machine 8, data related to required specifications, and other data detected by a sensor (not shown) attached to the wire electric discharge machine 8.
- the programs and data stored in the non-volatile memory 14 may be developed in the RAM 13 at the time of execution/use.
- Various system programs such as a well-known analysis program are pre-written in the ROM 12 .
- the interface 15 is an interface for connecting the CPU 11 of the processing condition estimation device 1 and an external device 72 such as an external storage medium.
- an external device 72 such as an external storage medium.
- Programs, data, and the like edited in the machining condition estimating apparatus 1 can be stored in an external storage medium (not shown) such as a CF card or USB memory via the external device 72 .
- the interface 20 is an interface for connecting the CPU of the processing condition estimation device 1 and the wired or wireless network 5 .
- the network 5 communicates using techniques 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's okay.
- a control device for controlling other machines, a fog computer 6, a cloud server 7, and other high-level management devices are connected to the network 5, and exchange data with the processing condition estimation device 1. .
- each data read into the memory, data obtained as a result of executing the program, etc. are output via the interface 17 and displayed.
- An 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 block diagram showing the functions of the machining condition estimating device 1 according to the first embodiment of the present invention.
- Each function provided in the machining condition estimation device 1 according to the present embodiment is such that the CPU 11 provided in the machining condition estimation device 1 shown in FIG. It is realized by
- the machining condition estimation device 1 of this embodiment includes a machining condition derivation unit 100, a simulation unit 110, a machining condition evaluation unit 120, and a database update unit 130. Further, the RAM 13 to the non-volatile memory 14 of the machining condition estimating device 1 are areas for storing machining information data in which data relating to machining conditions are associated with data relating to predetermined machining contents and data relating to required specifications. A processing information database 200 is provided.
- FIG. 3 shows an example of processing information data stored in the processing information database 200.
- the data relating to the machining contents and the data relating to the required specifications are associated with the data relating to the machining conditions for satisfying the machining contents and the required specifications.
- the data related to the machining contents include data such as work material, work plate thickness, machining shape, steps, and surrounding environment.
- the data related to the required specifications include machining speed, disconnection frequency, straightness accuracy,
- data related to the machining conditions include voltage waveform, voltage polarity, current waveform, discharge time, rest time, machining fluid volume, machining fluid pressure, wire tension, and wire feed control. It includes data such as Each piece of processed information data is associated with identification information that uniquely identifies the processed information data.
- the machining information data stored in the machining information database 200 in the initial stage may be, for example, data input by the operator via the input device 71 or the external device 72, or may be data previously input by the wire electric discharge machine 8. It may be obtained from data observed in the processing performed.
- the data to be stored in the machining information database 200 at the initial stage need not exhaustively cover all machining details and required specifications.
- the machining condition derivation unit 100 executes a system program read from the ROM 12 by the CPU 11 of the machining condition estimation apparatus 1 shown in FIG. is realized by The machining condition deriving unit 100 derives a predetermined machining condition that is estimated to satisfy the machining contents and required specifications based on the data on the machining details and the data on the required specifications input by the operator.
- the machining condition deriving unit 100 may derive predetermined machining conditions that are estimated to satisfy the machining details and required specifications input by the operator based on the machining information data stored in the machining information database 200, for example.
- the machining condition deriving unit 100 extracts the data on the machining content and the data on the required specification input by the operator, and the data on the machining content and the request contained in each machining information data stored in the machining information database 200.
- a similarity search is performed with the data related to the specification.
- the distance is calculated when the data related to each processing content and the data related to the required specification are regarded as vectors, and the one with the shortest distance is extracted as processing information data with a high degree of similarity.
- a plurality of machining conditions obtained by adding predetermined changes to the machining conditions contained in the extracted machining information data are derived as predetermined machining conditions that are estimated to satisfy the machining contents and required specifications.
- the processing condition derivation unit 100 may change the data by adding a predetermined variable, for example.
- the predetermined variable may be multiple variables.
- the machining conditions derived by the machining condition derivation unit 100 are used as parameters for the simulation operation of the wire electric discharge machine by the simulation unit 110 . Basically, in the simulation, it is also possible to set machining conditions that cannot be actually machined due to the specifications of the actual machine. Therefore, the change applied to the data by the processing condition derivation unit 100 may exceed the range of general set values and the range of combinations.
- the processing condition deriving unit 100 adds a predetermined change predetermined for each condition item to the data related to the processing conditions included in the processing information data extracted from the processing information database 200, so that the processing contents and Predetermined processing conditions that are estimated to satisfy the required specifications may be derived.
- This may be a variation of each condition item, or a combination of variations of each condition item.
- the machining condition derivation unit 100 derives the machining conditions by adding the following eight changes to the machining information data extracted from the machining information database 200 .
- (Processing condition 1) Voltage value + 0.1 V (Processing condition 2) Voltage value -0.1 V (Machining condition 3) discharge time + 1 ⁇ sec (Machining condition 4) discharge time -1 ⁇ sec (Processing condition 5) voltage value +0.1 V, discharge time +1 ⁇ sec (Processing condition 6) Voltage value +0.1 V, discharge time -1 ⁇ sec (Processing condition 7) voltage value -0.1 V, discharge time +1 ⁇ sec (Processing condition 8) voltage value -0.1 V, discharge time -1 ⁇ sec
- a random number may be used to derive a machining condition in which a change is added to the machining condition.
- Such changes in machining conditions can be used to derive machining conditions outside the machine specifications and machining conditions not assumed by humans.
- the machining conditions derived by the machining condition deriving unit 100 are for simulating machining conditions not covered in the machining information database 200. Therefore, it is desirable that the processing conditions derived by the processing condition derivation unit 100 are not those in which the processing information data including the processing conditions are already stored in the processing information database 200 . If the processing information data to which a predetermined change has been added is the same as that already stored in the processing information database 200, the processing condition derivation unit 100 may exclude the processing condition from the output targets.
- the simulation unit 110 is realized by executing a system program read from the ROM 12 by the CPU 11 provided in the machining condition estimation apparatus 1 shown in FIG. be done.
- the simulation unit 110 performs wire electric discharge machine simulation based on the machining conditions derived by the machining condition derivation unit 100, and outputs the machining result.
- the simulation unit 110 sets data that can be set as a parameter of the simulation operation, among the machining conditions derived by the machining condition deriving unit 100 and the data on the machining content and the data on the required specifications input by the operator. , the simulation processing of the wire electric discharge machine is executed.
- the simulation of the wire electric discharge machine performed by the simulation unit 110 is described in, for example, "Japanese Unexamined Patent Application Publication No. 2002-160127" and “Masanori Kunieda,”Electrical discharge machining simulation”Journal of the Japan Society for Precision Engineering, Vol.76, No.8, 2010, pp. 861-866” and the like may be used.
- the simulation unit 110 outputs the machining speed, wire breakage frequency, straightness accuracy, surface roughness, shape error, etc. as the simulation results of the wire electric discharge machine using the set parameters.
- the machining condition evaluation unit 120 executes a system program read from the ROM 12 by the CPU 11 of the machining condition estimation apparatus 1 shown in FIG. is realized by The machining condition evaluation unit 120 evaluates to what extent the simulation result based on the machining conditions derived by the machining condition derivation unit 100 satisfies the data related to the required specifications input by the operator. For example, the machining condition evaluation unit 120 sets 1 when the shape error of the simulation result is smaller than the shape error input by the operator, 0.5 when the shape error is less than twice, and 0.5 when the shape error is twice or more. Each item may be scored such that a high score is given when the result is good, and a low score is given when the result is unsatisfactory, and the total value may be used for evaluation.
- the scoring may be weighted according to the importance of each item.
- the machining condition evaluation unit 120 outputs each machining condition and its evaluation.
- the evaluation result by the processing condition evaluation unit 120 may be displayed on the display device 70 or may be transmitted to a higher-level device such as the fog computer 6 or the cloud server 7 via the network 5 .
- the database update unit 130 executes a system program read from the ROM 12 by the CPU 11 provided in the machining condition estimation apparatus 1 shown in FIG. Realized.
- the database update unit 130 updates the machining information database based on the machining conditions output by the machining condition evaluation unit 120 and the evaluation thereof.
- the database update unit 130 creates processing information data in association with, for example, the processing conditions to which the processing condition evaluation unit 120 has given the highest evaluation, with the processing details input by the operator and the required specification items as simulation results by the simulation unit, It may be stored in the machining information database 200 .
- the database update unit 130 may create processing information data for processing conditions to which the processing condition evaluation unit 120 has given a predetermined evaluation score or higher, and store the processing information data in the processing information database 200 .
- the database updating unit 130 may create processing information data for processing conditions selected by the operator from among the processing conditions displayed on the display device, and store the processing information data in the processing information database 200 .
- the machining condition evaluation unit 120 obtains an evaluation point equal to or higher than a predetermined threshold, for example, when an evaluation equal to or higher than a predetermined value is obtained for each machining condition. If not, the machining condition deriving unit 100 may be commanded to derive a further machining condition. Upon receipt of such a command, the machining condition deriving unit 100 further derives a machining condition in which predetermined changes are superimposed multiple times, or derives a machining condition in which a further random number change is added. In this way, the wire electric discharge machine may be simulated by the simulation unit 110 based on the newly derived machining conditions, and the machining conditions that give a predetermined evaluation or higher may be continuously searched for.
- the machining condition estimating apparatus 1 uses simulation technology to evaluate the machining conditions predicted by the search when searching for machining conditions that satisfy the machining details and required specifications input by the operator. By using , it is possible to evaluate machining conditions without actually machining. Since there is no need for actual processing, it is possible to reduce the manpower involved in actual processing. Also, by using high-speed computational resources for simulation, it is possible to acquire more data in a much shorter time than actual machining. In the simulation, it is possible to evaluate machining conditions that cannot be actually machined due to the specifications of the actual machine. Therefore, it is possible to simulate machining conditions whose ranges and combinations were not assumed, so it is now possible to evaluate machining conditions that are outside the machine specifications and machining conditions that the operator, etc. cannot think of. , can be a guideline for improvement of machine specifications and new research and development.
- FIG. 4 is a schematic hardware configuration diagram showing the essential parts of the machining condition estimation device according to the second embodiment of the present invention.
- a machining condition estimation device 1 according to the present embodiment uses a machine learning device 2 for estimating machining conditions.
- the machining condition estimation device 1 includes an interface 21 and a machine learning device 2 in addition to the components of the machining condition estimation device 1 (FIG. 2) according to the first embodiment.
- the interface 21 is an interface for connecting the CPU 11 and the machine learning device 2 .
- the machine learning device 2 includes a processor 201 that controls the entire machine learning device 2, a ROM 202 that stores system programs and the like, a RAM 203 that temporarily stores each process related to machine learning, and a learning target.
- a non-volatile memory 204 is provided for storing a model that has learned a data group.
- the machine learning device 2 can observe data generated by the machining condition estimating device 1 via the interface 21 (for example, data relating to machining content, data relating to required specifications, data relating to machining conditions, etc.). .
- the processing condition estimation device 1 acquires the processing results output from the machine learning device 2 via the interface 21, stores and displays the acquired results, and communicates the network 5 and the like to other devices. Send via.
- the machine learning device 2 is built in the processing condition estimation device 1 in FIG. 1, it may be externally connected to the processing condition estimation device 1 via a predetermined interface.
- FIG. 5 is a schematic block diagram showing the functions of the machining condition estimating device 1 according to the second embodiment of the present invention.
- Each function provided in the machining condition estimating apparatus 1 according to the present embodiment is such that the CPU 11 provided in the machining condition estimating apparatus 1 and the processor 201 provided in the machine learning device 2 shown in FIG. 1 and machine learning device 2.
- the machining condition estimation apparatus 1 of the present embodiment includes a machining condition derivation unit 100, a simulation unit 110, a machining condition evaluation unit 120, a database update unit 130, and a machine learning unit 205 configured on the machine learning device 2.
- the RAM 13 to the non-volatile memory 14 of the machining condition estimating device 1 are areas for storing machining information data in which data relating to machining conditions are associated with data relating to predetermined machining contents and data relating to required specifications.
- a processing information database 200 is provided.
- a model storage section 209 is prepared in advance as an area for storing a model created as a result of learning by the learning section 206.
- the machine learning unit 205 executes a system program read from the ROM 202 by the processor 201 provided in the machine learning device 2 shown in FIG. is realized by performing The machine learning unit 205 performs processing (learning, estimation, etc.) related to machine learning based on commands from each function of the machining condition estimation device 1 .
- the learning unit 206 included in the machine learning unit 205 determines the correlation between the data related to the processing content, the data related to the required specifications, and the data related to the processing conditions based on the processing information data stored in the processing information database 200. is created, and the created model is stored in the model storage unit 209 .
- the learning performed by the learning unit 206 may be, for example, known supervised learning.
- the model created by the learning unit 206 performs machine learning, and when data related to processing details and data related to required specifications are input, data related to processing conditions that satisfy the details of processing and required specifications are estimated. is possible. Examples of the model created by the learning unit 206 include a regression learner and a multilayer neural network.
- the estimating unit 208 provided in the machine learning unit 205 calculates the processing conditions using the model stored in the model storage unit 209 based on the data related to the processing content and the data related to the required specifications input from the processing condition derivation unit 100. Execute the estimation process.
- the estimation processing performed by the estimation unit 208 may be estimation processing based on known supervised learning or reinforcement learning.
- the machining condition derivation unit 100 calculates the machining contents based on the data relating to the machining contents and the data relating to the required specifications input by the operator. and a predetermined machining condition that is estimated to satisfy the required specifications.
- the machining condition derivation unit 100 according to the present embodiment in the stage where the model learning by the learning unit 206 is not sufficient, is similar to the machining condition derivation unit 100 according to the first embodiment, and the machining information data stored in the machining information database 200 Based on this, predetermined processing conditions are derived.
- the machining condition deriving unit 100 inputs to the machine learning unit 205 the data related to the machining content and the data related to the required specifications input by the operator. Then, a predetermined machining condition presumed to satisfy the machining details and required specifications input by the operator is obtained. Then, a plurality of machining conditions obtained by adding predetermined changes to the estimated machining conditions are derived as predetermined machining conditions that are estimated to satisfy the machining details and required specifications.
- Whether or not the model learning by the learning unit 206 is sufficient may be determined based on the number of pieces of processing information data stored in the processing information database 200 . For example, when the number of pieces of processing information data stored in the processing information database 200 is equal to or greater than a predetermined threshold, the processing condition deriving unit 100 requests the machine learning unit 205 to estimate the processing conditions. good.
- the machining condition estimating apparatus 1 uses simulation technology to evaluate the machining conditions predicted by the search when searching for machining conditions that satisfy the machining details and required specifications input by the operator. By using , it is possible to evaluate machining conditions without actually machining. By estimating the machining conditions that serve as search criteria by machine learning, it can be expected that the calculation amount of the simulation process related to the search will be greatly reduced as the estimation accuracy of the machine learning device is improved.
Landscapes
- Engineering & Computer Science (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- Mechanical Engineering (AREA)
- Chemical & Material Sciences (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Manufacturing & Machinery (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- Electrical Discharge Machining, Electrochemical Machining, And Combined Machining (AREA)
Abstract
Description
そのため、極力人手をかけずに加工条件の探索の作業を行うことを可能とする技術が望まれている。
図1は本発明の第1実施形態による加工条件推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。
本発明の加工条件推定装置1は、例えば、ワイヤ放電加工機8を制御する制御装置として実装することができ、また、制御装置に併設されたパソコンとして実装することができ、更には、フォグコンピュータ6、クラウドサーバ7等のコンピュータとして実装することもできる。本実施形態による加工条件推定装置1は、有線/無線のネットワーク5を介してワイヤ放電加工機8(を制御する制御装置)と接続されたコンピュータとして実装されている。
本実施形態による加工条件推定装置1が備える各機能は、図1に示した加工条件推定装置1が備えるCPU11がそれぞれシステム・プログラムを実行し、加工条件推定装置1の各部の動作を制御することにより実現される。
図3に例示されるように、加工情報データベース200には、加工内容に係るデータ及び要求仕様に係るデータに対し、その加工内容及び要求仕様を満足するための加工条件に係るデータが関連づけられて記憶される。そして前記加工内容に係るデータにはワーク材質、ワーク板厚、加工形状、段差、周辺の環境などのデータが含まれ、前記要求仕様に係るデータには加工速度、断線頻度、真直精度、面粗さ、形状誤差などのデータが含まれ、また、前記加工条件に係るデータには電圧波形、電圧極性、電流波形、放電時間、休止時間、加工液量、加工液圧、ワイヤ張力、ワイヤ送り制御などのデータが含まれる。それぞれの加工情報データは、該加工情報データを一意に識別する識別情報と関連付けられている。
加工条件導出部100は、例えば加工情報データベース200に記憶された加工情報データに基づいて、オペレータから入力された加工内容及び要求仕様を満足すると推定される所定の加工条件を導出してもよい。この場合、加工条件導出部100は、オペレータから入力された加工内容に係るデータ及び要求仕様に係るデータと、加工情報データベース200に記憶される各加工情報データに含まれる加工内容に係るデータ及び要求仕様に係るデータとの間で類似検索を行う。類似検索では、例えばそれぞれの加工内容に係るデータ及び要求仕様に係るデータをベクトルに見立てた場合の距離を計算し、最も距離が近いものを類似度が高い加工情報データとして抽出する。そして、抽出した加工情報データに含まれる加工条件に対して、所定の変化を加えた複数の加工条件を、加工内容及び要求仕様を満足すると推定される所定の加工条件として導出する。
説明を簡単にするために、加工条件として電圧値、放電時間の2つの条件項目があるとする。また、電圧値については±0.1V、放電時間は±1μsecが所定の変化として予め定義されているとする。この時、加工条件導出部100は、加工情報データベース200から抽出した加工情報データに対して、以下8つの変化を加えることで加工条件を導出する。
(加工条件1)電圧値+0.1V
(加工条件2)電圧値-0.1V
(加工条件3)放電時間+1μsec
(加工条件4)放電時間-1μsec
(加工条件5)電圧値+0.1V,放電時間+1μsec
(加工条件6)電圧値+0.1V,放電時間-1μsec
(加工条件7)電圧値-0.1V,放電時間+1μsec
(加工条件8)電圧値-0.1V,放電時間-1μsec
インタフェース21は、CPU11と機械学習器2とを接続するためのインタフェースである。機械学習器2は、機械学習器2全体を統御するプロセッサ201と、システム・プログラム等を記憶したROM202、機械学習に係る各処理における一時的な記憶を行うためのRAM203、及び学習の対象となるデータ群を学習したモデル等の記憶に用いられる不揮発性メモリ204を備える。機械学習器2は、インタフェース21を介して加工条件推定装置1で生成されたデータ(例えば、加工内容に係るデータや、要求仕様に係るデータ、加工条件に係るデータ等)を観測することができる。また、加工条件推定装置1は、機械学習器2から出力される処理結果をインタフェース21を介して取得し、取得した結果を記憶したり、表示したり、他の装置に対してネットワーク5等を介して送信する。なお、図1では機械学習器2は加工条件推定装置1に内蔵されているが、加工条件推定装置1との間で所定のインタフェースを介して外部接続されていてもよい。
本実施形態による加工条件推定装置1が備える各機能は、図4に示した加工条件推定装置1が備えるCPU11及び機械学習器2が備えるプロセッサ201がそれぞれシステム・プログラムを実行し、加工条件推定装置1及び機械学習器2の各部の動作を制御することにより実現される。
機械学習部205が備える学習部206は、加工情報データベース200に記憶された加工情報データに基づいて、加工内容に係るデータ及び要求仕様に係るデータと、加工条件に係るデータとの間の相関性を学習したモデルを作成し、作成したモデルをモデル記憶部209に記憶する。学習部206が行う学習は、例えば公知の教師あり学習であってよい。学習部206が作成するモデルは、機械学習を行うことで加工内容に係るデータ及び要求仕様に係るデータが入力されると、その加工内容及び要求仕様を満足する加工条件に係るデータを推定することが可能なものとなる。学習部206が作成するモデルとしては、例えば回帰学習器や多層ニューラルネットワーク等が挙げられる。
5 ネットワーク
6 フォグコンピュータ
7 クラウドサーバ
8 ワイヤ放電加工機
11 CPU
12 ROM
13 RAM
14 不揮発性メモリ
15,17,18,20,21 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 加工条件導出部
110 シミュレーション部
120 加工条件評価部
130 データベース更新部
2 機械学習器
201 プロセッサ
202 ROM
203 RAM
204 不揮発性メモリ
205 機械学習部
206 学習部
208 推定部
209 モデル記憶部
Claims (2)
- ワイヤ放電加工機における加工条件を推定する加工条件推定装置であって、
加工内容に係るデータ及び要求仕様に係るデータに対して該加工内容及び該要求仕様を満足する加工条件に係るデータが関連付けられた加工情報データが記憶された加工情報データベースと、
前記加工情報データベースに記憶された加工情報データに基づいて、所望の加工内容及び要求仕様を満足すると推定される少なくとも1つの加工条件を導出する加工条件導出部と、
前記加工条件導出部が導出した加工条件に基づいてワイヤ放電加工機のシミュレーションを実行するシミュレーション部と、
前記シミュレーション部によるシミュレーションの結果に基づいて、前記加工条件を評価する加工条件評価部と、
前記加工条件評価部による評価の結果に基づいて、前記加工情報データベースを更新するデータベース更新部と、
を備えた加工条件推定装置。 - さらに、前記加工情報データベースに記憶された加工条件データに基づいて、加工内容に係るデータ及び要求仕様に係るデータと、加工条件に係るデータとの相関性を学習する機械学習部を備え、
前記加工条件導出部は、前記機械学習部による学習結果に基づいて、所望の加工内容及び要求仕様を満足すると推定される少なくとも1つの加工条件を導出する、
請求項1に記載の加工条件推定装置。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2023511061A JP7492080B2 (ja) | 2021-03-29 | 2022-03-23 | 加工条件推定装置 |
US18/548,906 US20240139846A1 (en) | 2021-03-29 | 2022-03-23 | Machining condition estimation device |
EP22780385.5A EP4316714A1 (en) | 2021-03-29 | 2022-03-23 | Processing-condition estimation device |
CN202280023723.6A CN117042906A (zh) | 2021-03-29 | 2022-03-23 | 加工条件推定装置 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2021055156 | 2021-03-29 | ||
JP2021-055156 | 2021-03-29 |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2022210170A1 true WO2022210170A1 (ja) | 2022-10-06 |
WO2022210170A9 WO2022210170A9 (ja) | 2023-07-20 |
Family
ID=83456748
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2022/013554 WO2022210170A1 (ja) | 2021-03-29 | 2022-03-23 | 加工条件推定装置 |
Country Status (5)
Country | Link |
---|---|
US (1) | US20240139846A1 (ja) |
EP (1) | EP4316714A1 (ja) |
JP (1) | JP7492080B2 (ja) |
CN (1) | CN117042906A (ja) |
WO (1) | WO2022210170A1 (ja) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06320389A (ja) * | 1993-05-18 | 1994-11-22 | Mitsubishi Electric Corp | 加工条件決定装置 |
JPH07116927A (ja) * | 1993-10-21 | 1995-05-09 | Sodick Co Ltd | 放電加工の加工設定データ決定装置と方法 |
JP2002160127A (ja) | 2000-09-13 | 2002-06-04 | Japan Science & Technology Corp | ワイヤ放電加工シミュレーション・システム |
JP2010042499A (ja) * | 2008-07-18 | 2010-02-25 | Mitsubishi Electric Corp | 加工条件探索装置 |
WO2020255370A1 (ja) | 2019-06-21 | 2020-12-24 | 三菱電機株式会社 | 加工条件探索装置およびワイヤ放電加工機 |
-
2022
- 2022-03-23 CN CN202280023723.6A patent/CN117042906A/zh active Pending
- 2022-03-23 EP EP22780385.5A patent/EP4316714A1/en active Pending
- 2022-03-23 WO PCT/JP2022/013554 patent/WO2022210170A1/ja active Application Filing
- 2022-03-23 JP JP2023511061A patent/JP7492080B2/ja active Active
- 2022-03-23 US US18/548,906 patent/US20240139846A1/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06320389A (ja) * | 1993-05-18 | 1994-11-22 | Mitsubishi Electric Corp | 加工条件決定装置 |
JPH07116927A (ja) * | 1993-10-21 | 1995-05-09 | Sodick Co Ltd | 放電加工の加工設定データ決定装置と方法 |
JP2002160127A (ja) | 2000-09-13 | 2002-06-04 | Japan Science & Technology Corp | ワイヤ放電加工シミュレーション・システム |
JP2010042499A (ja) * | 2008-07-18 | 2010-02-25 | Mitsubishi Electric Corp | 加工条件探索装置 |
WO2020255370A1 (ja) | 2019-06-21 | 2020-12-24 | 三菱電機株式会社 | 加工条件探索装置およびワイヤ放電加工機 |
Non-Patent Citations (1)
Title |
---|
KUNIEDA MASANORI: "Simulation of Electrical Discharge Machining", JOURNAL OF THE JAPAN SOCIETY FOR PRECISION ENGINEERING, vol. 76, no. 8, 2010, pages 861 - 866 |
Also Published As
Publication number | Publication date |
---|---|
WO2022210170A9 (ja) | 2023-07-20 |
JP7492080B2 (ja) | 2024-05-28 |
US20240139846A1 (en) | 2024-05-02 |
CN117042906A (zh) | 2023-11-10 |
JPWO2022210170A1 (ja) | 2022-10-06 |
EP4316714A1 (en) | 2024-02-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10564611B2 (en) | Control system and machine learning device | |
CN109960219B (zh) | 控制装置以及机器学习装置 | |
US10331104B2 (en) | Machine tool, simulation apparatus, and machine learning device | |
CN106552974B (zh) | 具有移动轴异常负载警告功能的线放电加工机 | |
CN108241342B (zh) | 数值控制装置以及机器学习装置 | |
US20180267489A1 (en) | Cleaning process optimization device and machine learning device | |
US20190196454A1 (en) | Chip removal apparatus and information processing apparatus | |
CN109725606B (zh) | 加工条件调整装置以及机器学习装置 | |
US11897066B2 (en) | Simulation apparatus | |
US20170090452A1 (en) | Machine tool for generating speed distribution | |
CN109794657B (zh) | 控制装置以及机器学习装置 | |
CN110347120A (zh) | 控制装置以及机器学习装置 | |
JP2019139755A (ja) | 研磨工具摩耗量予測装置、機械学習装置及びシステム | |
JP2019082836A (ja) | 工具寿命予測装置 | |
CN110171159A (zh) | 控制装置以及机器学习装置 | |
JP2019145086A (ja) | 制御装置、機械学習装置及びシステム | |
JP6841852B2 (ja) | 制御装置及び制御方法 | |
US10698380B2 (en) | Numerical controller | |
US11579000B2 (en) | Measurement operation parameter adjustment apparatus, machine learning device, and system | |
WO2022210170A1 (ja) | 加工条件推定装置 | |
US11556142B2 (en) | Warm-up evaluation device, warm-up evaluation method, and warm-up evaluation program | |
JP6940425B2 (ja) | 制御装置及び機械学習装置 | |
WO2022210472A1 (ja) | 加工条件調整装置 | |
JP2019184575A (ja) | 測定動作パラメータ調整装置、機械学習装置及びシステム | |
JP7417922B2 (ja) | 知識モデル構築システム及び知識モデル構築方法 |
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: 22780385 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2023511061 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18548906 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202280023723.6 Country of ref document: CN |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2022780385 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2022780385 Country of ref document: EP Effective date: 20231030 |