CN113993646B - Machining condition search device and wire electric discharge machine - Google Patents
Machining condition search device and wire electric discharge machine Download PDFInfo
- Publication number
- CN113993646B CN113993646B CN201980097579.9A CN201980097579A CN113993646B CN 113993646 B CN113993646 B CN 113993646B CN 201980097579 A CN201980097579 A CN 201980097579A CN 113993646 B CN113993646 B CN 113993646B
- Authority
- CN
- China
- Prior art keywords
- machining
- condition
- discharge energy
- unit
- machining condition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- B23H1/00—Electrical discharge machining, i.e. removing metal with a series of rapidly recurring electrical discharges between an electrode and a workpiece in the presence of a fluid dielectric
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- Electrical Discharge Machining, Electrochemical Machining, And Combined Machining (AREA)
Abstract
A machining condition search device (1) searches for a machining condition for electric discharge machining in a wire electric discharge machine (100) that performs electric discharge machining by generating electric discharge in a gap between a wire and a workpiece. A processing condition search device (1) is provided with: a screening unit (10) that divides a discharge energy range, which is a range in which a discharge energy value relating to each preset machining condition is distributed, into a plurality of discharge energy ranges, reads out the machining conditions of each of the plurality of discharge energy ranges, and screens a set of machining conditions to be searched by determining 1 of the plurality of discharge energy ranges based on a result of trial machining according to each of the read-out machining conditions; and a machining condition determination unit (11) that determines a machining condition for electric discharge machining from the machining condition group.
Description
Technical Field
The present invention relates to a machining condition search device for searching for a machining condition of an electric discharge machining device, and a wire electric discharge machine.
Background
A wire electric discharge machine machines a workpiece by generating electric discharge in a gap between a wire and the workpiece. The wire electric discharge machine can change the state of the machining process by changing the machining conditions in the machining process. The processing conditions include a plurality of control parameters. The machining condition is configured by selecting 1 of the plurality of control parameters from the values at which the control parameters are obtained. In a wire electric discharge machine, it is required to select a machining condition that can satisfy a surface roughness required for a machined surface and a shape accuracy required for a machined product, and that has a high machining speed and does not cause wire breakage.
Patent document 1: japanese patent laid-open No. 2008-36812
Disclosure of Invention
However, according to the technique of patent document 1, since the machining condition selected for trial machining deviates from the optimum machining condition, in the search using 1 of the selected machining conditions as the starting point, the selected machining condition may reach a local optimum solution in a searchable range, instead of the optimum machining condition. In this case, the search by the machining condition search means is completed under a machining condition that has reached a lower machining speed than the case of the optimum machining condition, and therefore the machining condition search means cannot search for the optimum machining condition. As described above, according to the technique of patent document 1, there is a problem that the machining condition search device cannot search for a machining condition in which the machining speed is high and the wire breakage does not occur.
The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a machining condition search device capable of searching for a machining condition in which a wire breakage does not occur at a high machining speed.
In order to solve the above-described problems and achieve the object, a machining condition search device according to the present invention searches for machining conditions for electric discharge machining in a wire electric discharge machine that performs electric discharge machining by generating electric discharge in a gap between a wire and a workpiece. The processing condition search device according to the present invention includes: a screening unit that divides an electrical discharge energy range, which is a range in which electrical discharge energy values relating to each of preset machining conditions are distributed, into a plurality of electrical discharge energy ranges, reads out the machining conditions of each of the plurality of electrical discharge energy ranges, and screens a set of machining conditions to be searched by specifying 1 of the plurality of electrical discharge energy ranges based on a result of trial machining according to each of the read-out machining conditions; and a machining condition determining unit that determines a machining condition for the electric discharge machining from the machining condition group.
ADVANTAGEOUS EFFECTS OF INVENTION
The machining condition search device according to the present invention has an effect of being able to search for machining conditions that have a high machining speed and do not cause wire breakage.
Drawings
Fig. 1 is a diagram showing a processing condition search device according to embodiment 1 of the present invention.
Fig. 2 is a view showing a schematic configuration of the wire electric discharge machine shown in fig. 1.
Fig. 3 is a diagram showing a configuration of a filtering unit included in the machining condition search device according to embodiment 1.
Fig. 4 is a diagram showing an example of data stored in the machining condition database of the screening unit shown in fig. 3.
Fig. 5 is a diagram for explaining the values of the discharge energy stored in the machining condition database included in the screening unit shown in fig. 3.
Fig. 6 is a diagram for explaining a relationship between a value of the discharge energy and the machining speed stored in the machining condition database included in the screening unit shown in fig. 3.
Fig. 7 is a view 1 for explaining the operation of the trial machining instructing section included in the screening section shown in fig. 3.
Fig. 8 is a view 2 for explaining the operation of the trial machining instructing section included in the screening section shown in fig. 3.
Fig. 9 is a diagram showing a configuration of a machining condition determining unit included in the machining condition search device according to embodiment 1.
Fig. 10 is a flowchart showing an operation procedure of the machining condition search device according to embodiment 1.
Fig. 11 is a diagram showing a modification of the machining condition determining unit included in the machining condition search device according to embodiment 1.
Fig. 12 is a block diagram showing a functional configuration of a machine learning device provided in the processing condition determination unit shown in fig. 11.
Fig. 13 is a flowchart showing an operation procedure of the machine learning device included in the processing condition determination unit shown in fig. 11.
Fig. 14 is a diagram showing an example of a hardware configuration in a case where the function of the machining condition search device according to embodiment 1 is realized using a computer system.
Fig. 15 is a diagram showing a wire electric discharge machine according to embodiment 2 of the present invention.
Fig. 16 is a diagram showing a configuration of a filtering unit included in a machining condition search device according to embodiment 3 of the present invention.
Detailed Description
Hereinafter, a machining condition search device and a wire electric discharge machine according to an embodiment of the present invention will be described in detail with reference to the drawings. The present invention is not limited to the embodiments.
Fig. 1 is a diagram showing a machining condition search device according to embodiment 1 of the present invention. The machining condition search device 1 searches for a machining condition for electric discharge machining performed by the wire electric discharge machine 100. Fig. 1 shows a machining condition search device 1 and a wire electric discharge machine 100 connected to the machining condition search device 1.
Fig. 2 is a view showing a schematic configuration of the wire electric discharge machine shown in fig. 1. The wire electric discharge machine 100 machines the workpiece 24 by generating electric discharge in a gap between the wire 30 and the workpiece 24. The wire electric discharge machine 100 includes a machining unit 20 that performs machining of a workpiece 24 and a control device 21 that controls the entire wire electric discharge machine 100. The control device 21 includes a processing control unit 22 that controls the processing unit 20.
The processing unit 20 includes: a table 33 on which the workpiece 24 is placed; a drive device 23 for moving the table 33; a power supply 25; a wire bobbin 26 that draws out a wire 30 as a wire electrode; a pair of power feeding members 31 in contact with the wires 30; and a pair of wire guides 32 that support the wires 30. The power supply 25 applies a pulse voltage between the power supply 31 and the stage 33. The processing unit 20 includes: a feed roller 27 that advances the wire 30 drawn out from the bobbin 26 toward the workpiece 24; a recovery roller 29 that recovers the thread 30; and a lower roller 28 that advances the wire 30 passing through the workpiece 24 toward a recovery roller 29. The machining control unit 22 controls the driving device 23 and the power supply 25.
Fig. 1 shows a functional configuration of the machining condition search device 1. The machining condition search device 1 includes a screening unit 10, and the screening unit 10 divides an electrical discharge energy range, which is a range in which a value of electrical discharge energy for each preset machining condition is distributed, into a plurality of electrical discharge energy ranges, reads the machining conditions for each of the plurality of electrical discharge energy ranges, and identifies 1 of the plurality of electrical discharge energy ranges based on a result of trial machining for each of the read machining conditions, thereby screening a set of machining conditions to be searched. The machining condition search device 1 includes: a machining condition determining unit 11 that determines machining conditions for electric discharge machining from the machining condition group selected by the selecting unit 10; and a display unit 12 that displays information related to the machining condition determined by the machining condition determination unit 11.
The machining condition search device 1 according to embodiment 1 performs the screening of the machining condition group in the screening unit 10, and the machining condition determination unit 11 performs the search for the machining condition from the screened machining condition group. The machining instruction 13 is an instruction for trial machining and is output from the machining condition search device 1 to the machining control unit 22. The machining result information 14 is information obtained by trial machining and is output from the machining control unit 22 to the machining condition search device 1. The trial processing is described later. The search target data 15 is data related to the set of processing conditions screened by the screening unit 10. The machining condition information 16 is information on the machining condition determined by the machining condition determining unit 11.
Fig. 3 is a diagram showing a configuration of a filtering unit included in the processing condition search device according to embodiment 1. The screening unit 10 includes: a machining condition database 40 for storing data of machining conditions and discharge energy; a trial machining instruction unit 41 that outputs a machining instruction 13 to the wire electric discharge machine 100; and a search range determination unit 42 that determines a search range of the machining condition. The screening unit 10 includes a condition information storage unit 43 and a range information storage unit 44.
Next, each functional unit included in the screening unit 10 will be described. The machining condition database 40 stores data of discharge energy for each preset machining condition. The processing conditions include a plurality of control parameters.
Fig. 4 is a diagram showing an example of data stored in the machining condition database of the screening unit shown in fig. 3. The plurality of control parameters include various parameters for controlling the electric discharge machining, such as a voltage value, a current value, a rest time, and a usage amount of the wire 30. The voltage value is a value of the interelectrode voltage. The interelectrode voltage is a voltage applied between the work 24 and the wire 30. The current value is a value of the current supplied from the power supply 25. The rest time is a time at which discharge is to be stopped. Here, detailed description about the control parameters is omitted. The number of control parameters included in the machining conditions is set to an arbitrary number. Fig. 4 shows an example of data stored in the machining condition database 40 for 6 control parameters C1, C2, C3, C4, C5, and C6 among a plurality of control parameters included in the machining conditions.
In embodiment 1, 211200 machining conditions can be set by making the values of the plurality of control parameters different from each other. In the machining condition database 40, the machining condition number, each of the values of the plurality of control parameters, and the value of the discharge energy are associated with each other for all 211200 machining conditions set in advance. The machining condition number is a number assigned to each machining condition to identify the machining condition. The machining condition numbers are assigned in the order of high to low discharge energy.
In the machining condition database 40, each value of the plurality of control parameters and the value of the discharge energy are stored for each of the machining conditions from "1" to "211200" of the machining condition numbers. Fig. 4 shows the values of the control parameters C1, C2, C3, C4, C5, and C6 and the values of the discharge energy among the plurality of parameters, with respect to the machining conditions with the machining condition numbers from "1" to "10". The value of the discharge energy is a value of the discharge energy per unit time. Each value of the discharge energy shown in fig. 4 is a relative value when the maximum value of the discharge energy in the machining performed by the wire electric discharge machine 100 is "1".
Fig. 5 is a diagram for explaining the values of the discharge energy stored in the machining condition database included in the screening unit shown in fig. 3. Fig. 5 shows a waveform of a discharge current in 1 discharge. In fig. 5, the vertical axis represents the discharge current, and the horizontal axis represents time. The wire electric discharge machine 100 performs electric discharge machining by generating an electric discharge current shown in fig. 5 several tens to several hundreds of thousands of times per unit time.
The value of the discharge energy for 1 discharge was calculated by finding the area of the waveform shown in fig. 5. The value of the discharge energy per unit time can be estimated based on the value of the discharge energy generated by 1 discharge and characteristic values such as the rest time, the command value of the machining speed, the command value of the inter-electrode voltage, and the discharge current control. The value of the discharge energy for each machining condition was obtained based on the measurement value of the oscilloscope. The value of the discharge energy associated with a part of all the machining conditions may be obtained based on the measurement value, and the value of the discharge energy associated with the other machining conditions may be calculated by interpolation of the measurement value or based on the design value of the machining condition set by the on-line electric discharge machine 100. The value of the discharge energy related to the machining condition may be calculated based on a design value such as a voltage value of the machining-gap voltage, a time during which the machining-gap voltage is applied, or a resistance value in the power supply circuit.
Fig. 6 is a diagram for explaining a relationship between a value of discharge energy and a machining speed stored in a machining condition database included in the screening unit shown in fig. 3. In fig. 6, the relationship between the measured value of the machining speed and the measured value of the discharge energy is shown by white dots. In fig. 6, the vertical axis represents the machining speed, and the horizontal axis represents the discharge energy. In fig. 6, the machining speed is represented as a relative value when an arbitrary speed value is set to "1". The discharge energy is expressed as a relative value when an arbitrary discharge energy value is set to "1". Data in high energy conditions where the line 30 is broken is evident is excluded in fig. 6. A drawing with a processing speed of zero indicates that a wire break has occurred. As shown in fig. 6, a proportional relationship holds between the discharge energy and the machining speed. In addition, when the discharge energy is lower than that in the case of the high energy condition in which the disconnection of the line 30 is conspicuous, the disconnection may occur depending on the content of the control parameter.
The machining condition search device 1 searches for an optimum machining condition, which is a machining condition when the machining speed is highest and wire breakage does not occur, among all preset machining conditions. Among all the machining conditions, the machining conditions in which the discharge energy is so high that the wire breakage is conspicuous are excluded from the results of the search by the machining condition search device 1. In addition, among all the machining conditions, the machining condition having a lower machining speed than the lowest value of the machining speed required for the machining by the machining condition search device 1 is excluded from the search result by the machining condition search device 1. The black circles shown in fig. 6 indicate examples of the minimum values of the machining speed required for machining.
As the 1 st stage of the search of the machining condition in the machining condition search device 1, the filtering unit 10 determines the range of the machining condition number as the search range, and filters the search range. As the 2 nd stage of the search of the machining condition in the machining condition search device 1, the machining condition determination unit 11 searches for the machining condition in the range screened by the screening unit 10.
Fig. 7 is a view 1 for explaining the operation of the trial machining instructing section included in the screening section shown in fig. 3. In the graph shown in fig. 7, the horizontal axis represents the machining condition number, and the vertical axis represents the discharge energy. The trial machining instruction unit 41 divides a discharge energy range, which is a range in which a value of discharge energy for each preset machining condition is distributed, into a plurality of discharge energy ranges, and reads out the machining conditions of each of the plurality of discharge energy ranges from the machining condition database 40. In embodiment 1, the trial machining instruction unit 41 divides the discharge energy range relating to all preset machining conditions into 5 discharge energy ranges, and reads data of the machining conditions for each of the 5 discharge energy ranges. Each of the 5 circles shown in fig. 7 represents an overview of the discharge energy range of the machining condition to be read.
The trial machining instructing unit 41 divides the entire discharge energy range relating to all preset machining conditions into a plurality of discharge energy ranges each of which is a uniform discharge energy range. In embodiment 1, the trial machining instructing unit 41 divides the discharge energy range from the maximum value to the minimum value among the discharge energy values relating to all preset machining conditions equally into 5 parts. Thus, the screening unit 10 reads out the machining conditions for the trial machining without variation from the entire discharge energy range for all the preset machining conditions.
Here, an example of processing performed by the trial machining instructing unit 41 to determine each discharge energy range will be described. The trial machining instructing unit 41 reads out the value of the discharge energy closest to the maximum value of the discharge energy, that is, the value of the discharge energy in the machining condition number "1", from the machining condition database 40. The trial processing instruction section 41 obtains the respective values of 4 in 5 minutes, 3 in 5 minutes, 2 in 5 minutes and 1 in 5 minutes of the maximum value.
The trial machining instructing unit 41 reads the data of the machining condition number "1" from the machining condition database 40. The trial machining instruction unit 41 reads out the data of the machining conditions having the values of the discharge energy that match the respective values of 4 out of 5, 3 out of 5, 2 out of 5, and 1 out of 5 from the machining condition database 40. When there is no machining condition in which the value of the discharge energy matches the value of 4/5 of the maximum value, the trial machining instructing unit 41 reads out data of the machining condition in which the value of the discharge energy is closest to the value of 4/5 of the maximum value. The same applies to the case where there is no machining condition in which the value of the discharge energy matches each of the values of 3 to 5, 2 to 5, or 1 to 5 of the maximum value.
For example, if the value closest to 4/5 of the maximum value among the values of the discharge energy stored in the machining condition database 40 is "0.800005", which is the value of the discharge energy of the machining condition number "41780", the trial machining instruction unit 41 reads the data of the machining condition number "41780". When the value closest to 3/5 of the maximum value among the values of the discharge energy stored in the machining condition database 40 is "0.600006" which is the value of the discharge energy of the machining condition number "83465", the trial machining instruction unit 41 reads the data of the machining condition number "83465". When the value closest to 2/5 of the maximum value among the values of the discharge energy stored in the machining condition database 40 is "0.400006", which is the value of the discharge energy of the machining condition number "125340", the trial machining instruction unit 41 reads the data of the machining condition number "125340". When the value closest to 1/5 of the maximum value among the values of the discharge energy stored in the machining condition database 40 is "0.200016", which is the value of the discharge energy of the machining condition number "167613", the trial machining instruction unit 41 reads the data of the machining condition number "167613".
When there are a plurality of machining conditions, i.e., a value of the discharge energy that is closest to 4/5 of the maximum value, the trial machining instructing unit 41 selects 1 of the plurality of machining conditions and reads data of the selected machining condition. The same applies to the case where there are a plurality of machining conditions, i.e., the values of the discharge energy and the values closest to 3/5, 2/5, or 1/5 of the maximum value.
Thus, the trial machining instructing unit 41 extracts the data of 5 machining conditions having different discharge energies from the data of the full machining condition. The trial machining instruction unit 41 extracts the data of the machining conditions for 4 machining conditions having consecutive machining condition numbers in the machining condition number from which the data is extracted.
Fig. 8 is a view 2 for explaining an operation of the trial machining instructing unit included in the screening unit shown in fig. 3. In the above example, the trial machining instructing unit 41 extracts data of each of the machining conditions "2" to "5" which are consecutive to the machining condition number "1". The trial machining instruction unit 41 extracts the data of the respective machining conditions of the machining condition numbers "41781" to "41784" consecutive to the machining condition number "41780", the data of the respective machining conditions of the machining condition numbers "83466" to "83469" consecutive to the machining condition number "83465", the data of the respective machining conditions of the machining condition numbers "125341" to "125344" consecutive to the machining condition number "125340", and the data of the respective machining conditions of the machining condition numbers "167614" to "167617" consecutive to the machining condition number "167613".
Thus, the trial machining instruction unit 41 extracts data of the machining conditions for each of the 5 discharge energy ranges. The trial machining instructing unit 41 equally divides the entire range of the discharge energy into 5 pieces, and extracts the data of the machining conditions for each of the divided ranges. In the following description, the 5 discharge energy ranges are sometimes referred to as a 1 st discharge energy range, a 2 nd discharge energy range, a 3 rd discharge energy range, a 4 th discharge energy range, and a 5 th discharge energy range, respectively, in the order of the discharge energy from high to low.
The condition information storage unit 43 stores information on conditions set in advance to determine the discharge energy range. The condition information storage unit 43 stores the number of divisions of the discharge energy range and the number of machining conditions for each discharge energy range. In embodiment 1, the condition information holding unit 43 holds the division number "5" and the machining condition number "5". The trial machining instructing unit 41 reads the division number and the machining condition number from the condition information storage unit 43, and extracts the data of the machining condition in accordance with the read division number and the machining condition number. The condition information storage unit 43 can store the division number and the machining condition number input by the user of the machining condition search device 1. In this case, the division number and the machining condition number stored in the condition information storage unit 43 are updated by an input operation of the user.
The trial machining instruction unit 41 outputs the machining instruction 13 based on the extracted data of each machining condition to the machining control unit 22. The wire electric discharge machine 100 performs trial machining in accordance with the machining instruction 13. As described above, the machining condition search device 1 outputs the machining instruction 13 to the machining control unit 22, thereby causing the wire electric discharge machine 100 to perform the trial machining for sorting the machining condition groups. The trial machining instruction unit 41 instructs the wire electric discharge machine 100 to perform 5 trial machining under different machining conditions in the 1 st to 5 th electric discharge energy ranges. The wire electric discharge machine 100 performs 5 trial machining operations under different machining conditions for each of the 1 st to 5 th discharge energy ranges. That is, the wire electric discharge machine 100 performs 25 trial machining operations under different machining conditions. The machining control unit 22 outputs the machining result information 14 including the wire breakage information during the trial machining to the trial machining instruction unit 41.
Next, the trial machining instructing unit 41 determines a discharge energy range closest to the broken line boundary point from the 1 st to 5 th discharge energy ranges. The broken line boundary point is a value at which the discharge energy is increased from the minimum value to the boundary point at which the broken line occurs due to the high energy of the discharge energy. The trial machining instructing unit 41 determines the discharge energy range closest to the broken line boundary point based on the broken line information obtained by the trial machining for each discharge energy range.
Here, the 1 st discharge energy range is defined as the occurrence of wire breakage in all of the 5 trial machining. The 2 nd discharge energy range is set such that wire breakage occurs 3 times out of 5 trial machining, and wire breakage does not occur 2 times. The 3 rd energy range is defined as 1 out of 5 trial processes in which wire breakage occurred, and 4 times in which wire breakage did not occur. The 4 th discharge energy range is set so that no wire breakage occurs in all of the 5 trial machining. The 5 th discharge energy range is also set so that no wire breakage occurs in all of the 5 test machining.
The trial machining instructing unit 41 determines, as the discharge energy range closest to the wire breakage boundary point, the discharge energy range having the highest discharge energy among the discharge energy ranges of the trial machining in which the wire breakage occurs and the trial machining in which the wire breakage does not occur. In the case of the above example, since all the trial machining has been broken in the 1 st discharge energy range, the trial machining instructing unit 41 determines that the 1 st discharge energy range is not the discharge energy range closest to the broken line boundary point. In addition, since no wire breakage occurs in all of the 4 th and 5 th discharge energy ranges, the trial machining instructing unit 41 determines that the 4 th and 5 th discharge energy ranges are not the discharge energy range closest to the wire breakage boundary point. The trial machining instruction unit 41 determines the 2 nd discharge energy range, which is the discharge energy range having the higher discharge energy among the 2 nd and 3 rd discharge energy ranges in which the trial machining in which the wire breakage occurs and the trial machining in which the wire breakage does not occur, as the discharge energy range closest to the wire breakage boundary point.
As described above, the screening unit 10 selects, as the discharge energy range closest to the wire breakage boundary point, the discharge energy range in which both the trial machining in which the wire breakage occurs and the trial machining in which the wire breakage does not occur are included in the plurality of trial machining for each discharge energy range among the plurality of discharge energy ranges, and the discharge energy range having the highest value of the discharge energy. The screening unit 10 selects the discharge energy range, thereby identifying 1 of the plurality of discharge energy ranges.
As shown in fig. 6, since the machining speed is higher as the discharge energy is higher, the machining condition in which the machining speed is high and the wire 30 is not broken can be regarded as being searchable from the machining conditions in the discharge energy range close to the broken wire boundary point. However, with regard to the combination of control parameters included in the machining conditions, wire breakage may occur even when the discharge energy is lower than the wire breakage boundary point. The trial machining instructing unit 41 can accurately determine whether or not the wire electric discharge machine 100 is the closest discharge energy range to the broken wire boundary point by causing the wire electric discharge machine 100 to perform a plurality of trial machining operations under different machining conditions for each discharge energy range.
If the trial machining instructing unit 41 determines the discharge energy range closest to the disconnection boundary point, it outputs boundary range information 45, which is information on the determined discharge energy range, to the search range determining unit 42. The boundary range information 45 includes information indicating the determined discharge energy range and disconnection information related to the determined discharge energy range. In the above example, the trial machining instructing unit 41 outputs boundary range information 45 including information indicating the 2 nd discharge energy range and wire breakage information obtained by trial machining under each machining condition to the search range determining unit 42.
The search range determination unit 42 determines a search range based on the boundary range information 45. Here, an example of processing performed by the search range determining unit 42 to determine the machining condition group will be described. When the boundary range information 45 including the information indicating the 2 nd discharge energy range is input to the search range determination unit 42, the search range determination unit 42 determines "0.800005", which is the value closest to 4 out of 5 of the maximum value, as the reference value, and determines the search range based on the reference value. The search range determination unit 42 determines a constant discharge energy range width including "0.800005" as a reference value as a search range.
The search range determining unit 42 determines the discharge energy range serving as the search range, and thereby selects a machining condition group including the discharge energy value in the discharge energy range as a machining condition group to be searched. The machining condition search device 1 determines the search range in the search range determination unit 42, and can thereby filter the set of machining conditions to be searched from all the machining conditions.
The search range determining unit 42 reads out data of each machining condition from the machining condition database 40 for the machining condition group included in the specified search range. The search range determination unit 42 outputs the search target data 15, which is the data read from the machining condition database 40, to the machining condition determination unit 11.
The search range determining unit 42 can determine the search range by the range of the machining condition number. In this case, the search range determination unit 42 determines "41780" as the reference value because the value of the discharge energy closest to 4/5 of the maximum value is the value of the discharge energy of the machining condition number "41780". The search range determining unit 42 determines a certain range width including "41780" which is a reference value, as a search range. For example, the predetermined range width is a machining condition number range of "± 50" centered on the reference value.
The range information storage unit 44 stores range information set in advance to determine a search range. The range information is information related to processing for determining the search range based on the boundary range information 45, and includes information related to processing for determining the reference value and information related to the above-described range width. The search range determining unit 42 reads the range information from the range information storage unit 44, and determines the search range according to the read range information. The range information input by the user of the machining condition search device 1 may be stored in the range information storage unit 44. In this case, the range information stored in the range information storage unit 44 is updated by an input operation by the user.
As the set range width of the machining condition search device 1 becomes smaller, it is possible to perform a search in which it is more important to shorten the time required for the search than the accuracy of the search. The machining condition search device 1 can perform a search in which the accuracy of the search is emphasized more than the reduction in time as the set range width is larger. The user can cause the machining condition search device 1 to perform a search corresponding to the request by appropriately adjusting the range width.
Fig. 9 is a diagram showing the configuration of a machining condition determination unit included in the machining condition search device according to embodiment 1. The machining condition determining section 11 includes: a trial machining instruction unit 46 that outputs a machining instruction 13 to the wire electric discharge machine 100; and an optimization processing unit 47 that performs optimization processing for obtaining a processing condition that the processing speed is high and the wire 30 is not broken. The optimization unit 47 executes optimization processing according to the bayesian optimization method. The method for the optimization process may be a method other than bayesian optimization.
The search target data 15 is input to the optimization processing unit 47. The optimization processing unit 47 searches for the machining condition by the optimization processing, and outputs the search result 48, that is, the data of the machining condition, to the trial machining instruction unit 46. The trial machining instruction unit 46 outputs the machining instruction 13 based on the search result 48, that is, the data of the machining condition, to the machining control unit 22. The wire electric discharge machine 100 performs trial machining in accordance with the machining instruction 13. As described above, the machining condition search device 1 outputs the machining instruction 13 to the machining control unit 22, thereby causing the wire electric discharge machine 100 to perform trial machining for searching for the machining condition. The machining control unit 22 outputs the machining result information 14 including the wire breakage information during the trial machining and the information of the machining speed during the trial machining to the optimization processing unit 47.
The optimization processing unit 47 performs optimization processing based on the wire breakage information and the machining speed information included in the search result 48 and the machining result information 14. When determining that the machining condition having the highest machining speed without causing wire breakage is obtained, the optimization processing unit 47 determines the machining condition as the machining condition serving as the search result. The machining condition determining unit 11 outputs machining condition information 16, which is information related to the determined machining condition, to the display unit 12. The display unit 12 displays the machining condition information 16.
The optimization processing unit 47 updates a model for searching for a combination having the highest machining speed and not causing a wire break among the combinations of control parameters included in the search target data 15, based on the evaluation point. For example, the optimization processing unit 47 calculates the evaluation point based on a relational expression "evaluation point = machining speed x (1-wire breakage coefficient) during trial machining". The disconnection coefficient is a value indicating whether or not there is a disconnection, and is set to "0" when there is no disconnection, and is set to "1" when there is a disconnection. From this relationship, if there is no wire breakage, the higher the machining speed, the higher the evaluation point becomes. In addition, regardless of the machining speed, the evaluation point becomes zero when there is a wire break. The above relational expression used for the calculation of the evaluation point is an example, and the optimization processing unit 47 may calculate the evaluation point by a relational expression other than the above relational expression. The relation may contain a term for weighting corresponding to the number of wire breakage for a certain processing length.
At the start of the search, the optimization processing unit 47 outputs data relating to any one of the machining conditions included in the search target data 15 to the trial machining instruction unit 46 as a search result 48. The arbitrary machining conditions are randomly determined. The optimization processing unit 47 may select the machining condition based on a preset condition at the start of the search. Then, the optimization processing unit 47 calculates an evaluation point based on the wire breakage information and the machining speed obtained by the trial machining, and updates the model based on the evaluation point. The optimization processing unit 47 outputs the search result 48 obtained based on the updated model to the trial machining instructing unit 46. Thus, the updating and trial processing of the search result 48 are repeated.
When a preset termination condition is satisfied, the optimization processing unit 47 terminates the search for the machining condition. An example of the termination condition is a case where the search result 48 is not updated in a predetermined number of trial processes, for example, 10 trial processes. In another example of the end condition, a case where the machining speed reaches the target speed is given. The number of trial processing or the target speed set as the termination condition is set by an input operation performed by the user. The machining condition determining unit 11 may search for a machining condition by a machine learning method. The search for the machining conditions by the machine learning method is described later.
Fig. 10 is a flowchart showing an operation procedure of the processing condition search device according to embodiment 1. In step S1, the trial machining instruction unit 41 extracts the machining conditions for the trial machining from the machining conditions stored in the machining condition database 40. As described above, the trial machining instruction unit 41 extracts the machining conditions relating to the plurality of discharge energy ranges having different discharge energy values.
In step S2, the trial machining instruction unit 41 outputs the machining instruction 13 to the machining control unit 22, thereby instructing the wire electric discharge machine 100 to perform trial machining. In step S3, the trial machining instruction unit 41 obtains the wire breakage information indicating the occurrence state of the wire breakage during the trial machining from the machining control unit 22.
In step S4, the trial machining instruction unit 41 determines whether or not the trial machining related to all the machining conditions extracted in step S1 is completed. If there is a machining condition under which the trial machining is not completed (No at step S4), the trial machining instruction unit 41 repeats the sequence from step S2 for the machining condition under which the trial machining is not completed.
When trial machining is completed for all the machining conditions (Yes in step S4), the search range determining unit 42 determines a set of machining conditions to be searched for in step S5. In other words, the search range determining unit 42 determines the search range.
Next, in step S6, the machining condition determining unit 11 determines a machining condition from the machining condition group by the optimization processing in the optimization processing unit 47. In step S7, the display unit 12 displays information on the machining condition determined in step S6. Thereby, the machining condition search device 1 ends the operation of the procedure shown in fig. 10.
Next, a search for machining conditions according to the machine learning method will be described. Fig. 11 is a diagram showing a modification of the machining condition determining unit included in the machining condition search device according to embodiment 1. The processing condition determination unit 60 shown in fig. 11 includes a machine learning device 61 and an intention determination unit 62 instead of the optimization unit 47.
The machine learning device 61 learns the machining conditions under which the wire breakage does not occur and the machining speed is the highest. The intention determining unit 62 determines a processing condition as a search final result based on the result learned by the machine learning device 61. The machining result information 14 and the search target data 15 are input to the machine learning device 61.
Fig. 12 is a block diagram showing a functional configuration of a machine learning device provided in the processing condition determination unit shown in fig. 11. The machine learning device 61 includes a state observation unit 63 and a learning unit 64. The state observation unit 63 observes the wire breakage information and the machining speed included in the machining result information 14 and the search target data 15 as state variables. The learning unit 64 learns the machining conditions with the highest machining speed without wire breakage, in accordance with the training data set created based on the state variables.
Any learning algorithm may be used for the learning unit 64. As an example, a case where Reinforcement Learning (Reinforcement Learning) is applied will be described. Reinforcement learning refers to an action subject, an agent in a certain environment, observing a current state and determining an action to be taken. The agent selects an action to receive a return from the environment, and learns a countermeasure that is most returned by a series of actions. As a representative method of reinforcement learning, Q-learning (Q-learning), TD-learning (TD-learning), and the like are known. For example, in the case of Q learning, an action value table, which is a typical update of the action value function Q (s, a), is expressed by the following expression (1). The action cost function Q (s, a) represents an action cost Q, which is the cost of an action for selecting the action "a" based on the environment "s".
[ formula 1 ]
Q(s t ，a t )←Q(s t ，a t )+α(r t+1 +γmax a Q(s t+1 ，a t )-Q(s t ，a t ))…(1)
In the above formula (1), "s" is t+1 "indicates the environment at time" t ". "a" of t "represents an action at time" t ". By action "a t ", environment becomes" s t+1 ”。“r t+1 "indicates a return by a change in its environment. "γ" represents the discount rate. "α" represents a learning coefficient. When Q learning is applied, the value of the control parameter included in the search target data 15 becomes the action "a t ”。
The update represented by the above expression (1) is such that if the action value of the most favorable action "a" at the time "t +1" is greater than the action value Q of the action "a" executed at the time "t", the action value Q is increased, and conversely, the action value Q is decreased. In other words, the action-value function Q (s, a) is updated so that the action value Q of the action "a" at the time "t" approaches the best action value at the time "t + 1". Thus, the best action value in a certain environment is propagated to the action values in the previous environments in turn.
The learning unit 64 includes a reward calculation unit 65 and a function update unit 66. The reward calculation unit 65 calculates a reward based on the state variable. The function updating unit 66 updates the function for determining the machining condition for performing the electric discharge machining in accordance with the returns calculated by the return calculating unit 65.
The return calculation unit 65 calculates a return "r" based on the change in the machining speed and the presence or absence of a break. For example, the reward calculation unit 65 increases the reward "r" when the machining speed is increased or when the wire is not broken as a result of changing the value of the control parameter. The reward calculation unit 65 increases the reward "r" by giving a value of the reward, i.e., "1". The value of the reward is not limited to "1". In addition, the reward calculation unit 65 decreases the reward "r" when the machining speed decreases or the wire breakage occurs as a result of changing the value of the control parameter. The reward calculation unit 65 reduces the reward "r" by assigning a value of the reward "-1". The value of the reward is not limited to "-1".
The function updating unit 66 updates the function for determining the machining condition in accordance with the return calculated by the return calculating unit 65. The updating of the function can be performed according to the training data set, for example by updating an action value table. The action value table is a data set stored in the form of a table in which an arbitrary action and the action value are associated with each other. For example, in the case of Q learning, the action merit function Q(s) expressed by the above expression (1) is used t ，a t ) As a function for calculating the values of the respective control parameters.
Fig. 13 is a flowchart showing an operation procedure of the machine learning device included in the processing condition determination unit shown in fig. 11. A reinforcement learning method for updating the action merit function Q (s, a) will be described with reference to the flowchart of fig. 13.
In step S11, the state observation unit 63 acquires a state variable. In step S12, the return calculation unit 65 calculates a return "r" based on the change in the machining speed and the presence or absence of a break. In step S13, the function update unit 66 updates the action cost function Q (S, a) based on the return "r" calculated in step S12. The function update unit 66 updates the action cost function Q (s, a) according to the above equation (1).
In step S14, the function update unit 66 determines whether or not the action merit function Q (S, a) converges. The function updating unit 66 determines that the action cost function Q (S, a) converges, based on the fact that the updating of the action cost function Q (S, a) in step S13 is not performed.
If it is determined that the action cost function Q (S, a) does not converge (No at step S14), the machine learning device 61 returns the operation sequence to step S11. When it is determined that the action cost function Q (S, a) converges (Yes in step S14), the learning unit 64 ends the learning. Thereby, the device learning apparatus 61 ends the operation according to the procedure shown in fig. 13. The machine learning device 61 may continue the learning by returning the operation sequence from step S13 to step S11 without performing the determination of step S14.
The intention determining unit 62 selects the processing condition that gives the most returns, based on the updated action cost function Q (s, a) that is the result of learning by the learning unit 64. The intention determining unit 62 outputs the machining condition information 16, which is the information of the selected machining condition, to the display unit 12.
In embodiment 1, the case where the learning unit 64 executes machine learning by reinforcement learning is described. The learning unit 64 may perform machine learning according to other known methods, such as a neural network, genetic programming, functional logic programming, and a support vector machine. The machining condition determining unit 60 is not limited to searching for the machining condition by machine learning in the machine learning device 61, which is a component inside the machining condition searching device 1. The machining condition determination unit 60 may search for the machining condition by machine learning in a device external to the machining condition search device 1.
Next, a hardware configuration of the machining condition search device 1 according to embodiment 1 will be described. Each functional unit included in the machining condition search device 1 is realized by using a computer system such as a personal computer or a general-purpose computer. Fig. 14 is a diagram showing an example of a hardware configuration in a case where the function of the processing condition search device according to embodiment 1 is realized by using a computer system.
The machining condition search device 1 includes: a processor 51 that executes various processes; a memory 52 which is a built-in memory; an external storage device 53 that stores various information; an input/output interface 54 that handles input and output of various information; and a display 55 that displays various information.
The processor 51 is a CPU (Central Processing Unit). The Processor 51 may be a processing device, an arithmetic device, a microprocessor, a microcomputer, or a DSP (Digital Signal Processor). The functions of the trial machining instructing unit 41, the search range determining unit 42, and the machining condition determining unit 11 are realized by the processor 51 and software, firmware, or a combination of software and firmware. The software or firmware is described as a program and stored in the external storage device 53. The processor 51 reads software or firmware stored in the external storage device 53 into the memory 52 and executes the software or firmware.
The Memory 52 is a nonvolatile or volatile semiconductor Memory, and is a RAM (Random Access Memory), a ROM (Read Only Memory), a flash Memory, an EPROM (Erasable Programmable Read Only Memory), or an EEPROM (registered trademark) (Electrically Erasable Programmable Read Only Memory). The external storage device 53 is an HDD (Hard Disk Drive) or SSD (Solid State Drive). The functions of the machining condition database 40, the condition information storage unit 43, and the range information storage unit 44 are realized using the external storage device 53.
The input/output interface 54 receives information from the wire electric discharge machine 100 and outputs information to the wire electric discharge machine 100. The input/output interface 54 also includes an input device such as a keyboard, a mouse, or a touch panel. The function of the display section 12 is realized using the display 55.
According to embodiment 1, the machining condition search device 1 divides the discharge energy range for each preset machining condition into a plurality of discharge energy ranges, and reads the machining condition for each of the plurality of discharge energy ranges. The machining condition search device 1 determines the range of the discharge energy based on the results of the trial machining obtained for each of the read machining conditions, and thereby screens the set of machining conditions to be searched. The machining condition search device 1 determines the discharge energy range closest to the broken line boundary point and determines the search range of the machining condition, thereby being able to search for the optimum machining condition among all the machining conditions. Thus, the machining condition search device 1 has an effect of being able to search for a machining condition in which the machining speed is high and the wire 30 is not broken.
Fig. 15 is a diagram showing a wire electric discharge machine according to embodiment 2 of the present invention. The wire electric discharge machine 110 according to embodiment 2 includes a processing unit 20 and a control device 111 that controls the entire wire electric discharge machine 110. The control device 111 includes a machining control unit 22 and a machining condition search device 1. In embodiment 2, the same components as those in embodiment 1 described above are denoted by the same reference numerals, and a description will be given mainly of a configuration different from embodiment 1.
According to embodiment 2, the wire electric discharge machine 110 is provided with the machining condition search device 1 in the wire electric discharge machine 110, and thus, the machining condition can be searched as in embodiment 1 without using a device outside the wire electric discharge machine 110.
Fig. 16 is a diagram showing a configuration of a filtering unit included in a machining condition search device according to embodiment 3 of the present invention. In embodiment 3, the screening unit 70 includes a processing condition extraction unit 71 and an extraction information input unit 72 in addition to the respective units included in the screening unit 10 shown in fig. 3. In embodiment 3, the same components as those in embodiments 1 and 2 are denoted by the same reference numerals, and configurations different from those in embodiments 1 and 2 will be mainly described. The machining condition search device 1 according to embodiment 3 has the same configuration as the machining condition search device 1 according to embodiment 1 or 2 except that the screening unit 70 is provided instead of the screening unit 10.
The information of the extraction condition in the search range of the processing condition is input to the extraction information input unit 72. The information of the extraction condition is input to the extraction information input unit 72 by the user. The extraction information input unit 72 outputs the input information of the extraction conditions to the processing condition extraction unit 71. The processing condition extraction unit 71 extracts the data of the processing conditions from the processing condition database 40 in accordance with the input information of the extraction conditions. The trial machining instructing unit 41 reads out the data of the machining condition from the machining condition extracting unit 71. Thus, the screening unit 70 screens the processing condition group from the data of the processing conditions extracted according to the information of the extraction conditions.
As an example of the extraction condition, a condition based on a restriction on the usage amount of the line 30 is cited. If the value of the control parameter indicating the usage amount of the wire 30 is less than or equal to a certain value as the extraction condition, the processing condition extraction unit 71 extracts the data of the processing condition in which the value of the control parameter is less than or equal to the certain value from the processing condition database 40, to the extraction information input unit 72. The more the amount of the wire 30 used, the higher the running cost of the wire electric discharge machine 100. The extraction condition is set to a value of the control parameter indicating the amount of usage of the line 30 equal to or less than a predetermined value, whereby the processing condition in which the amount of usage of the line 30 is greater than the predetermined amount is excluded from the search target. Thus, the screening unit 70 can screen the machining conditions corresponding to the user's request for suppressing the running cost.
According to embodiment 3, the machining condition search device 1 can search for a machining condition in which the machining speed is high and the wire breakage does not occur, as in the case of embodiment 1. The processing condition search device 1 can extract the data of the processing conditions according to the extraction conditions, thereby filtering the processing conditions corresponding to the request of the user.
The configuration described in the above embodiment is an example of the contents of the present invention, and may be combined with other known techniques, and a part of the configuration may be omitted or modified without departing from the scope of the present invention.
Description of the reference symbols
1 processing condition search device, 10, 70 selection unit, 11, 60 processing condition determination unit, 12 display unit, 13 processing instruction, 14 processing result information, 15 search object data, 16 processing condition information, 20 processing unit, 21, 111 control device, 22 processing control unit, 23 drive device, 24 processed object, 25 power supply, 26 bobbin, 27 supply roller, 28 lower roller, 29 recovery roller, 30 wire, 31 power supply, 32 godet, 33 table, 40 processing condition database, 41, 46 trial processing instruction unit, 42 search range determination unit, 43 condition information storage unit, 44 range information storage unit, 45 boundary range information, 47 optimization processing unit, 48 search result, 51 processor, 52 memory, 53 external storage unit, 54 input/output interface, 55 display, 61 machine learning device, 62 intention determination unit, 63 state observation unit, 64 learning unit, 65 calculation unit, 66 function update unit, 71 processing condition extraction unit, 72 extraction information input unit, 100, 110 wire electric discharge processing machine, and reporting.
Claims (10)
1. A machining condition search device for searching for a machining condition for electrical discharge machining in a wire electrical discharge machine that performs electrical discharge machining by generating electrical discharge in a gap between a wire and a workpiece,
the machining condition search device is characterized by comprising:
a screening unit that divides a discharge energy range, which is a range in which a value of discharge energy relating to each preset machining condition is distributed, into a plurality of discharge energy ranges, reads out the machining conditions of each of the plurality of discharge energy ranges, and screens a set of machining conditions to be searched by determining 1 of the plurality of discharge energy ranges based on a result of trial machining according to each of the read-out machining conditions; and
and a machining condition determining unit configured to determine a machining condition for the electric discharge machining from the machining condition group.
2. The processing condition search device according to claim 1,
the screening unit divides the entire discharge energy range relating to all preset machining conditions into the plurality of discharge energy ranges, which are equal discharge energy ranges.
3. The processing condition search device according to claim 1 or 2,
the screening unit instructs the wire electric discharge machine to perform the trial machining a plurality of times under the different machining conditions in each of the plurality of discharge energy ranges.
4. The processing condition search device according to claim 3,
the screening unit identifies 1 of the plurality of discharge energy ranges by selecting a discharge energy range in which the plurality of trial machining for each of the plurality of discharge energy ranges includes both trial machining in which the wire breakage occurs and trial machining in which the wire breakage does not occur, and the discharge energy range having the highest value of the discharge energy.
5. The processing condition search device according to claim 1,
the machining condition determination unit determines the machining condition for the electric discharge machining by performing optimization processing by updating a model for searching for a combination having the highest machining speed and not causing a wire break based on the evaluation point.
6. The processing condition search device according to claim 1,
the machining condition determining section includes:
a machine learning device that learns machining conditions for the electric discharge machining; and
an intention determining unit that determines machining conditions for the electric discharge machining based on a result of learning by the machine learning device,
the machine learning device includes:
a state observation unit that observes, as state variables, wire breakage information regarding the presence or absence of wire breakage and a machining speed; and
and a learning unit that learns the machining conditions for the electric discharge machining in accordance with a training data set created based on the state variables.
7. The processing condition search device according to claim 6,
the learning unit includes:
a reward calculation unit that calculates a reward based on the state variable; and
and a function updating unit that updates a function for determining a machining condition for the electric discharge machining, based on the return.
8. The processing condition search device according to claim 7,
the reward calculation unit increases the reward when the machining speed is high and when the wire breakage does not occur, and decreases the reward when the machining speed is low and when the wire breakage occurs.
9. The processing condition search device according to claim 1,
the screening unit screens the machining condition group from the data of the machining conditions extracted in accordance with the information of the extraction conditions.
10. A wire electric discharge machine for performing electric discharge machining by generating electric discharge in a gap between a wire and a workpiece,
the wire electric discharge machine is characterized in that,
a machining condition search device for searching for a machining condition for the electric discharge machining,
the processing condition search device comprises:
a screening unit that divides a discharge energy range, which is a range in which a value of discharge energy relating to each preset machining condition is distributed, into a plurality of discharge energy ranges, reads out the machining conditions of the plurality of discharge energy ranges, and screens a set of machining conditions to be searched by determining 1 of the plurality of discharge energy ranges based on a result of trial machining according to each read-out machining condition; and
and a machining condition determining unit configured to determine a machining condition for the electric discharge machining from the machining condition group.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/JP2019/024662 WO2020255370A1 (en) | 2019-06-21 | 2019-06-21 | Machining condition lookup device and wire electrical discharge machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113993646A CN113993646A (en) | 2022-01-28 |
| CN113993646B true CN113993646B (en) | 2023-01-10 |
Family
ID=70858115
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201980097579.9A Active CN113993646B (en) | 2019-06-21 | 2019-06-21 | Machining condition search device and wire electric discharge machine |
Country Status (3)
| Country | Link |
|---|---|
| JP (1) | JP6704550B1 (en) |
| CN (1) | CN113993646B (en) |
| WO (1) | WO2020255370A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022210170A1 (en) | 2021-03-29 | 2022-10-06 | ファナック株式会社 | Processing-condition estimation device |
| WO2022269664A1 (en) * | 2021-06-21 | 2022-12-29 | 三菱電機株式会社 | Machining condition searching device and machining condition searching method |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS63105829A (en) * | 1986-10-24 | 1988-05-11 | Mitsubishi Electric Corp | Wire cut electric discharge machine |
| JP4795282B2 (en) * | 2006-07-11 | 2011-10-19 | 三菱電機株式会社 | Machining condition search device |
| JP6140228B2 (en) * | 2015-08-27 | 2017-05-31 | ファナック株式会社 | Wire electrical discharge machine for machining while adjusting machining conditions |
| JP6487497B2 (en) * | 2016-07-28 | 2019-03-20 | ファナック株式会社 | Wire electric discharge machine and wire electric discharge machining method |
| JP6680714B2 (en) * | 2017-03-30 | 2020-04-15 | ファナック株式会社 | Control device and machine learning device for wire electric discharge machine |
| JP6680748B2 (en) * | 2017-11-17 | 2020-04-15 | ファナック株式会社 | Control device and machine learning device |
-
2019
- 2019-06-21 WO PCT/JP2019/024662 patent/WO2020255370A1/en active Application Filing
- 2019-06-21 JP JP2020506291A patent/JP6704550B1/en active Active
- 2019-06-21 CN CN201980097579.9A patent/CN113993646B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113993646A (en) | 2022-01-28 |
| WO2020255370A1 (en) | 2020-12-24 |
| JPWO2020255370A1 (en) | 2021-09-13 |
| JP6704550B1 (en) | 2020-06-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108687415B (en) | Control device for wire electric discharge machine and machine learning device | |
| JP6140228B2 (en) | Wire electrical discharge machine for machining while adjusting machining conditions | |
| CN113993646B (en) | Machining condition search device and wire electric discharge machine | |
| KR0169811B1 (en) | Analytical method of influencing primary factor of quality of product and controlling method of molding condition | |
| Dubois-Lacoste et al. | Anytime Pareto local search | |
| JP7071904B2 (en) | Information processing equipment, information processing methods and programs | |
| JP2017030067A (en) | Control device-added machining apparatus with machining time measuring function and on-machine measuring function | |
| CN102802511B (en) | System and method for medical treatment hypothesis testing | |
| JP6602512B2 (en) | Aging deterioration diagnosis apparatus and aging deterioration diagnosis method | |
| CN111954582B (en) | Machine learning device | |
| JP6695518B1 (en) | Machine learning device, numerical control device, wire electric discharge machine, and machine learning method | |
| JP6985180B2 (en) | Numerical control device | |
| CN113093584B (en) | Welding abnormity detection method and device, computer equipment and storage medium | |
| JP7204952B1 (en) | MACHINING CONDITION SEARCH DEVICE AND MACHINING CONDITION SEARCH METHOD | |
| JP2022191680A (en) | Data selection support device, and data selection support method | |
| CN111857055A (en) | Machining support device, numerical controller, and machining support system | |
| CN115397593B (en) | Machining report creation device and wire electric discharge machine | |
| EP4316714A1 (en) | Processing-condition estimation device | |
| CN114746203A (en) | Control device, electric discharge machine, and machine learning device | |
| CN114971599B (en) | Food manufacturing processing technological parameter setting method, device, equipment and medium | |
| Korzybski et al. | The On-line Evolutionary Method for Soft Fault Diagnosis in Diode-transistor Circuits | |
| JPWO2020196441A1 (en) | Process status monitoring device and process status monitoring method | |
| JPH10217039A (en) | Electric discharge machining control device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |