Wire discharge machining device, wire discharge machining method, learning device and inference device

Abstract

The wire discharge machining device comprises: a machining mechanism (13), which is a mechanism for discharge machining; a plate thickness estimator (24), which estimates the plate thickness of the workpiece at the machining position when performing rough machining of the workpiece by discharge machining; a plate thickness outputter (25), which outputs plate thickness data that associates plate thickness information indicating the estimated plate thickness with position information to the outside of the wire discharge machining device; a plate thickness inputter (26), to which the plate thickness data is input from the outside of the wire discharge machining device; a step position estimator (27), which estimates the position of a step portion of the workpiece where the plate thickness changes based on the input plate thickness data; an electrical condition controller (22), which controls the application of a pulse voltage based on the plate thickness data and step information indicating the position of the step portion when performing fine machining of the workpiece by discharge machining after rough machining; and a control device, which controls the machining mechanism based on the plate thickness data and the step information when performing fine machining.

Description

Technical Field

[0001] The present invention relates to a wire discharge machining device, a wire discharge machining method, a learning device, and an inference device for performing electrical discharge machining on a workpiece. Background Art

[0002] In an online electrical discharge machining device, machining conditions corresponding to the plate thickness of the workpiece to be machined, or machining conditions corresponding to required specifications such as surface roughness, are prepared in advance. An operator using the online electrical discharge machining device appropriately selects machining conditions suitable for machining from the prepared machining conditions, thereby enabling high-precision machining, for example, machining with a tolerance of 1 / 100 mm to 1 / 1000 mm. However, in the case of a workpiece whose plate thickness changes dramatically during machining of a single machined shape, dimensional errors sometimes occur at the boundary portion between the portions of the workpiece where the plate thicknesses differ from each other, i.e., the step portion. In addition, stripes sometimes occur on the surface of the step portion. In order to prevent the occurrence of dimensional errors or the reduction in machining quality caused by the occurrence of stripes, a method has been proposed in the past in which the step position of the workpiece, i.e., the position of the step portion, is estimated and electrical discharge machining is performed under machining conditions suitable for the plate thickness.

[0003] Patent Document 1 discloses a wire EDM device that detects the thickness of a workpiece during rough machining and stores the thickness information. During finish machining, the device estimates the step position based on the thickness information and changes machining conditions. According to Patent Document 1, the wire EDM device stores the thickness information in a storage area of the device.

[0004] Patent Document 1: Japanese Patent No. 6808868 Summary of the Invention

[0005] In the technology of Patent Document 1, plate thickness information is accumulated in the storage area of the wire EDM device during rough machining. Therefore, the amount of plate thickness information that can be stored is limited to the capacity of the storage area within the wire EDM device. This limitation in the amount of plate thickness information that can be used to estimate the step position makes it difficult to perform control to improve machining quality.

[0006] The present invention has been made in view of the above situation, and its object is to provide a wire discharge machining device that can perform control for improving machining quality without placing restrictions on the amount of plate thickness information data that can be used to estimate the step position in the workpiece.

[0007] In order to solve the above-mentioned problems and achieve the object, a wire electrical discharge machining device according to the present invention performs electrical discharge machining of a workpiece by applying a pulse voltage between a wire electrode and the workpiece. The wire discharge machining device involved in the present invention comprises: a machining mechanism, which is a mechanism for discharge machining; a plate thickness estimator, which estimates the plate thickness of the workpiece at the machining position when performing rough machining of the workpiece by discharge machining; a plate thickness outputter, which outputs plate thickness data that associates plate thickness information representing the estimated plate thickness with position information to the outside of the wire discharge machining device; a plate thickness inputter, which inputs plate thickness data from the outside of the wire discharge machining device; a step position estimator, which estimates the position of a step portion of the workpiece where the plate thickness changes based on the input plate thickness data; an electrical condition controller, which controls the application of a pulse voltage based on the plate thickness data and step information representing the position of the step portion when performing fine machining of the workpiece by discharge machining after rough machining; a control device, which controls the machining mechanism based on the plate thickness data and the step information when performing fine machining; and a position information correction unit, which corrects the position information contained in the plate thickness data input to the plate thickness inputter. The electrical condition controller controls the application of the pulse voltage based on the plate thickness data including the corrected position information and the step information. The control device controls the processing mechanism based on the plate thickness data including the corrected position information and the step information.

[0008] Effects of the Invention

[0009] The wire electrical discharge machining device according to the present invention has the effect of enabling control for improving machining quality without placing a limit on the amount of plate thickness information data that can be used to estimate a step position in a workpiece. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a diagram showing a configuration example of a wire electrical discharge machining device according to the first embodiment.

[0011] Figure 2 This is a diagram showing the functional configuration of a power supply unit and a control unit included in the wire electrical discharge machining device according to the first embodiment.

[0012] Figure 3 This is a flowchart showing the operating procedure of the wire electrical discharge machining device according to the first embodiment.

[0013] Figure 4 This is a wireframe diagram for explaining control during rough machining performed by the wire electrical discharge machining device according to the first embodiment.

[0014] Figure 5 This is a wireframe diagram for explaining control during finish machining performed by the wire electrical discharge machining device according to the first embodiment.

[0015] Figure 6 This is a diagram showing a control unit in which a coordinate corrector as a position information correcting unit is added to the first embodiment.

[0016] Figure 7 It is used to append Figure 6 This is a wireframe diagram illustrating control during finish machining performed by a wire discharge machining device using the coordinate corrector shown.

[0017] Figure 8 This is a diagram for explaining the mechanical coordinate system of the wire electrical discharge machining device according to the first embodiment.

[0018] Figure 9 This is a diagram for explaining a relative coordinate system applicable to coordinates associated with plate thickness information in the first embodiment.

[0019] Figure 10 This is a diagram showing a configuration example of a control circuit according to the first embodiment.

[0020] Figure 11 This is a diagram showing a learning device according to the second embodiment.

[0021] Figure 12 This is a diagram showing a configuration example of a neural network used for learning by a learning device according to the second embodiment.

[0022] Figure 13 This is a flowchart showing the procedure of a learning process performed by the learning device according to the second embodiment.

[0023] Figure 14 This is a diagram showing an inference device according to the third embodiment.

[0024] Figure 15 This is a flowchart showing the procedure of the inference processing performed by the inference device involved in the third embodiment. DETAILED DESCRIPTION

[0025] Hereinafter, a wire electrical discharge machining device, a wire electrical discharge machining method, a learning device, and an estimating device according to embodiments will be described in detail with reference to the drawings.

[0026] Implementation method 1.

[0027] Figure 1This figure shows an example configuration of a wire EDM device 100 according to Embodiment 1. The wire EDM device 100 is a machine tool that processes a workpiece 18 by generating an electric discharge in the gap between the workpiece 18 and a wire electrode 2 serving as a machining electrode. The X, Y, and Z axes constitute the three axes of the machine coordinate system of the wire EDM device 100. For example, the XY plane is a horizontal plane, and the Z-axis direction is a vertical direction. In the following description, the positive Z direction is considered upward, and the negative Z direction is considered downward.

[0028] The wire electrical discharge machining device 100 includes a machining mechanism 13 for electrical discharge machining, a power supply unit 14 including a machining power supply, and a control unit 15 including a numerical control (NC) device as a control device.

[0029] The machining mechanism 13 includes: a wire electrode spool 1; a feed roller 3 for feeding the wire electrode 2 pulled from the wire electrode spool 1; an upper power supply 4 positioned above the workpiece 18; a lower power supply 5 positioned below the workpiece 18; an upper guide 6 and a lower guide 7 for supporting the wire electrode 2 during machining of the workpiece 18; and a table 8 on which the workpiece 18 is placed. The machining mechanism 13 also includes: a lower roller 9 for feeding the wire electrode 2 used in machining; a recovery roller 10 for generating a driving force to feed the wire electrode 2; a wire electrode recovery box 11 for recovering the used wire electrode 2; and an X-axis drive motor 12X and a Y-axis drive motor 12Y for driving the table 8.

[0030] The NC device sends position commands to the upper guide 6 and lower guide 7, respectively. The upper guide 6 and lower guide 7 support the wire electrode 2 at a position and at an inclination in accordance with the position commands. The upper power supply 4 and lower power supply 5 are each connected to a machining power source. The NC device sends axis commands to the X-axis drive motor 12X and the Y-axis drive motor 12Y, respectively. The X-axis drive motor 12X drives the worktable 8 in the X-axis direction according to the axis commands. The Y-axis drive motor 12Y drives the worktable 8 in the Y-axis direction according to the axis commands. The machining portion 16 is provided as the wire electrode 2 between the upper guide 6 and lower guide 7.

[0031] Figure 2 1 is a diagram showing the functional configuration of the power supply unit 14 and the control unit 15 included in the wire electrical discharge machining device 100 according to the first embodiment. Figure 2 Shown are a power supply unit 14 and a control unit 15, an upper power supply 4 and a lower power supply 5 connected to a machining power supply 20, an upper guide unit 6 and a lower guide unit 7 that operate according to instructions sent from an NC device 23, an X-axis drive motor 12X, and a Y-axis drive motor 12Y.

[0032] The power supply unit 14 includes a machining power supply 20, a machining voltage detector 21, and an electrical condition controller 22. The machining power supply 20 applies a pulse voltage between the wire electrode 2 and the workpiece 18 in accordance with a voltage command output by the NC device 23. The machining voltage detector 21 detects the machining voltage, which is the inter-electrode voltage applied between the wire electrode 2 and the workpiece 18. The electrical condition controller 22 controls the application of the pulse voltage.

[0033] The control unit 15 includes an NC device 23, a plate thickness estimator 24, a plate thickness output device 25, a plate thickness input device 26, and a step position estimator 27. The NC device 23 generates various commands corresponding to machining conditions according to the machining program for electrical discharge machining. By outputting these commands, the NC device 23 controls the machining mechanism 13 and the power supply unit 14.

[0034] When rough machining of the workpiece 18 is performed by electrical discharge machining, the plate thickness estimator 24 estimates the plate thickness of the workpiece 18 at the position where machining is performed. The plate thickness output device 25 outputs plate thickness data to the outside of the wire electrical discharge machining device 100. The plate thickness data is obtained by associating position information with plate thickness information indicating the plate thickness estimated by the plate thickness estimator 24. When finishing machining of the workpiece 18 by electrical discharge machining after rough machining is performed, the plate thickness data is input to the plate thickness input device 26 from outside the wire electrical discharge machining device 100. The step position estimator 27 estimates the position of the step portion based on the plate thickness data input to the plate thickness input device 26. The step portion is a portion of the workpiece 18 where the plate thickness changes, that is, a portion at the boundary between portions with different plate thicknesses.

[0035] The electrical condition controller 22 controls the application of pulse voltage during finishing based on the plate thickness data and step information. The step information indicates the position of the step. The NC device 23 controls the machining mechanism 13 during finishing based on the plate thickness data and step information.

[0036] The plate thickness output device 25 outputs the plate thickness data by writing it to a file 17 stored externally from the in-line EDM apparatus 100. The file 17 is stored in a storage device such as a memory device or a storage medium. The plate thickness output device 25 can also output the plate thickness data by writing it to a machining program stored externally from the in-line EDM apparatus 100. The plate thickness input device 26 reads the plate thickness data from the file 17 or the machining program, thereby inputting the plate thickness data to the plate thickness input device 26.

[0037] Next, the operation of the wire electrical discharge machining device 100 will be described. Figure 3This is a flowchart showing the operation sequence of the wire discharge machining device 100 involved in embodiment 1. The wire discharge machining device 100 performs multiple machining operations until a machining shape corresponding to the required specifications is obtained. Rough machining is the first machining operation performed among multiple machining operations, and is a machining operation that prioritizes machining speed over shape accuracy. Finishing machining is the machining operation performed after rough machining among multiple machining operations. The number of finishing operations is arbitrary. Figure 3 2 shows the operations in rough machining and finish machining, and illustrates the sequence of operations performed by the wire electrical discharge machining device 100 in order to adjust machining on the step portion of the workpiece 18 .

[0038] The wire EDM device 100 performs steps S1 and S2 during rough machining. In step S1, the wire EDM device 100 estimates the thickness of the workpiece 18 using the thickness estimator 24. In step S2, the wire EDM device 100 writes the thickness data to the file 17 or machining program using the thickness output device 25. This outputs the thickness data to the outside of the wire EDM device 100.

[0039] The wire EDM device 100 performs steps S3 to S5 during finishing. In step S3, the wire EDM device 100 reads the plate thickness data from the file 17 or the machining program via the plate thickness input device 26. In other words, the wire EDM device 100 reads the plate thickness data from outside the wire EDM device 100.

[0040] In step S4, the wire discharge machining device 100 estimates the position of the step portion based on the plate thickness data read in. In step S5, the wire discharge machining device 100 adjusts at least one of the electrical conditions and the axis instructions based on the plate thickness data and the step information. The electrical conditions are conditions related to the application of the pulse voltage, such as the voltage value or the rest time of the pulse. The wire discharge machining device 100 adjusts at least one of the electrical conditions and the axis instructions, thereby controlling the application of the pulse voltage and at least one of the machining mechanism 13 based on the plate thickness data and the step information. The above is the end of the wire discharge machining device 100. Figure 3 The actions involved are in the order shown.

[0041] Figure 4This is a block diagram illustrating the control during rough machining performed by the wire EDM device 100 according to Embodiment 1. The machining power supply 20 applies a pulse voltage corresponding to a voltage command from the NC device 23 between the wire electrode 2 and the workpiece 18. The X-axis drive motor 12X and the Y-axis drive motor 12Y move the worktable 8 in the X-axis and Y-axis directions in response to axis commands from the NC device 23. The wire EDM device 100 adjusts the distance between the wire electrode 2 and the workpiece 18 by moving the worktable 8. The wire EDM device 100 controls the discharge energy in the machining portion 16 according to the voltage command and axis command. As described above, the wire EDM device 100 controls the EDM process.

[0042] The machining voltage detector 21 detects the machining voltage in the machining section 16. The wire discharge machining device 100 adjusts the electrical conditions indicated by the voltage instruction by feedback of the machining voltage detected by the machining voltage detector 21. The machining power supply 20 applies a pulse voltage according to the voltage instruction after the electrical conditions are adjusted. The wire discharge machining device 100 adjusts the axis instruction by feedback of the machining voltage detected by the machining voltage detector 21. The X-axis drive motor 12X and the Y-axis drive motor 12Y move the worktable 8 according to the adjusted axis instruction. In addition, the adjustment by feedback of the machining voltage is not limited to the adjustment of both the electrical conditions and the axis instruction. The wire discharge machining device 100 can adjust at least one of the electrical conditions and the axis instruction by feedback of the machining voltage.

[0043] The plate thickness estimator 24 estimates the plate thickness at the location where rough machining is performed based on machining data. Machining data, such as machining voltage, machining current, number of discharge pulses, or machining speed, represents the state of the machining unit 16. The plate thickness estimator 24 generates plate thickness data that correlates position information with the estimated plate thickness. The plate thickness estimator 24 outputs the plate thickness data to the plate thickness output device 25. The plate thickness output device 25 writes the plate thickness data to the file 17 or machining program.

[0044] Figure 5 This is a wireframe diagram illustrating control during finish machining performed by the wire EDM apparatus 100 according to Embodiment 1. The wire EDM apparatus 100 controls EDM machining according to voltage commands and axis commands. The wire EDM apparatus 100 adjusts at least one of the electrical conditions and axis commands based on feedback from the machining voltage detected by the machining voltage detector 21.

[0045] The plate thickness input device 26 reads plate thickness data from the file 17 or the machining program. The plate thickness input device 26 outputs the plate thickness data to the step position estimator 27 and the electrical condition controller 22. The step position estimator 27 detects changes in plate thickness at each location on the workpiece 18 based on the plate thickness data. The step position estimator 27 estimates locations where the plate thickness changes sharply as the locations of steps. The step position estimator 27 generates step information indicating the estimated locations. The step position estimator 27 outputs the step information to the electrical condition controller 22.

[0046] The electrical condition controller 22 determines the timing when the position for finishing machining reaches the step portion based on the step information. The electrical condition controller 22 adjusts the electrical conditions according to the plate thickness indicated by the plate thickness data. Thus, when finishing machining is performed, the electrical condition controller 22 controls the application of the pulse voltage based on the plate thickness data and the step information. The electrical condition controller 22 adjusts the position of the worktable 8 indicated by the axis instruction according to the plate thickness indicated by the plate thickness data. Thus, when finishing machining is performed, the NC device 23 controls the discharge machining according to the machining conditions adjusted based on the plate thickness data and the step information. In addition, the adjustment based on the plate thickness data and the step information is not limited to the adjustment of the electrical conditions and the axis instruction. The wire discharge machining device 100 only needs to adjust at least one of the electrical conditions and the axis instruction based on the plate thickness data and the step information. That is, the wire discharge machining device 100 controls at least one of the application of the pulse voltage and the machining mechanism 13 based on the plate thickness data and the step data.

[0047] The wire EDM device 100 outputs the plate thickness data generated during rough machining to the outside of the device 100. Furthermore, during finish machining, the wire EDM device 100 generates step information based on the plate thickness data input from outside the device 100, and controls the application of the pulse voltage and the machining mechanism 13 based on the plate thickness data and the step information. The wire EDM device 100 can perform machining appropriate to the plate thickness on the step portion, thereby achieving high machining quality.

[0048] According to the first embodiment, since the plate thickness data does not need to be accumulated within the wire EDM apparatus 100, there is no need to impose a limit on the amount of plate thickness information that can be used to estimate the position of the step. Saving the plate thickness data in a file 17 or machining program stored externally from the wire EDM apparatus 100 also ensures traceability of the machining process performed by the wire EDM apparatus 100.

[0049] The wire electrical discharge machining device 100 may include a position information correction unit that corrects the position information included in the plate thickness data. Here, an example in which the position information correction unit is added to the control unit 15 will be described. Figure 6This diagram shows the control unit 15 in which a coordinate corrector 28 serving as a position information correcting unit is added to the first embodiment.

[0050] The coordinate corrector 28 corrects the position information contained in the plate thickness data, i.e., the coordinates, when the position or inclination of the workpiece 18 on the worktable 8 changes from the time the plate thickness data is generated. The coordinate corrector 28 corrects the coordinates so as to offset the change in the position or inclination of the workpiece 18. The electrical condition controller 22 controls the application of the pulse voltage based on the plate thickness data and the step information including the corrected position information. The NC device 23 controls the processing mechanism 13 based on the plate thickness data and the step information including the corrected position information. Even when the position or inclination of the workpiece 18 changes, the wire discharge machining device 100 can control the pulse voltage or the processing mechanism 13 based on the plate thickness data by correcting the coordinates through the coordinate corrector 28.

[0051] After rough machining, the workpiece 18 is removed from the worktable 8 and then placed back on the worktable 8, which may cause the position or inclination of the workpiece 18 to change. Furthermore, when machining the workpiece 18 by changing the model of the wire EDM device 100 for each machining step, such as rough machining and finishing, the position or inclination of the workpiece 18 during finishing may change from that during rough machining. An example of changing the model of the wire EDM device 100 is to use a wire EDM device 100 that uses water as a machining fluid for rough machining and a wire EDM device 100 that uses oil as a machining fluid for finishing. Using a wire EDM device 100 that uses water as a machining fluid for rough machining enables machining at a high machining speed. Using a wire EDM device 100 that uses oil as a machining fluid for finishing enables machining at a low machining speed but with high precision.

[0052] Furthermore, when the model of the wire EDM device 100 is changed for each machining step, the size of the table 8 may differ for each model. In this case, the wire EDM device 100 uses the coordinate corrector 28 to correct the coordinates, thereby enabling control of the pulse voltage and the machining mechanism 13 based on the plate thickness data even during finish machining.

[0053] Figure 7 It is used to append Figure 6The wire discharge machining device 100 is shown as a wireframe diagram illustrating the control of the coordinate corrector 28 during finish machining. The plate thickness input device 26 outputs the input plate thickness data to the coordinate corrector 28. If the position or inclination of the workpiece 18 has changed since the plate thickness data was generated, the coordinate corrector 28 corrects the coordinates included in the plate thickness data. The coordinate corrector 28 outputs the coordinate-corrected plate thickness data to the step position estimator 27 and the electrical condition controller 22, respectively. Thus, the wire discharge machining device 100 can control the pulse voltage or the machining mechanism 13 based on the plate thickness data even if the position or inclination of the workpiece 18 on the worktable 8 has changed since the plate thickness data was generated.

[0054] The coordinates associated with the plate thickness information in the plate thickness data may not be the coordinates of the machine coordinate system unique to the wire EDM apparatus 100, but rather the coordinates of a coordinate system based on the workpiece 18. The coordinate system based on the workpiece 18 is a coordinate system whose origin is a predetermined position within the workpiece 18. In the following description, the coordinate system based on the workpiece 18 is referred to as a relative coordinate system.

[0055] Figure 8 : is a diagram for explaining the mechanical coordinate system of the wire electrical discharge machining device 100 according to the first embodiment. Figure 8 In the example shown, one point on the table 8 is assumed to be the origin of the machine coordinate system.

[0056] When the coordinates associated with plate thickness information are set as coordinates in the machine coordinate system, if the workpiece 18 is removed from the worktable 8 and then reinstalled on the worktable 8 after plate thickness data is generated, the position of the workpiece 18 relative to the origin may change. Alternatively, the inclination of the workpiece 18 relative to the machine coordinate system may change. During finish machining, if the position or inclination of the workpiece 18 has changed since rough machining, the wire EDM device 100 may be unable to control the pulse voltage or machining mechanism 13 based on the plate thickness data.

[0057] When the model of the wire EDM device 100 is changed for each machining step, such as roughing and finishing, and the workpiece 18 is machined, the position or inclination of the workpiece 18 during finishing may differ from that during roughing. Furthermore, when the model of the wire EDM device 100 is changed for each machining step, the dimensions of the table 8 may differ between models. In such cases, the wire EDM device 100 cannot control the pulse voltage or the machining mechanism 13 based on the plate thickness data.

[0058] Figure 9This is a diagram for explaining a relative coordinate system applicable to coordinates associated with plate thickness information in the first embodiment. Figure 9 The x-axis, y-axis, and z-axis shown are assumed to be the three axes of the relative coordinate system. Figure 9 In the example shown, the origin of the relative coordinate system is the starting point of the machining trajectory 19, that is, the machining start position. Alternatively, the origin of the relative coordinate system may be a position other than the machining start position. The origin of the relative coordinate system may be a position other than the position on the machining trajectory 19. The wire discharge machining device 100 can set any position on the workpiece 18 as the origin of the relative coordinate system.

[0059] The wire EDM apparatus 100 sets the coordinates included in the plate thickness data as coordinates of the relative coordinate system. This allows the pulse voltage and the machining mechanism 13 to be controlled based on the plate thickness data, even if the position or inclination of the workpiece 18 changes. Furthermore, even if the model of the wire EDM apparatus 100 changes, the wire EDM apparatus 100 can still control the pulse voltage and the machining mechanism 13 based on the plate thickness data.

[0060] Next, the hardware configuration of each component that realizes the machining voltage detector 21, the electrical condition controller 22, the NC device 23, the plate thickness estimator 24, the plate thickness output device 25, the plate thickness input device 26, the step position estimator 27, and the coordinate corrector 28 will be described. Each of the above components is realized by a circuit in which a processor executes software, i.e., a processing circuit. The processing circuit that executes software is, for example, Figure 10 The control circuit shown. Figure 10 1 is a diagram showing a configuration example of a control circuit 30 according to Embodiment 1. The control circuit 30 includes an input unit 31 , a processor 32 , a memory 33 , and an output unit 34 .

[0061] The input unit 31 is an interface circuit that receives data input from the outside of the control circuit 30 and gives it to the processor 32. The output unit 34 is an interface circuit that sends data from the processor 32 or the memory 33 to the outside of the control circuit 30. Figure 10 In the case of the control circuit 30 shown, the aforementioned components are implemented by the processor 32 reading and executing programs corresponding to the components stored in the memory 33. The memory 33 is also used as a temporary storage for the various processes performed by the processor 32. The processor 32 can output data such as calculation results to the memory 33 for storage, or store the data such as calculation results in an auxiliary storage device via the volatile memory of the memory 33.

[0062] The processor 32 is a CPU (also known as a Central Processing Unit, central processing unit, processing unit, computing unit, microprocessor, microcomputer, processor, or DSP (Digital Signal Processor). The memory 33 is, for example, a nonvolatile or volatile semiconductor memory such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable Read Only Memory), or EEPROM (registered trademark) (Electrically Erasable Programmable Read Only Memory), a magnetic disk, a floppy disk, an optical disk, a compact disk, a minidisc, or a DVD (Digital Versatile Disc).

[0063] Figure 10 This is an example of hardware in which the above-mentioned components are implemented by a general-purpose processor 32 and memory 33. Alternatively, the above-mentioned components may be implemented by a dedicated hardware circuit. The processing circuit as a dedicated hardware circuit may be a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination thereof. The above-mentioned components may be implemented by a combination of the control circuit 30 and the dedicated hardware circuit.

[0064] According to the first embodiment, the wire EDM apparatus 100 outputs plate thickness data to the outside of the wire EDM apparatus 100, and estimates the position of the step based on the plate thickness data input from the outside of the wire EDM apparatus 100. Consequently, the wire EDM apparatus 100 has the effect of eliminating restrictions on the amount of plate thickness information data that can be used to estimate the position of the step in the workpiece 18, thereby enabling control to improve machining quality.

[0065] Implementation method 2.

[0066] In the second embodiment, a learning device for using machine learning for at least one of estimating the plate thickness and estimating the step position will be described. Figure 11 This is a diagram showing a learning device 40 according to Embodiment 2. In Embodiment 2, the same components as those in Embodiment 1 are denoted by the same reference numerals, and the configuration different from that in Embodiment 1 will be mainly described.

[0067] The learning device 40 learns, with respect to the wire electrical discharge machining apparatus 100, the relationship between machining data related to the state of electrical discharge machining and at least one of the thickness of the workpiece 18 and the position of a step portion in the workpiece 18 where the thickness varies. The following describes an example in which the learning device 40 learns the relationship between machining data and both the thickness and the position of the step portion.

[0068] The learning device 40 includes a data acquisition unit 41 and a model generation unit 42. Processing data, plate thickness data, and step information are input to the data acquisition unit 41. The data acquisition unit 41 uses the input processing data, plate thickness data, and step information to create learning data. In the second embodiment, the learning data is data in which the processing data, plate thickness information, and step information are associated with each other. As described above, the data acquisition unit 41 acquires learning data including the processing data, plate thickness information, and step information.

[0069] The model generation unit 42 uses the learning data to generate a trained model 43 for estimating the plate thickness and the position of the step portion from the machining data. The trained model storage unit 44 stores the generated trained model 43. Figure 11 The trained model storage unit 44 shown is a storage unit external to the learning device 40. The trained model storage unit 44 may also be provided inside the learning device 40.

[0070] As the learning algorithm used by the model generation unit 42, a publicly known algorithm such as supervised learning, unsupervised learning, or reinforcement learning can be used. As an example, a case where a neural network is applied will be described.

[0071] The model generation unit 42 learns the plate thickness and the position of the step portion through so-called supervised learning, for example, using a neural network model. Here, supervised learning is a method in which a set of input and result data is given to the learning device 40, thereby learning the characteristics of the learning data and inferring the result based on the input.

[0072] Learning data consists of input and the corresponding output, or labels. Processing data represents the input, while plate thickness and step information represent the labels. A neural network consists of an input layer composed of multiple neurons, an intermediate layer, or hidden layer, also composed of multiple neurons, and an output layer, also composed of multiple neurons. The number of intermediate layers can be one or two or more.

[0073] Figure 12 This is a diagram showing a configuration example of a neural network used for learning in the learning device 40 according to the second embodiment. Figure 12The neural network shown is a three-layer neural network. The input layer contains neurons X1, X2, and X3. The middle layer contains neurons Y1 and Y2. The output layer contains neurons Z1, Z2, and Z3. The number of neurons in each layer is arbitrary. Values input to the input layer are multiplied by weights W1 (w11, w12, w13, w14, w15, and w16) and then input to the middle layer. Values input to the middle layer are multiplied by weights W2 (w21, w22, w23, w24, w25, and w26) and then output from the output layer. The output from the output layer varies depending on the values of weights W1 and W2.

[0074] In the second embodiment, the neural network learns the plate thickness and the position of the step according to the learning data obtained by the data acquisition unit 41 through so-called supervised learning. Specifically, the neural network adjusts the weights W1 and W2 so that the processing data input to the input layer and the output from the output layer approximate the plate thickness information and the step information, thereby learning the plate thickness and the position of the step. The model generation unit 42 performs the above learning to generate a trained model 43 and outputs the trained model 43. The trained model storage unit 44 stores the trained model 43 output from the model generation unit 42. The model generation unit 42 can read the trained model 43 that has been generated from the trained model storage unit 44 and update the trained model 43 by re-learning according to the learning data.

[0075] Next, the learning process performed by the learning device 40 will be described. Figure 13 This is a flowchart illustrating the sequence of learning processing performed by the learning device 40 according to Embodiment 2. In step S11, the learning device 40 acquires learning data including machining data, plate thickness information, and step information via the data acquisition unit 41. The data acquisition unit 41 creates learning data using the machining data, plate thickness data, and step information acquired simultaneously. Furthermore, the data acquisition unit 41 only needs to create learning data that associates the machining data, plate thickness information, and step information with each other, and does not need to acquire the machining data, plate thickness data, and step information simultaneously.

[0076] In step S12, the learning device 40 learns the plate thickness and the position of the step portion through the so-called teacher learning according to the learning data through the model generation unit 42, and generates or updates the trained model 43. In step S13, the model generation unit 42 outputs the generated or updated trained model 43. Figure 13 The trained model storage unit 44 stores the trained model 43 obtained by the learning process.

[0077] In the second embodiment, the case where supervised learning is applied to the learning algorithm used by the model generation unit 42 is described. However, learning algorithms other than supervised learning may also be applied. The model generation unit 42 may perform machine learning using a learning algorithm such as reinforcement learning, unsupervised learning, or semi-supervised learning. The model generation unit 42 may perform machine learning using a learning algorithm such as deep learning, genetic programming, inductive logic programming, or support vector machines.

[0078] In the second embodiment, the learning device 40 is configured as a device external to the wire EDM apparatus 100. The learning device 40 may be connected to the wire EDM apparatus 100 via a network. The learning device 40 may be hosted on a cloud server. The learning device 40 is not limited to being external to the wire EDM apparatus 100; it may also be a device built into the wire EDM apparatus 100.

[0079] The learning device 40 is not limited to learning the plate thickness and the position of the step based on learning data generated for a single wire EDM device 100. The learning device 40 can also learn the plate thickness and the position of the step based on learning data generated for multiple wire EDM devices 100. The learning device 40 can acquire learning data from multiple wire EDM devices 100 used in the same location, or from multiple wire EDM devices 100 used in different locations. Learning data can be acquired from multiple wire EDM devices 100 operating independently of each other in multiple locations. After acquiring learning data from multiple wire EDM devices 100 begins, a new wire EDM device 100 can be added to the list of devices from which learning data is to be acquired. Furthermore, after acquiring learning data from multiple wire EDM devices 100 begins, some of the multiple wire EDM devices 100 can be excluded from the list of devices from which learning data is to be acquired.

[0080] The learning device 40 that has learned about a certain wire EDM device 100 can then learn about other wire EDM devices 100 other than the wire EDM device 100. The learning device 40 can update the trained model 43 by re-learning about the other wire EDM devices 100.

[0081] The learning device 40 can learn the relationship between the machining data and at least one of the plate thickness and the position of the step. When the learning device 40 learns the relationship between the machining data and the plate thickness, the machining data and the plate thickness data are input to the data acquisition unit 41. The data acquisition unit 41 uses the input machining data and plate thickness data to create learning data, which is data that associates the machining data and the plate thickness information. The data acquisition unit 41 acquires the learning data containing the machining data and the plate thickness information. The model generation unit 42 uses the learning data to generate a trained model 43 for inferring the plate thickness based on the machining data.

[0082] When learning the relationship between processing data and the position of a step, the processing data and step information are input to the data acquisition unit 41. Using the input processing data and step information, the data acquisition unit 41 creates learning data, which is data that associates the processing data and step information. The data acquisition unit 41 acquires the learning data, which includes the processing data and step information. The model generation unit 42 uses the learning data to generate a trained model 43 for inferring the position of the step based on the processing data.

[0083] The learning device 40 is connected to Figure 10 Each component of the learning device 40 is implemented by a circuit in which a processor executes software, i.e., a processing circuit. Each component of the learning device 40 may be implemented by a dedicated processing circuit, or by a combination of a processing circuit in which a processor executes software and a dedicated processing circuit.

[0084] According to Embodiment 2, the learning device 40 generates a trained model 43 using machining data and learning data including at least one of plate thickness information and step information. The learning device 40 can generate a trained model 43 for estimating at least one of plate thickness and step position based on the machining data.

[0085] Implementation method 3.

[0086] In the third embodiment, an estimation device that estimates at least one of the plate thickness and the position of the step portion using the trained model 43 will be described. Figure 14 This figure shows an estimation device 50 according to Embodiment 3. In Embodiment 3, the same components as those in Embodiment 1 or 2 are denoted by the same reference numerals, and the description will focus on the components different from Embodiment 1 or 2.

[0087] The estimation device 50 estimates at least one of the thickness of the workpiece 18 and the position of a step portion where the thickness varies within the workpiece 18 based on machining data related to the state of the electrical discharge machining performed by the wire electrical discharge machining device 100. In the following description, the estimation device 50 uses an example in which both the thickness and the position of the step portion are estimated based on the machining data.

[0088] The estimation device 50 includes a data acquisition unit 51 and an estimation unit 52. Processing data is input to the data acquisition unit 51. Specifically, the data acquisition unit 51 acquires the processing data. The estimation unit 52 reads the trained model 43 from the trained model storage unit 44, which is used to estimate the plate thickness and the position of the step based on the processing data. The estimation unit 52 inputs the processing data, serving as estimation data, into the trained model 43, thereby outputting plate thickness information and step information. Figure 14 The trained model storage unit 44 shown is a storage unit external to the estimation device 50. The trained model storage unit 44 may also be provided inside the estimation device 50. In the third embodiment, the estimation device 50 uses the trained model 43 generated by the learning device 40 according to the second embodiment to estimate the plate thickness and the position of the step portion based on the processing data.

[0089] Next, the estimation process performed by the estimation device 50 will be described. Figure 15 3 is a flowchart showing the order of the inference processing performed by the inference device 50 involved in the third embodiment. In step S21, the inference device 50 obtains the processing data through the data acquisition unit 51. In step S22, the inference device 50 inputs the processing data to the trained model 43 through the inference unit 52. In step S23, the inference unit 52 outputs the plate thickness information and the step information. Figure 15 The estimation process is performed in the order shown. The estimation device 50 transmits the plate thickness information and the step information to the wire electrical discharge machining device 100.

[0090] In the third embodiment, the estimation device 50 is configured as a device external to the wire EDM apparatus 100. The estimation device 50 may be connected to the wire EDM apparatus 100 via a network. The estimation device 50 may be hosted on a cloud server. The estimation device 50 is not limited to being external to the wire EDM apparatus 100; it may also be a device built into the wire EDM apparatus 100.

[0091] The estimation device 50 may use the trained model 43 to estimate at least one of the plate thickness and the position of the step. When the estimation device 50 estimates the plate thickness based on the processing data, the estimation unit 52 inputs the processing data into the trained model 43 for estimating the plate thickness based on the processing data, thereby outputting the plate thickness information. Furthermore, when the estimation device 50 estimates the position of the step based on the processing data, the estimation unit 52 inputs the processing data into the trained model 43 for estimating the position of the step based on the processing data, thereby outputting the step information.

[0092] The inference device 50 is Figure 10 Each component of the inference device 50 is implemented by hardware identical to the hardware shown. Each component of the inference device 50 is implemented by a circuit in which a processor executes software, i.e., a processing circuit. Each component of the inference device 50 may be implemented by a dedicated processing circuit, or by a combination of a processing circuit in which a processor executes software and a dedicated processing circuit.

[0093] According to the third embodiment, the inference device 50 inputs processing data into a trained model 43 for inferring at least one of plate thickness and the position of a step portion based on the processing data, thereby outputting at least one of plate thickness information and step information. The inference device 50 can infer at least one of plate thickness and the position of a step portion based on the processing data.

[0094] The wire discharge machining device 100 controls machining based on at least one of the plate thickness and the position of the step estimated by the estimation device 50. The wire discharge machining device 100 can perform machining suitable for the plate thickness in the step, thereby achieving high machining quality.

[0095] The structures shown in the above embodiments illustrate an example of the content of the present invention. The structures of the embodiments can be combined with other known technologies. The structures of the embodiments can also be appropriately combined with each other. A part of the structure of the embodiments can be omitted or changed without departing from the scope of the present invention.

[0096] Description of the label

[0097] 1. Wire electrode spool, 2. Wire electrode, 3. Conveyor roller, 4. Upper power supply, 5. Lower power supply, 6. Upper guide, 7. Lower guide, 8. Worktable, 9. Lower roller, 10. Recovery roller, 11. Wire electrode recovery box, 12. X-axis drive motor, 12. Y-axis drive motor, 13. Machining mechanism, 14. Power supply, 15. Control unit, 16. Machining unit, 17. File, 18. Workpiece, 19. Machining trajectory, 20. Machining power supply, 21. Machining voltage detector, 22. Electrical condition controller, 23. NC device, 24. Plate thickness estimator, 25. Plate thickness output device, 26. Plate thickness input device, 27. Step position estimator, 28. Coordinate corrector, 30. Control circuit, 31. Input unit, 32. Processor, 33. Memory, 34. Output unit, 40. Learning device, 41. 51. Data acquisition unit, 42. Model generation unit, 43. Trained model, 44. Trained model storage unit, 50. Inference device, 52. Inference unit, 100. Wire discharge machining device.

Claims

1. A wire electrical discharge machining device for performing electrical discharge machining of a workpiece by applying a pulse voltage between a wire electrode and the workpiece. The wire discharge machining device is characterized by having: a machining mechanism, which is a mechanism for the electrical discharge machining; a plate thickness estimator for estimating the plate thickness of the workpiece at a position where machining is to be performed when rough machining of the workpiece is performed by the electrical discharge machining; a plate thickness output device configured to output plate thickness data in which plate thickness information indicating the estimated plate thickness is associated with position information to the outside of the wire electrical discharge machining device; a plate thickness input device to which the plate thickness data is input from outside the wire discharge machining device; a position information correction unit that corrects the position information included in the plate thickness data input to the plate thickness input device; a step position estimator for estimating a position of the step portion where the thickness of the workpiece changes based on the thickness data including the corrected position information; an electrical condition controller that controls application of the pulse voltage based on the plate thickness data including the corrected position information and step information indicating the position of the step portion when finishing the workpiece by the electrical discharge machining after the rough machining; as well as A control device controls the machining mechanism based on the plate thickness data including the corrected position information and the step information when performing the finish machining.

2. The wire discharge machining device according to claim 1, wherein The position information included in the plate thickness data is a coordinate of a coordinate system having a predetermined position in the workpiece as an origin.

3. The wire discharge machining device according to claim 1 or 2, wherein: The plate thickness output device writes the plate thickness data to a file stored outside the wire electrical discharge machining device or a machining program for the electrical discharge machining.

4. A wire electrical discharge machining method, wherein a wire electrical discharge machining device performs electrical discharge machining of a workpiece by applying a pulse voltage between a wire electrode and the workpiece. The wire discharge machining method is characterized by comprising the following steps: When rough machining of the workpiece is performed by the electrical discharge machining, estimating the thickness of the workpiece at a position where machining is performed; outputting plate thickness data in which plate thickness information indicating the estimated plate thickness is associated with position information to the outside of the wire electrical discharge machining device; reading the plate thickness data from outside the wire discharge machining device; Correcting the position information included in the read plate thickness data; estimating a position of a step portion where the thickness changes in the workpiece based on the thickness data including the corrected position information; When finishing the workpiece by the discharge machining after the rough machining, the application of the pulse voltage and at least one of the mechanism used for the discharge machining, i.e., the machining mechanism, are controlled based on the plate thickness data including the corrected position information and the step information indicating the position of the step portion.

5. A learning device for a wire electrical discharge machining apparatus that performs electrical discharge machining of a workpiece by applying a pulse voltage between a wire electrode and the workpiece, the device learning the relationship between machining data related to the state of the electrical discharge machining, the thickness of the workpiece, and the position of a step portion in the workpiece where the thickness changes. The learning device is characterized by having: a data acquisition unit that acquires learning data including the processing data, plate thickness information indicating the plate thickness, and step information indicating the position of the step portion; and A model generating unit generates a trained model for estimating the plate thickness and the position of the step portion based on the machining data using the learning data.

6. An estimation device for a wire electrical discharge machining apparatus that performs electrical discharge machining of a workpiece by applying a pulse voltage between a wire electrode and the workpiece, the device estimating the thickness of the workpiece and the position of a step portion in the workpiece where the thickness changes, based on machining data related to the state of the electrical discharge machining. The inference device is characterized by having: a data acquisition unit that acquires the processed data; and An inference unit inputs the processing data into a trained model for inferring the plate thickness and the position of the step portion based on the processing data, thereby outputting plate thickness information indicating the plate thickness and step information indicating the position of the step portion.

Images