Electrical discharge machining device and electrical discharge machining method

Abstract

An electrical discharge machining device (1A) comprises: a power source device (20) that supplies power to a machining gap between a tool electrode (4) and a workpiece (3); a current detection unit (9) that detects an inter-electrode current value, which is the current value of a current flowing from the power source device to the machining gap; a voltage command detection unit (12) that detects an applied voltage value, which is a command value for the voltage value of a voltage applied to the machining gap; and a computation device (10A) that acquires the inter-electrode current value and the applied voltage value, infers electrical characteristics from the inter-electrode current value and the applied voltage value using a learning model for inferring electrical characteristics unique to the electrical discharge machining device from an inter-electrode current value and an applied voltage value, and determines a correction value for correcting the inter-electrode current value and the applied voltage value so that the inferred electrical characteristics match reference characteristics, which are reference electrical characteristics.

Description

Electric discharge machining device and electric discharge machining method

[0001] The present disclosure relates to an electric discharge machining apparatus and an electric discharge machining method for machining a workpiece using electric discharge energy.

[0002] 2. Description of the Related Art Electric discharge machining apparatuses that generate electric discharges between machining poles formed by a tool electrode and a workpiece and machine the workpiece using the discharge energy are desired to perform stable machining according to the electric discharge machining apparatus.

[0003] The machining condition adjustment device described in Patent Document 1 learns adjustment behavior of machining conditions (voltage waveform, current waveform, etc.) in relation to machining states (machining voltage, machining current, machining speed, etc.), and predicts adjustment behavior of machining conditions based on the machining states when a specified machining is performed.

[0004] International Publication No. 2022 / 210472

[0005] However, the technology of Patent Document 1 learns adjustment behavior common to multiple electric discharge machining devices, so it is not possible to correct machining errors caused by electrical characteristics unique to the electric discharge machining device, resulting in a problem of reduced machining quality.

[0006] The present disclosure has been made in view of the above, and has an object to provide an electric discharge machining apparatus that can suppress a decrease in machining quality.

[0007] In order to solve the above-mentioned problems and achieve the object, the electric discharge machining apparatus of the present disclosure includes a power supply device that supplies power to a gap between the machining poles between the tool electrode and the workpiece, a current detection unit that detects an inter-pole current value, which is the current value of a current flowing from the power supply device to the gap between the machining poles, a voltage command detection unit that detects an applied voltage value, which is a command value for the voltage value applied between the machining poles, and a calculation device that acquires the inter-pole current value and the applied voltage value, infers electrical characteristics from the inter-pole current value and the applied voltage value using a learning model for inferring electrical characteristics specific to the apparatus from the inter-pole current value and the applied voltage value, and determines a correction value for correcting the inter-pole current value and the applied voltage value so that the inferred electrical characteristics become reference characteristics, which are standard electrical characteristics.

[0008] The electric discharge machining apparatus according to the present disclosure has the effect of suppressing a decrease in machining quality.

[0009] FIG. showing the configuration of the electric discharge machining apparatus according to Embodiment 1; FIG. showing the configuration of the learning apparatus included in the electric discharge machining apparatus according to Embodiment 1; FIG. showing a configuration example of the neural network used in the learning apparatus of Embodiment 1; FIG. flowchart showing the processing procedure of the processing executed when the electric discharge machining apparatus according to Embodiment 1 corrects the electrical characteristics; FIG. showing a waveform example of the interelectrode current value acquired by the electric discharge machining apparatus according to Embodiment 1; FIG. for explaining the process of the electric discharge machining apparatus according to Embodiment 1 inferring the impedance and stray capacitance value; FIG. for explaining the range that can be corrected by the electric discharge machining apparatus according to Embodiment 1; FIG. showing the configuration of the electric discharge machining apparatus according to Embodiment 2; FIG. showing the machining circuit of the machining part when the machining electrodes of the electric discharge machining apparatus according to Embodiment 2 are in the open state; FIG. showing the equivalent circuit corresponding to the machining circuit of FIG. 9; FIG. for explaining the impedance and phase delay when the machining electrodes of the electric discharge machining apparatus according to Embodiment 2 are in the open state, which is calculated by the electric discharge machining apparatus according to Embodiment 2; FIG. showing the frequency characteristics when the machining electrodes of the electric discharge machining apparatus according to Embodiment 2 are in the open state, which is calculated by the electric discharge machining apparatus according to Embodiment 2; FIG. showing the machining circuit of the machining part when the machining electrodes of the electric discharge machining apparatus according to Embodiment 2 are in the short-circuit state; FIG. showing the equivalent circuit corresponding to the machining circuit of FIG. 13; FIG. for explaining the impedance and phase delay when the machining electrodes of the electric discharge machining apparatus according to Embodiment 2 are in the short-circuit state, which is calculated by the electric discharge machining apparatus according to Embodiment 2; FIG. showing the frequency characteristics when the machining electrodes of the electric discharge machining apparatus according to Embodiment 2 are in the short-circuit state, which is calculated by the electric discharge machining apparatus according to Embodiment 2; FIG. flowchart showing the processing procedure of the processing executed when the electric discharge machining apparatus according to Embodiment 2 corrects the electrical characteristics; FIG. showing an example of the screen displayed on the display when the electric discharge machining apparatus according to Embodiment 3 has a deviation in electrical characteristics; FIG. showing an example of the screen displayed on the display after the electric discharge machining apparatus according to Embodiment 3 corrects the deviation in electrical characteristics; FIG. showing a hardware configuration example for realizing the arithmetic unit according to Embodiment 1

[0010] Hereinafter, the electric discharge machining apparatus and the electric discharge machining method according to the embodiments of the present disclosure will be described in detail based on the drawings.

[0011] 1 is a diagram showing the configuration of an electric discharge machining apparatus according to embodiment 1. The electric discharge machining apparatus 1A applies a voltage pulse between machining poles formed by a tool electrode (machining electrode) 4 and a workpiece (work) 3, and generates an electric discharge between the machining poles by bringing the tool electrode 4 and the workpiece 3 close to each other, and machines the workpiece 3 with the arc heat of the generated electric discharge.

[0012] The electric discharge machining apparatus 1A includes a machining unit 2A, a power supply device 20, and a computing device 10A. The power supply device 20 is a machining power source connected in series between the machining poles between the tool electrode 4 and the workpiece 3, and supplies power between the machining poles. The power supply device 20 supplies power between the machining poles by outputting an AC or DC voltage between the machining poles.

[0013] The machining unit 2A has a tool electrode 4 and a current detection unit 9. The machining unit 2A performs electrical discharge machining on the workpiece 3 using power supplied from a power supply unit 20. The current detection unit 9 is connected in series between the power supply unit 20 and the machining gap, and measures the current value of the current flowing from the power supply unit 20 to the machining gap (hereinafter sometimes referred to as the gap current value). The current detection unit 9 transmits the measured gap current value to the calculation unit 10A. The calculation unit 10A is a computer that executes calculations of information used during electrical discharge machining.

[0014] The power supply device 20 and the machining pole are connected by a cable (not shown). This cable has electrical characteristics (electrical load) in the electrical circuit, such as a parasitic inductance PX1, a stray capacitance value (described later), and impedance. The parasitic inductance PX1, the stray capacitance value, and the impedance have a significant effect on the current flowing between the machining poles. The impedance is a value calculated based on the parasitic inductance PX1 and the stray capacitance value. In the first embodiment, the electric discharge machining device 1A corrects the impedance and the stray capacitance value to prevent a decrease in machining quality.

[0015] Even if the length, thickness, and number of cables connecting the power supply device 20 and the machining gap are constant, their electrical characteristics vary depending on mechanical characteristics such as their spatial path, bending state, and contact with the connection. Therefore, machining characteristics such as the surface roughness of the machined surface of the workpiece 3 and the post-machining dimensions of the workpiece 3 vary depending on the cable condition. For example, even between electrical discharge machining apparatuses 1A of the same model, if the mechanical characteristics of individual cables vary, the current flowing between the electrodes may change, and the machining results may not meet the desired dimensional and surface roughness tolerances. Therefore, in embodiment 1, the electrical discharge machining apparatus 1A corrects the applied voltage value and the gap current value (described below) to correct the electrical characteristics (impedance and stray capacitance values ​​in embodiment 1).

[0016] The arithmetic device 10A is connected to the machining unit 2A, the power supply device 20, and the display device 25. Note that the connection lines between the arithmetic device 10A and the machining unit 2A are not shown. The arithmetic device 10A has a control unit 11, a voltage command detection unit 12, a calculation unit 13, a learning device 14, and a correction value determination unit 16. The control unit 11 controls the machining unit 2A, the power supply device 20, and the display device 25.

[0017] The voltage command detection unit 12 detects a command value for the voltage value applied between the machining electrodes (hereinafter, sometimes referred to as an applied voltage value). The voltage command detection unit 12 detects the applied voltage value based on a voltage command output from the control unit 11 to the power supply device 20. The voltage command detection unit 12 transmits the detected applied voltage value to the learning device 14.

[0018] The calculation unit 13 calculates various information. The display 25 displays information of the electric discharge machining device 1A in accordance with instructions from the electric discharge machining device 1A. The display 25 displays the state of the electric discharge machining device 1A, machining conditions, etc.

[0019] During learning, the learning device 14 performs machine learning of the relationship between the inter-electrode current value in the discharge circuit and the measured impedance, and during inference, infers the impedance corresponding to the inter-electrode current value in the discharge circuit.

[0020] During learning, the learning device 14 calculates the amount of electricity flowing between the machining electrodes by integrating the inter-electrode current value with respect to time. During learning, the learning device 14 performs machine learning to determine the relationship between the amount of electricity, the applied voltage value, and the stray capacitance multiplied by a constant (constant α, described below). Hereinafter, the stray capacitance multiplied by the constant α may be referred to as the stray capacitance value αC. During inference, the learning device 14 infers the stray capacitance value αC corresponding to the amount of electricity and the applied voltage value.

[0021] The stray capacitance value αC is a value specific to the electric discharge machining apparatus 1A. In the first embodiment, the electric discharge machining apparatus 1A learns the stray capacitance value αC, thereby inferring the stray capacitance value αC specific to the electric discharge machining apparatus 1A. That is, the electric discharge machining apparatus 1A learns and infers the stray capacitance value αC specific to each electric discharge machining apparatus 1A.

[0022] Generally, when the electrical characteristics of the electric discharge machining device, such as impedance, change, the current flowing between the machining electrodes during discharge also changes. Since the machining accuracy, such as the surface roughness of the machined surface of the workpiece 3 and the dimensions of the workpiece 3 after machining, is affected by the current flowing between the machining electrodes during discharge, the machining accuracy also changes when the current changes.

[0023] The electric discharge machining apparatus 1A of the first embodiment corrects the applied voltage value and the inter-electrode current value in order to correct the electrical characteristics themselves, and therefore can achieve stable machining quality regardless of the size of the workpiece 3, the type of wire, the condition of the cable, etc.

[0024] Furthermore, the electric discharge machining apparatus 1A can correct the applied voltage value and the gap current value without adjusting the machining conditions provided by the electric discharge machining apparatus manufacturer, which makes it easier to control the machining quality.

[0025] Furthermore, the electric discharge machining apparatus 1A corrects the applied voltage value and the gap current value to correct the electrical characteristics specific to the electric discharge machining apparatus 1A, thereby suppressing individual differences in machining accuracy of the electric discharge machining apparatus 1A. Note that the electric discharge machining apparatus 1A may correct the discharge frequency, voltage rest time, peak value of the discharge current, pulse width of the discharge current, axial feed speed, etc. to correct the electrical characteristics.

[0026] Here, a detailed configuration of the learning device 14 will be described. Fig. 2 is a diagram showing the configuration of the learning device provided in the electric discharge machining apparatus according to embodiment 1. The learning device 14 has a state observation unit 141, a data acquisition unit 142, a learning unit 143, and an inference unit 144.

[0027] The state observing unit 141 acquires the applied voltage value from the voltage command detecting unit 12. The state observing unit 141 also acquires the inter-electrode current value from the current detecting unit 9. The state observing unit 141 transmits the applied voltage value and the inter-electrode current value to the learning unit 143 both during learning and during inference.

[0028] During learning, the data acquiring unit 142 acquires the impedance measured with respect to the discharge circuit. The impedance may be measured by any method. Furthermore, during learning, the data acquiring unit 142 acquires the measured stray capacitance value αC between the machining electrodes. The stray capacitance value αC may be measured by any method. The data acquiring unit 142 transmits the impedance and the stray capacitance value αC to the learning unit 143.

[0029] The learning unit 143 learns the impedance (predicted value) corresponding to the inter-electrode current value based on a data set (learning data) created based on a combination of the inter-electrode current value received from the state observing unit 141 and the impedance received from the data acquiring unit 142. That is, the learning unit 143 uses the learning data including the inter-electrode current value and the impedance to generate a learning model (hereinafter sometimes referred to as an impedance learning model) for inferring the impedance from the inter-electrode current value.

[0030] Here, the data set used to generate the impedance learning model is data in which the inter-electrode current value, which is a state variable, and the impedance, which is judgment data, are associated with each other. The impedance learning model is generated for each electric discharge machining apparatus 1A. In other words, the electric discharge machining apparatus 1A generates the impedance learning model using data measured for its own apparatus, without using data from other apparatuses.

[0031] The learning unit 143 also calculates the amount of electricity flowing between the machining electrodes by time-integrating the inter-electrode current value received from the state observing unit 141. The learning unit 143 learns the stray capacitance value αC (predicted value) corresponding to the applied voltage value and the amount of electricity based on a data set created based on a combination of the stray capacitance value αC, which is the stray capacitance between the machining electrodes, the applied voltage value received from the state observing unit 141, and the calculated amount of electricity. That is, the learning unit 143 generates a learning model (hereinafter sometimes referred to as a stray capacitance learning model) for inferring the stray capacitance value αC from the applied voltage value and the amount of electricity using learning data including the stray capacitance value αC, the applied voltage value, and the amount of electricity.

[0032] Here, the data set used to generate the stray capacitance learning model is data in which the applied voltage value and the amount of electricity, which are state variables, are associated with the stray capacitance value αC, which is judgment data. The stray capacitance learning model is generated for each electric discharge machining apparatus 1A. In other words, the electric discharge machining apparatus 1A generates the stray capacitance learning model using data measured for its own apparatus, without using data from other apparatuses.

[0033] When the applied voltage value is the applied voltage value V and the electrical quantity is the electrical quantity Q, the learning unit 143 learns the relationship of the following equation (1) to learn the stray capacitance value αC corresponding to the applied voltage value and the electrical quantity.

[0034] Q=αC×V...(1)

[0035] The impedance learning model and stray capacitance learning model generated by the learning unit 143 are stored in a storage device (not shown) included in the electric discharge machining apparatus 1A. The inference unit 144 infers the impedance from the applied voltage value using the impedance learning model. Specifically, the inference unit 144 infers the impedance corresponding to the applied voltage value by inputting the applied voltage value to the impedance learning model.

[0036] Furthermore, the inference unit 144 infers the stray capacitance value αC from the applied voltage value and the amount of electricity using a stray capacitance learning model. Specifically, the inference unit 144 infers the stray capacitance value αC corresponding to the applied voltage value and the amount of electricity by inputting the applied voltage value and the amount of electricity into the stray capacitance learning model. The inference unit 144 transmits the impedance and stray capacitance value αC, which are the inference results, to the correction value determination unit 16.

[0037] The correction value determination unit 16 corrects at least one of the voltage value of the voltage applied between the machining poles by the power supply unit 20 and the current value of the current flowing between the machining poles, based on the impedance and stray capacitance value αC received from the inference unit 144.

[0038] The learning device 14 may be, for example, a device separate from the electric discharge machining device 1A that is connected to the electric discharge machining device 1A via a network. The learning device 14 may also exist on a cloud server.

[0039] The learning device 14 learns the impedance of the discharge circuit or the stray capacitance value αC between the machining poles by so-called supervised learning, for example, according to a neural network model. Here, supervised learning refers to a technique in which a large number of pairs of data of certain inputs and results (labels) are provided to a machine learning device, and the device learns the features of these data sets and infers the results from the inputs.

[0040] The neural network is composed of an input layer consisting of multiple neurons, an intermediate layer (hidden layer) consisting of multiple neurons, and an output layer consisting of multiple neurons. The intermediate layer may be one layer or two or more layers. Note that part of the processing performed by the learning device 14 may be performed by the calculation unit 13.

[0041] 3 is a diagram showing an example of the configuration of a neural network used in the learning device of embodiment 1. For example, in a three-layer neural network as shown in FIG. 3, when multiple inputs are input to the input layer (X1 to X3), the values ​​are multiplied by weights W1 (w11 to w16) and input to the intermediate layers (Y1 to Y2). The results are then further multiplied by weights W2 (w21 to w26) and output from the output layers (Z1 to Z3). This output result varies depending on the values ​​of weights W1 and W2.

[0042] 3 used by the learning device 14 is an impedance learning model, the neural network learns the impedance corresponding to the inter-electrode current value by so-called supervised learning in accordance with a data set created based on a combination of the inter-electrode current value acquired by the state observing unit 141 and the impedance acquired by the data acquiring unit 142.

[0043] That is, in the case of an impedance learning model, the neural network learns by inputting the inter-electrode current value as the first input and adjusting the weights W1 and W2 so that the result output from the output layer approaches the impedance (correct answer) as the second input. In this case, the learning device 14 learns the correspondence between the inter-electrode current value and the impedance, thereby generating an impedance learning model that can output an appropriate impedance when the inter-electrode current value is input. In this way, the learning device 14 learns a learning model that can output the correct impedance when the inter-electrode current value is input.

[0044] 3 used by the learning device 14 is a stray capacitance learning model, the neural network learns the stray capacitance value αC corresponding to the applied voltage value and the amount of electricity by so-called supervised learning in accordance with a data set created based on a combination of the applied voltage value and the amount of electricity acquired by the state observing unit 141 and the stray capacitance value αC acquired by the data acquiring unit 142.

[0045] That is, in the case of a stray capacitance learning model, the neural network learns by inputting the applied voltage value and the amount of electricity as the first input and adjusting the weights W1 and W2 so that the result output from the output layer approaches the stray capacitance value αC (correct answer) as the second input. In this case, the learning device 14 learns the correspondence between the applied voltage value and the amount of electricity and the stray capacitance value αC, thereby generating a learning model that can output an appropriate stray capacitance value αC when an applied voltage value and an amount of electricity are input. In this way, the learning device 14 learns a learning model that can output the correct stray capacitance value αC when an applied voltage value and an amount of electricity are input.

[0046] The learning device 14 can also learn the impedance or stray capacitance value αC through so-called unsupervised learning. Unsupervised learning is a technique in which a machine learning device is provided with a large amount of input data alone to learn the distribution of the input data and then learns to compress, classify, reshape, and so on for the input data without providing corresponding teacher output data. In unsupervised learning, the learning device 14 can, for example, cluster data sets with similar features. Using the results of this clustering, the learning device 14 can set some kind of criterion and assign outputs that optimize the criterion, thereby realizing output prediction. The learning device 14 may also learn the impedance or stray capacitance value αC through reinforcement learning. Q-learning and TD-learning are known as representative reinforcement learning techniques.

[0047] Deep learning, which learns to extract features themselves, can also be used as the learning algorithm used in the learning device 14. The learning device 14 may also perform machine learning according to other known methods, such as genetic programming, functional logic programming, or support vector machines.

[0048] The electric discharge machining apparatus 1A generates an impedance learning model and a stray capacitance learning model by performing machining under various machining conditions. The electric discharge machining apparatus 1A performs machining at various gap current values ​​and measures the impedance during each machining. The learning device 14 of the electric discharge machining apparatus 1A generates the impedance learning model by learning the impedance corresponding to the gap current value based on a data set created based on a combination of the gap current value and the impedance.

[0049] Furthermore, the electric discharge machining apparatus 1A performs machining with various applied voltage values ​​and gap current values, and measures the stray capacitance value αC during each machining operation. The learning device 14 of the electric discharge machining apparatus 1A calculates the amount of electricity flowing between the machining gaps by integrating the gap current value over time during each machining operation. The learning device 14 generates a stray capacitance learning model by learning the stray capacitance value αC corresponding to the applied voltage value and the amount of electricity based on a data set created based on a combination of the applied voltage value, the stray capacitance value αC, and the amount of electricity.

[0050] When actually machining the workpiece 3, the electric discharge machining apparatus 1A infers the impedance using the impedance learning model and infers the stray capacitance value αC using the stray capacitance learning model. The electric discharge machining apparatus 1A calculates a correction value corresponding to the inferred impedance and the inferred stray capacitance value αC. The correction value corresponding to the inferred impedance corresponds to the difference between the reference impedance and the inferred impedance. Furthermore, the correction value corresponding to the inferred stray capacitance value αC corresponds to the difference between the reference stray capacitance value αC and the inferred stray capacitance value αC. In this way, the electric discharge machining apparatus 1A calculates a correction value corresponding to the deviation between the inferred electrical characteristics and the reference electrical characteristics (reference characteristics).

[0051] The correction values ​​calculated by the electric discharge machining device 1A include a correction value (voltage correction value) for correcting the voltage value of the voltage applied by the power supply device 20 between the machining poles, and a correction value (current correction value) for correcting the current value of the current flowing between the machining poles.

[0052] The voltage correction value is a correction value for a reference voltage value, and the current correction value is a correction value for a reference current value. The electric discharge machining device 1A corrects the reference voltage value using the voltage correction value and corrects the reference current value using the current correction value, thereby correcting the impedance and stray capacitance value αC specific to the electric discharge machining device 1A.

[0053] 4 is a flowchart showing the procedure of processing executed when the electric discharge machining apparatus according to the first embodiment corrects the electrical characteristics. The electric discharge machining apparatus 1A stores an impedance learning model and a stray capacitance learning model obtained by learning.

[0054] The electric discharge machining apparatus 1A sets machining parameters in accordance with instructions from the user (step S10). The machining parameters are physical quantities that occur when the workpiece 3 is electric discharge machined. Examples of the machining parameters include the thickness of the workpiece 3, the material of the workpiece 3, the positions of the upper and lower nozzles, and the wire diameter of the tool electrode 4.

[0055] The electric discharge machining device 1A starts machining the workpiece 3 using the machining parameters and acquires a machining waveform (step S20). The machining waveform here includes a waveform of the machining gap current value measured by the current detection unit 9 and a waveform of the applied voltage value detected by the voltage command detection unit 12.

[0056] The learning device 14 of the electric discharge machining apparatus 1A infers the impedance from the gap current value by inputting the gap current value to the impedance learning model (step S30). In other words, the learning device 14 infers the impedance component of the components that affect the machining quality from the gap current value.

[0057] The learning device 14 also calculates the amount of electricity flowing between the machining electrodes by integrating the gap current value with respect to time. The learning device 14 inputs the applied voltage value and the amount of electricity into the stray capacitance learning model, and infers the stray capacitance value αC from the applied voltage value and the amount of electricity (step S40). In other words, the learning device 14 infers the stray capacitance component, which is one of the components that affect the machining quality, from the applied voltage value and the amount of electricity.

[0058] Here, a process for inferring impedance from the inter-electrode current value and a process for inferring stray capacitance value αC from the applied voltage value and the amount of electricity will be described. Fig. 5 is a diagram showing an example of a waveform of the inter-electrode current value acquired by the electric discharge machining apparatus according to the first embodiment. Fig. 6 is a diagram for explaining a process for inferring impedance and stray capacitance values ​​by the electric discharge machining apparatus according to the first embodiment. The horizontal axis of the graphs shown in Fig. 5 and Fig. 6 represents time, and the vertical axis represents the inter-electrode current value.

[0059] The current detection unit 9 measures the gap current value at a specific cycle, and therefore the obtained gap current value is a fragmentary value as shown in Fig. 5. The inference unit 144 calculates a waveform 40 of the continuously changing gap current value from the fragmentary gap current value by interpolation or the like.

[0060] The inference unit 144 infers the impedance from the inter-electrode current value based on the waveform 40 of the inter-electrode current value and the impedance learning model.

[0061] The inference unit 144 also calculates the quantity of electricity by integrating the inter-electrode current value over time. When the applied voltage value is constant, the quantity of electricity is proportional to the stray capacitance value αC. In other words, when the applied voltage value is constant, the time integral value of the inter-electrode current value is proportional to the stray capacitance value αC. The inference unit 144 infers the stray capacitance value αC from the quantity of electricity calculated from the waveform 40 of the inter-electrode current value, the applied voltage value, and the stray capacitance learning model.

[0062] The inference unit 144 may infer the stray capacitance value αC using the impedance immediately after discharge. In this case, the inference unit 144 differentiates the inter-electrode current value immediately after discharge with respect to time to calculate the slope 41 of the inter-electrode current value immediately after discharge. That is, the inference unit 144 calculates the increase over time of the inter-electrode current value immediately after discharge. The increase over time of the inter-electrode current value immediately after discharge is proportional to the impedance immediately after discharge. The inference unit 144 infers the stray capacitance value αC using the calculated impedance immediately after discharge. This allows the inference unit 144 to improve the accuracy of inferring the stray capacitance value αC.

[0063] The electric discharge machining device 1A calculates correction values ​​(voltage correction value and current correction value) for correcting the impedance and stray capacitance value αC (step S50). The electric discharge machining device 1A determines the calculated correction values ​​as the current correction values ​​of the electric discharge machining device 1A (step S60).

[0064] The electric discharge machining apparatus 1A executes the processes of steps S10 to S60 at the start of machining. The electric discharge machining apparatus 1A may execute the process of step S10 at the start of machining, and execute the processes of steps S20 to S60 while machining. In this case, the electric discharge machining apparatus 1A executes the processes of steps S30 to S60 when the machining waveform changes.

[0065] Here, the range in which correction is possible with an electric discharge machining apparatus of a comparative example (hereinafter referred to as a comparative electric discharge machining apparatus) and the range in which correction is possible with the electric discharge machining apparatus 1A of the first embodiment will be described.

[0066] When the comparative electric discharge machining device is shipped from the manufacturer of the comparative electric discharge machining device, a machining test is performed and various adjustments are made based on the results of the machining test. This allows adjustments to be made for machining errors and the like that are caused by the mechanical assembly specific to the comparative electric discharge machining device, but the machining test takes time and costs money.

[0067] There is also a method in which the machining conditions applied to the comparative electric discharge machining device are adjusted by a machining condition adjustment device. In this method, the machining condition adjustment device learns adjustment behavior of the machining conditions in response to the machining state, such as the machining voltage, and predicts adjustment behavior of the machining conditions based on the machining state when a predetermined machining is performed.

[0068] Since this machining condition adjustment device learns common adjustment behaviors for a plurality of electric discharge machining devices, it cannot eliminate machining errors that occur in each comparison electric discharge machining device. Therefore, the machining condition adjustment device cannot correct machining errors caused by electrical characteristics (impedance, stray capacitance value αC, etc.) unique to the comparison electric discharge machining device, resulting in a decrease in machining quality.

[0069] For example, in the case of a comparative electric discharge machining device, the electrical characteristics specific to the comparative electric discharge machining device change depending on the machine installation difference when the comparative electric discharge machining device is installed, but the comparative electric discharge machining device cannot correct the machining error due to the machine installation difference of the comparative electric discharge machining device.

[0070] Furthermore, in the case of a comparative electric discharge machining device, when the condition of the comparative electric discharge machining device changes over time, the electrical characteristics specific to the comparative electric discharge machining device change, but the comparative electric discharge machining device cannot correct machining errors caused by changes in the condition of the comparative electric discharge machining device.

[0071] Furthermore, in the comparative electric discharge machining device, when the state of the machining fluid changes, the electrical characteristics specific to the comparative electric discharge machining device change, but the comparative electric discharge machining device cannot correct machining errors caused by changes in the state of the machining fluid.

[0072] Furthermore, in the comparative electric discharge machining device, the electrical characteristics specific to the comparative electric discharge machining device change when parts are replaced, but the comparative electric discharge machining device cannot correct machining errors resulting from part replacement.

[0073] Furthermore, the machining condition adjustment device does not eliminate errors that occur for each individual machine, but simply associates the machining conditions with the adjustment actions for the machining conditions. Therefore, the machining condition adjustment device has to change the adjustment contents of the machining conditions every time the type of workpiece to be machined or the wire type is changed, which is time-consuming.

[0074] The comparative electric discharge machining device changes the adjustment contents of the machining conditions every time there is a change in, for example, the type of workpiece to be machined, the type of electrode, the state of the cable connecting the power supply device provided in the comparative electric discharge machining device and the machining electrode, etc. Therefore, for the comparative electric discharge machining device, it is necessary to individually correct each of the groups of machining conditions provided by the manufacturer, making it difficult to manage the machining conditions.

[0075] On the other hand, the electric discharge machining apparatus 1A of the first embodiment generates an impedance learning model for inferring impedance from an applied voltage value during learning, and infers impedance from the applied voltage value using the impedance learning model during inference.Furthermore, the electric discharge machining apparatus 1A generates a stray capacitance learning model for inferring a stray capacitance value αC from an applied voltage value and an electric quantity during learning, and infers the stray capacitance value αC from the applied voltage value and an electric quantity during inference.

[0076] The electric discharge machining device 1A then calculates a voltage correction value and a current correction value for correcting the impedance and the stray capacitance value αC, and corrects the voltage and current during machining using the voltage correction value and the current correction value.

[0077] In this way, even if the electrical characteristics specific to the electrical discharge machining device 1A change, the electrical discharge machining device 1A can infer the changed electrical characteristics and calculate the voltage correction value and current correction value based on the electrical characteristics, thereby easily correcting machining errors.

[0078] 7 is a diagram for explaining the range of correction possible by the electric discharge machining apparatus according to embodiment 1. The electric discharge machining apparatus 1A can correct, as individual differences, machining errors caused by differences in machine installation, machining errors caused by changes in the machine condition over time, machining errors caused by the machining fluid condition, and machining errors caused by differences in replaced parts.

[0079] Even if the electrical characteristics specific to the electrical discharge machining device 1A change due to, for example, machine installation differences, the electrical discharge machining device 1A can infer the electrical characteristics and use voltage correction values ​​and current correction values ​​according to the electrical characteristics, thereby correcting machining errors due to machine installation differences.

[0080] Furthermore, even if a difference in mechanical condition occurs due to aging, the electric discharge machining device 1A infers the electrical characteristics and uses voltage correction values ​​and current correction values ​​according to the electrical characteristics, so that machining errors due to the difference in mechanical condition can be corrected.

[0081] Furthermore, even when there is a difference in the state of the machining fluid, the electric discharge machining device 1A infers the electrical characteristics and uses voltage correction values ​​and current correction values ​​according to the electrical characteristics, so that machining errors due to the difference in the state of the machining fluid can be corrected.

[0082] Furthermore, even if there is a difference in the replaced parts (such as a difference in wire diameter), the electric discharge machining device 1A infers the electrical characteristics and uses voltage correction values ​​and current correction values ​​according to the electrical characteristics, so that machining errors caused by differences in the replaced parts can be corrected.

[0083] Furthermore, even if the type of workpiece 3 to be machined by the electric discharge machining device 1A and the type of wire are changed, the electric discharge machining device 1A infers the electrical characteristics and uses voltage correction values ​​and current correction values ​​according to the electrical characteristics, so there is no need to change the adjustment contents of the machining conditions.

[0084] As described above, in the first embodiment, the electric discharge machining device 1A infers the electrical characteristics and corrects the electrical characteristics using a voltage correction value and a current correction value according to the electrical characteristics, so that machining errors caused by the electrical characteristics can be corrected regardless of individual differences due to differences in the installation of the machine (machine), changes over time, or changes in the installation environment.

[0085] Furthermore, the electric discharge machining device 1A corrects deviations that may occur in individual electric discharge machining devices 1A, so that fluctuations in machining characteristics can be suppressed and individual adjustment of machining conditions becomes unnecessary.

[0086] As described above, the electric discharge machining apparatus 1A of the first embodiment infers electrical characteristics from the gap current value and applied voltage value using a learning model for inferring electrical characteristics specific to the apparatus from the gap current value and applied voltage value. The electric discharge machining apparatus 1A then corrects the gap current value and applied voltage value so that the inferred electrical characteristics become reference characteristics, which are standard electrical characteristics. This allows the electric discharge machining apparatus 1A to correct the electrical characteristics specific to the apparatus, thereby maintaining a certain level of machining accuracy and preventing a decrease in machining quality.

[0087] Second Embodiment Next, a second embodiment will be described with reference to FIGS. 8 to 17. The electric discharge machining apparatus 1A of the first embodiment can infer the electrical characteristics present on the machining circuit from the gap current value and applied voltage value detected during machining. When applying the electric discharge machining apparatus 1A, the user needs to perform preliminary machining to obtain the gap current value and applied voltage value before performing actual machining. In the second embodiment, the electrical characteristics on the machining circuit are inferred without performing preliminary machining before machining. The machining circuit includes an electric circuit such as a cable, a machining gap, a tool electrode 4, a workpiece 3, etc.

[0088] The electrical characteristics in the second embodiment are at least one of impedance, stray capacitance αC, parasitic inductance, machining fluid resistance, and wiring resistance. In the second embodiment, the frequency characteristics of impedance and phase lag are compared with frequency characteristics calculated from the circuit equation of the equivalent circuit of the machining circuit to infer electrical characteristics such as stray capacitance αC and parasitic inductance. The phase lag is the phase difference between the inter-electrode current value and the applied voltage value.

[0089] Fig. 8 is a diagram showing the configuration of an electric discharge machining apparatus according to embodiment 2. Of the components in Fig. 8, those that achieve the same functions as those in the electric discharge machining apparatus 1A of embodiment 1 shown in Fig. 1 are assigned the same reference numerals, and duplicated explanations will be omitted.

[0090] The electric discharge machining apparatus 1B infers electrical characteristics on a machining circuit without performing preliminary machining before machining. Compared to the electric discharge machining apparatus 1A, the electric discharge machining apparatus 1B includes a machining unit 2B instead of the machining unit 2A and a computing unit 10B instead of the computing unit 10A. That is, the electric discharge machining apparatus 1B includes the machining unit 2B, a power supply unit 20, and the computing unit 10B.

[0091] In addition to the components of the processing unit 2A, the processing unit 2B has a voltage detection unit 8. Compared to the calculation device 10A, the calculation device 10B does not have a voltage command detection unit 12. Moreover, compared to the calculation device 10A, the calculation device 10B has an inference device 15 instead of the learning device 14.

[0092] The voltage detection unit 8 is electrically connected in parallel between the machining poles and detects, as an applied voltage value, the voltage value of the voltage applied between the machining poles from the power supply device 20. The voltage detection unit 8 transmits the detected applied voltage value to the calculation device 10B.

[0093] The current detection unit 9 is electrically connected in series between the machining gap and the power supply unit 20, and detects, as the gap current value, the current value of the current supplied from the power supply unit 20 to the machining gap. The current detection unit 9 transmits the detected gap current value to the calculation unit 10B.

[0094] The control unit 11 of the calculation device 10B controls the power supply device 20 and the display 25. The control unit 11 controls, for example, parameters of the power supply device 20 (applied voltage value, inter-electrode current value, discharge frequency, voltage rest time, peak value of discharge current, pulse width of discharge current, axial feed speed, etc.).

[0095] The calculation unit 13 of the calculation device 10B calculates the frequency characteristics of the impedance and the frequency characteristics of the phase delay (phase lag) based on the applied voltage value, which is the output value from the voltage detection unit 8, and the inter-pole current value, which is the output value from the current detection unit 9.

[0096] The inference device 15 of the calculation device 10B infers the stray capacitance value αC and the parasitic inductance present in the machining circuit based on the frequency characteristics of the impedance and the frequency characteristics of the phase delay output from the calculation unit 13. Note that the power supply device 20 of the second embodiment may have any circuit configuration, but is preferably a device capable of applying both AC and DC voltages between the machining poles.

[0097] Here, a method by which the electric discharge machining device 1B infers the stray capacitance value αC and parasitic inductance on the machining circuit (between the machining poles) will be described. In an open state where the tool electrode 4 and the workpiece 3 are not in contact, the stray capacitance value αC is dominant, and in a short-circuited state where the tool electrode 4 and the workpiece 3 are in contact, the parasitic inductance is dominant. For this reason, the electric discharge machining device 1B infers the stray capacitance value αC between the machining poles based on the frequency characteristics of the machining circuit in the open state, and infers the parasitic inductance on the machining circuit based on the frequency characteristics of the machining circuit in the short-circuited state.

[0098] First, a method for the electric discharge machining apparatus 1B to infer the stray capacitance value αC will be described. Fig. 9 is a diagram showing the machining circuit of the machining unit when the machining gap of the electric discharge machining apparatus according to the second embodiment is in a released state. Fig. 10 is a diagram showing an equivalent circuit corresponding to the machining circuit of Fig. 9. As shown in Fig. 9, in the machining circuit 51 of the machining unit 2B, when the tool electrode 4 and the workpiece 3 are not in contact with each other, i.e., when the machining gap is in a released state, the machining circuit 51 is represented by an equivalent circuit 55 shown in Fig. 10. The released state machining circuit 51 is the first machining circuit.

[0099] In the equivalent circuit 55, a parasitic inductance PX1 occurs between the power supply 20 and the tool electrode 4, a stray capacitance value C1 occurs between the tool electrode 4 and the workpiece 3 as a stray capacitance value αC, and a machining fluid resistance R1, which is the resistance of the machining fluid, occurs between the machining electrodes.

[0100] In this state, the electric discharge machining device 1B applies an AC voltage from the power supply device 20 and detects the gap current value and the applied voltage value. The calculation device 10B calculates the impedance and the phase delay based on the detected gap current value and applied voltage value.

[0101] 11 is a diagram illustrating the impedance and phase delay calculated by the electric discharge machining apparatus according to the second embodiment when the machining gap is in an open state. The horizontal axis of the upper graph shown in FIG. 11 represents time, and the vertical axis represents the applied voltage value. The horizontal axis of the lower graph shown in FIG. 11 represents time, and the vertical axis represents the gap current value.

[0102] The calculation device 10B of the electric discharge machining device 1B calculates the impedance IZ based on the detected inter-electrode current value Ip and applied voltage value Vp. The inter-electrode current value Ip is the maximum absolute value (peak value) of the inter-electrode current value Ip and corresponds to the amplitude of the waveform of the inter-electrode current value. The applied voltage value Vp is the maximum absolute value of the applied voltage value Vp and corresponds to the amplitude of the waveform of the applied voltage value. Since the relationship between the inter-electrode current value Ip, applied voltage value Vp, and impedance IZ is expressed by the following equation (2), the calculation device 10B calculates the impedance IZ using equation (2).

[0103] Z=Vp / Ip...(2)

[0104] Furthermore, the calculation device 10B calculates a phase lag (angle) θ based on the period T1 of the applied voltage value Vp and the phase lag time t1. The phase lag time t1 is the phase lag time of the inter-pole current value Ip relative to the applied voltage value Vp. Since the relationship between the period T1 and the phase lag time t1 is expressed by the following equation (3), the calculation device 10B calculates the phase lag θ using equation (3).

[0105] θ=2π×(t / T)...(3)

[0106] Here, the calculation device 10B calculates the phase lag θ by calculating 2π × (t1 / T1). The calculation device 10B executes the process of calculating the impedance IZ and the process of calculating the phase lag θ while changing the AC frequency of the machining power source, thereby obtaining the frequency characteristics of the machining circuit 51 when the machining gap is in an open state.

[0107] 12 is a diagram showing frequency characteristics calculated by the electric discharge machining apparatus according to the second embodiment when the machining gap is in the released state. The horizontal axis of Fig. 12 represents frequency, the vertical axis on the left represents impedance, and the vertical axis on the right represents phase lag. In Fig. 12, the frequency characteristics of the impedance in the released state are represented by impedance IZ1, and the frequency characteristics of the phase lag in the released state are represented by phase lag θ1.

[0108] The inference device 15 of the electric discharge machining apparatus 1B infers the stray capacitance value C1 between the machining poles by comparing the acquired frequency characteristics with the frequency characteristics calculated from the circuit equation of the equivalent circuit 55. That is, the inference device 15 infers the stray capacitance value C1 between the machining poles by comparing the frequency characteristics of the impedance and the frequency characteristics of the phase delay calculated for the released state with the frequency characteristics of the impedance and the frequency characteristics of the phase delay calculated from the circuit equation of the equivalent circuit 55. The circuit equation of the equivalent circuit 55 in the released state is the first circuit equation. Moreover, the frequency characteristics of the machining circuit 51 in the released state are the first frequency characteristics, and the frequency characteristics of the circuit equation of the equivalent circuit 55 in the released state are the second frequency characteristics.

[0109] Furthermore, since the impedance obtained during the process of inferring the stray capacitance value C1 coincides with the machining fluid resistance R1 present between the machining electrodes, the inference device 15 can also calculate the machining fluid resistance R1 as a value corresponding to the state of the machining fluid.

[0110] Next, a method for the electric discharge machining apparatus 1B to infer the parasitic inductance will be described. Fig. 13 is a diagram showing the machining circuit of the machining unit when the machining poles of the electric discharge machining apparatus according to the second embodiment are short-circuited. Fig. 14 is a diagram showing an equivalent circuit corresponding to the machining circuit of Fig. 13. As shown in Fig. 13, in the machining circuit 52 of the machining unit 2B, when the tool electrode 4 and the workpiece 3 are in contact with each other, i.e., when the machining poles are short-circuited, the machining circuit 52 is represented by an equivalent circuit 56 shown in Fig. 14. The machining circuit 52 in the short-circuited state is the second machining circuit.

[0111] In the equivalent circuit 56, a wiring resistance R2 occurs on the equivalent circuit 56, a stray capacitance value C2 occurs as a stray capacitance value αC between the tool electrode 4 and the workpiece 3, and a machining fluid resistance R1 (not shown in FIG. 14 ) which is the resistance of the machining fluid and a parasitic inductance PX2 occur between the tool electrode 4 and the workpiece 3. The wiring resistance R2 on the equivalent circuit 56 includes the resistance of the wiring present on the equivalent circuit 56 and the contact resistance between the wiring and the tool electrode 4. Note that in a short-circuit state between the machining electrodes, the machining fluid resistance R1 may be ignored.

[0112] In this state, the electric discharge machining device 1B applies an AC voltage from the power supply device 20 and detects the inter-machine current value and the applied voltage value. The calculation device 10B calculates the impedance and phase lag based on the detected inter-machine current value and applied voltage value. The calculation device 10B calculates the impedance and phase lag in the short-circuited state between the machining poles by processing similar to that in the open state between the machining poles.

[0113] 15 is a diagram illustrating the impedance and phase delay calculated by the electric discharge machining apparatus according to the second embodiment when the machining gap is short-circuited. The horizontal axis of the upper graph shown in FIG. 15 represents time, and the vertical axis represents the applied voltage value. The horizontal axis of the lower graph shown in FIG. 15 represents time, and the vertical axis represents the gap current value.

[0114] The calculation device 10B of the electric discharge machining device 1B calculates the impedance IZ based on the formula (2), the detected inter-machine current value Ip, and the applied voltage value Vp, in the same way as when the machining inter-machine gap is in the released state.

[0115] Similarly to the case where the machining gap is in the open state, the calculation device 10B calculates the phase lag θ based on the formula (3), the period T2 of the applied voltage value Vp, and the phase lag time t2, which is the phase lag time of the machining gap current value Ip relative to the applied voltage value Vp.

[0116] Here, the calculation device 10B calculates the phase lag θ by calculating 2π × (t2 / T2). The calculation device 10B executes the process of calculating the impedance IZ and the process of calculating the phase lag θ while changing the AC frequency of the machining power source, thereby obtaining the frequency characteristics of the machining circuit 52 when the machining electrodes are short-circuited.

[0117] Fig. 16 is a diagram showing frequency characteristics calculated by the electric discharge machining apparatus according to the second embodiment when the machining gap is short-circuited. The horizontal axis of Fig. 16 represents frequency, the vertical axis on the left represents impedance, and the vertical axis on the right represents phase lag. In Fig. 16, the frequency characteristics of the impedance in the short-circuited state are represented by impedance IZ2, and the frequency characteristics of the phase lag in the short-circuited state are represented by phase lag θ2.

[0118] Similar to the inference process for the stray capacitance value C1, the inference device 15 of the electric discharge machining apparatus 1B infers the parasitic inductance PX2 on the machining circuit by comparing the acquired frequency characteristics with the frequency characteristics calculated from the circuit equation of the equivalent circuit 56. That is, the inference device 15 infers the parasitic inductance PX2 on the machining circuit by comparing the frequency characteristics of the impedance and the frequency characteristics of the phase delay calculated for the short-circuit state with the frequency characteristics of the impedance and the frequency characteristics of the phase delay calculated from the circuit equation of the equivalent circuit 56. The circuit equation of the equivalent circuit 56 in the short-circuit state is the second circuit equation. Furthermore, the frequency characteristics of the machining circuit 52 in the short-circuit state are the third frequency characteristics, and the frequency characteristics of the circuit equation of the equivalent circuit 56 in the short-circuit state are the fourth frequency characteristics.

[0119] Furthermore, since the impedance obtained in the process of inferring the parasitic inductance PX2 coincides with the wiring resistance R2 on the machining circuit, the inference device 15 can also detect the wiring resistance R2 as a value corresponding to the assembly state of the machining circuit. The assembly state of the machining circuit includes the state of the wiring present on the machining circuit, the state of the tool electrode 4, and the contact state between the wiring and the tool electrode 4. In other words, the wiring resistance R2 includes the resistance of the wiring itself, the resistance of the tool electrode 4, and the resistance of the contact portion between the wiring and the tool electrode 4.

[0120] By performing the processing described in Figures 9 to 16, the electric discharge machining device 1B is able to estimate in advance the stray capacitance value C1, parasitic inductance PX2, and impedance present on the machining circuit without actually performing electric discharge machining.

[0121] 17 is a flowchart showing the procedure of processing executed when the electric discharge machining apparatus according to the second embodiment corrects the electrical characteristics. The electric discharge machining apparatus 1B sets the machining gap to a released state (step S110).

[0122] The control unit 11 sets the frequency of the machining power supply in the power supply device 20 (step S120). The power supply device 20 applies an AC voltage of the set frequency to the machining gap (step S130).

[0123] The voltage detector 8 and the current detector 9 detect the voltage value and the current value, respectively (step S140). The calculator 13 calculates the impedance and the phase delay based on the detected values ​​(voltage value and current value) (step S150).

[0124] The control unit 11 determines whether or not the calculation of the impedance and phase delay at all the set frequencies has been completed (step S160). If the calculation of the impedance and phase delay at all the set frequencies has not been completed (step S160, No), the control unit 11 sets a new frequency of the machining power supply in the power supply device 20 (step S170). Then, the electric discharge machining device 1B executes the processing of steps S130 to S160. The electric discharge machining device 1B repeats the processing of steps S130 to S160 until the calculation of the impedance and phase delay at all the set frequencies has been completed.

[0125] When the calculation of the impedance and the phase delay at all the set frequencies is completed (Yes at step S160), the control unit 11 determines whether or not the measurement in the state where the machining electrodes are short-circuited is completed (step S180).

[0126] If the measurement with the machining electrode gap shorted has not been completed (No in step S180), the electric discharge machining device 1B sets the machining electrode gap to a short-circuited state (step S190). Then, the electric discharge machining device 1B executes the processes of steps S120 to S180. The electric discharge machining device 1B repeats the processes of steps S120 to S180 until the measurement with the machining electrode gap shorted is completed.

[0127] When the measurement is completed in the state where the machining poles are short-circuited (step S180, Yes), the inference device 15 infers the stray capacitance value αC and the parasitic inductance (step S200). Specifically, the inference device 15 infers the stray capacitance value αC between the machining poles by comparing the frequency characteristics of the impedance and the frequency characteristics of the phase delay calculated in the open state between the machining poles with the frequency characteristics of the impedance and the frequency characteristics of the phase delay calculated from the circuit equation in the open state.

[0128] Furthermore, the inference device 15 infers the parasitic inductance by comparing the frequency characteristics of the impedance and the frequency characteristics of the phase delay calculated in a short-circuit state between the machining poles with the frequency characteristics of the impedance and the frequency characteristics of the phase delay calculated from the circuit equation in a short-circuit state.

[0129] The inference device 15 may infer the machining fluid resistance R1 based on the impedance calculated when the machining electrodes are in an open state. The inference device 15 may infer the wiring resistance R2 based on the impedance calculated when the machining electrodes are in a short-circuit state.

[0130] After the inference device 15 infers the electrical characteristics, the correction value determination unit 16 corrects at least one of the voltage value of the voltage applied between the machining poles by the power supply device 20 and the current value of the current flowing between the machining poles based on at least one of the impedance, the stray capacitance value C1, the parasitic inductance PX2, the machining fluid resistance R1, and the wiring resistance R2.

[0131] In this way, the electric discharge machining apparatus 1B of the second embodiment infers electrical characteristics such as the stray capacitance value C1 and the parasitic inductance PX2 before machining by comparing the frequency characteristics of the impedance and phase delay in the machining circuits 51, 52 with the frequency characteristics calculated from the circuit equations of the equivalent circuits 55, 56 of the machining circuits 51, 52. This allows the electric discharge machining apparatus 1B to infer the electrical characteristics of the machining circuits 51, 52 before machining without performing pre-machining. Furthermore, the electric discharge machining apparatus 1B can infer the electrical characteristics of the machining circuits 51, 52 without performing prior learning.

[0132] Third Embodiment Next, a third embodiment will be described with reference to Figures 18 and 19. In the third embodiment, the electric discharge machining apparatus 1A, 1B displays on the display 25 a screen prompting the user to correct electrical characteristics such as the stray capacitance value αC, and a screen indicating that the correction has been completed.

[0133] In embodiment 3, the electric discharge machining devices 1A and 1B perform similar processing, so below we will explain the case where the electric discharge machining device 1B displays on the display 25 a screen prompting correction of electrical characteristics and a screen indicating that the correction has been completed.

[0134] The electric discharge machining device 1B infers the stray capacitance value αC and impedance, which are the electrical characteristics of the electric discharge machining device 1B, by the processing described in embodiment 2. Fig. 18 is a diagram showing an example of a screen that the electric discharge machining device according to embodiment 3 displays on the display when there is a deviation in the electrical characteristics.

[0135] When there is a deviation of the electrical characteristics from the reference characteristics, the arithmetic unit 10B of the electric discharge machining apparatus 1B displays a screen on the display 25 that prompts the user to correct the electrical characteristics. Specifically, the electric discharge machining apparatus 1B simultaneously displays both an explanation 251 about the correction and a button 252 for executing the correction in a window WX1 on the screen. The window WX1 is a window that is newly displayed on the screen or a window that is continuously displayed on the screen.

[0136] The explanation 251 about the correction is a sentence indicating the correction content of the electrical characteristics, such as "The stray capacitance value will be corrected by AA" or "The impedance will be corrected by BB."

[0137] Button 252 is a button for correcting deviations of the electrical characteristics from the reference characteristics. When button 252 is clicked, touched, or keyed in, electric discharge machining apparatus 1B corrects the electrical characteristics by correcting the voltage value and current value.

[0138] The electric discharge machining device 1B simultaneously displays on the display 25 an explanation 251 about the correction and a button 252 for executing the correction, so that the user can easily instruct the correction of the electrical characteristics by clicking, touching, or keying in the button 252. This allows the user to reduce the deviation in the machining characteristics of each individual electric discharge machining device 1B without performing complicated operations.

[0139] 19 is a diagram showing an example of a screen displayed on the display after the electric discharge machining apparatus according to the third embodiment corrects the deviation of the electrical characteristics. When the correction of the electrical characteristics is completed, the arithmetic unit 10B of the electric discharge machining apparatus 1B causes the display 25 to display a message 253 indicating that the correction has been completed in a window WX2 on the screen. The window WX2 is a window that is newly displayed on the screen or a window that has been continuously displayed on the screen.

[0140] The message 253 indicating that the correction has been completed includes, for example, a statement that the correction has been completed and a statement indicating the degree of electrical deviation (a statement indicating how much deviation there was in the electrical characteristics). That is, the message 253 includes a statement indicating that the correction of the deviation of the electrical characteristics from the reference characteristics has been completed and a statement indicating how much deviation there was between the electrical characteristics and the reference characteristics. The message 253 indicating that the correction has been completed includes, for example, statements such as "Correction completed," "Deviation of stray capacitance value = AA," and "Deviation of impedance = BB."

[0141] In this way, in embodiment 3, the electric discharge machining device 1B displays a window WX1 on the display 25 that prompts the user to correct the electrical characteristics, so that the user can easily understand the content of the correction of the electrical characteristics and can easily instruct the correction of the electrical characteristics.

[0142] Furthermore, the electric discharge machining apparatus 1B displays a window WX2 on the display 25 indicating that the correction of the electrical characteristics has been completed, so that the user can easily understand that the correction of the electrical characteristics has been completed and can easily understand the details of the correction of the electrical characteristics. In other words, the user can easily understand that the electric discharge machining apparatus 1B has been individually adjusted.

[0143] Next, a description will be given of the hardware configuration of the arithmetic devices 10A and 10B. Note that the arithmetic devices 10A and 10B have similar hardware configurations, so the hardware configuration of the arithmetic device 10A will be described here.

[0144] 20 is a diagram illustrating an example of a hardware configuration for implementing the arithmetic device according to the first embodiment. The arithmetic device 10A can be implemented by an input device 300, a processor 100, a memory 200, and an output device 400. Examples of the processor 100 include a CPU (Central Processing Unit, also referred to as a central processing unit, processing device, microprocessor, microcomputer, or DSP (Digital Signal Processor)) or a system LSI (Large Scale Integration). Examples of the memory 200 include a RAM (Random Access Memory) and a ROM (Read Only Memory).

[0145] The arithmetic device 10A is realized by the processor 100 reading and executing a computer-executable arithmetic program for executing the operations of the arithmetic device 10A stored in the memory 200. The arithmetic program, which is a program for executing the operations of the arithmetic device 10A, can also be said to be a program that causes a computer to execute the procedure or method of the arithmetic device 10A.

[0146] The arithmetic program executed by the processor 100 has a modular configuration including an arithmetic device 10A, and these components are loaded onto the main storage device and generated on the main storage device. Specifically, the arithmetic program executed by the processor 100 has a modular configuration including a control unit 11, a voltage command detection unit 12, an arithmetic unit 13, and a learning device 14, and these components are loaded onto the main storage device and generated on the main storage device.

[0147] The input device 300 receives information set by the user and sends it to the processor 100 or the memory 200. The memory 200 stores calculation programs and the like. The memory 200 is also used as a shared area, which is a temporary memory when the processor 100 executes various processes. The output device 400 outputs the calculation results of the processor 100 to the machining unit 2A, the power supply device 20, the display 25, etc.

[0148] The calculation program may be provided as a computer program product stored in a computer-readable storage medium as an installable or executable file. The calculation program may also be provided to the calculation device 10A via a network such as the Internet. Some of the functions of the calculation device 10A may be implemented by dedicated hardware such as a dedicated circuit, and some may be implemented by software or firmware. For example, the learning device 14 of the calculation device 10A may be implemented by the hardware configuration described in FIG. 20.

[0149] The configurations shown in the above embodiments are merely examples, and may be combined with other known technologies, or different embodiments may be combined with each other. It is also possible to omit or modify parts of the configurations as long as they do not deviate from the gist of the invention.

[0150] 1A, 1B Electric discharge machining device, 2A, 2B Machining unit, 3 Workpiece, 4 Tool electrode, 8 Voltage detection unit, 9 Current detection unit, 10A, 10B Calculation unit, 11 Control unit, 12 Voltage command detection unit, 13 Calculation unit, 14 Learning device, 15 Inference device, 16 Correction value determination unit, 20 Power supply unit, 25 Display, 40 Waveform, 41 Slope, 51, 52 Machining circuit, 55, 56 Equivalent circuit, 100 Processor, 141 State observation unit, 142 Data acquisition unit, 143 Learning unit, 144 Inference unit, 200 Memory, 251 Explanation, 252 Button, 253 Message, 300 Input device, 400 Output device, C1, C2, αC Stray capacitance value, Ip Inter-electrode current value, IZ, IZ1, IZ2 Impedance, PX1, PX2 Parasitic inductance, Q: electrical quantity, R1: machining fluid resistance, R2: wiring resistance, T1, T2: period, V, Vp: applied voltage value, w11 to w16, w21 to w26, W1, W2: weight, WX1, WX2: window.

Claims

1. A discharge machining apparatus comprising: a power supply device that supplies power to a machining gap between a tool electrode and a workpiece; a current detection unit that detects a value of an inter-electrode current, which is a current value of a current flowing from the power supply device to the machining gap; a voltage command detection unit that detects a value of an applied voltage, which is a command value of a voltage applied to the machining gap; and an arithmetic unit that acquires the inter-electrode current value and the applied voltage value, infers an electrical characteristic specific to the apparatus itself from the inter-electrode current value and the applied voltage value using a learning model for inferring the electrical characteristic, and determines a correction value for correcting the inter-electrode current value and the applied voltage value so that the inferred electrical characteristic becomes a reference electrical characteristic which is a reference characteristic.

2. The electrical characteristic includes an impedance in a machining circuit including the power supply device and the machining gap, and a value of a stray capacitance between the machining gaps. The learning model includes an impedance learning model for inferring the impedance and a stray capacitance learning model for inferring the value of the stray capacitance. The arithmetic unit infers the impedance from the inter-electrode current value using the impedance learning model, calculates an amount of electricity that has flowed through the machining gap from the inter-electrode current value, infers the value of the stray capacitance from the amount of electricity and the applied voltage value using the stray capacitance learning model, and determines the correction value so that the inferred impedance and the value of the stray capacitance become a reference impedance and a reference value of the stray capacitance. The discharge machining apparatus according to claim 1, characterized in that.

3. The arithmetic unit according to claim 1 or 2, characterized in that it acquires learning data including the inter-electrode current value, the applied voltage value, and the electrical characteristic, and generates the learning model using the learning data. The discharge machining apparatus described.

4. A power supply device that supplies power to the machining gap between the tool electrode and the workpiece, a current detection unit that detects the inter-electrode current value, which is the current value of the current flowing from the power supply device to the machining gap, a voltage detection unit that detects the applied voltage value, which is the voltage value of the voltage applied to the machining gap, the inter-electrode current value and the applied voltage value when the machining gap is in an open state, the first circuit equation in the first machining circuit including the power supply device and the machining gap in the open state, the inter-electrode current value and the applied voltage value when the machining gap is in a short-circuit state, and the second circuit equation in the second machining circuit including the power supply device and the machining gap in the short-circuit state. Based on these, an arithmetic unit that infers the electrical characteristics unique to the device itself and determines a correction value for correcting the inter-electrode current value and the applied voltage value so that the inferred electrical characteristics become the reference characteristics, which are the reference electrical characteristics. A discharge machining device characterized by comprising the above.

5. The electrical characteristics unique to the device itself are the stray capacitance value between the machining gaps and the parasitic inductance on the machining circuit. The arithmetic unit calculates the first frequency characteristic, which is the frequency characteristic of the first machining circuit, and infers the stray capacitance value between the machining gaps by comparing the second frequency characteristic, which is the frequency characteristic of the first circuit equation, with the first frequency characteristic. The arithmetic unit calculates the third frequency characteristic, which is the frequency characteristic of the second machining circuit, and infers the parasitic inductance on the machining circuit by comparing the fourth frequency characteristic, which is the frequency characteristic of the second circuit equation, with the third frequency characteristic. The discharge machining device according to claim 4, characterized in that the correction value is determined so that the stray capacitance value and the parasitic inductance become the reference characteristics.

6. The first frequency characteristic is the frequency characteristic of the impedance in the first processing circuit and the frequency characteristic of the phase delay between the inter-electrode current value and the applied voltage value in the first processing circuit; the second frequency characteristic is the frequency characteristic of the impedance in the first circuit equation and the frequency characteristic of the phase delay in the first circuit equation; the third frequency characteristic is the frequency characteristic of the impedance in the second processing circuit and the frequency characteristic of the phase delay in the second processing circuit; the fourth frequency characteristic is the frequency characteristic of the impedance in the second circuit equation and the frequency characteristic of the phase delay in the second circuit equation. The electric discharge machining apparatus according to claim 5, characterized in that.

7. The arithmetic unit calculates the first frequency characteristic from the inter-electrode current value and the applied voltage value in the open state, and calculates the third frequency characteristic from the inter-electrode current value and the applied voltage value in the short-circuit state. The electric discharge machining apparatus according to claim 6, characterized in that.

8. The arithmetic unit causes a display connected to the arithmetic unit to display a button for correcting the deviation of the electrical characteristics from the reference characteristic and a text indicating the correction content of the electrical characteristics. The electric discharge machining apparatus according to any one of claims 1 to 7, characterized in that.

9. The arithmetic unit causes the display to display a text indicating that the correction of the deviation of the electrical characteristics from the reference characteristic has been completed and a text indicating how much deviation there is between the electrical characteristics and the reference characteristic. The electric discharge machining apparatus according to claim 8, characterized in that.

10. A power supply device included in an electric discharge machining apparatus includes a power supply step of supplying power to an inter-electrode gap between a tool electrode and a workpiece, a current detection step of detecting an inter-electrode current value that is a current value of a current flowing from the power supply device to the inter-electrode gap, a voltage command detection step of detecting an applied voltage value that is a command value of a voltage value of a voltage applied to the inter-electrode gap, and an arithmetic step of acquiring the inter-electrode current value and the applied voltage value, inferring the electrical characteristics from the inter-electrode current value and the applied voltage value using a learning model for inferring electrical characteristics specific to the apparatus itself, and determining a correction value for correcting the inter-electrode current value and the applied voltage value so that the inferred electrical characteristics become reference electrical characteristics that are reference characteristics. A method for electric discharge machining, characterized by including the above.

11. A power supply device included in an electric discharge machining apparatus includes a power supply step of supplying power to an inter-electrode gap between a tool electrode and a workpiece, a current detection step of detecting an inter-electrode current value that is a current value of a current flowing from the power supply device to the inter-electrode gap, a voltage detection step of detecting an applied voltage value that is a voltage value of a voltage applied to the inter-electrode gap, and an arithmetic step of inferring electrical characteristics specific to the apparatus itself based on the inter-electrode current value and the applied voltage value when the inter-electrode gap is in an open state, the first circuit equation in a first machining circuit including the power supply device and the inter-electrode gap in the open state, the inter-electrode current value and the applied voltage value when the inter-electrode gap is in a short-circuit state, and the second circuit equation in a second machining circuit including the power supply device and the inter-electrode gap in the short-circuit state, and determining a correction value for correcting the inter-electrode current value and the applied voltage value so that the inferred electrical characteristics become reference electrical characteristics that are reference characteristics. A method for electric discharge machining, characterized by including the above.

Images