Drive setting determination device and drive setting determination method

Abstract

A numerical control device (1a) is a drive setting determination device for determining a drive setting of a machine tool that performs vibratory cutting, which enables chip breakage, by vibrating a shaft that changes the relative position between a workpiece and a tool during cutting. The numerical control device (1a) comprises: a search setting input unit (100) which receives a search setting, which includes a search range and a machine machining reference setting (11), wherein the search range is set for a drive setting, which includes a machine machining setting for the machine tool (3) and / or a vibration setting for the shaft and / or a control parameter, which is a parameter for determining a control property of the shaft.wherein the machine machining reference setting (11) is the machine machining setting serving as a reference, which is determined independently of whether vibratory cutting is performed; and a setting search unit (102) which, based on the search setting, determines an actual drive setting in the set search range such that a chip breaking condition is satisfied, wherein the actual drive setting is the drive setting used when performing vibratory cutting, and wherein the chip breaking condition is a condition under which chip breaking occurs.

Description

[0001] The present invention relates to a drive setting determining apparatus and a drive setting determining method for determining a drive setting of a machine tool that performs vibration cutting. background

[0002] A cutting machine tool utilizes relative motion between a workpiece and a tool, while generating engagement between the workpiece and the tool, removing material from a surface of the workpiece to machine the workpiece into a desired shape. In the process, the removed material is discharged as a chip. If a long, continuous chip is generated, this chip may wrap around the workpiece, tool, or the like, resulting in poor machining accuracy and a scratched surface of the workpiece. This causes machining failure.

[0003] To prevent the generation of a long continuous chip, Patent Literature 1 discloses a control device for a machine tool that performs vibration cutting for breaking a chip into small pieces by vibrating a shank for driving a tool at a low frequency so that the moment of engagement of the tool and a workpiece is not generated. The control device disclosed in Patent Literature 1 determines whether chip breakage occurs in a case of vibrating a specific shank of a plurality of feed shanks based on tool data, a relative positional relationship between the workpiece and the tool, and movement data for moving the workpiece and the tool relative to each other, and automatically selects a shank to be vibrated. Citation listPatent literature

[0004] Patent Literature 1: Japanese Patent No. 7007531 Short descriptionTechnical problem

[0005] However, the conventional technique described above has a problem that there is a high probability that chip breakage will not occur regardless of which shank is selected because settings different from the shank to be vibrated are preset.

[0006] The present disclosure has been made in view of the circumstances, and an object of the present disclosure is to provide a drive setting determining apparatus which can increase a probability that chip breakage occurs when performing vibration cutting by a machine tool. Solution to the problem

[0007] To solve the above-described problems and achieve the objective, a drive setting determining device according to the present disclosure is a drive setting determining device that determines a drive setting of a machine tool that performs vibration cutting, which allows chip breaking to occur, by vibrating a shaft to change a relative position between a workpiece and a tool during cutting. The drive setting determining device includes: a search setting input unit which obtains a search setting including a search range and a machining reference setting, wherein the search range is set for a drive setting which includes a machining setting for the machine tool and / or a vibration setting for the shaft and / or a control parameter which is a parameter for determining a control characteristic of the shaft, wherein the machining reference setting is the machining setting serving as a reference, which is determined regardless of whether the vibration cutting is performed; and a setting search unit, which, based on the search setting, determines an actual drive setting in the set search range such that a chip breaking condition is satisfied, wherein the actual drive setting is the drive setting used when performing vibration cutting, wherein the chip breaking condition is a condition under which chip breaking occurs. Advantageous effects of the invention

[0008] The drive setting determining device according to the present invention has an effect that it can provide the drive setting determining device which can increase the probability of chip breakage occurring when performing vibration cutting by the machine tool. Short description of the drawing Fig. 1 is a diagram showing a functional configuration of a numerical control apparatus according to a first embodiment. Fig. 2 is an explanatory diagram showing vibration cutting using a Fig. 1 shows the machine tool shown. Fig. 3 is an explanatory diagram showing a process in which chip breakage occurs in the vibration cutting performed by the machine tool. Fig. 4 is a flow chart for describing the operation of a Fig. 1 shown setting search unit. Fig. 5 is a diagram showing a functional configuration of an information processing apparatus according to a second embodiment. Fig. 6 is a diagram showing an example of a Fig. 5 shows the machine model shown. Fig. 7 is a flowchart for describing a first example of operations of a Fig. 5 shown setting search unit. Fig. 8 is a flowchart for describing a second example of operations of the Fig. 5 shown setting search unit. Fig. 9 is a diagram showing an experimentally derived relationship of a response amplitude with respect to a command value of a vibration amplitude. Fig. 10 is a diagram showing a functional configuration of an information processing apparatus according to a third embodiment. Fig. 11 is a diagram showing an example of a Fig. 10 shows the machine model shown. Fig. 12 is a flow chart for describing the operation of a Fig. 10 shown setting search unit. Fig. 13 is a diagram showing a functional configuration of an information processing apparatus according to a modification example of the third embodiment. Fig. 14 is a diagram showing a functional configuration of a numerical control apparatus according to a fourth embodiment. Fig. 15 is a flow chart for describing the operation of a Fig. 14 shown setting search unit. Fig. 16 is a diagram showing a functional configuration of an information processing apparatus according to a fifth embodiment. Fig. 17 is a flow chart for describing the operation of a Fig. 16 shown setting search unit. Fig. 18 is a diagram showing a functional configuration of a numerical control apparatus according to a sixth embodiment. Fig. 19 is a diagram showing a functional configuration of an information processing apparatus according to a seventh embodiment. Fig. 20 is a flowchart concerning a learning processing of a Fig. 19 shown setting search unit. Fig. 21 is a diagram showing a functional configuration of a numerical control apparatus according to an eighth embodiment. Fig. 22 is a flowchart for describing inference processing by the Fig. Numerical control device shown in Figure 21. Fig. 23 is a diagram showing dedicated hardware for implementing the functions of each of the numerical control devices according to the first, fourth, sixth, and eighth embodiments. Fig. 24 is a diagram showing a configuration of a control circuit for implementing the functions of each of the numerical control devices according to the first, fourth, sixth, and eighth embodiments. Fig. 25 is a diagram showing an exemplary configuration of a computer system implementing each of the information processing apparatuses according to the second, third, fifth, and seventh embodiments. Description of embodiments

[0009] Hereinafter, with reference to the drawings, a detailed description will be provided of a drive timing determination apparatus and a drive timing determination method according to embodiments of the present disclosure. First embodiment.

[0010] Fig. 1 is a diagram showing a functional configuration of a numerical control device 1a according to a first embodiment. The numerical control device 1a has a function of controlling a machine tool 3 by outputting a drive shaft command 17 and a spindle command 18 to a drive unit 2, which are command values ​​for controlling the machine tool 3 according to a machining program 10.

[0011] Based on the drive shaft command 17 and the spindle command 18 output from the numerical control device 1a, the drive unit 2 supplies a spindle current 20 and a servo motor current 22 to the machine tool 3, which are used to control the machine tool 3. The drive unit 2 can generate the spindle current 20 based on a spindle position 21 returned from the machine tool 3 and can generate the servo motor current 22 based on a drive shaft position 23 returned from the machine tool 3.

[0012] The machine tool 3 includes a spindle 300 and a drive shaft 301, which are shafts that change a relative position between a workpiece 303 and a tool 304. The machine tool 3 performs cutting on the workpiece 303 in response to the spindle 300 and the drive shaft 301 being driven according to the spindle current 20 and the servo motor current 22 supplied from the drive unit 2. At this time, the machine tool 3 vibrates at least one of the shafts, which changes the relative position between the workpiece 303 and the tool 304, thereby enabling vibration cutting to occur, which allows chip breaking to occur.

[0013] The numerical control device 1a is an example of a drive setting determination device for determining a drive setting of the machine tool 3. The drive setting is a setting that defines a driving state of the machine tool 3. A machining setting, a vibration setting, and a control parameter are each a type of drive setting. The machining setting is a setting for machining the workpiece into a desired shape. The vibration setting is a setting for defining a vibration frequency and a vibration amplitude. The control parameter is a parameter for determining a control characteristic of a shaft.

[0014] The numerical control device 1a includes a search setting input unit 100, a machining program input unit 101, a setting search unit 102, and a command value generation unit 104. The search setting input unit 100 acquires a setting for searching the drive setting.

[0015] The search setting input unit 100 acquires a search setting including a search range and a machining reference setting 11. The search range is set for the drive setting, which includes the machining setting, the vibration setting, and / or the control parameter. The machining reference setting 11 is a machining setting serving as a reference and is set regardless of whether vibration cutting is performed. Specifically, in the first embodiment, the search setting input unit 100 acquires the machining reference setting 11, a vibration reference setting 12, and a vibration setting search range 14. The vibration reference setting 12 is a vibration setting serving as a reference. The vibration setting search range 14 is a search range set for the vibration setting.The search setting input unit 100 outputs the acquired search setting to the setting search unit 102. The search setting input unit 100 includes input means such as a keyboard, a button, and a mouse, receives an operator input to be input to the numerical control device 1a, and acquires input information.

[0016] The setting search unit 102 searches for the drive setting based on the search setting output by the search setting input unit 100 and determines an actual drive setting, which is the drive setting to be actually used. In the first embodiment, the actual drive setting includes an actual machining setting 15, which is a machining setting to be actually used, and an actual vibration setting 16, which is a vibration setting to be actually used. A detailed method by which the setting search unit 102 searches for the drive setting will be described later. The setting search unit 102 outputs the determined actual machining setting 15 and actual vibration setting 16.

[0017] The machining program input unit 101 receives the machining program 10 for controlling the machine tool 3 as input to thereby acquire the machining program 10, and outputs the acquired machining program 10 to the command value generation unit 104.

[0018] The command value generation unit 104 generates the drive shaft command 17 and the spindle command 18 based on the machining program 10 output by the machining program input unit 101 and the actual machining setting 15 and the actual vibration setting 16 determined by the setting search unit 102, and outputs the generated drive shaft command 17 and spindle command 18 to the drive unit 2. The drive shaft command 17 is a command for the drive shaft 301 of the machine tool 3. The spindle command 18 is a command for the spindle 300.

[0019] The drive unit 2 includes a spindle servo control unit 201 and a drive shaft servo control unit 202.

[0020] The spindle servo control unit 201 performs position control so that the spindle position 21 of a spindle motor 302 of the machine tool 3 conforms to the spindle command 18, and outputs the spindle current 20. However, when the spindle command 18 is a speed command, the spindle servo control unit 201 performs speed control so that a spindle speed conforms to the spindle command 18.

[0021] The drive shaft servo control unit 202 performs position control so that the drive shaft position 23 of a servo motor 305 of the machine tool 3 conforms to the drive shaft command 17, and outputs the servo motor current 22. Although only one drive shaft 301 is shown in the drawing for simplicity of illustration, in a case where the machine tool 3 includes two or more drive shafts 301, the drive unit 2 may include a plurality of drive shaft servo control units 202, each of which is assigned to one of the plurality of drive shafts 301.

[0022] The machine tool 3 is a lathe and includes the spindle 300, the drive shaft 301, the spindle motor 302 connected to the spindle, and the servo motor 305 connected to the drive shaft 301.

[0023] The tool 304 is attached to the drive shaft 301, and the workpiece 303 is installed on the spindle 300. The spindle motor 302 is supplied with the spindle current 20, which is generated by the spindle servo control unit 201 of the drive unit 2 based on the spindle command 18. The servo motor 305 is supplied with the servo motor current 22, which is generated by the drive shaft servo control unit 202 of the drive unit 2 based on the drive shaft command 17. The spindle motor 302 drives the spindle 300 according to the spindle current 20. The servo motor 305 drives the drive shaft 301 according to the servo motor current 22.

[0024] The Fig. However, the configurations of the spindle 300 and the drive shaft 301 in the machine tool 3 shown in FIG. 1 are examples of the lathe. In the case of turning using a simultaneous five-axis rotary machine tool, both a rotary table on which the workpiece 303 is placed and the drive shaft that drives the tool 304 are driven by the drive shaft servo control unit 202. Furthermore, the machine tool 3 is not limited to a machine that performs turning. The machine tool 3 may be a machine that performs milling cutting. Although the workpiece 303 mounted on the spindle 300 is rotated in the above configuration, the tool 304 may also be rotated to perform vibration cutting. For example, drilling, milling, and the like are methods for cutting the workpiece 303 using the tool 304 in a rotating state.

[0025] Fig. 2 is an explanatory diagram showing vibration cutting using the Fig. 1 shows the machine tool 3. The spindle 300 (in Fig. 2, the workpiece 303 rotates at a constant speed according to the spindle command 18. In response to the servo motor 305 being controlled in a Z-axis direction based on the drive shaft command 17, the drive shaft 301 in the Z-axis direction moves the tool 304 in the Z-axis direction along a tool path defined by the machining program 10 while creating engagement of the tool 304 and the workpiece 303. Here, the drive shaft command 17 includes a feed rate command defined in the actual machining setting 15 and a vibration command of an amplitude and frequency based on the actual vibration setting 16. In response to the drive shaft command 17, the drive shaft 301 causes the tool 304 to vibrate while the tool 304 is moved along the tool path.Therefore, relative vibration is generated between the tool 304 and the workpiece 303 to break the chip. Although the tool 304 is vibrated using the drive shaft 301 here, as long as relative vibration can be generated between the tool 304 and the workpiece 303, the workpiece 303 can be vibrated using the spindle 300, or the tool 304 and the workpiece 303 can both be vibrated using both the drive shaft 301 and the spindle 300.

[0026] In addition, relative vibration may be generated using the vibration transmitted from the tool 304 to the workpiece 303 by a reaction force of a motor that drives the tool 304. Furthermore, relative vibration may be generated using a drive shaft 301 (not shown) driven in an X-axis direction orthogonal to a Z-axis, or oblique vibration may be generated while simultaneously driving the drive shaft 301 (not shown) in the X-axis direction and the drive shaft 301 in the Z-axis direction.

[0027] Fig. Figure 3 is an explanatory diagram showing a process in which chip breakage occurs in vibration cutting performed by the machine tool 3. The horizontal axis in Fig. 3 indicates a spindle rotation angle of 300. The rotation angle goes through 360 degrees and returns to 0 degrees. The vertical axis in Fig. 3 indicates a relative distance between the tool 304 and the workpiece 303 in the direction along the tool path. During the application of no vibration, the tool 304 moves at a feed rate per revolution F for each revolution of the spindle 300, which is specified by the tool path. During the application of vibration, the tool 304 is caused to vibrate while feeding in the Z-axis direction, and therefore, the relative distance between the workpiece 303 and the tool 304 during one revolution of the spindle 300 corresponds to a trajectory of a sine wave. Such a trajectory is referred to as a vibration trajectory.

[0028] The example of Fig. 3 shows a vibration trajectory in a case where the drive shaft 301 is vibrated 1.5 times in the Z-axis direction during one revolution of the spindle 300. The vibration trajectory is based on a spindle speed S (r / min), a feed per revolution F (mm / r), a vibration amplitude A (mm) of the tool 304, and an angular frequency ω. v (rad / s) of the vibration of the tool 304. The feed per revolution F (mm / r) is a feed rate of the tool 304 relative to the workpiece 303 per revolution of the spindle 300.

[0029] Fig. 3 shows an nth vibration trajectory 110 and an (n+1)th vibration trajectory 111. The nth vibration trajectory 110 is a vibration trajectory during the nth spindle revolution. The (n+1)th vibration trajectory 111 is a vibration trajectory during the (n+1)th spindle revolution. The nth vibration trajectory 110 is a vibration trajectory between a time t(n) and a time t(n+1). The time t(n) is a time at which the spindle traverses 300 degrees. The time t(n+1) is a time at which the spindle has completed one revolution. The (n+1)th vibration trajectory 111 is a vibration trajectory between a time t(n+1) and a time t(n+2). Time t(n+2) is the time at which the spindle has completed one revolution after time t(n+1). In this case, it should be noted that time t(n) can be any reference time. For example, the reference time can be the time at which machining starts.A distance between the nth vibration trajectory 110 and the (n+1)th vibration trajectory 111 at the same spindle angle corresponds to a thickness of the chip, ie, a chip thickness. Chip breakage areas 112, which are hatched areas in . Fig. 3 are regions where the n-th vibration trajectory 110 and the (n+1)-th vibration trajectory 111 overlap each other. In these regions, the material has already been removed from the surface of the workpiece 303 in the n-th vibration trajectory 110, and therefore, air cutting occurs in the (n+1)-th vibration trajectory 111 without removing the material. In a region between the air cutting regions, the chip is not continuously formed, and therefore the chip is broken. Therefore, in order to enable chip breaking to occur, the drive setting for vibration cutting is desirably set to create the air cutting regions.

[0030] Now, a description is provided of a setting with which chip breaking occurs. When the spindle speed S (r / min) and the feed per revolution F (mm / r) are given as a machining setting, which is determined in turning regardless of whether vibration cutting is performed, and the vibration amplitude A (mm) of the relative vibration between the tool 304 and the workpiece 303 and the angular frequency ω v (rad / s) of vibration are given as a vibration setting, an angular frequency ω s (rad / s) of spindle rotation is calculated by formula (1) below. Formula 1: ωs=2πS60

[0031] If an angle of the spindle 300 is denoted as θ (rad), a trajectory T (θ) n the n-th vibration trajectory 110 through which a cutting edge of the tool 304 passes is calculated by formula (2) below, where “0<θ<2π”. Formula 2: T(θ)n=A sin(ωVωS(θ+2πn)+F(θ+2πn))

[0032] When the n-th vibration trajectory 110 and the (n+1)-th vibration trajectory 111 come into contact with each other, that is, when formula (3) below is satisfied, the chip is broken. Formula 3: T(θ)n=T(θ)n+1

[0033] Therefore, a relationship represented by formula (4) below is derived from formula (2) and formula (3), where φ is a phase difference between the n-th vibration trajectory 110 and the (n+1)-th vibration trajectory 111. Formula 4: A{(1−cos 2πωVωS)2+(sin 2πωVωS)2sin(ωVωSθ+ϕ)}=2πF

[0034] Under the condition that formula (5) below is satisfied, there exists a θ which satisfies formula (3) and formula (4). Formula 5: 0<(sin(ωVωSθ+ϕ))≤1

[0035] In particular, when a formula (6) below is satisfied, the n-th vibration trajectory 110 and the (n+1)-th vibration trajectory 111 come into contact with each other at a point. Formula 6: sin(ωVωSθ+ϕ)=1

[0036] Because the setting that the two vibration trajectories come into contact with each other at a point when formula (6) is satisfied is calculated, it is understood that chip breakage occurs when a value of the vibration amplitude A is larger than a value of the vibration amplitude A satisfying formula (4).

[0037] As described above, the conditions under which chip breaking occurs can be expressed by formulas based on the machining setting and the vibration setting. If the conditions expressed by formulas (4) and (5) can be met, the machining setting and the vibration setting can be freely selected. On the other hand, if the drive setting that does not satisfy formulas (4) and (5) is set, chip breaking does not occur, and therefore vibration cutting is unsatisfactory.

[0038] A description will now be given of a machining setting search using the numerical control device 1a. First, the operator uses the search setting input unit 100 to input a spindle speed and a feed rate per tooth as the machining reference setting 11. However, the machining reference setting 11 may be information expressed in any format as long as the angular frequency of the spindle rotation and the feed rate per revolution can be uniquely determined. For example, the machining reference setting 11 may include information in which a feed rate along the Z-axis is expressed as a feed per minute (mm / min).In this case, the search setting input unit 100 calculates the feed rate per tooth based on the input feed per minute and transmits a calculation result to the setting search unit 102. In addition, the machining reference setting 11 may directly include the angular frequency of spindle rotation instead of the spindle speed.

[0039] Next, the operator uses the search setting input unit 100 to input the vibration frequency and vibration amplitude, which serve as the vibration reference setting 12, as the search setting. Furthermore, the operator uses the search setting input unit 100 to input the vibration setting search range 14, which is the search range for the vibration setting, as the search setting. The vibration setting search range 14 includes a search range for the vibration frequency and a search range for the vibration amplitude. Note that, for the vibration reference setting 12 and the vibration setting search range 14, the vibration reference setting 12 and the vibration setting search range 14 may also be information expressed in any format, as long as the vibration frequency and vibration amplitude can be uniquely determined.For example, the vibration reference setting 12 and the vibration setting search range 14 may include a value of the vibration frequency as the number of vibrations per spindle revolution, or may include a value of the vibration amplitude as a ratio relative to the feed rate per tooth. In a case where a value other than the vibration frequency and vibration amplitude is set, the search setting input unit 100 converts the input value into the vibration frequency and vibration amplitude and outputs the vibration frequency and vibration amplitude to the setting search unit 102.

[0040] The setting search unit 102 determines an actual drive setting based on the search setting output by the search setting input unit 100. The actual drive setting is a setting used when actually performing machining. In the first embodiment, the actual drive setting determined by the setting search unit 102 includes the actual machining setting 15 and the actual vibration setting 16. The actual machining setting 15 is the machining setting used when actually performing machining. The actual vibration setting 16 is the vibration setting used when actually performing machining.

[0041] Fig. 4 is a flow chart for describing operations of the Fig. 1. The setting search unit 102 first sets the machining reference setting 11 and the vibration reference setting 12 included in the search setting output from the search setting input unit 100 (step S1). The setting search unit 102 determines whether the set machining setting and vibration setting satisfy a chip breaking condition (step S2).

[0042] If the chip breaking condition is not met (step S2: no), the setting search unit 102 determines whether the vibration amplitude can be adjusted (step S3). If the vibration amplitude can be adjusted (step S3: yes), the setting search unit 102 changes the vibration amplitude within a vibration amplitude search range (step S4). After step S4, the setting search unit 102 returns to the processing of step S2. In this case, the setting search unit 102 repeats the processing of steps S2 to S4 of changing the vibration amplitude and determining whether the chip breaking condition is met until the chip breaking condition is met and as long as the vibration amplitude can be adjusted.For example, the adjustment search unit 102 may search from a lower limit to an upper limit of the vibration amplitude search range such that, starting from the lower limit of the vibration amplitude search range, a value of the changed vibration amplitude is set to a value incremented by a constant value each time the processing is repeated. In this case, the adjustment search unit 102 may determine in step S3 that the vibration amplitude can be adjusted when the value of the changed vibration amplitude has not reached the upper limit, and may determine that the vibration amplitude cannot be adjusted when the value of the changed vibration amplitude has reached the upper limit.

[0043] If the vibration amplitude cannot be adjusted (step S3: no), the adjustment search unit 102 changes the vibration frequency within a vibration frequency search range (step S5). At this time, the adjustment search unit 102 sets the vibration amplitude value to the lower limit of the vibration amplitude search range and returns to the processing of step S2.

[0044] If the chip breaking condition is satisfied (step S2: yes), the setting search unit 102 outputs the set machining setting and vibration setting as the actual drive setting (step S6).

[0045] Through the above steps, when the machining reference setting 11 and the vibration reference setting 12 satisfy the chip breaking condition, the setting search unit 102 outputs the machining reference setting 11 and the vibration reference setting 12 as they are as the actual drive setting, and when the machining reference setting 11 and the vibration reference setting 12 do not satisfy the chip breaking condition, the setting search unit 102 first searches for the vibration setting that satisfies the chip breaking condition while changing the vibration amplitude from the lower limit to the upper limit of the vibration amplitude search range by a constant value.If the vibration setting that satisfies the chip breaking condition is not found even when the vibration amplitude reaches the upper limit, the setting search unit 102 then changes the vibration frequency to the lower limit, changes the vibration amplitude to the lower limit, and searches for the vibration setting that satisfies the chip breaking condition while changing the vibration amplitude again from the lower limit to the upper limit by a constant value. By repeating the processing of determining the chip breaking condition while changing the vibration frequency from the lower limit to the upper limit by a constant value, the setting search unit 102 can search for a combination of vibration amplitude and vibration frequency that satisfies the chip breaking condition within the search range.

[0046] As described above, according to the first embodiment, the numerical control device 1a is the drive setting determining device for determining the drive setting of the machine tool 3 that performs vibration cutting, which enables chip breaking to occur, by vibrating the shaft that changes the relative position between the workpiece 303 and the tool 304 during cutting. The drive setting determining device includes: the search setting input unit 100 that obtains the search setting including the search range and the machining reference setting 11, wherein the search range is set for the drive setting that defines the machining setting for the machine tool 3 and / or the vibration setting that defines the vibration frequency and vibration amplitude of at least one of the drive shaft 301 and / or the spindle 300 to be vibrated.and / or the control parameter, which is the parameter for determining the control characteristic of the shaft, wherein the machining reference setting 11 is the machining setting serving as the reference, which is determined regardless of whether the vibration cutting is performed; and the setting search unit 102, which, based on the search setting, determines the actual drive setting within the set search range so that the chip breaking condition is satisfied, wherein the actual drive setting is the drive setting used when performing the vibration cutting, wherein the chip breaking condition is the condition under which the chip breaking occurs. Therefore, even if the operator cannot appropriately determine the drive setting of the machine tool 3 when performing the vibration cutting, it is possible,Search for the drive setting within the specified search range and automatically determine the drive setting at which chip breakage occurs. This can increase the probability of chip breakage occurring when performing vibration cutting using the machine tool. Second embodiment.

[0047] Fig. 5 is a diagram showing a functional configuration of an information processing device 1b according to a second embodiment. The information processing device 1b is an example of the drive setting determination device for determining the drive setting of the machine tool 3. Hereinafter, structural components similar to those of the first embodiment are denoted by the same reference numerals, and detailed descriptions thereof will be omitted. Structural components different from those of the first embodiment will be mainly described.

[0048] The information processing device 1b is a device mounted within a computer and determines a drive setting used when performing vibration cutting using the machine tool 3, that is, a machining setting and a vibration setting. The information processing device 1b receives the machining reference setting 11, the vibration reference setting 12, and the vibration setting search area 14 as inputs and outputs the actual machining setting 15 and the actual vibration setting 16 to a machining program generation device 103.

[0049] The machining program generation device 103 is, for example, computer-aided manufacturing (CAM) software that generates the machining program 10 for the machine tool 3 based on machining path generation information. The machining program 10 is referred to as an EIA program or G-code. Alternatively, the machining program generation device 103 may be software that further processes information included in a machining program and outputs the processed machining program 10. The machining program is output, for example, by the CAM software and is a program that describes a machining path along which machining is to be performed under the machining reference setting 11.The information corresponds to commands regarding spindle speed, feed per tooth, vibration frequency and vibration amplitude.

[0050] The information processing device 1b includes the search setting input unit 100 and a setting search unit 102b. The setting search unit 102b determines an actual drive setting using a machine model 105 that simulates the characteristics of the machine tool 3. In the first embodiment, it was assumed that the drive shaft 301 vibrates at the same vibration amplitude as the vibration amplitude commanded to the drive shaft servo control unit 202. However, in the actual machine tool 3, in some cases, the amplitude of the relative vibration between the tool 304 and the workpiece 303 is different from the commanded vibration amplitude due to the influence of mechanical properties of a machine structure supporting the drive shaft 301, the drive shaft 301 (not shown), the spindle 300, and the like.In such a case, even if the commanded vibration amplitude and vibration frequency satisfy the chip breaking condition, chip breaking may not occur in some cases because the vibration amplitude generated during actual machining differs from the command value. Therefore, the setting search unit 102b of the information processing device 1b searches for the vibration setting by taking into account the difference between the command value of the vibration amplitude and the actual value of the vibration amplitude using the machine model 105 that simulates the mechanical characteristics of the machine tool 3.Specifically, the setting search unit 102b uses the machine model 105 to estimate the actual vibration amplitude at a position of a tip of the tool 304 for the commanded vibration amplitude, and searches for a vibration setting such that the value of the estimated vibration amplitude satisfies the chip breaking condition.

[0051] Fig. 6 is a diagram showing an example of the Fig. 5 shows the machine model 105. Fig. 6 shows the machine model 105 in which mechanical properties of the drive shaft servo control unit 202 and the drive shaft 301 are simulated in a frequency domain. The drive shaft servo control unit 202 has a cascade control structure, which includes a controller that controls a position x of the tip of the tool 304 for a drive shaft command 17r, and a speed control loop provided within a position control loop. Here, the position controller includes a proportional controller (P), which is a position controller that generates a speed command vr by multiplying the difference of the tool tip position x with respect to the drive shaft command 17r by a position loop gain K. pThe speed control includes a proportional-integral (PI) control, which is a speed control that calculates a speed by multiplying the difference between the speed command vr and a tool tip speed v by a speed loop gain K vp result obtained and a result obtained by multiplying the difference by a velocity integral gain K vi and integrating the product, the result obtained is added to calculate the torque Tr output from the servo motor 305. Further, the machine model 105 calculates the tool tip position x by multiplying a torque command by J, which simulates a total moment of inertia of the drive shaft 301, and integrating the product, calculating the tool tip speed v, and integrating the tool tip speed v, where s is a Laplace operator and "1 / s" represents an integral operation.

[0052] The response of the tool tip position x to the drive shaft command 17r is calculated by formula (7) below. Formula 7: x(s)r(s)=Kvps+KviJs3+Kvps2+(KvpKp+Kvi)s+KpKvi

[0053] However, the machine model 105 is an example, and any model can be used as long as the model can calculate the response of the tool tip position to the position command. For example, a control other than P control and PI control may be used, or the characteristic of the drive shaft 301 may be expressed by a transfer function instead of the total moment of inertia. For example, within the speed control loop, a current control loop may be provided to calculate the servo motor current 22 output from the servo motor 305. Here, the torque Tr is calculated by multiplying a motor current by a torque constant to calculate a motor torque based on the motor current.

[0054] Instead of a continuous system model using a Laplace operator, a model described by a difference equation in a discrete system can also be used as the machine model 105.

[0055] Fig. 7 is a flowchart for describing a first example of operations of the Fig. 5. The processing of steps S1 to S6 is the same as in Fig. 4. Before determining whether the clamping break condition is satisfied in step S2, the setting search unit 102b estimates in Fig. 7, the vibration amplitude is calculated using the machine model 105 (step S7). Specifically, the setting search unit 102b calculates the actual vibration amplitude between the tool 304 and the workpiece 303 based on the set vibration amplitude using the machine model 105. Here, a description will be given of a method of calculating the vibration amplitude using the model represented by Formula (7) above. In the model described in the form of a transfer function, the response at a certain frequency ω can be calculated by substituting jω for s in Formula (7), where j is an imaginary unit. Substituting jω for s in Formula (7) yields Formula (8). Formula 8: X(jω)r(iω)=jKvpω+Kvi{−Jω3+(KvpKp+Kvi)ω}j+(−Kvpω2+KpKvi)

[0056] Here, a ratio of the output to the input corresponds to the change value of the vibration amplitude, and therefore, when the absolute value of formula (8) is calculated, the result is expressed by formula (9) below. Formula 9: ‖X(jω)r(iω)‖=[Kvpω{−Jω3+(KvpKp+Kvt)ω}+(−Kvpω2+KpKvt)Kvt]2+[(−Kvpω2+Kp Kvt)Kvpω+{−Jω3+(KvpKp+Kvt)ω}Kvt]2{−Jω3+(KvpKp+Kvt)ω}2+(−Kvpω2+KpKvt)2

[0057] As described above, when the input vibration frequency is determined, the output of the actual vibration between the tool 304 and the workpiece 303 can be calculated as a formula. Therefore, the actual vibration amplitude A' between the tool 304 and the workpiece 303 can be calculated using the set vibration frequency ω v and formula (9) for the set vibration amplitude A can be calculated.

[0058] Here, the calculation is performed assuming that the input vibration has a single frequency ω, but the input vibration waveform may be a square wave, a triangular wave, or the like. For example, it is known that a square wave vibration command can be described as a sum of individual vibrations of a frequency (2π-1)ω with a vibration amplitude (4 / π) × (A / 2n-1) for each n, as expressed by formula (10) using a Fourier series. Formula 10: f(ωt)=∑n=1∞4πA2n−1sin(2n−1)ωt

[0059] By calculating the sum of the amplitude ratios for the respective frequencies using Formula (10) and Formula (9), the amplitude for the rectangular-wave vibration command can be calculated. Alternatively, given that a first-order frequency component is most prominent, when calculating a response to a rectangular wave input, an amplitude ratio can be calculated by approximation as a function of only the first-order frequency component. The amplitude ratio can be calculated similarly for a triangular wave, a command simulating other periodic vibration, and the like.

[0060] In step S2 in Fig. 7, the setting search unit 102b determines whether the chip breaking condition is satisfied using the vibration amplitude A' calculated in step S7 instead of the set vibration amplitude A.

[0061] Fig. 8 is a flowchart for describing a second example of operations of the Fig. 5 shown setting search unit 102b. In the Fig. In the first example shown in Figure 7, the actual vibration amplitude A' is calculated before determining whether the chip breaking condition is met. In the example shown in Fig. However, in the second example shown in Figure 8, after a drive setting that satisfies the chip breaking condition is found, the setting search unit 102b corrects the vibration amplitude based on the machine model 105 before outputting the drive setting as the actual drive setting (step S8). After the vibration amplitude A and the vibration frequency ω v, which satisfy the chip breaking condition, are found, the setting search unit 102b calculates a corrected vibration amplitude A'' by multiplying the vibration amplitude A by the reciprocal of formula (9) so that the vibration amplitude between the tool 304 and the workpiece 303 coincides with the vibration amplitude A. In step S6, the setting search unit 102b outputs the actual drive setting including the corrected vibration amplitude A''.

[0062] In the above example, the actual vibration amplitude value is also calculated based on the vibration amplitude command value using the formula. However, the method of estimating the actual vibration amplitude value is not limited to the above example. For example, the setting search unit 102b may experimentally estimate the actual vibration amplitude value using a formula, a data table, or the like that approximates the actual vibration amplitude value experimentally derived for the vibration amplitude command value.Furthermore, instead of using formula (7), the setting search unit 102b may calculate the amplitude ratio by converting a discrete system model described by a difference equation into a continuous system using a conversion formula for converting a discrete system model into a continuous system model, which is called bilinear transformation or Tustin transformation. Furthermore, the actual vibration amplitude value may be calculated using another existing algorithm for calculating the vibration amplitude. Alternatively, the setting search unit 102b may calculate a response waveform based on the model by performing numerical simulation and calculate an amplitude ratio based on the response waveform obtained by the simulation.

[0063] Fig. 9 is a diagram showing an experimentally derived relationship of a response amplitude for a command value of a vibration amplitude. Fig. 9 is a diagram called a Bode diagram, which is obtained by commanding a sine signal or random noise whose frequency changes continuously to the servo motor and measuring a vibration between the tool 304 and the workpiece 303 at that time using an acceleration sensor, a displacement sensor, or the like. In this drawing, a ratio of an output amplitude to an input amplitude is calculated at each frequency. However, 0 dB means that the input amplitude matches the output amplitude, a gain greater than 0 dB means that the output amplitude is greater than the input amplitude, and a gain less than 0 dB means that the output amplitude is smaller than the input amplitude.Using the Bode plot, the actual vibration amplitude can be calculated for the command value of the input vibration amplitude without using numerical calculation. For example, the characteristics of the Bode plot can be approximated by the formula, or the actual value of the vibration amplitude can be calculated using the Bode plot as table data for the machine model 105.

[0064] As described above, in the information processing device 1b according to the second embodiment, the setting search unit 102b searches for the drive setting that satisfies the chip breaking condition based on the vibration amplitude estimated using the machine model 105, which estimates the actual vibration amplitude at the tip position of the tool 304 based on the drive shaft command. Instead of the command value of the vibration amplitude, determining whether the estimated value of the actual vibration amplitude satisfies the chip breaking condition can more reliably increase the probability of chip breaking when performing vibration cutting using the machine tool 3. Third embodiment.

[0065] Fig. 10 is a diagram showing a functional configuration of an information processing device 1c according to a third embodiment. The information processing device 1c is an example of a drive setting determination device. The information processing device 1c includes a search setting input unit 100c and a setting search unit 102c.

[0066] The search setting input unit 100c acquires the machining reference setting 11, the vibration reference setting 12, the machining setting search area 13, and the vibration setting search area 14 as the search setting.

[0067] The setting search unit 102c searches for a drive setting using a machine model 105c and an evaluation function 106.

[0068] Fig. 11 is a diagram showing an example of the Fig. 10. The machine model 105c differs from the machine model 105 of the second embodiment in that the machine model 105c includes a machine end transfer function model Gm(s). In normal feedback control, control is performed so that a position detected by a detector coincides with a command position. In the case of the machine tool 3 performing vibration cutting, the vibration amplitude is actually to be controlled for the relative vibration between the tool 304 and the workpiece 303. However, it is difficult to mount a detector that detects a relative displacement between the tool 304 and the workpiece 303.Therefore, feedback control is performed using a detector attached to the servo motor 305, and the actual relative vibration between the tool 304 and the workpiece 303 is estimated using the machine end transfer function model Gm(s).

[0069] A machine end model is measured, for example, with an acceleration sensor installed in each of the tool 304 and the workpiece 303. For example, the Bode diagram is drawn in which an acceleration signal is input by twice differentiating a detection signal at the time of driving a motor and a relative acceleration is output, and a transfer function can be identified by curve regression, a transfer function calculated based on a model of a structure of the machine tool 3 by a finite element method (FEM), or a state space model output from an element synthesis matrix of an FEM model can be used.

[0070] Fig. 12 is a flow chart for describing operations of the Fig. 10. The setting search unit 102c first sets the machining reference setting 11 and the vibration reference setting 12 (step S1). The setting search unit 102c then estimates the actual vibration amplitude using the machine model 105c (step S7). The setting search unit 102c determines whether the set machining setting and vibration setting satisfy the chip breaking condition (step S2). At this time, the setting search unit 102c uses the actual vibration amplitude estimated in step S7 as the vibration amplitude of the vibration setting.

[0071] If the chip breaking condition is not met (step S2: NO), the setting search unit 102c determines whether the vibration amplitude can be adjusted (step S3). If the vibration amplitude can be adjusted (step S3: YES), the setting search unit 102c changes the vibration amplitude within the vibration amplitude search range (step S4) and returns to the processing of step S7.

[0072] If the vibration amplitude cannot be adjusted (step S3: no), the adjustment search unit 102c determines whether the vibration frequency can be adjusted (step S9). If the vibration frequency can be adjusted (step S9: yes), the adjustment search unit 102c changes the vibration frequency within the vibration frequency search range (step S5) and returns to the processing of step S7.

[0073] If the vibration frequency cannot be adjusted (step S9: No), the setting search unit 102c determines whether the spindle speed can be adjusted (step S10). If the spindle speed can be adjusted (step S10: Yes), the setting search unit 102c changes the spindle speed within a rotation speed search range (step S11) and returns to the processing of step S7.

[0074] If the spindle speed cannot be adjusted (step S10: No), the setting search unit 102c determines whether the feedrate can be adjusted (step S12). If the feedrate can be adjusted (step S12: Yes), the setting search unit 102c changes the feedrate within the feedrate search range (step S13) and returns to the processing of step S7.

[0075] If the feed cannot be adjusted (step S12: no), a search failure is output (step S14) and processing ends.

[0076] If the chip breaking condition is satisfied (step S2: yes), the setting search unit 102c then determines whether the set machining setting and vibration setting satisfy a first evaluation function (step S15). If the first evaluation function is not satisfied (step S15: no), the setting search unit 102c proceeds to the processing of step S3. If the first evaluation function is satisfied (step S15: yes), the setting search unit 102c outputs the set machining setting and vibration setting as the actual drive setting (step S6).

[0077] Here, the first evaluation function is a function for evaluating the desired machining setting and vibration setting. Even if the desired machining setting and vibration setting meet the chip breaking condition, if machining requires too much time or the machine tool 3 is subjected to excessive load, it is not preferable to perform machining using such a desired machining setting and vibration setting. Therefore, the information processing device 1c uses the evaluation function to determine whether a combination of the desired machining setting and vibration setting is suitable.The first evaluation function is represented by a linear sum of at least one of an electrical energy generated to generate vibration, a vibration acceleration, a machining time, a cutting volume, a maximum machining load, a mechanical wear amount, and an accumulated vibration cutting time. For example, the first evaluation function may be "V>100", which represents a cutting volume V(mm). 3 / min). The cutting volume V can be expressed by formula (11) below using a spindle speed S, a feed per tooth F, and a radial cutting depth h and diameter R (mm) of the workpiece 303. Formula 11: V=2πRhFS

[0078] In the first evaluation function, the spindle speed can simply be greater than or equal to the lower limit, or the feed rate can be greater than or equal to the lower limit. Alternatively, the first evaluation function can be a combination of these.

[0079] As described for the vibration amplitude in the first embodiment, it should be noted that in the step of changing each setting within the search range, the value included in each setting can be changed by a constant value from the lower limit to the upper limit of the search range. In this case, in the step of determining whether each setting can be adjusted, the determination of whether each setting can be adjusted can be made based on whether the changed value exceeds the upper limit.In this case, in step S5, the value of the vibration amplitude is changed to the lower limit of the vibration amplitude search range, in step S11, the value of the vibration amplitude is changed to the lower limit of the vibration amplitude search range, and the value of the vibration frequency is changed to the lower limit of the vibration frequency search range, and in step S13, the value of the vibration amplitude is changed to the lower limit of the vibration amplitude search range, the value of the vibration frequency is changed to the lower limit of the vibration frequency search range, and the value of the spindle speed is changed to the lower limit of the rotational speed search range.This enables the search for the drive setting that satisfies the chip breaking condition and the first evaluation function while changing each value included in the machining setting and the vibration setting from the lower limit to the upper limit of the search range.

[0080] In the third embodiment, the search occasionally fails in some cases because the evaluation is performed using the first evaluation function. If the drive setting that satisfies both the chip breaking condition and the first evaluation function is not found, a user is notified of the search failure in step S14. In this case, the user can reset the search range and perform the search again.

[0081] It should be noted that in Fig. 12 The search ends when a drive setting that satisfies both the chip breaking condition and the first evaluation function is found. However, multiple candidates of the actual drive setting that satisfy the chip breaking condition can be searched within the entire search range, and the actual drive setting can be determined from the multiple candidates based on the first evaluation function. In this case, if the multiple candidates exist, it is possible to use a setting from the multiple candidates that is suitable for machining.

[0082] As described above, according to the information processing device 1c according to the third embodiment, the setting search unit 102c can search for a candidate for the actual drive setting that satisfies the chip breaking condition, and determine whether the searched candidate should be applied as the actual drive setting based on the first evaluation function for evaluating cutting using the searched candidate. Therefore, even if the chip breaking condition is satisfied, it is possible to prevent a setting with which the cutting evaluation is low, for example, a setting with which cutting requires too much time or the machine tool 3 is subjected to excessive load, from being used as the actual drive setting.

[0083] Furthermore, the first evaluation function may be a function represented by a linear sum of at least one parameter selected from the energy required to generate vibration, the vibration acceleration, the machining time, the cutting volume, the maximum machining load, the amount of mechanical wear, and the accumulated vibration cutting time. This enables the evaluation of cutting based on these parameters.

[0084] For example, if the mass of the shaft used to perform vibration cutting is considered as M, the energy required to generate the vibration is given by “1 / 2MA 2 ω v 2when expressed in terms of vibration energy. Alternatively, as an energy required to generate vibration, a value obtained by converting the above-described vibration energy into electrical energy may be used. In this case, as the energy required to generate vibration, a value obtained by dividing the vibration energy by a coefficient representing the efficiency of converting electrical energy into vibration energy may be used. Regarding the machining time, the machining time “L / SF” can be calculated by calculating a shaft movement amount per minute SF based on the feed per revolution F and the spindle speed S, and dividing a total machining length L along which vibration cutting is performed by the shaft movement amount per minute SF.A maximum machining load is given by “K. C AF / 1000" using a specific cutting force (or a specific cutting resistance K C ) K C which is determined based on physical material properties of the workpiece 303. In addition, the mechanical wear amount is calculated by accumulating a vibration cutting time so far and multiplying the accumulated vibration cutting time by an experimentally determined coefficient.

[0085] Combining these evaluation values ​​also enables the development of a more flexible evaluation function. For example, when searching for an optimal setting for both machining time and vibration energy, an evaluation function Z can be calculated as a linear sum of two evaluation functions with coefficients P1 and P2, as expressed by formula (12) below. However, the coefficients P1 and P2 can take any predetermined real number. Formula 12: Z=P112MA2ωv2+P2LSF

[0086] In addition, in the first embodiment, if the drive setting that satisfies the chip breaking condition and the first evaluation function is not found within the set search range, the user is notified of the search failure. Therefore, the user can change the search setting and search for the drive setting again.

[0087] Although, according to the above description, the value of the actual vibration amplitude is estimated based on the command value of the vibration amplitude using the machine model 105, an artificial intelligence (AI) model may be used instead of the machine model 105c, which simulates a physical phenomenon. Fig. Fig. 13 is a diagram showing a functional configuration of an information processing device 1c-2 according to a modification example of the third embodiment. The information processing device 1c-2 shown in Fig. 13 differs from the information processing device 1c in that the information processing device 1c-2 includes a setting search unit 102c-2 that estimates an actual value based on a command value of a vibration amplitude using an AI model 107 instead of the machine model 105c. The AI ​​model 107 is a learned model that outputs the actual vibration amplitude at the tip position of the tool 304 in response to receiving, as inputs, the command value of the vibration amplitude, the spindle speed, the feed rate per tooth, and the vibration frequency. The AI ​​model 107 may be, for example, a model learned by artificial intelligence using an algorithm such as a neural network, reinforcement learning, or Q-learning. Fourth embodiment.

[0088] Fig. 14 is a diagram showing a functional configuration of a numerical control device 1d according to a fourth embodiment. The numerical control device 1d includes the search setting input unit 100, the machining program input unit 101, a setting search unit 102d, and the command value generation unit 104.

[0089] The numerical control device 1d differs from the numerical control device 1a in that the inputs to the search setting input unit 100 are the machining reference setting 11, the machining setting search range 13, and the vibration setting search range 14, and the numerical control device 1d includes the setting search unit 102d, which uses the machine model 105 and the evaluation function 106 as inputs. Note that in the numerical control device 1d, the vibration reference setting is not included in the inputs to the search setting input unit 100. Therefore, when starting the search, the search should be started from the lower limit of the vibration setting search range, the upper limit of the vibration setting search range, a middle value of the vibration setting search range, or a preset search initial setting with parameters or the like.

[0090] Fig. 15 is a flow chart for describing operations of the Fig. 14. Now, a description will be given of a difference from the setting search unit 102d shown in Fig. 12. If the first evaluation function is satisfied (step S15: yes), the setting search unit 102d further determines whether a second evaluation function is satisfied (step S17).

[0091] If the second evaluation function is satisfied (step S17: yes), the setting search unit 102d returns to step S3 to continue the setting search without applying the set setting. If the second evaluation function is not satisfied (step S17: no), the setting search unit 102d proceeds to step S6.

[0092] In addition, Fig. 15, if the feed cannot be adjusted (step S12: no), the setting search unit 102 sets the drive setting including the machining reference setting 11 and not performing the vibration cutting (step S16) and proceeds to step S6.

[0093] Step S17 in Fig. 15 serves as a safety device, and the second evaluation function is set so that "the second evaluation function is satisfied" in a case where "an abnormality occurs when vibration cutting is performed using the set machining setting and vibration setting." For example, the second evaluation function is satisfied in an exemplary case where the vibration amplitude is too large and a load on the machine tool 3 and loads on electrical devices provided in the machine tool 3 increase, which may cause a failure. Examples of the electrical devices provided in the machine tool 3 include a numerical control device, a drive device called a drive unit, a motor, an electromagnetic switch, a relay, and the like.

[0094] Examples of the second evaluation function include functions using a vibration energy H, a power consumption, and a vibration amplitude. Furthermore, different thresholds using the same function may be provided for the first evaluation function and the second evaluation function. For example, the first evaluation function is such that a machining time is three minutes or more, and the second evaluation function is such that a machining time is 10 minutes or more. In this case, the first evaluation function is not satisfied when the machining time is less than three minutes, and the second evaluation function is satisfied when the machining time is 10 minutes or more. Accordingly, the set drive setting is not selected.Therefore, the machining setting will be output as the actual drive setting only when the machining time is three minutes or more and less than 10 minutes.

[0095] Although not in Fig. 14, the numerical control device 1d may further include an evaluation function setting unit for the user to set any setting as the first evaluation function and the second evaluation function.

[0096] In addition, like the first evaluation function, the second evaluation function may also be a function represented by the linear sum of at least one element of an electrical energy required to generate vibration, a vibration acceleration, a machining time, a cutting volume, a maximum machining load, a mechanical wear amount, and an accumulated vibration cutting time.

[0097] The first evaluation function is preferably a function that can determine that, when the first evaluation function is satisfied, vibration cutting using the drive setting that satisfies the first evaluation function is appropriate. The second evaluation function is preferably a function that can determine that, when the second evaluation function is satisfied, it is preferable not to apply the drive setting as the actual drive setting, for example, in a case where an abnormality occurs in vibration cutting using the drive setting.

[0098] Note that when the maximum machining load, the amount of mechanical wear, the accumulated vibration cutting time, and the like are used as the evaluation function, a machining load and a wear amount are predicted by performing a machining simulation using the machine model 105. Furthermore, as the accumulated vibration cutting time, a memory for recording the total time of performing vibration cutting so far is set. In addition to the above, for example, an evaluation function using the number of chips that can be broken by vibration cutting in one revolution may be used. For example, if the number of times a chip break occurs during one revolution is too large, a load is applied to the servo motor 305, and as a result, heat is generated.On the other hand, when machining the workpiece 303 with a large radius, if the frequency of chip breakage is low, a long continuous chip is formed, which is more likely to wrap around the tool 304 or the like. Therefore, using the frequency of chip breakage during one revolution as an evaluation function enables a search for the drive setting so that the chip is broken at an appropriate frequency.

[0099] As described above, the setting search unit 102d of the numerical control device 1d according to the fourth embodiment evaluates a candidate for the actual drive setting such that the chip breakage condition is satisfied based on the second evaluation function for evaluating whether an abnormality occurs during cutting using the candidate, and does not apply the candidate as the actual drive setting if it is evaluated that an abnormality occurs during cutting using the candidate. This can prevent selection of a drive setting such that an abnormality occurs during cutting even if the chip breakage condition is satisfied.

[0100] Furthermore, if the drive setting to be applied as the actual drive setting is not found based on the second evaluation function, the setting search unit 102d may determine, as the actual drive setting, the drive setting that includes the machining reference setting 11 and does not perform vibration cutting. In this case, if a drive setting evaluated based on the second evaluation function so that no abnormality occurs is not found, it is possible to prioritize performing cutting so that no abnormality occurs without performing vibration cutting. Fifth embodiment.

[0101] Fig. 16 is a diagram showing the functional configuration of an information processing device 1e according to a fifth embodiment. The information processing device 1e differs from the information processing device of the third embodiment in that the information input to the search setting input unit 100 includes the machining reference setting 11, the vibration setting search area 14, and the control parameter search area 19, and the information processing device 1e includes a setting search unit 102e instead of the setting search unit 102c.The inputs to the information processing device 1e are the machining reference setting 11, the vibration setting search range 14, and the control parameter change range 19, and the outputs from the information processing device 1e are the actual machining setting 15, the actual vibration setting 16, and the control parameter 24. Note that in the numerical control device 1e, the vibration reference setting is not included in the inputs to the search setting input unit 100. Therefore, when starting the search, the search should be started from the lower limit of the vibration setting search range, the upper limit of the vibration setting search range, the middle value of the vibration setting search range, or the preset search initial setting with parameters, etc.

[0102] Fig. 17 is a flow chart for describing operations of the Fig. 16 shown setting search unit 102e.

[0103] The setting search unit 102e sets the machining reference setting 11 (step S1e). The setting search unit 102e determines whether the set setting satisfies the chip breaking condition (step S2). If the chip breaking condition is not satisfied (step S2: no), the setting search unit 102e determines whether the vibration amplitude can be adjusted (step S3). If the vibration amplitude can be adjusted (step S3: yes), the setting search unit 102e changes the vibration amplitude within the vibration amplitude search range (step S4) and returns to the processing of step S2.

[0104] If the vibration amplitude cannot be adjusted (step S3: no), the adjustment search unit 102e determines whether the vibration frequency can be adjusted (step S9). If the vibration frequency can be adjusted (step S9: yes), the adjustment search unit 102e changes the vibration frequency within the vibration frequency search range (step S5) and returns to the processing of step S2.

[0105] If the vibration frequency cannot be adjusted (step S9: No), the setting search unit 102e determines whether the control parameter can be adjusted (step S18). If the control parameter can be adjusted (step S18: Yes), the setting search unit 102e changes the control parameter within the control parameter adjustment range (step S19) and returns to the processing of step S2.

[0106] If the control parameter cannot be adjusted (step S18: no), the setting search unit 102e sets a drive setting that includes the machining reference setting 11 and does not perform vibration cutting (step S16), and outputs the set machining setting, vibration setting, and control parameter as an actual drive setting (step S6e).

[0107] If the chip breaking condition is met (step S2: yes), the setting search unit 102e corrects the vibration amplitude based on the machine model 105 (step S8). The setting search unit 102e determines whether the set drive setting satisfies the second evaluation function (step S17). If the second evaluation function is met (step S17: yes), the setting search unit 102e proceeds to the processing of step S3, and if the second evaluation function is not met (step S17: no), the setting search unit 102e proceeds to the processing of step S6e.

[0108] As in Fig. As shown in Figure 17, in the fifth embodiment, the control parameter is searched in addition to the vibration setting. If the machine model 105 is the same as the machine model 105 used in the third embodiment, the control parameters are, for example, the position loop gain K p , the speed loop gain K vp and the velocity integral gain K vi The control parameters are parameters that determine the control characteristics of the drive shaft 301, and the control parameters affect the calculation of the vibration amplitude, as expressed by formula (10). Therefore, even with the same vibration setting, whether chip breakage occurs varies depending on the value of each of the control parameters. As the control parameter to be changed, only the position loop gain K p be changed or the position loop gain Kp and the speed loop gain K vp Both can be changed. The parameter to be changed can be predetermined or can be optionally selected by the user for each machining operation. For example, if a model different from machine model 105 is used, a control parameter that affects the vibration amplitude can also be set as a search target in the model to be used. Setting the control parameter as a search target can increase the probability of being able to search for a drive setting that enables chip breaking.

[0109] When changing the control parameter, it is preferable to determine threshold values ​​of a phase range and a gain range using the evaluation function so that the control system is not unstable with respect to the change in the control parameters. The phase range is a range of a phase starting from -180 degrees when the gain is 0 dB in the control system, and usually the control system is stable if a phase range of 30 degrees or more is ensured. In addition, the gain range is a gain starting from 0 dB when the phase is -180 degrees. Setting the evaluation function in this way enables a search for a drive setting such that chip breakage occurs while maintaining the stability of the control system.

[0110] As described above, according to the fifth embodiment, it is possible to determine, as the actual drive setting, the vibration setting and the control parameter so that chip breaking occurs while maintaining the stability of the control system. Sixth embodiment.

[0111] Fig. 18 is a diagram showing a functional configuration of a numerical control device 1f according to a sixth embodiment. The numerical control device 1f differs from the numerical control device 1d according to the fourth embodiment in that the numerical control device 1f includes a machine model updating unit 113 and a failure prediction unit 114. The machine model updating unit 113 updates the machine model 105c based on an actually measured value of the vibration amplitude output by an acceleration sensor 306 that measures the vibration amplitude. The failure prediction unit 114 predicts a failure of the machine tool 3 based on aging of the machine model 105c. However, the machine model 105c is the same as that shown in Fig. 11. Note that in the numerical control device 1f, the vibration reference setting is not included in the inputs to the search setting input unit 100. Therefore, at the beginning of the search, the search is started from the lower limit of the vibration setting search range, the upper limit of the vibration setting search range, the middle value of the vibration setting search range, or the preset search initial value with parameters or the like.

[0112] The vibration characteristics of the machine tool 3 gradually change due to aging. For example, in some cases, vibration of the machine structure increases due to loosening of a fastening component, fatigue fracture of a structural member, loosening of a preload of a bearing or ball screw, and the like. Furthermore, in some cases, a motor load increases due to an increase in friction. In some cases, continuously performing vibration cutting in such a state causes failure of the machine tool 3. To address such a situation, the numerical control device 1f has a function of monitoring the aging of the machine tool 3 based on the difference between the vibration amplitude predicted by performing a calculation and the actual vibration amplitude, and predicting failure before failure actually occurs.This enables the machine tool 3 to be repaired at a suitable time.

[0113] The acceleration sensor 306 is installed on the drive shaft 301. In Fig. 18, the acceleration sensor 306 is mounted on a nut portion of the ball screw. However, the acceleration sensor 306 may be mounted, for example, on the inside of a tool holder of the tool 304 or may be mounted on a turret on which a lathe tool is mounted. The acceleration sensor 306 measures a vibration level during vibration cutting and transmits the vibration level to the machine model update unit 113. The machine model update unit 113 compares the calculated value of the vibration amplitude calculated based on the actual machining setting 15 and the actual vibration setting 16 with the actually measured value of the actual vibration amplitude.If a difference occurs between the calculated value and the actually measured value due to a change in the mechanical properties, the machine model update unit 113 changes Gm(s), which simulates the characteristics of the drive shaft 301 in the machine model 105c. This can accurately estimate the vibration amplitude even if the mechanical properties change.

[0114] The failure prediction unit 114 monitors a change history of the machine model 105c. When the change amount of the machine model 105c exceeds a predetermined threshold, the failure prediction unit 114 determines that the aging of the machine tool 3 exceeds an allowable value and a failure has occurred, and issues a warning to the user. A method of issuing the warning is not particularly limited, and the warning may be displayed on a screen or issued by sound. However, the failure prediction unit 114 may make a determination based on whether the current change amount of the machine model 105c exceeds the threshold, or may predict that the change amount will exceed the threshold after a certain period of time to issue a warning in advance.

[0115] As described above, the numerical control device 1f according to the sixth embodiment has the effect of being able to accurately estimate the vibration amplitude even when the mechanical properties change by changing the control parameter according to the change in the machine model 105c due to the aging deterioration of the machine tool 3. In addition, detecting the occurrence of a failure or a sign of the occurrence of a failure based on the amount of change in the machine model 105c can prepare a repair or a repair plan in advance and avoid a situation in which production is stopped due to a sudden failure. Seventh embodiment.

[0116] Fig. 19 is a diagram showing a functional configuration of an information processing device 1g according to a seventh embodiment. The information processing device 1g includes the search setting input unit 100, a setting search unit 102g, and a learned model storage unit 120. The setting search unit 102g includes a learning data acquisition unit 40 and a model generation unit 41.

[0117] The learning data acquisition unit 40 receives the machining reference setting 11 and the vibration reference setting 12 from the search setting input unit 100 and acquires, as vibration cutting learning data, the control parameter 24, tool information 30, workpiece information 31, and per-shaft operation information 32. The tool information 30 includes information indicating a tool material and a tool shape. The workpiece information 31 includes information indicating the material of the workpiece. The per-shaft operation information 32 includes information indicating a feed rate of each shaft and an acceleration of each shaft.

[0118] Based on the vibration cutting learning data acquired by the learning data acquisition unit 40, the model generation unit 41 uses the machine model 105, a machining surface quality determination model 42, and a chip breakage determination model 43 to learn, from actual drive conditions that satisfy the chip breakage condition, an actual drive setting with which a machining quality of cutting is best.That is, the model generation unit 41 receives as inputs the machining reference setting 11, the vibration reference setting 12, the control parameter 24, the operation information per shaft 32, the workpiece information 31, and the tool information 30, and outputs, as a result of learning, a setting and control parameter search model 48 that outputs a combination of the actual machining setting 15, the actual vibration setting 16, and the control parameter 24 that satisfies the chip breaking condition and satisfies the machining quality criteria of cutting.

[0119] The per-shaft operating information 32 is information indicating the operating position of the motor per shaft of the machine tool 3. The model generation unit 41 uses the machine model 105 to obtain, from the per-shaft operating information 32 and the control parameter 24, information indicating the movement of the machine structure attached to each axis of the machine tool 3. That is, the machine model 105 receives the per-shaft operating information 32 and the control parameter 24 as inputs and outputs information indicating the movement of the machine structure attached to each shaft of the machine tool 3. Furthermore, the model generation unit 41 uses the chip break determination model 43 to determine whether chip breakage occurs, that is, to determine whether a chip breakage condition is satisfied.The chip breakage determination model 43 receives as inputs the output of the machine model 105, the machining reference setting 11, the vibration reference setting 12, and the control parameter 24, and outputs a result of determining whether chip breakage occurs. Furthermore, the model generation unit 41 uses the machining surface quality determination model 42 to determine whether the machining quality of cutting using the drive setting for which chip breakage is determined to occur meets a criterion. The machining surface quality determination model 42 determines whether a machining result of the workpiece 303 is good or bad based on the operation information per shaft 32.The machining surface quality determination model 42 receives as inputs the output of the machine model 105, the drive setting for which a chip breaking condition is determined to be satisfied using the chip breaking determination model 43, the workpiece information 31, and the tool information 30, and determines the machining quality based on the smoothness of the machining surface. For example, the machining surface quality determination model 42 can evaluate the machining quality for the tool path using variations or the maximum error amount per tool path for an average line and an average plane, which is calculated based on the arithmetic mean.Alternatively, the machining surface quality determination model 42 may estimate the machining surface taking into account the shape of the tool 304 and evaluate the machining quality using a hill height after the workpiece 303 is removed.

[0120] Furthermore, a machining surface quality determination section can be modeled as the machining surface quality determination model 42 and included in a learning objective. The machining surface quality determination model 42 only needs to be able to calculate the machining surface of the workpiece 303 based on the relative displacement between the tool 304 and the workpiece 303.

[0121] The relative displacement may be a command for the motor, a motor end response calculated using a model of motor properties, or a machine end response calculated using a model of mechanical properties.

[0122] In addition, when calculating the machining surface of the workpiece 303, the machining surface may be calculated only by the relative displacement between the tool 304 and the workpiece 303, the relative displacement may be corrected with the shape of the tool 304 with geometric consideration, or the quality of the machining surface may be calculated based on a physical cutting event theory with the materials of the tool 304 and the workpiece 303 under further consideration.

[0123] The machining surface quality determination model 42 may be replaced by a data set obtained from the actual machine of the machine tool 3. For example, in addition to the machining setting and the vibration setting, the data set of the tool shape, the tool material, and the workpiece material is associated with the information of the quality of the surface when machined in the setting of the data set to obtain the data set for learning.

[0124] As described above, the model generation unit 41 uses the machine model, the machining surface quality determination model 42, and the chip breakage determination model 43 to learn the combination of the machining setting, the vibration setting, and the control parameter based on the vibration cutting learning data described above. That is, the model generation unit 41 generates the learned model from the vibration cutting learning data described above, which infers the drive setting including the machining setting, the vibration setting, and / or the control parameter.

[0125] Next, a description will be provided of a learning process of the model generation unit 41. As a learning algorithm used by the model generation unit 41, a known algorithm such as supervised learning, unsupervised learning, reinforcement learning, or the like can be used. As an example, a description will be provided of a case where reinforcement learning is applied as a learning algorithm. In reinforcement learning, an agent, which is an action subject in a certain environment, observes environmental parameters indicating a current state and determines an action to be taken. The agent's action dynamically changes the environment, and the agent is given a reward according to the change in the environment. The agent repeats this process and learns an action plan that yields the greatest reward through a series of actions.Representative reinforcement learning methods include Q-learning and TD-learning. In the case of Q-learning, a typical update formula of an action value function Q(s,a) is expressed, for example, by formula (13) below. Formula 13: Q(st,at)←Q(st,at)+α(rt+1+γ maxa Q(st+1,a)−Q(st,at))

[0126] In formula (13) s represents t an environmental state at time t, and a t represents an action at time t. The action a t changes the state to s t+1 . r t+1 represents a reward given by a change in the state, γ represents a discount factor, and α represents a learning rate. Note that γ is in a range of 0<γ≤1, and α is in a range of 0<α≤1. The selection of the machining setting, the vibration setting, and the control parameter corresponds to action a. t, the determination of the presence or absence of chip breakage and the machining surface quality information correspond to the state s t and the best action a t in the state s t learning takes place at time t.

[0127] In the update formula expressed by formula (13), an action value Q is increased when an action value Q of an action with a highest Q value at time t+1 is greater than an action value Q of an action a performed at time t, and the action value Q is reduced otherwise. In other words, the action value function Q(s,a) is updated so that the action value Q of action a at time t approaches the best action value at time t+1. The best action value in a particular environment is therefore sequentially carried forward to the action values ​​in the previous environments.

[0128] As described above, when the model generation unit 41 generates the learned model by the reinforcement learning, the model generation unit 41 includes a reward calculation unit 44 and a function updating unit 45.

[0129] The reward calculation unit 44 calculates a reward r based on the selection from the machining setting, the vibration setting, and the control parameter, the determination of the presence or absence of chip breakage, and the machining surface quality information. The reward calculation criteria are as follows. For example, the reward r is increased (for example, a reward of "1") when the machining surface quality information is improved, that is, when the variations or the maximum amount of errors in each tool path described above are reduced, or when the hillock height is reduced. On the other hand, the reward r is reduced (for example, a reward of "-1") when the machining surface quality information deteriorates.As another example, the reward r is increased when it is determined that chip breakage occurs, and the reward r is reduced when it is determined that chip breakage does not occur. Chip breakage is required to achieve the effect of vibration cutting, and therefore the reward r is greatly reduced (for example, a reward of "-5") when it is determined that chip breakage does not occur.

[0130] The function updating unit 45 updates a function for determining the combination of the machining setting, the vibration setting, and the control parameter according to the reward calculated by the reward calculating unit 44 and outputs the updated function to the learned model storage unit 120. For example, in the case of Q-learning, the function updating unit 45 uses the action value function Q(s t ,a t), which is expressed by formula (13), as a function for calculating the combination of the machining setting, the vibration setting and the control parameter.

[0131] The learning described above is carried out repeatedly. The learned model storage unit stores the action value function Q(s b ,a t ), which is updated by the function updating unit 45, ie the learned model.

[0132] Next, with reference to Fig. 20 a description of a processing of learning by a learning device is provided. Fig. 20 is a flowchart concerning a learning processing of the Fig. 19 shown setting search unit 102g.

[0133] The learning data acquisition unit 40 performs data acquisition processing for acquiring the machining setting, the vibration setting, and the control parameter as learning data (step S31).

[0134] The model generation unit 41 calculates a reward based on the selection of the machining setting, the vibration setting, and the control parameter, the determination of the presence or absence of chip breakage, and the machining surface quality information (step S32). Specifically, the reward calculation unit 44 uses each of the above-described models to obtain the determination of the presence or absence of chip breakage and the machining surface quality information based on the selection of the combination of the machining setting, the vibration setting, and the control parameter, and determines whether to increase or decrease the reward based on a predetermined reward determination criterion.

[0135] If it is determined to increase the reward (step S32: reward increase criterion), the reward calculation unit 44 increases the reward (step S33). On the other hand, if it is determined to decrease the reward (step S32: reward decrease criterion), the reward calculation unit 44 decreases the reward (step S34).

[0136] The function update unit 45 updates the action value function Q(s t ,a t ), which is expressed by formula (13) and stored in the learned model storage unit 120, based on the reward calculated by the reward calculation unit 44 (step S35).

[0137] The setting search unit 102g repeatedly executes the above steps from step S31 to step S35 and stores the generated action value function Q(s t ,a t ) than the learned model.

[0138] As described above, the information processing apparatus 1g according to the seventh embodiment stores the learned model in the learned model storage unit 120 provided inside the information processing apparatus 1g, however, the learned model storage unit 120 may be arranged outside the information processing apparatus 1g.

[0139] The information processing apparatus 1g according to the seventh embodiment learns a machining phenomenon associated with a complicated phenomenon by artificial intelligence using information during machining and therefore has an effect that even an operator who has no machining knowledge can easily find an optimal chip breaking condition.

[0140] In addition, as a learning algorithm used in the model generation unit 41, deep learning which learns extraction of a feature set itself may be used, and machine learning may be performed according to other known methods such as a neural network, genetic programming, functional logic programming, support vector machine, and the like.

[0141] Furthermore, the model generation unit 41 can learn the combination of the machining setting, the vibration setting, and the control parameter using pieces of learning data acquired from multiple numerical control devices. Note that the model generation unit 41 can acquire the pieces of learning data from the multiple numerical control devices used in the same area, or learn the combination of the machining setting, the vibration setting, and the control parameter using pieces of learning data collected from the multiple numerical control devices operating independently in different areas. Furthermore, the numerical control device from which learning data is collected can be added to or removed from target objects intermittently.In addition, an information processing device that has learned the combination of the machining setting, the vibration setting, and the control parameter for a specific numerical control device can be applied to a numerical control device different from the specific numerical control device, and the combination of the machining setting, the vibration setting, and the control parameter can be newly learned and updated for the numerical control device different from the specific numerical control device. Eighth embodiment.

[0142] Fig. 21 is a diagram showing a functional configuration of a numerical control device 1h according to an eighth embodiment. In the eighth embodiment, inference is performed using the learned model generated in the seventh embodiment. A setting search unit 102h includes an inference data acquisition unit 46 and an inference unit 47.

[0143] The inference data acquisition unit 46 acquires the vibration cutting learning data as inference data.

[0144] The inference unit 47 uses the learned model to infer the combination of the machining setting, the vibration setting, and the control parameter from the inference data. This means that the inference unit 47 can infer the combination of the machining setting, the vibration setting, and the control parameter that can break the chip while maintaining good machining surface quality by inputting the vibration cutting learning data acquired by the inference data acquisition unit 46 into the setting and control parameter search model 48, which is the learned model.

[0145] As a method for acquiring the learned model, the learned model may be acquired from an external device other than the numerical control device 1h, for example, an external personal computer, a storage area on a network, or the like, and the combination of the machining setting, the vibration setting, and the control parameter may be output based on the acquired learned model.

[0146] Note that in the present embodiment, it is assumed that the combination of the machining setting, the vibration setting, and the control parameter is output using the learned model learned by the model generation unit 41 of the information processing device. However, a learned model generated by performing learning using the model generation unit 41 provided in the numerical control device 1h may be used.

[0147] Next, a description is provided of processing for obtaining the combination of the machining setting, the vibration setting, and the control parameter.

[0148] First, the inference data acquisition unit 46 acquires the vibration cutting learning data. At this time, it is sufficient for the vibration cutting learning data to include at least the vibration reference setting 12 and the machining reference setting 11 described above, but it is expected that the accuracy of the inference will be improved by adding information other than these.

[0149] Next, the inference unit 47 inputs vibration cutting learning data, which is inference data, into the setting and control parameter search model 48, which is the related learned model, and obtains the combination of the machining setting, the vibration setting, and the control parameter. The inference unit 47 outputs the obtained combination of the machining setting, the vibration setting, and the control parameter to the command value generation unit 104.

[0150] Then, the command value generation unit 104 generates a drive shaft command and a spindle command by using the output combination of the machining setting, the vibration setting, and the control parameter, and outputs the drive shaft command and the spindle command to the drive unit 2 (in Fig. 21 not shown). This allows vibration cutting to be performed in an optimal setting, estimated by the learned model, which achieves both chip breaking and good machining surface quality.

[0151] Fig. 22 is a flowchart for describing inference processing by the Fig. 21 shown numerical control device 1h.

[0152] The inference data acquisition unit 46 acquires the above-described vibration cutting learning data as the inference data (step S41).

[0153] The inference unit 47 inputs the vibration cutting learning data, which is the inference data, into the learned model (step S42) and obtains a combination of the actual machining setting 15, the actual vibration setting 16, and the control parameter 24. The inference unit 47 performs data output processing to output the obtained combination of the actual machining setting 15, the actual vibration setting 16, and the control parameter 24 to the command value generation unit 104 (step S43).

[0154] The command value generation unit 104 generates a command value using a reasoning result (step S44).

[0155] Note that in the present embodiment described above, reinforcement learning is used as the learning algorithm used in the inference unit 47. However, the present embodiment is not limited to this. Supervised learning, unsupervised learning, semi-supervised learning, or the like may be used as the learning algorithm in addition to reinforcement learning.

[0156] The above-described numerical control apparatus 1h according to the eighth embodiment has an effect that the operator can perform the optimal vibration cutting without determining a machining setting when the vibration cutting is performed using a model learned by artificial intelligence.

[0157] Next, a description will be provided of a hardware configuration of each of the numerical control devices 1a, 1d, 1f, and 1h according to the first, fourth, sixth, and eighth embodiments. Functional units included in the numerical control devices 1a, 1d, 1f, and 1h are implemented using processing circuit parts. The processing circuit parts may be implemented by dedicated hardware or may be a control circuit using a central processing unit (CPU).

[0158] When the parts of a processing circuit described above are implemented by dedicated hardware, the parts of a processing circuit are each implemented using a processing circuit 90 which is Fig. 23 is shown. Fig. 23 is a diagram showing dedicated hardware for implementing the functions of each of the numerical control devices 1a, 1d, 1f, and 1h according to the first, fourth, sixth, and eighth embodiments. The processing circuit 90 is a single circuit, a combined circuit, a programmed processor, a parallel-programmed processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination thereof.

[0159] When the above processing circuit is implemented by a control circuit using the CPU, this control circuit is, for example, a control circuit 91 having a configuration shown in Fig. 24 is shown. Fig. 24 is a diagram showing a configuration of the control circuit 91 for implementing the function of each of the numerical control devices 1a, 1d, 1f, and 1h according to the first, fourth, sixth, and eighth embodiments. As shown in Fig. As shown in Figure 24, the control circuit 91 includes a processor 92 and a memory 93. The processor 92 is the CPU and is also known as a processing unit, a calculation unit, a microprocessor, a microcomputer, and a digital signal processor (DSP), for example. The memory 93 is, for example, a non-volatile or volatile semiconductor memory such as a random access memory (RAM), a read-only memory (ROM), a flash memory, an erasable programmable ROM (EPROM), or an electrically EPROM (EEPROM, registered trademark), a magnetic floppy disk, a flexible floppy disk, an optical disk, a compact disk, a mini disk, a digital versatile disk (DVD), or the like.

[0160] When the above-described processing circuit is implemented using the control circuit 91, the above processing circuit is implemented by the processor 92, which reads and executes a program corresponding to the processing of each structural component and stored in the memory 93. Furthermore, the memory 93 is used as a temporary storage when the processor 92 executes various processing.

[0161] Next, a description will be given of a hardware configuration of each of the information processing devices 1b, 1c, 1c-2, 1e, and 1g of the present embodiment. When the information processing devices 1b, 1c, 1c-2, 1e, and 1g are separate devices from the numerical control device, each of the information processing devices 1b, 1c, 1c-2, 1e, and 1g of the present embodiment is implemented by, for example, a computer system. Each of the information processing devices 1b, 1c, 1c-2, 1e, and 1g may be implemented by a single computer system or may be implemented by multiple computer systems. For example, each of the information processing devices 1b, 1c, 1c-2, 1e, and 1g may be implemented by a cloud system. In the cloud system, it is possible to optionally set a separation between hardware of the computer system and a device such as a server for each function.For example, a single computer system may function as multiple devices, or multiple computer systems may function as a single device.

[0162] A description of an exemplary configuration of a computer system implementing each of the information processing devices 1b, 1c, 1c-2, 1e and 1g is provided. Fig. 25 is a diagram showing an exemplary configuration of a computer system implementing each of the information processing devices 1b, 1c, 1c-2, 1e, and 1g according to the second, third, fifth, and seventh embodiments. As shown in Fig. 25, the computer system comprises a control unit 401, an input unit 402, a storage unit 403, a display unit 404, a communication unit 405 and an output unit 406, which are connected to each other via a system bus 407.

[0163] In Fig. 25, the control unit 401 is, for example, the CPU or the like. The control unit 401 executes programs describing various processing performed by each of the information processing devices 1b, 1c, 1c-2, 1e, and 1g of the present embodiment. The input unit 402 includes, for example, a keyboard, a mouse, and the like, and is used by a user of the computer system to input various types of information. The storage unit 403 includes various memories such as a random access memory (RAM) and a read-only memory (ROM), and a storage device such as a hard disk, and stores the programs to be executed by the control unit 401, necessary data acquired during processing, and the like. In addition, the storage unit 403 is used as a temporary storage area of ​​the program.The display unit 404 is formed, for example, by a liquid crystal display (LCD) panel and displays various screens for a user of the computer system. The communication unit 405 is, for example, a communication circuit that performs communication processing. The communication unit 405 may include multiple communication circuits that are mapped one-to-one to multiple communication methods. The output unit 406 is an output interface that outputs data to an external device, such as a printer or an external storage device.

[0164] It should be noted that Fig. 25 shows an example, and the configuration of the computer system does not apply to the example of Fig. 25. For example, the computer system does not necessarily have to include the output unit 406. In addition, when each of the information processing devices 1b, 1c, 1c-2, 1e, and 1g is implemented by the plurality of computer systems, all of these computer systems do not necessarily have to support the Fig. 25. For example, some computer systems may not necessarily include the display unit 404 and / or the output unit 406 and / or the input unit 402 shown in Fig. 25, include.

[0165] A description will now be given of an exemplary operation of the computer system until a drive setting determination program is in an executable state. The drive setting determination program is a program that describes the processing of each of the information processing devices 1b, 1c, 1c-2, 1e, and 1g of the present embodiment. In the computer system having the above-described configuration, the drive setting determination program is installed in the storage unit 403 of, for example, a compact disk (CD)-ROM or a DVD-ROM, which is inserted into a CD-ROM drive or a DVD-ROM drive (not shown). When the drive setting determination program is executed, the drive setting determination program read from the storage unit 403 is then stored in an area serving as a main storage device of the storage unit 403.In this state, the control unit 401 executes processing as each of the information processing devices 1b, 1c, 1c-2, 1e, and 1g of the present embodiment according to the drive setting determination program stored in the storage unit 403.

[0166] Note that in the above description, the program describing the processing of each of the information processing devices 1b, 1c, 1c-2, 1e, and 1g is provided using the CD-ROM or DVD-ROM as a recording medium, but the present disclosure is not limited to this. For example, a program provided through a transmission medium such as the Internet by the communication unit 405 can also be used to adjust the configuration of the computer system, a capability of a program to be provided, or the like.

[0167] The drive setting determination program according to the present embodiments is the drive setting determination program for determining the drive setting of the machine tool that performs vibration cutting, which enables chip breaking to occur, by vibrating the shaft that changes the relative position between the workpiece and the tool during cutting, wherein the drive setting determination program causes the computer to execute: a step of obtaining the search setting including the search range and the machining reference setting 11, wherein the search range is set for the drive setting including the machining setting for the machine tool and / or the vibration setting for the shaft and / or the control parameter, which is the parameter for determining the control characteristic of the shaft,wherein the machining reference setting 11 is the machining setting serving as the reference, which is determined regardless of whether vibration cutting is performed; and a step of determining the actual drive setting in the set search range based on the search setting so that the chip breaking condition is satisfied, wherein the actual drive setting is the drive setting used when performing vibration cutting, and the chip breaking condition is the condition under which chip breaking occurs.

[0168] The search setting input unit 100 of each of the information processing devices 1b, 1c, 1c-2, 1e, and 1g is implemented by the input unit 402. The setting search units 102b, 102c, 102c-2, and 102e of the information processing devices 1b, 1c, 1c-2, 1e, and 1g are each implemented by the control unit 401. Note that the machine models 105 and 105c and the evaluation function 106 are each stored in the storage unit 403.

[0169] It should be noted that in the system including each of the information processing devices 1b, 1c, 1c-2, 1e and 1g, an allocation of the respective functions of the devices shown is an example, and an allocation of the respective functions of the devices is not limited to the Fig.1 is limited as long as the above-described operations can be performed. For example, the information processing devices 1b, 1c, 1c-2, 1e, and 1g may each be implemented by the same computer system as the machining program generation device 103.

[0170] The configurations described in the above embodiments are examples and can be combined with the other known techniques, the embodiments can be combined with each other, and a part of each of the configurations can be omitted or modified without departing from the gist.

[0171] For example, in each of the above embodiments, an example of the method of searching for the drive setting was described, however, any algorithm can be used as long as necessary settings such as the spindle speed, feed per tooth, vibration amplitude, and vibration frequency can be determined. For example, the order of the search can be changed by changing the order of the steps shown. Furthermore, the drive setting can be searched not only using the method of searching for the drive setting in all possible ways, but also using various known optimization algorithms, for example, an optimization algorithm such as a genetic algorithm or Bayesian optimization using artificial intelligence.

[0172] Furthermore, in the above embodiments, the hardware configuration was described based on the assumption that the information processing device is connected to the numerical control device, for example, via the network and is a separate device from the numerical control device. However, the information processing device may be formed in the numerical control device. Alternatively, the information processing device may exist on a cloud server. List of reference symbols 1a, 1d, 1f, 1h Numerical control device; 1b, 1c, 1c-2, 1e, 1g information processing device; 2 drive unit; 3 machine tool; 10 machining programs; 11 Machining reference setting; 12 Vibration reference setting; 13 Machining setting search area; 14 Vibration setting search area; 15 actual machining setting; 16 actual vibration settings; 17, 17r drive shaft command; 18 spindle command; 19 Control parameter search area; 20 spindle current; 21 spindle position; 22 Servo motor current; 23 Drive shaft position; 24 control parameters; 30 tool information; 31 Workpiece information; 32 operating information per shaft; 40 Learning data reference unit; 41 Model generation unit; 42 Machining surface quality determination model; 43 Chip breakage determination model; 44 Reward calculation unit; 45 Function update unit; 46 Inference data reference unit; 47 Unit of inference; 48 Setting and control parameter search model; 90 processing circuit; 91 control circuit; 92 processor; 93 storage; 100, 100c search setting input unit; 101 machining program input unit; 102, 102b, 102c, 102c-2, 102d, 102e, 102g, 102h setting search unit; 103 machining program generation device; 104 Command value generation unit; 105, 105c machine model; 106 Evaluation function; 107 AI model; 110 n-th vibration trajectory; 111 (n+1)-th vibration trajectory; 112 chip breaking area; 113 Machine model update unit; 114 Failure Prediction Unit; 120 Learned model storage unit; 201 spindle servo control unit; 202 Drive shaft servo control unit; 300 spindle; 301 drive shaft; 302 spindle motor; 303 workpiece; 304 tools; 305 servo motor; 306 acceleration sensor; 401 control unit; 402 input unit; 403 storage unit; 404 display unit; 405 communication unit; 406 output unit; 407 System bus. QUOTES CONTAINED IN THE DESCRIPTION

[0000] This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions. Cited patent literature

[0000] JP 7007531

[0004]

Claims

[1] A drive setting determining device that determines a drive setting of a machine tool that performs vibration cutting that allows chip breaking to occur by vibrating a shaft for changing a relative position between a workpiece and a tool during cutting, the drive setting determining device comprising: a search setting input unit which obtains a search setting including a search range and a machining reference setting, wherein the search range is set for a drive setting which includes a machining setting for the machine tool and / or a vibration setting for the shaft and / or a control parameter which is a parameter for determining a control characteristic of the shaft, wherein the machining reference setting is the machining setting serving as a reference which is determined regardless of whether the vibration cutting is performed; and a setting search unit which, based on the search setting, determines an actual drive setting in the set search range so that a chip breaking condition is met, where the actual drive setting is the drive setting used when performing vibration cutting, where the chip breaking condition is a condition under which chip breaking occurs. [2] The drive setting determining apparatus according to claim 1, wherein the setting searching unit searches for the drive setting that satisfies the chip breaking condition based on a vibration amplitude estimated using a machine model that estimates the vibration amplitude at a position of a tip of the tool based on a drive command for the shaft. [3] The drive setting determining apparatus according to claim 1 or 2, wherein the setting searching unit searches for a candidate for the actual drive setting that satisfies the chip breaking condition, and determines whether the candidate is to be applied as the actual drive setting based on a first evaluation function for evaluating cutting using the searched candidate. [4] The drive setting determining apparatus according to claim 3, wherein the setting searching unit searches for a plurality of candidates for the actual drive setting that satisfy the chip breaking condition, and determines the actual drive setting from the plurality of searched candidates based on the first evaluation function. [5] The drive setting determining apparatus according to claim 3 or 4, wherein the first evaluation function is represented by a linear sum of at least one of an electric energy required to generate vibration, a vibration acceleration, a machining time, a cutting volume, a maximum machining load, a mechanical wear amount, and / or an accumulated vibration cutting time. [6] The drive setting determining apparatus according to any one of claims 1 to 5, wherein the setting searching unit evaluates a candidate for the actual drive setting that satisfies the chip breaking condition based on a second evaluation function for evaluating whether an abnormality occurs in cutting using the candidate, and does not apply the candidate as the actual drive setting when it is evaluated that an abnormality occurs in cutting using the candidate. [7] The drive setting determining device according to claim 6, wherein, when the drive setting to be applied as the actual drive setting is not found based on the second evaluation function, the setting searching unit determines, as the actual drive setting, a drive setting which includes the machining reference setting and does not perform the vibration cutting. [8] The drive setting determining apparatus according to claim 6 or 7, wherein the second evaluation function is represented by a linear sum of at least one of an electric energy required to generate vibration, a vibration acceleration, a machining time, a cutting volume, a maximum machining load, a mechanical wear amount, and / or an accumulated vibration cutting time. [9] A drive setting determining apparatus according to claim 2, further comprising: a machine model updating unit that updates the machine model based on a measured value of the vibration amplitude. [10] The drive setting determining apparatus according to claim 1, wherein the setting searching unit comprises: an inference data acquisition unit that acquires the machining setting, the vibration setting, a material of the workpiece, a material of the tool, a shape of the tool, a feed rate of the shaft, and an acceleration of the shaft as inference data; and an inference unit that infers the actual drive setting from the inference data using a learned model that infers the actual drive setting with which a machining quality of cutting is best from a plurality of actual drive states that satisfy the chip breaking condition, from the machining setting, the vibration setting, the material of the workpiece, the material of the tool, the shape of the tool, the feed rate of the shaft, and the acceleration of the shaft. [11] The drive setting determining apparatus according to claim 1, wherein the machining setting includes a rotational speed of the shaft, a cutting direction, and a cutting depth per revolution. [12] The drive setting determining apparatus according to any one of claims 1 to 11, wherein the drive setting determining apparatus is a numerical control apparatus, further comprising: a command value generating unit that generates the drive command for the shaft based on the actual drive setting determined by the setting searching unit. [13] A drive setting determining method for determining a drive setting of a machine tool that performs vibration cutting allowing chip breaking to occur by vibrating a shaft for changing a relative position between a workpiece and a tool during cutting, the drive setting determining method comprising: a step of obtaining a search setting including a search range and a machining reference setting, wherein the search range is set for a drive setting which includes a machining setting for a machine tool and / or a vibration setting for the shaft and / or a control parameter which is a parameter for determining a control characteristic of the shaft, wherein the machining reference setting is the machining setting serving as a reference which is determined regardless of whether the vibration cutting is performed; and a step of determining an actual drive setting in the set search range based on the search setting so that a chip breaking condition is satisfied, where the actual drive setting is the drive setting used when performing vibration cutting, where the chip breaking condition is the condition under which chip breaking occurs.

Images