CN117957088A - Numerical control device, machining system, numerical control method and machining method - Google Patents

Numerical control device, machining system, numerical control method and machining method Download PDF

Info

Publication number
CN117957088A
CN117957088A CN202180102184.0A CN202180102184A CN117957088A CN 117957088 A CN117957088 A CN 117957088A CN 202180102184 A CN202180102184 A CN 202180102184A CN 117957088 A CN117957088 A CN 117957088A
Authority
CN
China
Prior art keywords
operation command
machining
numerical control
tool
command
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202180102184.0A
Other languages
Chinese (zh)
Inventor
高币一树
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Mitsubishi Electric Corp
Original Assignee
Mitsubishi Electric Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Mitsubishi Electric Corp filed Critical Mitsubishi Electric Corp
Publication of CN117957088A publication Critical patent/CN117957088A/en
Pending legal-status Critical Current

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
    • B23Q15/00—Automatic control or regulation of feed movement, cutting velocity or position of tool or work
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
    • G05B19/404—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by control arrangements for compensation, e.g. for backlash, overshoot, tool offset, tool wear, temperature, machine construction errors, load, inertia
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
    • G05B19/406—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by monitoring or safety
    • G05B19/4069—Simulating machining process on screen
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
    • G05B19/4155—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by programme execution, i.e. part programme or machine function execution, e.g. selection of a programme

Abstract

The numerical control device (3) is characterized by comprising: a command generation unit (31) that generates a basic operation command, which is an operation command, based on the numerical control program (4), and generates a corrected operation command, which is an operation command after correction of the basic operation command; a coupling simulation unit (33) that calculates process information that represents results obtained by simulating machining when a basic operation command and a correction operation command are each given to the machine tool (2), the process information being obtained by calculating the effect of the dynamics of a member that generates vibrations during the operation of the machine tool (2) and the operation of the drive system on the machining process (M) of the machining object (W) performed by the tool (23); and a process evaluation unit (34) that evaluates the magnitude of the machining error when a plurality of operation commands are used, respectively, based on the plurality of process information, and selects an operation command to be given to the machine tool (2) from among the basic operation command and the corrected operation command.

Description

Numerical control device, machining system, numerical control method and machining method
Technical Field
The present invention relates to a numerical control device, a machining system, a numerical control method, and a machining method for controlling a machine tool.
Background
The machine tool is a machining device capable of performing a removal process of imparting a force or energy to a workpiece by using a tool, thereby removing unnecessary portions from the workpiece. The machine tool includes a spindle drive system for rotating a tool or a workpiece, and a feed drive system for changing the relative positions of the tool and the workpiece, and the numerical control device drives the spindle drive system and the feed drive system in accordance with an operation command generated based on a numerical control program to machine the workpiece. Even if the machine tool is controlled in accordance with the command described in the numerical control program, there are cases where machining cannot be performed in accordance with the command due to various factors, and machining errors may occur.
Patent document 1 proposes a technique for calculating a displacement of a tool caused by a cutting resistance applied to the tool during cutting, thereby reproducing the properties of a machined surface. In the method described in patent document 1, a parameter indicating the dynamic characteristics of the tool is stored in advance, so that the displacement of the tool center when the cutting resistance corresponding to the cutting thickness of the tool calculated by simulation is generated is regarded as a machining error.
Patent document 1: japanese patent laid-open No. 2013-132733
Disclosure of Invention
However, according to the above-mentioned conventional technique, there is a problem that the machining error cannot be reduced with high accuracy. In the technique described in patent document 1, the deflection amount of the tool is predicted, and the displacement of the center of the tool is regarded as a machining error, but in reality, the machining process, the operation of the drive system, and the mechanical dynamics of the member that generates vibration during the operation of the machine tool are mutually affected. Here, the machining process means a series of processes in which the cutting edge of the tool penetrates into the object to be machined to generate chips and form a machined surface, and the mechanical dynamics means the dynamic characteristics of a member that vibrates when vibration is transmitted from a vibration source inside and outside the machine tool. Therefore, in the method described in patent document 1, the machining error cannot be accurately evaluated, and the machining error cannot be reduced with high accuracy.
The present invention has been made in view of the above circumstances, and an object thereof is to provide a numerical control device capable of reducing machining errors of a machine tool with high accuracy.
In order to solve the above-described problems and achieve the object, a numerical control device according to the present invention controls a machine tool having a drive system including a main shaft drive system for driving a main shaft for rotating a tool or a machining object for machining the machining object and a feed drive system for driving a feed shaft for changing the relative positions of the tool and the machining object, by giving an operation command to the machine tool, the numerical control device comprising: a command generation unit that generates a basic operation command, which is an operation command, based on the numerical control program, and generates a corrected operation command, which is an operation command after correction of the basic operation command; a coupling simulation unit that calculates process information indicating a result of simulation of machining in a case where a basic operation command and a correction operation command are each given to a machine tool, the process information being calculated by an influence of dynamics of a member that generates vibration during operation of a drive system and during operation of the machine tool on a machining process of a machining object by a tool; and a process evaluation unit that evaluates the magnitude of the machining error when a plurality of operation commands are used, respectively, based on the plurality of process information, and selects an operation command to be given to the machine tool from among the basic operation command and the corrected operation command.
ADVANTAGEOUS EFFECTS OF INVENTION
According to the present invention, the machining error of the machine tool can be reduced with high accuracy.
Drawings
Fig. 1 is a diagram showing a functional configuration of a processing system according to embodiment 1.
Fig. 2 is a diagram showing an example of the physical structure of the work machine shown in fig. 1.
Fig. 3 is a diagram showing time waveforms of the spindle rotation speed and the feed speed of the basic operation command.
Fig. 4 is a diagram showing a tool and a workpiece when machining is performed using the spindle rotation speed and the feed speed shown in fig. 3.
Fig. 5 is a diagram showing time waveforms of the spindle rotation speed and the feed speed of the correction operation command.
Fig. 6 is a diagram showing a tool and a workpiece when machining is performed using the spindle rotation speed and the feed speed shown in fig. 5.
Fig. 7 is a diagram showing the relationship among the spindle drive system, mechanical dynamics, and machining process shown in fig. 1.
Fig. 8 is a diagram showing the physical quantities shown in fig. 7 together with the physical structure of the work machine.
Fig. 9 is a diagram showing the relationship among the feeder drive system, the mechanical dynamics, and the machining process shown in fig. 1.
Fig. 10 is a diagram showing the physical quantities shown in fig. 9 together with the physical structure of the work machine.
Fig. 11 is a diagram for explaining an example of the spindle drive control model of fig. 1.
Fig. 12 is a diagram for explaining an example of the feed drive control model of fig. 1.
Fig. 13 is a flowchart for explaining the operation of the numerical control apparatus shown in fig. 1.
Fig. 14 is a diagram showing a functional configuration of a processing system according to embodiment 2.
Fig. 15 is a flowchart for explaining the operation of the numerical control apparatus shown in fig. 14.
Fig. 16 is a diagram showing an example of the configuration of a learning device related to the numerical control device shown in fig. 14.
Fig. 17 is a flowchart for explaining a learning process of the learning device shown in fig. 16.
Fig. 18 is a diagram showing an example of the configuration of the estimating device related to the numerical control device shown in fig. 14.
Fig. 19 is a flowchart for explaining the operation of the estimating device shown in fig. 18.
Fig. 20 is a diagram showing a configuration of a processing system according to embodiment 3.
Fig. 21 is a diagram showing dedicated hardware for realizing the functions of the numerical control device, the learning device, and the estimating device according to embodiments 1 to 3.
Fig. 22 is a diagram showing the configuration of a control circuit for realizing the functions of the numerical control device, the learning device, and the estimating device according to embodiments 1 to 3.
Detailed Description
The numerical control device, the machining system, the numerical control method, and the machining method according to the embodiment of the present invention will be described in detail below with reference to the drawings. In the following description, a plurality of components having the same function may be distinguished by a common number followed by a hyphen and a number. In the case where it is not necessary to distinguish between each of a plurality of components having the same function, only common numerals are labeled.
Embodiment 1.
Fig. 1 is a diagram showing a functional configuration of a processing system 1 according to embodiment 1. The machining system 1 has a work machine 2 and a numerical controller 3. The numerical control device 3 controls the work machine 2 by giving an operation command generated based on the command described in the numerical control program 4 to the work machine 2.
The machine tool 2 includes 1 spindle drive system 21, 1 or more feed drive systems 22, a tool 23 for machining the object W, and a table 24 for holding the object W.
The spindle drive system 21 has a spindle motor 211 and a spindle drive mechanism 212 driven by the spindle motor 211. A tool 23 is connected to the spindle drive system 21, and the spindle drive system 21 can rotate the tool 23. The spindle motor 211 or the spindle drive mechanism 212 includes an encoder (not shown) that indicates angle information of the spindle drive system 21.
The feed drive system 22 has a servomotor 221 and a feed drive mechanism 222 driven by the servomotor 221. The feed drive system 22 can change the relative positions of the tool 23 and the object W. The servo motor 221 and the feed drive mechanism 222 have encoders (not shown) that indicate position information of the feed drive system 22. A table 24 or a tool 23 for holding the object W is connected to the feed drive system 22, and the feed drive system 22 can change the relative positions of the tool 23 and the object W by moving the table 24 or the tool 23. In the example shown in fig. 1, the machine tool 2 is provided with the feed drive system 22-1 for moving the tool 23 and the feed drive system 22-2 for moving the table 24, and both the tool 23 and the table 24 are moved, but only the tool 23 may be moved or only the table 24 may be moved. The relative position of the workpiece W held by the tool 23 and the table 24 may be changed. The feed drive system 22 changes the relative positions of the tool 23 and the object W, and thereby the tool 23 cuts the object W along the machining path.
The spindle drive system 21 and the feed drive system 22 are connected to the numerical control device 3, and control the spindle motor 211 and the servo motor 221 by operation commands given from the numerical control device 3. Hereinafter, in the case of referring specifically to both the spindle drive system 21 and the feed drive system 22, the drive system 20 is simply referred to. The series of processes in which the edge of the tool 23 penetrates into the object W to generate chips and form a machined surface is referred to as a machining process M.
Fig. 2 is a diagram showing an example of the physical structure of the work machine 2 shown in fig. 1. The table 24 is in a table shape having a horizontal plane, and is placed on the horizontal plane to face the object W. The spindle drive mechanism 212 is provided such that the tool 23 is positioned above the object W held by the table 24. The spindle motor 211 is disposed adjacent to the spindle drive mechanism 212. The spindle of the spindle drive system 21 having the spindle motor 211 and the spindle drive mechanism 212 is in a direction perpendicular to the horizontal plane of the table 24, and the spindle drive system 21 rotates the tool 23 around the spindle.
The feed drive mechanism 222-1 of the feed drive system 22-1 that moves the cutter 23 is connected to the cutter 23 via a member including the spindle drive mechanism 212 to which the cutter 23 is attached. The servo motor 221-1 of the feed drive system 22-1 is disposed adjacent to the feed drive mechanism 222-1. The feed axis of the feed drive system 22-1 is parallel to the main axis, and the feed drive system 22-1 moves the cutter 23 up and down along the feed axis.
The feed drive mechanism 222-2 of the feed drive system 22-2 for moving the table 24 is connected to the table 24. The servo motor 221-2 of the feed drive system 22-2 is disposed adjacent to the feed drive mechanism 222-2. The feed axis of the feed drive system 22-2 is oriented in the horizontal plane of the table 24, and the feed drive system 22-2 moves the table 24 in the horizontal direction. Further, although only 1 feed drive system 22 for moving the table 24 is described here, the work machine 2 may further include a feed drive system 22 having a feed axis perpendicular to the feed axis of the feed drive system 22-2 and in a direction within the horizontal plane of the table 24.
The physical structure shown here is an example for facilitating the description, and the physical structure of the work machine 2 is not limited to the example shown in fig. 2. For example, the number of the feed drive systems 22 of the work machine 2 may be 1 or 3 or more. The directions of the main shaft and the feed shaft are also an example. The table-like table 24 is an example of a mechanism for holding the object W, and may be configured to hold the object W and control the relative position with respect to the tool 23.
Returning to the description of fig. 1. The numerical control device 3 includes a command generation unit 31, a storage unit 32, a coupling simulation unit 33, a process evaluation unit 34, and a drive control unit 35.
The numerical control program 4 includes a plurality of commands for instructing movement of the main shaft and the feed shaft of the machine tool 2. The instruction included in the numerical control program 4 is, for example, an instruction to specify a path along which the tool 23 moves by a relative position with respect to the object W. The command for specifying the path of the cutter 23 includes a plurality of position commands for specifying the position on the path. The numerical control program 4 also includes a spindle rotation speed command indicating the rotation speed of the spindle at the position indicated by each position command, and a feed speed command indicating the movement speed of the feed shaft. The nc program 4 may be provided to the nc apparatus 3 from the outside of the nc apparatus 3, or the nc apparatus 3 may be held inside.
The command generating unit 31 analyzes the command described in the numerical control program 4, and generates an operation command at a time point to be given to the machine tool 2 for controlling the machine tool 2. The command generating unit 31 generates a basic operation command for directly executing the work machine 2 without correcting the command described in the numerical control program 4, and a corrected operation command for correcting the basic operation command. The instruction generation unit 31 can generate 1 or more correction operation instructions. The correction operation command may be an operation command in which at least one of the feed amount of the feed shaft and the cut thickness of the object W is changed, as in the basic operation command, in a path for moving the tool 23 relative to the object W. The feed amount is a feed amount per unit process, and is, for example, a feed amount per 1 edge of the cutter 23. In this case, in the correction operation command, at least one of the spindle rotation speed command and the feed speed command at the moment when the plurality of blade edges of the tool 23 feed the object W is different for each tool blade edge. The spindle rotation speed command and the feed speed command at each time are modulated in accordance with the respective angles of the plurality of blade edges of the tool 23 and the relative positions between the tool 23 and the object W. The command generating unit 31 can generate, as the correction operation command, an operation command obtained by changing at least one of the spindle rotation speed command and the feed speed command at each time of the basic operation command in accordance with the feed amount per 1 edge of each edge of the tool 23 or the cutting thickness of the object W set in the command generating unit 31 or outside. The command generating unit 31 outputs the generated basic operation command and the generated corrected operation command to the coupling simulation unit 33 and the drive control unit 35, respectively.
Fig. 3 is a diagram showing time waveforms of the spindle rotation speed and the feed speed of the basic operation command. Here, for simplicity, the case will be described in which the positions P1 and P2 at 2 points are specified in the numerical control program 4, and the spindle rotation speed and the feed speed of a constant value are specified for the command trajectory between the positions P1 and P2. Fig. 3 shows the spindle rotation speed and the feed speed with respect to the commanded trajectory between positions P1 and P2. The basic operation command is an operation command for directly executing the machine tool 2 without modifying the command described in the numerical control program 4. Therefore, as described in the numerical control program 4, the basic operation command specifies the spindle rotation speed and the feed speed for the command trajectory between the positions P1 and P2 to be constant.
Fig. 4 is a diagram showing the tool 23 and the object W when processing is performed using the spindle rotation speed and the feed speed shown in fig. 3. The tool 23 moves from the position P1 toward the position P2 while rotating in the rotation direction R1, and if the tool contacts the object W, the edge of the tool 23 cuts the object W. In the basic operation command, since the spindle rotation speed and the feed speed are constant, the feed amount c per 1 blade becomes constant. In this case, the cutting area A1 per 1 edge becomes constant.
Fig. 5 is a diagram showing time waveforms of the spindle rotation speed and the feed speed of the correction operation command. Here, the command trajectory of the basic operation command described in fig. 3 and 4 is kept unchanged, and the spindle rotation speed and the feed speed are varied in a sine wave shape with reference to a constant value described in the numerical control program 4.
Fig. 6 is a diagram showing the tool 23 and the object W when processing is performed using the spindle rotation speed and the feed speed shown in fig. 5. The tool 23 moves from the position P1 toward the position P2 while rotating in the rotation direction R1, and if the tool contacts the object W, the edge of the tool 23 cuts the object W. In the correction operation command, the spindle rotation speed and the feed speed are always changed. Therefore, the feed amount c per 1 blade changes with time, and as a result, the cutting area A1 per 1 blade also changes for each 1 blade.
In the example of fig. 5, the command generating unit 31 generates the correction operation command by changing the spindle rotation speed and the feed speed to a sinusoidal fluctuation pattern based on the feed amount c per 1 blade or the cutting thickness of the object W based on the basic operation command. However, the variation pattern to be used is not limited to a sine wave, and various variation patterns including a triangular wave shape and a random wave shape may be used. The command generating unit 31 can generate the correction operation command by superimposing a fluctuation of a predetermined profile on at least one of the spindle rotation speed and the feed speed of the basic operation command. The command generating unit 31 can hold information indicating a profile superimposed on the fluctuation of the basic operation command in advance. In the above description, the instruction generating unit 31 has been described as generating 1 correction operation instruction based on 1 basic operation instruction, but the instruction generating unit 31 may generate a plurality of correction operation instructions based on 1 basic operation instruction.
Returning to the description of fig. 1. The storage unit 32 stores a machining process model 321, a dynamics model 322, a spindle drive control model 323, a feed drive control model 324, and machining condition information 325. The storage unit 32 can output the stored information to the coupling simulation unit 33. The machining condition information 325 includes, for example, tool shape information including the number of edges of the tool 23, the tool diameter, and the torsion angle, and the feed amount in the case where the tool 23 is used. Details of the machining process model 321, the dynamics model 322, the spindle drive control model 323, and the feed drive control model 324 are described later.
Since the cutting process performed by the machine tool 2 is a physical phenomenon in which the machining process M and the mechanical dynamics affect each other, it is preferable to perform analysis in which both the machining process and the mechanical dynamics are combined in order to manage or control the machining state. The machining process herein means a series of processes in which the cutting edge of the tool 23 penetrates into the object W to generate chips and form a machined surface. The mechanical dynamics represent the dynamic actions of the components that vibrate due to the vibration sources inside and outside the work machine 2. The component referred to herein is a component constituting the machine tool 2, and may further include the tool 23 and the object W.
The drive system 20 is controlled by the numerical control device 3, and thereby moves the tool 23 while rotating and passing through a predetermined path with respect to the object W. During cutting of the object W by the tool 23, the cutting force F c generated between the tool 23 and the object W passes through the member and is transmitted to the feed drive system 22 as the disturbance force F d and is transmitted to the spindle drive system 21 as the disturbance torque T d. Since the disturbance force F d is applied to the feed drive system 22, the position of the feed drive system 22 changes according to the amplitude and frequency of the disturbance force F d when the position of the tool 23 in the case where the object W is not cut is used as a reference. Similarly, if the disturbance torque T d is applied to the spindle drive system 21, the rotation angle of the spindle drive system 21 varies with respect to the rotation angle when the tool 23 is not cutting the object W.
The above-described relationship will be described with reference to the drawings. Fig. 7 is a diagram showing the relationship among the spindle drive system 21, mechanical dynamics, and machining process M shown in fig. 1. Fig. 8 is a diagram showing the physical quantities shown in fig. 7 together with the physical structure of the work machine 2. When the numerical control device 3 gives an operation command to the spindle drive system 21, the spindle motor 211 drives the spindle drive mechanism 212, and the member of the machine tool 2 including the tool 23 rotates to machine the object W. Here, if the spindle drive system 21 is controlled to the spindle drive system angle θ1 based on the operation command, the actual angle of the tool 23 is affected by the tool-side mechanical dynamics MD1, and becomes the tool angle θ2. The tool 23 penetrates into the object W to perform a series of machining processes M for forming a machined surface while generating chips. The cutting torque T c generated at this time is influenced by the tool-side mechanical dynamics MD1 through the member, and is fed back to the spindle drive system 21 as a disturbance torque T d. The work machine 2 outputs a feedback signal to the numerical control device 3. When the state of the spindle drive system 21 to which the disturbance torque T d is applied is different from the operation command, the numerical control device 3 changes the operation command based on the feedback signal transmitted from the spindle drive system 21.
Fig. 9 is a diagram showing the relationship among the feeder driving system 22-2, mechanical dynamics, and the machining process M shown in fig. 1. Fig. 10 is a diagram showing the physical quantities shown in fig. 9 together with the physical structure of the work machine 2. If the numerical control device 3 gives an operation command to the feed drive system 22-2, the processing object W is processed by the relative movement of the tool 23 and the processing object W. At this time, the servo motor 221-2 of the feed drive system 22-2 drives the feed drive mechanism 222-2 based on the operation command, and as a result, the drive system displacement r1 is generated in the table 24. The actual displacement generated in the object W is affected by the object-side mechanical dynamics MD2 when the drive system displacement r1 is generated, and becomes the member displacement r2. The cutting force F c generated at this time passes through the member to be fed back to the feed drive system 22-2 as the disturbance force F d. When the state of the feed drive system 22-2 receiving the disturbance force F d is different from the operation command, the numerical control device 3 changes the operation command based on the feedback signal transmitted from the feed drive system 22-2.
In order to explain the above, the spindle drive system 21 and the feed drive system 22 are described separately by using fig. 7 to 10, but the displacement and the force transmission during the machining are performed simultaneously in the spindle drive system 21 and the feed drive system 22.
As described above, in the cutting process, the system in which the machining process M, the mechanical dynamics, and the drive system 20 are coupled is configured, and the numerical control device 3 participates in the machining process M via the drive system 20 and the mechanical dynamics. In addition, during the cutting process between the tool 23 and the object W, the machining point where the cutting force F c is generated disappears as the chip is generated, and therefore, the sensor cannot be provided and the cutting force F c cannot be directly detected. Therefore, in order to accurately evaluate the cutting process including the movement of the tool 23 and the object W, it is necessary to simulate the operation of the spindle drive system 21 and the feed drive system 22 in addition to the machining process M and the mechanical dynamics.
Next, specific examples of the machining process model 321, the dynamics model 322, the spindle drive control model 323, and the feed drive control model 324 stored in the storage unit 32 will be described. These models are used when the coupling simulation unit 33 described later performs simulation.
The machining process model 321 represents machining characteristics between the tool 23 and the object W. More specifically, the machining process model 321 is a mathematical model that expresses the cutting force F c generated in accordance with the positional relationship between the tool 23 and the object W. The following expression (1) is an example of an expression for expressing the cutting force F c during contact between the edge of the tool 23 and the object W. The relative cutting resistance K c, the edge force coefficient K e, the minute thickness Deltaa of the cross section of the tool 23, the cutting thickness h of the object W, and the rotation angle of the tool 23 are used in the calculation formula (1)And the time t, the minute cutting force Δf c for each section of the tool 23 is shown. The total cutting force F c generated by the feeding of the tool 23 can be calculated by adding the minute cutting force Δf c shown in expression (1) in the axial direction of the tool 23. The cut-off thickness h of the object W is the distance between the radially front machining surface and the radially rear machining surface of the tool 23. Equation (1) shows that the cutting force F c can be calculated by the sum of a force proportional to the cutting thickness h and a certain amount of force called edge force.
[ 1 ]
The cut-off thickness h can be expressed by the following expression (2). The cutting thickness h is represented by a component indicating a nominal cutting thickness determined by the feed amount c of the cutter 23 per 1 blade, a component indicating the relative vibration of the cutter 23 and the object W, and a component indicating the increase or decrease in cutting thickness due to the difference in the rotation radius of each blade when the cutter 23 has a plurality of blades. The component of the vibration indicating the relative movement between the tool 23 and the object W is represented by the difference between the radial component u r of the tool 23 which is the relative displacement between the tool 23 and the object W at the instant of the current cutting of the machined surface and the radial component W r of the relative displacement between the tool 23 and the object W transferred to the previous machined surface. The component indicating the increase or decrease in the cutting thickness due to the difference in the turning radius of each blade edge is indicated by the turning radius correction amount Δe of the blade edge of the cutter 23.
[ 2 ]
Equation (1) is an example of the process model 321, and the process model 321 is not limited to the above example. For example, a model may be used to calculate the cutting force F c using voxels representing the shape of the tool 23 and the shape of the object W.
The dynamic model 322 represents the dynamic characteristics of a member that vibrates during operation of the work machine 2. Specifically, the kinetic model 322 is a mathematical model that dynamically generates displacement of a component when dynamic forces are applied to the component. For example, the behavior of the object W when the cutting force F c is applied to the object W connected to the drive system 20 can be expressed by the following expression (3).
[ 3 ] Of the following
Equation (3) is an example of an equation that expresses vibration of the object W. The cutting force F c generated between the tool 23 and the object W is expressed by using the relative displacement u between the tool 23 and the object W, the relative displacement v of the drive system 20, the equivalent mass m of the object W, the equivalent viscosity coefficient C of the object W, and the equivalent spring constant K of the object W. Equation (3) shows mechanical dynamics in which the cutting force F c is transmitted to the drive system 20 as the disturbance force F d through the object W.
The kinetic model 322 is not limited to equation (3). For example, the shape of the object W may be expressed by voxels, and displacement at the time of vibration of the member may be calculated by FEM (FINITE ELEMENT Method) analysis. The dynamic model 322 described here only shows the vibration of the object W, but the dynamic model 322 may show the vibration of the tool 23 or another member instead of the object W. Alternatively, the dynamic model 322 may exhibit vibration of both the tool 23 and the object W.
The spindle drive control model 323 is a mathematical model that represents the spindle drive system 21 of the machine tool 2 and a spindle drive controller that is provided in the drive control unit 35 of the numerical control device 3 and controls the spindle drive system 21. Fig. 11 is a diagram for explaining an example of the spindle drive control model 323 of fig. 1. The spindle drive control model 323 is a mathematical model in which, when a spindle rotation angle command is given, the position and speed of the spindle drive system 21 are controlled by a position controller and a speed controller provided in a spindle drive controller in a state where disturbance torque T d caused by cutting torque T c is transmitted to the spindle drive system 21. The mathematical model outputs the actual rotation angle θ of the spindle if a spindle rotation angle command θ r is input to the controller. Here, K pp1、Kvp1、Kvi1 is a control gain, which is a proportional gain K pp1 for position control, a proportional gain K vp1 for speed control, and an integral gain K vi1.P1(s) for speed control, respectively, are transfer functions of torque to position from the spindle drive system 21 as a whole, and s is a complex number. P 1(s) can be identified by known system identification methods based on the actual response of the spindle drive system 21. In this case, the spindle drive system 21 is modeled as a 1-inertia system, but the spindle drive system 21 may be modeled as a multi-inertia system. In addition, a feedforward controller may be added to the spindle drive controller.
The feed drive control model 324 is a mathematical model that indicates the feed drive system 22 of the machine tool 2 and the feed drive controller that is present in the drive control unit 35 of the numerical control device 3. Fig. 12 is a diagram for explaining an example of the feed drive control model 324 of fig. 1. The feed drive control model 324 is a mathematical model in which, when a feed drive system position command is given, the position and speed of the feed drive system 22 are controlled by a position controller and a speed controller included in the feed drive controller in a state where the disturbance force F d caused by the cutting force F c is transmitted to the spindle drive system 21. The mathematical model outputs the actual position x of the feed drive system if the feed drive system position command x r is input. Here, K pp2、Kvp2、Kvi2 is a control gain, which is a proportional gain K pp2 for position control, a proportional gain K vp2 for speed control, and an integral gain K vi2.P2(s) for speed control, respectively, are transfer functions of force to position from the entire feed drive system 22, and s is a complex number. P 2(s) can be identified by known system identification methods based on the actual response of the feeder drive system 22. In addition, here, the feed drive system 22 is modeled as a 1-inertia system, but the feed drive system 22 may also be modeled as a multi-inertia system. In addition, a feedforward controller may be added to the feed drive controller.
The coupling simulation unit 33 simulates machining when a plurality of operation commands output from the command generation unit 31 are each given to the machine tool 2, and calculates process information indicating the simulation result. The process information includes parameters that can compare machining errors, including, for example, a cutting thickness of the object W, a cutting force F c, an interference force F d, and the like. Here, the cutting thickness of the object W is, for example, the cutting thickness of the object W per 1 edge of the cutter 23. The coupling simulation unit 33 can simulate the machining performed by the machine tool 2 based on the influence of the dynamics of the components that generate vibrations during the operation of the machine tool 2 and the operation of the drive system 20 including the spindle drive system 21 and the feed drive system 22 on the machining process M. The coupling simulation unit 33 simulates the number of operation instructions generated by the instruction generation unit 31, and generates process information indicating the simulation result from the number of operation instructions. The coupling simulation unit 33 outputs the generated plurality of pieces of process information to the process evaluation unit 34.
The coupling simulation unit 33 simulates the machining performed by the machine tool 2 by applying the operation command output by the command generation unit 31 to the machining process model 321, the dynamics model 322, the spindle drive control model 323, and the feed drive control model 324 under the specified machining conditions, and calculates process information indicating the simulation result. In this case, the coupling simulation unit 33 can use the machining process model 321, the dynamics model 322, the spindle drive control model 323, the feed drive control model 324, and the machining condition information 325 stored in the storage unit 32. When the machining condition information 325 stored in the storage unit 32 is used, the specified machining condition is the machining condition indicated by the machining condition information 325.
The coupling simulation unit 33 performs simulation of the machining process M between the tool 23 and the object W, mechanical dynamics of the components of the machine tool 2, and the operation of the spindle drive system 21 and the operation coupling of the feed drive system 22. Based on the relationships shown in fig. 7 to 10, the coupling simulation unit 33 simulates the coupling model obtained by combining the respective models of the machining process model 321, the dynamics model 322, the spindle drive control model 323, and the feed drive control model 324, and performs coupling simulation for calculating the time series information and the frequency component information by applying the drive signal, the spindle drive system angle θ1, the drive system displacement r1, the tool angle θ2, the member displacement r2 of the feed system, the cutting thickness h of the workpiece, the cutting torque T c, the cutting force F c, the disturbance torque T d, the disturbance force F d, and the feedback signal under the machining conditions described by the machining condition information 325.
The process evaluation unit 34 evaluates the magnitude of the machining error when a plurality of operation commands are used, based on the plurality of process information output from the coupling simulation unit 33, and selects an operation command to be given to the machine tool 2 from among the basic operation command and the corrected operation command generated by the command generation unit 31. The process evaluation unit 34 outputs a command selection signal indicating the selected operation command to the drive control unit 35.
An example of the evaluation method in the process evaluation unit 34 will be described below. The process evaluation unit 34 can evaluate the magnitude of the machining error based on the time variation of the cutting thickness h of the object W. The process evaluation unit 34 evaluates that the magnitude of the machining error is smaller as the increase in the cutting thickness h of the object W is smaller. The process evaluation unit 34 can select an operation command that minimizes the increase in the cutting thickness h as an operation command to be given to the work machine 2. The cutting thickness h represents the vibration between the tools 23 and the object W. If vibration called chatter occurs between the tool 23 and the object W, the amplitude increases with the passage of time, and the machining error is deteriorated. Therefore, by evaluating the temporal change in the cutting thickness h, the process evaluation unit 34 can select an operation command that minimizes the vibration between the tool 23 and the object W. The operation command for minimizing the vibration between the tool 23 and the object W minimizes the machining error caused by the vibration between the tool 23 and the object W.
The process evaluation unit 34 can evaluate the magnitude of the machining error based on the maximum amplitude of the disturbance force F d or the disturbance torque T d when each operation command is executed. The process evaluation unit 34 evaluates that the magnitude of the machining error is smaller as the maximum amplitude of the disturbance force F d or the disturbance torque T d is smaller. The process evaluation unit 34 can select an operation command having the smallest maximum amplitude as an operation command to be given to the work machine 2. The smaller the maximum amplitude of the disturbance force F d or the disturbance torque T d, the smaller the vibration of the drive system 20 caused by the disturbance force F d or the disturbance torque T d becomes. Therefore, by selecting an operation command in which the maximum amplitude of the disturbance force F d or the disturbance torque T d is minimized, machining errors due to vibration of the drive system 20 can be minimized.
The process evaluation unit 34 can compare the time waveform of the process information calculated by the coupling simulation unit 33 with a target profile set in advance, and evaluate the magnitude of the machining error based on the deviation from the target profile. The target profile is a profile having a machining error of less than or equal to an allowable value, and is set in advance in the process evaluation unit 34, for example. The process evaluation unit 34 evaluates the process error as smaller as the deviation from the target profile is smaller. The process evaluation unit 34 may evaluate the deviation from the target contour based on a loss function such as a square error, or may evaluate the deviation from the target contour based on a machine learning method such as pattern matching. The process evaluation unit 34 can minimize the machining error by selecting the operation command that minimizes the deviation from the target profile.
The process evaluation unit 34 may evaluate the magnitude of the machining error by using any 1 of the above-described plurality of evaluation methods, or may use a combination of the above-described plurality of evaluation methods.
The drive control unit 35 controls the drive system 20 of the work machine 2 based on the operation command indicated by the command selection signal output from the course evaluation unit 34 among the plurality of operation commands generated by the command generation unit 31. The drive control section 35 has a spindle drive controller for controlling the spindle drive system 21 and a feed drive controller for controlling the feed drive system 22. The spindle drive controller outputs a command to the spindle motor 211 so that the position and speed of the spindle drive system 21 become the amounts specified by the operation command while monitoring the signal of the encoder provided in the spindle drive system 21. The feed drive controller monitors the signal of the encoder included in the feed drive system 22 and outputs a command to the servo motor 221 so that the position and speed of the feed drive system 22 become the amounts specified by the operation command.
Fig. 13 is a flowchart for explaining the operation of the numerical control device 3 shown in fig. 1. When the machining system 1 starts to operate, the instruction generating unit 31 of the numerical control device 3 reads the numerical control program 4, analyzes the read numerical control program 4, and generates a basic operation instruction for causing the machine tool 2 to execute an instruction described in the numerical control program 4 and a corrected operation instruction after correcting the basic operation instruction (step S101). The command generating unit 31 outputs the generated operation commands to the coupling simulation unit 33 if 1 basic operation command and 1 pattern or more of the corrected operation commands are generated.
The coupling simulation unit 33 executes coupling simulation for each operation instruction output from the instruction generation unit 31, and calculates a plurality of pieces of process information (step S102). The coupling simulation unit 33 outputs the calculated process information to the process evaluation unit 34.
The process evaluation unit 34 compares and evaluates the plurality of process information, evaluates the magnitude of the machining error when each operation command is used, and selects an operation command to be given to the machine tool 2 from among the basic operation command and the corrected operation command (step S103). The process evaluation unit 34 outputs a command selection signal indicating the selected operation command to the drive control unit 35.
The drive control unit 35 controls the operation of the work machine 2 using the selected operation command based on the command selection signal output from the process evaluation unit 34 (step S104). The instruction generation unit 31 determines whether or not reading of all instructions described in the numerical control program 4 is completed (step S105). When the reading is not completed (step S105: no), the instruction generating unit 31 repeats the processing from step S101. When the reading is completed (step S105: yes), the processing system 1 ends the operation.
As described above, in the machining system 1 according to embodiment 1, the numerical control device 3 calculates process information indicating a result obtained by simulating machining when a basic operation command generated based on a numerical control program and a corrected operation command obtained by correcting the basic operation command are applied to the machine tool 2, the process information indicating an influence of the dynamics of the member that generates vibration during the operation of the machine tool 2 on the machining process of the object W by the tool 23, and selects the operation command applied to the machine tool 2 based on the evaluation result of the process information. Therefore, even when machining errors occur due to the mutual influence of machining processes, the operation of the drive system 20, and mechanical dynamics of the members that vibrate during the operation of the machine tool 2, the numerical control device 3 can reduce the machining errors.
The coupling simulation unit 33 calculates process information when an operation command is given to the machining process model 321 indicating the machining characteristics between the tool 23 and the workpiece W, the dynamics model 322 indicating the dynamic characteristics of the member that vibrates during the operation of the machine tool 2, the spindle drive control model 323 indicating the spindle drive system 21 and the spindle drive controller that controls the spindle drive system 21, and the feed drive control model 324 indicating the feed drive system 22 and the feed drive controller that controls the feed drive system 22. By performing the coupling simulation using the mathematical model, the influence of the operation command on the machining process M via the drive system 20 and the mechanical dynamics can be accurately evaluated.
In embodiment 1, the storage unit 32 for storing the machining process model 321, the dynamics model 322, the spindle drive control model 323, the feed drive control model 324, and the machining condition information 325 indicating the machining conditions is provided in the numerical control device 3, but the storage unit 32 may be provided outside the numerical control device 3.
The command generating unit 31 can generate, as the correction operation command, a command in which the relative path of movement of the tool 23 with respect to the object W is the same as the basic operation command, and the feeding amount per 1 blade or the cutting thickness h of the object W is changed. For example, the command generating unit 31 may set a command to change at least one of the spindle rotation speed and the feed speed of the basic operation command with respect to the feed amount per 1 blade or the cutting thickness h of the object W as the correction operation command. Specifically, the command generating unit 31 can superimpose a predetermined profile fluctuation on at least one of the spindle rotation speed and the feed speed of the basic operation command, thereby generating the correction operation command. By generating the correction operation command in the above manner, the operation command for reducing the machining error can be generated without changing the shape of the object W.
The storage unit 32 may store different models and processing conditions according to the processing steps described in the numerical control program 4. The coupling simulation unit 33 can simulate the machining process using different models and machining conditions. In embodiment 1, the work machine 2 is provided with 1 spindle drive system 21 and 1 or more feed drive systems 22, but the work machine 2 may be provided with a plurality of spindle drive systems 21. In the case where the machine tool 2 includes a plurality of spindle drive systems 21, the operations shown in fig. 13 may be performed in the same manner.
In embodiment 1, the machine tool 2 in which the tool 23 is connected to the spindle drive system 21 and the tool 23 rotates as in the machining center, for example, but the machine tool 2 may be configured such that the machining object W is connected to the spindle drive system 21 and the machining object W rotates as in the NC (Numerically Control) lathe, for example. In this case, the command generating unit 31 can select the operation command for reducing the machining error from a plurality of operation commands without changing the path specified by the numerical control program 4 by changing the feed amount per 1 blade to the feed amount per 1 rotation of the spindle.
Embodiment 2.
Fig. 14 is a diagram showing a functional configuration of a processing system 1a according to embodiment 2. The same reference numerals as those of embodiment 1 are given to functional structures having the same functions as those of embodiment 1, and redundant description thereof is omitted. The following mainly describes differences from embodiment 1. The machining system 1a is different from the machining system 1 in that an operation instruction is generated based on the simulation result.
The machining system 1a includes a machine tool 2 and a numerical controller 3a. The numerical control device 3a controls the machine tool 2 based on the instruction described in the numerical control program 4, similarly to the numerical control device 3. The numerical control device 3a includes a command generating unit 31a, a storage unit 32a, a coupling simulation unit 33a, a process evaluation unit 34, and a drive control unit 35.
The command generating unit 31a can use the process information output from the coupling simulation unit 33a when generating the correction operation command. The command generation unit 31a can set the operation command after the basic operation command is corrected based on the process information as the corrected operation command. At this time, the command generating unit 31a can use the machining process model 321, the dynamics model 322, the spindle drive control model 323, the feed drive control model 324, and the machining condition information 325 stored in the storage unit 32 a. Specifically, the command generating unit 31a adds a variation compensating for the amplitude or phase of the dynamic vibration component superimposed on the cut thickness of the object W included in the process information to the basic operation command, and generates the correction operation command. The dynamic vibration component corresponds to the 2 nd item on the right of the above expression (2). The command generating unit 31a can add a variation in compensating the amplitude or phase of the vibration component to the basic operation command by using a band-stop filter for attenuating the amplitude of the dynamic vibration component superimposed on the cut thickness of the object W, or by using a phase compensation filter for compensating the phase delay of the vibration component with reference to the timing of cutting by the edge of the tool 23.
The storage unit 32a stores the machining process model 321, the dynamics model 322, the spindle drive control model 323, the feed drive control model 324, and the machining condition information 325, and outputs the stored information to the coupling simulation unit 33a, similarly to the storage unit 32. The storage unit 32a can further output the information stored in the instruction generation unit 31 a.
The coupling simulation unit 33a calculates process information indicating a result of simulation of machining in a case where the basic operation command and the correction operation command are respectively given to the machine tool 2, similarly to the coupling simulation unit 33. The coupling simulation unit 33a outputs the calculated process information to the process evaluation unit 34 and also outputs the calculated process information to the instruction generation unit 31a.
Fig. 15 is a flowchart for explaining the operation of the numerical control device 3a shown in fig. 14. When the machining system 1a starts to operate, the instruction generating unit 31a of the numerical control device 3a reads the numerical control program 4, analyzes the read numerical control program 4, and generates a basic operation instruction for causing the machine tool 2 to execute an instruction described in the numerical control program 4 (step S201). The command generating unit 31a outputs the generated basic operation command to the coupling simulation unit 33a.
The coupling simulation unit 33a generates process information by performing coupling simulation when the work machine 2 executes the basic operation command outputted from the command generation unit 31a (step S202). The coupling simulation unit 33a outputs the generated process information to the process evaluation unit 34 and the instruction generation unit 31a, respectively.
The command generating unit 31a corrects the basic operation command based on the process information output as a result of executing step S202, and generates a corrected operation command (step S203). The command generating unit 31a outputs the generated correction operation command to the coupling simulation unit 33a.
The coupling simulation unit 33a generates process information by performing coupling simulation when the work machine 2 executes the correction operation command outputted from the command generation unit 31a (step S204). The coupling simulation unit 33a outputs the generated process information to the process evaluation unit 34 and the instruction generation unit 31a, respectively.
The process evaluation unit 34 compares and evaluates the plurality of process information, evaluates the magnitude of the machining error when each operation command is used, and selects an operation command to be given to the machine tool 2 from among the basic operation command and the corrected operation command (step S205). The process evaluation unit 34 outputs a command selection signal indicating the selected operation command to the drive control unit 35.
The drive control unit 35 controls the operation of the work machine 2 using the selected operation command based on the command selection signal output from the process evaluation unit 34 (step S206). The instruction generation unit 31a determines whether or not reading of all instructions described in the numerical control program 4 is completed (step S207). When the reading is not completed (step S207: no), the instruction generating unit 31a repeats the processing from step S201. When the reading is completed (Yes in step S207), the processing system 1a ends the operation.
In the above example, the instruction generation unit 31a generates the correction operation instruction based on the process information indicating the simulation result in the case where the basic operation instruction is given to the work machine 2, but may further generate the correction operation instruction based on the process information indicating the simulation result in the case where the correction operation instruction is given to the work machine 2. In this case, a method of searching for a correction operation command capable of reducing the vibration of the cut thickness of the object W using a machine learning method using the amplitude or phase of the vibration component of the cut thickness of the object W as an evaluation value can be employed.
Fig. 16 is a diagram showing an example of the configuration of the learning device 50 related to the numerical control device 3a shown in fig. 14. The learning device 50 may be provided in the numerical control device 3a shown in fig. 14, or may be an information processing device different from the numerical control device 3 a. The learning device 50 includes a learning data acquisition unit 51 and a model generation unit 52.
The learning data acquisition unit 51 acquires, as learning data, the operation command generated by the command generation unit 31a and the process information corresponding to the operation command, that is, the process information indicating the simulation result in the case where the operation command is given to the work machine 2. The learning data acquisition unit 51 can output the acquired learning data to the model generation unit 52. The learning data acquisition unit 51 may acquire all or a part of the process information. For example, the learning data acquisition unit 51 may acquire, as the learning data, a parameter indicating the magnitude of the machining error among the process information. For example, the learning data acquisition unit 51 may acquire, as the learning data, the cutting thickness of the object W, or the amplitude or phase of the vibration component of the cutting thickness of the object W.
The model generation unit 52 learns the new corrected operation instruction based on learning data including the operation instruction and process information indicating a simulation result in the case where the operation instruction is given to the work machine 2. That is, the model generation unit 52 generates a trained model for estimating a new correction operation command from the process information of the numerical control device 3 a. The model generation unit 52 outputs the generated trained model to the trained model storage unit 53.
The learning algorithm used by the model generation unit 52 may be a known algorithm such as teacher learning, non-teacher learning, or reinforcement learning (Reinforcement Learning). As an example, a case where reinforcement learning is applied will be described. In reinforcement learning, an agent, which is a subject of action within an environment, observes parameters representing the environment in the current state and determines actions to be taken. The environment is dynamically changed by the actions of the agent, and the agent is given a return in response to the change in the environment. The agent repeatedly performs this operation, and learns the action policy that is most reported after a series of actions. As typical methods of reinforcement Learning, Q Learning (Q-Learning) and TD Learning (TD-Learning) are known. For example, in the case of Q learning, a general update expression of the action cost function Q (s, a) is expressed by the following expression (4).
[ 4 ] Of the following
In equation (4), s t represents the state of the environment at time t, and a t represents the action at time t. By action a t, the state change s t+1.rt+1 represents the return by the change of its state, γ represents the discount rate, and α represents the learning coefficient. In addition, gamma is a value in the range of 0 < gamma.ltoreq.1, and alpha is a value in the range of 0 < alpha.ltoreq.1. The corrected operation instruction becomes the action a t, the process information becomes the state s t, and the learning device 50 learns the best action a t in the state at the time t.
The update expressed by the expression (4) is to increase the action value Q if the action value Q of the action a having the highest Q value at the time t+1 is larger than the action value Q of the action a executed at the time t, and to decrease the action value Q in the opposite case. In other words, the action cost function Q (S, a) is updated so that the action cost Q of the action a at the time t is close to the best action cost at the time t+1. Thus, the best action value Q in an environment is propagated in turn as the action value Q in its previous environment.
As described above, when a trained model is generated by reinforcement learning, the model generation unit 52 includes the return calculation unit 54 and the function update unit 55.
The return calculation unit 54 calculates a return based on the operation instruction and the process information. The return calculation unit 54 calculates the return r based on the return reference D including the return increase reference D1 and the return decrease reference D2. For example, the reporting criterion D is determined based on the magnitude of the machining error shown in the process information. As a parameter indicating the magnitude of the machining error, for example, the amplitude of the vibration component of the cut thickness of the object W is used. For example, the return increase criterion D1 may be set such that the amplitude of the vibration component of the cutting thickness of the object W is smaller than the threshold value, and the return decrease criterion D2 may be set such that the amplitude of the vibration component of the cutting thickness of the object W is larger than or equal to the threshold value. The return calculation unit 54 increases the return r by giving a return of "+1", for example, when the return increase criterion D1 is satisfied, and decreases the return r by giving a return of "+1", for example, when the return decrease criterion D2 is satisfied. The return calculation unit 54 outputs the calculated return r to the function update unit 55. As another example, as a parameter indicating the magnitude of the machining error, the phase of the vibration component of the cut thickness of the object W may be used in addition to the amplitude of the vibration component of the chip thickness. Here, the phase of the vibration component of the cutting thickness is a phase of vibration superimposed on the chip shape at the moment when cutting of the object W starts at the edge of the cutter 23. In this case, the return increase criterion D1 may be set to a value within a predetermined range of the phase of the vibration component of the cutting thickness of the object W, and the return decrease criterion D2 may be set to a value outside the range of the phase of the vibration component of the cutting thickness of the object W.
The function updating unit 55 updates the function for determining the correction operation instruction in accordance with the return r calculated by the return calculating unit 54, and outputs the updated function to the trained model storage unit 53. For example, in the case of Q learning, the action cost function Q (s t,at) expressed by the expression (4) is used as a function for calculating the corrected operation instruction.
The above learning is repeatedly performed. The trained model storage unit 53 stores the action cost function Q (s t,at), that is, the trained model, updated by the function updating unit 55.
Next, a process of learning by the learning device 50 will be described with reference to fig. 17. Fig. 17 is a flowchart for explaining the learning process of the learning device 50 shown in fig. 16.
The learning data acquisition unit 51 acquires, as learning data, the operation command generated by the command generation unit 31a and the process information indicating the simulation result when the operation command is given to the work machine 2 (step S301).
The model generating unit 52 calculates the return r based on the operation instruction and the process information included in the learning data acquired by the learning data acquiring unit 51 (step S302). Specifically, the report calculating unit 54 acquires the operation instruction and the process information, and determines whether to increase or decrease the report r based on the predetermined report criterion D (step S303).
When determining that the return r is to be increased (step S303: increase), the return calculation unit 54 increases the return r (step S304). When determining that the return r is to be reduced (step S303: reduced), the return calculation unit 54 reduces the return r (step S305).
The function updating unit 55 updates the action cost function Q stored in the trained pattern storage unit 53 (S t,at) based on the return r calculated by the return calculation unit 54 (step S306).
The learning device 50 repeatedly executes the processing of steps S301 to S306 described above, and stores the generated action cost function Q (S t,at) as a trained model.
In fig. 16, the trained model storage unit 53 is provided outside the learning device 50, but the learning device 50 may have the trained model storage unit 53 inside. In the case where the learning device 50 is provided in the numerical control device 3a, the trained model storage unit 53 may be provided in the same storage device as the storage unit 32a or may be provided in a different storage device.
Fig. 18 is a diagram showing an example of the configuration of the estimating device 60 related to the numerical control device 3a shown in fig. 14. The estimation device 60 includes a data acquisition unit 61 and an estimation unit 62. The estimating device 60 may be provided in the numerical control device 3a, or may be an information processing device different from the numerical control device 3 a. The estimating device 60 is provided in the command generating unit 31a of the numerical control device 3a, for example.
The data acquisition unit 61 acquires the process information output from the coupling simulation unit 33 a. The data acquisition unit 61 outputs the acquired data to the estimation unit 62.
The estimating unit 62 estimates a new correction operation command based on the process information acquired by the data acquiring unit 61, using the trained model stored in the trained model storage unit 53. That is, the estimating unit 62 can estimate the correction operation command suitable for the process information by inputting the process information output from the data acquiring unit 61 into the trained model.
In the above description, the estimation device 60 outputs the correction operation command using a trained model obtained by performing machine learning using the data acquired from the numerical control device 3a, but the correction operation command may be output based on a trained model acquired from another numerical control device 3 a.
Fig. 19 is a flowchart for explaining the operation of the estimating device 60 shown in fig. 18. The data acquisition unit 61 of the estimation device 60 acquires the process information as estimation data (step S401), and outputs the acquired data to the estimation unit 62.
The estimating unit 62 inputs the process information, which is the data for estimation obtained in step S401, to the trained model stored in the trained model storage unit 53 (step S402). The estimating unit 62 outputs a corrected operation command, which is a result of inputting the process information into the trained model (step S403). The command generating unit 31a of the numerical control device 3a acquires the correction operation command outputted from the estimating unit 62, and outputs the acquired correction operation command to the coupling simulation unit 33a.
In the above description, the estimation unit 62 uses reinforcement learning as the learning algorithm, but the learning algorithm used by the estimation unit 62 is not limited to reinforcement learning. The estimating unit 62 may use learning algorithms such as learning with or without a teacher or learning with a half teacher, in addition to reinforcement learning.
Further, as a learning algorithm used by the model generating unit 52, deep learning (DEEP LEARNING) for learning the extraction of the feature quantity itself may be used, and machine learning may be performed according to other known methods, for example, neural network, genetic programming, functional inference programming, support vector machine, and the like.
The learning device 50 and the estimating device 60 may be connected to the numerical control device 3a via a network, for example, and may be separate devices from the numerical control device 3a. The learning device 50 and the estimating device 60 may be incorporated in the numerical control device 3a. The learning device 50 and the estimation device 60 may each be present on a cloud server.
The model generation unit 52 may learn the correction operation command using learning data acquired from the plurality of numerical control devices 3 a. The model generating unit 52 may acquire learning data from a plurality of numerical control devices 3a used in the same area, or may learn the correction operation command using learning data collected from a plurality of numerical control devices 3a operating independently in different areas. The numerical control device 3a that collects learning data may be added to or removed from the subject in the middle of the learning. The learning device 50 that learns the correction operation command with respect to the certain numerical control device 3a may be applied to another numerical control device 3a, and the correction operation command may be relearned and updated with respect to the other numerical control device 3 a.
As described above, the numerical control device 3a according to embodiment 2 generates a corrected operation command in which the basic operation command and the use process information generated from the numerical control program 4 are corrected, and selects an operation command to be given to the machine tool 2 based on the evaluation result of each operation command. The command generating unit 31a generates a new correction operation command based on the simulation result executed by the coupling simulation unit 33a, and thus can generate the correction operation command based on the characteristics of the drive system 20, the mechanical dynamics, and the machining process M. Therefore, the numerical control device 3a can efficiently reduce the machining error.
The numerical control device 3a may further generate other correction operation instructions based on the correction operation instructions. In this case, the learning device 50 can be used to learn the correction operation command based on the learning data including the correction operation command and the process information by machine learning. The numerical control device 3a can use the correction operation command outputted from the estimating device 60, and the estimating device 60 estimates the correction operation command using the trained model, which is the learning result of the learning device 50. Since the numerical control device 3a can exploratory generation of the correction operation command by using machine learning, the machining system 1a can generate the correction operation command capable of reducing machining errors without preparing a rule for correcting the operation command in advance.
Embodiment 3.
Fig. 20 is a diagram showing a configuration of a processing system 1b according to embodiment 3. The same reference numerals as those in embodiment 1 are given to the components having the same functions as those in embodiment 1, and redundant description thereof is omitted. The following mainly describes the differences from embodiments 1 and 2.
The machining system 1b includes a machine tool 2b and a numerical controller 3b. The work machine 2b has a spindle drive system 21, a feed drive system 22, a cutter 23, a table 24, and a sensor 25.
The sensor 25 detects vibration of a member that generates vibration during operation of the work machine 2b. The sensor 25 is, for example, an acceleration sensor or a force sensor. Alternatively, the sensor 25 may be an encoder provided in the drive system 20 in advance for feedback control of the drive system 20. The sensor 25 is connected to the numerical control device 3b, and a sensor signal, which is a signal obtained by the sensor 25, is output to the numerical control device 3b.
The numerical control device 3b includes a command generating unit 31b, a storage unit 32, a coupling simulation unit 33, a process evaluation unit 34, and a drive control unit 35. The numerical control device 3b differs from embodiment 1 and embodiment 2 in that an operation command is generated based on a sensor signal output from the sensor 25.
The command generating unit 31b generates a basic operation command in the same manner as the command generating unit 31 of embodiment 1. The command generating unit 31b can generate a corrected operation command by correcting the basic operation command based on the sensor signal output from the sensor 25. Specifically, the command generating unit 31b determines the feed amount per 1 blade or the cut thickness of the object W at the time of generating the correction operation command based on the sensor signal. For example, the instruction generation unit 31b learns the time waveform of the sensor signal or the feed amount per 1 blade or the cut thickness of the object W corresponding to the frequency spectrum in advance, and determines the feed amount per 1 blade or the cut thickness of the object W by using a machine learning method such as pattern matching when the sensor signal is input. Alternatively, a table of correspondence between the amplitude of the sensor signal and the feed amount per 1 blade or the cutting thickness of the object W may be recorded in advance, and the command generating unit 31b may determine the feed amount per 1 blade or the cutting thickness of the object W based on the table.
The operation of the numerical control device 3b is the same as that of the numerical control device 3 shown in fig. 13 except that the sensor signal is used when generating the correction operation command, and therefore, a detailed description thereof is omitted here.
In the above, the command generating unit 31b is configured to generate the corrected operation command by correcting the basic operation command using the sensor signal, but the correction of the operation command may be performed sequentially. That is, the command generating unit 31b may further generate the correction operation command using the sensor signal detected when the correction operation command generated using the sensor signal is applied to the work machine 2 b. In this case, a machine learning method such as reinforcement learning may be used to evaluate the amplitude or phase of the vibration component of the sensor signal, and a method of searching for a correction operation command for reducing the vibration of the sensor signal may be used.
In the case of using machine learning, for example, a trained model can be obtained using the learning device 50 shown in fig. 16, and a correction operation command can be obtained from the trained model using the estimating device 60 shown in fig. 18. In this case, in the description of embodiment 2, the "process information" acquired by the learning data acquisition unit 51 and the data acquisition unit 61 is changed to "sensor signal", and thus the description of the method for generating the correction operation command used by the numerical control device 3b according to embodiment 3 is omitted. In this case, the operation command acquired by the learning data acquisition unit 51 is an operation command corresponding to the sensor signal, specifically, an operation command given to the machine tool 2b when the sensor signal is acquired.
As described above, with respect to the numerical control device 3b according to embodiment 3, the work machine 2b includes the sensor 25, and the command generating unit 31b of the numerical control device 3b can generate the correction operation command based on the sensor signal. Therefore, the command generating unit 31b can correct the operation command according to the state of vibration actually generated in the machine tool 2b, and can efficiently generate the operation command for reducing the machining error.
Further, by explorably generating the correction operation command by using machine learning, the machining system 1b can generate the correction operation command for reducing the machining error without preparing the correction rule of the operation command in advance.
Next, the hardware configuration of the numerical control devices 3, 3a, 3b, the learning device 50, and the estimation device 60 according to embodiments 1 to 3 will be described. The instruction generating units 31, 31a, 31b, the coupling simulation units 33, 33a, the process evaluation unit 34, the drive control unit 35, the learning data acquiring unit 51 and the model generating unit 52 of the learning device 50, and the data acquiring unit 61 and the estimating unit 62 of the estimating device 60 are realized by processing circuits. These processing circuits may be implemented by dedicated hardware or may be control circuits using CPU (Central Processing Unit).
In the case where the above processing circuits are implemented by dedicated hardware, they are implemented by the processing circuit 90 shown in fig. 21. Fig. 21 is a diagram showing dedicated hardware for realizing the functions of the numerical control devices 3, 3a, and 3b, the learning device 50, and the estimation device 60 according to embodiments 1 to 3. The processing Circuit 90 is a single Circuit, a composite Circuit, a programmed processor, a parallel programmed processor, an ASIC (Application SPECIFIC INTEGRATED Circuit), an FPGA (Field Programmable GATE ARRAY), or a combination thereof.
In the case where the processing circuit is implemented by a control circuit using a CPU, the control circuit is, for example, the control circuit 91 having the configuration shown in fig. 22. Fig. 22 is a diagram showing the configuration of a control circuit 91 for realizing the functions of the numerical control devices 3, 3a, and 3b, the learning device 50, and the estimation device 60 according to embodiments 1 to 3. As shown in fig. 22, the control circuit 91 has a processor 92 and a memory 93. The Processor 92 is a CPU, also called an arithmetic device, a microprocessor, a microcomputer, a DSP (DIGITAL SIGNAL Processor), or the like. The memory 93 is, for example, a nonvolatile or volatile semiconductor memory such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable ROM), EEPROM (registered trademark) (ELECTRICALLY EPROM), a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, DVD (Digital Versatile Disk), or the like.
In the case where the processing circuit is implemented by the control circuit 91, the processor 92 reads and executes a program corresponding to the processing of each component stored in the memory 93. The memory 93 is also used as a temporary memory in each process executed by the processor 92.
The program executed by the processor 92 may be provided by being stored in a storage medium or may be provided via a communication path. The functions of the numerical control devices 3, 3a, 3b, the learning device 50, and the estimation device 60 according to embodiments 1 to 3 may be realized by using either the processing circuit 90 shown in fig. 21 or the control circuit 91 shown in fig. 22, or the processing circuit 90 and the control circuit 91 may be used in combination.
The configuration shown in the above embodiment is an example, and other known techniques may be combined, or the embodiments may be combined with each other, and a part of the configuration may be omitted or changed without departing from the scope of the present invention.
Description of the reference numerals
1. 1A and 1b processing systems, 2 and 2b working machines, 3a and 3b numerical control devices, 4 numerical control programs, 20 driving systems, 21 main shaft driving systems, 22-1 and 22-2 feeding driving systems, 23 cutters, 24 working tables, 25 sensors, 31a and 31b instruction generating parts, 32 and 32a storage parts, 33 and 33a coupling simulation parts, 34 process evaluation unit, 35 drive control unit, 50 learning device, 51 learning data acquisition unit, 52 model generation unit, 53 trained model storage unit, 54 report calculation unit, 55 function update unit, 60 estimation device, 61 data acquisition unit, 62 estimation unit, 90 processing circuit, 91 control circuit, 92 processor, 93 memory, 211 spindle motor, 212 spindle drive, 221-1, 221-2 servo motor, 222-1, 222-2 feed drive, 321 process model, 322 dynamics model, 323 spindle drive control model, 324 feed drive control model, 325 process condition information, A1 cutting area per 1 blade, c feed, F c cutting force, F d disturbance force, M process, MD1 tool side mechanical dynamics, MD2 object side mechanical dynamics, P1, P2 position, R1 rotation direction, R1 drive system displacement, R2 member displacement, T c cutting torque, T d disturbance torque, W object, θ1 spindle drive system angle, θ2 tool angle.

Claims (20)

1. A numerical control device for controlling a machine tool having a drive system for imparting an operation command to the machine tool, the drive system including a spindle drive system for driving a spindle for rotating a tool for machining an object or the object, and a feed drive system for driving a feed shaft for changing the relative positions of the tool and the object,
The numerical control device is characterized by comprising:
a command generating unit that generates a basic operation command, which is the operation command, based on a numerical control program, and generates a corrected operation command, which is the operation command after correction of the basic operation command;
A coupling simulation unit that calculates process information indicating a result of simulation of machining in a case where a basic operation command and a correction operation command are each given to the machine tool, the process information being calculated from an influence of dynamics of a member that generates vibration during operation of the machine tool and a machining process of the machining object by the tool; and
And a process evaluation unit that evaluates the magnitude of a machining error when a plurality of operation commands are used, based on a plurality of pieces of process information, and selects the operation command to be given to the machine tool from among the basic operation command and the corrected operation command.
2. The numerical control device according to claim 1, wherein,
The coupling simulation unit calculates the process information when the operation command is given by the specified machining condition, with respect to a machining process model which is a mathematical model indicating machining characteristics between the tool and the machining object, a dynamics model which is a mathematical model indicating dynamic characteristics of the member, a spindle drive control model which is a mathematical model indicating the spindle drive system and a spindle drive controller which controls the spindle drive system, and a feed drive control model which is a mathematical model indicating the feed drive system and a feed drive controller which controls the feed drive system.
3. The numerical control device according to claim 2, wherein,
Further comprising a storage unit that stores the machining process model, the dynamics model, the spindle drive control model, the feed drive control model, and machining condition information indicating the machining conditions,
The coupling simulation unit calculates the process information using the machining process model, the dynamics model, the spindle drive control model, the feed drive control model, and the machining condition information stored in the storage unit.
4. The numerical control device according to any one of claim 1 to 3,
The command generating unit generates, as the correction operation command, a command in which a path along which the tool moves relative to the object is the same as the basic operation command and at least one of a feed amount of the feed shaft and a cut thickness of the object is changed.
5. The numerical control device according to claim 4, wherein,
The command generating unit sets, as the correction operation command, an operation command obtained by changing at least one of a spindle rotation speed and a feed speed of the basic operation command in accordance with the feed amount or the cutting thickness of the object.
6. The numerical control device according to any one of claims 1 to 5,
The command generating unit generates the correction operation command by superimposing a fluctuation of a predetermined profile on at least one of a spindle rotation speed and a feed speed of the basic operation command.
7. The numerical control device according to any one of claims 1 to 6,
The instruction generating unit generates the correction operation instruction based on the process information.
8. The numerical control device according to claim 7, characterized in that,
The command generating unit further generates a correction operation command based on the process information when the correction operation command is given to the work machine.
9. The numerical control device according to claim 7 or 8, characterized in that,
The device also comprises:
a learning data acquisition unit that acquires learning data including the process information and the operation instruction corresponding to the process information; and
And a model generation unit that generates a trained model for estimating a new correction operation instruction from the process information, using the learning data.
10. The numerical control device according to any one of claims 7 to 9,
The device also comprises:
A data acquisition unit that acquires the process information; and
An estimating unit that outputs a new corrective operation instruction from the process information acquired by the data acquiring unit, using a trained model for estimating the new corrective operation instruction from the process information.
11. The numerical control device according to any one of claims 1 to 6,
The work machine further includes a sensor that detects vibration of the member during operation and outputs a sensor signal,
The instruction generating unit generates the correction operation instruction based on the sensor signal.
12. The numerical control device according to claim 11, characterized in that,
The device also comprises:
a learning data acquisition unit that acquires learning data including the sensor signal and the operation command corresponding to the sensor signal; and
And a model generation unit that generates a trained model for estimating a new correction operation command from the sensor signal, using the learning data.
13. The numerical control device according to claim 11 or 12, characterized in that,
The device also comprises:
A data acquisition unit that acquires the sensor signal; and
An estimating unit that outputs a new correction operation command from the sensor signal acquired by the data acquiring unit, using a trained model for estimating the new correction operation command from the sensor signal.
14. A processing system, comprising:
A machine tool including a drive system that includes a spindle drive system that drives a spindle that rotates a tool or a machining object for machining the machining object, and a feed drive system that drives a feed shaft that changes a relative position of the tool and the machining object, the machine tool machining the machining object based on an operation command generated by a numerical control program; and
A numerical control device that controls the machine tool by giving the operation command to the machine tool,
The numerical control device comprises:
A command generating unit that generates a basic operation command, which is the operation command, based on the numerical control program, and generates a corrected operation command, which is the operation command after correction of the basic operation command;
a coupling simulation unit that calculates process information indicating a result of simulation of machining in a case where the basic operation command and the correction operation command are each given to the machine tool, the process information being calculated from an influence of dynamics of a member that generates vibration during operation of the machine tool and a machining process of the machining object by the tool; and
And a process evaluation unit that evaluates the magnitude of a machining error when a plurality of operation commands are used, based on a plurality of pieces of process information, and selects the operation command to be given to the machine tool from among the basic operation command and the corrected operation command.
15. The processing system of claim 14, wherein the processing system comprises a plurality of processing stations,
Also provided is a learning device provided with:
A learning data acquisition unit that acquires learning data including the operation command generated by the numerical control device and the process information indicating a simulation result in a case where the operation command is given to the work machine; and
And a model generation unit that generates a trained model for estimating a new correction operation command from the process information of the numerical control device, using the learning data.
16. The processing system of claim 14 or 15, wherein the processing system comprises a plurality of processing stations,
Also provided is an estimation device provided with:
A data acquisition unit that acquires the process information generated by the numerical control device; and
An estimating unit that outputs a new corrective operation instruction from the process information acquired by the data acquiring unit, using a trained model for estimating the new corrective operation instruction from the process information.
17. The processing system of claim 14, wherein the processing system comprises a plurality of processing stations,
The work machine further includes a sensor that detects vibration of the member during operation and outputs a sensor signal,
The processing system further includes a learning device including:
a learning data acquisition unit that acquires learning data including the sensor signal and the operation command corresponding to the sensor signal when the numerical control device controls the machine tool; and
And a model generation unit that generates a trained model for estimating a new correction operation command from the sensor signal, using the learning data.
18. The processing system of claim 14 or 17, wherein the processing system comprises a plurality of processing stations,
The work machine further includes a sensor that detects vibration of the member during operation and outputs a sensor signal,
The processing system further includes an estimating device including:
a data acquisition unit that acquires the sensor signal when the numerical control device gives the operation command to the machine tool; and
An estimating unit that outputs a new correction operation command based on the sensor signal acquired by the data acquiring unit, using a trained model for estimating the new correction operation command based on the sensor signal.
19. A numerical control method is executed by a numerical control device for controlling a machine tool having a drive system for imparting an operation command to the machine tool, the drive system including a spindle drive system for driving a spindle for rotating a tool for machining an object or the object, and a feed drive system for driving a feed shaft for changing the relative positions of the tool and the object,
The numerical control method is characterized by comprising the following steps:
generating the operation instruction, namely a basic operation instruction, based on a numerical control program;
generating a corrected operation instruction which is the operation instruction after correcting the basic operation instruction;
Calculating process information indicating a result of simulation of machining in a case where the basic operation command and the correction operation command are each given to the machine tool, including an influence of dynamics of a member that generates vibration during operation of the machine tool and a machining process of the machining object by the tool; and
The magnitude of machining errors when a plurality of operation commands are used is evaluated based on a plurality of the process information, and the operation command given to the machine tool is selected from the basic operation command and the corrected operation command.
20. A machining method for machining an object by giving an operation command to a machine tool having a drive system including a spindle drive system for driving a tool for machining the object or a spindle for rotating the object and a feed drive system for driving a feed shaft for changing the relative positions of the tool and the object,
The processing method is characterized by comprising the following steps:
generating the operation instruction, namely a basic operation instruction, based on a numerical control program;
generating a corrected operation instruction which is the operation instruction after correcting the basic operation instruction;
Calculating process information indicating a result of simulation of machining in a case where the basic operation command and the correction operation command are each given to the machine tool, including an influence of dynamics of a member that generates vibration during operation of the machine tool and a machining process of the machining object by the tool;
the step of evaluating the magnitude of a machining error when a plurality of operation instructions are used, based on a plurality of pieces of process information, and selecting the operation instruction given to the machine tool from among the basic operation instruction and the corrected operation instruction;
assigning the selected operation command to the work machine; and
And operating the drive system in accordance with the operation command, thereby machining the object with the tool.
CN202180102184.0A 2021-09-30 2021-09-30 Numerical control device, machining system, numerical control method and machining method Pending CN117957088A (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2021/036265 WO2023053399A1 (en) 2021-09-30 2021-09-30 Numerical control device, machining system, numerical control method, and machining method

Publications (1)

Publication Number Publication Date
CN117957088A true CN117957088A (en) 2024-04-30

Family

ID=85226236

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202180102184.0A Pending CN117957088A (en) 2021-09-30 2021-09-30 Numerical control device, machining system, numerical control method and machining method

Country Status (3)

Country Link
JP (1) JP7224541B1 (en)
CN (1) CN117957088A (en)
WO (1) WO2023053399A1 (en)

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2846896B2 (en) * 1989-09-08 1999-01-13 東芝機械株式会社 NC servo simulator
US6266572B1 (en) * 1996-11-07 2001-07-24 Okuma Corporation Apparatus for generating a numerical control command according to cut resistance value and cut torque value of machining simulation
JP2000084794A (en) * 1998-09-14 2000-03-28 Makino Milling Mach Co Ltd Machining device
JP3399419B2 (en) * 1999-10-28 2003-04-21 三菱電機株式会社 Numerical control simulation device
JP5082621B2 (en) * 2007-06-28 2012-11-28 株式会社ジェイテクト Workpiece grinding method and processing apparatus
US9421657B2 (en) * 2011-09-14 2016-08-23 Jtekt Corporation Machining control apparatus and machining control method thereof
JP6606967B2 (en) * 2014-11-07 2019-11-20 株式会社ジェイテクト Gear processing apparatus and gear processing method
JP6557285B2 (en) * 2017-05-26 2019-08-07 ファナック株式会社 Control device and machine learning device
JP6608879B2 (en) * 2017-07-21 2019-11-20 ファナック株式会社 Machine learning device, numerical control device, numerical control system, and machine learning method
DE112017007995T5 (en) * 2017-08-30 2020-06-18 Mitsubishi Electric Corporation NUMERICAL CONTROL SYSTEM AND MOTOR DRIVE CONTROL
JP6871842B2 (en) * 2017-11-30 2021-05-19 三菱重工工作機械株式会社 Machining simulation condition optimization method, machining simulation equipment, machining simulation system and program

Also Published As

Publication number Publication date
JP7224541B1 (en) 2023-02-17
WO2023053399A1 (en) 2023-04-06
JPWO2023053399A1 (en) 2023-04-06

Similar Documents

Publication Publication Date Title
US10331104B2 (en) Machine tool, simulation apparatus, and machine learning device
CN108073137B (en) numerical controller
Ratchev et al. An advanced FEA based force induced error compensation strategy in milling
CN109308048B (en) Machining machine system and manufacturing system
EP1967320A1 (en) Method and system for reducing milling failure
CN108693829B (en) Control device
CN110405532A (en) Tool selecting apparatus and machine learning device
JP6811908B1 (en) Numerical control device, machine learning device and numerical control method
WO2021060090A1 (en) Control system
US20220137591A1 (en) System and method for design and manufacture using multi-axis machine tools
US20230116059A1 (en) Digital twin
Pereverzev et al. Optimization of control programs for numerically controlled machine tools by dynamic programming
US20210247734A1 (en) Numerical control device and numerical control method
US20220382253A1 (en) Machining program conversion device, numerical control device, and machining program conversion method
CN115315665A (en) Numerical control device
US20220382265A1 (en) Online multi-force-adaption during machining
CN109388099B (en) Machining of workpieces with model-supported error compensation
JP7166488B1 (en) Numerical controller, machining system, numerical control method and machining method
KR102046364B1 (en) Method and device for optimizing processing using numerical control program
JP6961128B1 (en) Simulation equipment, machine tool system, simulation method and machining method
CN117957088A (en) Numerical control device, machining system, numerical control method and machining method
CN118019614A (en) Numerical control device, machining system, numerical control method and machining method
KR20200051485A (en) Decelerator system, correction method of command value to drive unit, correction data generation method and method for manufacturing decelerator system
Epureanu et al. Reconfigurable machine tool programming–a new approach
WO2023153446A1 (en) Proposal device, proposal system, proposal method, and program

Legal Events

Date Code Title Description
PB01 Publication
SE01 Entry into force of request for substantive examination