CN113646613A - Numerical control device and learning device - Google Patents
Numerical control device and learning device Download PDFInfo
- Publication number
- CN113646613A CN113646613A CN202080025983.8A CN202080025983A CN113646613A CN 113646613 A CN113646613 A CN 113646613A CN 202080025983 A CN202080025983 A CN 202080025983A CN 113646613 A CN113646613 A CN 113646613A
- Authority
- CN
- China
- Prior art keywords
- unit
- phase difference
- timing signal
- vibration
- angle
- 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
Links
- 238000012545 processing Methods 0.000 claims abstract description 72
- 238000004364 calculation method Methods 0.000 claims abstract description 41
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 claims abstract description 25
- 230000001360 synchronised effect Effects 0.000 claims abstract description 5
- 238000010801 machine learning Methods 0.000 claims abstract description 4
- 244000145845 chattering Species 0.000 claims description 34
- 238000010586 diagram Methods 0.000 description 44
- 238000000034 method Methods 0.000 description 25
- 238000003754 machining Methods 0.000 description 23
- 230000001133 acceleration Effects 0.000 description 19
- 238000012937 correction Methods 0.000 description 16
- 238000005259 measurement Methods 0.000 description 10
- 230000015654 memory Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 7
- 238000002474 experimental method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 4
- 230000007704 transition Effects 0.000 description 4
- 230000004069 differentiation Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000022233 establishment of spindle orientation Effects 0.000 description 3
- 230000001788 irregular Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000003801 milling Methods 0.000 description 2
- 229910000975 Carbon steel Inorganic materials 0.000 description 1
- 241000135164 Timea Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000010962 carbon steel Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000036461 convulsion Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 102200082816 rs34868397 Human genes 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H1/00—Measuring characteristics of vibrations in solids by using direct conduction to the detector
- G01H1/003—Measuring characteristics of vibrations in solids by using direct conduction to the detector of rotating machines
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automatic Control Of Machine Tools (AREA)
- Numerical Control (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
A numerical control device (1) is characterized by comprising: a drive command unit (15) that gives an operation command to a main shaft (101) and a feed shaft (102) of a machine tool (100); a sensor signal processing unit (11) that generates a plurality of types of state quantities on the basis of a sensor signal (200) that detects vibration of a tool or a workpiece attached to a machine tool (100); a timing signal generation unit (16) that periodically generates and outputs a timing signal (207) at a timing synchronized with the rotation of the main shaft (101); a phase difference calculation unit (12) that generates, for each timing signal (207), a dimensionless quantity that represents a plurality of types of state quantities in a state space, and calculates phase difference information (203) that represents a difference between the dimensionless quantities; and a vibration determination unit (13) which has an information observation unit that creates an estimation data set from the phase difference information (203), and an estimation unit that has a trained estimation model for which machine learning is performed to determine whether or not there is chatter vibration by inputting the estimation data set, and which inputs the estimation data set to the estimation unit to determine the occurrence of chatter vibration.
Description
Technical Field
The present invention relates to a numerical control device that determines the occurrence of chatter vibration in a machine tool, a chatter vibration occurrence determination method, and a learning device.
Background
There are machine tools that remove and machine an object to be machined into a desired shape by changing the relative position between the object and a tool. A machine tool represented by a milling machine or a lathe mounts a tool or an object to be machined on a spindle, and rotates the spindle to perform machining. Vibration called "chatter" sometimes occurs in the process. If chattering occurs, the precision of the finished surface deteriorates or the tool is damaged.
Patent document 1: japanese patent laid-open publication No. 2013-7647
Disclosure of Invention
However, the technique described in patent document 1 has a problem that the time until the occurrence of chatter vibration is determined during machining becomes long. Specifically, in the technique described in patent document 1, frequency analysis is used for analyzing the vibration. In frequency analysis such as fft (fast Fourier transform), there is a limit that the frequency resolution Δ F is inversely proportional to the data acquisition time T in the calculation algorithm. Therefore, in order to obtain a sufficient frequency resolution Δ F in determining chatter vibration, the data acquisition time is increased. In addition, in the technique described in patent document 1, since 2 measurements are required at predetermined intervals, the time required to measure the vibration during machining is also long.
The present invention has been made in view of the above circumstances, and an object thereof is to obtain a numerical control device capable of shortening the time required for determining chattering vibration.
In order to solve the above problems and achieve the object, a numerical control device according to the present invention includes: a drive command unit that gives an operation command to a main shaft and a feed shaft of the machine tool; a sensor signal processing unit that generates a plurality of types of state quantities based on a sensor signal that detects vibration of a tool or a processing object attached to a machine tool; a timing signal generation unit that periodically generates and outputs a timing signal at a timing synchronized with rotation of the main shaft; a phase difference calculation unit that generates, for each timing signal, a dimensionless number indicating a plurality of types of state quantities in a state space, and calculates phase difference information indicating a difference between phases of the dimensionless number; an information observation unit that creates an estimation data set from the phase difference information; and a vibration determination unit having an estimation unit provided with a trained estimation model for machine learning, the estimation unit determining whether or not chatter vibration is present by inputting the estimation data set, and determining the occurrence of chatter vibration by inputting the estimation data set to the estimation unit.
ADVANTAGEOUS EFFECTS OF INVENTION
According to the present invention, the time required for determining chatter vibration can be shortened.
Drawings
Fig. 1 is a diagram showing a functional configuration of a numerical control device according to embodiment 1.
Fig. 2 is a diagram for explaining filter characteristics of the filter processing unit shown in fig. 1.
Fig. 3 is a diagram showing a relationship between a timing signal output from the timing signal generating unit shown in fig. 1 and a spindle angle command.
Fig. 4 is a diagram showing dimensionless quantities calculated by the phase difference calculation unit shown in fig. 1.
Fig. 5 is a diagram showing an example of transition of the phase difference calculated by the phase difference calculation unit shown in fig. 1 when chatter vibration is occurring.
Fig. 6 is a diagram showing an example of transition of the phase difference calculated by the phase difference calculation unit shown in fig. 1 when chatter vibration does not occur.
Fig. 7 is a diagram showing waveforms of acceleration generated during machining, which is an experimental result in the case where chatter vibration occurs.
Fig. 8 is a graph showing the dimensionless phase difference obtained from the experimental results shown in fig. 7.
Fig. 9 is a diagram showing waveforms of acceleration generated during machining, which is an experimental result in the case where chatter vibration is not generated.
Fig. 10 is a graph showing a phase difference of a dimensionless amount obtained from the experimental result shown in fig. 9.
Fig. 11 is a diagram for explaining example 1 of the process of the vibration determination unit shown in fig. 1.
Fig. 12 is a diagram for explaining example 2 of the process of the vibration determination unit shown in fig. 1.
Fig. 13 is a diagram showing a functional configuration of a numerical control device according to embodiment 2.
Fig. 14 is a diagram showing an example 1 of the relationship between the timing signal output from the timing signal generating unit shown in fig. 13 and the angle command for the spindle.
Fig. 15 is a diagram showing an example 2 of the relationship between the timing signal output from the timing signal generating unit shown in fig. 13 and the angle command for the spindle.
Fig. 16 is a diagram showing a functional configuration of a numerical control device according to embodiment 3.
Fig. 17 is a diagram showing a functional configuration of a numerical control device according to embodiment 4.
Fig. 18 is a diagram showing a functional configuration of a numerical control device according to embodiment 5.
Fig. 19 is a diagram showing a functional configuration of a numerical control device according to embodiment 6.
Fig. 20 is a diagram showing dedicated hardware for realizing the functions of the numerical control devices according to embodiments 1 to 6.
Fig. 21 is a diagram showing a configuration of a control circuit for realizing functions of the numerical control devices according to embodiments 1 to 6.
Fig. 22 is a diagram showing a configuration example for realizing the 3 rd embodiment of the process of the vibration determination unit shown in fig. 1.
Fig. 23 is a diagram showing an example of the structure of an inference model using a neural network.
Fig. 24 is a diagram showing a functional configuration of a learning device for learning an estimation model used in the vibration determination unit shown in fig. 22.
Detailed Description
The numerical control device, the chattering vibration occurrence determination method, and the learning device according to the embodiments of the present invention will be described in detail below with reference to the drawings. The technical scope of the present invention is not limited to the embodiments.
Fig. 1 is a diagram showing a functional configuration of a numerical control device 1 according to embodiment 1. The numerical control device 1 gives an operation command 208 to the machine tool 100, thereby numerically controlling the machine tool 100.
The machine tool 100 includes a main shaft 101 and a feed shaft 102, which have motors driven by an operation command 208. In the present embodiment, a processing object is provided on the main spindle 101, and a tool is provided on the feed spindle 102. Further, the machine tool 100 outputs operation information 209 including at least the positions, the speeds, and the motor currents of the main shaft 101 and the feed shaft 102 to the numerical control device 1. In the present embodiment, the number of cutting edges of the cutter is 1.
A sensor 103 is mounted on the work machine 100. The sensor 103 outputs a sensor signal 200, which detects vibration of the tool or the object, to the numerical control device 1. The sensor 103 is attached to a member of the main shaft 101 or the feed shaft 102 of the machine tool 100. The position where the sensor 103 is attached may be any position as long as it can detect vibration of the tool or the object, and is preferably in the vicinity of a point where the tool and the object contact each other. The sensor 103 may be any sensor as long as it can detect vibration of the tool or the object, and the sensor 103 is, for example, a displacement sensor, a velocity sensor, an acceleration sensor, an angular velocity sensor, or the like. The sensor 103 may be a force sensor for detecting a cutting reaction force or a microphone for detecting a cutting sound during machining. Alternatively, instead of the sensor 103, at least 1 of the position, speed, and motor current of the main shaft 101 and the feed shaft 102 included in the operation information may be used to detect vibration of the tool or the object generated during machining, and information indicating the detected vibration may be output as the sensor signal 200.
The numerical control device 1 includes a filter processing unit 10, a sensor signal processing unit 11, a phase difference calculation unit 12, a vibration determination unit 13, a command value correction unit 14, a drive command unit 15, and a timing signal generation unit 16.
The drive command unit 15 receives the operation information 209 from the machine tool 100, outputs the operation command 208 to the machine tool 100 based on the operation information 209, and outputs the spindle operation command 206 to the timing signal generation unit 16. The drive command unit 15 corrects the operation command 208 based on the correction signal 205 output from the command value correction unit 14 described later. The operation command 208 includes at least one of an angle command and a speed command for the main shaft 101 of the machine tool 100, and at least one of a position command and a speed command for the feed shaft 102. The main shaft operation command 206 includes at least one of an angle command and a speed command of the main shaft 101.
The filter processing unit 10 filters the sensor signal 200 output from the machine tool 100 to generate a chattering component signal 201, and outputs the generated chattering component signal 201 to the sensor signal processing unit 11. The filter processing unit 10 removes the cutting component from the sensor signal 200.
Fig. 2 is a diagram for explaining filter characteristics of the filter processing unit 10 shown in fig. 1. In fig. 2, the horizontal axis represents frequency and the vertical axis represents amplitude. Fig. 2 shows the passband of the flutter component, the cutting component and the filter in the frequency region. The cutting component is mainly a vibration component of a frequency obtained by multiplying the rotation speed of the spindle by the number of edges of the tool and a harmonic component thereof. The filter processing unit 10 removes a frequency band including each cutting component by a predetermined frequency bandwidth. For example, the predetermined frequency bandwidth can be set to about several Hz near the cutting component. The filter processing unit 10 can be designed using a known band pass filter, a notch filter, a combination of a plurality of band pass filters, a combination of a plurality of notch filters, a comb filter, or the like. By using a filter having a pass band as shown in fig. 2, the filter processing unit 10 can remove the cutting component from the sensor signal 200 to generate the chattering component signal 201.
The description returns to fig. 1. The sensor signal processing unit 11 generates a plurality of types of state quantities based on the sensor signal 200, and outputs a state quantity signal 202 indicating the generated plurality of types of state quantities to the phase difference calculation unit 12. Specifically, the sensor signal processing unit 11 generates the state quantity signal 202 based on the chattering component signal 201 output from the filter processing unit 10. The state quantity signal 202 includes the 1 st state quantity and the 2 nd state quantity. For example, the 1 st state quantity is the dither component signal 201, and the 2 nd state quantity is a state quantity obtained by differentiating the dither component signal 201 by 1 time. The sensor signal processing unit 11 simultaneously uses the dither component signal 201 and a signal obtained by differentiating the dither component signal 201 by 1 time as the time-series signal as the state quantity signal 202.
The difference in the number of time differentials between the 1 st state quantity and the 2 nd state quantity may be an odd number, and any combination may be used. For example, the 1 st state quantity is a state quantity obtained by performing time differentiation P times on the chattering component signal 201, and the 2 nd state quantity is a state quantity obtained by performing time differentiation Q times. P and Q are integers. In this case, the difference between P and Q may be an odd number. The 1 st state quantity and the 2 nd state quantity may be the time-integrated factors of the chattering component signal 201. As a specific example, the 1 st state quantity may be an acceleration, and the 2 nd state quantity may be a velocity. Alternatively, the 1 st state quantity may be a jerk, which is a differential value of the acceleration, and the 2 nd state quantity may be a position. The sensor signal processing unit 11 can generate, for example, 2 or more types of state quantities among the sensor signal 200, the state quantity obtained by time-differentiating the sensor signal 200, and the state quantity obtained by time-integrating the sensor signal.
The timing signal generation unit 16 outputs a timing signal 207 to the phase difference calculation unit 12 if it is determined that the angle command of the main shaft 101 has passed through the predetermined angle based on the main shaft operation command 206 output from the drive command unit 15. The details of the method of generating the timing signal 207 will be described.
Fig. 3 is a diagram showing a relationship between the timing signal 207 output from the timing signal generating unit 16 shown in fig. 1 and the angle command of the spindle 101. The angle command of the main shaft 101 is included in the main shaft operation command 206 output from the drive command unit 15. In fig. 3, the angle command takes a value of 0 to 360 degrees, and returns to a signal of 0 degree if 360 degrees is reached. The timing signal generation unit 16 outputs a timing signal 207 every time the angle command of the main shaft 101 passes through a predetermined angle ψ 1. Thereby, the timing signal 207 is periodically output at a timing synchronized with the rotation of the main shaft 101 of the machine tool 100. The angle ψ 1 may be any angle if it is fixed at 1 during 1 rotation of the main shaft 101, and may be, for example, the angle ψ 1 of the main shaft 101 at the time of orientation of the main shaft 101. The spindle orientation is a reference angle at which the spindle 101 is stopped.
Alternatively, the timing signal generation unit 16 may generate the timing signal 207 using a speed command of the spindle 101 included in the spindle operation command 206. In this case, the timing signal generator 16 outputs the timing signal 207 in units of time T1 calculated from the speed command s (rpm) of the spindle 101 by using the following equation (1) with the initial time T0 as a reference time. The timing signal generator 16 may be used by combining an angle command and a speed command of the main shaft 101. Here, the timing signal generating unit 16 generates the timing signal 207 using the operation command of the main spindle 101, but may generate the timing signal 207 using the operation command of the feed shaft 102 instead of the operation command of the main spindle 101 or in addition to the operation command of the main spindle 101.
[ formula 1 ]
The phase difference calculation unit 12 receives the timing signal 207 output from the timing signal generation unit 16 and the state quantity signal 202 output from the sensor signal processing unit 11. The phase difference calculation unit 12 generates a dimensionless quantity indicating a plurality of types of state quantities in a state space for each timing signal 207 based on the timing signal 207 and the state quantity signal 202, and calculates phase difference information 203 indicating a difference between the dimensionless quantities. The phase difference calculation unit 12 outputs the generated phase difference information 203 to the vibration determination unit 13.
The phase difference calculation unit 12 normalizes each of the plurality of state quantities included in the state quantity signal 202. The phase difference calculation unit 12 normalizes each state quantity by dividing each state quantity by a predetermined maximum value of each state quantity. The maximum value used here may be the maximum value of each state quantity obtained by a previous machining experiment, or may be the maximum value of each state quantity obtained by a previous simulation.
The phase difference calculation unit 12 receives the timing signal 207 at time t1 and time t 2. At this time t2 is set to a value greater than t 1. The phase difference calculation unit 12 normalizes the state quantity signal 202 at time t1, and sets the normalized value as the 1 st dimensionless quantity N1. The phase difference calculation unit 12 normalizes the state quantity signal 202 at time t2 in the same manner as at time t1, and sets the normalized value as the 2 nd dimensionless quantity N2.
Fig. 4 is a diagram showing dimensionless quantities calculated by the phase difference calculation unit 12 shown in fig. 1. Fig. 4 shows the 1 st dimensionless quantity N1 and the 2 nd dimensionless quantity N2 calculated by the phase difference calculation unit 12 in a state space formed by the 1 st state quantity dimension and the 2 nd state quantity dimension of the state quantity signal 202. The phase difference calculation unit 12 calculates an angle θ formed by the origin of the state space and the 2 nd non-dimensional amount N2, which is the previous non-dimensional amount, as the phase difference between the 1 st non-dimensional amount N1 and the 2 nd non-dimensional amount N2. The phase difference calculation unit 12 performs the above-described calculation for each timing signal 207, and calculates the phase difference between the latest dimensionless amount and the previous dimensionless amount. The phase difference calculation unit 12 outputs phase difference information 203 indicating the calculated phase difference to the vibration determination unit 13.
Fig. 5 is a diagram showing an example of transition of the phase difference calculated by the phase difference calculation unit 12 shown in fig. 1 when chatter vibration is occurring. The dimensionless numbers N10 to N13 are dimensionless numbers calculated at respective times t10 to t13 when the timing signal 207 is received. At this time, t13 > t12 > t11 > t 10. Further, an angle θ 10 shows an angle formed by the dimensionless number N10, the origin of the state space, and the dimensionless number N11, an angle θ 11 shows an angle formed by the dimensionless number N11, the origin of the state space, and the dimensionless number N12, and an angle θ 12 shows an angle formed by the dimensionless number N12, the origin of the state space, and the dimensionless number N13.
When chattering vibration is occurring, the locus of the dimensionless amounts N10 to N13 in the state space is circular, and the angle between the dimensionless amounts is constant. Therefore, the angle θ at each time when the timing signal 207 is received is constant.
Fig. 6 is a diagram showing an example of transition of the phase difference calculated by the phase difference calculation unit 12 shown in fig. 1 when chatter vibration does not occur. The dimensionless numbers N20 to N23 are dimensionless numbers calculated at respective times t20 to t23 when the timing signal 207 is received. At this time, t23 > t22 > t21 > t 20. Further, an angle θ 20 shows an angle formed by the dimensionless number N20, the origin of the state space, and the dimensionless number N21, an angle θ 21 shows an angle formed by the dimensionless number N21, the origin of the state space, and the dimensionless number N22, and an angle θ 22 shows an angle formed by the dimensionless number N22, the origin of the state space, and the dimensionless number N23.
In the case where chattering vibration does not occur, angles between the trajectories and the angular dimensionless amounts of the dimensionless amounts N20 through N23 in the state space become irregular. Therefore, the angle θ at each time when the timing signal 207 is received is not constant.
Therefore, the phase difference calculation unit 12 calculates a phase difference, which is an angle θ of a constant value when chatter vibration is occurring, and calculates a phase difference, which is an angle θ of an irregular value when chatter vibration is not occurring.
Here, the experimental results for confirming the difference in the angle θ with respect to the presence or absence of chatter vibration will be described. In this experiment, a round bar of S45C, which is a carbon steel material, was set on a chuck of a general cnc (computer Numerical control) lathe, and the outer periphery of the round bar was machined by turning. Further, a superhard tool is used as the tool, and an acceleration sensor is provided in the tool to measure the acceleration during machining.
The machining conditions when chatter occurred were a spindle rotation speed of 2000(RPM), a feed of 0.1(mm) per 1 blade, a radial cut of 1.0(mm), and a projection amount of the workpiece from the chuck of 200 (mm).
Fig. 7 is a diagram showing waveforms of acceleration generated during machining, which is an experimental result in the case where chatter vibration occurs. Fig. 8 is a graph showing the dimensionless phase difference obtained from the experimental results shown in fig. 7. In this experiment, the filter processing unit 10, the sensor signal processing unit 11, the timing signal generating unit 16, and the phase difference calculating unit 12 calculate the dimensionless amount and the angle θ shown in fig. 8 by processing the acceleration data output from the acceleration sensor as the sensor signal 200.
First, the filter processing unit 10 removes a cutting component including a harmonic of 33.3(Hz) and 2000/60 from the acceleration data based on the spindle rotation speed. Next, the sensor signal processing unit 11 calculates and outputs a state quantity signal 202 in which the 1 st state quantity is an acceleration and the 2 nd state quantity is a velocity. The 2 nd state quantity, i.e., the velocity, is obtained by integrating the acceleration.
The timing signal generator 16 outputs a timing signal 207 every time the angle command of the spindle 101 passes through the spindle angle at the time of spindle orientation. The phase difference calculation unit 12 normalizes the state quantity signal 202, and calculates the dimensionless quantities N101 to N106 at the respective times t101 to t106 when the timing signals 207 are received. Here t106 > t105 > t104 > t103 > t102 > t 101.
FIG. 8 shows dimensionless quantities N101N 106 within the state space. The angle θ 101 shows an angle formed by the dimensionless quantity N101, the origin of the state space, and the dimensionless quantity N102, the angle θ 102 shows an angle formed by the dimensionless quantity N102, the origin of the state space, and the dimensionless quantity N103, and the angle θ 103 shows an angle formed by the dimensionless quantity N103, the origin of the state space, and the dimensionless quantity N104. The angle θ 104 shows an angle formed by the dimensionless number N104, the origin of the state space, and the dimensionless number N105, and the angle θ 105 shows an angle formed by the dimensionless number N105, the origin of the state space, and the dimensionless number N106. The angles theta 101 to theta 105 are constant. From the above experimental results, it was experimentally shown that, when chattering vibration is occurring, the locus of the dimensionless amount in the state space becomes a circle, and the angles θ 101 to θ 105 at each time point take a constant value.
Next, the machining conditions when chatter vibration did not occur were a spindle rotation speed of 2000(RPM), a feed of 0.1(mm) per 1 blade, a radial cut of 1.0(mm), and a projecting amount of the workpiece from the chuck of 100 (mm).
Fig. 9 is a diagram showing waveforms of acceleration generated during machining, which is an experimental result in the case where chatter vibration is not generated. Fig. 10 is a graph showing a phase difference of a dimensionless amount obtained from the experimental result shown in fig. 9. In this experiment, the filter processing unit 10, the sensor signal processing unit 11, the timing signal generating unit 16, and the phase difference calculating unit 12 also calculate the dimensionless amount and the angle θ shown in fig. 10 by processing the acceleration data output from the acceleration sensor as the sensor signal 200.
First, the filter processing unit 10 removes a cutting component including a harmonic thereof and 33.3(Hz) 2000/60 from the acceleration data based on the spindle rotation speed. Next, the sensor signal processing unit 11 calculates and outputs a state quantity signal 202 in which the 1 st state quantity is an acceleration and the 2 nd state quantity is a velocity. The 2 nd state quantity, i.e., the velocity, is obtained by integrating the acceleration.
The timing signal generator 16 outputs a timing signal 207 every time the angle command of the spindle 101 passes through the spindle angle at the time of spindle orientation. The phase difference calculation unit 12 normalizes the state quantity signal 202, and calculates the dimensionless quantities N201 to N206 at the respective times t201 to t206 at which the timing signals 207 are received. Here t206 > t205 > t204 > t203 > t202 > t 201.
The dimensionless quantities N201N 206 within the state space are shown in FIG. 10. The angle θ 201 shows an angle formed by the dimensionless number N201, the origin of the state space, and the dimensionless number N202, the angle θ 202 shows an angle formed by the dimensionless number N202, the origin of the state space, and the dimensionless number N203, and the angle θ 203 shows an angle formed by the dimensionless number N203, the origin of the state space, and the dimensionless number N204. The angle θ 204 shows an angle formed by the dimensionless quantity N204, the origin of the state space, and the dimensionless quantity N205, and the angle θ 205 shows an angle formed by the dimensionless quantity N205, the origin of the state space, and the dimensionless quantity N206. From the above experimental results, it was experimentally shown that when chattering vibration does not occur, the trajectories of dimensionless quantities in the state space are irregular, and the angles θ 201 to θ 205 at respective times are not constant.
The description returns to fig. 1. The vibration determination unit 13 receives the angle θ, which is the phase difference, from the phase difference calculation unit 12, and determines the chatter vibration by using the procedure described below. The vibration determination unit 13 determines whether or not chatter vibration occurs based on the phase difference information 203 calculated by the phase difference calculation unit 12. When determining that chattering vibration is occurring, the vibration determination unit 13 outputs the vibration determination information 204 to the command value correction unit 14. The details of the vibration determination unit 13 will be described.
The vibration determination unit 13 records the phase difference information 203 output from the phase difference calculation unit 12. This recording is repeated every time the phase difference information 203 is received, and the angle θ included in the phase difference information 203 is recorded as time-series data.
The vibration determination unit 13 calculates the difference between the recorded angles θ, determines that chatter vibration is occurring when the difference between the angles θ is lower than a predetermined threshold, and outputs the vibration determination information 204 to the command value correction unit 14. Here, a threshold value used by the vibration determination unit 13 will be described. Here, the phase difference calculation unit 12 outputs the phase difference in a range of ± 180 degrees from the angle θ. When no chattering vibration occurs, the angle θ takes an indefinite value in the range of ± 180 degrees, and therefore the difference between the angles θ takes a value of ± 360 degrees. When chattering vibration is occurring, the angle θ takes a constant value, and therefore the difference between the angles θ becomes zero. However, the actual angle θ includes an error due to a measurement error or the like. Therefore, if the threshold value is set to a value sufficiently larger than the error of the angle θ, it can be determined whether or not chattering vibration is present. For example, when the error of the angle θ is ± 10 degrees, the threshold value may be a value larger than 20 degrees, for example, 30 degrees.
Alternatively, the vibration determination unit 13 calculates a standard deviation of the angle θ included in the plurality of pieces of phase difference information 203 that are repeatedly received, and determines that chatter vibration is occurring when the standard deviation of the angle θ is lower than a predetermined threshold value. Fig. 11 is a diagram for explaining example 1 of the process of the vibration determination unit 13 shown in fig. 1. The vibration determination unit 13 calculates the standard deviation using the angle θ acquired between the time t3 and the time t4, and determines whether or not chattering vibration is present. In example 1 shown in fig. 11, the standard deviation of the angle θ exceeds the threshold value of the standard deviation. Therefore, the vibration determination unit 13 can determine that chatter vibration has not occurred. Fig. 12 is a diagram for explaining example 2 of the process of the vibration determination unit 13 shown in fig. 1. In the 2 nd example shown in fig. 12, the standard deviation of the angle θ is lower than the threshold value of the standard deviation. Therefore, the vibration determination unit 13 can determine that chatter vibration is occurring.
A method of determining the threshold value of the standard deviation will be described. When chattering vibration occurs, the angle θ takes a constant value, and therefore the difference between the angles θ becomes zero. However, the actual angle θ has an error due to a measurement error or the like. Therefore, by setting a value sufficiently larger than the error included in the angle θ at the threshold value, it is possible to determine whether or not chattering vibration is present. For example, when the error of the angle θ is ± 10 degrees, the threshold value of the standard deviation may be a value larger than 10 degrees, for example, 20 degrees.
As another example, the vibration determination unit 13 may determine the presence or absence of chatter vibration using the dispersion of the angle θ instead of the standard deviation of the angle θ included in the plurality of pieces of phase difference information 203 that are repeatedly received. In this case, the threshold value of the dispersion can be determined by the same method as in the case of the standard deviation.
As another example, the vibration determination unit 13 may determine chatter vibration using a difference between the maximum value and the minimum value of the angle θ. In this case, the vibration determination unit 13 calculates a difference between the maximum value and the minimum value of the angle θ received over a predetermined length, and can determine that chatter vibration is occurring when the calculated difference between the maximum value and the minimum value is smaller than a predetermined threshold value.
As another example, the vibration determination unit 13 may determine the presence or absence of the chattering vibration by using an estimation model that is previously machine-learned so as to determine the presence or absence of the chattering vibration. Fig. 22 is a diagram showing a configuration example for realizing the 3 rd embodiment of the process of the vibration determination unit 13 shown in fig. 1. In example 3, the vibration determination unit 13 includes an information observation unit 301 and an estimation unit 302. The information observation unit 301 observes the angle θ included in the phase difference information 203 of a predetermined number of samples and generates an estimation data set 303 as time-series data. The estimation unit 302 inputs the estimation data set 303 generated by the information observation unit 301 to an estimation model that has been previously machine-learned so as to output the presence or absence of chatter vibration, and outputs vibration determination information 204 indicating the presence or absence of chatter vibration.
The inference unit 302 may use an inference model of an arbitrary algorithm. As an example, an inference model using a neural network will be described. Fig. 23 is a diagram showing an example of the structure of an inference model using a neural network. In the example shown in fig. 23, the neural network is composed of an input layer x1, x2, ·, xn with n neurons, an intermediate layer y1 with m neurons, y2, ·, ym, and an output layer z1 with 1 neuron. Fig. 23 shows an example in which the number of intermediate layers is 1, but 2 or more intermediate layers may be provided.
Input layers x1, x2, ·, xn are connected to intermediate layers y1, y2, ·, ym, and intermediate layers y1, y2, ·, ym are connected to output layer z 1. Note that the connection between the input layers and the intermediate layers shown in fig. 23 is an example, and each of the input layers x1, x2, ·, xn may be connected to any of the intermediate layers y1, y2, ·, ym.
In the case of the 3-layer neural network as shown in fig. 23, after a plurality of inputs are input to the input layers x1, x2, ·, xn, the values are given weights a1 to Aa and input to the intermediate layers y1, y2, ·, ym. The values input to the intermediate layers y1, y2, ·, ym are further given weights B1 to Bb, input to the output layer z1, and output from the output layer z 1. Each of a and b is a natural number, and in the example shown in fig. 23, b is equal to m. The output results vary depending on the values of the weights A1 to Aa and B1 to Bb.
Fig. 24 is a diagram showing a functional configuration of a learning device 400 for learning the estimation model used in the vibration determination unit 13 shown in fig. 22. The learning device 400 includes a data acquisition unit 401 and a learning processing unit 402.
The data acquisition unit 401 acquires a data set 304 for learning, which correlates the phase difference information 203 acquired during actual machining with chatter presence/absence information 305 indicating the presence/absence of chatter vibration. The presence or absence of chatter vibration can be represented by a numerical value that differs depending on whether chatter vibration has occurred. For example, "1" may be used when chattering vibration occurs, and "0" may be used when chattering vibration does not occur. The information 305 on the presence or absence of chatter vibration included in the learning dataset 304 can be determined by evaluating a machined surface after machining, for example.
The learning processing unit 402 learns the phase difference information 203 included in the learning data set 304 as input data. The learning processing unit 402 performs so-called teacher learning so that the output of the estimation model matches the value of the chattering presence/absence information 3-5. The learning processing unit 402 learns an estimation model that outputs an output value corresponding to the presence or absence of chatter vibration if the phase difference information 203 is input by adjusting the weights a1 to Aa and B1 to Bb so that the value output from the output layer when the phase difference information 203 is input to the input layer approaches a value indicating the presence or absence of chatter vibration.
The learning processing unit 402 can use an error back propagation method as a teacher learning method used for learning the estimation model. In order to improve generalization performance of the estimation model, the learning processing unit 402 may use a method of "dropout" in which neurons are randomly excluded during learning and "early stopping" in which learning is completed by monitoring an error. The learning processing unit 402 outputs the learned estimation model as a trained estimation model. The trained estimation model output by the learning processing unit 402 can be used by the estimation unit 302 shown in fig. 22.
Although the above description has been made of the case where a Neural network is used as the estimation model, the estimation model may be constructed by using other known methods, for example, rnn (current Neural network), LSTM (Long Short-Term Memory), svm (support Vector machine), or the like.
When receiving the vibration determination information 204 from the vibration determination unit 13, the command value correction unit 14 outputs a correction signal 205 instructing to change the operation command 208 to the drive command unit 15. The correction signal 205 is a signal for changing the speed command of the spindle 101 at a predetermined rate in accordance with the current spindle speed.
Alternatively, the correction signal 205 may be a signal that changes the rotation speed of the main shaft 101 so that the rotation speed of the main shaft 101 matches an integer fraction of the resonance frequency of the mechanical structure calculated in advance by finite element analysis. The resonance frequency of the mechanical structure may be determined experimentally in advance, not by finite element analysis.
The correction signal 205 may be a signal that changes the speed of the feed shaft 102 at a predetermined rate in accordance with a command. Specifically, the correction signal 205 may be a signal for decreasing the speed command value of the feed shaft 102 so that the motor current of the feed shaft 102 is smaller than a predetermined reference value.
As described above, according to embodiment 1, time-series data of a plurality of types of state quantities is generated based on the sensor signal 200 that detects vibration of the tool or the object attached to the machine tool 100. Further, in the state space, dimensionless quantities representing a plurality of types of state quantities are generated for each timing signal 207, and phase difference information 203 representing the angle θ, which is the difference between the phases of the dimensionless quantities, is calculated. The occurrence of chattering vibration in the work machine 100 is determined based on the fluctuation of the phase difference information 203.
Since the numerical control device 1 does not use frequency analysis represented by FFT in determining chattering vibration, it is possible to obtain sufficient frequency resolution in determining chattering vibration without being limited by data acquisition time. Therefore, the time required for determining the chatter vibration, that is, the time from the occurrence of the chatter vibration to the determination of the occurrence of the chatter vibration can be shortened. Therefore, the time from the generation of chatter vibration to the suppression of chatter vibration is also shortened, and chatter vibration can be suppressed at high speed.
Further, in the numerical controller 1, chattering vibration is determined based on the phase difference information 203, which is a dimensionless quantity. As a conventional method, for example, there is a method of determining chatter vibration based on the amplitude of the chatter vibration. When the amplitude of the chatter vibration is used, the amplitude varies depending on the machining conditions, and therefore, it is necessary to set a threshold value of the amplitude in accordance with the machining conditions. In contrast, in the numerical control device 1 that determines chattering vibration based on the phase difference information 203, which is a dimensionless quantity, chattering vibration can be determined without depending on the machining conditions, and it is not necessary to set a threshold value according to the machining conditions.
Further, the machine tool 100 according to embodiment 1 is configured to set the object to be machined on the main spindle 101, but the same effect can be obtained even when a tool is set on the main spindle 101, as typified by a milling machine or a lathe.
In embodiment 1, although the configuration is such that 1 sensor 103 is used, the sensors 103 may be provided at a plurality of locations of the machine tool 100. In this case, the processing described in embodiment 1 can be performed for all the sensors 103 provided, and the occurrence of chatter vibration can be determined. When the sensors 103 are provided at a plurality of locations, chatter vibration can be determined and suppressed even when chatter vibration occurs at a plurality of locations during machining.
The sensor 103 provided in the machine tool 100 may detect vibration using 2 or more types of sensors 103 and output a sensor signal 200 including 2 or more types of state quantities to the filter processing unit 10. In this case, the sensor signal processing unit 11 can set the 2 kinds of sensor outputs to the 1 st state quantity and the 2 nd state quantity, respectively. By directly measuring the 2 nd state quantity by the sensor 103, the judder can be determined without being affected by the quantization error associated with the differentiation or integration.
In embodiment 1, the sensor signal processing unit 11 extracts 2 types of state quantities, but may extract 3 or more types of state quantities.
In embodiment 1, an example in which the number of blades of the cutter is 1 is described. In embodiment 2, a configuration for determining the occurrence of chatter vibration when the number of edges of the tool is 2 or more will be described.
Fig. 13 is a diagram showing a functional configuration of the numerical control device 2 according to embodiment 2. The numerical control device 2 includes a filter processing unit 10, a sensor signal processing unit 11, a phase difference calculation unit 12, a vibration determination unit 13, a command value correction unit 14, a drive command unit 15, a timing signal generation unit 16-1, and a tool information recording unit 17.
The numerical control device 2 includes a tool information recording unit 17 that outputs tool information 210 in addition to the configuration of the numerical control device 1 according to embodiment 1, and includes a timing signal generating unit 16-1 instead of the timing signal generating unit 16 of the numerical control device 1. Next, a description will be given mainly of a portion different from the numerical control device 1.
The tool information recording unit 17 records tool information 210, which is information related to a tool provided in the machine tool 100, and outputs the recorded tool information 210 to the timing signal generating unit 16-1. The tool information 210 includes at least information indicating the number of edges of the tool. The tool information 210 may include information indicating the shape of the tool, such as the type of the tool, such as an end mill or a turning tool, the length of the tool, and the diameter of the tool. Further, when 1 turning tool is mounted on the machine tool 100, the tool information recording unit 17 outputs tool information 210 indicating that the number of edges of the tool is 1. When the turning tool is attached to the machine tool 100, the number of edges is equal to the number of tools when a plurality of tools simultaneously cut. For example, when the machine tool 100 includes a lower tool rest and an upper tool rest and machining is performed by mounting 1 turning tool on each of the two tool rests, the tool information recording unit 17 outputs tool information 210 indicating that the number of cutting edges is 2.
The timing signal generation unit 16-1 determines that the spindle angle has passed a predetermined angle based on the spindle operation command 206 output from the drive command unit 15 and the tool information 210 output from the tool information recording unit 17, and outputs the timing signal 207 to the phase difference calculation unit 12 at the timing when the determination has passed.
The details of the processing of the timing signal generating unit 16-1 will be described. The following describes a case where a tool having an edge number of α blades is attached to the spindle 101. Alpha is a natural number of 2 or more.
First, a case where α is 2 will be described. Fig. 14 is a diagram showing an example 1 of the relationship between the timing signal 207 output from the timing signal generating unit 16-1 shown in fig. 13 and the angle command for the spindle 101. The angle command takes a value between 0 and 360 degrees, and returns to a signal of 0 degree if 360 degrees is reached. The timing signal 207 is output every time the angle command of the main shaft 101 passes through predetermined angles, that is, the angle ψ 1 and the angle ψ 2. That is, the timing signal 207 is output 2 times the same number of times as the number of blades during 1 rotation of the spindle 101. The angle ψ 1 may be any angle if it is fixed at 1 during 1 rotation of the main shaft 101. For example, the angle ψ 1 can be set as the main axis angle at the time of main axis orientation. The difference between the angle ψ 1 and the angle ψ 2 is a value obtained by dividing 360 degrees by 2, which is the number of tool edges, and is set to ψ 2- ψ 1 of 180 degrees.
Next, a case where α is an arbitrary natural number will be described. Fig. 15 is a diagram showing an example 2 of the relationship between the timing signal 207 output from the timing signal generating unit 16-1 shown in fig. 13 and the angle command for the spindle 101. The timing signal 207 is a timing signal for instructing the angle of the main shaft 101 to pass through a predetermined angle ψ each timeβIs output. Beta is a natural number of 2 or more and α or less. The timing signal 207 is output α times during 1 rotation of the spindle 101. ψ 1 may be any angle if it is fixed at 1 during 1 rotation of the main shaft 101. Between ψ 1 and ψ β -1, there is a restriction shown by equation (2) shown below. In other words, the timing signal generator 16-1 outputs a timing when the spindle 101 rotates by an angle obtained by dividing 360 degrees by the number of blades α each timeA time signal 207.
[ formula 2 ]
The timing signal generation unit 16-1 may generate the timing signal 207 using a speed command of the spindle 101 included in the spindle operation command 206. In this case, the timing signal generating unit 16-1 generates the timing signal 207 in units of time T2 calculated by using the following expression (3) in accordance with the speed command s (rpm) of the spindle 101.
[ formula 3 ]
As described above, according to embodiment 2, since the timing signal 207 is generated based on the tool information 210, even when the number of edges of the tool attached to the machine tool 100 is large, the time required for determining chatter vibration, that is, the time from the occurrence of chatter vibration to the determination of the occurrence of chatter vibration can be shortened as in embodiment 1.
In the case where the number of blades is 1, the numerical control device 2 can determine and suppress chattering vibration by the same processing as the numerical control device 1.
Fig. 16 is a diagram showing a functional configuration of the numerical control device 3 according to embodiment 3. The numerical control device 3 includes a filter processing unit 10, a sensor signal processing unit 11, a phase difference calculation unit 12, a vibration determination unit 13, a command value correction unit 14, a drive command unit 15, and a timing signal generation unit 16-2. The numerical control device 3 includes a timing signal generation unit 16-2 instead of the timing signal generation unit 16 of the numerical control device 1. Next, a description will be given mainly of a portion different from the numerical control device 1.
The machine tool 100 further includes an angle information sensor 104 attached to the main shaft 101 in addition to the configuration described in embodiment 1. The angle information sensor 104 is a sensor for measuring the spindle angle, and for example, an encoder, a potentiometer sensor, or the like can be used. The angle information 211 is a signal including at least an actual measurement value of the spindle angle measured by the angle information sensor 104. The angle information sensor 104 outputs the generated angle information 211 to the numerical control device 3.
The timing signal generator 16-2 generates the timing signal 207 based on the measured value of the spindle angle included in the angle information 211. The timing signal generator 16-2 generates the timing signal 207 in the same manner as in embodiment 1, but uses the actual measurement value of the spindle angle instead of the angle command of the spindle 101.
The angle information sensor 104 may be a sensor that detects an actual measurement value of the spindle speed. In this case, the angle information sensor 104 is an angular velocity sensor. The timing signal generation unit 16-2 can generate the timing signal 207 based on the measured value of the spindle speed, instead of the angle command of the spindle 101. The timing signal generating unit 16-2 uses the initial time t0 as a reference time to generate a timing signal based on the measured value S of the spindle speedref(rpm) the timing signal 207 is output in units of time T3 calculated by equation (4) shown below.
[ formula 4 ]
As described above, according to embodiment 3, the timing signal 207 is generated based on the measured value of the spindle angle. Therefore, the timing signal 207 can be generated without being affected by a follow-up error in control that occurs between the angle command of the main spindle 101 and the actual angle. Therefore, even when a following error in control occurs between the angle command and the actual angle of the main spindle 101, the numerical control device 3 can shorten the time required for determining chatter vibration, that is, the time from the occurrence of chatter vibration to the determination of the occurrence of chatter vibration, as in embodiment 1.
In embodiment 3, an example in which the timing signal 207 is generated using the actual measurement value of the spindle angle or the spindle speed has been described, but the timing signal generation unit 16-2 may use the spindle angle command and the actual measurement value of the spindle angle at the same time, or may use the spindle speed command and the actual measurement value of the spindle speed at the same time.
Fig. 17 is a diagram showing a functional configuration of the numerical control device 4 according to embodiment 4. The numerical control device 4 includes a filter processing unit 10, a sensor signal processing unit 11, a phase difference calculation unit 12, a vibration determination unit 13, a command value correction unit 14, a drive command unit 15, a timing signal generation unit 16-3, and a tool information recording unit 17. That is, the numerical control device 4 has a tool information recording unit 17 in addition to the configuration of the numerical control device 3 described in embodiment 3, and has a timing signal generating unit 16-3 instead of the timing signal generating unit 16-2. Next, a description will be given mainly of a portion different from the numerical control device 2.
The timing signal generation unit 16-3 generates the timing signal 207 based on the angle information 211 output from the angle information sensor 104 and the tool information 210 output from the tool information recording unit 17, and outputs the generated timing signal 207 to the phase difference calculation unit 12. The timing signal generator 16-3 can generate the timing signal 207 by the same method as the timing signal generator 16-1 of embodiment 2. At this time, the timing signal generating unit 16-3 generates the timing signal 207 using the measured value of the spindle angle, instead of the angle command of the spindle 101.
As described above, according to embodiment 4, as in embodiment 3, the timing signal 207 can be generated without being affected by the following error of the control generated between the angle command of the main spindle 101 and the actual angle, and also in the case where the number of blades is large, as in embodiment 2, the time required for determining chatter vibration, that is, the time from the occurrence of chatter vibration to the determination of the occurrence of chatter vibration can be shortened as in embodiment 1.
Fig. 18 is a diagram showing a functional configuration of the numerical control device 5 according to embodiment 5. The numerical control device 5 includes a filter processing unit 10, a sensor signal processing unit 11, a phase difference calculation unit 12, a vibration determination unit 13, a command value correction unit 14, a drive command unit 15, and a timing signal generation unit 16-4. The numerical control device 5 can acquire machining program information 212 including a spindle rotation speed command 213 from the machining program 18 for controlling the machine tool 100. Next, a description will be given mainly of a portion different from the numerical control device 1.
The spindle rotation speed command 213 is output to the timing signal generation unit 16-4, and the machining program information 212 is output to the drive command unit 15. The drive command unit 15 can output the operation command 208 to the machine tool 100 according to the machining program information 212.
The timing signal generation unit 16-4 generates the timing signal 207 based on the main spindle rotation speed command 213 extracted from the machining program information 212. The timing signal generator 16-4 outputs the timing signal 207 in units of time T4 calculated using the spindle rotation speed command 213 and the following equation (5) with reference to the initial time T0. In addition, S in equation (5)cmdThe spindle rotational speed indicated by the spindle rotational speed command 213 is shown.
[ FORMULA 5 ]
As described above, according to embodiment 5, the timing signal 207 can be generated based on the spindle rotation speed command 213 included in the machining program 18. When the timing signal 207 is generated using the machining program 18, as in embodiment 1, the time required for determining chatter vibration, that is, the time from the occurrence of chatter vibration to the determination of the occurrence of chatter vibration can be shortened.
Fig. 19 is a diagram showing a functional configuration of the numerical control device 6 according to embodiment 6. The numerical control device 6 includes a filter processing unit 10, a sensor signal processing unit 11, a phase difference calculation unit 12, a vibration determination unit 13, a command value correction unit 14, a drive command unit 15, a timing signal generation unit 16-5, and a tool information recording unit 17. The numerical control device 6 has a tool information recording unit 17 in addition to the configuration of the numerical control device 5, and has a timing signal generating unit 16-5 instead of the timing signal generating unit 16-4.
The timing signal generation unit 16-5 generates the timing signal 207 based on the tool information 210 and the spindle rotation speed command 213, and outputs the generated timing signal 207 to the phase difference calculation unit 12.
The timing signal generation unit 16-5 uses the initial time t0 as a reference time, and uses the following equation (6), the number of blades α, and the spindle rotation speed ScmdAnd outputs the timing signal 207 in units of the calculated time T5.
[ formula 6 ]
As described above, according to embodiment 6, in addition to the effect of embodiment 5, even when the number of edges of the tool is plural, the occurrence of chatter vibration can be determined.
Next, the hardware configuration of the numerical control devices 1 to 6 according to embodiments 1 to 6 will be explained. The functional units of the numerical control devices 1 to 6 are realized by processing circuits. These Processing circuits may be realized by dedicated hardware, or may be control circuits using a cpu (central Processing unit).
In the case where the above-described processing circuits are realized by dedicated hardware, they are realized by the processing circuit 90 shown in fig. 20. Fig. 20 is a diagram showing dedicated hardware for realizing the functions of the numerical control devices 1 to 6 according to embodiments 1 to 6. 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.
When the processing circuit is realized by a control circuit using a CPU, the control circuit is, for example, a control circuit 91 having a configuration shown in fig. 21. Fig. 21 is a diagram showing a configuration of a control circuit 91 for realizing functions of the numerical control devices 1 to 6 according to embodiments 1 to 6. As shown in fig. 21, the control circuit 91 has a processor 92 and a memory 93. The processor 92 is a CPU, and is also referred to as a central processing unit, a processing unit, an arithmetic unit, a microprocessor, a microcomputer, a dsp (digital Signal processor), or the like. Examples of the memory 93 include nonvolatile or volatile semiconductor memories such as ram (random Access memory), rom (read Only memory), flash memory, EPROM (erasable Programmable rom), and EEPROM (Electrically EPROM), magnetic disks, flexible disks, optical disks, compact disks, mini disks, and dvd (digital Versatile disk).
When the processing circuit is realized by the control circuit 91, the processor 92 reads out 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 configurations described in the above embodiments are only examples of the contents of the present invention, and may be combined with other known techniques, or the embodiments may be combined with each other, and some of the configurations may be omitted or modified without departing from the scope of the present invention.
Description of the reference numerals
1. 2, 3, 4, 5, 6 numerical control devices, 10 filter processing units, 11 sensor signal processing units, 12 phase difference calculating units, 13 vibration determining units, 14 instruction value correcting units, 15 drive instruction units, 16-1, 16-2, 16-3, 16-4, 16-5 timing signal generating units, 17 tool information recording units, 18 machining programs, 90 processing circuits, 91 control circuits, 92 processors, 93 memories, 100 machines, 101 spindles, 102 feed shafts, 103 sensors, 104 angle information sensors, 200 sensor signals, 201 chatter component signals, 202 state quantity signals, 203 phase difference information, 204 vibration determining information, 205 correcting signals, 206 spindle operation instructions, 207 timing signals, 208 operation instructions, 209 operation information, 210 tool information, 211 angle information, 212 machining program information, 213 spindle rotation speed instructions, 301 information observing units, a 302 estimating unit, 303 estimating a dataset, 304 learning a dataset, 305 information on the presence or absence of chattering, 400 learning means, 401 data acquiring unit, and 402 learning processing unit.
Claims (2)
1. A numerical control apparatus, comprising:
a drive command unit that gives an operation command to a main shaft and a feed shaft of the machine tool;
a sensor signal processing unit that generates a plurality of types of state quantities based on a sensor signal that detects vibration of a tool or a workpiece attached to the machine tool;
a timing signal generating unit that periodically generates and outputs a timing signal at a timing synchronized with rotation of the spindle;
a phase difference calculation unit that generates a dimensionless quantity indicating the state quantities of the plurality of types in a state space for each of the timing signals, and calculates phase difference information indicating a difference between the phases of the dimensionless quantity; and
and a vibration determination unit having an information observation unit that creates an estimation data set from the phase difference information, and an estimation unit that has a trained estimation model for which machine learning is performed to determine whether or not there is chatter vibration by inputting the estimation data set, wherein the occurrence of chatter vibration is determined by inputting the estimation data set to the estimation unit.
2. A learning device is characterized by comprising:
a data acquisition unit that acquires phase difference information from a numerical control device having a drive command unit that gives an operation command to a main shaft and a feed shaft of a machine tool, a sensor signal processing unit that generates a plurality of types of state quantities based on a sensor signal that detects vibration of a tool or a workpiece attached to the machine tool, a timing signal generation unit that periodically generates and outputs a timing signal at a timing synchronized with rotation of the main shaft, a phase difference calculation unit that generates a dimensionless quantity indicating the plurality of types of state quantities in a state space for each of the timing signals, and calculates phase difference information indicating a difference between the dimensionless quantities; and
and a learning processing unit that performs machine learning of the estimation model so as to output a numerical value corresponding to the presence or absence of chattering if the phase difference information is input.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/JP2019/015327 WO2020208685A1 (en) | 2019-04-08 | 2019-04-08 | Numerical control device and chattering identification method |
| JPPCT/JP2019/015327 | 2019-04-08 | ||
| PCT/JP2020/002108 WO2020208893A1 (en) | 2019-04-08 | 2020-01-22 | Numerical control device and learning device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113646613A true CN113646613A (en) | 2021-11-12 |
Family
ID=68532198
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202080025983.8A Pending CN113646613A (en) | 2019-04-08 | 2020-01-22 | Numerical control device and learning device |
Country Status (4)
| Country | Link |
|---|---|
| JP (2) | JP6605185B1 (en) |
| CN (1) | CN113646613A (en) |
| DE (1) | DE112020001795T5 (en) |
| WO (2) | WO2020208685A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6775720B1 (en) * | 2020-03-24 | 2020-10-28 | 三菱電機株式会社 | Numerical control device |
| CN117120946A (en) * | 2021-04-26 | 2023-11-24 | 三菱电机株式会社 | Numerical control device, learning device, and chatter suppression method |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB1100339A (en) * | 1964-08-05 | 1968-01-24 | Rolls Royce | Gas turbine engine fuel system |
| JPH07110716A (en) * | 1993-08-20 | 1995-04-25 | Mitsubishi Electric Corp | Positioning device |
| JPH0970872A (en) * | 1995-06-28 | 1997-03-18 | Asahi Chem Ind Co Ltd | Powder resin extruder and extrusion method using the same |
| JPH1172378A (en) * | 1997-08-28 | 1999-03-16 | Omron Corp | State judgment apparatus |
| JP2005214631A (en) * | 2004-01-27 | 2005-08-11 | Kansai Electric Power Co Inc:The | State monitoring/maintaining device and method |
| CN102165172A (en) * | 2008-09-26 | 2011-08-24 | 本田技研工业株式会社 | Frequency component analyzer |
| CN102243143A (en) * | 2011-04-20 | 2011-11-16 | 上海斐赛轴承科技有限公司 | Bearing abnormal sound detection control method and bearing vibration measuring instrument |
| CN102314534A (en) * | 2011-06-03 | 2012-01-11 | 东北大学 | Gear profile modification method based on vibration reliability and genetic algorithm |
| US9046463B1 (en) * | 2006-04-21 | 2015-06-02 | University Of Washington | Method for conducting nonlinear electrochemical impedance spectroscopy |
| CN109270486A (en) * | 2018-07-25 | 2019-01-25 | 中国电子科技集团公司第二十九研究所 | A kind of frequency-dependent signal two dimension direction-finding method rotated using two sensors |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08229772A (en) * | 1995-03-01 | 1996-09-10 | Toyota Motor Corp | Method and device for setting spindle rotational speed |
| US20020146296A1 (en) * | 2001-02-26 | 2002-10-10 | National Institute Of Standards And Technology | Method and device for avoiding chatter during machine tool operation |
| JP4703315B2 (en) * | 2005-08-12 | 2011-06-15 | 国立大学法人名古屋大学 | Rotational speed calculation device of machining device, chatter vibration evaluation device of machining device, and chatter vibration evaluation method of machining device |
| JP4321581B2 (en) * | 2006-11-30 | 2009-08-26 | パナソニック電工株式会社 | Machine tool comprehensive monitoring device |
| JP4942839B2 (en) * | 2010-09-10 | 2012-05-30 | 株式会社牧野フライス製作所 | Chatter vibration detection method, chatter vibration avoidance method, and machine tool |
| JP5742312B2 (en) * | 2011-03-10 | 2015-07-01 | 株式会社ジェイテクト | Chatter vibration detection method |
| JP5853437B2 (en) * | 2011-06-24 | 2016-02-09 | 株式会社ジェイテクト | Chatter vibration detection method |
| JP5908342B2 (en) * | 2012-05-17 | 2016-04-26 | オークマ株式会社 | Machining vibration suppression method and machining vibration suppression device for machine tool |
| JP6021632B2 (en) * | 2012-12-20 | 2016-11-09 | 三菱重工業株式会社 | Processing device control device, processing device, processing device control program, processing device control method, and processing method |
| JP2014140918A (en) * | 2013-01-23 | 2014-08-07 | Hitachi Ltd | Cutting vibration inhibition method, arithmetic control device, and machine tool |
| JP6257481B2 (en) * | 2014-09-02 | 2018-01-10 | 三菱電機株式会社 | Numerical controller |
-
2019
- 2019-04-08 WO PCT/JP2019/015327 patent/WO2020208685A1/en active Application Filing
- 2019-04-08 JP JP2019542739A patent/JP6605185B1/en active Active
-
2020
- 2020-01-22 CN CN202080025983.8A patent/CN113646613A/en active Pending
- 2020-01-22 DE DE112020001795.8T patent/DE112020001795T5/en active Pending
- 2020-01-22 WO PCT/JP2020/002108 patent/WO2020208893A1/en active Application Filing
- 2020-01-22 JP JP2020555927A patent/JP6987275B2/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB1100339A (en) * | 1964-08-05 | 1968-01-24 | Rolls Royce | Gas turbine engine fuel system |
| JPH07110716A (en) * | 1993-08-20 | 1995-04-25 | Mitsubishi Electric Corp | Positioning device |
| JPH0970872A (en) * | 1995-06-28 | 1997-03-18 | Asahi Chem Ind Co Ltd | Powder resin extruder and extrusion method using the same |
| JPH1172378A (en) * | 1997-08-28 | 1999-03-16 | Omron Corp | State judgment apparatus |
| JP2005214631A (en) * | 2004-01-27 | 2005-08-11 | Kansai Electric Power Co Inc:The | State monitoring/maintaining device and method |
| US9046463B1 (en) * | 2006-04-21 | 2015-06-02 | University Of Washington | Method for conducting nonlinear electrochemical impedance spectroscopy |
| CN102165172A (en) * | 2008-09-26 | 2011-08-24 | 本田技研工业株式会社 | Frequency component analyzer |
| CN102243143A (en) * | 2011-04-20 | 2011-11-16 | 上海斐赛轴承科技有限公司 | Bearing abnormal sound detection control method and bearing vibration measuring instrument |
| CN102314534A (en) * | 2011-06-03 | 2012-01-11 | 东北大学 | Gear profile modification method based on vibration reliability and genetic algorithm |
| CN109270486A (en) * | 2018-07-25 | 2019-01-25 | 中国电子科技集团公司第二十九研究所 | A kind of frequency-dependent signal two dimension direction-finding method rotated using two sensors |
Non-Patent Citations (1)
| Title |
|---|
| 李国强;张卫国;陈立;聂博文;张鹏;岳廷瑞;: "风力机叶片翼型动态试验技术研究", 力学学报, no. 04, pages 49 - 63 * |
Also Published As
| Publication number | Publication date |
|---|---|
| JP6605185B1 (en) | 2019-11-13 |
| WO2020208893A1 (en) | 2020-10-15 |
| JPWO2020208685A1 (en) | 2021-05-06 |
| WO2020208685A1 (en) | 2020-10-15 |
| DE112020001795T5 (en) | 2022-03-24 |
| JPWO2020208893A1 (en) | 2021-04-30 |
| JP6987275B2 (en) | 2021-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5160980B2 (en) | Vibration suppression method and apparatus | |
| US9211624B2 (en) | Vibration determination method and vibration determination device | |
| JP5234772B2 (en) | Vibration suppression method and apparatus for machine tool | |
| JP4777960B2 (en) | Vibration suppression device | |
| JP4582660B2 (en) | Vibration suppressor for machine tools | |
| JP4743646B2 (en) | Vibration suppressor for machine tools | |
| JP4433422B2 (en) | Vibration suppression device | |
| US8014903B2 (en) | Method for suppressing vibration and device therefor | |
| JP5742312B2 (en) | Chatter vibration detection method | |
| CN111052015B (en) | Numerical control system and motor control device | |
| JP6888375B2 (en) | Vibration analysis system and processing machine | |
| CN105204443A (en) | Method Of Calculating Stable Spindle Rotation Number Capable Of Suppressing Chatter Vibration, Method Of Informing The Same, Method Of Controlling Spindle Rotation Number, And Method Of Editing Nc Program, And Apparatus Therefor | |
| CN113646613A (en) | Numerical control device and learning device | |
| JP4891150B2 (en) | Vibration suppressor for machine tools | |
| JP5631779B2 (en) | Vibration suppression method and apparatus for machine tool | |
| JP5155090B2 (en) | Vibration determination method and vibration suppression device for machine tool | |
| JP2018043317A (en) | Machine tool | |
| CN109702554B (en) | self-adaptive vibration shaping milling chatter suppression method | |
| JP5587707B2 (en) | Vibration suppression device | |
| JP7179198B1 (en) | Numerical controller, learning device, and chatter vibration suppression method | |
| Sanz-Calle et al. | The influence of radial engagement and milling direction for thin wall machining: a semi-analytical study | |
| CN110053042A (en) | Robot controller | |
| JPH068106A (en) | Adaptive control system and state judgment device | |
| EP3447592B1 (en) | Milling machine feed rate control | |
| CN112236729B (en) | Numerical control device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |