CN115244477A

CN115244477A - Numerical control device and machine learning device

Info

Publication number: CN115244477A
Application number: CN202080098172.0A
Authority: CN
Inventors: 半谷幸宽
Original assignee: Mitsubishi Electric Corp
Current assignee: Mitsubishi Electric Corp
Priority date: 2020-07-21
Filing date: 2020-07-21
Publication date: 2022-10-25
Anticipated expiration: 2040-07-21
Also published as: DE112020007089T5; JPWO2022018822A1; WO2022018822A1; JP6865908B1; CN115244477B

Abstract

A numerical control device (1A) is provided with: a control unit (21) that controls the machine tool (2A); a state observation unit (11A) for observing state variables including a motor load current value (41) of a motor for driving a cutting tool used in a machine tool (2A), a cutting coordinate value (40) which is a cutting position from the cutting tool to a workpiece, a tool type (42) which is a type of the cutting tool, a workpiece type (43) which is a type of the workpiece, and a workpiece temperature (44) which is a temperature of the workpiece; a data acquisition unit (12) that acquires a wear amount measurement result (45), which is a result obtained by measuring the wear amount of the cutting tool; and a learning unit (13) that learns the amount of wear of the cutting tool in accordance with a data set created based on a combination of the state variable and the wear amount measurement result (45).

Description

Numerical control device and machine learning device

Technical Field

The present invention relates to a numerical control device and a machine learning device for estimating an amount of wear of a cutting tool used in a machine tool.

Background

A machine tool that machines a workpiece using a cutting tool is controlled by a numerical control device. If the machine tool is used for a long period of time, the cutting edge of the cutting tool is worn, and the dimensional error of the finished workpiece becomes large. In order to suppress the dimensional error, the operator of the machine tool periodically measures the amount of wear of the cutting tool.

Various countermeasures have been attempted in order to save the amount of work for the operator to measure the amount of wear as described above. The numerical control device described in patent document 1 estimates an actual amount of wear of the cutting tool from data indicating a correlation between a rate of change in motor load current and an amount of wear of the cutting tool when the cutting tool collides with a workpiece.

Patent document 1: japanese patent laid-open publication No. H10-20911

Disclosure of Invention

However, in the technique of patent document 1, the amount of wear of the cutting tool is estimated without considering mounting abnormality of the workpiece, shape abnormality of the workpiece, and the like. That is, in the technique of patent document 1, it is impossible to distinguish between an increase in the motor load current due to wear of the cutting tool and an increase in the motor load current due to a change in the cutting region of the workpiece due to mounting abnormality of the workpiece, shape abnormality of the workpiece, or the like, and it is impossible to estimate an accurate wear amount.

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 accurately estimating the amount of wear of a cutting tool.

In order to solve the above problems and achieve the object, a numerical control device according to the present invention includes: a control unit that controls the machine tool based on the machining program; and a state observation unit that observes state variables including a load current value of a motor that drives a cutting tool used in the machine tool, a cutting position from the cutting tool to the workpiece, a tool type that is a type of the cutting tool, a workpiece type that is a type of the workpiece, and a workpiece temperature that is a temperature of the workpiece. Further, a numerical control device of the present invention includes: a data acquisition unit that acquires a wear amount measurement result that is a result of measuring a wear amount of a cutting tool; and a learning unit that generates a learning model for estimating the amount of wear of the cutting tool from the state variables, based on a data set created based on a combination of the state variables and the results of the measurement of the amount of wear.

ADVANTAGEOUS EFFECTS OF INVENTION

The numerical control device according to the present invention has an effect that the amount of wear of the cutting tool can be accurately estimated.

Drawings

Fig. 1 is a diagram showing a configuration of a control system including a numerical control device according to embodiment 1.

Fig. 2 is a flowchart showing a processing procedure of machine learning performed by the machine learning device according to embodiment 1.

Fig. 3 is a flowchart showing a procedure of estimated wear amount estimation processing by the machine learning device according to embodiment 1.

Fig. 4 is a diagram showing a configuration of a neural network used in the machine learning device according to embodiment 1.

Fig. 5 is a diagram showing an example of a hardware configuration for realizing the machine learning device according to embodiment 1.

Fig. 6 is a diagram showing a configuration of a control system including the numerical control device according to embodiment 2.

Fig. 7 is a diagram for explaining cutting start coordinates of a workpiece having no mounting error detected by the numerical control device according to embodiment 2.

Fig. 8 is a diagram for explaining cutting start coordinates of a workpiece having an attachment error detected by the numerical control device according to embodiment 2.

Detailed Description

The numerical control device and the machine learning device according to the embodiment of the present invention will be described in detail below with reference to the drawings.

Embodiment 1.

Fig. 1 is a diagram showing a configuration of a control system including a numerical control device according to embodiment 1. The Control system 100A includes a Numerical Control (NC) device 1A and a work machine 2A.

The numerical control device 1A is a computer that controls the machine tool 2A. The machine tool 2A is a device that machines a workpiece as a workpiece using a cutting tool. The work Machine 2A includes a drive unit 31, an HMI (Human Machine Interface) screen 32, a temperature sensor 33, and a wear amount measuring device 34.

The driving unit 31 drives the motor. The motors driven by the drive unit 31 are a servo motor and a spindle motor. When the cutting tool is driven by the servo motor, the drive unit 31 transmits a load current value of the servo motor to the numerical control device 1A as a motor load current value 41. When the cutting tool is driven by the spindle motor, the drive unit 31 transmits the load current value of the spindle motor to the numerical control device 1A as the motor load current value 41.

The HMI screen 32 is a screen for displaying information input by the operator. The HMI screen 32 is connected to an input device (not shown) that receives information input by an operator, and displays information transmitted from the input device. Examples of input devices are a mouse, a keyboard, etc.

The information input by the operator to the input device is a tool type 42 and a workpiece type 43. The tool type 42 and the workpiece type 43 displayed on the HMI screen 32 are transmitted to the numerical control device 1A. The tool type 42 is information indicating the type of the cutting tool, and the workpiece type 43 is information indicating the type of the workpiece. The workpiece type 43 includes information on the material of the workpiece, information on the shape of the workpiece, information on the size of the workpiece, and the like. The tool type 42 and the workpiece type 43 may be set by any method. In the following description, the tool type 42 and the workpiece type 43 input to the input device are transmitted to the HMI screen 32, and a case where the tool type 42 and the workpiece type 43 are transmitted from the HMI screen 32 to the numerical control device 1A will be described.

The temperature sensor 33 is an example of a temperature detection device capable of measuring the temperature of the workpiece. The temperature sensor 33 transmits the measured temperature to the numerical control device 1A as the workpiece temperature 44.

The wear amount measuring device 34 is a device for measuring the wear amount of the cutting tool. In the case where the wear amount measuring device 34 is a vernier caliper or the like that manually measures the amount of wear of the cutting tool, the wear amount measurement result 45, which is a measurement result of the amount of wear, is input to the numerical control device 1A by the operator. When the wear amount measuring device 34 is a device that automatically measures the wear amount of the cutting tool, the wear amount measuring device 34 transmits the wear amount measurement result 45 to the numerical control device 1A.

When the wear amount measuring device 34 is a device for manual measurement, the wear amount measuring device 34 is disposed outside the machine tool 2A, and when the wear amount measuring device 34 is a device for automatic measurement, the wear amount measuring device 34 is disposed inside the machine tool 2A. In the following description, a case will be described in which the wear measuring device 34 is an automatic measuring device, and the wear measurement result 45 is transmitted from the wear measuring device 34 to the numerical control device 1A.

The numerical control device 1A includes a machine learning device 10, a control unit 21, and an estimated wear amount reflecting unit 22. The control unit 21 controls the machine tool 2A using the machining program 20. Further, when executing the machining program 20, the control unit 21 calculates a cutting coordinate value 40 indicating a cutting position (tool coordinate) of the workpiece by the cutting tool based on the machining program 20. The control unit 21 transmits the cutting coordinate value 40 to the machine learning device 10.

The machine learning device 10 is a computer that learns the wear amount of a cutting tool based on information obtained when the cutting tool machines a workpiece. The machine learning device 10 has a function of learning the wear amount of the cutting tool and a function of estimating the wear amount of the cutting tool using the learning result. The machine learning device 10 outputs the estimated wear amount 75, which is the estimation result, to the estimated wear amount reflecting unit 22.

The machine learning device 10 includes a state observation unit 11A, a data acquisition unit 12, and a learning unit 13. The state observation unit 11A acquires the motor load current value 41, the tool type 42, the workpiece type 43, and the workpiece temperature 44 from the machine tool 2A.

Specifically, the state observation unit 11A acquires the motor load current value 41 from the drive unit 31, and acquires the tool type 42 and the workpiece type 43 from the HMI screen 32. Further, the state observing unit 11A acquires the workpiece temperature 44 from the temperature sensor 33. Further, the state observation unit 11A acquires the cutting coordinate value 40 from the control unit 21. The state observation unit 11A transmits the acquired cutting coordinate value 40, the motor load current value 41, the tool type 42, the workpiece type 43, and the workpiece temperature 44 to the learning unit 13.

The data acquisition unit 12 acquires the wear amount measurement result 45 from the wear amount measurement device 34. The data acquisition unit 12 transmits the acquired wear amount measurement result 45 to the learning unit 13.

The learning unit 13 learns the estimated wear amount 75 based on a data set created by a combination of the cutting coordinate value 40 output from the state observation unit 11A, the motor load current value 41, the tool type 42, the workpiece type 43, the workpiece temperature 44, and the wear amount measurement result 45 output from the data acquisition unit 12. Here, the data set is data in which the state variables and the determination data are associated with each other. In embodiment 1, the cutting coordinate value 40, the motor load current value 41, the tool type 42, the workpiece type 43, and the workpiece temperature 44 are state variables, and the wear amount measurement result 45 is determination data.

The learning unit 13 learns the estimated wear amount 75 by updating a learning model such as a neural network in a learning stage. The learning unit 13 adjusts the learning model so that the wear amount measurement result 45 is output from the learning model when the state variable is input to the learning model. The learning unit 13 stores the learning model.

In the effective use stage (estimation stage), if a state variable is received from the state observation unit 11A, the learning unit 13 inputs the state variable to the learning model. In this case, the estimated wear amount 75 corresponding to the state variable is output from the learning model. The learning unit 13 transmits the estimated wear amount 75 to the estimated wear amount reflecting unit 22.

The estimated wear amount reflection unit 22 calculates the correction amount 76 based on the estimated wear amount 75. The correction amount 76 is a position correction amount of the cutting tool for correcting the machining position of the workpiece relating to the cutting tool. The correction amount 76 is used to eliminate machining errors of the workpiece caused by wear of the cutting tool.

The estimated wear amount reflecting unit 22 serving as a reflecting unit reflects the correction amount 76 on the position of the cutting tool by transmitting the correction amount 76 to the control unit 21. The control unit 21 performs control of the machine tool 2A while correcting the position of the cutting tool by using the correction amount 76.

Next, a processing procedure of machine learning by the machine learning device 10 and a processing procedure of estimating the estimated wear amount 75 by the machine learning device 10 will be described. Fig. 2 is a flowchart showing a processing procedure of machine learning performed by the machine learning device according to embodiment 1.

The tool type 42 and the workpiece type 43 used for machining the workpiece are set in advance using the HMI screen 32. The state observation unit 11A acquires the tool type 42 and the workpiece type 43 from the HMI screen 32 (step S10).

The control unit 21 calculates the cutting coordinate values 40 based on the machining program 20 if execution of the machining program 20 is started. The state observation unit 11A acquires the cutting coordinate value 40 from the control unit 21 (step S20). The state observation unit 11A acquires the motor load current value 41 from the drive unit 31 (step S30), and acquires the workpiece temperature 44 from the temperature sensor 33 (step S40). The state observing unit 11A transmits the acquired data to the learning unit 13 (step S50). The data transmitted from the state observation unit 11A to the learning unit 13 are the cutting coordinate value 40, the motor load current value 41, the tool type 42, the workpiece type 43, and the workpiece temperature 44.

During machine learning, the data acquisition unit 12 acquires the wear amount measurement result 45 from the wear amount measurement device 34 (step S60). The data acquisition unit 12 transmits the acquired data to the learning unit 13 (step S70). That is, the data acquisition unit 12 transmits the wear amount measurement result 45 to the learning unit 13. Further, the processing of steps S10 to S70 may be performed in an arbitrary order.

The learning unit 13 learns the estimated wear amount 75 based on the data acquired by the state observation unit 11A and the data acquisition unit 12 (step S80). That is, the learning unit 13 generates a learning model based on a data set in which the state variables and the determination data are associated with each other. The learning unit 13 stores the learning model.

Fig. 3 is a flowchart showing a procedure of estimated wear amount estimation processing by the machine learning device according to embodiment 1. Among the processes shown in fig. 3, the same processes as those shown in fig. 2 will not be described.

The processing from step S10 to step S50 in the processing performed by the machine learning device 10 when the estimated wear amount 75 is estimated is the same as that in the machine learning. In step S50, after the state observation unit 11A transmits the acquired data to the learning unit 13, the learning unit 13 estimates the estimated wear amount 75 based on the learning model and the data acquired by the state observation unit 11A (step S90). That is, the learning unit 13 estimates the estimated wear amount 75 based on the state variables and the learning model. As described above, the learning unit 13 estimates the estimated wear amount 75 from the state variable acquired from the state observation unit 11A based on the learning result (learning model) generated using the data set in which the state variable and the determination data are associated with each other.

The learning unit 13 may update the learning model when estimating the estimated wear amount 75. In other words, the learning unit 13 can learn the estimated wear amount 75 while estimating the estimated wear amount 75.

The learning unit 13 transmits the estimated wear amount 75 to the estimated wear amount reflecting unit 22. The estimated wear amount reflection unit 22 calculates a correction amount 76 for correcting the position of the cutting tool based on the acquired estimated wear amount 75. The estimated wear amount reflection unit 22 transmits the calculated correction amount 76 to the control unit 21. The control unit 21 controls the machine tool 2A using the correction amount 76 and the machining program 20.

Here, a relationship between each data acquired by the state observing unit 11A and the wear amount measurement result 45 acquired by the data acquiring unit 12 will be described. As the cutting tool wears and the sharpness decreases, the resistance between the workpiece and the cutting tool increases, and therefore the motor load current value 41 increases. Further, when the cutting region of the cutting tool changes due to an attachment error of the workpiece, fluctuation in the shape of the workpiece, expansion of the workpiece, or the like, the motor load current value 41 also changes.

The machine learning device 10 uses the cutting coordinate value 40 to determine whether the change in the motor load current value 41 is caused by wear of the cutting tool or by a change in the cutting region.

The machine learning device 10 determines that the motor load current value 41 has changed due to wear of the cutting tool if the motor load current value 41 changes at a timing at which the cutting coordinate value 40 has reached a predetermined normal coordinate. In this case, the machine learning device 10 adjusts the learning model so that the estimated wear amount 75 approaches the wear amount measurement result 45. That is, the machine learning device 10 adjusts the learning model so that the estimated wear amount 75 approaches the wear amount measurement result 45 as the cutting coordinate value 40 approaches the normal coordinate.

On the other hand, if the motor load current value 41 changes at a timing when the cutting coordinate value 40 is not the preset normal coordinate, the machine learning device 10 determines that the cutting region has changed due to a mounting error of the workpiece or the like, and thus the motor load current value 41 changes. In this case, the machine learning device 10 adjusts the learning model so that the estimated wear amount 75 does not approach the wear amount measurement result 45. That is, the machine learning device 10 adjusts the learning model so that the estimated wear amount 75 is farther from the wear amount measurement result 45 as the cutting coordinate value 40 is farther from the normal coordinate.

Further, if the material or shape of the cutting tool and the workpiece is changed, the amount of wear of the cutting tool changes even in the same machining. Therefore, the machine learning device 10 adjusts the learning model based on the tool type 42 and the workpiece type 43.

In addition, if the workpiece temperature 44 changes, the workpiece itself may deform, and therefore if the workpiece temperature 44 changes, the cutting area may change. For example, if the workpiece temperature 44 is increased, the workpiece expands, and thus the cutting area becomes large. In this case, the motor load current value 41 also increases with an increase in the workpiece temperature 44. That is, if the workpiece temperature 44 changes, the motor load current value 41 also changes. Therefore, the machine learning device 10 adjusts the learning model based on the workpiece temperature 44.

As described above, the machine learning device 10 is used to learn the estimated wear amount 75 corresponding to the cutting coordinate value 40, the motor load current value 41, the tool type 42, the workpiece type 43, and the workpiece temperature 44. The machine learning device 10 may be a separate device independent of the numerical control device 1A, connected to the numerical control device 1A via a network, for example. The machine learning device 10 may be incorporated in the numerical control device 1A. The machine learning device 10 may also be present on a cloud server.

The learning unit 13 learns the estimated wear amount 75 by so-called teacher learning, for example, according to a neural network model. Here, the teacher learning means a model in which a large number of data sets of a certain input and a result (label) are given to a learning device, so that features existing in these data sets are learned, and the result is estimated from the input.

The neural network is composed of an input layer composed of a plurality of neurons, an intermediate layer (hidden layer) composed of a plurality of neurons, and an output layer composed of a plurality of neurons. The intermediate layer may be 1 layer or 2 or more layers.

Fig. 4 is a diagram showing a configuration of a neural network used in the machine learning device according to embodiment 1. For example, in the case of the 3-layer neural network shown in fig. 4, if a plurality of inputs are input to the input layers X1 to X3, the values are multiplied by weights w11 to w16 and input to the intermediate layers Y1 and Y2, and the results are further multiplied by weights w21 to w26 and output from the output layers Z1 to Z3. The output result changes depending on the values of the weights w11 to w16 and the weights w21 to w 26.

The neural network of embodiment 1 learns the estimated wear amount 75 by so-called teacher learning, for a data set created based on a combination of the cutting coordinate value 40, the motor load current value 41, the tool type 42, the workpiece type 43, the workpiece temperature 44, and the wear amount measurement result 45.

That is, the neural network learns the estimated wear amount 75 by adjusting the weights w11 to w16 and w21 to w26 so that the results output from the output layers Z1 to Z3 approach the wear amount measurement result 45 by inputting the cutting coordinate value 40, the motor load current value 41, the tool type 42, the workpiece type 43, and the workpiece temperature 44. The learning unit 13 stores the neural network in which the weights w11 to w16 and w21 to w26 are adjusted.

The neural network can also learn the estimated wear amount 75 by so-called teachers-less learning. The teacher-less learning is a method of learning what distribution the input data is distributed by giving only a large amount of input data to the machine learning device, and learning a device that compresses, classifies, shapes, and the like the input data without giving corresponding teacher data (output data). In teachers-less learning, feature similarities existing in these data sets can be clustered with each other, and the like. By performing the output allocation such that no teacher learns which reference is set and is optimal using the result, the output can be predicted. As a problem setting in the middle of teacher-less learning and teacher-less learning, there is learning called half-teacher learning, which is a case where only a part of a data group is input and output, and only input data other than the part is present.

The learning unit 13 may learn the estimated wear amount 75 from a data set created for the plurality of numerical control devices 1A. The learning unit 13 may acquire data sets from a plurality of work machines 2A used at the same site, or may learn the estimated wear amount 75 using data sets collected from a plurality of work machines 2A independently operating at different sites. Further, the numerical control device that collects the data set may be added to the object in the middle or removed from the object in the opposite way. In addition, in a certain numerical control device, a machine learning device that learns the estimated wear amount 75 may be attached to another numerical control device, and the estimated wear amount 75 may be re-learned and updated in the other numerical control device.

As the Learning algorithm used in the Learning unit 13, deep Learning (Deep Learning) for Learning the extraction of the feature quantity itself may be used, and the Learning unit 13 may execute machine Learning by other known methods, for example, genetic programming, functional logic programming, support vector machine, and the like.

Here, a hardware configuration of the machine learning device 10 will be described. Fig. 5 is a diagram showing an example of a hardware configuration for realizing the machine learning device according to embodiment 1. The machine learning device 10 can be realized by an input device 103, a processor 101, a memory 102, a display device 105, and an output device 104.

Examples of the Processor 101 are a CPU (also referred to as a Central Processing Unit, a Processing device, an arithmetic device, a microprocessor, a microcomputer, a DSP (Digital Signal Processor)) or a system LSI (Large Scale Integration). Examples of the Memory 102 are a RAM (Random Access Memory) and a ROM (Read Only Memory).

The machine learning device 10 is realized by the processor 101 reading out and executing a computer-executable learning program stored in the memory 102 for executing the operation of the machine learning device 10. The learning program that is a program for executing the operation of the machine learning device 10 can be said to cause a computer to execute the procedure or method of the machine learning device 10.

The learning program executed by the machine learning device 10 has a module configuration including the state observation unit 11A, the data acquisition unit 12, and the learning unit 13, and these are downloaded to the main storage device, and are generated on the main storage device.

The input device 103 receives the motor load current value 41, the tool type 42, the workpiece type 43, and the workpiece temperature 44, which are state variables, from the machine tool 2A, and inputs them to the processor 101. The input device 103 receives the wear amount measurement result 45 as determination data from the machine tool 2A, and inputs the result to the processor 101. The input device 103 receives the cutting coordinate value 40 as a state variable from the control unit 21 and inputs the received value to the processor 101.

The memory 102 is used as a temporary memory when various processes are executed by the processor 101. The memory 102 stores cutting coordinate values 40, motor load current values 41, tool types 42, workpiece types 43 and workpiece temperatures 44, wear amount measurement results 45, estimated wear amounts 75, and the like. The output device 104 outputs the estimated wear amount 75 and the like to the estimated wear amount reflecting unit 22.

The display device 105 displays the cutting coordinate value 40, the motor load current value 41, the tool type 42, the workpiece type 43, the workpiece temperature 44, the wear amount measurement result 45, the estimated wear amount 75, and the like. An example of the display device 105 is a liquid crystal monitor.

The learning program may be provided as a computer program product by being stored in a computer-readable storage medium in an installable form or an executable form of a file. The learning program may be provided to the machine learning device 10 via a network such as the internet. The functions of the machine learning device 10 may be partly implemented by dedicated hardware such as a dedicated circuit, and partly implemented by software or firmware. The numerical control device 1A can also be realized by the same hardware configuration as the machine learning device 10.

The machine tool 2A performs machining while a workpiece is fixed in the machine tool 2A, but in addition to an attachment error at the time of workpiece attachment, deformation of the workpiece or the like may occur due to a size of the workpiece itself, fluctuation in a shape of the workpiece, a temperature change of the workpiece, and the like. Due to these factors, even in the same machining, the cutting area of the workpiece changes, and thus the wear amount of the cutting tool changes. In addition, since the cutting tool is worn, resistance between the workpiece and the cutting tool becomes large, and thus the motor load current value 41 necessary for machining increases. In addition, when a mounting error of the workpiece or a fluctuation in the shape of the workpiece is large, the workpiece accuracy of the finished product may be affected.

In embodiment 1, the numerical control device 1A can estimate the estimated wear amount 75 of the cutting tool with high accuracy because the estimated wear amount 75 is estimated based on the motor load current value 41, the workpiece temperature 44, and the cutting coordinate value 40 in order to take into account the influence of the mounting error of the workpiece, the fluctuation in the shape of the workpiece, and the like. Therefore, the numerical control device 1A can calculate the correction amount 76 with high accuracy based on the estimated wear amount 75 estimated with high accuracy.

Since the calculated correction amount 76 is automatically reflected in the control unit 21, the numerical control device 1A can be continuously operated for a long period of time without manual operation by an operator, and productivity is improved.

As described above, in embodiment 1, the numerical control device 1A includes the state observation unit 11A, the data acquisition unit 12, and the learning unit 13. The state observation unit 11 observes state variables including the motor load current value 41, the cutting coordinate value 40 that is the cutting position from the cutting tool to the workpiece, the tool type 42, the workpiece type 43, and the workpiece temperature 44. The data acquisition unit 12 acquires a wear amount measurement result 45, which is a result of measuring the wear amount of the cutting tool. The learning unit 13 generates a learning model for estimating the amount of wear of the cutting tool from the state variables, based on the data set created based on the combination of the state variables and the wear amount measurement results 45. As described above, the numerical control device 1A estimates the wear amount in consideration of the mounting abnormality of the workpiece, the shape abnormality of the workpiece, and the like, using the cutting coordinate value 40, the motor load current value 41, and the workpiece temperature 44, and thus can accurately estimate the wear amount of the cutting tool.

Embodiment 2.

Next, embodiment 2 will be described with reference to fig. 6 to 8. In embodiment 2, the numerical control device detects an abnormality of a workpiece such as an abnormality of a mounting position of the workpiece or an abnormality of a shape of the workpiece.

Fig. 6 is a diagram showing a configuration of a control system including a numerical control device according to embodiment 2. Of the components of fig. 6, those having the same functions as those of the numerical control device 1A of embodiment 1 shown in fig. 1 are given the same reference numerals, and redundant description thereof is omitted.

The control system 100B includes a numerical control device 1B and a work machine 2B. The numerical control device 1B is a computer that controls the work machine 2B. The numerical control device 1B has a function of detecting an abnormality or the like in the mounting position of a workpiece and a function of calculating the mounting error amount of the workpiece. The machine tool 2B is a device for machining a workpiece with a cutting tool, similarly to the machine tool 2A. The work machine 2A has a drive unit 31 and an HMI screen 32.

The information input by the operator to the input device connected to the HMI screen 32 is the tool type 42, the workpiece type 43, and the error threshold 46. The error threshold 46 is a threshold for determining whether or not the attachment error amount of the workpiece is within an allowable range. That is, the error threshold 46 is a threshold for determining whether or not to issue a warning with respect to the mounting error amount of the workpiece. The mounting error amount of the workpiece is calculated based on cutting start coordinates, which are start positions of cutting of the workpiece by the cutting tool. The difference between the normal cutting start coordinate and the actual cutting start coordinate is the mounting error amount of the workpiece.

The numerical control device 1B includes a control unit 21, a state observation unit 11B, an abnormality determination device 50, and an error amount calculation device 60. The abnormality determination device 50, the error amount calculation device 60, and the numerical control device 1B can be realized by the same hardware configuration as the machine learning device 10. The state observation unit 11B of the numerical control device 1B acquires the motor load current value 41, the tool type 42, the workpiece type 43, and the error threshold value 46 from the machine tool 2B.

Specifically, the state observation unit 11B acquires the motor load current value 41 from the drive unit 31, and acquires the tool type 42, the workpiece type 43, and the error threshold value 46 from the HMI screen 32. Further, the state observation unit 11B acquires the cutting coordinate value 40 from the control unit 21. The state observation unit 11B transmits the acquired cutting coordinate value 40, the motor load current value 41, the tool type 42, the workpiece type 43, and the error threshold value 46 to the abnormality determination device 50.

The abnormality determination device 50 is a device that determines whether or not the amount of mounting error of the workpiece, the shape of the workpiece, or the like exceeds a preset error threshold 46. The error amount calculation device 60 is a device that calculates the installation error amount of the workpiece.

The abnormality determination device 50 includes a mounting abnormality determination unit 52 and a warning display unit 51. The error amount calculation device 60 includes an error amount calculation unit 62 and a calculation result display unit 61.

The mounting abnormality determination unit 52 receives the motor load current value 41, the cutting coordinate value 40, the tool type 42, the workpiece type 43, and the error threshold value 46 output from the state observation unit 11B. The mounting abnormality determination unit 52 detects a cutting start coordinate, which is a start position of cutting, based on the motor load current value 41 and the cutting coordinate value 40.

Here, the cutting start coordinate will be described. Fig. 7 is a diagram for explaining cutting start coordinates of a workpiece having no mounting error detected by the numerical control device according to embodiment 2. Fig. 8 is a diagram for explaining cutting start coordinates of a workpiece having an attachment error detected by the numerical control device according to embodiment 2.

In fig. 7 and 8, a case will be described where the Z-axis direction is a vertical direction and an XY plane parallel to the upper surface of the machining table 85 on which the workpiece 80 is mounted is a horizontal plane. That is, 2 axes within a plane parallel to the upper surface of the machining table 85 and orthogonal to each other are defined as X and Y axes. In addition, an axis orthogonal to the X axis and the Y axis is a Z axis.

In fig. 7, the workpiece 80 is shown as being mounted straight without being tilted with respect to the machining table 85. Fig. 8 shows a case where the workpiece 80 is mounted in a state of being inclined with respect to the processing table 85.

For example, the cutting tool 71 machines the workpiece 80 from the Z-axis direction. In this case, the cutting tool 71 moves from the upper side of the workpiece 80 and contacts the workpiece 80.

In the case where there is no mounting error of the workpiece 80 to the machining table 85, the machining of the workpiece 80 is started after the cutting tool 71 comes into contact with the workpiece 80 at the desired cutting start coordinates (X1, Z1). In this case, since the cutting tool 71 is in contact with the workpiece 80 at the cutting start coordinates (X1, Z1), the motor load current value 41 sharply increases at the cutting start coordinates (X1, Z1). Then, the cutting tool 71 performs machining in the Z-axis direction with respect to the workpiece 80, thereby machining a machining region 81 extending in the Z-axis direction in the workpiece 80.

On the other hand, when there is an error in mounting the workpiece 80 on the machining table 85, the cutting tool 71 starts machining the workpiece 80 after coming into contact with the workpiece 80 at the cutting start coordinates (X2, Z2) different from the desired cutting start coordinates (X1, Z1). In this case, since the cutting tool 71 is in contact with the workpiece 80 at the cutting start coordinates (X2, Z2), the motor load current value 41 sharply increases at the cutting start coordinates (X2, Z2). Then, the cutting tool 71 performs machining in the Z-axis direction with respect to the workpiece 80, thereby machining a machining region 82 in a lower portion of the workpiece 80. The processing region 82 is a region different from the processing region 81.

As described above, when there is an attachment error of the workpiece 80, the cutting start coordinate changes compared to the case where there is no attachment error. Likewise, in the case where there is fluctuation in the shape of the workpiece 80, the cutting start coordinates change as compared with the case where there is no fluctuation in the shape of the workpiece 80. In addition, when the workpiece 80 expands or contracts, the cutting start coordinate also changes compared to the case where the workpiece 80 does not expand or contract.

The mounting abnormality determination unit 52 determines that the workpiece 80 is abnormal when the coordinate difference, which is the difference between the changed cutting start coordinates (X2, Z2) and the cutting start coordinates (X1, Z1) during normal operation, exceeds the preset error threshold 46. The abnormality of the workpiece 80 is an abnormality in attachment of the workpiece 80 to the machining table 85, an abnormality in shape of the workpiece 80, or the like.

The normal cutting start coordinates are different for each combination of the tool type 42 and the workpiece type 43. Therefore, the mounting abnormality determination unit 52 determines whether or not there is an abnormality in the workpiece 80 using the cutting start coordinates in the normal state corresponding to the combination of the tool type 42 and the workpiece type 43.

When detecting an abnormality, the attachment abnormality determination unit 52 transmits abnormality information indicating the abnormality determination to the warning display unit 51. The mounting abnormality determination unit 52 sends the start position error, the tool type 42, and the workpiece type 43, which are the coordinate difference between the changed cutting start coordinate and the cutting start coordinate at the time of normality, to the error amount calculation unit 62.

Upon receiving the abnormality information from the mounting abnormality determination unit 52, the warning display unit 51 displays a warning indicating that the workpiece 80 is abnormal, and warns the operator of the machining accuracy of the finished workpiece 80. The warning display unit 51 is not limited to displaying a warning, and may output a warning by any method. For example, the warning display section 51 may output a warning sound.

If the starting position error is received from the mounting abnormality determination unit 52, the error amount calculation unit 62 calculates the workpiece mounting error amount based on the starting position error, the tool type 42, and the workpiece type 43, assuming that the shape of the workpiece 80 is normal. The error amount calculation unit 62 transmits the calculation result, i.e., the workpiece attachment error amount, to the calculation result display unit 61. The calculation result display 61, upon receiving the workpiece attachment error amount from the error amount calculation 62, displays the received workpiece attachment error amount to alert the operator to the machining accuracy of the finished workpiece 80. As described above, since the numerical control device 1B warns the operator when there is an abnormality such as a workpiece mounting error, it is possible to prevent a defective product of the finished workpiece 80 from flowing out.

Further, the numerical control devices 1A and 1B may be combined. That is, the numerical control device 1A may include the abnormality determination device 50, and the numerical control device 1A may include the abnormality determination device 50 and the error amount calculation device 60. The numerical control device 1B may include the machine learning device 10, and the numerical control device 1B may include the machine learning device 10 and the estimated wear amount reflecting unit 22.

As described above, in embodiment 2, the numerical control device 1B detects an abnormality of the workpiece, such as an abnormality in the mounting position of the workpiece or an abnormality in the shape of the workpiece, using the cutting coordinate value 40, the motor load current value 41, and the error threshold value 46. Thus, the numerical control device 1B can output a warning or the like when an abnormality of the workpiece occurs.

The configurations shown in the above embodiments are merely examples, and may be combined with other known techniques, or may be combined with each other, and some of the configurations may be omitted or modified without departing from the scope of the invention.

Description of the reference symbols

1A, 1B numerical control device, 2A, 2B machine tool, 10 machine learning device, 11A, 11B state observation unit, 12 data acquisition unit, 13 learning unit, 20 machining program, 21 control unit, 22 estimated wear amount reflection unit, 31 drive unit, 32HMI screen, 33 temperature sensor, 34 wear amount measurement device, 40 cutting coordinate value, 41 motor load current value, 42 tool type, 43 workpiece type, 44 workpiece temperature, 45 wear amount measurement result, 46 error threshold value, 50 abnormality determination device, 51 warning display unit, 52 mounting abnormality determination unit, 60 error amount calculation device, 61 calculation result display unit, 62 error amount calculation unit, 71 cutting tool, 75 estimated wear amount, 76 correction amount, 80 workpiece, 81, 82 machining region, 85 machining table, 100A, 100B control system, 101 processor, 102 memory, 103 input device, 104 output device, 105 display device, X1 to X3 input layer, Y1, Y2, Z1 to Z3 output layer.

Claims

1. A numerical control apparatus, comprising:

a control unit that controls the machine tool based on the machining program;

a state observation unit that observes state variables including a load current value of a motor that drives a cutting tool used in the machine tool, a cutting position from the cutting tool to a workpiece, a tool type that is a type of the cutting tool, a workpiece type that is a type of the workpiece, and a workpiece temperature that is a temperature of the workpiece;

a data acquisition unit that acquires a wear amount measurement result that is a result of measuring a wear amount of the cutting tool; and

and a learning unit that generates a learning model for estimating the amount of wear of the cutting tool from the state variables, based on a data set created based on a combination of the state variables and the wear amount measurement results.

2. The numerical control apparatus according to claim 1,

the learning unit estimates an amount of wear of the cutting tool from the state variable using the learning model.

3. The numerical control apparatus according to claim 2,

the present invention further includes a reflecting unit that calculates a position correction amount for correcting the position of the cutting tool based on the wear amount estimated by the learning unit, and that reflects the position correction amount on the position of the cutting tool by transmitting the position correction amount to the control unit.

4. The numerical control apparatus according to any one of claims 1 to 3,

the machining device further includes an abnormality determination device that calculates a cutting start coordinate that is a coordinate at which the cutting tool starts machining the workpiece based on the cutting position and the load current value, and outputs a warning when a coordinate difference that is a difference between the cutting start coordinate and the coordinate at which the cutting tool starts machining the workpiece in a state where the workpiece is normal exceeds a threshold value.

5. The numerical control apparatus according to claim 4,

further, an error amount calculation device is provided which estimates an attachment error amount of the workpiece in a case where the shape of the workpiece is assumed to be normal based on the coordinate difference, and outputs the attachment error amount.

6. A machine learning device, comprising:

a data acquisition unit that acquires a wear amount measurement result that is a result of measuring the wear amount of the cutting tool; and