JP7049531B1 - Numerical control device - Google Patents

Abstract

The numerical control device (100) is a section for cutting on the cutting path when cutting the work, based on the processing information (103) obtained by controlling the machine tool to cut the work. A speed map creation unit (102) that identifies a portion and a non-cut portion that is a section not to be cut, and creates a speed map having information on a feed speed in the non-cut portion and a feed speed in the cut portion, and a speed map. A speed map database (105) for holding the machine tool and a command output unit (107) for generating commands to the machine tool based on the speed map.

Description

The present disclosure relates to a numerical control device for controlling a machine tool.

Machine tools are required to improve processing efficiency in order to reduce costs and man-hours. Adaptive control is a method of shortening the machining time. Adaptive control monitors the machining state using a signal obtained by a sensor or the like, and changes the machining conditions in real time according to the machining state.

A numerical control device that performs adaptive control is described in Patent Document 1. In the numerical control device described in Patent Document 1, the cycle time is shortened and the machining time is shortened by controlling the feed rate of the shaft according to the spindle load value of the spindle motor.

JP-A-2017-0970701

However, when the control is performed according to the spindle load value, the speed control starts after detecting the change in the spindle load value due to the tool coming into contact with the work, and the tool comes into contact with the work at the timing when the speed control is started. It will be later than the timing to do it. That is, there may be a discrepancy between the speed described in the machining program and the actual speed.

The present disclosure has been made in view of the above, and an object of the present disclosure is to suppress the difference between the speed described in the machining program and the actual speed.

In order to solve the above-mentioned problems and achieve the object, the numerical control device according to the present disclosure is used when cutting a workpiece based on machining information obtained by cutting a workpiece by controlling a machine tool. Identify the cutting section that is the section where cutting is performed and the non-cutting section that is not cutting on the cutting path of It is equipped with a speed map creation unit. Further, the numerical control device includes a speed map database that holds a speed map, and a command output unit that generates commands to the machine tool based on the speed map. If the speed map database holds a speed map specified by the machining program or the user, the command output unit generates a command to the machine tool based on the machining program or the speed map specified by the user , and the machining program or the user can generate a command. If the speed map database does not hold the specified speed map, a command to the machine tool is generated based on the machining program, and if a different speed map is specified by the machining program and the user, the command to the machine machine is specified by the user. Generated based on the speed map created.

The numerical control device according to the present disclosure has an effect of suppressing the difference between the speed described in the machining program and the actual speed.

The figure which shows the structural example of the numerical control apparatus which concerns on Embodiment 1. The figure which shows an example of the machining information generated by the data acquisition part of the numerical control apparatus which concerns on Embodiment 1. The figure which shows the configuration example of the speed map creation part of the numerical control device which concerns on Embodiment 1. The figure which shows an example of the speed map created by the speed map creation part of the numerical control device which concerns on Embodiment 1. A flowchart showing an example of the operation of the speed map creating unit of the numerical control device according to the first embodiment. A flowchart showing an example of the operation of the command output unit of the numerical control device according to the first embodiment. The figure which shows an example of the machining operation performed by using the numerical control device which concerns on Embodiment 1. The figure which shows the speed map corresponding to the machining operation shown in FIG. The figure which shows the hardware configuration example of the numerical control apparatus which concerns on Embodiment 1. The first figure which shows the structural example of the numerical control apparatus which concerns on Embodiment 2. The second figure which shows the structural example of the numerical control apparatus which concerns on Embodiment 2. The figure which shows the structural example of the machine learning apparatus provided in the numerical control apparatus which concerns on Embodiment 2. Diagram showing a configuration example of a neural network A flowchart showing an example of the operation of the machine learning device according to the second embodiment. The figure which shows the structural example of the inference device provided in the numerical control device which concerns on Embodiment 2. A flowchart showing an example of the operation of the inference device according to the second embodiment.

Hereinafter, the numerical control device according to the embodiment of the present disclosure will be described in detail with reference to the drawings.

Embodiment 1.
FIG. 1 is a diagram showing a configuration example of a numerical control device according to the first embodiment. The numerical control device 100 according to the first embodiment includes a data collection unit 101, a speed map creation unit 102, a speed map database 105, a graphical user interface unit (GUI unit) 106, and a command output unit 107. The GUI unit 106 includes a speed map display unit 108 and a speed map selection unit 109. The numerical control device 100 having such a configuration is connected to an amplifier 120 for driving a motor included in a machine tool (not shown), generates a command for controlling the machine tool, and outputs the command to the amplifier 120.

In the numerical control device 100 shown in FIG. 1, the operation differs depending on whether or not the speed map creating unit 102 has created the speed map. Specifically, the numerical control device 100 generates a command according to the machining program 110 and outputs the command to the amplifier 120 in a state where the speed map has not been created, and also creates the speed map. Further, the numerical control device 100 generates a command according to the speed map and outputs it to the amplifier 120 in a state where the speed map has been created.

Hereinafter, the operation of each part of the numerical control device 100 will be described.

The data collection unit 101 collects information output by the amplifier 120 while the machine tool is processing by outputting a command to the amplifier 120 by the command output unit 107, which will be described later, and processing information is based on the collected information. Generate 103. The data collection unit 101 generates machining information 103 when the speed map has not been created by the speed map creation unit 102, which will be described later. The data acquisition unit 101 may generate the machining information 103 while the machine tool is machining, regardless of whether or not the speed map creation section 102, which will be described later, has created the speed map. good.

The machining information 103 includes a spindle load value and a movement command value. The details of the processing information 103 will be described separately. The data collection unit 101 outputs the generated processing information 103 to the speed map creation unit 102.

Based on the machining information 103 generated by the data collecting section 101 and the predetermined cutting determination threshold value 104, the speed map creating unit 102 determines which of the time between the start of machining of the work and the end of machining by the machine tool. It is determined whether cutting was performed in time, and a velocity map is created based on the determination result. The speed map is information for increasing the speed of the non-cut portion, and the details will be described separately. The speed here means the feed speed of the tool. The speed map creation unit 102 registers the created speed map in the speed map database 105.

The command output unit 107 is the machining program 110 at the time of the first machining, that is, when the speed map creation unit 102 has not completed the creation of the speed map and the speed map is not registered in the speed map database 105. A command is generated according to the above and output to the amplifier 120. Further, the command output unit 107 acquires a speed map from the speed map database 105 at the time of the second and subsequent machining, that is, when the speed map is registered in the speed map database 105, and is based on the speed map. That is, the machining time is shortened by generating a command for moving the tool at the speed indicated by the speed map and outputting it to the amplifier 120.

Here, the machine tool does not always perform the same machining on a workpiece of the same material, but by changing the machining program 110 executed by the numerical control device 100 that controls the machine tool, the workpiece can be made of various materials. It is possible to process under various conditions. Therefore, the speed map creating unit 102 of the numerical control device 100 creates a speed map for each of various cases determined by the material of the work, the tool used for machining, the target shape of the product obtained by machining, and the speed. Register in the map database 105. The user of the numerical control device 100 selects a speed map corresponding to the machining operation to be executed by the machine tool from the speed maps registered in the speed map database 105. At this time, the GUI unit 106 is used. That is, the user of the numerical control device 100 can select any speed map from the speed maps registered in the speed map database 105 via the GUI unit 106.

FIG. 2 is a diagram showing an example of machining information 103 generated by the data acquisition unit 101 of the numerical control device 100 according to the first embodiment.

As shown in FIG. 2, the machining information 103 includes a spindle load value l and a movement command value p for each time t. The movement command value p is, for example, information for designating the position of the movement destination of each axis of the machine tool. The movement command value p may be information that specifies the position of the movement destination of an arbitrary point on the movable part of the machine tool, for example, the position of the movement destination of an arbitrary point on the tool. The unit of the time t is the output cycle of the command from the numerical control device 100 to the amplifier 120, and the time t represents the cumulative time from the start of machining. The spindle load value l and the movement command value p are information fed back from the machine tool via the amplifier 120. It is not necessary to acquire the time t from the machine tool via the amplifier 120, but the time t may be fed back in addition to the spindle load value l and the movement command value p.

FIG. 3 is a diagram showing a configuration example of the speed map creating unit 102 of the numerical control device 100 according to the first embodiment.

The speed map creation unit 102 includes a cutting / non-cutting determination unit 201, a speed map generation unit 202, and a speed map registration unit 204.

The cutting / non-cutting determination unit 201 determines cutting / non-cutting based on the machining information 103 and the cutting determination threshold value 104. That is, the cutting / non-cutting determination unit 201 determines whether the machine tool during the machining operation is in the cutting state where the workpiece is being cut or the non-cutting state in which the workpiece is not being cut, based on the machining information 103 and the cutting determination threshold value 104. judge. The cutting / non-cutting determination unit 201 determines that the spindle load value included in the machining information 103 is larger than the cutting determination threshold value 104, the cutting state is determined, and the spindle load value is the cutting determination threshold value 104 or less, the cutting state is determined. The cutting / non-cutting determination unit 201 is a state determination unit.

The speed map generation unit 202 generates the speed map 203 based on the cutting / non-cutting determination result by the cutting / non-cutting determination unit 201 and the machining condition parameter 205. The machining condition parameter 205 includes a cutting feed time constant and a cutting feed limit speed. An example of the speed map 203 is shown in FIG. FIG. 4 is a diagram showing an example of a speed map 203 created by the speed map creating unit 102 of the numerical control device 100 according to the first embodiment.

The speed map 203 includes position information for each axis and a speed command value at the switching position of the command speed. The switching position of the command speed is a position determined based on the position where the judgment result by the cutting / non-cutting determination unit 201 changes. Specifically, the switching position from the non-cutting state to the cutting state, or cutting. It is a position determined based on the switching position from the state to the non-cutting state. The switching position of the command speed when switching from the non-cutting state to the cutting state is the position where the deceleration time is added from the switching position from the non-cutting state to the cutting state. The switching position of the command speed when switching from the cutting state to the non-cutting state coincides with the switching position from the cutting state to the non-cutting state. That is, the speed map 203 shows the position from the cutting state to the non-cutting state, the command speed which is the target speed at the time of non-cutting, the position to start deceleration before the non-cutting state changes to the cutting state, and the cutting time. It consists of the command speed, which is the target speed. The target speed is the feed speed of the tool described in the machining program 110.

The speed map registration unit 204 registers the speed map generated by the speed map generation unit 202 in the speed map database 105.

FIG. 5 is a flowchart showing an example of the operation of the speed map creating unit 102 of the numerical control device 100 according to the first embodiment.

The speed map creation unit 102 first reads the machining information 103 output from the data collection unit 101 (step S11). In this step S11, the speed map creation unit 102 reads one record of the machining information 103. More specifically, the speed map creation unit 102 is among the sets of the time t, the spindle load value l, and the movement command value p included in the machining information 103, which are not read in the previously executed step S11. Read the oldest set of times.

Next, the speed map creation unit 102 determines the non-cutting unit existing on the cutting path in the cutting / non-cutting determination unit 201 based on the machining information 103 and the cutting determination threshold value 104. The non-cutting part is a section where cutting is not performed. That is, the cutting / non-cutting determination unit 201 uses the machining information 103 and the cutting determination threshold value 104 to cut the workpiece in which section of the cutting path, which is the path through which the tool moves when machining the workpiece, and in which section. It is determined whether or not the work is to be cut in (step S12). In the following description, for convenience, a section for cutting on the cutting path, specifically, a section where the spindle load value is larger than the cutting determination threshold value 104 is referred to as a cutting portion. Further, the section where the spindle load value is equal to or less than the cutting threshold is the above-mentioned non-cutting portion.

Next, the cutting / non-cutting determination unit 201 determines whether or not the switching between the cutting unit and the non-cutting unit, that is, whether or not the latest determination result in step S12 is switched from the previous determination result in step S12. Is determined (step S13). If the cutting portion and the non-cutting portion are not switched (step S13: No), the process returns to step S11, the machining information 103 is read, and the cutting / non-cutting determination is performed again.

When the cut portion and the non-cut portion are switched (step S13: Yes), the speed map generation unit 202 calculates the acceleration / deceleration time (step S14). The acceleration / deceleration time here is a time for accelerating the feed rate of the tool at a predetermined acceleration and a time for decelerating the feed rate of the tool at a predetermined deceleration. In step S14, the speed map generation unit 202 sets the continuous time of the non-cutting portion and the machining information 103 specified from the determination result in step S12 at the first change point of switching from the non-cutting portion to the cutting portion. The acceleration / deceleration time is calculated from the included movement command value. For example, the speed map generation unit 202 decelerates so that the feed rate of the tool is reduced to a speed suitable for cutting the work before the time when the non-cutting portion ends, that is, before the time when the cutting portion starts. Calculate the time. In order to shorten the machining time, it is desirable that the timing at which the feed rate of the tool becomes a speed suitable for cutting the work coincides with the start timing of the cutting portion. On the other hand, due to the relationship between the set value of the cutting determination threshold value 104 and the spindle load value, there is a possibility that an error may be included in the determination result by the cutting / non-cutting determination unit 201. Therefore, the speed map generation unit 202 may calculate the deceleration time in consideration of the above error. By doing so, it is possible to prevent the machining accuracy from deteriorating when an error is included in the determination result by the cutting / non-cutting determination unit 201. The above-mentioned "speed suitable for cutting the work" is the feed speed of the tool when cutting the work, which is specified by the command described in the machining program 110. Further, in step S14, the speed map generation unit 202 accelerates the feed speed of the tool at a predetermined acceleration after the start of the non-cutting portion at the second change point where the cutting portion is switched to the non-cutting portion (acceleration). Time) is calculated.

Next, the speed map generation unit 202 calculates the command speed in consideration of the acceleration / deceleration time calculated above, and updates the speed map (step S15). Updating the map means adding a line to the map.

When the speed map update process in step S15 is completed, has the speed map creation unit 102 read all the machining information 103, that is, has the reading of all the records of the machining information 103 completed in the above step S11 to be repeatedly executed? Is confirmed (step S16). If the reading is not completed (step S16: No), the process returns to step S11. When the reading is completed (step S16: Yes), the speed map registration unit 204 registers the speed map updated in step S15 in the speed map database 105 (step S17).

After the speed map creation unit 102 completes the creation of the speed map, the numerical control device 100 controls the machine tool using the created speed map to perform machining. In machining using a speed map, if there is a problem with one or both of the machining time and the machining result, the speed map creation unit 102 re-executes the series of processes shown in FIG. 5 after adjusting the cutting determination threshold value 104. Create a highly accurate speed map.

FIG. 6 is a flowchart showing an example of the operation of the command output unit 107 of the numerical control device 100 according to the first embodiment. FIG. 6 shows an operation in which the command output unit 107 outputs a command based on the speed map registered in the speed map database 105.

The command output unit 107 first reads one record from the speed map 203 registered in the speed map database 105 (step S21), and further acquires the current machining position (step S22). Next, the command output unit 107 indicates whether the current machining position has reached the position indicated by the speed map, that is, the current machining position indicated by the position information of the record read in step S21 (hereinafter referred to as the current record). It is confirmed whether the position has been reached (step S23). When the current machining position has not reached the position indicated by the speed map (step S23: No), the command output unit 107 is based on a command based on the speed command value of the speed map, that is, based on the speed command value of the current record. The command is created (step S24). Next, the command output unit 107 outputs the created command to the amplifier 120 (step S25). Next, the command output unit 107 determines whether the machining program 110 is finished (step S26), and if it is not finished (step S26: No), returns to step S22. When the machining program 110 is completed (step S26: Yes), the command output unit 107 ends the operation. Further, in step S23, when it is determined that the current machining position has reached the position indicated by the speed map (step S23: Yes), the command output unit 107 returns to step S21.

Next, a machining operation performed by using the numerical control device 100 according to the first embodiment will be described. FIG. 7 is a diagram showing an example of a machining operation performed by using the numerical control device 100 according to the first embodiment. FIG. 7 shows an example of a change in speed when the numerical control device 100 uses a speed map to generate a command. Assuming that the coordinates of the time T1 are (X1, Y1), the coordinates of the time T2 are (X2, Y2), the coordinates of the time T3 are (X3, Y3), and the coordinates of the time T4 are (X4, Y4), the case of FIG. The speed map corresponding to is as shown in FIG.

As shown in FIG. 7, when the machine tool performs cutting by generating a command using the speed map, the machine tool starts accelerating at the switching position from the cutting portion to the non-cutting portion. Then accelerate to speed v2. After that, the machine tool decelerates to the original speed v1 by the switching position from the non-cutting portion to the cutting portion.

When the command output unit 107 generates a command using the speed map, the speed map to be used is specified by the machining program 110. If the speed map specified by the machining program 110 exists in the speed map database 105, the command output unit 107 generates a command using the speed map, and if it does not exist, the command output unit 107 generates a command according to the machining program 110.

Further, if the speed map to be used is not specified in the machining program 110, the speed control using the speed map becomes invalid. Further, when the speed map to be used is not specified by the machining program 110 and the user specifies an arbitrary speed map using the GUI unit 106 described later, the numerical control device 100 uses the specified speed map. Can generate commands. When the speed map to be used is specified by both the machining program 110 and the GUI unit 106, and the designated speed maps are different, the numerical control device 100 uses the speed map specified by the machining program 110. Alternatively, the speed map specified by using the GUI unit 106 may be used. The configuration may be such that the user can set which designation is prioritized.

The GUI unit 106 is used when the user specifies a speed map used when the command output unit 107 generates a command.

In the GUI unit 106, the speed map display unit 108 displays a list of speed maps registered in the speed map database 105 when the user specifies the speed map. The speed map selection unit 109 accepts an operation for selecting an arbitrary speed map from the list of speed maps from the user. In this case, the command output unit 107 acquires the speed map selected by the user from the speed map database 105, generates a command based on the acquired speed map, and outputs the command to the amplifier 120.

As described above, the numerical control device 100 according to the present embodiment creates a speed map showing the time change of the feed rate of the tool based on the result of the machining operation performed by controlling the machine tool according to the machining program 110. After the speed map is created, the speed map is used to control the machine tool. The speed map includes information on the speed switching position and a speed command value at the speed switching position. According to the numerical control device 100, the starting point of the cutting portion is specified by comparing the spindle load value with the cutting determination threshold value 104, and the speed is controlled in consideration of the starting point of the cutting portion. The speed can be appropriately controlled to suppress the difference between the speed described in the machining program and the actual speed. As a result, it is possible to prevent the machining accuracy from deteriorating, and further, in the non-cutting portion, the machining time can be shortened by increasing the feed rate of the tool.

In the present embodiment, the speed represented by the speed map is used as the feed speed of the tool, but the speed represented by the speed map may be the moving speed of the work or the relative speed between the work and the tool.

Here, the hardware configuration of the numerical control device 100 will be described. FIG. 9 is a diagram showing a hardware configuration example of the numerical control device 100 according to the first embodiment.

The numerical control device 100 can be realized by, for example, the processor 91, the memory 92, the display device 93, the input device 94, and the interface circuit 95 shown in FIG. The processor 91 is a CPU (Central Processing Unit, central processing unit, processing unit, arithmetic unit, microprocessor, microprocessor, DSP (Digital Signal Processor)) or system LSI (Large Scale Integration). The memory 92 includes a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable Read Only Memory), an EEPROM (registered trademark) (Electrically Erasable Programmable Read Only Memory), and the like. The display device 93 is a liquid crystal panel or the like. The input device 94 is a keyboard, a mouse, or the like. The display device 93 and the input device 94 may be a touch panel in which they are integrated.

The data acquisition unit 101, the speed map creation unit 102, the GUI unit 106, and the command output unit 107 of the numerical control device 100 are realized by the processor 91 executing a program for operating as each of these units. The program for operating as the data acquisition unit 101, the speed map creation unit 102, the GUI unit 106, and the command output unit 107 is stored in the memory 92. The processor 91 operates as a data acquisition unit 101, a speed map creation unit 102, a GUI unit 106, and a command output unit 107 by reading this program from the memory 92 and executing it. The processor 91 uses the interface circuit 95 when operating as the data acquisition unit 101 or the command output unit 107. Further, the processor 91 uses the display device 93 and the input device 94 when operating as the GUI unit 106. It can be said that the program stored in the memory 92 causes the computer to execute the procedure or method of the data acquisition unit 101, the speed map creation unit 102, the GUI unit 106, and the command output unit 107. The memory 92 is also used as a temporary memory when the processor 91 executes various processes. The above-mentioned program stored in the memory 92 is provided to a user or the like in a state of being written in a storage medium such as a CD (Compact Disc) -ROM or a DVD (Digital Versatile Disc) -ROM. It may be present or it may be provided via a network.

Further, the memory 92 is used to realize the speed map database 105 of the numerical control device 100. The memory 902 is also used for the numerical control device 100 to hold the machining information 103, the cutting determination threshold value 104, and the machining program 110 shown in FIG. 1 and the like.

The interface circuit 95 is used to connect the numerical control device 100 to another device. An example of another device in this embodiment is an amplifier 120.

The hardware configuration of the numerical control device described in another embodiment is the same as that of the numerical control device 100.

Embodiment 2.
10 is a first diagram showing a configuration example of the numerical control device according to the second embodiment, and FIG. 11 is a second diagram showing a configuration example of the numerical control device according to the second embodiment. Among the components of the numerical control device shown in FIGS. 10 and 11, the components that achieve the same functions as the numerical control device 100 according to the first embodiment are designated by the same reference numerals as those of the first embodiment. .. Since the operation of the components having the same reference numerals as those of the first embodiment is the same as that of the first embodiment, the description thereof will be omitted.

The numerical control device according to the second embodiment learns the cutting determination threshold value 104 from the work material, the tool type / material, the spindle load value at the time of cutting, and the speed, and creates a speed map using the learned cutting determination threshold value 104. The point is different from the numerical control device 100 according to the first embodiment. "Tool type / material" is information indicating the type of tool and the material of the tool.

The numerical control device 100a shown in FIG. 10 has a configuration in which the data collection unit 101 of the numerical control device 100 according to the first embodiment is replaced with the data collection unit 101a, and the machine learning device 130 is further added. The operation of the data collection unit 101a is the same as that of the data collection unit 101 of the numerical control device 100, except that the machining information 103a is generated. The machining information 103a includes a spindle load value, a movement command value, a work material, and a tool type / material. That is, the machining information 103a has a configuration in which the work material and the tool type / material are added to the machining information 103. Further, the numerical control device 100b shown in FIG. 11 has a configuration in which the data collection unit 101 of the numerical control device 100 according to the first embodiment is replaced with the data collection unit 101a, and the inference device 140 is further added. The data collection unit 101a and the processing information 103a shown in FIG. 11 are the same as the data collection unit 101a and the processing information 103a shown in FIG.

The numerical control device 100a of FIG. 10 has a function that the machine learning device 130 learns the cutting determination threshold value 104 and generates a trained model. On the other hand, the numerical control device 100b of FIG. 11 has a function of creating a cutting determination threshold value 104 using a learned model generated by an external device and creating a speed map using the created cutting determination threshold value 104. .. An example of an external device that generates a trained model used by the numerical control device 100b is the machine learning device 130 of the numerical control device 100a.

In the present embodiment, for convenience, the numerical control device 100a provided with the machine learning device 130 and the numerical control device 100b provided with the inference device 140 will be described separately, but both the machine learning device 130 and the inference device 140 will be described separately. It may be a numerical control device having a configuration including.

First, the details of the numerical control device 100a that learns the cutting determination threshold value 104 will be described.

FIG. 12 is a diagram showing a configuration example of the machine learning device 130 included in the numerical control device 100a according to the second embodiment. The machine learning device 130 includes a data acquisition unit 301, a model generation unit 302, and a trained model storage unit 303.

The data acquisition unit 301 acquires the spindle load value and speed at the time of cutting, the work material, the tool type / material, and the cutting determination threshold value as learning data. The spindle load value at the time of cutting is the spindle load value when the machine tool is cutting the workpiece among the spindle load values included in the machining information 103a. Whether or not it is cutting is determined by comparing the cutting determination threshold value with the spindle load value. The speed at the time of cutting is calculated from the movement command value included in the machining information 103a. The work material and tool type / material are the work material and tool type / material included in the machining information 103a. The cutting determination threshold is the cutting determination threshold 104 shown in FIG. 10, which corresponds to the correct answer data of machine learning. The data acquisition unit 301 outputs each acquired data to the model generation unit 302.

The model generation unit 302 is used for learning data created based on the combination of the spindle load value and speed at the time of cutting output from the data acquisition unit 301, the work material, the tool type / material, and the cutting determination threshold value. Based on this, the cutting determination threshold is learned. That is, the model generation unit 302 generates a trained model for inferring the optimum cutting determination threshold value based on the spindle load value and speed at the time of cutting, the work material, the tool type / material, and the cutting determination threshold value. do. Here, the learning data is data in which the spindle load value and speed at the time of cutting, the work material, the tool type / material, and the cutting determination threshold value are associated with each other.

As the learning algorithm used by the model generation unit 302, known algorithms such as supervised learning, unsupervised learning, and reinforcement learning can be used. As an example, a case where a neural network is applied will be described.

The model generation unit 302 learns the cutting determination threshold value by so-called supervised learning according to, for example, a neural network model. Here, supervised learning refers to a method of learning a feature in those learning data by giving a set of input and result (label) data to a machine learning device, and inferring the result from the input.

A 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 one layer or two or more layers.

For example, in the case of a three-layer neural network as shown in FIG. 13, when a plurality of data are input to each neuron (X1-X3) in the input layer, each neuron weights W1 (weight W1) on the value of the input data. Multiply w11-w16) and output to each neuron (Y1-Y2) in the middle layer. That is, each neuron in the input layer outputs the value obtained by multiplying the input value by the weight W1 toward all the neurons in the intermediate layer. Similarly, each neuron in the middle layer multiplies the input value by the weight W2 (w21-w26) and outputs to each neuron (Z1-Z3) in the output layer. Each neuron in the output layer outputs the value input from each neuron in the middle layer to the outside. This output result depends on the values of the weights W1 and W2.

In the present embodiment, the neural network is created based on the combination of the spindle load value and speed at the time of cutting acquired by the data acquisition unit 301, the work material, the tool type / material, and the cutting determination threshold. The cutting judgment threshold is learned by so-called supervised learning according to the learning data.

That is, the neural network inputs the spindle load value and velocity at the time of cutting, the work material, and the tool type / material, and sets the weights W1 and W2 so that the result output from the output layer approaches the cutting determination threshold value. Learn by adjusting.

The model generation unit 302 generates and outputs a trained model by executing the above learning.

The trained model storage unit 303 stores the trained model output from the model generation unit 302.

Next, the operation of the machine learning device 130 to learn the cutting determination threshold value will be described with reference to FIG. FIG. 14 is a flowchart showing an example of the operation of the machine learning device 130 according to the second embodiment.

In the machine learning device 130, first, the data acquisition unit 301 acquires the spindle load value and speed at the time of cutting, the work material, the tool type / material, and the cutting determination threshold value (step S31). Here, it is assumed that the spindle load value and speed at the time of cutting, the work material, the tool type / material, and the cutting determination threshold value are acquired at the same time, but it is sufficient if each of these data can be input in association with each other. May be acquired at different timings.

Next, the model generation unit 302 performs learning processing, that is, a combination of the spindle load value and speed at the time of cutting acquired by the data acquisition unit 301, the work material, the tool type / material, and the cutting determination threshold value. According to the learning data created based on the above, the cutting determination threshold is learned by so-called supervised learning, and a trained model is generated (step S32).

Next, the trained model storage unit 303 stores the trained model generated by the model generation unit 302 (step S33).

In the present embodiment, the numerical control device 100a including the machine learning device 130 for learning the cutting determination threshold is described, but the machine learning device 130 may be an independent device outside the numerical control device 100a. For example, the machine learning device 130 may be connected to the numerical control device 100a via a network and may be a device separate from the numerical control device 100a. Further, the machine learning device 130 may exist on the cloud server.

Next, the details of the numerical control device 100b for inferring the cutting determination threshold value by using the trained model generated by the external machine learning device will be described. Here, it is assumed that the other device that generates the trained model is the machine learning device 130 of the numerical control device 100a.

FIG. 15 is a diagram showing a configuration example of the inference device 140 included in the numerical control device 100b according to the second embodiment. The inference device 140 includes a data acquisition unit 401, an inference unit 402, and a trained model storage unit 403. It is assumed that the trained model storage unit 403 receives and stores the trained model created by the machine learning device 130 of the numerical control device 100a described above.

The data acquisition unit 401 acquires the spindle load value and speed at the time of cutting, the work material, and the tool type / material. The data acquisition unit 401 outputs each acquired data to the inference unit 402.

The inference unit 402 infers the cutting determination threshold value using the learned model stored in the learned model storage unit 403. That is, the inference unit 402 inputs these input data (cutting) by inputting the spindle load value and speed at the time of cutting acquired by the data acquisition unit 401, the work material, and the tool type / material into this trained model. It is possible to output the cutting judgment threshold value inferred from the spindle load value and speed at the time, work material, tool type / material). The inference unit 402 outputs the inferred cutting determination threshold value to the speed map creation unit 102.

In the present embodiment, the inference device 140 of the numerical control device 100b infers the cutting determination threshold using the trained model learned by the machine learning device 130 of the numerical control device 100a, but the numerical control device 100b You may try to learn inside. That is, the numerical control device 100b includes a machine learning device similar to the machine learning device 130 of the numerical control device 100a, and the inference device 140 infers the cutting determination threshold using the trained model learned by this machine learning device. May be.

Next, the operation of the inference device 140 inferring the cutting determination threshold value will be described with reference to FIG. FIG. 16 is a flowchart showing an example of the operation of the inference device 140 according to the second embodiment.

In the inference device 140, first, the data acquisition unit 401 acquires the spindle load value and speed at the time of cutting, the work material, and the tool type / material (step S41).

Next, the inference unit 402 inputs the spindle load value and speed at the time of cutting, the work material, and the tool type / material into the trained model stored in the trained model storage unit 403 (step S42). Along with this, the cutting judgment threshold output from the trained model is acquired.

Next, the inference unit 402 outputs the cutting determination threshold value acquired in step S42 to the speed map creation unit 102 (step S43).

The speed map creating unit 102 that has received the cutting determination threshold value inferred by the inference device 140 in this way executes the operation described in the first embodiment by using the received cutting threshold value, and creates a speed map. As a result, it is possible to set an appropriate cutting determination threshold value for various conditions that affect the machining result, such as the spindle load value and speed at the time of cutting, the work material, and the tool type / material. That is, the cutting determination threshold value used by the speed map creation unit 102 when creating the speed map can be optimized. As a result, the accuracy of machining performed using the speed map is improved.

In the present embodiment, the case where supervised learning is applied to the learning algorithm used by the model generation unit 302 has been described, but the present invention is not limited to this. As for the learning algorithm, it is also possible to apply unsupervised learning or the like in addition to supervised learning.

Further, the model generation unit 302 may learn the cutting determination threshold value according to the learning data created for the plurality of numerical control devices. The model generation unit 302 may acquire learning data from a plurality of numerical control devices used in the same area, or may acquire learning data from a plurality of numerical control devices that operate independently in different areas. The cutting determination threshold value may be learned by using the data. It is also possible to add or remove a numerical control device for acquiring learning data from the target on the way. Further, the learning device that has learned the cutting judgment threshold for a certain numerical control device is applied to another numerical control device, and the cutting judgment threshold is relearned for the other numerical control device to update the trained model. You may do so.

Further, as the learning algorithm used by the model generation unit 302, deep learning, which learns the extraction of the feature amount itself, can also be used, and other known methods such as genetic programming, functional logic programming, and support can be used. Machine learning may be performed according to a vector machine or the like.

The configuration shown in the above embodiments is an example, and can be combined with another known technique, can be combined with each other, and does not deviate from the gist. It is also possible to omit or change a part of the configuration.

100, 100a, 100b Numerical control device, 101, 101a Data collection unit, 102 Speed map creation unit, 103, 103a Machining information, 104 Cutting judgment threshold, 105 Speed map database, 106 Graphical user interface unit, 107 Command output unit, 108 Speed map display unit, 109 speed map selection unit, 110 machining program, 120 amplifier, 130 machine learning device, 140 inference device, 201 cutting / non-cutting determination unit, 202 speed map generator, 203 speed map, 204 speed map registration unit , 205 Machining condition parameter, 301, 401 data acquisition unit, 302 model generation unit, 303, 403 trained model storage unit, 402 inference unit.

Claims (8)

Based on the machining information obtained by cutting the workpiece by controlling the machine tool, the section where cutting is performed on the cutting path when cutting the workpiece and the section where cutting is not performed. A speed map creation unit that identifies a cut portion and creates a speed map having information on a feed speed in the non-cut portion and a feed speed in the cut portion.
A speed map database that holds the speed map and
A command output unit that generates commands for the machine tool based on the speed map, and
Equipped with
When the speed map database holds a speed map specified by the machining program or the user, the command output unit generates a command to the machine tool based on the machining program or the speed map specified by the user . If the speed map database does not hold the machining program or the speed map specified by the user, a command to the machine tool is generated based on the machining program, and a different speed map is specified by the machining program and the user. If so, a command to the machine tool is generated based on the speed map specified by the user.
A numerical control device characterized by that. The speed map creating unit creates the speed map so that the feed speed is reduced to the feed speed at the time of cutting specified by the machining program by the timing when the feed speed is switched from the non-cutting portion to the cutting portion.
The numerical control device according to claim 1. The speed map is
At the first change point where the non-cutting portion is switched to the cutting portion, the position information of the deceleration start point at which deceleration is started in the non-cutting portion and the feed speed so as to be the feed speed specified by the machining program. including,
The numerical control device according to claim 1 or 2. The numerical control device according to any one of claims 1 to 3, wherein the machining information includes a spindle load value of the machine tool and a movement command value. The speed map creation unit
A state determination unit that determines whether the cutting portion or the non-cut portion is based on the spindle load value and the cutting determination threshold value.
A speed map generation unit that generates the speed map based on the determination result by the state determination unit, and a speed map generation unit.
A speed map registration unit that registers the speed map generated by the speed map generation unit in the speed map database, and a speed map registration unit.
The numerical control device according to claim 4, wherein the numerical control device is provided. Based on the machining information obtained by cutting the workpiece by controlling the machine tool, the section where cutting is performed on the cutting path when cutting the workpiece and the section where cutting is not performed. A speed map creation unit that identifies a cut portion and creates a speed map having information on a feed speed in the non-cut portion and a feed speed in the cut portion.
A speed map database that holds the speed map and
A command output unit that generates commands for the machine tool based on the speed map, and
The spindle load value and feed speed of the machine tool at the time of cutting the work, the material of the work, the type and material of the tool for cutting the work, and the speed map creating part are the cutting part and the non-cutting part. A model generation unit that learns the cutting judgment threshold and generates a trained model based on the cutting judgment threshold used in the process of specifying
Inference to infer the cutting determination threshold based on the spindle load value and feed rate at the time of cutting the work, the material of the work, the type and material of the tool for cutting the work, and the learned model. Department and
A numerical control device characterized by being provided with. The speed map creating unit creates the speed map based on the processing information obtained in the first processing of the work.
The numerical control device according to any one of claims 1 to 6, wherein the numerical control device is characterized. A graphical user interface unit for selecting a speed map to be used for cutting from the speed maps registered in the speed map database.
The numerical control device according to any one of claims 1 to 7, wherein the numerical control device is provided.

Images