JP7548690B2 - Machining program creation device - Google Patents

Description

The present invention relates to a machining program creation device, and in particular to a creation device for a machining program executed by a numerical control device.

The numerical control device loads a machining program and executes the loaded machining program to perform automatic operation. The machining program is created manually, for example, by an operator. When creating a machining program, the operator specifies in the machining program the machining commands for realizing the machining shape of the workpiece, while specifying preparatory commands (tool change command, spindle rotation command, approach command, etc.) and post-processing commands (escape command, spindle stop command, etc.) required to execute the machining commands before and after the specified machining commands. Machining commands specified in the machining program include commands that combine multiple commands to machine a workpiece into a specified shape, and cycle commands that cause the machine to perform a series of operation sequences with a single command (for example, Patent Document 1).

JP 2015-011669 A

In this way, every time an operator specifies a machining command in a machining program, the operator must specify multiple auxiliary commands before and after the command, which are necessary for executing the machining command. There are many such auxiliary commands depending on the machine configuration, workpiece shape, etc. Therefore, it is necessary to understand such information, which is a burden on the operator.
Therefore, there is a need for a function that can learn or assist in the task of specifying preparation commands and post-processing commands that are required before and after machining commands such as cycle commands.

A numerical control device according to one aspect of the present invention extracts commands that are specified near commands related to machining (such as cycle commands) from machining programs previously created by an operator, and performs machine learning on the extracted commands according to predetermined rules. Then, when an operator creates a new machining program, at the point in time when the operator inputs a command related to machining, an inference process is executed using the results of the machine learning, and auxiliary commands that should be specified before and after the command related to machining are output as inference results.

One aspect of the present invention is a machining program creation device that assists in the creation of a control program for a machine tool, comprising: a data acquisition unit that acquires a machining program; a machining program analysis unit that extracts at least one machining-related command, at least one preparatory command, and at least one post-processing command from the machining program, and analyzes the relative positions of each of the preparatory commands and post-processing commands as viewed from each of the machining-related commands, including the distance from the machining commands; and a learning unit that creates a first learning model that learns the positions of each of the preparatory commands and post-processing commands as viewed from the machining commands, based on the analysis results by the machining program analysis unit.

Another aspect of the present invention is a machining program creation device that assists in the creation of a control program for a machine tool, comprising: a data acquisition unit that acquires machining-related commands; a machining program analysis unit that analyzes the machining- related commands; a first learning model stored in a learning model memory unit that stores a first learning model that has learned the relative positions of each preparatory command and post-processing command from each machining-related command, including the distance from the machining-related command; a command estimation unit that estimates preparatory commands and post-processing commands to be specified at relative positions including a predetermined distance from the machining-related command based on the analysis results by the machining program analysis unit; and an estimation result display unit that displays a template of a machining program including the machining-related commands and the preparatory commands and post-processing commands estimated by the command estimation unit.

One aspect of the present invention makes it possible to learn or assist in the task of specifying preparation commands and post-processing commands required before and after machining commands such as cycle commands.

1 is a schematic hardware configuration diagram of a machining program creating device according to an embodiment; 1 is a schematic functional block diagram of a machining program creating device according to a first embodiment; FIG. 4 is a diagram showing an example of a machining program. FIG. 1 is a diagram showing an example of a typical processing pattern. FIG. 2 is a diagram illustrating an example of a first learning model. FIG. 13 is a diagram illustrating an example of a second learning model. FIG. 11 is a schematic functional block diagram of a machining program creating device according to a second embodiment. 13A to 13C are diagrams illustrating a method of estimating preparation commands and post-processing commands at each relative position using the first learning model. A diagram explaining a method of estimating arguments of each preparation command and post-processing command using the second learning model. FIG. 11 is a diagram showing an example of a template for a machining program. FIG. 13 is a diagram showing a modified example in which a learning model storage unit is provided on an external computer.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
1 is a schematic hardware configuration diagram showing a main part of a machining program creation device according to an embodiment of the present invention. The machining program creation device 1 of the present invention can be implemented as, for example, a numerical control device that controls an industrial machine based on a machining program. The machining program creation device 1 of the present invention can also be implemented on a personal computer attached to a numerical control device that controls an industrial machine based on a machining program, or on a personal computer, cell computer, fog computer, or cloud server connected to a numerical control device via a wired/wireless network. In this embodiment, an example is shown in which the machining program creation device 1 is implemented on a personal computer connected to a numerical control device via a network.

The CPU 11 provided in the machining program creation device 1 according to this embodiment is a processor that controls the entire machining program creation device 1. The CPU 11 reads the system program stored in the ROM 12 via the bus 22, and controls the entire machining program creation device 1 according to the system program. The RAM 13 temporarily stores temporary calculation data, display data, various data input from outside, etc.

The non-volatile memory 14 is composed of, for example, a memory backed up by a battery (not shown) or an SSD (Solid State Drive), and the memory state is maintained even when the power supply of the machining program creation device 1 is turned off. The non-volatile memory 14 stores data and machining programs read from an external device 72 via the interface 15, and data and machining programs input via the input device 71. The data and machining programs stored in the non-volatile memory 14 may be expanded in the RAM 13 when executed/used. In addition, various system programs such as known analysis programs are written in advance in the ROM 12.

The interface 15 is an interface for connecting the CPU 11 of the machining program creation device 1 to an external device 72 such as a USB device. For example, machining programs and various parameters used to control industrial machinery can be read from the external device 72. In addition, machining programs and various parameters edited within the machining program creation device 1 can be stored in an external storage means via the external device 72.

The interface 20 is an interface for connecting the CPU of the machining program creation device 1 to a wired or wireless network 5. The network 5 is connected to the numerical control device 3, fog computer, cloud server, etc., and exchanges data with the machining program creation device 1.

On the display device 70, various data loaded into the memory, data obtained as a result of executing programs, etc. are output via the interface 17 and displayed. In addition, the input device 71, which is composed of a keyboard, pointing device, etc., passes instructions, data, etc. based on operations by the operator to the CPU 11 via the interface 18.

Figure 2 is a schematic block diagram showing the functions of the machining program creation device 1 according to the first embodiment of the present invention. Each function of the machining program creation device 1 according to this embodiment is realized by the CPU 11 of the machining program creation device 1 shown in Figure 1 executing a system program and controlling the operation of each part of the machining program creation device 1. The machining program creation device 1 according to this embodiment creates a learning model used to assist an operator in creating a machining program that includes control commands related to the industrial machine to be controlled by the numerical control device 3.

The machining program creation device 1 of this embodiment includes a data acquisition unit 100, a machining program analysis unit 110, and a machine learning unit 150. In addition, the RAM 13 to the non-volatile memory 14 of the machining program creation device 1 are provided with a machining program storage unit 210 in advance as an area for storing the machining program acquired from the input device 71, the external device 72, the numerical control device 3, etc., and information related to the operating environment of the machining program.

The data acquisition unit 100 is realized by the CPU 11 included in the machining program creation device 1 shown in FIG. 1 executing the system program read from the ROM 12, and mainly performing arithmetic processing by the CPU 11 using the RAM 13 and non-volatile memory 14, and input control processing by the interface 15, 18 or 20. The data acquisition unit 100 acquires the machining program and information related to the operating environment of the machining program and stores them in the machining program storage unit 210. The data acquisition unit 100 may acquire the machining program and information related to the operating environment of the machining program from the input device 71, the external device 72, the numerical control device 3, etc. The machining program acquired by the data acquisition unit 100 may include commands related to machining, such as cycle commands and a series of cutting commands. The information related to the operating environment of the machining program acquired by the data acquisition unit 100 together with the machining program includes machine configuration information (type of industrial machine, axis configuration, tool type, etc.) of the industrial machine executing the machining program, work material information (shape of the work, material of the work, etc.), etc.

The machining program analysis unit 110 is realized by the CPU 11 included in the machining program creation device 1 shown in FIG. 1 executing a system program read from the ROM 12, and the CPU 11 mainly performing arithmetic processing using the RAM 13 and the non-volatile memory 14. The machining program analysis unit 110 reads and analyzes the machining program stored in the machining program storage unit 210 and information related to the operating environment of the machining program, and creates learning data used for learning by the machine learning unit 150. The machining program analysis unit 110 identifies commands related to machining included in the machining program. Then, it associates the relative position from the command related to machining with the preparation command and post-processing command specified before and after the identified command related to machining. Then, the machining program analysis unit 110 outputs the analyzed machining program and information related to the operating environment of the machining program to the machine learning unit 150.

Figure 3 shows an example of a machining program. A machining program used to machine a workpiece includes at least one machining command. For example, in a machine tool, the machining command is indicated by a cycle command or a series of cutting commands (a set of cutting commands or fast-forward commands that start and end with a cutting command). In the example of Figure 3, the machining program analysis unit 110 identifies a drill cycle command G81 from the machining program as a machining command. When the machining command is indicated by a series of cutting commands, the tool path drawn by the series of cutting commands is calculated by a simulation process or the like, and known shape matching is performed between the series of cutting commands and a typical machining pattern as exemplified in Figure 4, to identify the type of machining that the series of cutting commands will perform.

Next, the machining program analysis unit 110 calculates and associates the relative positions of the specified machining-related command (drill cycle command G81) with the preparation command and post-processing command specified before and after the specified machining-related command. Typical preparation commands include a return to origin command, a tool change command, a spindle rotation command, a workpiece coordinate system selection command, a tool diameter correction command, and an approach command. Typical post-processing commands include an escape command, a spindle rotation stop command, and an end command. The machining program analysis unit 110 then associates the block distance from the machining-related command with each preparation command and post-processing command as a relative position. In the example of FIG. 3, the return to origin command G28 is located five blocks before the drill cycle command G81, which is a machining-related command, so -5 is associated as the relative position.

The machining program analysis unit 110 may preset typical machining commands, preparation commands, and post-processing commands in the form of, for example, tables, and may identify the machining commands, preparation commands, and post-processing commands included in the machining program by referring to these tables. Also, when the machining commands are represented by a series of cutting commands, it may be possible to identify the set of cutting commands and fast-forward commands that are sandwiched between preparation commands and post-processing commands in the machining program and that start and end with cutting commands as the machining commands.

In addition, when the machining program analysis unit 110 determines that the machining program contains multiple machining commands, it executes the above-mentioned process for each machining command. Generally, when a machining program contains multiple machining commands, the flow of preparation command -> machining command -> post-processing command is repeated, so that each command included in the machining program is identified as a machining command, preparation command, post-processing command, or other command, and then the machining program can be divided into a set of commands with the flow of preparation command -> machining command -> post-processing command as one set.

The machine learning unit 150 is realized by the CPU 11 included in the machining program creation device 1 shown in FIG. 1 executing a system program read from the ROM 12, and the CPU 11 mainly performing arithmetic processing using the RAM 13 and non-volatile memory 14. The machine learning unit 150 executes processing related to machine learning based on the analysis results by the machining program analysis unit 110. The machine learning unit 150 according to this embodiment includes at least a learning unit 152 and a learning model storage unit 220, which is an area provided in the RAM 13 to the non-volatile memory 14 for storing the learning model created by the learning unit 152.

The learning unit 152 creates a learning model by machine learning using the learning data input as the analysis result by the machining program analysis unit 110, and stores the model in the learning model storage unit 220. The learning model created by the learning unit 152 includes a first learning model that learns the preparatory commands and post-processing commands that should be specified before and after the commands related to machining in the machining program, and a second learning model that learns the arguments in each of the preparatory commands and post-processing commands.

The first learning model created by the learning unit 152 may indicate the occurrence frequency of each preparatory command and post-processing command with respect to the relative position from the command related to machining, as exemplified in FIG. 5, for example. The learning unit 152 creates a first learning model for each command related to machining. The learning unit 152 creates a frequency graph as exemplified in FIG. 5 using multiple learning data obtained by the machining program analysis unit 110 analyzing multiple machining programs including commands related to the same or similar machining, and may use this as the first learning model for the command related to the machining. The command related to the same or similar machining may be determined as follows: when the command related to machining is indicated by a cycle command, the same type of cycle command is determined to be the command related to the same or similar machining, and when the command related to machining is indicated by a series of cutting commands, the machining pattern identified by the machining program analysis unit 110 is determined to be the same machining pattern. The learning unit 152 creates a first learning model for each machine configuration information and workpiece material information included in the information related to the operating environment of the machining program. For example, the learning unit 152 creates a first learning model for a linear three-axis machine tool of the cycle command G82 and a first learning model for a linear three-axis rotary two-axis machine tool of the plane machining pattern command group separately.

The second learning model created by the learning unit 152 may indicate the frequency of use of arguments of each preparatory command and post-processing command, as illustrated in FIG. 6, for example. The learning unit 152 creates a second learning model for each command related to machining. The learning unit 152 creates a frequency graph showing the frequency of the argument set for each preparatory command and post-processing command using multiple learning data obtained by the machining program analysis unit 110 analyzing multiple machining programs including commands related to the same or similar machining, and uses this as the second learning model. The learning unit 152 creates a second learning model for each machine configuration information and workpiece material information included in the information related to the operating environment of the machining program. For example, the learning unit 152 creates a second learning model for the origin return command G28 for a linear three-axis machine tool and a second learning model for the origin return command G28 for a linear three-axis rotating two-axis machine tool separately.

The machining program creation device 1 according to this embodiment, which is configured as described above, learns the preparatory commands and post-processing commands that should be specified before and after the machining commands in the machining program. The machining program creation device 1 according to this embodiment also learns the arguments of the preparatory commands and post-processing commands. The learning results are stored as a learning model. The learning model created by the machining program creation device 1 can be used to estimate the preparatory commands and post-processing commands that should be used for the machining commands input by the operator when creating the machining program.

As a modified example of the machining program creation device 1 according to this embodiment, when analyzing a machining program, the machining program analysis unit 110 may rearrange the order of preparatory commands in advance according to a predetermined rule. For example, a rule may be established that determines a typical order such as origin return processing -> tool exchange processing -> spindle rotation -> ... as the order of general preparatory processing, and the preparatory commands may be rearranged according to this rule. The machining program analysis unit 110 may also rearrange post-processing commands in a similar manner according to a predetermined rule. Some preparatory commands and post-processing commands do not have a specific order for execution. Therefore, depending on the operator, there may be cases where preparatory commands are specified in a different order, and if such machining programs occur frequently, the accuracy of learning by the learning unit 152 may decrease. By providing the configuration of this modified example, it is possible to alleviate the deterioration of the accuracy of this learning to some extent.

Figure 7 is a schematic block diagram showing the functions of the machining program creation device 1 according to the second embodiment of the present invention. Each function of the machining program creation device 1 according to this embodiment is realized by the CPU 11 of the machining program creation device 1 shown in Figure 1 executing a system program and controlling the operation of each part of the machining program creation device 1. The machining program creation device 1 according to this embodiment uses a learning model that has already been created to provide support when an operator creates a machining program that includes control commands related to industrial machinery to be controlled by the numerical control device 3.

The machining program creation device 1 of this embodiment includes a data acquisition unit 100, a machining program analysis unit 110, an estimation result display unit 120, and a machine learning unit 150.

The data acquisition unit 100 according to this embodiment is realized by the CPU 11 included in the machining program creation device 1 shown in FIG. 1 executing the system program read from the ROM 12, and mainly performing arithmetic processing using the RAM 13 and non-volatile memory 14 by the CPU 11, and input control processing by the interfaces 18 and 20. The data acquisition unit 100 acquires machining-related commands and information related to the operating environment of the commands, and outputs them to the machine learning unit 150. The data acquisition unit 100 may acquire machining-related commands from an operator via the input device 71, for example. The data acquisition unit 100 may also acquire information related to the operating environment of the commands from the input device 71 or the numerical control device 3. The machining-related commands acquired by the data acquisition unit 100 may be, for example, a set of cutting commands or fast-forward commands that start with a cycle command or a cutting command and end with a cutting command. The information related to the operating environment of the command acquired by the data acquisition unit 100 together with the command related to machining includes machine configuration information of the industrial machine that executes the command (type of industrial machine, shaft configuration, tool type, etc.), workpiece material information (machined shape of the workpiece, material of the workpiece, etc.), etc.

The machining program analysis unit 110 according to this embodiment is realized by the CPU 11 included in the machining program creation device 1 shown in FIG. 1 executing a system program read from the ROM 12, and the CPU 11 mainly performing arithmetic processing using the RAM 13 and non-volatile memory 14. The machining program analysis unit 110 analyzes the machining instructions acquired by the data acquisition unit 100 and information related to the operating environment of the instructions, and creates learning data used in the estimation process by the machine learning unit 150. For example, when the machining instructions are indicated by a series of cutting instructions, the machining program analysis unit 110 calculates the tool path drawn by the series of cutting instructions by simulation processing, etc., performs known shape matching with a typical machining pattern, and performs processing to identify what type of machining the series of cutting instructions will perform.

The machine learning unit 150 is realized by the CPU 11 included in the machining program creation device 1 shown in FIG. 1 executing a system program read from the ROM 12, and the CPU 11 mainly performing arithmetic processing using the RAM 13 and non-volatile memory 14. The machine learning unit 150 executes processing related to machine learning based on machining commands input from the data acquisition unit 100 and information related to the operating environment of the commands, and a learning model stored in the learning model storage unit 220. The machine learning unit 150 according to this embodiment includes at least a command estimation unit 154, and a learning model storage unit 220 which is an area provided in the RAM 13 to non-volatile memory 14 in which the learning model created by the learning unit 152 according to the first embodiment is stored.

The command estimation unit 154 uses the processing command input from the data acquisition unit 100 and information related to the operating environment of the command, and the learning model stored in the learning model storage unit 220, to perform estimation processing of the preparation command and the post-processing command that should occur before and after the processing command. The command estimation unit 154 outputs the estimation result to the estimation result display unit 120.

The command estimation unit 154 estimates the preparatory command and the post-processing command that should be before and after the command related to machining, using the first learning model corresponding to the command related to machining input from the data acquisition unit 100 and the information related to the operating environment of the command, among the first learning models stored in the learning model storage unit 220. FIG. 8 is a diagram illustrating a first learning model created as a frequency graph. The command estimation unit 154 may refer to the first learning model and estimate commands that are frequent in their respective relative positions from the command related to machining on the frequency graph as the preparatory command and the post-processing command that should be before and after the command related to machining. In the example of FIG. 8, the origin return command G28 is estimated as the block five blocks before the command related to machining, the tool change command M6 is estimated as the block four blocks before, the spindle rotation command M3 is estimated as the block three blocks before, the workpiece coordinate system setting command G54 is estimated as the block two blocks before, and the approach commands G00 and G43 are estimated as the block two blocks before. In this way, the command estimation unit 154 may estimate that the single command that occurs most frequently at each relative position is the preparation command and post-processing command that should be at that relative position, or may estimate that two or more commands that occur at a frequency equal to or greater than a predetermined first threshold are the preparation command and post-processing command that should be at that relative position. On the other hand, if the frequencies of the command codes at each relative position are all equal to or less than a predetermined second threshold, the command estimation unit 154 may estimate that there are no preparation commands and post-processing commands that should be at that relative position.

When the command estimation unit 154 estimates the preparation command and the post-processing command that should be in the respective relative positions with respect to the command related to processing, the command estimation unit 154 may further estimate arguments for each of the estimated preparation commands and post-processing commands. When estimating the arguments of the command, the command estimation unit 154 estimates the arguments of each preparation command and post-processing command using the second learning model created for each preparation command and post-processing command corresponding to the command related to processing input from the data acquisition unit 100 and the information related to the operating environment of the command, among the second learning models stored in the learning model storage unit 220. FIG. 9 is a diagram illustrating an example of the second learning model created as a frequency graph. The command estimation unit 154 may refer to the second learning model and estimate a set of arguments that are frequent on the frequency graph for each preparation command and post-processing command as the preparation command and post-processing command that should be before and after the command related to processing. In the example of FIG. 9, a set of two arguments, X, Y, and Z, is estimated as the appropriate argument set for the home position return command G28, which is a preparation command, and a set of two arguments, X and Y, is estimated as the appropriate argument set for each command for the work coordinate system option example G54, which is a preparation command. The command estimation unit 154 may estimate the most frequent argument set as the appropriate argument set for that command. Furthermore, when multiple argument sets show a frequency equal to or greater than a predetermined third threshold value, all arguments included in the multiple argument sets may be estimated as the appropriate arguments for that command.

The estimation result display unit 120 is realized by the CPU 11 of the machining program creation device 1 shown in FIG. 1 executing a system program read from the ROM 12, and mainly performing calculation processing by the CPU 11 using the RAM 13 and non-volatile memory 14, and output control processing by the interface 17. The estimation result display unit 120 displays a template of a machining program including machining-related commands on the display device 70, based on the preparatory commands and post-processing commands that should precede and follow the machining-related commands estimated by the command estimation unit 154, and on sets of arguments suitable for each of the preparatory commands and post-processing commands.

Figure 10 is a diagram showing an example of a template for a machining program displayed by the estimation result display unit 120. The estimation result display unit 120 creates a machining program in which the preparation command and post-processing command estimated by the estimation result display unit 120 are specified at a relative position from the command related to machining. The estimation result display unit 120 also inserts a set of arguments estimated by the estimation result display unit 120 after each preparation command and post-processing command. When the command estimation unit 154 estimates that there should be multiple preparation commands or post-processing commands for one relative position, the estimation result display unit 120 may specify the multiple estimated preparation commands or post-processing commands in a row at the relative position.

The machining program creation device 1 according to this embodiment, which is configured as described above, can use the learning model stored in the learning model storage unit 220 to estimate the preparatory commands and post-processing commands that should be specified before and after the commands related to machining in the machining program, and can present to the operator a template of the machining program based on the estimation results. In addition, the template of the machining program can also show a set of arguments suitable for each preparatory command and post-processing command. The operator can relatively easily complete the machining program by further inputting the necessary information while looking at the template of the machining program shown in this way.

Although one embodiment of the present invention has been described above, the present invention is not limited to the above-described embodiment, and can be embodied in various forms by making appropriate modifications.
For example, the first learning model and the second learning model provided in the machining program creation device 1 can be configured to be shared with other machining program creation devices 1. At this time, a plurality of machining program creation devices 1 may be connected via a network 5, and the first learning model and the second learning model may be shared by communicating with each other via the network 5. By configuring in this way, it is possible to collect machining programs created by a plurality of machining program creation devices 1, and create and use the first learning model and the second learning model. By increasing the number of machining programs used to create the learning model, the accuracy of learning is expected to improve, and by using the learning model created in this way, the accuracy of estimation is also expected to improve.
11, a learning model storage unit 220' for storing the first learning model and the second learning model may be provided in an external computer 6 such as a fog computer or a cloud server, and the learning model storage unit 220' may be configured to be shared by a plurality of machining program creation devices 1. With this configuration, each machining program creation device 1 does not need to be provided with the learning model storage unit 220, and therefore does not need to be provided with a large-scale memory, which has a significant cost advantage.

1 Machining program creating device 3 Numerical control device 5 Network 6 Computer 11 CPU
12 ROM
13 RAM
14 Non-volatile memory 15, 17, 18, 20 Interface 22 Bus 70 Display device 71 Input device 72 External device 100 Data acquisition unit 110 Machining program analysis unit 120 Estimation result display unit 150 Machine learning unit 152 Learning unit 154 Command estimation unit 210 Machining program storage unit 220, 220' Learning model storage unit

Claims (8)

A machining program creation device that supports creation of a control program for a machine tool, comprising:
A data acquisition unit that acquires a machining program;
a machining program analysis unit that extracts at least one machining command, at least one preparatory command, and at least one post-processing command from the machining program, and analyzes relative positions of the preparatory command and the post-processing command from the machining command, the relative positions including the distances from the machining commands ;
A learning unit that creates a first learning model that learns relative positions of each preparatory command and post-processing command from each command related to the machining, the relative positions including distances from the command related to the machining , based on an analysis result by the machining program analysis unit;
A machining program creating device comprising: The learning unit creates a second learning model that learns arguments of the preparation command and the post-processing command.
The machining program creating device according to claim 1. The learning unit creates the first learning model for each command related to the same or similar processing.
The machining program creating device according to claim 1. The data acquisition unit further acquires information related to an operating environment of the machining program,
The learning unit creates the first learning model for each machining program operating environment based on information related to the operating environment of the machining program.
The machining program creating device according to claim 1. A machining program creation device that supports creation of a control program for a machine tool, comprising:
A data acquisition unit that acquires instructions related to processing;
A machining program analysis unit that analyzes commands related to the machining;
a command estimation unit that estimates the preparatory commands and the post-processing commands to be placed at relative positions including a predetermined distance from the command related to the machining based on a first learning model stored in a learning model storage unit that stores a first learning model that has learned a relative position including a distance from the command related to the machining of each preparatory command and post-processing command from the command related to the machining, and an analysis result by the machining program analysis unit;
an estimation result display unit that displays a template of a machining program including the instructions related to the machining and the preparation instructions and post-processing instructions estimated by the instruction estimation unit;
A machining program creating device comprising: The learning model storage unit further stores a second learning model that has learned arguments of the preparation command and the post-processing command,
The command estimation unit further estimates arguments of the estimated preparation command and post-processing command.
The machining program creating device according to claim 5. The learning model created by the learning unit is shared among the plurality of machining program creation devices via a network.
The machining program creating device according to claim 1. A learning model used for estimation by the command estimation unit is shared among the plurality of machining program creation devices via a network.
The machining program creating device according to claim 5.

Images