WO2021152852A1

WO2021152852A1 - Control device, machine learning device, and control method

Info

Publication number: WO2021152852A1
Application number: PCT/JP2020/003799
Authority: WO
Inventors: 啓史長江; 剛志津田; 敏章木全
Original assignee: 三菱電機株式会社
Priority date: 2020-01-31
Filing date: 2020-01-31
Publication date: 2021-08-05
Also published as: CN114981741A; JP7282217B2; JPWO2021152852A1; DE112020005842T5

Abstract

A control device (10A) for determining a job allocation method for a numerical control device (1) that allocates a job constituting software to each of a plurality of calculation units so that the calculation unit executes the job is characterized by comprising: a transition diagram display unit (111) which, on the basis of log data acquired from the numerical control device (1), displays a transition diagram indicating, in time series, the execution status of the job executed by each of the plurality of calculation units, said log data including information identifying calculation units that executed jobs in the past, and also identifying the timings with which the jobs were executed in the past; an option generation unit (14) which, on the basis of constraints imposed on the software, generates options for how to change the allocation status of a job indicated by the transition diagram; an input reception unit (12) which receives input information indicating an option selected from among the generated options; and a change information output unit (16) which, in accordance with the option indicated by the input information, outputs change information for changing the allocation status of the job.

Description

Control device, machine learning device, and control method

In the present disclosure, a control device, a machine learning device, and a control device for determining a job allocation method of a numerical control device for assigning and executing jobs constituting software for controlling the operation of the numerical control device to each of a plurality of arithmetic units. Regarding the method.

In recent years, the functions required for numerical control devices that control machine tools have become diversified and sophisticated, and the required processing performance has also increased. One of the methods for improving the processing performance of the numerical control device is to execute the processing of the numerical control device in parallel by using hardware having a plurality of arithmetic units. In a numerical control device including a plurality of arithmetic units, the processing performance changes depending on the allocation state of a job, which is a processing unit to be executed in parallel, to the arithmetic unit. Therefore, it is important to control the job allocation status to the arithmetic unit in order to improve the processing performance of the numerical control device.

Patent Document 1 discloses a method of controlling a job allocation state to a calculation unit based on machining conditions set in a machine tool by using machine learning in a numerical control device having a plurality of calculation units. There is.

Japanese Unexamined Patent Publication No. 2019-003271

However, according to the technique disclosed in Patent Document 1, there is a problem that it is difficult for a person who does not have expertise in parallel programming to make adjustments while checking the job allocation status to the arithmetic unit.

In the software of the numerical control device, which has been developed on the premise of execution by a single arithmetic unit, there are various restrictions in assigning jobs that compose the software to each of a plurality of arithmetic units. For example, when it is necessary to use the execution result of the first job in the second job, the first job and the second job cannot be parallelized. Further, when the first job and the second job need to access the same memory area, the first job and the second job cannot be parallelized. As described above, since there are restrictions to be considered when performing parallel programming, it is difficult for a person who does not have expertise in parallel programming to adjust the job allocation state to the arithmetic unit.

This disclosure is made to solve the above-mentioned problems, and even a person who does not have expertise in parallel programming can make adjustments while checking the job allocation status to the arithmetic unit. The purpose is to obtain an easy control device.

In order to solve the above-mentioned problems and achieve the object, the control device according to the present disclosure determines a job allocation method of a numerical control device for assigning and executing jobs constituting software to each of a plurality of arithmetic units. In each of the plurality of arithmetic units, which is a control device, is acquired from the numerical control unit and includes log data including information that identifies the arithmetic unit that executed the job in the past and the timing in which the job was executed in the past. A transition diagram display unit that displays a transition diagram that shows the job execution status in chronological order, and an option generation that generates options for how to change the job allocation status displayed in the transition diagram based on the constraints imposed on the software. A unit, an input reception unit that accepts input information indicating the option selected from the generated options, and a change information output unit that outputs change information for changing the job allocation status according to the options indicated by the input information. It is characterized by having.

According to the present disclosure, even a person who does not have expertise in parallel programming can easily make adjustments while checking the job allocation status to the arithmetic unit.

The figure which shows the structure of the numerical control apparatus which comprises the control apparatus which concerns on Embodiment 1. A flowchart for explaining the operation of the control device shown in FIG. A diagram showing an example of a transition diagram displayed by the transition diagram display unit in step S103 of FIG. The figure which shows an example of the option displayed in step S106 of FIG. The figure which shows an example of the transition diagram after the change which is displayed in step S109 of FIG. A flowchart for explaining the details of step S108 of FIG. The figure which shows the functional structure of the control device which concerns on Embodiment 2. The figure which shows the structure of the numerical control apparatus which includes the control apparatus which concerns on Embodiment 3. A flowchart for explaining the operation of the control device shown in FIG. The figure which shows an example of the transition diagram abstracted in step S201 of FIG. A diagram showing an example of the options abstracted in step S202 of FIG. The figure which shows an example of the transition diagram after the change abstracted in step S203 of FIG. The figure which shows the structure of the control device which concerns on Embodiment 4. The figure which shows the structure of the numerical control apparatus which has the control apparatus which concerns on Embodiment 5. The figure which shows the functional structure of the machine learning apparatus shown in FIG. The figure which shows the structure of the control apparatus which concerns on Embodiment 6. The figure which shows the dedicated hardware for realizing the function of the control device which concerns on Embodiments 1-6. The figure which shows the structure of the control circuit for realizing the function of the control apparatus which concerns on Embodiments 1-6.

Hereinafter, the control device, the machine learning device, and the control method according to the embodiment of the present disclosure will be described in detail based on the drawings. The technical scope of the present disclosure is not limited by the embodiments shown below.

Embodiment 1.
FIG. 1 is a diagram showing a configuration of a numerical control device 1 including the control device 10A according to the first embodiment. The numerical control device 1 includes a control device 10A, a change information storage unit 17, a numerical control processing execution unit 18, and a log data storage unit 19.

The numerical control device 1 has a plurality of arithmetic units (not shown). The plurality of arithmetic units may be a multi-core CPU having a plurality of cores in one CPU (Central Processing Unit), or may be a multi-CPU having a plurality of CPUs. That is, the arithmetic unit included in the numerical control device 1 may be a "core" possessed by the CPU, or may be a processing device such as the "CPU". Hereinafter, each of the arithmetic units may be referred to as a “core”. The numerical control device 1 assigns jobs constituting software to each of a plurality of arithmetic units and executes them. Each of the plurality of arithmetic units executes the assigned job. By using the plurality of arithmetic units in this way, the numerical control device 1 can execute a plurality of jobs in parallel. By executing a plurality of jobs in parallel, the numerical control device 1 can increase the processing capacity as compared with executing the jobs sequentially by a single arithmetic unit.

The control device 10A has a function of determining a method of allocating jobs to a plurality of calculation units of the numerical control device 1. The control device 10A acquires log data from the numerical control device 1. The log data includes information for specifying the allocation state of the job executed in the past by the numerical control device 1 and information for specifying the execution state of the job. Here, the information for specifying the job allocation state is information for specifying in which arithmetic unit the job executed by the numerical control device 1 in the past was executed, and the information for specifying the job allocation state is the job. When information that specifies the timing at which is executed is added, it becomes information that specifies the execution state of the job. For example, the log data includes a job name which is information for identifying a job, information indicating an arithmetic unit to which a job is assigned, and event occurrence time information for each job. The job name and the information indicating the arithmetic unit to which the job is assigned are examples of information for specifying the job allocation status. The event occurrence time information for each job is an example of information that identifies the timing at which the job is executed. The control device 10A generates change information for changing the job allocation state by performing various processes based on the acquired log data, and outputs the generated change information. The change information storage unit 17 stores the change information generated by the control device 10A.

The numerical control processing execution unit 18 uses a plurality of arithmetic units to perform numerical control processing of the machine tool that is the control target of the numerical control device 1. The numerical control processing execution unit 18 is a software processing execution unit for realizing the functions required as the numerical control device 1. Specific examples of the processing executed by the numerical control processing execution unit 18 include a processing for analyzing a machining program that describes the machining content to be executed by the machine tool, an interpolation processing for smoothly commanding the path of the tool, and a machine tool. Acceleration / deceleration processing that creates a speed pattern for quick operation without vibration. The numerical control processing execution unit 18 can change the job allocation state according to the change information stored in the change information storage unit 17. The numerical control processing execution unit 18 determines the timing at which each of the plurality of arithmetic units executes the assigned job according to the restrictions imposed on the software. Further, the numerical control processing execution unit 18 generates log data and outputs it to the log data storage unit 19 while performing the numerical control processing.

The log data storage unit 19 stores the log data output by the numerical control processing execution unit 18. In FIG. 1, the change information storage unit 17 and the log data storage unit 19 are provided by the numerical control device 1. However, in the change information storage unit 17 and the log data storage unit 19, the numerical control device 1 is provided via the network. It may be a storage area such as a computer or a hard disk that can be accessed by. The log data includes, for example, the name of a job constituting the numerical control process, information for specifying an arithmetic unit assigned to each job, an event occurrence time for each job, and the like. A job is a processing unit on software that can change the allocation destination to a plurality of arithmetic units. A job includes not only units such as functions in programming, but also units that are a collection of functions such as tasks and processes.

There are multiple types of events. For example, the "start event" that occurs when a job gets the execution right in the calculation unit, and the execution right is given by a job that has a higher priority than the running job, such as an interrupt job. "Preempted event" that occurs when a job is stolen, "exit event" that occurs when a job completes processing and relinquishes execution rights, and occurs when a job releases execution rights to another job. There are "release to xxx events" and so on. Here, in "xxx" of "release to xxx event", a job name indicating another target job is entered. In order for the numerical control processing execution unit 18 to perform the event log acquisition processing, an API (Application Programming Interface) provided by a generally popular real-time OS (Operating System) or the like may be used.

The control device 10A includes a display unit 11, an input reception unit 12, a transition diagram generation unit 13, a choice generation unit 14, a post-change transition diagram estimation unit 15, and a change information output unit 16.

The display unit 11 provides a display screen including a transition diagram, options for changing the job allocation state, and a transition diagram after the change. The display unit 11 can perform drawing processing using an internal or external display device of the numerical control device 1 to provide the above display screen.

The display unit 11 includes a transition diagram display unit 111 that displays the transition diagram generated by the transition diagram generation unit 13, an option display unit 112 that displays the options generated by the option generation unit 14, and a transition diagram estimation unit 15 after the change. It has a changed transition diagram display unit 113 that displays an estimated changed transition diagram. Each of the transition diagram display unit 111, the option display unit 112, and the changed transition diagram display unit 113 has two or more of the transition diagram, the options, and the changed transition diagram in one screen area drawn by the display unit 11. May be performed so that is included at the same time. For example, when the display unit 11 provides a display screen including a transition diagram, options, and a changed transition diagram, each of the transition diagram display unit 111, the option display unit 112, and the changed transition diagram display unit 113 is a screen area. Perform drawing processing on a part. Further, when the user performs a switching operation while one or two of the transition diagram, the options, and the changed transition diagram are displayed, the display unit 11 may switch the displayed contents.

The input receiving unit 12 receives the input information generated by the user using the input device or the input information generated by the machine. The input receiving unit 12 can output the received input information to each of the option generation unit 14, the changed transition diagram estimation unit 15, and the change information output unit 16.

The transition diagram generation unit 13 generates a transition diagram representing the job execution status in each of the plurality of calculation units in chronological order based on the log data. The transition diagram shows in chronological order which job was executed by each of the plurality of arithmetic units of the numerical control device 1 at a certain time. The transition diagram generation unit 13 outputs the generated transition diagram to the transition diagram display unit 111 of the display unit 11.

The option generation unit 14 generates options for changing the allocation status of the job indicated by the input information output by the input reception unit 12. The job indicated by the input information output by the input receiving unit 12 is a designated job among the jobs displayed in the transition diagram. The options for changing the allocation status are which of the plurality of arithmetic units executes each job of the software of the numerical control device 1, which job is executed in parallel, or the jobs are distributed to the plurality of arithmetic units. It is an option regarding how to change the job allocation status, such as whether to execute in parallel. At this time, the option generation unit 14 generates "changeable options" based on the restrictions imposed on the software. The restrictions imposed on software are, for example, a combination of jobs that cannot be processed in parallel among multiple jobs that make up the software, restrictions imposed on the order of jobs, and restrictions imposed on the arithmetic unit that can execute jobs. There are restrictions and so on. If the option generator 14 does not generate options based on the constraints imposed on the software, the generated options may include options that are not mutable. The non-modifiable option is, for example, an option to process a plurality of jobs that cannot be processed in parallel. The option generation unit 14 outputs the generated options to the option display unit 112 of the display unit 11.

The post-change transition diagram estimation unit 15 estimates the transition diagram when the job allocation state is changed according to the options indicated by the input information output by the input reception unit 12 based on the log data. The options indicated by the input information output by the input receiving unit 12 are the options selected from the options generated by the option generating unit 14. The changed transition diagram estimation unit 15 outputs the estimated changed transition diagram to the changed transition diagram display unit 113 of the display unit 11.

The change information output unit 16 generates change information for changing the job allocation state according to the options indicated by the input information output by the input reception unit 12. The options indicated by the input information output by the input receiving unit 12 are the options selected from the options generated by the option generating unit 14. The input information may indicate multiple choices. When a plurality of options are selected, the change information output unit 16 generates change information based on all the currently selected options. The change information output unit 16 can output the generated change information to the change information storage unit 17.

The change information is data described in a format for reflecting the change in the job allocation status to the numerical control processing execution unit 18. For example, the change information is a file in which information such as which calculation unit each job is assigned to and whether or not a job is to be distributed and executed in a plurality of calculation units is described in a text format according to a predetermined format. It may be a binary file in which the above information is described so that it can be analyzed by a real-time OS or the like.

FIG. 2 is a flowchart for explaining the operation of the control device 10A shown in FIG. First, the control device 10A acquires log data from the log data storage unit 19 (step S101). The log data acquired from the log data storage unit 19 is output to each of the transition diagram generation unit 13 and the changed transition diagram estimation unit 15.

The transition diagram generation unit 13 generates a transition diagram based on the log data (step S102). Specifically, the log data includes information for specifying the job execution state such as the job name, the calculation unit that executed the job, and the event occurrence time for each job, and the transition diagram generation unit 13 includes information such as the job execution state. Based on the information, a transition diagram showing the job execution status in each of the plurality of arithmetic units in chronological order is generated. The transition diagram generation unit 13 outputs the generated transition diagram to the transition diagram display unit 111.

The transition diagram display unit 111 displays the transition diagram generated by the transition diagram generation unit 13 on the display screen (step S103). The job displayed in the transition diagram can be selected, and the input receiving unit 12 can receive input information indicating the selected job. Here, it is assumed that the user who sees the display screen performs an input operation for selecting a job included in the displayed transition diagram.

FIG. 3 is a diagram showing an example of a transition diagram displayed by the transition diagram display unit 111 in step S103 of FIG. The horizontal axis of FIG. 3 is the time axis. Core0, core1, core2, and core3 in FIG. 3 indicate a plurality of arithmetic units included in the numerical control device 1. Each of the plurality of blocks shown in FIG. 3 represents a job. Here, the type of job can be distinguished by the type of texture that fills the block. In addition to using textures, the transition diagram display unit 111 can display job types in a distinguishable manner by using block colors, text, and the like. When text is used, the transition diagram display unit 111 can display information indicating the nature of the job such as the type of job in a pop-up using text or the like when the box indicating the job is selected. FIG. 3 shows the execution state of the job in chronological order for each calculation unit. Note that FIG. 3 is an example, and the transition diagram may be a time-series representation of the job execution states in each of the plurality of arithmetic units. In FIG. 3, the horizontal axis is the time axis, but the vertical axis may be the time axis.

By displaying a transition diagram showing the job execution state in chronological order for each calculation unit, the user of the control device 10A can intuitively grasp which calculation unit has a high load. Further, in the transition diagram of FIG. 3, since the horizontal axis is the time axis, it is shown that when a plurality of blocks indicating jobs are vertically overlapped, these blocks are executed in parallel. According to FIG. 3, it can be seen that the arithmetic unit represented by “core1” has a higher processing load than the other arithmetic units.

The user can check the displayed transition diagram and understand how the current numerical control device 1 is operating. The user grasps how the current numerical control device 1 operates, and then performs an analysis based on each problem awareness. For example, if the processing of the numerical control device 1 is not completed within a predetermined period, the user identifies a job that becomes a bottleneck of the processing time, or analyzes the bias of the load status between the arithmetic units. Based on the results of the analysis, the user can perform an operation of determining and selecting a target job for problem solving.

Return to the explanation in Fig. 2. The input receiving unit 12 determines whether or not the job displayed on the transition diagram is selected (step S104). If there is no job selected displayed in the transition diagram (step S104: No), the process is repeated from step S103.

When there is a job selection displayed in the transition diagram (step S104: Yes), that is, when the input receiving unit 12 receives the input information indicating the selected job, the input receiving unit 12 receives the received input information. Output to the option generation unit 14. The option generation unit 14 generates options for changing the allocation state of the selected job based on the constraints imposed on the software (step S105). When the input information indicates a plurality of jobs, the option generation unit 14 generates options for changing the allocation state of each of the plurality of jobs. The option generation unit 14 may generate one option of the method of changing the allocation state for one job, or may generate a plurality of options.

The option generation unit 14 verifies the static constraint condition in the target job by using the constraint condition information indicating the constraint imposed on the software. Here, the static constraint condition is a constraint condition defined by the nature of each job regardless of how the job is assigned to the calculation unit. For example, the static constraint conditions include "the second job must not be executed until the execution of the first job is completed", "the third job and the fourth job must not be executed in parallel", and the like. It is a condition such as. By the verification of the static constraint condition, the option of the method of changing the allocation state that can be selected within the range of the constraint imposed on the software of the numerical control device 1 is selected.

The constraint condition information includes the constraint conditions existing in the software listed in advance by a person who has expertise in software for controlling the numerical control device 1, such as a software developer of a manufacturer of the numerical control device 1. Information saved in the form of a list, database, etc.

The option generation unit 14 subsequently verifies the dynamic constraint condition using the information indicating the calculation unit of the allocation destination for each job included in the log data. A dynamic constraint is a constraint imposed by the arithmetic unit to which the job is currently assigned. For example, when using an AMP (Asymmetrical Multi Processing) type multi-core CPU, there may be cores that cannot be assigned depending on the nature of the job and the core. The option generation unit 14 generates a changeable option as a result of verifying the static constraint condition and the dynamic constraint condition. The option generation unit 14 outputs the generated options to the option display unit 112.

The option display unit 112 displays the options generated by the option generation unit 14 on the display screen (step S106). The options displayed on the display screen can be selected, and the input receiving unit 12 can receive input information indicating the selected options. Here, it is assumed that the user who sees the display screen performs an input operation for selecting the displayed option.

FIG. 4 is a diagram showing an example of the options displayed in step S106 of FIG. Here, there are three jobs selected in step S104, and one option is generated for each of the three jobs. The option display unit 112 selects the selected job to be changed and the options of the method of changing the allocation status of the selected job, which are determined to be changeable based on the restrictions imposed on the software. It can be shown on the display screen. The option of the method of changing the allocation status of the jobs shown in the upper part of FIG. 4 is processing distribution, in which one job is divided into a plurality of jobs, here four jobs, and each of the four jobs is calculated differently. It is shown to be executed in the department. The option of the method of changing the allocation state of the job shown in the middle of FIG. 4 is to move to another core, and the job executed by the calculation unit indicated by "core1" is indicated by "core2". Indicates that the arithmetic unit that executes the job is moved so that it is executed in. The option of the method of changing the allocation state of the job shown in the lower part of FIG. 4 is to move to another core, and the job executed by the calculation unit indicated by "core2" is indicated by "core1". Indicates that the arithmetic unit that executes the job is moved so that it is executed in.

The option display method may be a method of illustrating the change in the schematic diagram before and after the application of the option as shown in the upper part of FIG. 4, or a list format as shown in the middle and lower parts of FIG. It may be expressed by. It is desirable that the option display method is a method that allows the user to grasp the state before and after the application of the option.

Return to the explanation in Fig. 2. The input receiving unit 12 determines whether or not there is a selection of options displayed on the display screen (step S107). If no option is selected (step S107: No), the process is repeated from step S106.

When there is a selection of options (step S107: Yes), that is, when the input receiving unit 12 receives the input information indicating the selected option, the input receiving unit 12 changes the received input information and changes the transition diagram estimation unit. Output to 15. The input information received by the input receiving unit 12 may indicate one option or may indicate a plurality of options. The post-change transition diagram estimation unit 15 estimates the transition diagram after changing the job allocation state according to the selected options based on the log data (step S108). When the input information indicates a plurality of options, the changed transition diagram estimation unit 15 estimates the transition diagram after changing the job allocation state according to the plurality of options. The changed transition diagram estimation unit 15 outputs the estimated transition diagram to the changed transition diagram display unit 113.

The changed transition diagram display unit 113 displays the estimated changed transition diagram on the display screen (step S109).

FIG. 5 is a diagram showing an example of a transition diagram after the change displayed in step S109 of FIG. Here, the changed transition diagram generated when all of the options shown in FIG. 4 are selected is shown. The method in which the changed transition diagram display unit 113 expresses the changed transition diagram is the same as the method in which the transition diagram display unit 111 expresses the transition diagram. The horizontal axis of FIG. 5 is the time axis. Core0, core1, core2, and core3 in FIG. 5 indicate a plurality of arithmetic units included in the numerical control device 1. Each of the plurality of blocks shown in FIG. 5 represents a job. Here, the type of job can be distinguished by the type of texture that fills the block. The changed transition diagram display unit 113 can display an operation unit for selectively inputting whether or not to confirm the change, together with the changed transition diagram as shown in FIG. The user confirms the transition diagram after the change, determines whether or not the problems such as processing time and processing load can be solved, and performs an input operation for selecting whether or not to confirm the change.

Return to the explanation in Fig. 2. The input receiving unit 12 determines whether or not to confirm the change based on the received input information (step S110). Note that "determination of change" means that the option selected in step S107 is applied to the job selected in step S104 from the options of the method of changing the allocation state generated in step S105.

When the change is not confirmed (step S110: No), the input receiving unit 12 outputs the input information to the transition diagram generation unit 13, and causes the transition diagram display unit 111 to repeat the process of step S103. At this time, the input receiving unit 12 may operate so that the process is repeated from step S106. In this case, the user can start over by selecting an option instead of selecting a job.

When confirming the change (step S110: Yes), the input receiving unit 12 adds the option selected in step S107 to the confirmed option (step S111). The input reception unit 12 instructs the transition diagram generation unit 15 after the change to display a screen for accepting an input operation as to whether or not to complete the selection of options, and the user performs an input operation on the displayed screen. Then, the input receiving unit 12 determines whether or not to complete the selection of the options based on the received input information (step S112).

When the selection of the options is not completed (step S112: No), the input receiving unit 12 outputs the input information to the changed transition diagram estimation unit 15, and the process is repeated from step S103. When the process is repeated from step S103 after the change is confirmed, the changed transition diagram to which the options selected in step S107 is applied is displayed in step S103, and the changed transition diagram is displayed in step S104. It will be determined whether or not there is a job selection displayed in. That is, when the process is repeated from step S103 after the change is confirmed, the transition diagram display unit 113 after the change displays the transition diagram in step S103.

When the selection of the options is completed (step S112: Yes), the input receiving unit 12 outputs the information indicating the confirmed options to the change information output unit 16, and the change information output unit 16 performs numerical control processing according to the confirmed options. The execution unit 18 outputs the change information for changing the job allocation state to the change information storage unit 17 (step S113). The numerical control processing execution unit 18 operates based on the change information stored in the change information storage unit 17, so that the job allocation status to the calculation unit is changed.

There may be multiple options for changing the job allocation status for one job. Therefore, the processing performance of the numerical control device 1 changes depending on the combination of which option is applied to each of the plurality of jobs. Depending on the combination of options to be applied, it is possible that the processing performance will rather decrease. Therefore, according to the operation shown in FIG. 5, the user can determine the combination of the options to be applied among the generated options by trial and error while looking at the estimated transition diagram.

FIG. 6 is a flowchart for explaining the details of step S108 of FIG. In step S108 of FIG. 2, in order to estimate the changed transition diagram, the changed transition diagram estimation unit 15 estimates the occurrence time of events related to the execution of the target job such as "start event" and "exit event". There is a need. Therefore, the post-change transition diagram estimation unit 15 estimates the post-change event occurrence time based on the event occurrence time before the allocation state change of the target job based on the log data.

First, the changed transition diagram estimation unit 15 starts searching the event log included in the log data from the beginning (step S11). When the event log is discovered, the changed transition diagram estimation unit 15 determines whether or not the event indicated by the discovered event log is an event of the target job (step S12). When it is an event of the target job (step S12: Yes), the changed transition diagram estimation unit 15 determines whether or not the event indicated by the found event log is the first "start event" (step S13).

If it is not an event of the target job (step S12: No) and if it is not the first "start event" (step S13: No), the changed transition diagram estimation unit 15 proceeds to search the next event log (step S12: No). Step S14), the process is repeated from step S12.

In the case of the first "start event" (step S13: Yes), the post-change transition diagram estimation unit 15 generates the "start event" after applying the change of the target job based on the occurrence time of the found event log. Estimate the time (step S15).

The changed transition diagram estimation unit 15 proceeds to the next event log search (step S21). When the event log is discovered, the changed transition diagram estimation unit 15 determines whether or not the event indicated by the discovered event log is an event of the target job (step S22). If it is not an event of the target job (step S22: No), the changed transition diagram estimation unit 15 repeats the process of step S21.

If it is an event of the target job (step S22: Yes), the changed transition diagram estimation unit 15 determines whether or not the event indicated by the found event log is an “exit event” (step S23). If it is not an “exit event” (step S23: No), the post-change transition diagram estimation unit 15 estimates the event occurrence time after applying the change of the target job (step S24), and returns to the process of step S21.

In the case of an "exit event" (step S23: Yes), the transition diagram estimation unit 15 after the change estimates the occurrence time of the "exit event" after the change is applied (step S25).

The changed transition diagram estimation unit 15 searches the event log in the range from step S21 to step S25 (step S31). The changed transition diagram estimation unit 15 determines whether or not the search of the event log in the search range has been completed (step S32). When the search of the search range is not completed (step S32: No), the changed transition diagram estimation unit 15 determines whether or not the event indicated by the target event log is affected by the events changed so far. Determine (step S33). Criteria for determining the presence or absence of influence are predetermined. For example, when the occurrence time of the "release event" for the target job is changed, the changed transition diagram estimation unit 15 determines that there is an influence. Further, when a job having a higher priority than the target job is executed in the same calculation unit as the target job due to the assignment change of the calculation unit, the changed transition diagram estimation unit 15 determines that there is an influence. do. When the time of the section from the "start event" to the "exit event" of the target job overlaps with the section from the "start event" to the "exit event" of another job, the changed transition diagram estimation unit 15 , Judged as having an impact.

If there is an effect (step S33: Yes), the post-change transition diagram estimation unit 15 estimates the event occurrence time after the change is applied (step S34), proceeds to the next event log search (step S35), and steps. Return to the process of S32. If there is no effect (step S33: No), the changed transition diagram estimation unit 15 skips the process of step S34 and proceeds to the process of step S35.

When the search of the search range is completed (step S32: Yes), the changed transition diagram estimation unit 15 repeats the processes of steps S11 to S35 for all the jobs including the event determined to have an influence (step S32: Yes). S41).

The changed transition diagram estimation unit 15 determines whether or not the search has been completed until the final event of the log data (step S42). When the search is completed up to the final event of the log data (step S42: Yes), the changed transition diagram estimation unit 15 ends the process. When the search is not completed until the final event of the log data (step S42: No), the changed transition diagram estimation unit 15 repeats the process from step S11. However, when returning from step S42 to step S11, the changed transition diagram estimation unit 15 executes the process of step S11 not from the beginning of the event log but from the first event determined to have an influence.

As described above, the changed transition diagram estimation unit 15 searches the event log of the selected target job from the beginning of the log data by performing the processes of steps S11 to S15, and the first "start event". Estimates the occurrence time of the "start event" after applying the change based on the occurrence time of. As a method of estimating the event occurrence time, for example, there is a method of estimating based on the occurrence time of the "relase event" for the target job immediately before the "start event" of interest. In addition, the post-change transition diagram estimation unit 15 performs the processes of steps S21 to S25, and among the events of the selected target job, by the "exit event" immediately after the "start event" of interest. For all the events that have occurred, the event occurrence time after applying the change is estimated using the above-mentioned event occurrence time estimation method. Further, the post-change transition diagram estimation unit 15 occurs in the section from the "start event" to the "exit event" of the selected target job, which is currently being focused on, by performing the processes of steps S31 to S35. , For all events of other jobs, it is determined whether or not there is an influence from the event changed in the estimation so far, and the occurrence time is estimated for the event judged to have an influence. After the change, the transition diagram estimation unit 15 performs the processes of steps S41 and S42, and for each of the jobs including the events determined to have an influence in the processes of steps S31 to S35, steps S11 to S35. Process is repeated until the final event included in the log data is reached.

In the above, the post-change transition diagram estimation unit 15 estimates the event occurrence time after the allocation change based on the event occurrence time before the allocation state is changed, but the performance of the calculation unit before and after the allocation change is different. In this case, the time required for job execution may be grasped and the event occurrence time may be estimated after considering the difference in performance.

As described above, according to the control device 10A according to the first embodiment, a transition diagram showing the job execution state in each of the plurality of arithmetic units of the numerical control device 1 in chronological order is displayed, and the transition diagram is displayed. The choice of how to change the assigned status of the displayed job is generated based on the constraints imposed on the software. Then, the input information indicating the option selected from the generated options is received, and the change information for changing the job allocation state is output according to the option indicated by the input information. Therefore, even a person who does not have expertise in parallel programming can easily make adjustments while checking the job allocation status to the arithmetic unit.

For example, a general software developer, a serviceman who performs product maintenance and maintenance services, a user of a numerical control device 1 such as a machine maker who purchases a numerical control device 1 and ships a machine tool having a built-in numerical control device 1. Does not necessarily have expertise in parallel programming. Even such a user can make appropriate adjustments because the options displayed by the control device 10A are narrowed down to those that do not violate the restrictions imposed on the software.

Further, the control device 10A displays a transition diagram showing the execution status of the jobs assigned to the calculation unit in chronological order, and options for changing the allocation status of the selected job among the jobs displayed in the transition diagram. Is generated, the execution state of the job after changing the allocation state according to the option selected from the generated options can be estimated, and the transition diagram after the change can be displayed. By having such a configuration, the user of the numerical control device 1 can adjust the allocation state while checking the job allocation state when the change method shown in the option is applied.

The machine tool to be controlled by the numerical control device 1 has various sizes and types of the machine tool itself, and the environment in which it is used also varies from user to user. Therefore, the performances and functions required of the numerical control device 1 vary widely, and the numerical control device 1 is required to have a wide variety of functions in order to meet this demand.

For example, a multi-tasking machine is an example of a machine tool having a large and complicated structure. A multi-tasking machine has multiple spindles, and while executing a large number of machining programs in parallel at the same time, the machining objects are delivered while synchronizing between the machining programs, and multiple machining objects are machined at the same time. Can be done. In such a multi-tasking machine, since a large number of shafts for moving tools and objects to be machined move around in the machining tank in a complicated manner, a function called interference check is required so as not to interfere with each other. With such a function, the processing time increases in the job of finding the trajectory of the axis.

Further, a small machine tool, for example, a machine tool having only one spindle and three or four drive axes for changing the relative position between the spindle and the object to be machined, is called an interference check like a multi-tasking machine. No function is required, but instead a function to analyze as many machining programs as possible in a short time and smooth the tool path is required. In such a small machine tool, the processing time increases in the job of analyzing the machining program.

As described above, the functions and performance required of the numerical control device 1 differ depending on the type of machine tool controlled by the numerical control device 1. Further, the functions and performance required of the numerical control device 1 differ depending on the usage environment such as what kind of product the user processes using these machine tools and for what purpose the production activity is performed. For example, the functions and performance required of the numerical control device 1 are completely different between a user who receives a request and performs prototype processing of a one-piece product and a user who mass-produces parts used for mass-produced products.

As described above, it is difficult to determine in advance the job allocation state of the numerical control device 1 having a plurality of arithmetic units so as to be optimal for all users. Therefore, by using the control device 10A, the user can easily adjust the job allocation state according to his / her own usage environment, and the original performance of the numerical control device 1 can be sufficiently brought out. Becomes possible.

Embodiment 2.
FIG. 7 is a diagram showing a functional configuration of the control device 10B according to the second embodiment. Since the control device 10B has the same functions as the control device 10A according to the first embodiment except that the control device 10B is a device separate from the numerical control device 1, detailed description of common matters will be omitted.

The control device 10B includes a display unit 11, an input reception unit 12, a transition diagram generation unit 13, a choice generation unit 14, a post-change transition diagram estimation unit 15, and a change information output unit 16. The display unit 11 includes a transition diagram display unit 111, a choice display unit 112, and a changed transition diagram display unit 113.

The numerical control device 1 is a device separate from the control device 10B. The change information storage unit 17 and the log data storage unit 19 are storage areas such as a computer and a hard disk that the numerical control device 1 can access via a network. Further, the change information storage unit 17 may be a storage area built in the numerical control device 1. Similarly, the log data storage unit 19 may be a storage area built in the numerical control device 1.

The operation of the control device 10B is the same as the operation of the control device 10A described with reference to FIG. 2, except for the following points. The control device 10B can acquire log data from the log data storage unit 19 via the network. Further, by connecting a portable storage medium such as an SD card or USB (Universal Serial Bus) memory in which log data is stored to the control device 10B, the control device 10B can also acquire the log data.

When the control device 10B is connected to the change information storage unit 17 outside the control device 10B, the change information output unit 16 may output the change information to the change information storage unit 17 or the control device 10B. The change information may be output to a storage area on a device such as a computer that constitutes the above.

As described above, according to the control device 10B according to the second embodiment, as with the control device 10A according to the first embodiment, even a person who does not have expertise in parallel programming can be assigned to the arithmetic unit. It becomes easy to make adjustments while checking the job allocation status.

Further, the control device 10B is a device separate from the numerical control device 1. Therefore, there is an advantage that the numerical control device 1 is not affected by the processing load for performing the process of changing the job allocation state. For example, some machine tools equipped with the numerical control device 1 cannot easily stop the operating state because they are incorporated in the automation line. In such a case, it is desired to avoid causing the numerical control device 1 to execute a process other than the numerical control process in consideration of the influence on the product being processed. According to the control device 10B, as long as the numerical control device 1 performs the log data acquisition process, other processes can be performed by the control device 10B which is separate from the numerical control device 1, and therefore the numerical control device 1 can perform other processes. It is possible to adjust the job allocation status while suppressing the impact on performance.

Embodiment 3.
FIG. 8 is a diagram showing a configuration of a numerical control device 1 including the control device 10C according to the third embodiment. The numerical control device 1 includes a control device 10C, a change information storage unit 17, a numerical control processing execution unit 18, and a log data storage unit 19. The control device 10C includes a display unit 11, an input reception unit 12, a transition diagram generation unit 13, a choice generation unit 14, a post-change transition diagram estimation unit 15, a change information output unit 16, and an abstraction unit 20. Has. The display unit 11 includes a transition diagram display unit 111, a choice display unit 112, and a changed transition diagram display unit 113. The abstraction unit 20 has a transition diagram abstraction unit 201, a choice abstraction unit 202, and a changed transition diagram abstraction unit 203.

The control device 10C has an abstraction unit 20 in addition to the configurations of the control devices 10A and 10B. The abstraction unit 20 has a function of changing the degree of abstraction of the display content of the display screen generated by the display unit 11 based on the identification information indicating the user's attribute. The identification information is information for determining the degree of importance of the internal information of the numerical control device 1 to be accessible. The identification information is represented by a numerical value called, for example, a user level. The user level of the user who is permitted to access all internal information, such as the developer of the manufacturer of the numerical control device 1, is set to "4", which is the highest value, and is in charge of maintenance and service of the manufacturer of the numerical control device 1. The user level of the user who is permitted to access except for some highly important information such as a person can be set to "3". In addition, the user level of users who are allowed access to restricted information, such as development staff, maintenance staff, and service staff of machine tool manufacturers who purchase the numerical control device 1 and ship it in combination with the machine tool. It can be set to "2", and the user level of a user who is permitted to access only a small part of information, such as an end user who purchases and uses a machine tool, can be set to "1".

Important inside information is the company secret held by the manufacturer of the numerical control device 1 and the manufacturer of the machine tool. Therefore, by using the abstraction unit 20 to restrict access to internal information, the company secrets of each manufacturer can be protected, and a user who does not have sufficient knowledge can inadvertently change the numerical control device 1 or the machine tool. In addition, it is possible to prevent unintended operations from being performed.

Each of the transition diagram abstraction unit 201, the option abstraction unit 202, and the changed transition diagram abstraction unit 203 realizes access restriction to internal information by performing abstraction processing based on the identification information. Specifically, the transition diagram abstraction unit 201 acquires the drawing data of the transition diagram generated by the transition diagram display unit 111, performs abstraction processing based on the user's identification information, and obtains the processed drawing data. Output to the transition diagram display unit 111. The option abstraction unit 202 acquires the drawing data of the options generated by the option display unit 112, performs abstraction processing based on the user's identification information, and outputs the processed drawing data to the option display unit 112. The changed transition diagram abstraction unit 203 acquires drawing data of the changed transition diagram from the changed transition diagram display unit 113, performs abstraction processing based on the user's identification information, and obtains the processed drawing data. After the change, it is output to the transition diagram display unit 113.

The method by which the abstraction unit 20 of the control device 10C acquires the identification information is not particularly limited. For example, if the password of the numerical control device 1 is set to be different for each user level and the user inputs the password using the input device provided in advance in the numerical control device 1, the input reception unit 12 will perform each password type. It is possible to give different identification information and notify the abstraction unit 20.

FIG. 9 is a flowchart for explaining the operation of the control device 10C shown in FIG. Since a part of the operation shown in FIG. 9 is the same as the operation of the control device 10A described with reference to FIG. 2, detailed description will be omitted here by assigning the same reference numerals to the same operation. .. Hereinafter, the points different from FIG. 2 will be mainly described.

When the transition diagram generation unit 13 generates the transition diagram in step S102 and the transition diagram display unit 111 generates the transition diagram drawing data, the transition diagram abstraction unit 201 generates the transition diagram drawing data from the transition diagram display unit 111. Acquire and perform the abstraction process of the transition diagram (step S201). There are various possible ways to abstract the display contents of the transition diagram. For example, since the specific job name is software internal information, the transition diagram abstraction unit 201 can abstract or hide the job name included in the transition diagram. For example, the job name is displayed as it is for users whose user levels are "4" and "3", and the job name is changed to "Processing program" for users whose user levels are "2" and "1". It can be represented by a job function such as "job to analyze". Further, as another example of the method of abstracting the display contents of the transition diagram, it is conceivable to hide the information for each job and show the ratio of the processing execution time for each fixed time in chronological order for each arithmetic unit.

FIG. 10 is a diagram showing an example of a transition diagram abstracted in step S201 of FIG. In the transition diagram shown in FIG. 10, the information for each job is hidden, and the ratio of the processing execution time for each fixed time is shown in time series for each calculation unit. Since the transition diagram showing the allocation status for each job can be a clue for estimating how the numerical control process is performed, it should be kept secret from users other than the manufacturer who manufactures the numerical control device 1. It may be informational. In such a case, the transition diagram abstraction unit 201 provides a transition diagram to the extent that the time-series tendency of the processing load amount for each calculation unit can be understood for the users whose user levels are "2" and "1". Can be abstracted. The horizontal axis of FIG. 10 is the time axis, and core0, core1, core2, and core3 of FIG. 10 indicate a plurality of arithmetic units included in the numerical control device 1. The vertical axis of FIG. 10 shows the processing load amount for each calculation unit. The user who sees the transition diagram after performing the abstraction process cannot know which job is being executed in which arithmetic unit, but it is not possible to determine which arithmetic unit the processing load is concentrated on. can.

Return to the explanation in Fig. 9. When the option generation unit 14 generates the options in step S105 and the option display unit 112 generates the option drawing data, the option abstraction unit 202 acquires the option drawing data from the option display unit 112 and abstracts the options. Process (step S202). There are various possible ways to abstract the display content of the options. For example, similar to the abstraction of the transition diagram, it is conceivable to abstract or hide the job name. Further, as shown in FIG. 10, when the transition diagram shows the ratio of the processing execution time at regular time intervals for each arithmetic unit in chronological order, the option abstraction unit 202 selects options that can be changed for each arithmetic unit. In displaying, it is possible to show only information such as how to distribute the processing of which arithmetic unit to other arithmetic units without clearly indicating which job allocation state is to be changed.

FIG. 11 is a diagram showing an example of the options abstracted in step S202 of FIG. In the options shown in FIG. 11, the information for each job is hidden, and the ratio occupied by the processing load of the target job and the calculation unit to be the distribution destination of the target job are shown for each calculation unit. For example, by looking at the abstracted options shown in FIG. 11, the user has an option to distribute the job currently occupying 50% of the processing load to all the arithmetic units in the arithmetic unit indicated by "core1". I understand. Further, by looking at the abstracted options shown in FIG. 11, the user indicates a job that currently occupies a processing load of 15% in the arithmetic unit indicated by "core1" by "core2" or "core3". It can be seen that there is an option to move to a specific calculation unit.

Return to the explanation in Fig. 9. When the changed transition diagram estimation unit 15 estimates the changed transition diagram in step S108 and the changed transition diagram display unit 113 generates drawing data of the changed transition diagram, the changed transition diagram abstraction unit 203 The drawing data of the changed transition diagram is acquired from the changed transition diagram display unit 113, and the changed transition diagram is abstracted (step S203). The method of abstracting the transition diagram after the change is the same as the method of the transition diagram abstraction unit 201 abstracting the transition diagram.

FIG. 12 is a diagram showing an example of a transition diagram after the change abstracted in step S203 of FIG. The horizontal axis of FIG. 12 is the time axis, and core0, core1, core2, and core3 of FIG. 12 indicate a plurality of arithmetic units included in the numerical control device 1. The vertical axis of FIG. 12 shows the processing load amount for each calculation unit. The user who sees the transition diagram after the change after performing the abstraction process cannot know which job is executed in which arithmetic unit, but determines which arithmetic unit the processing load is concentrated on. Can be done.

In the above, the abstraction unit 20 changes the degree of abstraction of the display content in two stages depending on the user whose user level is "4" and "3" and the user whose user level is "2" and "1". The degree of abstraction of the displayed content may be changed in four stages for each user-level value. The identification information indicating the user's attribute is represented by the user level of 4 steps in the above, but may be represented by 2 steps or 3 steps, or may be represented by 5 steps or more.

As described above, according to the control device 10C according to the third embodiment, even a person who does not have expertise in parallel programming, like the control devices 10A and 10B according to the first and second embodiments, can use the control device 10C. It becomes easy to make adjustments while checking the job allocation status to the calculation unit.

Further, the control device 10C has a function of changing the degree of abstraction of the display content of the display screen generated by the display unit 11 based on the identification information indicating the user's attribute. Therefore, it is possible to abstract the transition diagram, the options, and the changed transition diagram according to the attributes of the user, and appropriately limit the disclosure range and access range of the internal information.

By using the control device 10C, the manufacturer of the numerical control device 1 and the manufacturer of the machine tool to be controlled by the numerical control device 1 select information whose access should be restricted to each user and protect the company confidentiality. Will be possible.

In addition, by using the abstraction unit 20 to restrict access to internal information, a user who does not have sufficient knowledge makes an inadvertent change to the numerical control device 1 or the machine tool, and an unintended operation is executed. It becomes possible to prevent it from being done.

Embodiment 4.
FIG. 13 is a diagram showing a configuration of the control device 10D according to the fourth embodiment. Since the control device 10D has the same functions as the control device 10C according to the third embodiment except that the control device 10D is a device separate from the numerical control device 1, detailed description of common matters will be omitted.

The control device 10D includes a display unit 11, an input reception unit 12, a transition diagram generation unit 13, a choice generation unit 14, a post-change transition diagram estimation unit 15, a change information output unit 16, and an abstraction unit 20. Has. The display unit 11 includes a transition diagram display unit 111, a choice display unit 112, and a changed transition diagram display unit 113. The abstraction unit 20 has a transition diagram abstraction unit 201, a choice abstraction unit 202, and a changed transition diagram abstraction unit 203.

The numerical control device 1 is a device separate from the control device 10D. The change information storage unit 17 and the log data storage unit 19 are storage areas such as a computer and a hard disk that the numerical control device 1 can access via a network. Further, the change information storage unit 17 may be a storage area built in the numerical control device 1. Similarly, the log data storage unit 19 may be a storage area built in the numerical control device 1.

The operation of the control device 10D is the same as the operation of the control device 10C described with reference to FIG. 9, except for the following points. The control device 10D can acquire log data from the log data storage unit 19 via the network. Further, by connecting a portable storage medium such as an SD card or a USB memory in which log data is stored to the control device 10D, the control device 10D can also acquire the log data.

When the control device 10D is connected to the change information storage unit 17 outside the control device 10D, the change information output unit 16 may output the change information to the change information storage unit 17 or the control device 10D. The change information may be output to a storage area on a device such as a computer that constitutes the above.

As described above, according to the control device 10D according to the fourth embodiment, as with the control devices 10A to 10C according to the first to third embodiments, even a person who does not have expertise in parallel programming It becomes easy to make adjustments while checking the job allocation status to the calculation unit.

Further, the control device 10D is a device separate from the numerical control device 1. Therefore, similarly to the control device 10B, there is an advantage that the numerical control device 1 is not affected by the processing load for performing the process for changing the job allocation state. For example, some machine tools equipped with the numerical control device 1 cannot easily stop the operating state because they are incorporated in the automation line. In such a case, it is desired to avoid causing the numerical control device 1 to execute a process other than the numerical control process in consideration of the influence on the product being processed. According to the control device 10D, as long as the numerical control device 1 performs the log data acquisition process, other processes can be performed by the control device 10D which is separate from the numerical control device 1, and therefore the numerical control device 1 can perform other processes. It is possible to adjust the job allocation status while suppressing the impact on performance.

Further, the control device 10D has an abstraction unit 20. Therefore, similarly to the control device 10C, it is possible to abstract the transition diagram, the options, and the changed transition diagram according to the attributes of the user, and appropriately limit the disclosure range and access range of the internal information. .. In addition, the control device 10D can protect trade secrets, and a user who does not have sufficient knowledge can inadvertently make changes to the numerical control device 1 or the machine tool to perform an unintended operation. It becomes possible to prevent.

Embodiment 5.
FIG. 14 is a diagram showing a configuration of a numerical control device 1 having the control device 10E according to the fifth embodiment. The numerical control device 1 includes a control device 10E, a change information storage unit 17, a numerical control processing execution unit 18, and a log data storage unit 19.

The control device 10E includes a display unit 11, an input reception unit 12, a transition diagram generation unit 13, a choice generation unit 14, a post-change transition diagram estimation unit 15, a change information output unit 16, and an abstraction unit 20. , With a machine learning device 30. The display unit 11 includes a transition diagram display unit 111 and a changed transition diagram display unit 113. The abstraction unit 20 has a transition diagram abstraction unit 201 and a changed transition diagram abstraction unit 203. The control device 10C has a configuration in which the options are displayed on the display screen to obtain input information indicating the options selected by the user from the generated options, whereas the control device 10E has the machine learning device 30. The machine learning device 30 is different from the control device 10C in that it has a function of selecting an option to be applied from the generated options. Hereinafter, the differences from the control device 10C will be mainly described, and detailed description of the common points will be omitted.

In addition to the same operation as in the third embodiment, the transition diagram generation unit 13 outputs the event log of each job that is the source of the generated transition diagram to the machine learning device 30.

The option generation unit 14 generates options in the same operation as in the third embodiment, and outputs the generated options to the machine learning device 30.

In addition to the same operation as in the third embodiment, the changed transition diagram estimation unit 15 estimates the changed transition diagram, and obtains the estimated data of the event log of each job that is the basis of the estimated changed transition diagram. Output to the machine learning device 30.

The machine learning device 30 learns the changed job allocation state based on the input information indicating the selected option and the job allocation state indicated by the event log of the transition diagram and the changed transition diagram. The machine learning device 30 selects an option to be applied from the options generated by the option generation unit 14, generates input information indicating the selected option, and outputs the input information to the input reception unit 12. The input receiving unit 12 outputs the input information indicating the selected option to the post-change transition diagram estimation unit 15 and the change information output unit 16, respectively. In this case, the changed transition diagram estimation unit 15 estimates the changed transition diagram showing the job allocation state according to the learning result, and the changed transition diagram display unit 113 estimates the job allocation state according to the learning result. The changed transition diagram showing is displayed. At this time, the change information output unit 16 outputs the change information for realizing the job allocation state according to the learning result.

FIG. 15 is a diagram showing a functional configuration of the machine learning device 30 shown in FIG. The machine learning device 30 has a state observation unit 31 and a learning unit 32. The learning unit 32 has a reward calculation unit 33, a function update unit 34, and an action selection unit 35.

The state observing unit 31 indicates information indicating the past job execution status in each of the plurality of arithmetic units of the numerical control device 1 and the job execution status estimated when the job allocation status is changed according to the change information. Is observed as a state variable. Specifically, the state observation unit 31 acquires the event log that is the source of the transition diagram from the transition diagram generation unit 13, and estimates the event log that is the source of the transition diagram after the change from the transition diagram estimation unit 15 after the change. Acquire data and observe the acquired event log as a state variable.

The learning unit 32 learns the optimum system configuration, specifically, the job allocation state to a plurality of arithmetic units, according to the data set created based on the state variables.

The learning unit 32 may use any learning algorithm. As an example, a case where the learning unit 32 uses reinforcement learning will be described. Reinforcement learning is that an actor in an environment observes the current state and decides the action to be taken. Here, the actor is called an agent. Agents are rewarded by the environment by choosing an action and learn how to get the most reward through a series of actions. Q-learning, TD learning, etc. are known as typical methods of reinforcement learning. For example, in the case of Q-learning, the behavioral value table, which is a general update formula of the behavioral value function Q (s, a), is represented by the following mathematical formula (1).

In Equation (1), s _t represents the environment at time t, a _t represents the behavior in time t. By the action a _t, the environment is changed to s _{t + 1.} Specifically, in the present embodiment, the environment s is the job execution state, and the action a is the selected option. rt _{+ 1} represents the reward obtained by the change in the environment, γ represents the discount rate, and α represents the learning coefficient. Note that γ is greater than 0 and takes a value of 1 or less, and α is greater than 0 and takes a value of 1 or less. If you apply the Q-learning, the optimal system configuration is the action a _t.

The update formula represented by the formula (1) increases the action value Q if the action value Q of the best action a at time t + 1 is larger than the action value Q of the action a executed at time t, and vice versa. In the case of, the action value Q is reduced. In other words, the action value function Q (s, a) is updated so that the action value Q of the action a at time t approaches the best action value at time t + 1. As a result, the best behavioral value in a certain environment is sequentially propagated to the behavioral value in the previous environment.

The reward calculation unit 33 calculates the reward based on the state variable. The reward calculation unit 33 calculates the reward r based on the processing time required to complete the job to be executed within a fixed cycle and the utilization efficiency of the plurality of calculation units at that time. For example, if the completion time of the job to be executed within a certain cycle is earlier, or if the bias of the processing load among the plurality of calculation units is reduced, the reward calculation unit 33 increases the reward r. The method for increasing the reward r is not particularly limited, but for example, it is conceivable to add "1" to the reward r. Further, when the completion time of the job to be executed within a fixed cycle is extended, or when the bias of the processing load among the plurality of calculation units increases, the reward calculation unit 33 reduces the reward r. The method for reducing the reward r is not particularly limited, but for example, it is conceivable to subtract "1" from the reward r. The processing time required to complete the job to be executed within a fixed cycle and the utilization efficiency of the plurality of arithmetic units at that time are extracted according to a known method. For example, the reward calculation unit 33 can calculate the processing time by acquiring the completion time of the job to be executed within a fixed cycle from the log data and taking the average thereof. Further, the reward calculation unit 33 takes the sum of the time when the plurality of calculation units are executing the job and the time when the job is not executed within the range of the log data acquisition time, and the plurality of calculation units. Utilization efficiency can be calculated.

The function update unit 34 updates the function for determining the optimum system configuration according to the reward calculated by the reward calculation unit 33. For example, in the case of Q-learning, action value is expressed by Equation (1) function Q (s _{t, a} _t) and is used as a function for calculating an optimum system configuration. Function update unit 34, action value after update function _{Q (s} _{t, a} t) and can be output to the action selection unit 35.

Action selection unit 35, action value output by the function updating unit 34 function _{Q (s} _{t, a} t) on the basis of, for selecting an action a. Specifically, the action selection unit 35 selects the option to be applied from the options generated by the option generation unit 14, generates input information indicating the selected option, and outputs the input information to the input reception unit 12. At this time, the method in which the action selection unit 35 selects the action a is not particularly limited. For example, the action selecting unit 35, action value function _{_{Q (s t, a t)}} ' may be used greedy method for selecting, randomly action a with probability epsilon' highest action a of select probability (1-ε) at action value function _{Q (s} _{t, a} t) may be used epsilon-greedy method for selecting a highest action a '.

When the input reception unit 12 receives the input information from the action selection unit 35, the input reception unit 12 outputs the input information to the transition diagram estimation unit 15 after the change. The post-change transition diagram estimation unit 15 estimates the changed transition diagram based on the options selected by the action selection unit 35, and sends the estimated data of the event log that is the basis of the estimated transition diagram to the state observation unit 31. It will be output. When the optimum action a is determined, the action selection unit 35 outputs the determined action a to the input reception unit 12, and the input reception unit 12 outputs the result to the change information output unit 16 as change information. Notice.

While the machine learning is repeated, the machine learning device 30 does not need to display the transition diagram of the progress using the display unit 11. After the selection of the optimum action a is confirmed, in the above, the input receiving unit 12 automatically outputs the confirmed action a, but the machine learning device 30 has the changed transition diagram estimation unit 15 and the change. The post-transition diagram display unit 113 may be used to display a transition diagram when the option indicated by the determined action a is applied. In this case, the changed transition diagram display unit 113 displays the operation unit for selectively inputting whether or not to confirm the change together with the changed transition diagram, and the user operates the operation unit to make the change. It may be confirmed. In this case, when the input receiving unit 12 detects that the user has operated the operation unit, the input receiving unit 12 outputs the change to the change information output unit 16 so as to confirm the change.

In the present embodiment, the learning algorithm used by the learning unit 32 is reinforcement learning, but the present embodiment is not limited to such an example. In addition to reinforcement learning, the learning unit 32 can also use learning algorithms such as supervised learning, unsupervised learning, or semi-supervised learning. Further, the learning unit 32 may use deep learning for learning the extraction of the feature amount itself, and may use other known methods such as a neural network, genetic programming, functional logic programming, and a support vector machine.

As described above, according to the control device 10E according to the fifth embodiment, as with the control devices 10A to 10D according to the first to fourth embodiments, even a person who does not have expertise in parallel programming It becomes easy to make adjustments while checking the job allocation status to the calculation unit.

Further, the control device 10E has an abstraction unit 20. Therefore, similarly to the

control devices

10C and 10D, it is possible to abstract the transition diagram, the options, and the changed transition diagram according to the user's attributes, and appropriately limit the disclosure range and access range of the internal information. become. In addition, the control device 10E can protect trade secrets, and a user who does not have sufficient knowledge can inadvertently make changes to the numerical control device 1 or the machine tool to perform an unintended operation. It becomes possible to prevent.

Further, the machine learning device 30 of the control device 10E has a function of selecting an option to be applied from the options generated by the option generation unit 14 based on the learning result of the job allocation state. Therefore, the user can select the option to be applied and adjust the job allocation state without trial and error.

Although the control device 10E is provided with the abstraction unit 20, the abstraction unit 20 may be omitted. Further, although the machine learning device 30 is built in the control device 10E included in the numerical control device 1, it may be a device separate from the numerical control device 1. In this case, the machine learning device 30 and the numerical control device 1 are connected via a network.

Embodiment 6.
FIG. 16 is a diagram showing a configuration of the control device 10F according to the sixth embodiment. Since the control device 10F has the same functions as the control device 10E according to the fifth embodiment except that the control device 10F is a device separate from the numerical control device 1, detailed description of common matters will be omitted.

The control device 10F has the same function as the control device 10E except that it is a device separate from the numerical control device 1. The control device 10F includes a display unit 11, an input reception unit 12, a transition diagram generation unit 13, a choice generation unit 14, a post-change transition diagram estimation unit 15, a change information output unit 16, and an abstraction unit 20. , With a machine learning device 30. The display unit 11 includes a transition diagram display unit 111 and a changed transition diagram display unit 113. The abstraction unit 20 has a transition diagram abstraction unit 201 and a changed transition diagram abstraction unit 203.

The numerical control device 1 is a device separate from the control device 10F. The change information storage unit 17 and the log data storage unit 19 are storage areas such as a computer and a hard disk that the numerical control device 1 can access via a network. Further, the change information storage unit 17 may be a storage area built in the numerical control device 1. Similarly, the log data storage unit 19 may be a storage area built in the numerical control device 1.

The operation of the control device 10F is the same as the operation of the control device 10E except for the following points. The control device 10F can acquire log data from the log data storage unit 19 via the network. Further, by connecting a portable storage medium such as an SD card or a USB memory in which log data is stored to the control device 10F, the control device 10F can also acquire the log data.

When the control device 10F is connected to the change information storage unit 17 outside the control device 10F, the change information output unit 16 may output the change information to the change information storage unit 17 or the control device 10F. The change information may be output to a storage area on a device such as a computer that constitutes the above.

As described above, according to the control device 10F according to the sixth embodiment, as with the control devices 10A to 10E according to the first to fifth embodiments, even a person who does not have expertise in parallel programming It becomes easy to make adjustments while checking the job allocation status to the calculation unit.

Further, the machine learning device 30 of the control device 10F has a function of selecting an option to be applied from the options generated by the option generation unit 14 based on the learning result of the job allocation state. Therefore, the user can select the option to be applied and adjust the job allocation state without trial and error.

Further, the control device 10F is a device separate from the numerical control device 1. Therefore, there is an advantage that the influence of the processing load for performing the process for changing the job allocation state, the processing load for the machine learning process performed by the machine learning device 30, and the like does not affect the numerical control device 1. For example, some machine tools equipped with the numerical control device 1 cannot easily stop the operating state because they are incorporated in the automation line. In such a case, it is desired to avoid causing the numerical control device 1 to execute a process other than the numerical control process in consideration of the influence on the product being processed. According to the control device 10F, as long as the numerical control device 1 performs the log data acquisition process, other processes can be performed by the control device 10F which is separate from the numerical control device 1, and therefore the numerical control device 1 can perform other processes. It is possible to adjust the job allocation status while suppressing the impact on performance.

In the fifth embodiment, the machine learning device 30 is built in the numerical control device 1, and in the sixth embodiment, the machine learning device 30 is built in the control device 10F which is separate from the numerical control device 1. However, the present embodiment is not limited to such an example. The machine learning device 30 may be a device separate from both the numerical control device 1 and the control device 10F.

Next, the hardware configuration will be explained. The control devices 10A to 10F according to the first to sixth embodiments are realized by a processing circuit. These processing circuits may be realized by dedicated hardware, or may be control circuits using a CPU.

When the above processing circuits are realized by dedicated hardware, these are realized by the processing circuit 90 shown in FIG. FIG. 17 is a diagram showing dedicated hardware for realizing the functions of the control devices 10A to 10F according to the first to sixth embodiments. The processing circuit 90 is a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination thereof.

When the above processing circuit is realized by a control circuit using a CPU, this control circuit is, for example, a control circuit 91 having the configuration shown in FIG. FIG. 18 is a diagram showing a configuration of a control circuit 91 for realizing the functions of the control devices 10A to 10F according to the first to sixth embodiments. As shown in FIG. 18, the control circuit 91 includes a processor 92 and a memory 93. The processor 92 is a CPU, and is also called a processing unit, an arithmetic unit, a microprocessor, a microcomputer, a DSP (Digital Signal Processor), or the like. The memory 93 is, for example, a non-volatile or volatile semiconductor memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable ROM), or an EEPROM (registered trademark) (Electrically EPROM). Magnetic discs, flexible discs, optical discs, compact discs, mini discs, DVDs (Digital Versatile Disks), etc.

When the above processing circuit is realized by the control circuit 91, it is realized by the processor 92 reading and executing the program corresponding to the processing of each component stored in the memory 93. The memory 93 is also used as a temporary memory in each process executed by the processor 92.

The 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.

1 Numerical controller, 10A, 10B, 10C, 10D, 10E, 10F controller, 11 display unit, 12 input reception unit, 13 transition diagram generation unit, 14 option generation unit, 15 post-change transition diagram estimation unit, 16 change information Output unit, 17 change information storage unit, 18 numerical control processing execution unit, 19 log data storage unit, 20 abstraction unit, 30 machine learning device, 31 state observation unit, 32 learning unit, 33 reward calculation unit, 34 function update unit , 35 action selection unit, 90 processing circuit, 91 control circuit, 92 processor, 93 memory, 111 transition diagram display unit, 112 option display unit, 113 changed transition diagram display unit, 201 transition diagram abstraction unit, 202 option abstraction unit. Department, 203 Transition diagram abstraction part after change.

Claims

In a control device that determines a method of allocating the job of a numerical control device that assigns jobs constituting software to each of a plurality of arithmetic units and executes them.
The job in each of the plurality of arithmetic units based on log data acquired from the numerical control device and including information that identifies a calculation unit that has executed the job in the past and a timing in which the job has been executed in the past. A transition diagram display unit that displays a transition diagram showing the execution status of
An option generation unit that generates options for changing the allocation state of the job displayed in the transition diagram based on the constraints imposed on the software.
An input receiving unit that accepts input information indicating the selected option selected from the generated options, and an input receiving unit.
A change information output unit that outputs change information for changing the allocation state of the job according to the options indicated by the input information, and a change information output unit.
A control device comprising.
The changed transition diagram estimation unit, which estimates the transition diagram when the allocation state of the job is changed according to the selected option,
The control device according to claim 1, further comprising.
The control device according to claim 2, wherein the changed transition diagram estimation unit estimates a transition diagram based on the log data.
An option display unit that displays the options generated by the option generation unit, and
An abstraction unit that changes the degree of abstraction of the display contents displayed by the transition diagram display unit and the option display unit based on the identification information indicating the user's attribute.
The control device according to any one of claims 1 to 3, further comprising.
The control device according to any one of claims 1 to 4, wherein the control device is provided in the numerical control device.
The control device according to any one of claims 1 to 4, wherein the control device is a device separate from the numerical control device.
The control according to any one of claims 1 to 6, wherein the constraint imposed on the software indicates a combination of jobs that cannot be processed in parallel among the plurality of jobs constituting the software. Device.
State variables include information indicating the execution status of the job included in the transition diagram displayed by the transition diagram display unit and the execution status of the job estimated when the allocation status of the job is changed according to the change information. The state observation unit to observe as
A learning unit that learns the allocation state of the job according to the data set created based on the state variable, and
Based on the learning result of the learning unit, an action selection unit that selects an option to be applied from the options generated by the option generation unit and outputs the input information indicating the selected option to the input reception unit.
With more
The control device according to any one of claims 1 to 7, wherein the change information output unit outputs change information for realizing a job allocation state according to a learning result.
When the execution state of the job in the past in each of the plurality of arithmetic units acquired from the control device according to any one of claims 1 to 7 and the allocation state of the job are changed according to the change information. A state observer that observes information indicating the estimated execution state of the job as a state variable,
A learning unit that learns the allocation state of the job according to the data set created based on the state variable, and
A machine learning device characterized by being equipped with.
The control device that determines the job allocation method of the numerical control device that assigns the jobs that make up the software to each of the plurality of arithmetic units and executes them.
Based on log data acquired from the numerical control device and including information that identifies the calculation unit that executed the job in the past and the timing at which the job was executed in the past, the job in each of the plurality of calculation units A step to display a transition diagram showing the execution state in chronological order,
A step of generating options for changing the allocation state of the job displayed in the transition diagram based on the constraints imposed on the software.
A step of accepting input information indicating the option selected from the generated options, and
A step of outputting change information for changing the allocation state of the job according to the option indicated by the input information, and
A control method comprising.