Production floor management system, work effect determination method, and work effect determination program

Abstract

To provide a production floor management system capable of improving determination accuracy of whether a work instruction is correct or not.SOLUTION: A production floor management system 1 is a system for managing a state on a production floor provided with a production device for producing a product, and includes a state monitoring unit 20 for monitoring the state on the production floor, and a control unit 10 for, on the basis of the priority of each of a plurality of measures extracted corresponding to the state, there are provided the measure determination unit 30 that determines a measure corresponding to the first priority instruction to be executed from among the plurality of measures, the instruction output unit 50 that outputs the first priority instruction, and the effect determination unit 60 that determines the effect of the executed first priority instruction based on the states before and after the output first priority instruction is executed, and the production resource for which the measure corresponding to the first priority instruction is being executed is locked.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to a production floor management system that manages the status of a production floor equipped with production equipment that produces products, and a work effectiveness assessment method and work effectiveness assessment program for the system. [Background technology]

[0002] A conventional technology has been disclosed in which, when a problem occurs in a production device, a solution to the problem is updated, work instructions corresponding to the solution are output, and the priority of the solution is determined depending on whether the output work instructions have solved the problem (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2018 / 142604 Summary of the Invention [Problem to be solved by the invention]

[0004] However, it is difficult to determine whether the work instructions corresponding to the method of dealing with the problem are correct.

[0005] Therefore, the present disclosure provides a production floor management system and the like that can improve the accuracy of determining whether or not a work instruction is correct. [Means for solving the problem]

[0006] A production floor management system according to one embodiment of the present disclosure is a production floor management system that manages the status of a production floor equipped with production equipment that produces products, and includes: a status monitoring unit that monitors the status of the production floor; a countermeasure decision unit that decides which countermeasure corresponding to a first priority instruction to execute from among a plurality of countermeasures extracted in response to the status based on the respective priorities of the plurality of countermeasures; an instruction output unit that outputs the first priority instruction; and an effect determination unit that determines the effect of the executed first priority instruction based on the status before and after the output first priority instruction is executed, and a production resource on which the countermeasure corresponding to the first priority instruction is being executed is locked.

[0007] These comprehensive or specific aspects may be realized by a system, an apparatus, a method, a recording medium, or a computer program, or may be realized by any combination of a system, an apparatus, a method, a recording medium, and a computer program. [Effects of the Invention]

[0008] According to the production floor management system and the like according to the present disclosure, it is possible to improve the accuracy of determining whether or not a work instruction is correct. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing a mounting line to which a production floor management system according to an embodiment is applied. [Figure 2] FIG. 2 is a configuration diagram showing an example of a production floor management system according to an embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of a monitoring target of the state monitoring unit according to the embodiment. [Figure 4] FIG. 4 is a diagram showing a schematic flow of the operation of the production floor management system according to the embodiment. [Figure 5] FIG. 5 is a flowchart illustrating an example of the operation of the state monitoring unit according to the embodiment. [Figure 6]FIG. 6 is a flowchart illustrating an example of the operation of the countermeasure determining unit according to the embodiment. [Figure 7] FIG. 7 is a table illustrating an example of a countermeasure candidate list according to the embodiment. [Figure 8] FIG. 8 is a table illustrating an example of a priority measure list according to the embodiment. [Figure 9] FIG. 9 is a flowchart illustrating an example of the operation of the countermeasure arbitration unit according to the embodiment. [Figure 10] FIG. 10 is a table illustrating an example of a resource management table according to the embodiment. [Figure 11] FIG. 11 is a flowchart illustrating an example of the operations of the instruction output unit, the effect determination unit, and the update unit according to the embodiment. [Figure 12] FIG. 12 is a table illustrating an example of an updated countermeasure candidate list according to an embodiment. [Figure 13] FIG. 13 is a flowchart showing an example of a task effectiveness assessment method according to another embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] The production floor management system disclosed herein is a production floor management system that manages the status of a production floor equipped with production equipment that produces products, and includes a status monitoring unit that monitors the status of the production floor, a countermeasure decision unit that decides which countermeasure corresponding to a first priority instruction to execute from among a plurality of countermeasures based on the respective priorities of the plurality of countermeasures extracted in response to the status, an instruction output unit that outputs the first priority instruction, and an effect determination unit that determines the effect of the executed first priority instruction based on the status before and after the output first priority instruction is executed.

[0011] This allows the effectiveness of the first priority instruction to be determined based on whether or not the condition on the production floor has changed before and after the first priority instruction is executed, and if so, how it has changed, thereby improving the accuracy of determining whether the work instruction is correct.

[0012] In addition, the instruction output unit may not output a second priority instruction determined from among the plurality of measures and having a priority level lower than that of the first priority instruction until the effect determination unit determines the effect of the executed first priority instruction.

[0013] If a second priority instruction is output and executed after a first priority instruction has been executed but before the effectiveness of the first priority instruction has been determined, the state on the production floor will be affected by the second priority instruction, making it difficult to correctly determine the effectiveness of the first priority instruction. Therefore, by preventing the second priority instruction from being output until the effectiveness of the first priority instruction has been determined, it is possible to further improve the accuracy of determining whether a work instruction is correct.

[0014] Furthermore, if the effect determination unit determines that the execution of the first priority instruction results in a predetermined or greater tendency for improvement in the state after the execution of the first priority instruction compared to the state before the execution of the first priority instruction, the instruction output unit may not need to output the second priority instruction before execution that was extracted in relation to the state corresponding to the first priority instruction.

[0015] If the execution of the first priority instruction shows a tendency for the condition on the production floor to improve, the condition on the production floor can be improved without executing the second priority instruction. Therefore, in this case, by not outputting the second priority instruction, the effort of executing the second priority instruction can be saved.

[0016] In addition, if the effect judgment unit determines that the execution of the first priority instruction does not result in a predetermined or greater tendency for improvement in the state after the execution of the first priority instruction compared to the state before the execution of the first priority instruction, the countermeasure decision unit may decide the second priority instruction to be executed based on the priority of each of the multiple countermeasures excluding the first priority instruction, and the instruction output unit may output the second priority instruction.

[0017] If the first priority instruction is executed but there is no improvement in the conditions on the production floor, it can be determined that the first priority instruction was ineffective. Therefore, in this case, an additional second priority instruction can be issued to try to improve the conditions on the production floor.

[0018] In addition, if the effectiveness judgment unit is unable to judge the effectiveness for a specified period of time, the countermeasure decision unit may decide the second priority instruction to be executed based on the priority of each of the multiple countermeasures excluding the first priority instruction, and the instruction output unit may output the second priority instruction.

[0019] After a first priority instruction is executed, it takes some time to determine its effectiveness. Therefore, if the effectiveness cannot be determined within a predetermined period of time, an additional second priority instruction is output, thereby further improving the accuracy of determining whether the work instruction is correct.

[0020] In addition, the countermeasure decision unit may update the priority for determining the priority order for the first priority instruction based on a change in the state after execution of the first priority instruction from the state before execution of the first priority instruction, which change occurs due to the execution of the first priority instruction.

[0021] This makes it possible to determine whether the first priority instruction was effective or not based on the change in the state on the production floor caused by the execution of the first priority instruction, and to update the priority associated with the first priority instruction depending on the degree of its effectiveness.

[0022] The production floor management system may further include a learning model for updating the priorities, and the countermeasure decision unit may update the priorities based on the learning model.

[0023] According to this, by using the learning model, it is possible to effectively update the priority associated with the first priority instruction.

[0024] The work effectiveness assessment method disclosed herein is a work effectiveness assessment method in a production floor management system that manages the status of a production floor equipped with production equipment that produces products, and includes monitoring the status on the production floor, determining a measure corresponding to a first priority instruction to be executed from among a plurality of measures based on the respective priorities of the plurality of measures extracted in response to the status, outputting the first priority instruction, and assessing the effectiveness of the executed first priority instruction based on the status before and after the output first priority instruction was executed.

[0025] This provides a work instruction method that can improve the accuracy of determining whether a work instruction is correct.

[0026] The work effectiveness assessment program of the present disclosure is a work effectiveness assessment program that causes a computer to execute the above-described work effectiveness assessment method.

[0027] This makes it possible to provide a work effectiveness judgment program that can improve the accuracy of judging whether or not a work instruction is correct.

[0028] The embodiments described below are all comprehensive or specific examples, and the numerical values, shapes, materials, components, arrangement and connection of the components, steps, and order of steps shown in the following embodiments are merely examples and are not intended to limit the present disclosure.

[0029] (Embodiment) Hereinafter, an embodiment will be described with reference to FIGS.

[0030] FIG. 1 is a diagram showing a mounting line 4 to which a production floor management system 1 according to an embodiment is applied.

[0031] As shown in FIG. 1, the mounting line 4 is equipped with a plurality of production devices for producing products.

[0032] The mounting line 4 has the function of mounting components (electronic components) on boards to produce products (for example, mounted boards), and has the function of supplying, delivering, and collecting the boards to be mounted.

[0033] Specifically, a board supply device M1, a board transfer device M2, a printing device M3, mounting devices M4 and M5, a reflow device M6, and a board removal device M7 are connected in series in this order on the mounting line 4. Each device from the board supply device M1 to the board removal device M7 is connected to a management device 5 via a communication network 2.

[0034] For example, printing device M3, mounting devices M4 and M5, and reflow device M6 perform component mounting work to mount components on boards transported along mounting line 4. That is, boards supplied by board supply device M1 are carried into printing device M3 via board delivery device M2. Printing device M3 performs solder printing work to screen-print solder for joining components on the carried-in boards.

[0035] The solder-printed boards are then delivered to mounting devices M4 and M5, which perform component mounting work to mount components on the solder-printed boards.

[0036] The component mounting devices M4 and M5 are equipped with a base, a board transport unit, a component supply device, and a mounting head. A board is placed on the base. The board transport unit can transport boards delivered from an upstream device to a downstream device. The component supply device can supply components to the mounting head. The component supply device is provided with multiple tape feeders for supplying components to the mounting head. The mounting head can pick up and remove components from the tape feeders, move above the board, and mount the components at the mounting position on the board. The mounting head is equipped with suction nozzles that pick up and hold components and can be raised and lowered individually. Component mounting work is performed by these component mounting devices M4 and M5.

[0037] After the components are mounted, the board is then loaded into the reflow device M6 and heated according to a predetermined heating profile. This melts and solidifies the solder printed on the heated board to join the components. The components are soldered to the board in this way, completing the mounted board with the components mounted on the board. The completed mounted board is then collected by the board collection device M7.

[0038] Next, the configuration of the production floor system 1 will be described with reference to FIG.

[0039] FIG. 2 is a configuration diagram showing an example of a production floor management system 1 according to an embodiment.

[0040] The production floor management system 1 is a system that manages the status of a production floor equipped with production equipment that produces products. The production floor includes, for example, a mounting line 4, an inventory warehouse, a preparation area, and a maintenance area. As described above, the mounting line 4 is equipped with production equipment and inspection equipment, such as mounting devices M4 and M5 and printing device M3. The inventory warehouse stores materials such as components, solder, and screen masks. In the preparation area, equipment elements such as carts, feeders, nozzles, and heads are prepared. In the maintenance area, maintenance of the equipment elements and jigs is performed. The jigs referred to here are used to adjust feeders, nozzles, heads, etc., and may also be used to adjust the equipment's head movement mechanism or conveyance mechanism. Workers perform production, preparation, maintenance, and other tasks in each area of ​​the production floor, and transport parts and equipment elements between areas. For example, the production floor management system 1 is a computer installed on the production floor. For example, the functions of the production floor management system 1 may be provided in a management device 5. The production floor management system 1 may be a computer installed in one housing, or may be divided into two or more housings and implemented by two or more computers. Furthermore, the production floor management system 1 does not have to be located on the production floor, but may be a computer such as a server installed outside the production floor. The workers are not limited to people, and may include robots, working mechanisms, and automated guided vehicles that perform the above-mentioned tasks.

[0041] The production floor management system 1 outputs instructions to workers or production equipment on the production floor according to the status of the production floor. The production floor management system 1 includes an acquisition unit 10, a status monitoring unit 20, a countermeasure decision unit 30, a countermeasure mediation unit 40, an instruction output unit 50, an effect assessment unit 60, an update unit 70, learning models 23, 24, 33, and 34, and a resource database 41. The production floor management system 1 is implemented by a computer including a processor, memory, and the like. The acquisition unit 10, the status monitoring unit 20, the countermeasure decision unit 30, the countermeasure mediation unit 40, the instruction output unit 50, the effect assessment unit 60, and the update unit 70 are implemented by the processor operating in accordance with programs stored in the memory. The status monitoring unit 20 may be provided independently as a computer or may be provided in the production equipment. The production floor management system 1 may also include multiple status monitoring units 20. The learning models 23, 24, 33, and 34, and the resource database 41 are stored in the memory. The programs, learning models 23, 24, 33 and 34, and resource database 41 may be stored in the same memory or in different memories.

[0042] The acquisition unit 10 acquires information for monitoring the status of the production floor. For example, the acquisition unit 10 acquires information indicating the production status of the production floor. Specifically, the acquisition unit 10 acquires the results of the production process of the production equipment (specifically, productivity, quality, presence or absence of defects, etc.) as information indicating the production status of the production floor. The results of the production process may be a sensing history record obtained by a sensor or data entered by a person. Furthermore, for example, the acquisition unit 10 acquires information indicating the status of production resources managed on the production floor and used for production. Examples of production resources include production equipment, facility elements, workers, materials, jigs, etc. For example, the information indicating the status of production resources may be sensing data obtained by a camera or sensor, or data entered by a person. Furthermore, for example, the acquisition unit 10 acquires event information indicating changes on the production floor. Specifically, the acquisition unit 10 acquires information indicating that a production equipment has stopped, that a feeder, nozzle, part, or board attached to the production equipment has been replaced, that a worker has been replaced, or that the operation data of the production equipment has been changed.

[0043] The status monitoring unit 20 monitors the status on the production floor via the information acquired by the acquisition unit 10. For example, the status monitoring unit 20 detects a predetermined status (e.g., a first status or a second status described below) among the statuses on the production floor based on a first condition for detecting the predetermined status. For example, the first condition is a learning model associated with a detection threshold corresponding to the predetermined status. Note that the first condition may be a set detection threshold instead of a learning model.

[0044] The state monitoring unit 20 has a first state monitoring unit 21 and a second state monitoring unit 22. The first state monitoring unit 21 and the second state monitoring unit 22 each perform the operations of the state monitoring unit 20 described above.

[0045] The first status monitoring unit 21 monitors a first status on the production floor. For example, the first status is the production status of a production device, and the first status monitoring unit 21 monitors the results of the production process as the production status of the production device. For example, the first status monitoring unit 21 detects a first predetermined status based on a learning model 23. The learning model 23 is a learning model for detecting a first predetermined status that occurs on the production floor in response to the production status of the production device. The learning model 23 is also a learning model (i.e., a first condition) associated with a detection threshold corresponding to the production status of the production device. For example, the first status monitoring unit 21 detects a first predetermined status corresponding to a production index related to at least one of information on production errors that occurred in the production device, information on the production volume of products produced by the production device, and information on the quality of products produced by the production device within a predetermined period.

[0046] The second status monitoring unit 22 monitors a second status on the production floor that is different from the first status. For example, the second status is the status of a production resource, and the second status monitoring unit 22 monitors the status of the production resource. For example, the second status monitoring unit 22 detects a second predetermined status based on a learning model 24. The learning model 24 is a learning model for detecting a second predetermined status that occurs on the production floor in response to the status of the production resource. The learning model 24 is also a learning model (i.e., a first condition) associated with a detection threshold corresponding to the status of the production resource. For example, the second status monitoring unit 22 detects a second predetermined status that corresponds to an operation index related to the operating status of a production device included in the production resource. For example, the second status monitoring unit 22 detects a second predetermined status that corresponds to a work index related to work performed by a worker included in the production resource.

[0047] An example of an object to be monitored by the state monitoring unit 20 will now be described with reference to FIG.

[0048] Fig. 3 is a diagram showing an example of an object to be monitored by the state monitoring unit 20 according to the embodiment. In Fig. 3, the production device is a mounting device, and the production process is a mounting process.

[0049] 3, the state monitoring unit 20 (specifically, the first state monitoring unit 21) monitors, as a production state, the results of the mounting process, which is made up of processes such as pickup, recognition, and mounting. For example, the first state monitoring unit 21 detects, within a predetermined period of time, a first predetermined state (specifically, the presence or absence of mounting errors (defects), the mounting amount (productivity), and the quality of mounting, etc.) corresponding to a production index related to at least one of information about mounting errors that occurred in the mounting device, information about the mounting amount of components mounted by the mounting device, and information about the quality of components mounted by the mounting device.

[0050] Furthermore, the status monitoring unit 20 (specifically, the second status monitoring unit 22) monitors the status of elements (production resources) involved in the mounting process, such as boards, components, workers, heads, nozzles, and feeders, as the status of production resources. For example, the second status monitoring unit 22 detects a second predetermined status corresponding to an operation indicator related to the operating status of a mounting device included in the production resource (e.g., deterioration of the mounting device, nozzles, and feeders). Furthermore, for example, the second status monitoring unit 22 detects a second predetermined status corresponding to a work indicator related to work performed on a mounting device by a worker included in the production resource (e.g., a worker's work error). In addition to the work indicator, the second predetermined status may also be detected as a measurement indicator related to the difference between numerical values ​​(length, width, thickness, coordinate positions of various marks, viscosity) in the design data of the board, solder, or component and numerical values ​​actually measured by a camera or sensor, or a time indicator related to the expiration date and time of the solder or component and the date and time of actual measurement.

[0051] Returning to the explanation of FIG. 2 , the countermeasure determination unit 30 determines a countermeasure to be executed from among a plurality of countermeasures extracted in response to a state on the production floor monitored by the state monitoring unit 20. The countermeasure to be executed from among the plurality of countermeasures corresponds to a first priority instruction, a second priority instruction, etc., which will be described later. For example, the countermeasure determination unit 30 determines a countermeasure to be executed based on a second condition for determining a countermeasure corresponding to a predetermined state (e.g., a first or second countermeasure, which will be described later). For example, the second condition includes a priority set for each of the plurality of extracted countermeasures, and is a learning model associated with the plurality of countermeasures and their priorities corresponding to the predetermined state. For example, the countermeasure determination unit 30 determines a first priority instruction to be executed from among the plurality of countermeasures based on the priority of each of the plurality of countermeasures extracted in response to a state on the production floor monitored by the state monitoring unit 20. In other words, the countermeasure determination unit 30 determines a countermeasure to be executed from among the plurality of countermeasures (i.e., a first priority instruction) based on the priority of each of the plurality of countermeasures extracted in response to the predetermined state. For example, the countermeasure determination unit 30 analyzes the operation information of the production equipment acquired on the production floor, the information of the workers working on the production floor, and the information of the materials used in the product to determine a countermeasure corresponding to a predetermined state. The analysis may involve cases where a countermeasure can be determined based solely on the trend of the predetermined state, or cases where a countermeasure cannot be determined based solely on the trend of the predetermined state. When a countermeasure cannot be determined based solely on the trend of the predetermined state, the countermeasure determination unit 30 may determine a countermeasure corresponding to the predetermined state by analyzing the operation information of the production equipment acquired on the production floor for each production resource based on event information, the information of the workers working on the production floor, and the information of the materials used in the product, or by executing a predetermined countermeasure and further analyzing the trends before and after the execution. The analysis may also be performed using an analysis unit independent of the countermeasure determination unit 30. For example, the countermeasure determination unit 30 updates the priority for determining the priority of the first priority instruction (countermeasure) based on the change in the state of the production floor after the execution of the first priority instruction, which occurs due to the execution of the first priority instruction, compared to the state of the production floor before the execution of the first priority instruction. For example, the countermeasure determination unit 30 updates the priority based on a learning model for updating the priority.The second condition may not be a learning model, but may be a data table including priorities set for a plurality of measures.

[0052] The countermeasure decision section 30 has a first countermeasure decision section 31 and a second countermeasure decision section 32. The first countermeasure decision section 31 and the second countermeasure decision section 32 each perform the operations of the countermeasure decision section 30 described above.

[0053] The first measure determination unit 31 determines a first measure corresponding to the first state monitored by the first state monitoring unit 21. For example, the first measure determination unit 31 determines a first measure (i.e., a first priority instruction) to be executed from among multiple measures based on the priorities of each of the multiple measures extracted corresponding to the first state. For example, the first measure determination unit 31 determines a first measure including a measure to improve the production index. Specifically, the first measure determination unit 31 determines a first measure to improve MTTR (Mean Time To Recovery). MTTR is an index indicating the maintainability of a system or equipment, and a shorter MTTR indicates higher maintainability. For example, the first measure determination unit 31 determines the first measure based on a learning model 33. The learning model 33 is a learning model for determining a first measure corresponding to the first state, and specifically, a learning model for updating priorities. The learning model 33 is also a learning model (i.e., a second condition) associated with multiple measures and priorities corresponding to a predetermined state.

[0054] The second measure determination unit 32 determines a second measure corresponding to the second state monitored by the second state monitoring unit 22. For example, the second measure determination unit 32 determines a second measure (i.e., a first priority instruction) to be executed from among multiple measures based on the priorities of the multiple measures extracted corresponding to the second state. For example, the second measure determination unit 32 determines a second measure including a measure (maintenance or replacement) for a production device or facility element corresponding to the operation index, or a second measure including the availability or work training of a worker corresponding to the work index. Specifically, the second measure determination unit 32 determines a second measure to improve the mean time between failures (MTBF). The MTBF is an index indicating the reliability of a system or equipment, and a longer MTBF indicates higher reliability. For example, the second measure determination unit 32 determines the second measure based on a learning model 34. The learning model 34 is a learning model for determining a second measure corresponding to the second state, and specifically, a learning model for updating priorities. The learning model 34 is also a learning model (i.e., a second condition) associated with a plurality of countermeasures and priorities corresponding to a predetermined state. The second countermeasure determined here may be considered to be completed when the second countermeasure is notified to a maintenance plan creation device or a worker management device provided separately from the production floor management system 1, or may be completed when the execution result of the second countermeasure is received.

[0055] The countermeasure arbitration unit 40 arbitrates between the first countermeasure and the second countermeasure. Here, the reason why arbitration between the first countermeasure and the second countermeasure is necessary will be explained in detail with reference to FIG.

[0056] For example, as shown in Figure 3, the results of the pickup process are related to the board, components, workers, heads, nozzles, and feeders; the results of the recognition process are related to the components, heads, and nozzles; and the results of the placement process are related to the board, components, and nozzles. For example, the first countermeasure includes countermeasures for the board, components, workers, heads, nozzles, or feeders corresponding to the results of the production process. Meanwhile, the second countermeasure also includes countermeasures for the board, components, workers, heads, nozzles, or feeders corresponding to the status of the production resources. In other words, the production resources targeted by the first countermeasure may overlap with the production resources targeted by the second countermeasure. When the production resources targeted by the first countermeasure overlap with the production resources targeted by the second countermeasure, it is difficult to simultaneously execute both the first and second countermeasures, and therefore, reconciliation between the first and second countermeasures is necessary.

[0057] For example, the countermeasure arbitration unit 40 arbitrates between the first countermeasure and the second countermeasure based on the problem level set for the first state corresponding to the first countermeasure and the problem level set for the second state corresponding to the second countermeasure. Furthermore, for example, the countermeasure arbitration unit 40 arbitrates between the first countermeasure and the second countermeasure based on the availability of production resources required for the first countermeasure or the second countermeasure. The availability of production resources is managed in the resource database 41.

[0058] The instruction output unit 50 outputs a first priority instruction. Specifically, the instruction output unit 50 outputs the first or second measure, which is a first priority instruction, in accordance with the mediation by the measure mediation unit 40. For example, the instruction output unit 50 does not output a second priority instruction, which is determined from among multiple measures and has a priority level lower than the first priority instruction, until the effect determination unit 60, which will be described later, determines the effectiveness of the executed first priority instruction. Furthermore, for example, if the effect determination unit 60 determines that the execution of the first priority instruction has resulted in a predetermined or greater improvement in the state of the production floor after the execution of the first priority instruction compared to the state of the production floor before the execution of the first priority instruction, the instruction output unit 50 does not output the pre-execution second priority instruction extracted in relation to the state of the production floor corresponding to the first priority instruction. Furthermore, for example, if the effectiveness assessment unit 60 determines that the execution of the first priority instruction does not result in a predetermined improvement in the state of the production floor after the execution of the first priority instruction compared to the state of the production floor before the execution of the first priority instruction, the countermeasure decision unit 30 determines a second priority instruction to be executed based on the priorities of the multiple countermeasures excluding the first priority instruction, and the instruction output unit 50 outputs the second priority instruction. Furthermore, for example, if the effectiveness assessment unit 60 cannot determine the effectiveness for a predetermined period of time, the countermeasure decision unit 30 determines a second priority instruction to be executed based on the priorities of the multiple countermeasures excluding the first priority instruction, and the instruction output unit 50 outputs the second priority instruction. The instruction output unit 50 may output instructions to a control unit of a production device or a mobile device carried by a worker, or may output instructions to a production device or a worker via a production management device that manages the production device or a worker management device that manages the worker.

[0059] The effect determination unit 60 determines the effect of the executed measure (instruction) based on the state of the production floor before and after the determined measure (in other words, the output first priority instruction) was executed. Specifically, the effect determination unit 60 determines the effect of the executed first measure or second measure based on at least one of the first state and the second state before and after the first measure or second measure corresponding to the output instruction was executed.

[0060] The update unit 70 updates the first and second conditions, that is, the learning models 23, 24, 33, and 34, based on the determined effects.

[0061] The status monitoring unit 20, the countermeasure determination unit 30, the countermeasure arbitration unit 40, the instruction output unit 50, the effect determination unit 60 and the update unit 70 will be described in detail later.

[0062] The monitoring of the first state by the first state monitoring unit 21 and the determination of the first measure by the first measure decision unit 31, and the monitoring of the second state by the second state monitoring unit 22 and the determination of the second measure by the second measure decision unit 32 are carried out in parallel. This will be described with reference to FIG. 4.

[0063] FIG. 4 is a diagram showing a schematic flow of the operation of the production floor management system 1 according to the embodiment.

[0064] The production floor management system 1 performs problem detection by the status monitoring unit 20, decision on a countermeasure policy by the countermeasure decision unit 30, arbitration by the countermeasure arbitration unit 40, and execution of countermeasures by the instruction output unit 50. These can be applied to a so-called OODA loop, with problem detection corresponding to "Observe," decision on a countermeasure policy corresponding to "Orient," arbitration corresponding to "Decide," and execution of countermeasures corresponding to "Action."

[0065] As described above, the monitoring of the first state by the first state monitoring unit 21 and the determination of the first measure by the first measure decision unit 31 are intended to improve the MTTR, and in Fig. 4, the cycle of problem detection by the first state monitoring unit 21, determination of a measure policy by the first measure decision unit 31, arbitration by the measure arbitration unit 40, and execution of the measure by the instruction output unit 50 is referred to as the MTTR cycle. As described above, the monitoring of the second state by the second state monitoring unit 22 and determination of the second measure by the second measure decision unit 32 are intended to improve the MTBF, and in Fig. 4, the cycle of problem detection by the second state monitoring unit 22, determination of a measure policy by the second measure decision unit 32, arbitration by the measure arbitration unit 40, and execution of the measure by the instruction output unit 50 is referred to as the MTBF cycle.

[0066] In this way, the monitoring of the first state by the first state monitoring unit 21 and the determination of the first measure by the first measure decision unit 31, and the monitoring of the second state by the second state monitoring unit 22 and the determination of the second measure by the second measure decision unit 32 are performed in parallel. For example, process assurance can be achieved by an OODA loop from both the MTBF and MTTR perspectives.

[0067] In addition, each process in the OODA loop (problem detection, countermeasure policy decision, mediation, and countermeasure execution) remains independent and can be executed in parallel, minimizing the wait time between processes and achieving real-time control. As will be explained in more detail later, countermeasures can be executed while changing priorities in response to the diverse and changing conditions on the production floor over time.

[0068] Although the first state is the production state of a production device and the second state is the state of a production resource, the present invention is not limited to this. For example, the first state may be the production state of a production device, and the second state may be a production state of a production device different from the first state. Furthermore, the first state may be the state of a production resource, and the second state may be a state of a production resource different from the first state. For example, FIG. 4 illustrates an example in which an MTBF cycle and an MTTR cycle are performed in parallel. However, multiple MTBF cycles may be performed in parallel, or multiple MTTR cycles may be performed in parallel. When an MTBF cycle and an MTTR cycle are performed in parallel and the first and second countermeasures are arbitrated, the countermeasure arbitration unit 40 may prioritize the first countermeasure over the second countermeasure. In particular, prioritizing the first countermeasure when there is no difference in the problem level described below can maintain the operation of the production device. Here, "no difference in problem level" includes both the same problem level and the difference in problem level within a predetermined range.

[0069] Next, the status monitoring unit 20, the countermeasure determination unit 30, the countermeasure arbitration unit 40, the instruction output unit 50, the effect determination unit 60, and the update unit 70 will be described in detail with reference to FIGS.

[0070] First, the state monitoring unit 20 will be described in detail with reference to FIG.

[0071] Fig. 5 is a flowchart showing an example of the operation of the state monitoring unit 20 according to the embodiment. Fig. 5 shows the process of problem observation in the OODA loop.

[0072] First, the status monitoring unit 20 acquires monitoring data (step S11). Specifically, the first status monitoring unit 21 acquires monitoring data related to the production status of the production equipment, and the second status monitoring unit 22 acquires monitoring data related to the status of the production resources.

[0073] Next, the state monitoring unit 20 reads the learning model (step S12). Specifically, the first state monitoring unit 21 reads the learning model 23, and the second state monitoring unit 22 reads the learning model 24.

[0074] The learning model 23 is a learning model for detecting a first predetermined state that occurs on the production floor in response to the production state of the production equipment, and is associated with a detection threshold corresponding to the production state of the production equipment. For example, the learning model 23 is trained to output a first predetermined state (e.g., productivity, quality, or defects) corresponding to a production index related to at least one of information on a production error that occurred in the production equipment, information on the production volume of the product produced by the production equipment, and information on the quality of the product produced by the production equipment, as indicated by the acquired monitoring data. Here, a learning method (update method) for the learning model 23 will be described using a specific example.

[0075] For example, suppose that a decline in productivity is detected based on a detection threshold corresponding to productivity associated with the learning model 23, and measures to increase productivity are output. As a result, productivity increases and quality decreases, i.e., productivity is effective but quality deteriorates. For example, if the learning policy is set to emphasize quality, learning is performed based on the above effect to relax the detection threshold corresponding to productivity (making it more difficult to detect declines in productivity). As a result, a detection threshold that strikes a balance between productivity and quality is learned.

[0076] The learning model 24 is a learning model for detecting a second predetermined state that occurs on the production floor in response to the state of the production resources, and is associated with a detection threshold corresponding to the state of the production resources. For example, the learning model 24 is trained to output a second predetermined state (e.g., deterioration of production equipment or facility elements, or worker errors) corresponding to an operation index related to the operating state of a production device included in the production resources or an operation index related to an operation performed by a worker included in the production resources, as indicated by the acquired monitoring data, when the learning model 24 is input. Here, a learning method (update method) for the learning model 24 will be described using a specific example.

[0077] For example, suppose a decrease in the nozzle flow rate is detected based on a detection threshold corresponding to the nozzle flow rate associated with the learning model 24, and a countermeasure to perform nozzle maintenance within one week is output. For example, suppose the pickup error rate worsens before the countermeasure is output and maintenance is performed (before one week has passed), and the output countermeasure is not effective. In this case, since it is possible that the decrease in the nozzle flow rate was detected too late, learning is performed based on the above effect to tighten the detection threshold corresponding to the nozzle flow rate (i.e., to make it easier to detect the decrease in the nozzle flow rate sooner). This allows learning of a detection threshold that allows maintenance to be performed at the optimal time. Note that the detection threshold corresponding to the nozzle flow rate is just one example, and the above learning can also be applied even if detection thresholds are set for other factors such as a deviation in the feeder tape stop position, a deviation in the pickup position of a component picked up by the nozzle, or a deviation in the transport position of a board.

[0078] Next, the state monitoring unit 20 determines whether a problem has been detected in the first predetermined state or the second predetermined state (step S13). For example, the first state monitoring unit 21 determines whether a decrease in productivity, a decrease in quality, or an increase in defects has been detected. For example, the second state monitoring unit 22 determines whether a deterioration in a production device, a deterioration in an equipment element, or an error in an operator's work has been detected.

[0079] If no problem is detected (No in step S13), the process from step S11 is repeated until a problem is detected.

[0080] If a problem is detected (Yes in step S13), a countermeasure policy for the detected problem is determined.

[0081] Next, the details of the countermeasure determining unit 30 will be explained with reference to FIG.

[0082] Fig. 6 is a flowchart showing an example of the operation of the countermeasure decision unit 30 according to the embodiment. Fig. 6 shows the process of deciding (orienting) a countermeasure policy in an OODA loop.

[0083] The countermeasure decision unit 30 analyzes production resources related to the problem detected by the status monitoring unit 20 (for example, production resources that may be the cause) (step S21). For example, if the first status monitoring unit 21 detects a problem of reduced productivity in the mounting process of a mounting device, the countermeasure decision unit 30 analyzes that the production resources that may be the cause of the problem are the board, the component, the worker, the head, the nozzle, and the feeder (see FIG. 3). Also, for example, if the second status monitoring unit 22 detects a problem of nozzle deterioration, the countermeasure decision unit 30 analyzes that the production resources that may be the cause of the problem are the nozzle.

[0084] Next, the countermeasure decision unit 30 reads the learning model (step S22). Specifically, the first countermeasure decision unit 31 reads the learning model 33, and the second countermeasure decision unit 32 reads the learning model .

[0085] The learning model 33 is a learning model for determining a first measure corresponding to the production status of the production equipment, and specifically, a learning model for updating priorities for determining priorities for the first measures. For example, the learning model 33 is trained so that when a detected problem is input, the learning model 33 outputs a measure for the detected problem as a candidate. When multiple candidates are output for the detected problem, multiple measures are extracted corresponding to the multiple candidates. The learning method of the learning model 33 will be described later.

[0086] The learning model 34 is a learning model for determining a second measure corresponding to the state of the production resources, and more specifically, a learning model for updating priorities for determining the priority order for the second measures. For example, the learning model 34 is trained so that when a detected problem is input, the learning model 34 outputs a measure for the detected problem as a candidate. When multiple candidates are output for the detected problem, multiple measures are extracted corresponding to the multiple candidates. The learning method of the learning model 34 will be described later.

[0087] Next, the countermeasure decision unit 30 analyzes the priorities to determine the priority order of each of the multiple countermeasures (step S23). For example, when outputting countermeasure candidates for the detected problem, the learning models 33 and 34 output the countermeasures in association with the priorities of the countermeasures. This allows the countermeasure decision unit 30 to grasp the priority of each countermeasure.

[0088] Next, the countermeasure determining section 30 creates a countermeasure candidate list (step S24). The countermeasure candidate list will be explained with reference to FIG.

[0089] FIG. 7 is a table illustrating an example of a countermeasure candidate list according to the embodiment.

[0090] For example, suppose that a problem of a worsening component pickup error rate by the nozzle is detected as a problem of the first predetermined state (e.g., productivity, quality, or defects). In this case, the learning model 33 outputs candidate countermeasures such as pickup position teaching, feeder replacement, and nozzle replacement, and also outputs a priority probability as the priority of each candidate countermeasure. This allows the countermeasure decision unit 30 to create a candidate countermeasure list as shown in FIG. 7. In the candidate countermeasure list shown in FIG. 7, the candidate countermeasure of pickup position teaching has a priority probability of 60%, making it the highest priority among the candidate countermeasures for the problem of a worsening pickup error rate. Note that if there are candidate countermeasures with the same priority probability, the candidate countermeasure may be determined based on past performance (the number of times the countermeasure was successful, the transition of the priority probability, etc.).

[0091] Returning to the explanation of FIG. 6, next, the countermeasure determination unit 30 registers the countermeasure candidate with the highest priority in the created countermeasure candidate list in the priority countermeasure list as a countermeasure for the detected problem (step S25). For example, when the countermeasure candidate list shown in FIG. 7 is created, a countermeasure called "pickup position teach" is registered in the priority countermeasure list for the problem of an increase in the pickup error rate. For example, the multiple countermeasures extracted corresponding to the state of the production floor when the problem of an increase in the pickup error rate is detected are "pickup position teach," "feeder replacement," and "nozzle replacement." The countermeasure determination unit 30 registering the countermeasure called "pickup position teach" in the priority countermeasure list means that it determines "pickup position teach" as the first priority instruction to be executed from among the multiple countermeasures based on the priorities (priorities) of the multiple countermeasures.

[0092] The monitoring data is acquired repeatedly at predetermined time intervals, and various problems may be detected. For example, another problem may be detected before a countermeasure for one problem is completed. For example, multiple problems may be detected regarding a first predetermined state (e.g., productivity, quality, or defects), and multiple problems may be detected regarding a second predetermined state (e.g., deterioration of production equipment or facility elements, or operator errors). In this way, each time a problem is detected, a list of candidate countermeasures for that problem is created, and the countermeasure with the highest priority for each candidate countermeasure list is added to a priority countermeasure list. An example of a priority countermeasure list is shown in FIG. 8.

[0093] FIG. 8 is a table illustrating an example of a priority measure list according to the embodiment.

[0094] As shown in FIG. 8, for the problem of the worsening pickup error rate, which is a problem related to the first predetermined state, the countermeasure "pickup position teaching" is registered in the priority countermeasure list. Also, for the problem of the poor feeder sliding, which is a problem related to the second predetermined state, the countermeasure "cleaning" is registered in the priority countermeasure list. Also, for the problem of the wear of the conveyor belt, which is a problem related to the second predetermined state, the countermeasure "replacement" is registered in the priority countermeasure list. Furthermore, a problem level is pre-assigned to each of the problems related to the first and second predetermined states as an indicator of the severity of the problem. For example, the problem of the worsening pickup error rate can be considered to be a problem of the first state (production state of the production equipment) when the problem is detected, so the problem level assigned to the problem of the worsening pickup error rate can be considered to be the problem level assigned to the first state when the problem is detected. Also, for example, the problem of the poor feeder sliding can be considered to be a problem of the second state (state of the production resource) when the problem is detected, so the problem level assigned to the problem of the poor feeder sliding can be considered to be the problem level assigned to the second state when the problem is detected.

[0095] Next, the countermeasure arbitration unit 40 will be described in detail with reference to FIG.

[0096] Fig. 9 is a flowchart showing an example of the operation of the countermeasure arbitration unit 40 according to the embodiment. Fig. 9 shows arbitration (Decide) processing in the OODA loop.

[0097] First, the measure arbitration unit 40 reads the priority measure list (step S31) and selects a measure with a high priority (i.e., a high problem level) (step S32). For example, if the read priority measure list is the list shown in Fig. 8, the measure arbitration unit 40 selects pickup position teaching as a measure with a high priority.

[0098] Next, the countermeasure mediation unit 40 reads the resource data (resource management table) from the resource database 41 (step S33). The resource management table will be described with reference to FIG.

[0099] FIG. 10 is a table illustrating an example of a resource management table according to the embodiment.

[0100] For example, the resource management table manages the presence or absence of each production resource, specifically, whether or not some countermeasure is currently being taken for each production resource, or whether or not some countermeasure is currently being taken for each production resource. In FIG. 10, the presence or absence of a production resource is indicated by the lock status being on or off. The resource management table shown in FIG. 10 manages the presence or absence of production resources, such as heads, nozzles, feeders, and workers A and B. The heads and feeders are currently being locked because some countermeasure is being taken. The nozzles are currently not being locked because no countermeasure is being taken. Workers A and B are currently not being locked because no countermeasure is being taken. The term "lock" here may refer to either real space or virtual space, or both. For example, prohibiting a locked feeder from being removed from a production device until the lock is turned off refers to locking in real space. Furthermore, prohibiting a locked feeder from being used when creating or updating a production plan refers to locking in virtual space.

[0101] Returning to the explanation in FIG. 9, next, the countermeasure arbitration unit 40 determines whether or not the production resource is locked for the selected countermeasure (step S34). For example, it is assumed that the countermeasure arbitration unit 40 selects pickup position teach. Also, it is assumed that pickup position teach is a countermeasure performed by worker A. In this case, the countermeasure arbitration unit 40 checks the lock status of worker A in the read resource management table.

[0102] If the production resource for the selected measure is locked (Yes in step S34), the measure arbitration unit 40 selects the measure with the next highest priority (step S35) and repeats the process from step S33.

[0103] If the production resources for the selected measures are not locked (No in step S34), the measures arbitration unit 40 locks the production resources for the selected measures (step S36).

[0104] Then, it is determined whether or not the production resources for all measures included in the priority measure list are locked (step S37). If the production resources for all measures are not locked (No in step S37), the process is repeated from step S32, excluding the measure selected this time. If the production resources for all measures are locked (Yes in step S37), the measures with the highest priority selected from among the measures in the priority measure list for which production resources are not locked are executed.

[0105] Next, the instruction output unit 50, the effect determination unit 60, and the update unit 70 will be described in detail with reference to FIG.

[0106] 11 is a flowchart showing an example of the operations of the instruction output unit 50, the effect determination unit 60, and the update unit 70 according to the embodiment. Fig. 11 shows countermeasure execution (Action) in the OODA loop and processing after the countermeasure is executed. In the following, a case where the countermeasure selected by the countermeasure arbitration unit 40 for the problem of a worsening pickup error rate is pickup position teaching and the locked production resource is worker A is referred to as specific example 1, and a case where the countermeasure selected by the countermeasure arbitration unit 40 for the problem of poor feeder sliding is cleaning and the locked production resources are the feeder and worker B is referred to as specific example 2.

[0107] First, the instruction output unit 50 executes a countermeasure for the production resource locked by the countermeasure arbitration unit 40 (step S41). For example, in the case of specific example 1, the instruction output unit 50 outputs a first countermeasure (e.g., a first priority instruction) to have worker A perform pickup position teaching. For example, in the case of specific example 2, the instruction output unit 50 outputs a second countermeasure (e.g., a first priority instruction) to have worker B perform feeder cleaning. In this way, an instruction according to the countermeasure is output and executed. Note that the execution of the instruction may be performed manually by a worker or the like, or may be performed automatically by a production device or the like.

[0108] Next, the effect determination unit 60 acquires monitoring data (step S42). Specifically, the effect determination unit 60 acquires monitoring data regarding the production status of the production equipment or the status of the production resources. The reason the effect determination unit 60 acquires monitoring data is to confirm changes in the status on the production floor due to the execution of instructions corresponding to the countermeasures, i.e., to determine the effectiveness of the instructions corresponding to the executed countermeasures. For example, in the case of Specific Example 1, the effect determination unit 60 acquires monitoring data regarding the results of the mounting process related to pickup. That is, the effect determination unit 60 uses error information related to the nozzles being monitored as monitoring data and monitors the trends. For example, in the case of Specific Example 2, the effect determination unit 60 acquires monitoring data regarding the status of the feeders. That is, the effect determination unit 60 uses error information related to the feeders being monitored as monitoring data and monitors the trends. For example, the effect determination unit 60 detects the first or second predetermined status using the learning model 23 or 24, similar to the status monitoring unit 20.

[0109] Next, the effect determining unit 60 determines whether a problem has been detected in the first predetermined state or the second predetermined state (step S43). If a problem has been detected, it can be determined that the instruction corresponding to the executed measure has not been effective or that the effect of the instruction corresponding to the executed measure has not yet been seen, and if no problem has been detected, it can be determined that the instruction corresponding to the executed measure has been effective.

[0110] If no problem is detected (No in step S43), the update unit 70 updates the learning model 33 or 34 based on the determined effect (step S44). For example, in the case of specific example 1, if a problem is no longer detected, the update unit 70 determines that the pickup position teach was effective in solving the problem, and updates the learning model 33 so that the priority of the pickup position teach is increased. For example, in the case of specific example 2, if a problem is no longer detected, the update unit 70 determines that cleaning was effective in solving the problem, and updates the learning model 34 so that the priority of cleaning is increased.

[0111] Next, since the current instruction has been completed, the effect determination unit 60 unlocks the production resources that were locked when executing the current instruction (step S45). For example, in the specific example 1, the locked worker A is unlocked. For example, in the specific example 2, the locked worker B and the feeder are unlocked.

[0112] Next, the effect determination unit 60 deletes the measure executed in response to the current instruction from the priority measure list (step S46). For example, in the specific example 1, the pickup position teach is deleted from the priority measure list. For example, in the specific example 2, the cleaning is deleted from the priority measure list.

[0113] The effectiveness determination unit 60 then deletes the countermeasure candidate list for the problem that is no longer detected as a result of the current instruction (step S47). For example, in the specific example 1, the problem of the worsening pickup error rate is no longer detected, and therefore, countermeasures for the problem are no longer necessary. Therefore, the countermeasure candidate list shown in FIG. 7 is deleted. Deleting the countermeasure candidate list means that, if the effectiveness determination unit 60 determines that the pickup error rate after the pickup position teach instruction has improved by a predetermined level or more compared to the state (pickup error rate) before the pickup position teach instruction due to the execution of the first priority instruction (pickup position teach instruction), the instruction output unit 50 does not output the second priority instruction (feeder replacement instruction or nozzle replacement instruction) extracted in relation to the pickup error rate corresponding to the pickup position teach instruction. The effectiveness determination unit 60 may also determine whether problems presented in the priority countermeasure list continue to exist other than the problem for which the countermeasure was executed. The effectiveness determination unit 60 may also delete the priority countermeasure list for a problem that is no longer detected other than the problem for which the countermeasure was executed. Depending on the detected problems, they may be related to each other, and efficient countermeasures can be implemented for such problems.

[0114] On the other hand, if a problem is detected (Yes in step S43), the effect determining unit 60 determines whether a timeout has occurred (step S48). In other words, the effect determining unit 60 determines whether the effect has not been determined for a predetermined time. Since it may take some time for the effect to appear after an instruction is executed, the processing in step S48 is performed. The predetermined period is set, for example, as the time required to reap the effect for each instruction. Furthermore, for instructions that are not executed immediately, such as measures added to a production plan or maintenance plan, the production resources may be unlocked when a plan to execute the instruction is created, and the effect may be determined after the plan is executed.

[0115] If a timeout has not occurred (No in step S48), the processes in steps S42, S43 and S48 are repeated until a problem is no longer detected or a timeout occurs.

[0116] If a timeout occurs (Yes in step S48), the update unit 70 updates the learning model 33 or 34 based on the determined effect (step S49). For example, in specific example 1, if a timeout occurs while a problem is still detected, the update unit 70 determines that the pickup position teach was not effective for the problem and updates the learning model 33 so that the priority of the pickup position teach is lowered. For example, in specific example 2, if a timeout occurs while a problem is still detected, the update unit 70 determines that cleaning was not effective for the problem and updates the learning model 34 so that the priority of cleaning is lowered. Furthermore, if a problem is detected but there is an improvement trend in the monitoring data (there is an improvement trend below a predetermined level), the update unit 70 updates the learning model 34 so that the degree of priority reduction is reduced.

[0117] Next, since the current instruction has been completed, the effect determination unit 60 unlocks the production resources that were locked when executing the current instruction (step S50). For example, in the specific example 1, the locked worker A is unlocked. For example, in the specific example 2, the locked worker B and the feeder are unlocked.

[0118] Next, the effect determination unit 60 deletes the measure executed in response to the current instruction from the priority measure list (step S51). For example, in the specific example 1, the pickup position teach is deleted from the priority measure list. For example, in the specific example 2, the cleaning is deleted from the priority measure list.

[0119] Next, the effectiveness determining unit 60 updates the countermeasure candidate list for the problem that remains detected even after the current instruction is executed (step S52). Here, the updating of the countermeasure candidate list in the case of specific example 1 will be described with reference to FIG.

[0120] FIG. 12 is a table illustrating an example of an updated countermeasure candidate list according to an embodiment.

[0121] For example, if the problem of a worsening pickup error rate remains even after the pickup position teach command is executed, pickup position teach is removed from the countermeasure candidate list as shown in FIG. 12. Furthermore, since time has passed since the countermeasure candidate list shown in FIG. 7 was created, and production continues on the production floor during that time, the conditions of the feeders and nozzles may have changed, and the priorities of feeder replacement and nozzle replacement may have changed accordingly. Therefore, the effectiveness assessment unit 60 may analyze the priorities and update the priorities in the countermeasure candidate list. For example, in the countermeasure candidate list shown in FIG. 7, the ratio of the priorities (priority probability) between feeder replacement and nozzle replacement was 3:1, but in the countermeasure candidate list shown in FIG. 12, it can be seen that this has changed to 2:3.

[0122] Returning to the explanation of Fig. 11, the effectiveness determining unit 60 registers the highest priority countermeasure candidate in the created countermeasure candidate list in the priority countermeasure list as a countermeasure for the detected problem (step S53). For example, when the countermeasure candidate list shown in Fig. 12 is created, a countermeasure of nozzle replacement is registered in the priority countermeasure list for the problem of a worsening pickup error rate. In other words, a command to replace the nozzle may be output for the problem of a worsening pickup error rate that continues even after pickup position teaching has been performed.

[0123] This means that the operation after step S50 is not executed until the effect determination unit 60 determines the effect of the executed first priority instruction (pickup position teach), and therefore the instruction output unit 50 does not output the second priority instruction (feeder replacement or nozzle replacement) which has a higher priority than the pick-up position teach instruction, determined from among the multiple measures (pick-up position teach, feeder replacement, and nozzle replacement).This is because the instruction to replace the nozzle is output after it is determined that the pick-up position teach is ineffective.

[0124] This also means that when the effect determining unit 60 determines that the execution of the first priority instruction (pickup position teach) has not resulted in a predetermined or greater improvement in the pickup error rate after the execution of the pick-up position teach compared to the state (pick-up error rate) before the execution of the pick-up position teach, the countermeasure determining unit 30 determines the second priority instruction (nozzle replacement) to be executed based on the priorities of the multiple countermeasures (feeder replacement and nozzle replacement) excluding the pick-up position teach, and the instruction output unit 50 outputs an instruction for nozzle replacement. This is because the instruction for nozzle replacement with the highest priority is output after the pick-up position teach with the highest priority.

[0125] This also means that if the effectiveness determination unit 60 cannot determine the effectiveness for a predetermined period of time, the countermeasure determination unit 30 determines the second priority instruction (nozzle replacement) to be executed based on the priorities of the multiple countermeasures (feeder replacement instruction and nozzle replacement) excluding the first priority instruction (pickup position teach), and the instruction output unit 50 outputs an instruction to replace the nozzle. This is because, after a timeout, the instruction to replace the nozzle, which has the highest priority among the multiple countermeasures excluding the pick-up position teach, is output.

[0126] In step S13, after the status monitoring unit 20 detects a problem and registers a high-priority measure from the countermeasure candidate list for the problem in the prioritized countermeasure list, the registered countermeasure may not be implemented for a long time because the priority of the registered countermeasure is low or the production resources for the registered countermeasure are already locked. In such a case, the problem corresponding to the unimplemented countermeasure may be solved by a countermeasure for another problem that has been implemented earlier. In this case, the registered countermeasure may be deleted from the prioritized countermeasure list even before it is implemented, and the countermeasure candidate list may also be deleted.

[0127] As explained above, the effectiveness of the first priority instruction can be determined based on whether or not the condition on the production floor has changed before and after the first priority instruction is executed, and if so, how it has changed, thereby improving the accuracy of determining whether the work instruction is correct.

[0128] (Other embodiments) The production floor management system 1 of the present disclosure has been described above based on the embodiment, but the present disclosure is not limited to the above embodiment. As long as it does not deviate from the spirit of the present disclosure, various modifications that a person skilled in the art can make to the present embodiment and configurations constructed by combining components of different embodiments are also included within the scope of the present disclosure.

[0129] For example, in the above embodiment, the production floor control system 1 is described as including the update unit 70 and the learning models 23, 34, 33 and 34, but may not be provided.

[0130] For example, in the above embodiment, the first state is the production state of the production equipment, and the second state is the state of the production resource, but this is not limiting. For example, the first state and the second state are not particularly limited as long as they are different states on the production floor.

[0131] For example, in the above embodiment, an example has been described in which the production floor management system 1 includes the acquisition unit 10, the status monitoring unit 20, the countermeasure decision unit 30, the countermeasure arbitration unit 40, the instruction output unit 50, the effect assessment unit 60, and the update unit 70. However, some of these units may be included in the production equipment. For example, the production equipment may include the acquisition unit 10, the status monitoring unit 20, and the countermeasure decision unit 30.

[0132] For example, the instruction corresponding to the countermeasure may be composed of multiple instructions, and may be output to multiple production devices or portable devices carried by multiple workers.

[0133] For example, the present disclosure can be realized not only as a production floor management system 1, but also as a work effectiveness assessment method including steps (processing) performed by each component that makes up the production floor management system 1.

[0134] FIG. 13 is a flowchart showing an example of a task effectiveness assessment method according to another embodiment.

[0135] The work effectiveness assessment method is a work effectiveness assessment method in a production floor management system that manages the status of a production floor equipped with production equipment that produces products, and includes monitoring the status on the production floor (step S1), determining a measure corresponding to a first priority instruction to be executed from among a plurality of measures based on the respective priorities of a plurality of measures extracted in response to the above status (step S2), outputting the first priority instruction (step S3), and judging the effectiveness of the executed first priority instruction based on the above status before and after the output first priority instruction was executed (step S4).

[0136] For example, the steps in the work effectiveness assessment method may be executed by a computer (computer system). The present disclosure can be realized as a program for causing a computer to execute the steps included in the work effectiveness assessment method. Furthermore, the present disclosure can be realized as a non-transitory computer-readable recording medium, such as a CD-ROM, on which the program is recorded.

[0137] For example, when the present disclosure is realized as a program (software), each step is performed by running the program using hardware resources such as a computer's CPU, memory, input / output circuits, etc. In other words, each step is performed by the CPU acquiring data from memory or input / output circuits, etc., performing calculations on the data, and outputting the calculation results to memory or input / output circuits, etc.

[0138] Furthermore, each of the components included in the production floor management system 1 of the above embodiment may be realized as a dedicated or general-purpose circuit.

[0139] Furthermore, each of the components included in the production floor management system 1 of the above-described embodiment may be realized as an LSI (Large Scale Integration) which is an integrated circuit (IC).

[0140] Furthermore, the integrated circuit is not limited to an LSI, but may be realized by a dedicated circuit or a general-purpose processor. A programmable FPGA (Field Programmable Gate Array) or a reconfigurable processor in which the connections and settings of circuit cells within the LSI can be reconfigured may also be used.

[0141] Furthermore, if an integrated circuit technology that can replace LSI emerges due to advances in semiconductor technology or other derivative technologies, that technology may naturally be used to integrate each component included in the production floor management system 1 into an integrated circuit.

[0142] In addition, this disclosure also includes forms obtained by making various modifications to the embodiments that a person skilled in the art would think of, and forms realized by arbitrarily combining the components and functions of each embodiment within the scope of the present disclosure. [Industrial Applicability]

[0143] The present disclosure can be used, for example, in managing a production floor. [Explanation of symbols]

[0144] 1. Production floor management system 2. Communication Network 4. Mounting line 5 Management device 10 Acquisition Department 20 Status monitoring unit 21 First status monitoring unit 22 Second status monitoring unit 23, 24, 33, 34 Learning Model 30 Countermeasures Decision-Making Department 31 First Countermeasures Decision-Making Department 32 Second Countermeasures Decision-Making Department 40 Countermeasures and Mediation Department 41 Resource Database 50 Instruction output unit 60 Effect Assessment Section 70 Update section M1 board supply device M2 substrate transfer device M3 printing device M4, M5 mounting device M6 Reflow Machine M7 PCB collection device

Claims

1. A production floor management system for managing the status of a production floor equipped with production equipment for producing products, a status monitoring unit that monitors the status on the production floor; a countermeasure decision unit that decides a countermeasure corresponding to a first priority instruction to be executed from among the plurality of countermeasures based on the priority of each of the plurality of countermeasures extracted corresponding to the state; an instruction output unit that outputs the first priority instruction; an effect determination unit that determines an effect of the executed first priority instruction based on the state before and after the execution of the output first priority instruction, The production resource on which the measure corresponding to the first priority instruction is being taken is locked. Production floor management system.

2. The instruction output unit does not output a second priority instruction determined from the plurality of measures and having a priority ranking lower than the first priority instruction until the effect determination unit determines the effect of the executed first priority instruction. The production floor control system of claim 1 .

3. When the effect determination unit determines that the execution of the first priority instruction has resulted in a predetermined or greater improvement in the state after the execution of the first priority instruction compared to the state before the execution of the first priority instruction, the instruction output unit does not output the second priority instruction before execution that was extracted in relation to the state corresponding to the first priority instruction. The production floor control system according to claim 2 .

4. When the effect determining unit determines that the execution of the first priority instruction has resulted in no predetermined improvement in the state after the execution of the first priority instruction compared to the state before the execution of the first priority instruction, the countermeasure determining unit determines the second priority instruction to be executed based on the priorities of the plurality of countermeasures excluding the first priority instruction, The instruction output unit outputs the second priority instruction.

4. The production floor management system according to claim 2 or 3.

5. When the effectiveness determination unit is unable to determine the effectiveness for a predetermined period of time, the countermeasure determination unit determines the second priority instruction to be executed based on the priority of each of the plurality of countermeasures excluding the first priority instruction; The instruction output unit outputs the second priority instruction.

5. The production floor management system according to claim 2.

6. The countermeasure decision unit updates a priority for determining a priority order for the first priority instruction based on a change in the state after the execution of the first priority instruction, which change occurs due to the execution of the first priority instruction, compared to the state before the execution of the first priority instruction.

6. The production floor management system according to claim 2.

7. the production floor management system further comprises a learning model for updating the priority; The countermeasure decision unit updates the priority based on the learning model. The production floor control system according to claim 6.

8. A method for assessing work effectiveness in a production floor management system that manages the status of a production floor equipped with production equipment that produces products, comprising: monitoring conditions on the production floor; determining a countermeasure corresponding to a first priority instruction to be executed from among the plurality of countermeasures based on the priority of each of the plurality of countermeasures extracted corresponding to the state; outputting the first priority instruction; determining an effect of the executed first priority instruction based on the state before and after the execution of the output first priority instruction; The production resource on which the measure corresponding to the first priority instruction is being taken is locked. Methods for determining work effectiveness.

9. A work effectiveness assessment program that causes a computer to execute the work effectiveness assessment method according to claim 8.

Images