DE112021006886T5 - Production area management system, work instruction procedure and work instruction program - Google Patents

Abstract

A production area management system (1) manages conditions on a production area containing a production device that produces a product. The production area management system (1) includes: a first condition monitoring unit (21) configured to monitor a first condition on the production area; a first countermeasure determining unit (31) configured to determine a first countermeasure corresponding to the first state; a second condition monitoring unit (22) configured to monitor a second condition on the production floor that is different from the first condition; a second countermeasure determining unit (32) configured to determine a second countermeasure corresponding to the second state; a countermeasure decision unit (40) configured to make a decision between the first countermeasure and the second countermeasure; and a command issuing unit (50) configured to issue a command corresponding to the first countermeasure or the second countermeasure according to the decision.

Description

Technical area

The present invention relates to a shop floor management system that manages conditions on a shop floor having a production device that produces a product, and a work instruction method and a work instruction program for the shop floor management system.

State of the art

Conventionally, when a problem occurs in a production apparatus, a technique is disclosed for issuing a work instruction according to a countermeasure method for the problem while updating the countermeasure method (for example, Patent Literature (PTL) 1).

Citation list

Patent literature

[PTL 1] WO 2018 / 142 604

Summary of the invention

Technical problem

However, a variety of problems can occur in the production device. In such cases, it is difficult with the technique disclosed in PTL 1 to issue an optimal work instruction from a variety of measures to correct the problems.

In view of this, the present invention provides a production area management system, etc., which can issue an optimal work order from a variety of measures to correct problems.

Troubleshooting

A production area management system according to an aspect of the present invention is a production area management system that manages conditions on a production area that includes a production device that produces a product. The production area management system includes: a first condition monitoring unit configured to monitor a first condition on the production area; a first countermeasure determining unit configured to determine a first countermeasure corresponding to the first state; a second condition monitoring unit configured to monitor a second condition on the production floor, the second condition different from the first condition; a second countermeasure determination unit configured to determine a second countermeasure corresponding to the second state; a countermeasure decision unit configured to make a decision between the first countermeasure and the second countermeasure; and a command issuing unit configured to issue a command corresponding to the first countermeasure or the second countermeasure according to the decision.

It should be noted that these general or specific aspects may be implemented as a system, device, method, recording medium, or computer program, or as any combination of systems, devices, methods, recording media, and computer programs.

Advantageous effects of the invention

The production area management system and the like according to the present invention can issue an optimal work instruction from a variety of countermeasures.

Brief description of the drawings

• [ 1 ] 1 is a diagram showing a production line on which a shop floor management system is used according to an embodiment.
• [ 2 ] 2 is a block diagram for illustrating an example of the shop floor management system according to the embodiment.
• [ 3 ] 3 is a diagram illustrating an example of targets to be monitored by a condition monitoring unit according to the embodiment.
• [ 4 ] 4 is a diagram schematically illustrating an operation flow of the production area management system according to the embodiment.
• [ 5 ] 5 is a flowchart illustrating an example of the operation of the condition monitoring unit according to the embodiment.
• [ 6 ] 6 is a flowchart illustrating an example of the operation of a countermeasure determining unit according to the embodiment.
• [ 7 ] 7 is a table showing an example of a countermeasure candidate list according to the embodiment.
• [ 8th ] 8th is a table showing an example of a countermeasure priority list according to the embodiment.
• [ 9 ] 9 is a flowchart illustrating an example of the operation of a countermeasure decision unit according to the embodiment.
• [ 10 ] 10 is a table showing an example of a resource management table according to the embodiment.
• [ 11 ] 11 is a flowchart illustrating an example of operations of a command issuing unit, an effect judgment unit, and an updating unit according to the embodiment.
• [ 12 ] 12 is a table showing an example of an updated countermeasure candidate list according to the embodiment.
• [ 13 ] 13 is a flowchart illustrating an example of a work instruction method according to further embodiments.

Description of the embodiments

A production area management system according to the present invention is a production area management system that manages conditions on a production area having a production device that produces a product. The production area management system includes: a first condition monitoring unit configured to monitor a first condition on the production area; a first countermeasure determining unit configured to determine a first countermeasure corresponding to the first state; a second condition monitoring unit configured to monitor a second condition on the production floor, the second condition different from the first condition; a second countermeasure determination unit configured to determine a second countermeasure corresponding to the second state; a countermeasure decision unit configured to make a decision between the first countermeasure and the second countermeasure; and a command issuing unit configured to issue a command corresponding to the first countermeasure or the second countermeasure according to the decision.

Thus, the first countermeasure and the second countermeasure for executing a countermeasure against the first state and the second state different from each other on the production area are determined. By deciding between the first countermeasure and the second countermeasure, a command can be issued that corresponds to an optimal first countermeasure or an optimal second countermeasure. As described above, the shop floor management system according to the present invention can issue an optimal work instruction from a variety of countermeasures.

In addition, the monitoring of the first state by the first state monitoring unit and the determination of the first countermeasure by the first countermeasure determination unit can be carried out in parallel with the monitoring of the second state by the second state monitoring unit and the determination of the second countermeasure by the second countermeasure determination unit.

For example, although the first countermeasure and the second countermeasure determined when the first state and the second state are monitored in parallel may be difficult to reconcile, the present invention discriminates between the first countermeasure and the second countermeasure. Therefore, it is possible to issue an instruction corresponding to an optimal first countermeasure or an optimal second countermeasure. In addition, when the first countermeasure and the second countermeasure are compatible, an instruction corresponding to the first countermeasure and an instruction corresponding to the second countermeasure can be issued in parallel without the decision, and the countermeasures can be carried out efficiently.

Furthermore, the countermeasure decision unit may be configured to make the decision based on a problem level for the first state corresponding to the first countermeasure and a problem level for the second state corresponding to the second countermeasure.

This means that a countermeasure that corresponds to a higher problem level can be given priority.

If there is no difference between 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, the countermeasure decision The processing unit must also be configured so that it prefers the first countermeasure in the decision.

In this way, it is possible to maintain the operation of the production device by prioritizing the first countermeasure when there is no difference in problem levels.

Furthermore, the production area management system may further include an effect evaluation unit configured to evaluate an effect of the executed first countermeasure or second countermeasure based on the first state and/or the second state before and after the execution of the first countermeasure or the second countermeasure that corresponds to the issued instruction.

With this, it is possible to check whether the countermeasure carried out according to the condition on the production area is appropriate by assessing the effect of the countermeasure carried out, and the result can be used to improve countermeasures in the future.

Furthermore, the first state may be a production state of the production device, and the second state may be a state of each of the production resources managed on the production area and used for production.

For example, the MTTR (Mean Time To Repair) can be improved by monitoring the production state of the production device and issuing the first countermeasure that corresponds to the production state. For example, if production condition monitoring reveals that there is a problem with the production condition (e.g., if productivity or quality is poor or scrap occurs), the first countermeasure will be a countermeasure to resolve the production condition problem. Therefore, the MTTR can be improved by taking a measure equivalent to the first countermeasure.

In addition, for example, the MTBF (Mean Time Between Failures) can be improved by monitoring the states of the production resources and issuing the second countermeasure corresponding to a state of a production resource. For example, if monitoring the conditions of resources reveals that there is a problem with the condition of a resource (e.g., if the production device or a plant element is damaged or a worker's work is defective), the second countermeasure is a remediation countermeasure the problem of the state of the production resource. For example, if the problem of the production resource state is not solved, a problem in the production state may arise. Therefore, the MTBF can be improved by taking a measure equivalent to the second countermeasure. In other words, it is possible to prevent a problem in production before it occurs.

Furthermore, the countermeasure decision unit may be configured to make the decision based on the presence or absence of one or more of the production resources required for the first countermeasure or the second countermeasure.

For example, the first countermeasure for correcting the production condition problem and the second countermeasure for correcting the production resource condition problem are each often related to a production resource. When an instruction corresponding to the first countermeasure or the second countermeasure is issued and the corresponding production resource is used, it is difficult to execute the issued instruction. On the other hand, a decision is made based on the presence or absence of the production resource according to the present aspect. Therefore, an instruction corresponding to an optimal first countermeasure or an optimal second countermeasure can be issued according to the presence or absence of the production resource.

In addition, the production area management system may include a first trained model for detecting a first predetermined condition that occurs on the production area according to the production condition. The first condition monitoring unit may be configured to detect the first predetermined condition based on the first trained model. In particular, the first condition monitoring unit may be configured to detect, in a predetermined period of time, the first predetermined condition corresponding to a production indicator via at least one of the following information: production error information, production quantity information and quality information, wherein the production error information relates to an error occurred in the production device Production quantity information a quantity of a produced by the production device Product relate and the quality information relates to a quality of a product manufactured by the production device. The first countermeasure determination unit may be configured to determine the first countermeasure including a countermeasure for improving the production indicator.

By using the first trained model, as described above, the first predetermined state can be effectively captured.

In addition, the production area management system may include a second trained model for detecting a second predetermined state that occurs according to the state of each of the production resources on the production area. The second condition monitoring unit may be configured to detect the second predetermined condition based on the second trained model. In particular, the second condition monitoring unit may be configured to detect the second predetermined condition that corresponds to an operating indicator about the operating condition of the production device included in the production resources. The second countermeasure determination unit may be configured to determine the second countermeasure that includes a countermeasure for the production device that corresponds to the operation indicator. In addition, in particular, the second condition monitoring unit may be configured to detect the second predetermined condition corresponding to a work indicator about the work performed by a worker included in the production resources. The second countermeasure determination unit may be configured to determine the second countermeasure that includes the worker's work corresponding to the work indicator.

By using the second trained model, as described above, the second predetermined state can be effectively captured.

A work instruction method according to the present invention is a work instruction method in a shop floor management system that manages conditions on a shop floor containing a production device that produces a product. The work instruction procedure includes: monitoring a first condition on the production floor; monitoring a second condition on the production floor, the second condition different from the first condition; determining a first countermeasure corresponding to the first condition; determining a second countermeasure corresponding to the second condition; making a decision between the first countermeasure and the second countermeasure; and issuing an instruction corresponding to the first countermeasure or the second countermeasure according to the decision.

In this way, a work instruction process can be provided that can issue an optimal work instruction from a variety of actions to resolve problems.

A work instruction program according to the present invention is a work instruction program that causes a computer to execute the work instruction method described above.

This makes it possible to provide a work instruction program that can issue an optimal work instruction from a variety of troubleshooting measures.

It should be noted that each of the embodiments described below represents a general or specific example. The numerical values, shapes, materials, structural elements, arrangement and connection of structural elements, steps, order of steps, etc. given in the following embodiments are for illustrative purposes only and are not intended to limit the present invention.

Embodiment

An embodiment is described below with reference to 1 until 12 described.

1 is a schematic representation of the production line 4 on which the production area management system 1 according to the embodiment is provided.

As in 1 shown, the production line 4 includes a variety of production devices for producing products.

The production line 4 has the function of producing products (e.g. mounting substrates) by mounting components (electronic components) on each substrate. The production line 4 has the task of feeding, forwarding and collecting the substrate on which the components are mounted.

Specifically, in the production line 4, the substrate feed device M1, the substrate transport device M2, the printing device M3, the assembly devices M4 and M5, are the melters device M6 and the substrate collecting device M7 connected in series in this order. Each device, from the substrate feeding device M1 to the substrate collecting device M7, is connected to a management device 5 via the communication network 2.

For example, the soldering printing device M3, the component mounting devices M4 and M5 and the reflow device M6 perform component assembly work, i.e. H. Work to assemble components on the substrate transported along production line 4. In other words, the substrate supplied from the substrate supply device M1 is transported to the printing device M3 by the substrate transport device M2. The printing device M3 carries out the screen printing of the solder, i.e. H. the screen printing of the solder

The substrate on which the solder is printed is sequentially passed to the mounting devices M4 and M5. The assembly devices M4 and M5 carry out the assembly of components, i.e. H. the assembly of components on the substrate after soldering printing.

Each of the component mounters M4 and M5 includes a base, a substrate transport unit, a component feeder, and a mount head, etc. A substrate is placed on the base. The substrate transport unit can transport the substrate from a device on the upstream side to a device on the downstream side. The component feeding device can feed components to the assembly head. The component feeding device includes a plurality of feeding stations for feeding components to the assembly head. The mounting head can suck and pick up a component from the feed station, move across the substrate, and mount the component at the mounting position on the substrate. The assembly head is equipped with suction nozzles that can suck in components, hold them and move them up and down individually. Such component assembly devices M4 and M5 carry out the component assembly.

Subsequently, after the components have been mounted thereon, the substrate is fed to the reflow device M6 and heated according to a predetermined heating profile. This causes the solder to connect the components, which is printed on the heated substrate, to melt and solidify. In this way, the components are soldered to the substrate, creating a mounting substrate on which the components are mounted. The finished mounting substrate is collected by the substrate collecting device M7.

Below, a configuration of the production area management system 1 will be described with reference to 2 described.

2 is a block diagram showing an example of a production area management system 1 according to the embodiment.

The production area management system 1 is a system that manages conditions on a production area including the production devices that produce products.

The production area includes, for example, production line 4, a supply warehouse, a preparation area and a maintenance area. As already mentioned, there are 4 production devices on the production line, such as the assembly devices M4 and M5, the printing device M3 and a testing device. Materials such as components, solder and stencils are stored in the supply warehouse. In the preparation area, system elements such as carriages, feed stations, nozzles and heads are prepared. In the maintenance area, for example, maintenance of the above-mentioned system elements, devices, etc. is carried out. The devices mentioned here are used to adjust the feed stations, the nozzles, the heads, etc. and can also be used to adjust the head movement mechanism and the transport mechanism of the system. In each area of the production area, a worker carries out work such as production, preparation and maintenance, and carries out work such as transporting components and plant elements between areas. The production area management system 1 is, for example, a computer installed on the production area. The functions of the production area management system 1 can be included in the management device 5, for example. Note that the shop floor management system 1 may be a computer housed in one case, or divided into two or more cases and executed by two or more computers. Furthermore, the production area management system 1 need not be located on the production area, but may also be a computer such as a server provided outside the production area. It should be noted that the worker is not limited to a human. The worker may also include a robot, a work mechanism and an automated guided vehicle that perform the work described above.

The production area management system 1 is a system that issues an instruction to the workers or production devices, etc. on the production area according to the conditions on the production area. The management system 1 for The production area includes a detection unit 10, a condition monitoring unit 20, a countermeasure determination unit 30, a countermeasure decision unit 40, a command output unit 50, an effect assessment unit 60, an update unit 70, trained models 23, 24, 33 and 34 and a resource database 41. This Production area management system 1 is implemented by a computer including a processor, a memory, etc. The detection unit 10, the condition monitoring unit 20, the countermeasure determination unit 30, the countermeasure decision unit 40, the command issuing unit 50, the effect judgment unit 60 and the updating unit 70 are implemented by the processor operating according to the program stored in the memory.

In addition, the condition monitoring unit 20 can be provided as a standalone computer or integrated into the production device. In addition, the production area management system 1 may include a plurality of condition monitoring units 20. The trained models 23, 24, 33 and 34 as well as the resource database 41 are stored in memory. The memory in which the program, the trained models 23, 24, 33 and 34 and the resource database 41 are stored may be the same memory or a different memory.

The detection unit 10 obtains information for monitoring conditions on the production area. For example, the detection unit 10 receives information indicating a production status of the production area. Specifically, the detection unit 10 obtains a result of the production process of the production apparatus (specifically, productivity, quality, presence or absence of scrap, etc.) as the information indicating the production state of the production area. The result of the production process can be the recording of measurement data by a sensor or the entry of data by a human. In addition, the recording unit 10 receives, for example, information about the status of the production resources managed on the production area and used for production. The production resources are, for example, the production devices, plant elements, a worker, materials or devices. The information that indicates the status of the production resources can be, for example, sensor data from a camera or a sensor or data entered by a human. In addition, the detection unit 10 receives, for example, event information about an event that has changed on the production area. Specifically, the detection unit 10 obtains information indicating that a production device stops, that a feed station, a nozzle, a component or a substrate to be mounted on a production device has been replaced, that a worker performing the work has been replaced , or that the operating data of a production device has been changed.

The condition monitoring unit 20 monitors the conditions on the production area based on the information received from the detection unit 10. For example, the condition monitoring unit 20 detects a predetermined condition (e.g., a first condition or a second condition, which will be described later) among the conditions on the production area based on a first condition for detecting the predetermined condition. The first condition is, for example, a trained model associated with a detection threshold that matches the predetermined state. It should be noted that the first condition can be a set detection threshold and does not have to be the trained model.

The condition monitoring unit 20 includes a first condition monitoring unit 21 and a second condition monitoring unit 22. The first condition monitoring unit 21 and the second condition monitoring unit 22 each carry out the previously described operations of the condition monitoring unit 20.

The first condition monitoring unit 21 monitors a first condition on the production area. For example, the first state is a production state of each production device, and the first state monitoring unit 21 monitors the result of the production process as the production state of the production device. For example, the first condition monitoring unit 21 detects a first predetermined condition based on a trained model 23. The trained model 23 is a first trained model for detecting the first predetermined condition occurring on the production area according to the production condition of each production device. The trained model 23 is also a trained model (ie, the first condition) associated with a detection threshold corresponding to the production state of each production device. For example, in a predetermined period of time, the first condition monitoring unit 21 detects the first predetermined condition corresponding to the production indicator via at least one of the following information: production defect information, production quantity ninformation and quality information. The production error information refers to a production error that occurred in each production device, the production quantity information refers to the quantity of the product produced by each production device, and the quality information refers to the quality of the product produced by each production device.

The second condition monitoring unit 22 monitors a second condition on the production area. The second state is different from the first state. For example, the second state is a state of a production resource. The second condition monitoring unit 22 monitors a condition of each production resource. For example, the condition monitoring unit 22 detects a second predetermined condition based on the trained model 24. The trained model 24 is a second trained model for detecting the second predetermined condition occurring on the production floor according to a condition of each production resource. The trained model 24 is also a trained model (i.e., the first condition) associated with a detection threshold corresponding to a state of each production resource. For example, the second condition monitoring unit 22 detects a second predetermined condition that corresponds to an operational indicator about the operating condition of a production device included in the production resources. In addition, the second condition monitoring unit 22 detects, for example, a second predetermined condition corresponding to a work indicator about the work performed by a worker included in the production resources.

An example of targets to be monitored by the condition monitoring unit 20 is described below with reference to 3 described.

3 is a diagram showing an example of targets to be monitored by the condition monitoring unit 20 according to the embodiment. It should be noted that it is as described 3 the production device is an assembly device and the manufacturing process is an assembly process.

As in 3 shown, the condition monitoring unit 20 (in particular the first condition monitoring unit 21) monitors the result of the assembly process, which includes processes such as suction, detection and placement, as a production condition. For example, in a predetermined period of time, the first condition monitoring unit 21 detects the first predetermined condition corresponding to a production indicator via at least one of the following elements: assembly defect information, assembled quantity information, and quality information (in particular, the presence or absence of an assembly defect [scrap ], the quantity assembled [productivity] and the quality of assembly, e.g.). The information about an assembly error refers to an error that has occurred in the device. The assembled quantity information refers to the quantity of components assembled by the device. The quality information refers to the quality of the components assembled by the device.

In addition, the condition monitoring unit 20 (in particular the second condition monitoring unit 22) monitors the states of the elements (production resource) involved in the assembly process, such as substrates, components, workers, heads, nozzles and feed stations. For example, the second condition monitoring unit 22 detects a second predetermined condition corresponding to an operational indicator about the operating condition of the device included in the production resources (e.g., deterioration of the device, nozzles, and feed stations). In addition, the second condition monitoring unit 22 detects, for example, a second predetermined condition corresponding to a work indicator about the work performed by a worker in the production resources for the device (e.g., a work error by a worker). In addition, a second predetermined state may be detected, which, in addition to the working indicator (i), is a measurement indicator of the difference between numerical values (length, width, thickness, coordinate positions of various types of marks and viscosity) of a substrate, solder or a component on the design data and the actual numerical values measured by a camera or sensor, and (ii) a time indicator of the expiration date and time of the solder or a component and the actual measured date and time.

Referring again to the description of the 2 , the countermeasure determination unit 30 determines a countermeasure to be carried out from a plurality of countermeasures extracted according to the condition on the production area monitored by the condition monitoring unit 20. The countermeasure to be executed 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 carried out (for example, a first countermeasure or a second countermeasure, which will be described later). corresponds to a predetermined state based on a second condition for determining the countermeasure. The second condition includes, for example, a priority that is set for each of the plurality of extracted countermeasures. The second condition is a trained model associated with the plurality of countermeasures that match the predetermined condition and priority. For example, the countermeasure determination unit 30 determines a first priority instruction to be executed among the plurality of countermeasures according to the priority of each of the countermeasures extracted according to the condition on the production floor monitored by the condition monitoring unit 20. In other words, the countermeasure determining unit 30 determines the countermeasure to be executed (ie, the first priority instruction) among the countermeasures extracted according to the predetermined state based on the priority of each of the countermeasures. For example, the countermeasure determination unit 30 analyzes the operation information of the production device obtained on the production floor, worker information, which is information about a worker working on the production floor, and material information, which is information about a material used for the product to determine the countermeasure that corresponds to the given condition. When analyzing, it should be noted that there are cases in which a countermeasure can only be determined based on the tendency in the given state, and there may be cases in which a countermeasure cannot be determined based on the tendency in the given state alone. When the countermeasure cannot be determined based on the tendency of the predetermined state alone, the countermeasure determination unit 30 may determine a countermeasure corresponding to the predetermined state by analyzing the following information recorded on the production area for each production resource based on the event information Obtained: the operational information of a production device, the worker information about the workers working on the production floor, and the material information about the materials used for the products. The countermeasure determination unit 30 may also execute a predetermined countermeasure and further analyze the trend before and after the execution of the predetermined countermeasure to determine the countermeasure corresponding to the predetermined state. In addition, the analysis can be carried out with an analysis unit independent of the countermeasure determination unit 30. For example, the countermeasure determining unit 30 updates the priorities for determining the priority order of the first priority instruction (countermeasure) based on a change in the condition on the production floor after the execution of the first priority instruction for the condition on the production floor before the execution of the first priority instruction. In addition, the countermeasure determining unit 30 updates the priorities based on, for example, the trained priority updating model. It should be noted that the second condition can be a data table containing a priority set for each of the countermeasures, rather than the trained model.

The countermeasure determination unit 30 includes a first countermeasure determination unit 31 and a second countermeasure determination unit 32. The first countermeasure determination unit 31 and the second countermeasure determination unit 32 each perform the above-described operations of the countermeasure determination unit 30.

The first countermeasure determination unit 31 determines a first countermeasure that corresponds to the first state monitored by the first state monitoring unit 21. For example, the first countermeasure determination unit 31 determines the first countermeasure to be executed (i.e., the first priority instruction) from the countermeasures extracted according to the first state, according to the priority order of each of the countermeasures. For example, the first countermeasure determination unit 31 determines the first countermeasure that includes a countermeasure that improves the production indicator described above. Specifically, the first countermeasure determining unit 31 determines the first countermeasure for improving the MTTR. The MTTR is an indicator of the maintainability of a system or device, i.e. the shorter the MTTR, the higher the maintainability. For example, the first countermeasure determination unit 31 determines the first countermeasure based on the trained model 33. The trained model 33 is a trained model for determining the first countermeasure that correlates with the first state. More specifically, the trained model 33 is a trained model for updating priorities. The trained model 33 is also a trained model (i.e., the second state) associated with countermeasures and priorities corresponding to a given state.

The second countermeasure determination unit 32 determines a second countermeasure corresponding to the second state determined by the second state monitoring unit 22 is monitored. For example, the second countermeasure determination unit 32 determines the second countermeasure to be executed (ie, the first priority instruction) from the countermeasures extracted according to the first state, according to the priority order of each of the countermeasures. For example, the second countermeasure determination unit 32 determines the second countermeasure that includes countermeasures (maintenance and replacement) for the production devices and the equipment elements that correspond to the operation indicator described above, or that includes the work availability of the workers and the work training of the workers that correspond to the above correspond to the work indicator described. Specifically, the second countermeasure determining unit 32 determines the second countermeasure for improving the MTBF. The MTBF is an indicator of the re-availability of a system or device, i.e. the longer the MTBF, the higher the reliability. For example, the second countermeasure determination unit 32 determines the second countermeasure based on the trained model 34. The trained model 34 is a trained model for determining the second countermeasure corresponding to the second state. More specifically, the trained model 34 is a trained model for updating priorities. The trained model 34 is also a trained model (ie, the second state) associated with countermeasures and priorities that correlate with a predetermined state. It should be noted that the second countermeasure determined here can be completed when the second countermeasure is communicated to a maintenance schedule making device or a worker management device provided separately from the production area management system 1, or it can be completed when an execution result of the second countermeasure is received again.

The countermeasure decision unit 40 decides between the first countermeasure and the second countermeasure. Here reasons for the need to decide between the first countermeasure and the second countermeasure are given with reference to 3 described in detail.

Like for example in 3 shown, the result of the assembly process refers to suction on substrates, components, workers, heads, nozzles and feed stations; the result of the assembly process in terms of recognition relates to components, heads and nozzles; and the result of the assembly process in terms of placement refers to substrates, components and nozzles. For example, the first countermeasure includes countermeasures for substrates, components, workers, heads, nozzles or feed stations according to the result of the production process. On the other hand, the second countermeasure also includes countermeasures for substrates, components, workers, heads, nozzles or feeding stations according to the conditions of production resources. In other words, the production resources subject to the first countermeasure and the production resources subject to the second countermeasure may overlap. When the production resource subject to the first countermeasure overlaps with the production resource subject to the second countermeasure, it is difficult to execute both the first countermeasure and the second countermeasure at the same time, and therefore it is necessary to make a decision between the first countermeasure and the second countermeasure.

For example, the countermeasure decision unit 40 makes a decision based on a problem level set for the first state corresponding to the first countermeasure and a problem level set for the second state corresponding to the second countermeasure. In addition, the countermeasure decision unit 40 makes a decision based on the presence or absence of one or more production resources required for the first countermeasure or the second countermeasure. The presence or absence of one or more of the production resources is managed in the resource database 41.

The command issuing unit 50 issues the first priority command. Specifically, the command issuing unit 50 outputs the first countermeasure or the second countermeasure that is the first priority instruction according to the decision made by the countermeasure decision unit 40. For example, the command output unit 50 only outputs a second priority command when the effect assessment unit 60, to be described later, judges the effect of the executed first priority command. The second priority instruction is an instruction that has a lower priority than the priority of the first priority instruction and is determined from the plurality of countermeasures. For example, when the effect judgment unit 60 judges that the condition on the production floor after the execution of the first priority instruction has a tendency of at least a predetermined degree of improvement compared to the condition on the production floor before the execution of the first priority instruction, the instruction issuing unit 50 issues the second Priority statement which is extracted with respect to the state on the shop floor corresponding to the first priority instruction and which is an instruction before it is executed. For example, when the effect judgment unit 60 determines that the condition on the production floor after the execution of the first priority command does not tend to improve by at least a predetermined degree compared to the condition on the production surface before the execution of the first priority command, it determines the countermeasures -Determination unit 30 the second priority command to be executed based on the priority of each of the countermeasures except the first priority command, and the command output unit 50 outputs the second priority command. For example, when the effect judgment unit 60 cannot judge the effect for a predetermined period of time, the countermeasure determination unit 30 determines the second priority command to be executed based on the priority of each of the countermeasures except the first priority command, and the command output unit 50 issues the second priority command out of. The command issuing unit 50 may issue a command to a control unit of the production apparatus or a mobile terminal carried by a worker, or may issue a command to the production apparatus or a worker through a production management apparatus that manages the production apparatus or a worker management apparatus that Worker managed, spend.

The effect judgment unit 60 judges the effect of the executed countermeasure (instruction) based on the conditions on the production floor before and after the execution of the specified countermeasures (in other words, the first priority instruction issued). Specifically, the effect judgment unit 60 judges the effect of the first countermeasure or the second countermeasure that has been executed based on at least one of the two states, the first state and the second state, before and after the execution of the first countermeasure or the second countermeasure that has been executed corresponds to the issued instruction.

The updating unit 70 updates the first state and the second state, i.e. the trained models 23, 24, 33 and 34, based on the evaluated effect.

Details of the condition monitoring unit 20, the countermeasure determination unit 30, the countermeasure decision unit 40, the command issuing unit 50, the effect judgment unit 60 and the updating unit 70 will be described later.

The monitoring of the first state by the first state monitoring unit 21 and the determination of the first countermeasure by the first countermeasure determination unit 31 are carried out in parallel with the monitoring of the second state by the second state monitoring unit 22 and the determination of the second countermeasure by the second countermeasure determination unit 32. These operations are described with reference to 4 described.

4 is a diagram schematically illustrating an operation of the production area management system 1 according to the embodiment.

In the production area management system 1, the condition monitoring unit 20 detects a problem, the countermeasure determination unit 30 determines a countermeasure strategy, the countermeasure decision unit 40 makes a decision, and the command issuing unit 50 executes a countermeasure. These can be applied to the so-called OODA loop. Discovering a problem corresponds to “observing,” determining a countermeasure strategy corresponds to “orienting,” making a decision corresponds to “deciding,” and executing a countermeasure corresponds to “acting.”

The monitoring of the first state by the first state monitoring unit 21 and the determination of the first countermeasure by the first countermeasure determination unit 31 are for improving the MTTR as described above. In 4 MTTR cycle is a cycle of detecting a problem by the first condition monitoring unit 21, determining a countermeasure by the first countermeasure determining unit 31, making a decision by the countermeasure decision unit 40, and executing a countermeasure by the command issuing unit 50. As mentioned above, monitoring the second state by the second state monitoring unit 22 and determining the second countermeasure 32 by the second countermeasure determining unit 32 serve to improve the MTBF. In 4 an MTBF cycle is a cycle of discovering a problem by the second condition monitoring unit 22, determining a countermeasure strategy by the second countermeasure determining unit 32, making a decision by the countermeasure decision unit 40 and executing a countermeasure by the command issuing unit 50.

As described above, the monitoring of the first state by the first state monitoring unit 21 and the determination of the first countermeasure by the first countermeasure determination unit 31 are carried out in parallel with the monitoring of the second state by the second state monitoring unit 22 and the determination of the second countermeasure by the second countermeasure determination unit 22. Determination unit 32 carried out. For example, the OODA loop can achieve process safety in terms of both MTBF and MTTR.

In addition, each of the processes of the OODA loop, namely finding a problem, determining a countermeasure strategy, making a decision, and executing the countermeasure, is independent. By executing the processes in parallel, the waiting time between processes can be minimized and real-time control can be achieved. Although the details are described later, it is possible to implement a countermeasure while changing priorities for conditions on the production floor, including various situations that change over time.

Although an example is described in which the first state is a production state of each production device and the second state is a state of each production resource, the present invention is not limited to this example. For example, the first state can be a production state of a production device, and the second state can be a production state of the production device that deviates from the first state. In addition, the first state may be, for example, a state of a production resource, and the second state may be a state of the production resource that is different from the first state. 4 For example, shows an example in which the MTBF cycle and the MTTR cycle are performed in parallel, but a plurality of MTBF cycles may be performed in parallel or a plurality of MTTR cycles may be performed in parallel. It should be noted that when the MTBF cycle and the MTTR cycle are performed in parallel and a decision is to be made between the first countermeasure and the second countermeasure, the countermeasure decision unit 40 can make a decision by taking the first countermeasure prioritized over the second countermeasure. In particular, when there is no difference in the problem level, which will be described later, the operation of the production device can be maintained by prioritizing the first countermeasure. The expression "no difference in problem levels" mentioned here includes a situation in which the problem levels are the same and a situation in which the difference in problem levels is within a predetermined range.

Next, details of the condition monitoring unit 20, the countermeasure determination unit 30, the countermeasure decision unit 40, the command issuing unit 50, the effect judgment unit 60 and the updating unit 70 will be explained with reference to FIG 5 until 12 described.

First, details of the condition monitoring unit 20 will be discussed with reference to 5 described.

5 is a flowchart illustrating an example of the operation of the condition monitoring unit 20 according to the embodiment. 5 illustrates the process of finding a problem (observing) in the OODA loop.

First, the condition monitoring unit 20 acquires monitoring data (step S11). Specifically, the first condition monitoring unit 21 obtains monitoring data about the production condition of the production apparatus, and the second condition monitoring unit 22 obtains monitoring data about the conditions of the production resources.

Next, the condition monitoring unit 20 loads trained models (step S12). In particular, the first condition monitoring unit 21 loads the trained model 23, and the second condition monitoring unit 22 loads the trained model 24.

The trained model 23 is a first trained model for detecting a first predetermined state occurring on the production area according to the production state of the production apparatus. The trained model 23 is associated with a detection threshold that corresponds to the production state of the production device. For example, the trained model 23 is trained to output, in response to the input of the obtained monitoring data, a first predetermined state (e.g., productivity, quality, or scrap) corresponding to the production indicator for at least one of the following information contained in the Monitoring data obtained are: production error information relating to an error occurred in the production device, production quantity information relating to the amount of the product produced by the pro products produced by the production device, and quality information relating to the quality of the products produced by the production device. Here, a method for training (updating) the trained model 23 is described using a concrete example.

For example, assume that a decline in productivity is detected based on the detection threshold corresponding to the productivity associated with the trained model 23, and a countermeasure to increase productivity is issued. As a result of the countermeasure, productivity is assumed to have increased and quality to have decreased. In other words, the countermeasure increased productivity, but quality deteriorated. If e.g. For example, if the learning strategy is set to emphasize quality, learning is carried out in such a way that the detection threshold corresponding to productivity is relaxed due to the effect described above (a decline in productivity is less likely to be detected). In this way, a detection threshold is learned that has a good balance between productivity and quality.

The trained model 24 is a second trained model for recognizing a second predetermined condition occurring on the production area according to a condition of each production resource. The trained model 24 is associated with a detection threshold that corresponds to the state of the production resource. For example, the trained model 24 is trained to output, in response to the input of the obtained monitoring data, a second predetermined condition (for example, a deterioration of the production device or a plant element or an error in work by a worker) corresponding to the operational indicator corresponds to the operating state of a production device included in the production resources or the work indicator about the work performed by a worker included in the production resources. Here, a method for training (updating) the trained model 24 is described using a concrete example.

For example, it is assumed that a decrease in the flow rate of a nozzle is detected based on the detection threshold corresponding to the flow rate of the nozzle associated with the trained model 24, and a countermeasure to perform inspection and maintenance of the nozzle within a week is issued. For example, it is assumed that the suction failure rate deteriorates after the countermeasure is issued and before the maintenance is carried out (before one week), and the effect of the countermeasure issued cannot be achieved. In this case, the decrease in nozzle flow rate may have been detected too late. Based on the effect described above, it is learned to make the detection threshold for the flow rate of a nozzle narrower (i.e. a decrease in the flow rate of a nozzle is more likely to be detected earlier). In this way, a detection threshold is learned that allows maintenance to be carried out at an optimal time. The nozzle flow rate detection threshold is an example. The training described above can also be applied when the detection threshold is set for a deviation in the stop position of a feed station, for a deviation in the suction position of a component sucked by a nozzle, or for a deviation in the transport position of a substrate.

Next, the condition monitoring unit 20 judges whether a problem is detected in the first predetermined condition or the second predetermined condition (step S13). For example, the first condition monitoring unit 21 may judge whether a decrease in productivity, a decrease in quality, or an increase in scrap is detected. The second condition monitoring unit 22 judges, for example, whether a deterioration of a production device, a deterioration of an equipment element, or an error in a worker's work is detected.

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

If a problem is detected (Yes in step S13), a countermeasure strategy for the detected problem is determined.

Next, details of the countermeasure determination unit 30 will be described with reference to 6 described.

6 is a flowchart illustrating an example of operations of the countermeasure determining unit 30 according to the embodiment. 6 illustrates the process of determining a countermeasure strategy (orientation) in the OODA loop.

The countermeasure determination unit 30 analyzes the associated production resources (e.g. production resources) for the problem identified by the condition monitoring unit 20 cen that may cause the problem) (step S21). For example, when the first condition monitoring unit 21 detects a problem of reduced productivity in the assembling process of an assembling apparatus, the countermeasure determination unit 30 analyzes that the production resources that may cause the problem are the substrates, components and workers, heads, nozzles and feed stations (see 3 ). Furthermore, for example, when the problem of deterioration of a nozzle is detected by the second condition monitoring unit 22, the countermeasure determination unit 30 analyzes that the production resource that may cause the problem is the nozzle.

Next, the countermeasure determination unit 30 loads trained models (step S22). In particular, the first countermeasure determination unit 31 loads the trained model 33 and the second countermeasure determination unit 32 loads the trained model 34.

The trained model 33 is a trained model for determining the first countermeasure corresponding to the production state of the production device. More specifically, the trained model 33 is a trained priority update model for determining the priority order of the first countermeasure. For example, the trained model 33 is trained to output a candidate countermeasure against the detected problem in response to input of the detected problem. When a plurality of candidates for the detected problem are output, a plurality of countermeasures corresponding to the plurality of candidates are extracted. A training procedure for the trained model 33 will be described later.

The trained model 34 is a trained model for determining the second countermeasure corresponding to the states of the production resources. More specifically, the trained model 34 is a trained model for updating priorities to determine the priority order of the second countermeasure. For example, the trained model 34 is trained to output a countermeasure against the detected problem as a candidate in response to input of the detected problem. When a plurality of candidates for the detected problem are output, a plurality of countermeasures corresponding to the plurality of candidates are extracted. A training procedure for the trained model 34 will be described later.

Next, the countermeasure determination unit 30 analyzes the priority to determine the priority order for each of the countermeasures (step S23). For example, when each of the trained models 33 and 34 outputs a countermeasure against the detected problem as a candidate, each of the trained models 33 and 34 assigns priority to the countermeasure and outputs the countermeasure. Thereby, the countermeasure determining unit 30 can know the priority of each countermeasure.

Next, the countermeasure determination unit 30 creates a countermeasure candidate list (step S24). The countermeasure candidate list is provided with reference to 7 described.

7 is a table showing an example of the countermeasure candidate list according to the embodiment.

For example, it is assumed that a deterioration of a suction failure rate, which is a failure rate of sucking components through a nozzle, is recognized as a problem of the first predetermined state (eg, productivity, quality, or scrap). In this case, the trained model 33 outputs possible countermeasures, namely learning the suction position, replacing the feeding station and replacing the nozzle, and outputs a priority probability as a priority for each of the countermeasures. This allows the countermeasure determining unit 30 to be in 7 to create the countermeasure candidate list shown. In the in 7 In the countermeasure candidate list shown, suction position learning as a countermeasure candidate has a priority probability of 60% and has the highest priority among the countermeasure candidates for the suction failure rate deterioration problem. If there are candidate countermeasures with equivalent priority probabilities, the priorities can be determined based on previous results (number of countermeasure successes, changes in priority probability, etc.).

With reference to the description of the 6 Next, the countermeasure determination unit 30 lists the countermeasure candidate with the highest priority in the created countermeasure candidate list into the countermeasure priority list as a countermeasure for the detected problem (step S25). For example, if the in 7 When the countermeasure candidate list shown is created, the countermeasure of learning the suction position is entered into the countermeasure priority list for the suction failure rate deterioration problem. A variety of countermeasures to be deducted according to the condition on the production area, when a problem of deterioration of suction error rate is detected, for example: learning the suction position, replacing the feeding station and replacing the nozzle. Recording the suction position learning countermeasure by the countermeasure determination unit 30 means that the suction position learning is determined as a first priority instruction to be executed among the plurality of the countermeasures based on the priority order (priority) of each of the countermeasures.

Note that the monitoring data is repeatedly obtained at a predetermined time interval and various problems can be detected. For example, another problem may be detected before the countermeasure against a problem is completed. For example, multiple problems with the first predetermined condition (e.g., productivity, quality, or scrap) or multiple problems with the second predetermined condition (e.g., damage to a production device or a plant element or a work error by a worker) can be detected. Each time a problem is detected, a list of countermeasures against the problem is created, and the highest priority countermeasure in each countermeasure candidate list is added to the countermeasure priority list. An example of the countermeasure priority list is in 8th shown.

8th is a table showing an example of the countermeasure priority list according to the embodiment.

As in 8th shown, a countermeasure of learning the suction position is registered in the countermeasure priority list against the problem of deterioration of the suction error rate, which was previously described as a problem with the first predetermined state. In addition, the countermeasure of cleaning is included in the countermeasure priority list against the problem of poor sliding of a feeding station, which is a problem of the second predetermined state. In addition, the countermeasure of replacement is registered in the countermeasure priority list against the problem of wear of the conveyor belt, which is a problem of the second predetermined state. In addition, for each problem of the first and second predetermined states, a problem level is set in advance as an indicator of the severity of the respective problem. For example, the problem of deterioration of the suction failure rate can be regarded as a problem of the first state (the production state of the production device) when the problem is recognized. Therefore, the problem level set for the suction failure rate deterioration problem can be regarded as the problem level set for the first state when the problem is detected. In addition, e.g. For example, the problem of poor sliding of the feeding station can be considered as a problem of the second state (the state of the production resource) when the problem is detected. Therefore, the problem level set for the problem of poor feeding station sliding can be considered as a problem level to be set for the second state when the problem is detected.

Next, details of the countermeasure decision unit 40 will be described with reference to 9 described.

9 is a flowchart illustrating an example of operations of the countermeasure decision unit 40 according to the embodiment. 9 illustrates the process of making a decision (deciding) in the OODA loop.

First, the countermeasure decision unit 40 loads the countermeasure priority list (step S31) and selects the countermeasure with the highest priority (ie, the problem level) (step S32). For example, if the countermeasure priority list loaded is the one in 8th As shown in the list shown, the countermeasure decision unit 40 selects the suction position teaching as the highest priority countermeasure.

Next, the countermeasure decision unit 40 loads resource data (resource management table) from the resource database 41 (step S33). The resource management table is referred to 10 described.

10 is a table showing an example of the resource management table according to the embodiment.

For example, the resource management table manages the presence or absence of each productive resource, in particular, whether each productive resource is currently executing a particular countermeasure or whether a particular countermeasure is currently being executed for each production resource. 10 shows the presence or absence of each of the production resources as a lock that is on or off. In the in 10 The resource management table shown shows the presence and absence of head, nozzle, feed station, worker A and Worker B is managed as production resources. The head and feed station locks are currently on because certain countermeasures are being implemented. The nozzle lockout is turned off as no countermeasure is currently being taken. Workers A and B are currently not performing any countermeasures and the locks are turned off. The locks in this context may include either locks in a real space or a virtual space, or both. For example, if the removal of a feeding station, which is a locked resource, from the production device is prohibited until the lock is removed, this means a lock in a real space. In addition, prohibiting the use of the feed station, which is a locked resource, when creating or updating the production plan, means a lock in a virtual space.

With reference to the description of the 9 , next, the countermeasure decision unit 40 judges whether the production resource for the selected countermeasure is blocked (step S34). For example, assume that the countermeasure decision unit 40 selects learning the suction position. In addition, for example, it is assumed that learning the suction position is a countermeasure to be carried out by worker A. In this case, the countermeasure decision unit 40 checks the status of the lock of worker A in the loaded resource management table.

If the production resource for the selected countermeasure is blocked (Yes in step S34), the countermeasure decision unit 40 selects the countermeasure with the second highest priority (step S35) and re-executes the processes from step S33.

If the production resource for the selected countermeasure is not blocked (No in step S34), the countermeasure decision unit 40 blocks the production resource for the selected countermeasure (step S36).

Then, the countermeasure decision unit 40 judges whether the production resource is blocked for all the countermeasures included in the priority countermeasure list (step S37). If none of the production resources are blocked for all countermeasures (No in step S37), the processes of step S32 are performed again, excluding the countermeasure selected this time. If the production resources are blocked for all countermeasures (Yes in step S37), among the countermeasures for which the production resources are not blocked in the countermeasure priority list, the selected countermeasure with the highest priority order is executed.

Next, details of the command issuing unit 50, the effect judgment unit 60 and the updating unit 70 will be described with reference to 11 described.

11 is a flowchart showing an example of operations of the command issuing unit 50, the effect judgment unit 60 and the updating unit 70 according to the embodiment. 11 illustrates the processes of executing the countermeasure (action) in the OODA loop and the processes after executing the countermeasure. It should be noted that in the following examples, the case where the countermeasure selected by the countermeasure decision unit 40 against the suction error rate deterioration problem is suction position learning and the blocked production resource is worker A, as a concrete Example 1 is referred to. The case where the countermeasure against the problem of poor sliding of the feeding station selected by the countermeasure decision unit 40 is cleaning and the blocked production resource is the feeding station and the worker B is referred to as concrete example 2.

First, the command issuing unit 50 executes the countermeasure for the production resource blocked by the countermeasure decision unit 40 (step S41).

For example, in the case of concrete example 1, the command issuing unit 50 issues a first countermeasure (for example, the first priority command) that causes the worker A to perform the suction position learning. In the case of concrete example 2, the command issuing unit 50 issues a second countermeasure (e.g., the first priority command) that causes the worker B to clean the feeding station. In this way, an instruction is issued according to the countermeasure, and the instruction is executed. It should be noted that the execution of the instruction can be done manually by the worker, etc., or automatically by the production device, etc.

Next, the effect evaluation unit 60 obtains monitoring data (step S42). In particular, the effect assessment unit 60 receives monitoring data about the production status of the production device or monitoring data about the conditions of the production resources. The purpose of obtaining the monitoring data is to detect a change in the condition on the production floor due to the execution of the To check the instruction corresponding to the countermeasure, that is, to determine the effect of the instruction corresponding to the executed countermeasure. In the case of specific example 1, the effect assessment unit 60 receives, for example, monitoring data about the result of the assembly process with respect to suction. In other words, the effect judgment unit 60 monitors the tendency of error information related to the nozzle to be monitored by using the information as monitoring data. For example, in the case of specific example 2, the effect evaluation unit 60 obtains monitoring data about the state of the feeding station. In other words, the effect judgment unit 60 monitors the tendency of error information related to the feeding station to be monitored by using the information as monitoring data. For example, the effect evaluation unit 60 detects a first predetermined state and a second predetermined state using a trained model 23 or 24 as in the state monitoring unit 20.

Next, the effect judgment unit 60 judges whether a problem is detected in the first predetermined state or the second predetermined state (step S43). When a problem is detected, it can be judged that the command corresponding to the executed countermeasure is ineffective or that the command corresponding to the executed countermeasure has not yet been effective. If no problems are found, it can be judged that the instruction corresponding to the countermeasure executed is ineffective.

If no problems are detected (No in step S43), the updating unit 70 updates the trained model 33 or 34 based on the judged effect (step S44). For example, in the case of the concrete example 1, when the problem is no longer recognized, the updating unit 70 determines that the suction position learning was effective against the problem, and updates the trained model 33 to increase the priority of the suction position learning. For example, in the case of Specific Example 2, when the problem is no longer detected, the update unit 70 determines that the cleaning was effective against the problem and updates the trained model 34 to increase the priority of the cleaning.

Next, since this instruction is completed, the effect judgment unit 60 releases the production resource locked to execute this instruction (step S45). For example, in the case of concrete example 1, the locked worker A is unlocked. For example, in specific example 2, the locked worker B and the feed station are unlocked.

Next, the effect judgment unit 60 deletes the countermeasure executed according to the current instruction from the countermeasure priority list (step S46). For example, in specific example 1, learning the suction position is removed from the countermeasure priority list. For example, in specific example 2, cleaning is removed from the countermeasure priority list.

Subsequently, the effect judgment unit 60 deletes the countermeasure candidate list for the problem no longer recognized by the current instruction (step S47). For example, in the case of the concrete example 1, the problem of deterioration of the suction failure rate is no longer recognized and the countermeasures for this problem are no longer necessary, and therefore the in 7 countermeasure candidate list shown deleted. Clearing the countermeasure candidate list means the following situation: When the effect judgment unit 60 judges that the execution of the first priority instruction (suction position learning instruction) has a tendency of at least a predetermined degree of improvement for the suction error rate after the execution of the learning instruction of the suction position compared with the state (suction error rate) before the execution of the instruction for learning the suction position, the instruction output unit 50 does not output the second priority instruction (replacement of the feeding station or replacement of the nozzle), which is an instruction related to the Suction error rate was extracted, which corresponds to the instruction for learning the suction position, and which is an instruction before it is executed. In addition, the effect judgment unit 60 can also determine whether the problems listed in the countermeasure priority list persist in addition to the problem for which the countermeasure was carried out. The effect judgment unit 60 may clear the countermeasure priority list for problems that are no longer recognized other than the problem against which the countermeasure was carried out. Depending on the problems detected, the detected problems may be related to each other and an effective countermeasure against such problems may be taken.

On the other hand, if a problem is detected (Yes in step S43), the effect judgment unit 60 judges whether a timeout has occurred (step S48). In other words, the effect judging unit 60 judges whether the effect has not been judged for a predetermined time. Because there are some It may take time for the effect to occur after the command is executed, the process is carried out in step S48. The predetermined period of time is z. B. set as the time required to achieve the effect of each command. In addition, instructions that are not intended to be executed immediately, such as countermeasures added to the production plan and maintenance plan, can be unlocked when a plan to execute such instructions is made, and their effects can be assessed after the instructions are executed.

If no timeout has occurred (No in step S48), the processes in steps S42, S43 and S48 are repeated until the problem is no longer detected or a timeout occurs.

If the timeout occurs (Yes in step S48), the updating unit 70 updates the trained model 33 or 34 based on the judged effect (step S49). For example, in the case of the specific example 1, when the timeout occurred while the problem is still being detected, the updating unit 70 determines that the suction position learning was not effective against the problem and updates the trained model 33 to determine the priority of the problem Learning the suction position to reduce. For example, in the case of Specific Example 2, if the timeout occurred while the problem is still being detected, the update unit 70 determines that the cleaning was not effective against the problem and updates the trained model 34 to reduce the priority of the cleaning . In addition, if a problem has been detected but there is a trend toward improvement in the monitoring data (there is a trend equal to or less than the predetermined degree of improvement), the update unit 70 updates the trained model 34 to reflect the degree of improvement Reducing the priority to reduce.

Since this instruction is completed, the effect judgment unit 60 next releases the production resource that has been blocked from executing this instruction (step S50). For example, in the case of concrete example 1, the locked worker A is unlocked. For example, in the case of specific example 2, the locked worker B and the feeding station are unlocked.

Next, the effect judgment unit 60 deletes the countermeasure executed according to the current instruction from the countermeasure priority list (step S51). For example, in the case of specific example 1, learning the suction position is removed from the countermeasure priority list. For example, in specific example 2, cleaning is removed from the countermeasure priority list.

Next, the effect judgment unit 60 updates the countermeasure candidate list based on the problems that continue to be detected even after the current instruction is executed (step S52). Here, the update of the countermeasure candidate list in the case of the specific example 1 is discussed with reference to 12 described.

12 is a table showing an example of an updated countermeasure candidate list according to the embodiment.

For example, if the problem of deterioration of the suction error rate is still detected even when the suction position learning instruction is executed, the suction position learning countermeasure candidate is removed from the countermeasure candidate list as in 12 shown. In addition, since the creation of the in 7 Some time has already passed in the countermeasure candidate list shown, and production on the production floor has continued during the elapsed time. Therefore, the states of the feed station and nozzle have changed, and the priorities for replacing the feed station and nozzle may have changed accordingly. Therefore, the effect evaluation unit 60 can analyze the priorities and update the priorities in the countermeasure candidate list. For example, in the in 7 In the countermeasure candidate list shown, the ratio of priority (priority ratio) between replacing the feed station and replacing the nozzle is 3:1, but in the in 12 In the countermeasure candidate list shown, the ratio has changed to 2:3.

With reference to the description of the 11 Next, the effect judgment unit 60 inputs the countermeasure candidate with the highest priority in the created countermeasure candidate list into the countermeasure priority list as a countermeasure for the detected problem (step S53). For example, if one in 12 When the countermeasure candidate list shown is prepared, a countermeasure, namely replacement of the nozzle, is recorded in the countermeasure priority list against the problem of deterioration of the suction failure rate. In other words, an instruction to replace the nozzle can be issued against the problem of deterioration of the suction error rate which continues even after the suction position learning is performed.

Since the operation in step S50 and the subsequent operations are not carried out until the effect judgment unit 60 judges the effect of the executed first priority instruction (learning the suction position), this means that the instruction issuing unit 50 does not execute the second priority instruction (feeding station replacement or nozzle replacement) which is an instruction with a lower priority than the priority of the first priority instruction and is determined from a variety of countermeasures (learning the suction position, replacing the feed station and replacing the nozzle). This is because the nozzle replacement instruction is issued after suction position learning is judged to be ineffective.

Furthermore, this also means the following: The effect judgment unit 60 judges that the execution of the first priority instruction (suction position learning) has a tendency of at least a predetermined degree of improvement for the suction error rate after the execution of the suction position learning, compared to the state (suction error rate ) before executing suction position learning. The countermeasure determination unit 30 determines the second priority instruction (nozzle exchange) to be executed based on the priority order of each of the plurality of countermeasures (feed station exchange and nozzle exchange) except for learning the suction position. The command output unit 50 issues the nozzle change command. This is because the instruction of nozzle change, which has a priority order after learning the suction position with the highest priority, is issued.

This also means that when the effect judgment unit 60 cannot judge the effect for a predetermined period of time, the countermeasure determination unit 30 determines the second priority command (nozzle replacement) to be executed based on the priority of each of the countermeasures (feed station replacement and nozzle replacement). except for the first priority command (learning the suction position), and the command output unit 50 issues the command of nozzle replacement. This is because the nozzle replacement instruction, which has the highest priority among the countermeasures except suction position learning, is issued after a timeout.

It should be noted that in step S13, there may be cases where, after a problem is detected by the condition monitoring unit 20 and a countermeasure with the highest priority is recorded among the countermeasure candidates in the countermeasure priority list, the recorded countermeasure is in a low priority order in the countermeasure priority list and the production resource for the listed countermeasure may have already been blocked. In such cases, the listed countermeasure cannot be carried out immediately. In these cases, fixing other issues that were previously performed may resolve the issue corresponding to the countermeasure that was not performed. In this case, the listed countermeasure may be removed from the countermeasure priority list before it is executed, and the list of candidate countermeasures may also be deleted.

As described above, the first countermeasure and the second countermeasure are determined for executing countermeasures against the first condition and the second condition that are different from each other on the production floor. However, by deciding between the first countermeasure and the second countermeasure, an optimal first countermeasure or an optimal second countermeasure can be issued. Accordingly, the production area management system 1 according to the present invention can issue an optimal work instruction from a variety of measures to solve the problems.

Other embodiments

The production area management system 1 according to the present invention has been previously described according to the embodiment, but the present invention is not limited to the above embodiment. Various modifications of the present embodiment, as well as embodiments resulting from combinations of structural elements of the various embodiments that may be devised by those skilled in the art, may be included within the scope of the present invention as long as they do not depart from the spirit of the present invention.

For example, in the embodiment described above, an example was described in which the production area management system 1 includes an effect evaluation unit 60, an updating unit 70 and trained models 23, 34, 33 and 34, but the production area management system 1 does not need to have an effect evaluation unit 60, an updating unit 70 and no trained models 23, 34, 33 and 34.

For example, in the previously described embodiment, an example was described in which the first state is a production state production device and the second state is a state of each of the production resources, but the present invention is not limited to this example. For example, the first state and the second state may be any states if the first state and the second state are different states on the production floor.

For example, in the embodiment described above, an example has been described in which the production area management system 1 includes the detection unit 10, the condition monitoring unit 20, the countermeasure determination unit 30, the countermeasure decision unit 40, the command issuing unit 50, the effect judgment unit 60, and the updating unit 70 , but some of these units may also be included in the production device. For example, the production device may include the detection unit 10, the condition monitoring unit 20, and the countermeasure determination unit 30.

For example, an instruction corresponding to a countermeasure may include a plurality of instructions. In addition, an instruction corresponding to a countermeasure can be issued to a plurality of production devices or mobile terminals carried by a plurality of workers.

For example, the present invention can be implemented not only as a shop floor management system 1 but also as a work instruction method that includes the steps (processes) carried out by the structural elements included in the shop floor management system 1.

13 is a flowchart illustrating an example of a work instruction method according to other embodiments.

The work instruction method is a work instruction method in a shop floor management system that manages a condition on a shop floor containing a production device that produces a product. As in 13 As shown, the work instruction method includes: monitoring a first condition on the production area (step S1); monitoring a second condition on the production area (step S2), the second condition different from the first condition; determining a first countermeasure corresponding to the first condition (step S3); determining a second countermeasure corresponding to the second condition (step S4); making a decision between the first countermeasure and the second countermeasure (step S5); and issuing a command corresponding to the first countermeasure or the second countermeasure according to the decision (step S6).

The steps of the work instruction process can be carried out, for example, by a computer (computer system). The present invention can be implemented as a program that causes the computer to execute the steps contained in the work instruction method. Furthermore, the present invention may be implemented as a non-transitory, computer-readable recording medium, such as a CD-ROM, on which the program is recorded.

For example, when the present invention is implemented by a program (software), the program can be executed using hardware resources such as CPU, memory and an input/output circuit of the computer to execute each step. In other words, each step is performed by the CPU retrieving data from, for example, the memory or the input/output circuit and performing operations and outputting the results of the operations to, for example, the memory or the input/output circuit.

Furthermore, each structural element included in the production area management system 1 according to the above embodiment may be implemented as a dedicated or general-purpose circuit.

Furthermore, each structural element of the shop floor management system 1 according to the above embodiment can be implemented as an LSI (Large Scale Integration), that is, an integrated circuit (IC).

In addition, the integrated circuit is not limited to LSI, but can also be implemented by a dedicated circuit or a general-purpose processor. A field programmable gate array (FPGA) or a reconfigurable processor that allows reconfiguration of the connection or configuration of the internal circuit cells of the LSI circuit can be used after the LSI is fabricated.

If progress in semiconductor technology or advancements in other technologies produces a circuit integration technology that replaces the LSI, such a circuit integration technology may be used to integrate the structural elements of the shop floor management system 1.

Apart from the above, various modifications of the present embodiment, as well as embodiments resulting from any combinations of structural elements of the various embodiments that may be devised by those skilled in the art, may be included within the scope of the present invention as long as they do not depart from the spirit of the present invention differ.

Industrial applicability

For example, the present invention can be used to manage a production area.

Reference symbol list

1

Production area management system

2

Communication network

4

Production line

5

Management device

10

Acquisition unit

20

Condition monitoring unit

21

First condition monitoring unit

22

Second condition monitoring unit

23, 24, 33, 34

Trained model

30

Countermeasure determination unit

31

First countermeasure determination unit

32

Second countermeasure determination unit

40

Countermeasure Decision Unit

41

Resource database

50

Command output unit

60

Effect assessment unit

70

Update unit

M1

Substrate feeding device

M2

Substrate transport device

M3

Printing device

M4, M5

Mounting device

M6

Melting device

M7

Substrate collection device

Claims (14)

A production area management system that manages conditions on a production area containing a production device that produces a product, the production area management system comprising: a first condition monitoring unit configured to monitor a first condition on the production area; a first countermeasure determining unit configured to determine a first countermeasure corresponding to the first state; a second condition monitoring unit configured to monitor a second condition on the production floor, the second condition different from the first condition; a second countermeasure determining unit configured to determine a second countermeasure corresponding to the second state; a countermeasure decision unit configured to make a decision between the first countermeasure and the second countermeasure; and a command issuing unit configured to issue a command corresponding to the first countermeasure or the second countermeasure according to the decision. Production area management system in accordance with Claim 1 , wherein the monitoring of the first state by the first state monitoring unit and the determination of the first countermeasure by the first countermeasure determination unit are carried out in parallel with the monitoring of the second state by the second state monitoring unit and the determination of the second countermeasure by the second countermeasure determination unit. Production area management system in accordance with Claim 1 or 2 , wherein the countermeasure decision unit is configured to make the decision based on a problem level set for the first state corresponding to the first countermeasure and a problem level set for the second state corresponding to the second countermeasure. Production area management system in accordance with Claim 3 , wherein if there is no difference between 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, the countermeasure decision unit prioritizes the first countermeasure in the decision. Production area management system according to one of the Claims 1 until 4 , further comprising: an effect assessment unit configured to evaluate an effect of the first countermeasure or the second countermeasure that has been executed based on the first state and/or the second state before and after the execution of the first countermeasure or the second countermeasure that corresponds to the issued instruction is assessed. Production area management system according to one of the Claims 1 until 5 , wherein the first state is a production state of the production device, and the second state is a state of each of the production resources managed on the production area and used for production. Production area management system in accordance with Claim 6 , wherein the countermeasure decision unit is configured to make the decision based on the presence or absence of one or more of the production resources required for the first countermeasure or the second countermeasure. Production area management system in accordance with Claim 6 or 7 , further comprising: a first trained model for detecting a first predetermined condition occurring on the production area according to the production condition, the first condition monitoring unit being configured to detect the first predetermined condition based on the first trained model. Production area management system in accordance with Claim 8 , wherein the first condition monitoring unit is configured to detect, in a predetermined period of time, the first predetermined condition corresponding to a production indicator via at least one of the following information: production error information, production quantity information and quality information, the production error information relating to an error occurred in the production device, the Production quantity information concerns a quantity of a product produced by the production device, the quality information concerns a quality of a product produced by the production device, and the first countermeasure determining unit is configured to determine the first countermeasure including a countermeasure for improving the production indicator. Production area management system according to one of the Claims 6 until 9 , further comprising: a second trained model for detecting a second predetermined condition occurring on the production area according to the condition of each of the production resources, wherein the second condition monitoring unit is configured to detect the second predetermined condition based on the second trained model. Production area management system in accordance with Claim 10 , wherein the second state monitoring unit is configured to detect the second predetermined state corresponding to an operation indicator about the operation state of the production device included in the production resources, and the second countermeasure determination unit is configured to determine the second countermeasure including a countermeasure for the Production device is determined that corresponds to the operational indicator. Production area management system in accordance with Claim 10 or 11 , wherein the second condition monitoring unit is configured to detect the second predetermined condition corresponding to a work indicator about the work performed by a worker included in the production resources, and the second countermeasure determining unit is configured to determine the second countermeasure, which includes the worker's work that corresponds to the work indicator. A work instruction method for a production floor management system that manages conditions on a production floor that includes a production device that produces a product, the work instruction method comprising: monitoring a first condition on the production floor; monitoring a second condition on the production floor, the second condition different from the first condition; determining a first countermeasure corresponding to the first condition; determining a second countermeasure corresponding to the second condition; making a decision between the first countermeasure and the second countermeasure; and issuing a command corresponding to the first countermeasure or the second countermeasure according to the decision. Work instruction program that causes a computer to follow the work instruction procedure Claim 13 to carry out.

Images