Maintenance work notification system and maintenance work notification method

The maintenance work notification system addresses inefficiencies in equipment utilization by calculating slack time and scheduling maintenance work during downtime, enhancing operating rates through improved equipment utilization and scheduling.

JP7576748B2Active Publication Date: 2024-11-01PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
JP2023556298
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2021-10-26
Filing Date
2022-10-12
Publication Date
2024-11-01
Estimated Expiration
2042-10-12

Smart Images

  • Figure 0007576748000001
    Figure 0007576748000001
  • Figure 0007576748000002
    Figure 0007576748000002
  • Figure 0007576748000003
    Figure 0007576748000003
Patent Text Reader

Abstract

A maintenance work reporting system (100) comprises: a spare time estimation unit (122) that estimates a spare time on the basis of the number of in-progress products between pieces of equipment in an equipment group (1) that includes a plurality of pieces of equipment producing a product by sequentially executing processes assigned thereto; an executable work determination unit (123) that determines target work that is maintenance work executable in the spare time estimated by the spare time estimation unit (122); and an input / output device (130) that reports the target work and target equipment where the target work is performed.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates to a maintenance work notification system and a maintenance work notification method. [Background technology]

[0002] Patent Document 1 discloses a multi-connected module type surface mounting device in which component mounting modules are connected in multiple units to share and execute the process of mounting components on one board among the multiple component mounting modules. In this multi-connected module type surface mounting device, equipment maintenance processing is performed using the waiting time for the lapse of the mounting completion time when all component mounting modules have completed the component mounting operation. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2008-153292 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, there is still room for improvement in the above-mentioned conventional techniques in order to increase the operating rate.

[0005] Therefore, the present disclosure provides a maintenance work notification system and a maintenance work notification method that can improve the operating rate. [Means for solving the problem]

[0006] A maintenance work notification system according to one embodiment of the present disclosure includes an estimation unit that estimates a slack time based on a work-in-process quantity, which is the number of work-in-process items between pieces of equipment in a group of equipment that includes a plurality of pieces of equipment and produces products by sequentially executing processes assigned to each piece of equipment, a determination unit that determines, as target work, maintenance work that can be performed within the slack time estimated by the estimation unit, and a notification unit that notifies of the target work and the target equipment on which the target work will be performed.

[0007] A maintenance work notification method according to one aspect of the present disclosure includes the steps of estimating a slack time based on a work-in-process quantity, which is the number of work-in-process items between pieces of equipment in a group of equipment that includes a plurality of pieces of equipment and produces products by sequentially executing processes assigned to each piece of equipment, determining a maintenance work that can be performed within the estimated slack time as a target work, and notifying the target work and the target equipment on which the target work will be performed.

[0008] Moreover, one aspect of the present disclosure can be realized as a program for causing a computer to execute the maintenance work notification method. Alternatively, one aspect of the present disclosure can be realized as a computer-readable non-transitory recording medium storing the program. Effect of the Invention

[0009] According to the present disclosure, the operating rate can be improved. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram showing an example of a group of facilities to which a maintenance work notification system according to an embodiment of the present invention is applied. [Diagram 2] FIG. 2 is a diagram showing an example of a list of maintenance operations scheduled to be performed on a group of facilities. [Diagram 3] FIG. 3 is a diagram showing an example of the operation status, the work-in-process quantity, and the cumulative production quantity of a piece of equipment having a takt time difference when the maintenance work notification system according to the embodiment is not applied. [Figure 4] FIG. 4 is a diagram showing an example of the operation status, the work-in-process quantity, and the cumulative production quantity of a piece of equipment having a takt time difference when the maintenance work notification system according to the embodiment is applied. [Diagram 5] FIG. 5 is a configuration diagram of a maintenance work notification system according to an embodiment. [Figure 6] FIG. 6 is a block diagram illustrating a functional configuration of the maintenance work notification system according to the embodiment. [Figure 7]FIG. 7 is a diagram for explaining main parameters used in a first example of the process of estimating the margin of time by the maintenance work notification system according to the embodiment. [Figure 8] FIG. 8 is a diagram for explaining the relationship between the tact time difference between facilities and the number of works in progress. [Figure 9] FIG. 9 is a diagram showing an example of the margin time calculated in the first example of the margin time estimation process by the maintenance work notification system according to the embodiment. [Figure 10] FIG. 10 is a diagram for explaining main parameters used in a second example of the process of estimating the margin of time by the maintenance work notification system according to the embodiment. [Figure 11] FIG. 11 is a diagram for explaining a situation assumed in a third example of the process of estimating the margin of time by the maintenance work notification system according to the embodiment. [Figure 12] FIG. 12 is a diagram illustrating an example of input data used in a third example of the process of estimating the margin of time by the maintenance work notification system according to the embodiment. [Figure 13] FIG. 13 is a matrix table showing an example of a result of the third example of the process of estimating the margin of time by the maintenance work notification system according to the embodiment. [Figure 14] FIG. 14 is a sequence diagram showing the operation of the maintenance work notification system according to the embodiment. [Figure 15] FIG. 15 is a flowchart showing the operation of the maintenance work notification system according to the embodiment. [Figure 16] FIG. 16 is a flowchart showing pre-processing of the maintenance work notification system according to the embodiment. [Figure 17] FIG. 17 is a flowchart illustrating an example of a process of estimating a margin of time by the maintenance work notification system according to the embodiment. [Figure 18] FIG. 18 is a flowchart illustrating another example of the process of estimating the margin of time by the maintenance work notification system according to the embodiment. [Figure 19] FIG. 19 is a diagram showing an example of a notification screen of the maintenance work notification system according to the embodiment. [Figure 20] FIG. 20 is a diagram showing an example of a detailed notification screen in the maintenance work notification system according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] (Summary of the Disclosure) A maintenance work notification system according to one embodiment of the present disclosure includes an estimation unit that estimates a slack time based on a work-in-process quantity, which is the number of work-in-process items between pieces of equipment in a group of equipment that includes a plurality of pieces of equipment and produces products by sequentially executing processes assigned to each piece of equipment, a determination unit that determines, as target work, maintenance work that can be performed within the slack time estimated by the estimation unit, and a notification unit that notifies of the target work and the target equipment on which the target work will be performed.

[0012] Work in progress between facilities occurs mainly due to the difference in takt time between facilities. When the number of work in progress exceeds a certain number, a short-term standby (temporary stop) of the facility occurs, which is called a "choco stop." According to the maintenance work notification system according to the present embodiment, the number of work in progress is used to estimate the slack time.

[0013] The slack time is, for example, time that has little impact on the number of products produced and can be used for equipment maintenance. Since the maintenance work that can be performed within the slack time and the target equipment are notified, workers can perform the maintenance work promptly. For example, maintenance work that was scheduled for regular maintenance of a group of equipment can be performed in advance by using the slack time. This makes it possible to shorten the time for regular maintenance and increase the operating time. In this way, short periods of waiting are suppressed and maintenance work can be performed efficiently by using the slack time, so the operating rate of the group of equipment can be increased. Furthermore, since the number of works in process, which changes dynamically depending on the operating status of the group of equipment, is used, notifications of maintenance work can be appropriately made depending on changes in the operating status of the group of equipment.

[0014] Also, for example, the determination unit may determine the target work by referring to a work list indicating a plurality of maintenance works that have not yet been performed and the work time for each maintenance work.

[0015] This allows the workers to perform the necessary maintenance work efficiently without omissions.

[0016] Furthermore, for example, the determination unit may determine, as the target work, a maintenance work of the plurality of maintenance works, the maintenance work having a work time equal to or less than the margin of time and having the longest operating time of the group of facilities.

[0017] This maximizes the operating time of the equipment group, thereby further increasing the operating rate of the equipment group.

[0018] As an example, the determination unit may determine, as the target work, the maintenance work whose operation time is equal to or less than the slack time and is the longest among the plurality of maintenance works. As a result, the maintenance work that will result in the longest operation time of the equipment group can be determined as the target work. In this case, the time required for regular maintenance can be further shortened by performing the maintenance work that requires a long operation time during the slack time. By shortening the time required for regular maintenance, the operation rate of the equipment group can be further increased.

[0019] Also, for example, the system may further include an update unit that updates the task list when the target task is completed so that the target task becomes an executed task.

[0020] This makes it possible to avoid being notified again of maintenance work that has already been performed.

[0021] Also, for example, the estimation unit may estimate the slack time when a change in the number of works in progress or a stoppage of at least one of the plurality of pieces of equipment is detected.

[0022] In a group of equipment, the stoppage of one piece of equipment may affect the other pieces of equipment. In other words, it may become necessary to stop other pieces of equipment as well, and maintenance work may be performed during this stoppage. Therefore, by estimating the slack time when an increase or decrease in the number of pieces of work in process or a stoppage of equipment is detected, the accuracy of the estimation of the slack time can be improved, which contributes to improving the operating rate.

[0023] Furthermore, for example, the plurality of pieces of equipment may include a first piece of equipment and a second piece of equipment that performs a process after the first piece of equipment, and the estimation unit may acquire a first work-in-process quantity that is the number of pieces of work-in-process at a first time between the first piece of equipment and the second piece of equipment, calculate a second work-in-process quantity that is the number of pieces of work-in-process at a second time after the first time between the first piece of equipment and the second piece of equipment based on the first work-in-process quantity and each of the takt times of the first piece of equipment and the second piece of equipment, and calculate, as the slack time, a time until the work-in-process between the first piece of equipment and the second time is depleted and the first piece of equipment is restarted based on the second work-in-process quantity and each of the takt times of the first piece of equipment and the second piece of equipment.

[0024] This allows slack time to be estimated based on the number of work-in-process units in the future (for example, a few minutes from now), making it possible to avoid situations where maintenance work must be started immediately and ensure time for work preparation, such as moving workers, before the start of maintenance work. Since maintenance work can be performed with ample time, the accuracy of the maintenance work increases, contributing to improved operation rates.

[0025] Also, for example, the plurality of pieces of equipment may include a first piece of equipment and a second piece of equipment that performs a process after the first piece of equipment, and when a stop of the second piece of equipment is detected, the estimation unit may acquire a first work-in-process quantity that is the work-in-process quantity between the first piece of equipment and the second piece of equipment, and calculate, as the slack time, a time until the work-in-process goods between the first piece of equipment and the second piece of equipment are depleted and the first piece of equipment is resumed, based on the first work-in-process quantity, the takt time of each of the first piece of equipment and the second piece of equipment, and the mean recovery time of the second piece of equipment.

[0026] This allows maintenance work to be carried out on equipment by effectively utilizing downtime of other equipment, thereby increasing the operating rate.

[0027] Also, for example, the estimation unit may calculate the slack time further based on a time required for the work-in-progress to move from the first facility to the second facility.

[0028] This makes it possible to improve the accuracy of estimating slack time by taking into account the time it takes to move work-in-progress between facilities, thereby contributing to improved operating rates.

[0029] Furthermore, for example, the estimation unit may calculate the slack time further based on a time required to restart the first equipment.

[0030] This makes it possible to improve the accuracy of estimating the slack time by taking into account the time required to restart the equipment, which contributes to improving the operating rate.

[0031] Also, for example, the estimation unit may estimate the slack time using machine learning.

[0032] This makes it possible to improve the accuracy of estimating slack time through machine learning, which contributes to improving operation rates. For example, by modeling the effects between multiple pieces of equipment through machine learning, it is possible to accurately grasp the effect on other pieces of equipment when one piece of equipment is stopped for maintenance work.

[0033] Furthermore, for example, the estimation unit may use machine learning to calculate an expected value of the operating time of each piece of equipment for each combination of the plurality of pieces of equipment and one or more stoppage times of each piece of equipment, determine the stoppage time of the combination that results in the highest expected value of the operating time as the slack time, and the notification unit may notify the equipment of the combination that results in the highest expected value of the operating time as the target equipment.

[0034] This makes it possible to further improve the operating rate.

[0035] In addition, a maintenance work notification method according to one aspect of the present disclosure includes the steps of estimating a slack time based on a work-in-process quantity, which is the number of work-in-process items between pieces of equipment in a group of equipment that includes a plurality of pieces of equipment and produces products by sequentially executing processes assigned to each piece of equipment, determining a maintenance work that can be performed within the estimated slack time as a target work, and notifying the target work and the target equipment on which the target work will be performed.

[0036] This makes it possible to increase the availability of the facility group, similarly to the above-mentioned maintenance work notification system.

[0037] A program according to an aspect of the present disclosure is a program for causing a computer to execute the maintenance work notification method according to the above aspect.

[0038] This makes it possible to increase the availability of the facility group, similarly to the above-mentioned maintenance work notification system.

[0039] Hereinafter, the embodiment will be specifically described with reference to the drawings.

[0040] The embodiments described below are all comprehensive or specific examples. The numerical values, shapes, materials, components, component arrangements and connection forms, steps, and order of steps shown in the following embodiments are merely examples and are not intended to limit the present disclosure. Furthermore, among the components in the following embodiments, components that are not described in the independent claims are described as optional components.

[0041] In addition, each figure is a schematic diagram and is not necessarily illustrated precisely. Therefore, for example, the scales in each figure do not necessarily match. In addition, in each figure, substantially the same configurations are given the same reference numerals, and duplicated explanations are omitted or simplified.

[0042] (Embodiment) [1. Equipment group] First, a group of facilities to which the maintenance work notification system according to the embodiment is applied will be described with reference to FIG.

[0043] Fig. 1 is a diagram showing a facility group 1 to which a maintenance work notification system according to an embodiment is applied. As shown in Fig. 1, the facility group 1 includes a plurality of facilities 10a, 10b, 10c, ..., 10x. The facility group 1 produces products by having each facility sequentially execute the process assigned to it. The facility group 1 is, for example, a component mounting system, a component assembly system, etc. Each facility is a component mounter, an assembly device, an inspection device, etc.

[0044] Equipment 10a, 10b, 10c, ..., 10x are connected in this order to form one production line. Equipment 10a is the first equipment, and equipment 10x is the last equipment. One product is manufactured by each equipment performing a specific process in this order, from equipment 10a to equipment 10x.

[0045] Each piece of equipment is connected, for example, via a conveying device (not shown) arranged between the pieces of equipment. The conveying device conveys work-in-progress after a predetermined process has been carried out at one piece of equipment to the next piece of equipment. The conveying device is, for example, a belt conveyor, but may also be a robot arm or an autonomous mobile robot. The number of pieces of equipment included in the equipment group 1 that are connected is 2 or more, for example, 40 or more, but is not limited to this.

[0046] As shown in Fig. 1, work-in-progress storage areas 20a, 20b, and 20c are provided between the facilities. The work-in-progress storage area 20a is a space for storing the work-in-progress 30a output from the facility 10a. The work-in-progress storage area 20b is a space for storing the work-in-progress 30b output from the facility 10b. The work-in-progress storage area 20c is a space for storing the work-in-progress 30c output from the facility 10c. Although not shown in Fig. 1, there is also a work-in-progress storage area in front of the facility 10x.

[0047] Each of the work-in-progress storage areas 20a, 20b, and 20c has a limit on the number of work-in-progress items (= work-in-progress quantity) that can be stored. That is, a maximum work-in-progress quantity is set for each work-in-progress storage area. The maximum work-in-progress quantity for each work-in-progress storage area may be the same as or different from each other. The maximum work-in-progress quantity may be one or more, but may also be zero. That is, there may be facilities between which no work-in-progress storage area is provided.

[0048] Maintenance work for each piece of equipment is important in the equipment group 1 configured as above. By efficiently performing the necessary maintenance work for each piece of equipment, the operating rate of the equipment group 1 can be increased.

[0049] FIG. 2 is a diagram showing an example of a list of maintenance work (hereinafter referred to as a work list) scheduled to be performed on the group of facilities 1. The work list shows a number of maintenance work tasks that have not yet been performed and the work time for each maintenance work. The work list is generated in advance by, for example, a manager of the group of facilities 1. The work time can be determined based on, for example, the execution history of past maintenance work.

[0050] The work list shown in Figure 2 is categorized into a "minimum maintenance" list and a "quality improvement maintenance" list according to the importance of the maintenance work. The "minimum maintenance" list shows a list of maintenance work that must be performed. The "quality improvement maintenance" list shows a list of maintenance work that should be performed in order to improve the quality of the product. Note that such a classification according to importance does not have to be made.

[0051] As shown in Fig. 2, the work list lists the equipment to be maintained, the content of the maintenance work, and the time required for the maintenance work in association with each other. For example, "Equipment A Cleaning 5 minutes" at the top indicates that the maintenance work "cleaning" will be performed for "equipment A" (i.e., equipment 10a in Fig. 1), which is the target equipment, in "5 minutes."

[0052] 2 shows a list of tasks to be performed in one day, but the period covered by the task list is not limited to one day. The task list may show maintenance tasks to be performed within an hour, or may show maintenance tasks to be performed in a week or a month.

[0053] [2. Facility operation rate] Next, the availability rate of the facility group 1 depending on whether or not the maintenance work notification system according to the present embodiment is applied will be described with an example.

[0054] [2-1. When not applicable] Fig. 3 is a diagram showing an example of the operation status, work-in-process quantity, and cumulative production quantity of equipment with a takt time difference when the maintenance work notification system according to this embodiment is not applied. For simplicity, Fig. 3 shows an example in which a product is produced by two linked pieces of equipment A and B. Equipment B is the equipment immediately following equipment A. In other words, equipment B processes the work-in-process goods output from equipment A. The same applies to Fig. 4 described later.

[0055] There is a difference in takt time between equipment A and equipment B. Takt time (also simply called "takt") is the time it takes for equipment to process one work-in-progress item. In this embodiment, the takt time can be estimated for each piece of equipment by machine learning using artificial intelligence (AI).

[0056] 3, the takt time Ta of equipment A is shorter than the takt time Tb of equipment B. Therefore, when equipment A and B are operating normally, work in progress gradually accumulates between equipment A and equipment B, so the number of work in progress between equipment A and B increases monotonically.

[0057] As mentioned above, there is a limit to the number of work-in-progress that can be stored, so when the number of work-in-progress between equipment A and B reaches the maximum number of work-in-progress Ymax (time t1), equipment A will have to wait for equipment B to process it. When equipment B processes the work-in-progress and there is space in the work-in-progress storage area, equipment A will process again and output the work-in-progress, but due to the takt difference, the number of work-in-progress between equipment A and B will again reach the maximum number of work-in-progress Ymax in a relatively short period of time and will go into standby. In this way, after time t1, equipment A will alternate between short periods of standby (so-called "momentary stop") and operation. The number of work-in-progress between equipment A and B will remain approximately constant after time t1.

[0058] In Figure 3, at time t2, equipment B stops due to a certain factor. Because equipment B stops, it is unable to process the work-in-process between equipment A and B, so equipment A also waits until equipment B restarts and the number of work-in-process between equipment A and B decreases. At time t3, equipment B restarts and processes the work-in-process between equipment A and B, thereby decreasing the number of work-in-process. At this time, equipment A waits until the number of work-in-process decreases by a certain amount, and then restarts at time t4.

[0059] After that, at time t5, equipment A is stopped for routine maintenance. In routine maintenance, multiple maintenance tasks are performed as shown in the task list in Fig. 2. For example, as shown in Fig. 3, four maintenance tasks A to D are performed, which requires at least W+X+Y+Z seconds.

[0060] During the period when regular maintenance is being performed on equipment A, equipment B processes the work in progress between equipment A and B. At time t6, the number of works in progress between equipment A and B becomes 0, and equipment B also stops.

[0061] The cumulative production number increases monotonically while equipment B is in operation, and remains constant without increasing while equipment B is stopped. In the example shown in FIG. 3, the cumulative production number finally becomes Z1 at time t7.

[0062] 3, equipment A has to wait for equipment B. In addition, equipment B has to stop when equipment A is undergoing regular maintenance. As such, neither equipment A nor B can ensure sufficient operating time, resulting in a problem of low operating rate of equipment group 1.

[0063] [2-2. When applicable] Fig. 4 is a diagram showing an example of the operation status, work in progress, and cumulative production volume of equipment with a takt time difference when the maintenance work notification system according to the present embodiment is applied. Note that the takt time of each of equipment A and B shown in Fig. 4, and various conditions such as the maximum work in progress between the equipment, are the same as the example shown in Fig. 3.

[0064] Although details will be described later, the maintenance work notification system according to this embodiment estimates slack time based on the number of pieces of work in progress between pieces of equipment. Slack time is time that has little impact on the number of products produced and is time that can be used for maintenance work on equipment. Since the maintenance work that can be performed within the slack time and the target equipment are notified, workers can quickly carry out the maintenance work, thereby increasing the operating rate.

[0065] Specifically, as shown in FIG. 4, when the maintenance work notification system 100 is applied, time for special maintenance is secured before regular maintenance so that equipment A does not have to wait for a short period of time (so-called "short stop"). For example, equipment A needs to wait at time t1, but this waiting period is secured as a special maintenance period (for example, maintenance A is performed) until time t11. During this period, equipment B processes work-in-progress, so the number of work-in-progress between equipment A and B gradually decreases, and there is more space in the work-in-progress storage area. Therefore, even if equipment A resumes operation from time t11, a long time is secured until the maximum number of work-in-progress Ymax is reached.

[0066] Similarly, the period from time t2 to t4 and the period from time t12 to t13 caused by the stoppage of equipment B can be secured as special maintenance periods (for example, performing maintenance B and C, respectively). This reduces the amount of maintenance work to be performed in the regular maintenance, so the start of the regular maintenance can be delayed to time t14.

[0067] In this way, the standby time of equipment A is reduced, and the time for regular maintenance can also be shortened. This makes it possible to prevent the stoppage of equipment B, and to increase the operating rate. For example, in the example shown in FIG. 4, the cumulative production number finally becomes Z2 at time t7, which is more than Z1 in the example of FIG. 3.

[0068] The maintenance work notification system according to this embodiment can prevent short-term waiting periods by estimating the slack time for performing the temporary maintenance work shown in FIG. 4 based on the work-in-process quantity. Furthermore, maintenance work scheduled for regular maintenance of the equipment group 1 can be performed in advance by utilizing the slack time. This makes it possible to shorten the time for regular maintenance and to increase the operation time. In this way, short-term waiting periods are prevented and maintenance work can be performed efficiently by utilizing the slack time, thereby increasing the operation rate of the equipment group.

[0069] [3. Configuration] The configuration of the maintenance work notification system according to this embodiment will be described below with reference to FIGS.

[0070] Fig. 5 is a configuration diagram of the maintenance work notification system 100 according to this embodiment. Fig. 6 is a block diagram showing the functional configuration of the maintenance work notification system 100 according to this embodiment.

[0071] 5, the maintenance work notification system 100 includes a group of equipment 1, a storage device 110, a processing device 120, and an input / output device 130. The group of equipment 1, the storage device 110, the processing device 120, and the input / output device 130 are communicatively connected via a network. Communication between the devices is performed via wire and / or wireless.

[0072] 1, the equipment group 1 includes a plurality of pieces of equipment. Although not shown, the equipment group 1 also includes a plurality of sensors. The plurality of sensors are provided in each piece of equipment and in conveying devices between the pieces of equipment, and measure the operating status, work-in-process quantity, etc. of the equipment. The sensor data (measured values) obtained by each sensor through measurement are stored in the storage device 110.

[0073] [3-1.Storage device] The storage device 110 stores data used in arithmetic processing by the processing device 120. The storage device 110 is a non-volatile storage device such as a hard disk drive (HDD) or a solid state drive (SDD).

[0074] As shown in FIG. 6, the storage device 110 stores a product database 111, an equipment characteristic value database 112, an equipment state database 113, a maintenance work history database 114, and a maintenance schedule database 115.

[0075] The product database 111 is a database that accumulates information related to products manufactured by the equipment group 1. Specifically, the product database 111 stores the type, number, and processing time of work-in-progress for each piece of equipment included in the equipment group 1. The type, number, and processing time are each acquired by a sensor provided in the corresponding piece of equipment.

[0076] The equipment characteristic value database 112 is a database that accumulates characteristic values ​​(hereinafter, referred to as equipment characteristic values) for each piece of equipment included in the equipment group 1. The equipment characteristic values ​​are characteristic values ​​that are determined in advance for each piece of equipment. Specifically, the equipment characteristic values ​​include the takt time of the target equipment, the maximum number of pieces of work in progress between the target equipment and the equipment immediately following it, the movement time of work in progress between the target equipment and the equipment immediately following it, the preparation time (restart time) required to restart the target equipment, and the mean time to repair (MTTR) for each abnormality (error) that may occur in the target equipment.

[0077] The takt time is obtained by machine learning using AI. The maximum work-in-process is a value that is set when the equipment is installed. The travel time, restart time, and MTTR are values ​​that are calculated based on the measurements by the sensors. These equipment-specific values ​​are not values ​​that change in real time, but values ​​that do not change over a long period of time (e.g., one day to several months). The equipment-specific values ​​may be updated when the configuration of the equipment group 1 is changed (e.g., when the equipment is replaced). Here, an example is shown in which five types of equipment-specific values ​​are used, but the type and number of the equipment-specific values ​​are not particularly limited. For example, the equipment-specific values ​​do not need to include the travel time, restart time, and MTTR.

[0078] The equipment status database 113 is a database that accumulates status information for each piece of equipment included in the equipment group 1. The status information is information that can change in real time depending on the status of each piece of equipment. Specifically, the status information is the recording time of the target equipment, the number of works in process between the target equipment and the equipment immediately following it, and the status value of the equipment (operating or stopped). The recording time, the number of works in process, and the status value are each obtained by measurement using a sensor. The recording time is the time when a trigger such as a change in the number of works in process or a stop due to an abnormality occurs. Here, an example is shown in which three types of status information are used, but the type and number of status information are not particularly limited as long as the status information includes the number of works in process.

[0079] The maintenance work history database 114 is a database that accumulates history data of maintenance work performed in the past. The history data includes maintenance work execution history information for each piece of equipment included in the equipment group 1. Specifically, the execution history information includes the work time of the maintenance work, the person who performed the maintenance work (performer), and the person who can perform the maintenance work (personnel information). The work time, the performer, and the personnel information are obtained via the input / output device 130.

[0080] The maintenance schedule database 115 is a database that accumulates scheduled data for maintenance work. The scheduled data is generated based on a maintenance work plan, and specifically includes a work list shown in Fig. 2. The scheduled data is obtained by a manager or worker of the equipment group 1 inputting the data via an input device or an input / output device 130 associated with the processing device 120.

[0081] [3-2. Processing equipment] The processing device 120 is an arithmetic device that performs main processing of the maintenance work notification system 100. The processing device 120 is, for example, a computer device equipped with a processor and a memory. The processor reads out and executes a program stored in the memory to perform predetermined processing. At least a part of the processing performed by the processing device 120 may be executed by a dedicated circuit.

[0082] Furthermore, the processing device 120 may be connected to an input device that accepts a predetermined input from a user such as a system administrator, and an output device that outputs a processing result. As the input device, various input devices such as a mouse, a keyboard, a microphone, a touch panel, etc. may be used. As the output device, various output devices such as a display device, an audio output device, etc. The input device and the output device may be integrated, for example, like a touch panel display.

[0083] As shown in FIG. 6, the processing device 120 includes a takt time estimating unit 121, a slack time estimating unit 122, an executable work determining unit 123, and a maintenance schedule updating unit .

[0084] The takt time estimation unit 121 estimates the takt time for each piece of equipment. Specifically, the takt time estimation unit 121 estimates the takt time for each piece of equipment by performing machine learning using AI with manufacturing log data. The takt time is the average time required to perform the process assigned to the target piece of equipment on one work-in-progress item.

[0085] The slack time estimation unit 122 estimates the slack time based on the number of works in process between the facilities. In this embodiment, the slack time estimation unit 122 estimates the slack time when a change in the number of works in process or a stoppage of at least one of the facilities included in the facility group 1 is detected. In other words, a change in the number of works in process or a stoppage of a facility is a trigger for estimating the slack time. A specific method for estimating the slack time will be described later.

[0086] The executable work determination unit 123 is an example of a determination unit that determines a maintenance work that can be performed within the margin time as a target work. The executable work determination unit 123 determines the target work by referring to the work list stored in the maintenance schedule database 115. For example, the executable work determination unit 123 determines, as the target work, a maintenance work whose work time is equal to or less than the margin time and whose operation time of the equipment group 1 is the longest among the multiple maintenance works indicated in the work list. The maintenance work whose operation time of the equipment group 1 is the longest is, for example, a maintenance work whose work time is equal to or less than the margin time and whose operation time is the longest among the multiple maintenance works indicated in the work list.

[0087] When the target work is completed, the maintenance schedule update unit 124 updates the work list so that the target work becomes a completed work. Completion of the target work is determined based on information input by the input / output device 130.

[0088] For example, when a target task is completed, the maintenance schedule update unit 124 deletes the target task from the task list. Alternatively, the task list may be associated with flag information indicating whether or not the task has been performed for each task. When a target task is completed, the maintenance schedule update unit 124 may change the flag information to "performed."

[0089] In this embodiment, the maintenance schedule update unit 124 also updates the contents of the maintenance work history database 114. Specifically, the maintenance schedule update unit 124 records the target work in the maintenance work history database 114 as a work that has been performed.

[0090] [3-3. Input / Output Devices] The input / output device 130 is, for example, a mobile terminal carried by a worker performing maintenance work. Specifically, the input / output device 130 is a tablet terminal or a smartphone. Since the input / output device 130 is portable, notifications to the worker and input from the worker can be performed smoothly and efficiently.

[0091] The input / output device 130 is an example of a notification unit that notifies the user of the target work and the target equipment on which the target work will be performed. The input / output device 130 may further notify the user of the start time or the time until the start of the target work. Specifically, the input / output device 130 includes a touch panel display that displays images or videos. The input / output device 130 generates a notification screen (notification image) indicating the target work and the target equipment determined by the executable work determination unit 123, and displays the notification screen on the touch panel display. A specific example of the notification screen will be described later.

[0092] Furthermore, the input / output device 130 accepts input from an operator. Specifically, the input / output device 130 generates an input screen (input image) including GUI (Graphical User Interface) objects that can be operated by the operator, and displays the input screen on the touch panel display. The input / output device 130 accepts operations via the input screen, and transmits information indicating the accepted contents to the maintenance schedule update unit 124.

[0093] The notification is made visually by an image displayed on a display, but is not limited to this. The input / output device 130 may include a speaker and / or a vibrator. As a result, the notification may be made audibly by a sound output from the speaker. Vibration or the like may also be used in combination. The input / output device 130 may also include a microphone and receive input by voice.

[0094] There may be provided a plurality of input / output devices 130. For example, when there are a plurality of workers, an input / output device 130 is provided for each worker. This allows notifications to be sent to the workers and input from the workers to be performed smoothly and efficiently, and allows maintenance work to be performed more efficiently.

[0095] For example, the input / output device 130 may be realized by two or more devices each having an input function and a notification function separately. For example, a display device for making a notification may be realized by a large monitor in a factory in which the equipment group 1 is arranged. Also, each piece of equipment included in the equipment group 1 may be provided with a physical button or a touch panel for inputting the completion of maintenance work. In this way, the input / output device 130 may be a stationary terminal device instead of a mobile terminal.

[0096] Furthermore, the configuration of the maintenance work notification system 100 is not limited to the example shown in Fig. 5. For example, the storage device 110, the processing device 120, and the input / output device 130 may be integrated into one device. Also, for example, the processing device 120 may not include the takt time estimation unit 121 and the maintenance schedule update unit 124.

[0097] [4. Estimation of slack time] Next, a specific example of the slack time estimation process will be described.

[0098] [4-1. Example 1] First, the process of estimating slack time that is performed when a change occurs in the number of works in progress will be described with reference to FIGS.

[0099] Fig. 7 is a diagram for explaining main parameters used in a first example of the slack time estimation process by the maintenance work notification system 100 according to the present embodiment. For simplicity, as in Figs. 3 and 4, an example is shown in which a product is produced by two connected pieces of equipment A and B.

[0100] Equipment A is an example of a first equipment. Equipment B is an example of a second equipment that executes a process after the first equipment. Specifically, equipment B is the equipment immediately following equipment A. In other words, equipment B processes the work-in-progress output from equipment A.

[0101] 7, the takt time of facility A is Ta, and the takt time of facility B is Tb. Ta and Tb are estimated by the takt time estimation unit 121 and stored in the equipment characteristic value database 112. Furthermore, the movement time of the work-in-progress is Tm, and the time required to restart facility A is Tr. Both Tm and Tr are stored in the equipment characteristic value database 112 as equipment characteristic values.

[0102] In the first example, the slack time estimation unit 122 acquires the current work-in-process quantity Y. Here, the present is an example of a first time, and the work-in-process quantity Y is an example of a first work-in-process quantity. The "present" corresponds to the timing at which the slack time is estimated, and specifically, is the time at which the latest value of the work-in-process quantity between equipment A and B stored in the equipment status database 113 is acquired.

[0103] The slack time estimation unit 122 calculates the number of works in process Yx X minutes later based on the following formula (1) using Y, Ta, and Tb. Here, X minutes later is an example of a second time later than the first time, and the number of works in process Yx is an example of the second number of works in process.

[0104] (1) Yx=Y+int{abs(Tb-Ta)×X / Ta}

[0105] Note that int{} is a function that returns the integer value of the number in {}. abs() is a function that returns the absolute value of the number in ( ).

[0106] Next, the margin estimation unit 122 calculates the margin Mt based on the following formula (2) using Yx, Ta, Tb, Tm, and Tr.

[0107] (2) Mt = Yx × Tb - (Tr + Ta + Tm)

[0108] In formula (2), slack time Mt is considered to be the time until the work-in-progress between equipment A and B is cleared and equipment A is restarted. Yx×Tb on the right hand side of formula (2) is the time until all work-in-progress is processed. Also, Tr+Ta+Tm is the time until the first work-in-progress reaches equipment B after equipment A is restarted. Note that restart time Tr and travel time Tm may be omitted, as there may be cases where they are sufficiently small compared to the takt time.

[0109] The calculated slack time Mt is the time during which equipment A can be stopped without reducing productivity if it is stopped X minutes from now. When the work-in-process quantity Yx exceeds the maximum work-in-process quantity Ymax, the slack time estimation unit 122 calculates the slack time Mt by replacing Yx with Ymax in formula (2). In this case, the work-in-process quantity Y will reach the maximum work-in-process quantity Ymax by the time X minutes has passed, so equipment A may have to wait.

[0110] When the work-in-process quantity Yx exceeds the maximum work-in-process quantity Ymax, the slack time estimation unit 122 may change the value of X to a smaller value and recalculate Yx and Mt. Alternatively, the slack time estimation unit 122 may replace Yx in formula (1) with Ymax and calculate X using X as a variable. In other words, the slack time estimation unit 122 may calculate the time X until the work-in-process quantity Y matches the maximum work-in-process quantity Ymax, and then calculate the slack time Mt. This makes it possible to prevent equipment A from having to wait.

[0111] The predetermined or calculated time X can be regarded as the time until the start of the maintenance work. Therefore, the slack time estimation unit 122 can calculate the start time of the maintenance work based on the current time and X.

[0112] An example of calculating the margin time Mt will be described below using specific numerical values.

[0113] Fig. 8 is a diagram for explaining the relationship between the tact difference between facilities and the work-in-process quantity. Fig. 9 is a diagram showing an example of a slack time calculated in a first example of a slack time estimation process by the maintenance work notification system according to the embodiment.

[0114] 8 and 9, the takt time Ta of facility A is 1.0 sec, the takt time Tb of facility B is 2.0 sec, the restart time Tr of facility A is 5.0 sec, and the movement time Tm of work-in-progress between facilities A and B is 2.0 sec. Also, the maximum number of work-in-progress Ymax between facilities A and B is 30.

[0115] As shown in FIG. 8, when both equipment A and B are operating normally, the work-in-process quantity Y between equipment A and B increases by one every two seconds due to the tact time difference between equipment A and B. When the work-in-process quantity Y matches the maximum work-in-process quantity Ymax, equipment A is put on temporary standby. After that, equipment A repeats production and temporary standby. This is the same as the situation described using FIG. 3. The operating rates of equipment A and B can be increased by securing a margin of time for emergency maintenance at the time when the work-in-process quantity Y reaches the maximum work-in-process quantity Ymax or before this time.

[0116] As shown in Figure 9, when equipment A is stopped for emergency maintenance, the work-in-process quantity Y decreases by one every two seconds. When the remaining work-in-process quantity Y is four (i.e., there are eight seconds remaining until the work-in-process quantity Y reaches zero), equipment A will resume operation over the course of five seconds. Equipment A will begin reproduction and output work-in-process items from the three seconds remaining until the work-in-process quantity Y reaches zero. Because it takes two seconds to move a work-in-process item, the reproduced work-in-process item will reach equipment B before the work-in-process quantity Y reaches zero and equipment B goes into standby, allowing equipment B to continue processing.

[0117] In this way, in order to ensure that neither equipment A nor B has to wait and to ensure the longest maintenance time, maintenance work should begin when the work-in-process quantity Y reaches the maximum work-in-process quantity Ymax, and the first work-in-process quantity after restarting equipment B should reach the same time that the work-in-process quantity reaches 0. In this case, the slack time Mt available for maintenance work is when the work-in-process quantity Y reaches the maximum work-in-process quantity Ymax=30, so based on formula (2), it is 30×2.0-(5.0+1.0+2.0)=52 seconds.

[0118] [4-2. Example 2] Next, the process of estimating the slack time that is performed when a stop of equipment is detected will be described with reference to Fig. 10. Note that the description of the same matters as in the first example will be omitted or simplified.

[0119] Fig. 10 is a diagram for explaining main parameters used in a second example of the slack time estimation process by the maintenance work notification system 100 according to the embodiment. For simplicity, Fig. 10 shows an example in which a product is produced by two connected pieces of equipment A and B, similar to Fig. 7.

[0120] The example shown in Fig. 10 shows a case where an abnormal stop occurs in equipment B. Y, Ta, Tb, Tr, and Tm are the same as those in the example shown in Fig. 7. The mean recovery time of equipment B is Tmttr. Tmttr is stored in the equipment characteristic value database 112 as an equipment characteristic value.

[0121] In the second example, the slack time estimation unit 122 acquires the current work-in-progress quantity Y. Next, the slack time estimation unit 122 calculates the slack time Mt based on the following formula (3) using Y, Ta, Tb, Tm, Tr, and Tmttr.

[0122] (3) Mt = Y × Tb + Tmttr - (Tr + Ta + Tm)

[0123] Y×Tb on the right side of equation (3) is the time it takes to process all of the current work-in-progress. Also, Tr+Ta+Tm is the time it takes from restarting equipment A until the first work-in-progress arrives at equipment B. Note that the restart time Tr and travel time Tm may be omitted, as they may be sufficiently small compared to the takt time.

[0124] If an abnormal shutdown of equipment B occurs, the time until equipment B is restored (Tmttr) can be used for extra maintenance work on other equipment. For this reason, as shown in formula (3), the term Tmttr is added to the slack time Mt compared to formula (2). This makes it possible to calculate the slack time Mt with high accuracy by taking Tmttr into account.

[0125] [4-3. Third Example] Next, the process of estimating slack time using machine learning will be described with reference to Fig. 11 to Fig. 13. Note that the description of the same matters as in the first and second examples will be omitted or simplified.

[0126] Fig. 11 is a diagram for explaining a situation assumed in a third example of the slack time estimation process by the maintenance work notification system 100 according to this embodiment. When multiple pieces of equipment are linked, as shown in Fig. 11, the stoppage of one piece of equipment (e.g., equipment B) may affect equipment other than the equipment immediately before or after it. Similarly, a change in the number of in-process items between pieces of equipment (e.g., between equipment B and C) may affect equipment other than the equipment before and after it.

[0127] In this example, the slack time estimation unit 122 uses machine learning to calculate an expected value of the operation time of each piece of equipment for each combination of multiple pieces of equipment and one or more downtimes of each piece of equipment. The slack time estimation unit 122 determines the downtime of the combination that results in the highest expected value of the operation time as the slack time.

[0128] Fig. 12 is a diagram showing an example of input data used in a third example of slack time estimation processing by the maintenance work notification system 100 according to the embodiment. As shown in Fig. 12, the input data includes takt time, current work-in-process quantity, current operation status, maximum work-in-process quantity, movement time of work-in-process between facilities, restart time of facilities, and restart time of stop code (MTTR). Each of these is data for each facility or for each space between facilities. The slack time estimation unit 122 uses an estimation model that uses at least one of the input data shown in Fig. 12 as an explanatory variable and operation time as a response variable.

[0129] The estimation model is, for example, a regression model based on Bayesian estimation, but is not limited thereto. The machine learning method is not particularly limited. For example, as a supervised learning method, a method using a classifier, a method using a support vector machine, a decision tree method, a deep convolutional neural network method, etc. can be used.

[0130] Fig. 13 is a matrix table showing an example of the result of the third example of the slack time estimation process by the maintenance work notification system 100 according to this embodiment. In the matrix table shown in Fig. 13, a plurality of pieces of equipment constituting the equipment group 1 are arranged in the column direction (vertical axis), and a plurality of downtimes are arranged in the row direction (horizontal axis). An expected value of the operating time output from the estimation model is associated with each combination of equipment and downtime.

[0131] The slack time estimation unit 122 extracts the combination that results in the longest operation time from the matrix table. In the example shown in Fig. 13, the combination of "equipment F" and "50 seconds" is the combination that results in the longest operation time. Therefore, "equipment F" can be determined as the target equipment, and "50 seconds" can be determined as the slack time Mt.

[0132] At this time, the slack time estimation unit 122 may determine multiple combinations of slack time and target equipment. For example, the slack time estimation unit 122 may select multiple combinations in descending order starting from the combination that has the longest operating time, and assign priorities to each of them. This allows multiple target tasks to be notified in a list together with their priorities.

[0133] [5. Operation (maintenance work notification method)] Next, the operation of the maintenance work notification system 100 according to this embodiment will be described.

[0134] [5-1. Main processing] First, the main processing of the maintenance work notification system 100 will be described with reference to FIGS.

[0135] Fig. 14 is a sequence diagram showing the operation of the maintenance work notification system 100 according to this embodiment. Fig. 15 is a flowchart showing the operation of the maintenance work notification system 100 according to this embodiment.

[0136] 14 and 15, first, in the equipment group 1, various sensors measure the amount of work in progress and the equipment status, and output the sensor data obtained by the measurement to the storage device 110. The storage device 110 stores the sensor data output from the equipment group 1 as real-time data (S10). The real-time data is stored, for example, in an equipment status database 113. Note that part of the sensor data may be stored in a product database 111 and an equipment specific value database 112 as product-related information and equipment specific values.

[0137] Next, in the processing device 120, the slack time estimation unit 122 acquires equipment status data from the equipment status database 113 in the storage device 110 (S11). The equipment status data includes at least the number of pieces of work in progress for each piece of equipment. In this embodiment, the equipment status data further includes a status value (operating or stopped) for each piece of equipment.

[0138] Next, in the processing device 120, the slack time estimation unit 122 judges whether or not at least one of a change in the number of in-process items and a stoppage of equipment has been detected (S12). If neither has been detected, that is, if a trigger to start the slack time estimation process has not occurred (No in S12), the process is repeated from step S10.

[0139] When at least one of a change in the number of items in process and a stop of the equipment is detected (Yes in S12), the slack time estimation unit 122 acquires equipment characteristic value data from the equipment characteristic value database 112 in the storage device 110 (S13). Then, the slack time estimation unit 122 estimates the slack time based on the equipment characteristic value and the equipment state (specifically, the number of items in process) (S14). At this time, if an abnormal stop of the equipment occurs, the slack time estimation unit 122 estimates the slack time further based on the cause of the stop. A specific flow of the slack time estimation process will be described later.

[0140] Next, the executable work determination unit 123 acquires maintenance history data from the maintenance work history database 114 of the storage device 110, acquires maintenance schedule data from the maintenance schedule database 115, and generates a work list. For example, the executable work determination unit 123 determines a plurality of maintenance works to be performed based on the maintenance schedule data, and determines the work time for each of the determined maintenance works based on the maintenance history data. The work list itself may be stored in the maintenance schedule database 115 of the storage device 110.

[0141] The executable work determination unit 123 determines executable maintenance work based on the generated work list (S15). Specifically, the executable work determination unit 123 determines whether there is any maintenance work that can be performed within the estimated margin time. If there is no maintenance work that can be performed within the margin time (No in S15), the process is repeated from step S10. If there is one or more maintenance work that can be performed within the margin time, one of them is determined as the target work (Yes in S15). For example, the executable work determination unit 123 determines as the target work the maintenance work whose operation time is equal to or less than the margin time and is the longest.

[0142] At this time, the target work to be determined may be two or more maintenance works. For example, if the total of the work times of a plurality of maintenance works falls within the margin time, the executable work determination unit 123 may determine the plurality of maintenance works as the target work. At this time, the plurality of maintenance works that have the longest total work time may be determined.

[0143] The maintenance history data acquired by the executable work determination unit 123 is used, for example, to calculate the work time. When the work time is calculated in advance and stored in the maintenance schedule database 115, the executable work determination unit 123 does not need to acquire the maintenance history data.

[0144] Next, when the target work has been determined (Yes in S15), the executable work determination unit 123 notifies the I / O device 130 of the determined target work and target equipment (S16). Based on the received notification, the I / O device 130 generates a notification screen for the worker and displays it on the display. In this way, the worker is notified.

[0145] The worker performs the maintenance work according to the notification. When the maintenance work is completed, the worker inputs the fact that the notified maintenance work is completed via the I / O device 130. The processing device 120 waits until it receives a notification from the I / O device 130 (No in S17). Next, in the processing device 120, after receiving the work completion notification from the I / O device 130 (Yes in S17), the maintenance schedule update unit 124 updates the maintenance history and the work list (S18). Specifically, the maintenance schedule update unit 124 registers the work time required for the target work, the worker who performed the target work, and the like in the maintenance work history database 114 of the storage device 110. In addition, the maintenance schedule update unit 124 deletes the target work from the work list in the maintenance schedule database 115 of the storage device 110.

[0146] The above process is repeated in real time while the equipment group 1 is in operation. When time can be secured to perform temporary maintenance work based on the amount of work in process between the equipment, the target work and the target equipment are notified, so that the worker can perform the maintenance work promptly. Since the standby period of each equipment is shortened and the time for regular maintenance is also shortened, the operating rate of the equipment group 1 can be increased.

[0147] [5-2. Estimation of takt time] Next, the process of estimating the takt time by the takt time estimating unit 121 of the processing device 120 will be described with reference to Fig. 16. The process of estimating the takt time is performed as a pre-processing before the execution of the main processes shown in Figs.

[0148] Fig. 16 is a flowchart showing the pre-processing of the maintenance work notification system 100 according to this embodiment. The pre-processing shown in Fig. 16 is performed on a relatively long cycle, for example, once a month. The timing of performing the pre-processing is not particularly limited, and the pre-processing may be performed once or multiple times a day or week, or may be performed when a predetermined event occurs, such as replacement of equipment.

[0149] 16, in the processing device 120, the takt time estimation unit 121 acquires period data from the storage device 110 (S20). The period data is production log data for a predetermined period. The production log data is stored in, for example, the product database 111, and includes the type of product, the number of products, and the processing time per product for each processed product (work in progress).

[0150] Next, the takt time estimation unit 121 generates a takt time estimation model by machine learning (S21). The takt time estimation model is, for example, created for each piece of equipment, and is a learning model for estimating the takt time for each piece of equipment.

[0151] The takt time estimation model is, for example, a regression model based on Bayesian estimation, but is not limited thereto. The machine learning method is not particularly limited. For example, as a supervised learning method, a method using a classifier, a method using a support vector machine, a decision tree method, a deep convolutional neural network method, etc. can be used.

[0152] Next, the takt time estimation unit 121 evaluates the generated takt time estimation model (S22). Specifically, the takt time estimation unit 121 calculates the accuracy of the estimated value of the takt time by the takt time estimation model. The model is generally evaluated using a method for evaluating a model generated by machine learning.

[0153] If the accuracy of the estimated value is less than the threshold (No in S23), the takt time estimator 121 returns to step S21 and regenerates the takt time estimation model by changing the parameters or adding learning data to be used, etc. Model generation and evaluation are repeated until an estimated value with the desired accuracy is obtained.

[0154] If the accuracy of the estimated value is equal to or greater than the threshold (Yes in S23), the takt time estimation unit 121 stores the generated takt time estimation model in the equipment specific value database 112 of the storage device 110 (S24). Note that the takt time for each piece of equipment may be stored in the storage device 110 instead of the estimation model.

[0155] As described above, by using machine learning, it is possible to estimate the takt time with a desired degree of accuracy for a wide variety of equipment and product types. Note that the estimation process of the takt time is not limited to the machine learning method, and may be performed by statistical processing or the like.

[0156] [5-3. Estimation of slack time (S14)] Next, the estimation process of the slack time will be described with reference to Fig. 17 and Fig. 18. As described above, there are three examples, the first example to the third example, of the estimation process of the slack time. The slack time estimation unit 122 estimates the slack time using at least one of the first example to the third example.

[0157] Fig. 17 is a flowchart showing an example of the process of estimating the margin time by the maintenance work notification system 100 according to the present embodiment. Fig. 17 shows an example in which the first example and the second example are used together.

[0158] 17, when there is no equipment that has abnormally stopped (No in S30), the slack time estimation unit 122 performs slack time estimation processing according to the first example (S31). That is, the slack time estimation unit 122 calculates the work-in-process quantity Yx after X minutes based on the formula (1), and calculates the slack time Mt based on the calculated work-in-process quantity Yx and formula (2).

[0159] If there is any equipment that has abnormally stopped (Yes in S30), the process of estimating the margin time according to the second example is performed (S32). That is, the margin time estimation unit 122 calculates the margin time Mt based on the formula (3).

[0160] After step S31 or S32 is performed, the slack time estimation unit 122 outputs the calculated slack time Mt to the executable task determination unit 123 (S33).

[0161] In this way, the margin estimation unit 122 can switch the estimation method of the margin Mt depending on whether or not there is any equipment that has stopped abnormally.

[0162] Alternatively, the slack time estimation unit 122 may estimate the slack time based on the third example as shown in Fig. 18. Fig. 18 is a flowchart showing another example of the slack time estimation process performed by the maintenance work notification system 100 according to the present embodiment.

[0163] As shown in Fig. 18, the slack time estimation unit 122 performs machine learning to calculate an expected value of operation time for each combination of equipment and downtime (S41). Then, the slack time estimation unit 122 generates a matrix table as shown in Fig. 13 (S42). The slack time estimation unit 122 extracts a combination that has the highest expected value of operation time from the matrix table (S43). Next, the slack time estimation unit 122 outputs the equipment and time of the extracted combination as target equipment and target time, respectively (S44).

[0164] It is also possible to combine all of the first to third examples. For example, the leeway time calculated in step S31 or S32 shown in Fig. 17 may be used as the combined stop time used in the calculation in step S41 in Fig. 18.

[0165] [6.Notification screen] Next, a specific example of a notification screen displayed on the display by the input / output device 130 will be described.

[0166] 19 is a diagram showing an example of a notification screen by the maintenance work notification system 100 according to this embodiment. A notification screen 200 is displayed on the display of the input / output device 130.

[0167] As shown in Fig. 19, a notification screen 200 shows a list of a plurality of maintenance works to be notified to a worker. The names of the equipment to be subjected to the maintenance works are associated with the priority order of the maintenance works. The names of the equipment to be subjected to the maintenance works function as selection buttons 201, 202, ..., 2XX that can be selected by the worker. For example, when the worker selects the selection button 201, a detailed notification screen 300 shown in Fig. 20 is displayed on the input / output device 130.

[0168] FIG. 20 is a diagram showing an example of a detailed notification screen by the maintenance work notification system 100 according to this embodiment. The detailed notification screen 300 includes the start time of the work, the target equipment, and the work content. By looking at the detailed notification screen 300, a worker can easily understand when, on which equipment, and what work should be done. Note that the contents included in the detailed notification screen 300 are not limited to these. The detailed notification screen 300 may also include a map showing the location of the target equipment, work procedures, and the like.

[0169] The detail notification screen 300 also includes a completion button 301 that can be selected by the worker. When the worker selects the completion button 301, the input / output device 130 outputs a completion notification indicating that the target work on the target equipment has been completed to the processing device 120. This makes it possible to easily notify the processing device 120 of the completion of the maintenance work, and to update the work list.

[0170] The notification screen shown on the display is not limited to the examples shown in Fig. 19 and Fig. 20. When only one target work and one target piece of equipment are to be determined, the notification screen 200 shown in Fig. 19 does not need to be displayed. Even when there are multiple target works and multiple pieces of equipment, the notification screen 200 may display the work content and work time, as well as a completion button 301, instead of the selection buttons 201, 202, ..., 2XX.

[0171] (Other embodiments) Although the maintenance work notification system and the maintenance work notification method according to one or more aspects have been described based on the embodiments, the present disclosure is not limited to these embodiments. As long as they do not deviate from the gist of the present disclosure, various modifications conceived by a person skilled in the art to the present embodiment and forms constructed by combining components in different embodiments are also included within the scope of the present disclosure.

[0172] Furthermore, the communication method between the devices described in the above embodiment is not particularly limited. When wireless communication is performed between the devices, the wireless communication method (communication standard) is, for example, short-distance wireless communication such as ZigBee (registered trademark), Bluetooth (registered trademark), or wireless LAN (Local Area Network). Alternatively, the wireless communication method (communication standard) may be communication via a wide area communication network such as the Internet. Furthermore, wired communication may be performed between the devices instead of wireless communication. Specifically, the wired communication is communication using power line communication (PLC) or a wired LAN.

[0173] In the above embodiment, the process executed by a specific processing unit may be executed by another processing unit. The order of multiple processes may be changed, or multiple processes may be executed in parallel. The allocation of components provided in the maintenance work notification system to multiple devices is one example. For example, components provided in one device may be provided in another device. The maintenance work notification system may be realized as a single device.

[0174] For example, the processes described in the above embodiments may be realized by centralized processing using a single device (system), or may be realized by distributed processing using multiple devices. Also, the processor that executes the above programs may be single or multiple. That is, centralized processing or distributed processing may be performed.

[0175] In the above embodiment, all or part of the components such as the control unit may be configured with dedicated hardware, or may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU (Central Processing Unit) or a processor reading and executing a software program recorded on a recording medium such as a HDD (Hard Disk Drive) or a semiconductor memory.

[0176] Furthermore, components such as the control unit may be configured with one or more electronic circuits. Each of the one or more electronic circuits may be a general-purpose circuit or a dedicated circuit.

[0177] The one or more electronic circuits may include, for example, a semiconductor device, an integrated circuit (IC), or a large scale integration (LSI). The IC or LSI may be integrated into one chip or into multiple chips. Here, the IC or LSI is referred to as an IC or LSI, but the name may vary depending on the degree of integration, and may be called a system LSI, a very large scale integration (VLSI), or an ultra large scale integration (ULSI). Also, a field programmable gate array (FPGA) that is programmed after the LSI is manufactured can be used for the same purpose.

[0178] In addition, the general or specific aspects of the present disclosure may be realized as a system, an apparatus, a method, an integrated circuit, or a computer program. Alternatively, the present disclosure may be realized as a computer-readable non-transitory recording medium such as an optical disk, a HDD, or a semiconductor memory in which the computer program is stored. Furthermore, the present disclosure may be realized as any combination of a system, an apparatus, a method, an integrated circuit, a computer program, and a recording medium.

[0179] Furthermore, each of the above embodiments can be modified, substituted, added, omitted, and the like in various ways within the scope of the claims or their equivalents. [Industrial Applicability]

[0180] The present disclosure can be used as a maintenance work notification system that can increase the operating rate, and can be used, for example, in manufacturing equipment management systems, worker personnel management systems, and manufacturing systems. [Explanation of symbols]

[0181] 1 equipment group 10a, 10b, 10c, 10x equipment 20a, 20b, 20c Work in progress storage area 30a, 30b, 30c Work in progress 100 Maintenance Work Notification System 110 Storage device 111 Product Database 112 Equipment characteristic value database 113 Equipment Status Database 114 Maintenance work history database 115 Maintenance Schedule Database 120 Processing equipment 121 Takt time estimation unit 122 Marginal time estimation unit 123 Executable Work Judgment Unit 124 Maintenance Schedule Update Section 130 I / O Devices 200 Notification screen 201, 202 selection button 300 Detailed notification screen 301 Complete button

Claims

1. an estimation unit that estimates a slack time based on a work-in-process quantity, which is the number of work-in-process items between facilities in a facility group that includes a plurality of facilities and produces products by sequentially executing processes assigned to each of the facilities; a determination unit that determines, as a target maintenance work, a maintenance work that can be performed within the margin time estimated by the estimation unit; A notification unit that notifies the target work and the target equipment on which the target work is performed. Maintenance work notification system.

2. the determination unit determines the target work by referring to a work list indicating a plurality of maintenance works that have not yet been performed and a work time for each maintenance work; The maintenance work notification system according to claim 1 .

3. the determination unit determines, as the target work, a maintenance work having a work time equal to or less than the margin of time and having the longest operating time of the group of facilities, among the plurality of maintenance works; The maintenance work notification system according to claim 2 .

4. and an update unit that updates the task list when the target task is completed so that the target task becomes an executed task. The maintenance work notification system according to claim 2 .

5. The estimation unit estimates the slack time when a change in the work-in-process quantity or a stoppage of at least one of the plurality of facilities is detected. The maintenance work notification system according to any one of claims 1 to 4.

6. The plurality of facilities include a first facility and a second facility that performs a process subsequent to the first facility, The estimation unit is A first work-in-process quantity is obtained, which is a work-in-process quantity at a first time between the first facility and the second facility; calculating a second work-in-process quantity, which is the work-in-process quantity at a second time after the first time, between the first facility and the second facility based on the first work-in-process quantity and each of the takt times of the first facility and the second facility; calculating, based on the second work-in-process quantity and the takt times of the first equipment and the second equipment, a time period from the first equipment to the second time when the work-in-process is exhausted and the first equipment is restarted, as the slack time; The maintenance work notification system according to any one of claims 1 to 4.

7. The plurality of facilities include a first facility and a second facility that performs a process subsequent to the first facility, When a stop of the second equipment is detected, the estimation unit A first in-process quantity is obtained, which is a quantity of in-process between the first facility and the second facility; calculating, as the slack time, a time until the first equipment is restarted after the work-in-process between the first equipment and the second equipment is cleared based on the first work-in-process quantity, the takt time of each of the first equipment and the second equipment, and the mean recovery time of the second equipment; The maintenance work notification system according to any one of claims 1 to 4.

8. The estimation unit calculates the slack time further based on a time required for the work-in-progress to move from the first facility to the second facility. The maintenance work notification system according to claim 6.

9. The estimation unit calculates the margin time further based on a time required to restart the first equipment. The maintenance work notification system according to claim 6.

10. The estimation unit estimates the slack time using machine learning. The maintenance work notification system according to any one of claims 1 to 4.

11. The estimation unit is Using machine learning, calculate an expected value of the operation time of each piece of equipment for each combination of the plurality of pieces of equipment and one or more downtimes of each piece of equipment; determining a downtime of a combination that maximizes an expected value of the operating time as the surplus time; The notification unit notifies, as the target equipment, a combination of equipment that has the highest expected value of the operating time. The maintenance work notification system according to claim 10.

12. A step of estimating a slack time based on a work-in-process quantity, which is the number of work-in-process items between facilities in a facility group including a plurality of facilities, each of which produces a product by sequentially executing a process assigned to each facility; determining, as a target maintenance task, a maintenance task that can be performed within the estimated margin of time; Notifying the target work and the target equipment on which the target work is performed. Maintenance work notification method.

13. A program causing a computer to execute the maintenance work notification method according to claim 12.

Citation Information

Patent Citations

  • Stop time scheduling system for manufacturing device

    JP1997285948A

  • Multiple-connected module surface mounter, and multiple-connected surface mounting system

    JP2008153292A

  • Production activity support system

    JP2020102244A

  • Maintenance schedule creation program, maintenance schedule creation method, and maintenance schedule creation device

    JP2021064255A

  • JPP2978778B