Information processing program, information processing method, and information processing device

Abstract

An information processing device (100) acquires, for a plurality of devices (a-c) that each handle differing tasks from among a plurality of tasks (A-C) which form a target flow, a deadline for performing a replacement task that involves stopping part or all of the target flow. The information processing device (100) calculates a first cost in accordance with the remaining life of each device (a-c) in a case where the replacement task is performed in a time prior to the deadline, for each device (a-c). The information processing device (100) calculates a second cost in accordance with the stoppage period of the target flow in a case where the replacement task is performed in a time prior to the deadline, for each device (a-c). The information processing device (100) uses multi-objective optimization in which the first cost is a first objective function and the second cost is a second objective function, to calculate one or more combinations of times to perform the replacement task for each of the devices (a-c).

Description

[Technical Field]

[0001] The present invention relates to an information processing program, an information processing method, and an information processing device. [Background technology]

[0002] In the past, there have been cases where it was desirable to replace one of a plurality of machine tools forming a production line that produces a large number of products as the machine tool deteriorated, and in this case, the production line had to be stopped in order to replace the machine tool.

[0003] Prior art includes, for example, a technology for visually creating a maintenance plan using failure risks calculated from the elapsed time since the start of use of target equipment or parts and the usage status of parts, and maintenance costs such as part costs and downtime losses. Also, for example, there is a technology for collecting dynamic data from multiple sensors on a robot and determining the timing of maintenance or optimization, thereby minimizing downtime by eliminating unnecessary replacement of robot components and minimizing maintenance costs. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2009-217718 [Patent Document 2] Japanese Patent Application Laid-Open No. 2016-100026 Summary of the Invention [Problem to be solved by the invention]

[0005] However, with conventional techniques, it is difficult to determine when to replace machine tools in order to minimize losses for producers. For example, there is a tendency for each machine tool to be replaced at a different time, which means that the production line must be stopped each time a machine tool is replaced, leading to a decrease in product production volume and increased losses for producers. For example, if the types of machine tools are different, the progression of deterioration over time for each machine tool will differ, which will result in different replacement times for each machine tool, which will require the production line to be stopped at different times, which will likely increase losses for producers.

[0006] In one aspect, the present invention aims to suggest an appropriate timing for replacement taking into consideration the remaining lifespan of each device on the target flow and the effect of replacement of each device on stopping the target flow. [Means for solving the problem]

[0007] According to one embodiment, an information processing program, an information processing method, and an information processing device are proposed that obtain a deadline for performing replacement work that involves stopping the target flow for each of multiple devices that are responsible for different tasks among multiple tasks that form the target flow, and perform multi-objective optimization using a first objective function related to a first cost that corresponds to the remaining lifespan of each device if the replacement work is performed for each device before the deadline, and a second objective function related to a second cost that corresponds to the duration of the target flow being stopped due to each of the replacement tasks if the replacement work is performed for each device before the deadline, thereby calculating one or more combinations of times to perform the replacement work for each of the devices, and outputting the one or more calculated combinations. [Effects of the Invention]

[0008] According to one aspect, it is possible to present an appropriate timing for replacement taking into consideration the remaining lifespan of each device on the target flow and the effect of stopping the target flow due to replacement of each device. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is an explanatory diagram illustrating an example of an information processing method according to an embodiment. [Figure 2] FIG. 2 is an explanatory diagram illustrating an example of an information processing system. [Figure 3] FIG. 3 is a block diagram illustrating an example of the hardware configuration of an information processing device. [Figure 4] FIG. 4 is an explanatory diagram showing an example of the contents stored in the machine tool state information table. [Figure 5] FIG. 5 is an explanatory diagram of an example of the contents stored in the maintenance information table. [Figure 6] FIG. 6 is an explanatory diagram of an example of the contents stored in the line arrangement information table. [Figure 7] FIG. 7 is a diagram illustrating an example of the contents stored in the machine tool location information table. [Figure 8] FIG. 8 is a block diagram showing an example of the hardware configuration of a machine tool. [Figure 9] FIG. 9 is a block diagram illustrating an example of the hardware configuration of the client device. [Figure 10] FIG. 10 is a block diagram illustrating an example of a functional configuration of an information processing device. [Figure 11] FIG. 11 is a functional block diagram showing a first operation example of the information processing device. [Figure 12] FIG. 12 is an explanatory diagram of an example of calculation of loss costs due to planned line stoppages. [Figure 13] FIG. 13 is an explanatory diagram showing an example of the replacement timing optimized by multi-objective optimization. [Figure 14] FIG. 14 is a diagram showing a selection screen for a maintenance plan output by the information processing device. [Figure 15] FIG. 15 is a diagram showing a detailed screen of the maintenance plan output by the information processing device. [Figure 16] FIG. 16 is a diagram for explaining the comparison between the prior art and the embodiment regarding the influence of planned shutdown. [Figure 17] FIG. 17 is a functional block diagram showing a second operation example of the information processing device. [Figure 18] FIG. 18 is a flowchart illustrating an example of the overall processing procedure. [Figure 19] FIG. 19 is a flowchart showing an example of detailed steps of a process for generating a prediction model of remaining life. [Figure 20] FIG. 20 is a flowchart showing an example of detailed steps of the remaining life prediction process. [Figure 21] FIG. 21 is a flowchart showing an example of detailed steps for creating a plurality of maintenance plan proposals. DETAILED DESCRIPTION OF THE INVENTION

[0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an information processing program, an information processing method, and an information processing device according to embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0011] (An example of an information processing method according to an embodiment) 1 is an explanatory diagram showing an example of an information processing method according to an embodiment. An information processing device 100 is, for example, a server, a PC (Personal Computer), or a cloud on a network.

[0012] The information processing device 100 creates a maintenance plan indicating the timing of replacement work involving the suspension of all or part of the target flow for each of multiple devices 110 that are arranged on the target flow and each perform different tasks. The information processing device 100 creates a maintenance plan that optimizes the replacement timing for each of the multiple devices 110 and presents it to the user in an easy-to-understand manner.

[0013] The information processing device 100 processes, as a target flow, for example, a production line in which a plurality of devices 110 assemble different parts to produce products. The plurality of devices 110 are, for example, machine tools. In the following description, the term "devices 110" is also specifically described as the "machine tools 110" on the production line. The production line serializes the product assembly process and the arrangement of the machine tools 110, and produces products on an assembly line.

[0014] The information processing device 100 outputs a maintenance plan indicating the timing of replacement work that will involve the shutdown of the entire production line or part of the line on which the machine tools 110 are installed, before a failure occurs due to aging or other reasons of the multiple machine tools 110. The replacement work is performed on the entire device 110 or on part of a component such as an operating unit that constitutes the device 110, and either type of replacement will involve the shutdown of the device 110. For this reason, the term "device 110" described below will also include "components of the device 110."

[0015] The information processing device 100 acquires information regarding the deadline for performing replacement work that involves stopping all or part of the target flow for multiple machine tools 110 arranged on a production line. For example, the information processing device 100 acquires measurement data measured by sensors provided on each machine tool 110 as information regarding the deadline. The measurement data is data indicating the operation, status, etc., that can be used for maintenance such as failure or replacement of the machine tool 110.

[0016] In the example shown in Fig. 1, different devices 110 are arranged for each task included in the multiple tasks. Device a performs predetermined task A on a product on the product's production line, device b performs predetermined task B, and device c performs predetermined task C. Devices a to c on the production line are not limited to a line connection configuration in which they are connected in a straight line, and there are also line connection configurations in which they branch or are joined along the way. When device c at the end of the production line completes task C, the product becomes ready for shipment.

[0017] Here, the costs incurred due to the stoppage of the production line include the cost of products not being able to be produced due to the stoppage of the machine tool 110, and the cost of machine tool 110 parts, part replacement costs related to the part replacement work and the remaining useful life of the parts. For part replacement costs, for example, predictive maintenance technology can be used, which identifies or predicts the deterioration state of the machine tool 110 and performs maintenance as needed. This predictive maintenance predicts the replacement timing of parts for each machine tool 110 on the production line, making it possible to make the most of each part compared to periodic maintenance. Making the most of each part makes it possible to reduce part replacement costs.

[0018] Conventional technology makes it possible to predict the replacement timing of parts for individual machine tools 110 and reduce the cost of part replacement. However, conventional technology does not take into account the replacement timing of parts for each machine tool 110 in a production line made up of multiple machine tools 110. Furthermore, because it does not take into account the fact that multiple machine tools 110 are arranged on the same production line, when multiple machine tools 110 are stopped for replacement, the production line will be stopped multiple times accordingly, increasing the number of times the production line is stopped.

[0019] A production line may have various line connection configurations, such as multiple partial lines branching or joining along the way. Furthermore, multiple machine tools 110 may be arranged on each partial line, resulting in various line connection configurations. The prior art does not take such various line connection configurations into consideration. Therefore, in the prior art, if parts are replaced at the predicted replacement intervals for each individual machine tool 110, the number of machines that are stopped increases, which in turn increases the number of maintenance operations for part replacement, resulting in lower production costs. Furthermore, the entire production line may also be stopped, which would prevent products from being manufactured and increase loss costs.

[0020] Therefore, in this embodiment, we will explain an information processing method that can create and output a maintenance plan that takes into account not only the replacement costs of individual machine tools 110 on the production line, but also the impact of the production line being stopped due to replacement.

[0021] The information processing device 100 performs the following processes.

[0022] (1-1) Calculation process of remaining life of machine tool 110 The information processing device 100 acquires information relating to the deadline for replacing the machine tool 110 or the parts of the machine tool 110 from each of the multiple machine tools 110, and calculates the remaining lifespan of the multiple machine tools 110. For example, the information processing device 100 acquires measurement data measured by each sensor of the machine tools 110, and calculates the remaining lifespan of the multiple machine tools 110 based on the acquired measurement data. The remaining lifespan represents, for example, the remaining usable time until the machine tool 110 or parts of the machine tool 110 reach their lifespan limit at which they can operate stably without breaking down.

[0023] Furthermore, the information processing device 100 may calculate the deadline using a learning model. For example, the information processing device 100 acquires measurement data measured in the past by sensors provided on each machine tool 110 and the time when replacement work for each machine tool 110 was previously performed. For each machine tool 110, the information processing device 100 learns a model that outputs a deadline for performing replacement work for the machine tool 110 in response to input of the measurement data. For each machine tool 110, the information processing device 100 uses the learned model to calculate a deadline for performing replacement work based on the measurement data. The measurement data measured by the sensor indicates a sensor value corresponding to a change in the operating state of the machine tool 110 over time, and the information processing device 100 can predict a deadline corresponding to the life of the machine tool 110 based on the fluctuation state of the sensor value of this measurement data. Furthermore, the information processing device 100 may calculate the remaining life based on the difference between the life limit (endurance time) set for the machine tool 110 and the predicted deadline.

[0024] (1-2) Maintenance plan creation process The information processing device 100 creates a maintenance plan from the calculated remaining lifespan. The information processing device 100 calculates multiple times for replacing the machine tool 110 or parts of the machine tool 110 as the maintenance plan.

[0025] The information processing device 100 calculates one or more combinations of timings for performing replacement work for each machine tool 110 as a plurality of maintenance plans and presents them to the user. For example, the information processing device 100 performs multi-objective optimization using a first objective function and a second objective function to calculate one or more combinations of timings for performing replacement work that form the maintenance plan.

[0026] (1-2-1) Setting process of the first objective function for replacing the machine tool 110 The information processing device 100 sets a first objective function including an equation for a first cost according to the remaining life of each machine tool 110, assuming that an accelerated replacement work is carried out before the remaining life is reached, for each machine tool 110. For example, the information processing device 100 sets the sum of the part replacement cost and the loss cost for each machine tool 110 as the first cost.

[0027] The part replacement cost is the cost of procuring new parts when replacing machine tool 110 or parts of machine tool 110. The loss cost corresponds to the loss of value when a part with remaining life is removed before the end of its life. For example, the information processing device 100 sets the loss cost due to early removal using the following formula (1).

[0028] Loss cost due to early repair = Part cost × (Predicted remaining life / Elapsed time + Predicted remaining life) (1)

[0029] In the embodiment, based on the fact that the remaining lifespan of parts replacement varies depending on the usage status of each machine tool 110, the information processing device 100 sets the loss cost due to early part replacement, including the remaining lifespan, and includes the loss cost in the first cost.

[0030] (1-2-2) Setting process of the second objective function for replacing the machine tool 110 The information processing device 100 sets a second objective function including an equation for a second cost corresponding to the period of shutdown of all or part of the production line caused by each replacement work, assuming that the replacement work is carried out before the deadline for each machine tool 110. For example, the information processing device 100 sets, as the second cost, the total cost of losses caused by the stoppage of production when planned shutdown of production on the production line is caused by each replacement work in the line connection configuration indicated by the production line.

[0031] Planned shutdown, also known as planned downtime, refers to a planned shutdown of the production line for maintenance of the machine tool 110. In contrast, unplanned downtime refers to an unexpected line shutdown due to a breakdown of the machine tool 110 or the like.

[0032] (1-2-3) Optimization process for the combination of the first and second costs The information processing device 100 calculates one or more combinations of timings for carrying out replacement work for each machine tool 110 as a plurality of maintenance plans, and presents them to the user.

[0033] For example, the information processing device 100 performs multi-objective optimization using a first objective function and a second objective function to calculate one or more combinations of timings for performing replacement work to form a maintenance plan.

[0034] By using this multi-objective optimization, the information processing device 100 narrows down the infinite combinations of timings for carrying out replacement work for a combination of multiple machine tools 110 to candidate combinations for a maintenance plan and presents them to the user.

[0035] For example, as shown in (1-2-1), the information processing device 100 sets the first objective function to the first cost corresponding to the remaining life of each machine tool 110 when replacement work is performed for each machine tool 110 before the remaining life is reached.

[0036] For example, as shown in (1-2-2), the information processing device 100 sets the second objective function to the second cost corresponding to the period of shutdown of all or part of the production line due to each replacement work when replacement work is performed on each machine tool 110 before the remaining life of the machine tool 110 is reached.

[0037] The information processing device 100 performs multi-objective optimization using a first objective function and a second objective function to calculate one or more optimal combinations of timings for performing replacement work for each machine tool 110. The information processing device 100 calculates, for example, a Pareto solution. Through multi-objective optimization, the information processing device 100 considers both the cost of replacing parts for the machine tool 110 and the cost of losses due to planned shutdowns of the production line, narrows down the replacement timings, and calculates a plurality of optimized replacement timings.

[0038] There is a trade-off between the cost of replacing parts and the cost of losses due to planned shutdowns of the production line. The information processing device 100 presents a maintenance plan for multiple replacement periods, which has a relationship between the cost of replacing parts and the cost of losses due to planned shutdowns of the production line, in a form that is easy for the user to understand.

[0039] (1-3) User submission of maintenance plan The information processing device 100 presents and outputs a maintenance plan for the production line to the user's client device 150. For example, the information processing device 100 creates a maintenance plan for a two-month maintenance period based on an input of a maintenance period for the production line by a user operation of the client device 150, and displays and outputs the maintenance plan to the client device 150.

[0040] The information processing device 100 displays, for example, the trade-off relationship for each machine tool 110 arranged on the production line using a characteristic curve of a Pareto solution. The information processing device 100 displays, on the client device 150, information on the characteristic curve of the Pareto solution, for example, with the vertical axis representing the part replacement cost and the horizontal axis representing the loss cost due to the planned stoppage of the production line.

[0041] The information processing device 100 displays and outputs a guide regarding the trade-off between the part replacement cost when replacement is performed at each point and the loss cost due to planned shutdown of the production line for each point indicating a combination of multiple replacement times located on the characteristic curve of the Pareto solution. For example, the information processing device 100 displays and outputs information regarding the advantages and disadvantages of the part replacement cost and the loss cost due to planned shutdown of the production line for each point as a guide regarding the trade-off on the client device 150, allowing the user to intuitively understand.

[0042] Furthermore, when the user selects one of a plurality of replacement timing points located on the characteristic curve of the Pareto solution displayed on the client device 150, the information processing device 100 displays and outputs a specific maintenance plan corresponding to the selected point. For example, the information processing device 100 displays the timing for replacement stoppage of each machine tool 110 on the production line, the machine tools 110 that will be stopped for replacement ahead of schedule, and a display indicating that the replacement stoppage will be brought forward.

[0043] In this way, the information processing device 100 according to the embodiment creates a maintenance plan that takes into account the impact of stopping the production line due to part replacement, as well as the part replacement cost for each machine tool 110 on the production line, and presents the plan to the user. The information processing device 100 also presents to the user, as a maintenance plan, a specific trade-off between the part replacement cost and the loss cost due to the planned stoppage of the production line, allowing the user to understand the advantages and disadvantages of each replacement timing. This allows the user to appropriately and easily determine the replacement timing for each machine tool 110 using the maintenance plan presented by the information processing device 100.

[0044] (An example of an information processing system) Next, an example of an information processing system to which the information processing device shown in FIG. 1 is applied will be described with reference to FIG.

[0045] Fig. 2 is an explanatory diagram showing an example of an information processing system. In Fig. 2, the information processing system includes an information processing device 100, a client device 150, and machine tools 110-1 to 110-n arranged on a production line. The information processing system also includes sensors 202-1 to 202-n (n is a natural number equal to or greater than 2) provided on each of the machine tools 110-1 to 110-n. In the following description, the machine tools 110-1 to 110-n may be referred to as "machine tools 110," and the sensors 202-1 to 202-n may be referred to as "sensors 202."

[0046] In the information processing system, the information processing device 100 and sensors 202-1 to 202-n are connected via a wired or wireless network 210. The information processing device 100 and client device 150 are connected via a wired or wireless network 210. The network 210 is, for example, a LAN (Local Area Network), a WAN (Wide Area Network), the Internet, or the like.

[0047] In response to a user operation, the client device 150 outputs a request for creating a maintenance plan for the machine tool 110 on the production line to the information processing device 100. For example, the information processing device 100 displays and outputs the created maintenance plan on the client device 150 using a Web service on the network 210.

[0048] <Examples of information processing systems> Information processing device 100 is a computer that has various information processing tables shown in Figures 4 to 7 and creates and controls output of a maintenance plan for machine tools 110 on a production line based on information in the various information processing tables. Information processing device 100 is, for example, a server.

[0049] On the other hand, the client device 150 is, for example, a computer that has a display (for example, a display 912 shown in FIG. 9 described later) and can display various screens of the maintenance plan in accordance with the display control of the information processing device 100. The client device 150 is, for example, a PC, a notebook PC, a tablet PC, a smartphone, a wearable device, or the like.

[0050] When the information processing device 100 receives a request from the client device 150 to display a maintenance plan for the machine tool 110 on the production line, the information processing device 100 generates screen information for various screens of the maintenance plan based on the information in the various tables and transmits the screen information to the client device 150. As a result, the client device 150 displays the various screens on the display.

[0051] The information processing method of the embodiment creates a maintenance plan for multiple machine tools 110 arranged on a production line. The production line to which the information processing method of the embodiment is applied is not limited to one in which multiple machine tools 110 are simply arranged in a straight line. For example, the production line may be one in which multiple partial lines arranged in parallel merge into the same partial line, or one partial line branches into multiple partial lines. In this case, the information processing device 100 calculates, with regard to the second cost related to the stoppage of the production line, a cost corresponding to the stoppage period of any of the partial flows due to replacement work for the machine tools 110 that are responsible for work forming any of two or more partial flows.

[0052] (Example of hardware configuration of information processing device) Next, an example of the hardware configuration of the information processing device will be described with reference to FIG.

[0053] Fig. 3 is a block diagram showing an example of the hardware configuration of an information processing device. In Fig. 3, the information processing device 100 has a CPU (Central Processing Unit) 301, a memory 302, a network I / F (Interface) 303, a recording medium I / F 304, and a recording medium 305. Furthermore, each component is connected to each other by a bus 300.

[0054] Here, CPU 301 is responsible for overall control of information processing device 100. Memory 302 includes, for example, a read-only memory (ROM), a random access memory (RAM), and a flash ROM. Specifically, for example, the flash ROM or ROM stores various programs, and RAM is used as a work area for CPU 301. The programs stored in memory 302 are loaded into CPU 301, causing CPU 301 to execute coded processes.

[0055] The network I / F 303 is connected to the network 210 via a communication line, and is connected to other computers via the network 210. The network I / F 303 manages the internal interface with the network 210 and controls the input and output of data from other computers. The network I / F 303 is, for example, a modem or a LAN adapter.

[0056] The recording medium I / F 304 controls reading and writing of data from and to the recording medium 305 under the control of the CPU 301. The recording medium I / F 304 is, for example, a disk drive, a solid state drive (SSD), or a universal serial bus (USB) port. The recording medium 305 is a non-volatile memory that stores data written under the control of the recording medium I / F 304. The recording medium 305 is, for example, a disk, a semiconductor memory, or a USB memory. The recording medium 305 may be detachable from the information processing device 100.

[0057] In addition to the above-described components, the information processing device 100 may also include, for example, a keyboard, a mouse, a display, a printer, a scanner, a microphone, a speaker, etc. The information processing device 100 may also include a plurality of recording medium I / Fs 304 and recording media 305. The information processing device 100 may also not include the recording medium I / Fs 304 and recording media 305.

[0058] (Storage contents of information processing table) Next, an example of the contents stored in the information processing table will be described with reference to Fig. 4 to Fig. 7. The information processing table is realized by a storage area such as the memory 302 or recording medium 305 of the information processing device 100 shown in Fig. 3, for example.

[0059] Fig. 4 is an explanatory diagram showing an example of the contents stored in a machine tool status information table. As shown in Fig. 4, machine tool status information table 400 has fields for measurement data periodically output by sensor 202 of machine tool 110, such as sensor value, elapsed time, and endurance time, in association with a field for the machine tool, which is machine tool 110. Machine tool status information table 400 stores machine tool status information as record 400-a by setting information in each field for each machine tool. "a" is an arbitrary integer. In the example of Fig. 4, "a" is an arbitrary integer from 1 to 7.

[0060] The machine tools are identifiers A to Q of the machine tools 110 arranged on the production line. The sensor values ​​are the operating states of the machine tools 110 detected by the sensor 202. The elapsed time is the time that has passed since the last replacement of the machine tools A to Q. The endurance time is the time that guarantees stable operation of the machine tools 110 and their components. Replacement during the period until the elapsed time reaches the endurance time corresponds to early replacement of the device 110. The sensor 202 is not limited to detecting the sensor values, elapsed time, and endurance time, which are measurement data. For example, the endurance time, which is part of the measurement data, may be set as a fixed value in the machine tool status information table 400 by the information processing device 100, and the elapsed time may be the time since the device 110 was replaced, which the information processing device 100 stores in the machine tool status information table 400 for each timer count.

[0061] For example, record 400-1 is maintenance information in which the sensor value of machine tool A is associated with AAA, the elapsed time is a1, and the endurance time is ax.

[0062] Machine tool status information table 400 is created, for example, by adding record 400-a each time measurement data is periodically output by sensor 202 provided for each machine tool 110. Furthermore, machine tool 110 is made up of a combination of parts, and machine tool status information table 400 may be created, for example, by adding record 400-a each time measurement data is periodically output by sensor 202 provided for each part of machine tool 110.

[0063] FIG. 5 is an explanatory diagram showing an example of the contents stored in a maintenance information table. As shown in FIG. 5, the maintenance information table 500 has fields for the machine tool manufacturer and the planned downtime, which are associated with the machine tool field. The maintenance information table 500 stores maintenance information as record 500-a by setting information in each field for each machine tool. a is an arbitrary integer. In the example of FIG. 5, a is an arbitrary integer between 1 and 7.

[0064] The machine tools are identifiers A to Q of the machine tools 110 arranged on the production line. The machine tool manufacturers are the manufacturer names X to Z of the machine tool manufacturers. The planned downtime is the time for stopping the machine tools A to Q when they are replaced, and in the example of FIG. 5, it is 2, 3, and 5 (days).

[0065] For example, record 500-1 is maintenance information that associates machine tool A with manufacturer X and planned downtime of 3 days.

[0066] The maintenance information table 500 is created by adding a record 500-a based on an operation input from the client device 150 by a worker engaged in the maintenance plan, for example.

[0067] 6 and 7 show examples of the contents stored in the line configuration table. The line configuration table includes a line layout information table and a machine tool layout information table.

[0068] FIG. 6 is an explanatory diagram showing an example of the contents stored in a line layout information table. As shown in FIG. 6, the line layout information table 600 has fields for process, previous line, next line, and production volume, which are associated with fields for partial lines. The line layout information table 600 stores line layout information as record 600-a by setting information in each field for each partial line. a is an arbitrary integer. In the example of FIG. 6, a is an arbitrary integer between 1 and 4.

[0069] A line is an identifier for a partial line placed on a production line, Line1 to Line4. A process is an identifier for a production process on a production line, 1 to 3. A previous line is an identifier for a partial line located before the current partial line on the production line. A subsequent line is an identifier for a partial line located after the current partial line. A production volume is the amount of product produced on the current partial line.

[0070] For example, record 600-1 is line layout information in which line Line1 produces processes 1 and 2, and the succeeding line is Line4, with a production volume of 10. Record 600-4 is line layout information in which line Line4 produces process 3, and the preceding lines are Line1, Line2, and Line3, with a production volume of 40. The example in FIG. 6 shows that three parallel partial lines, Line1 to Line3, are combined into one production line, Line4.

[0071] The line arrangement information table 600 is created by adding a record 600-a based on an operation input to the client device 150 by a worker engaged in the maintenance plan, for example.

[0072] FIG. 7 is an explanatory diagram showing an example of the contents stored in a machine tool layout information table. As shown in FIG. 7, the machine tool layout information table 700 has fields for the line to which the machine tool belongs and its order within the line, in correspondence with the machine tool field. The machine tool layout information table 700 stores machine tool layout information as record 700-a by setting information in each field for each machine tool. a is an arbitrary integer. In the example of FIG. 7, a is an arbitrary integer between 1 and 7.

[0073] The machine tools are the identifiers A to Q of the machine tools 110 arranged on the production line. The belonging lines are the partial lines Lines 1 to 4 on which the machine tools are arranged. The in-line order is the position of the machine tool arranged on the partial line; in the example of Figure 7, the front position is 1 and the rear position is 2.

[0074] For example, record 700-1 is machine tool layout information in which the line to which machine tool A belongs is partial line Line1 and the order within the line is associated with 1. Record 700-2 is machine tool layout information in which the line to which machine tool B belongs is partial line Line1 and the order within the line is associated with 2. In this case, it is shown that machine tool A is placed in front of partial line Line1 and machine tool B is placed in the rear.

[0075] The machine tool location information table 700 is created by adding a record 700-a based on an operation input to the client device 150 by an operator engaged in the maintenance plan, for example.

[0076] (Example of machine tool hardware configuration) Next, an example of the hardware configuration of machine tool 110 included in the information processing system shown in FIG. 2 will be described with reference to FIG.

[0077] Fig. 8 is a block diagram showing an example of the hardware configuration of a machine tool. In Fig. 8, machine tool 110 has a CPU 801, a memory 802, a network I / F 803, an operating unit 810, a sensor 811, and a touch panel 812. Furthermore, each component is connected to each other by a bus 800.

[0078] Here, CPU 801 is responsible for overall control of machine tool 110. Memory 802 includes, for example, ROM, RAM, and flash ROM. Specifically, for example, flash ROM and ROM store various programs, and RAM is used as a work area for CPU 801. The programs stored in memory 802 are loaded into CPU 801, causing CPU 801 to execute coded processes.

[0079] The network I / F 803 is connected to the network 210 via a communication line, and is connected to other computers via the network 210. The network I / F 803 is connected to, for example, the information processing device 100 via the network 210. The network I / F 803 manages an internal interface with the network 210, and controls input and output of data from other computers.

[0080] The network I / F 803 is, for example, a communication circuit that connects to the wired or wireless network 210. The network I / F 803 may be a communication circuit that has an antenna for Wi-Fi (registered trademark).

[0081] Operation unit 810 constitutes machine tool 110 and corresponds to a part to be replaced. Machine tool 110 manufactures products through the operation of operation unit 810. Operation unit 810 is, for example, a manipulator. Operation unit 810 is controlled by the operation control of CPU 801, and performs operations such as incorporating parts for a product to be manufactured into the product in accordance with the process on the flow handled by machine tool 110.

[0082] The sensor 811 corresponds to the sensor 202 in FIG. 2 . The sensor 811 detects the operating state of the operational unit 810 and periodically outputs measurement data to the information processing device 100. The sensor 811 measures, for example, measurement data related to the operation of the operational unit 810. The measurement data is output as a sensor value indicating the amount of displacement of the operation or situation, etc., used for maintenance such as failure or replacement of the operational unit 810. The sensor 811 may have, for example, at least one of an acceleration sensor, a geomagnetic sensor, an optical sensor, a vibration sensor, a strain detection sensor, an infrared sensor, etc. The sensor 811 outputs a sensor value indicating the amount of displacement of the operational unit 810 to the information processing device 100.

[0083] Touch panel 812 displays various information about machine tool 110 controlled by CPU 801. Furthermore, touch panel 812 is used to set the operation of machine tool 110, information output, and the like, by touch operation.

[0084] (Example of client device hardware configuration) Next, an example of the hardware configuration of the client device 150 included in the information processing system shown in FIG. 2 will be described with reference to FIG.

[0085] Fig. 9 is a block diagram showing an example of the hardware configuration of a client device. In Fig. 9, client device 150 has a CPU 901, a memory 902, a network I / F 903, a recording medium I / F 904, a recording medium 905, an input / output I / F 910, an input device 911, and a display 912. Furthermore, each component is connected to each other by a bus 900.

[0086] Here, CPU 901 is responsible for overall control of client device 150. Memory 902 includes, for example, ROM, RAM, and flash ROM. Specifically, for example, flash ROM and ROM store various programs, and RAM is used as a work area for CPU 901. The programs stored in memory 902 are loaded into CPU 901, causing CPU 901 to execute coded processes.

[0087] The network I / F 903 is connected to the network 210 via a communication line, and is connected to other computers via the network 210. The network I / F 903 manages the internal interface with the network 210 and controls the input and output of data from other computers. The network I / F 903 is, for example, a modem or a LAN adapter.

[0088] The recording medium I / F 904 controls reading and writing of data from and to the recording medium 905 under the control of the CPU 901. The recording medium I / F 904 is, for example, a disk drive, an SSD, a USB port, etc. The recording medium 905 is a non-volatile memory that stores data written under the control of the recording medium I / F 904. The recording medium 905 is, for example, a disk, a semiconductor memory, a USB memory, etc. The recording medium 905 may be detachable from the client device 150.

[0089] The input / output I / F 910 controls the input and output of data to and from an input device 911 and a display 912 under the control of the CPU 901. The input device 911 has keys for inputting characters, numbers, various instructions, etc., and inputs data. The input device 911 may be a keyboard, a mouse, a touch panel input pad, a numeric keypad, etc. The display 912 displays data such as a cursor, icons, a toolbox, documents, images, and function information. The display 912 may be, for example, a CRT (Cathode Ray Tube), a liquid crystal display, or an organic EL (Electroluminescence) display.

[0090] In addition to the components described above, client device 150 may also include, for example, a printer, a scanner, a microphone, a speaker, etc. Client device 150 may also include a plurality of recording medium I / Fs 904 and recording media 905. Client device 150 may also not include recording medium I / Fs 904 and recording media 905.

[0091] (Example of functional configuration of information processing device) Next, an example of the functional configuration of the information processing device will be described with reference to FIG.

[0092] 10 is a block diagram showing an example of the functional configuration of an information processing device 100. The information processing device 100 includes a storage unit 1001, an acquisition unit 1002, a calculation unit 1003, and an output unit 1004.

[0093] The storage unit 1001 is realized by, for example, a storage area such as the memory 302 or the recording medium 305 shown in Fig. 3. In the following, a case where the storage unit 1001 is included in the information processing device 100 will be described, but this is not limiting. For example, the storage unit 1001 may be included in a device different from the information processing device 100, and the stored contents of the storage unit 1001 may be accessible from the information processing device 100.

[0094] The acquiring unit 1002 to the output unit 1004 function as an example of a control unit. Specifically, the acquiring unit 1002 to the output unit 1004 realize their functions by causing the CPU 301 to execute a program stored in a storage area such as the memory 302 or the recording medium 305 shown in Fig. 3, or by using the network I / F 303. The processing results of each functional unit are stored in a storage area such as the memory 302 or the recording medium 305 shown in Fig. 3, for example.

[0095] The storage unit 1001 stores various pieces of information that are referred to or updated in the processing of the acquisition unit 1002 to output unit 1004, which are the functional units of the control unit.

[0096] The acquisition unit 1002 acquires various types of information used in processing by each functional unit. The acquisition unit 1002 stores the acquired various types of information in the storage unit 1001 or outputs it to each functional unit. The acquisition unit 1002 may also output the various types of information stored in the storage unit 1001 to each functional unit. The acquisition unit 1002 acquires various types of information based on, for example, a user's operation input. The acquisition unit 1002 may receive various types of information from, for example, a device different from the information processing device 100.

[0097] The acquisition unit 1002 may receive a start trigger to start processing of one of the functional units. The start trigger may be, for example, a predetermined operation input by a user. The start trigger may be, for example, reception of predetermined information from another computer. The start trigger may be, for example, output of predetermined information by one of the functional units.

[0098] The output unit 1004 outputs the processing results of each functional unit. The output format may be, for example, display on a display, printout on a printer, transmission to an external device via the network I / F 303, or storage in a storage area such as the memory 302 or recording medium 305. In this way, the output unit 1004 can notify the user of the processing results of each functional unit, for example, information such as the cost and timing of replacing a machine tool 110 on the production line, and support the user in implementing a maintenance plan for the production line.

[0099] 1, the acquisition unit 1002 acquires information for calculating a deadline for carrying out replacement work that involves stopping all or part of the production line from multiple machine tools 110 that are responsible for different tasks among multiple tasks that form the production line. The deadline is, for example, the time when the replacement work should be carried out with the durability time of the device 110 at its maximum.

[0100] The storage unit 1001 includes and stores information on the machine tool status information table 400, the maintenance information table 500, the line layout information table 600, and the machine tool layout information table 700, which are the information processing tables described above.

[0101] The acquisition unit 1002 acquires measurement data detected by the sensors 202 of each of the multiple machine tools 110, and stores the data in the machine tool status information table 400. The acquisition unit 1002 acquires information from the maintenance information table 500, the line layout information table 600, and the machine tool layout information table 700 through external input such as a user operation, and stores the information in the storage unit 1001.

[0102] The calculation unit 1003 calculates the optimal time to perform replacement work for each machine tool 110, based on the information acquired by the acquisition unit 1002. The calculation unit 1003 includes a remaining life calculation unit 1010, a first objective function setting unit 1011, a second objective function setting unit 1012, and a multi-objective optimization unit 1013.

[0103] The remaining life calculation unit 1010 acquires information relating to the deadline for replacing the machine tool 110 or replacing parts of the machine tool 110 from each of the multiple machine tools 110, and calculates the remaining life of the multiple machine tools 110. The information processing device 100, for example, acquires measurement data measured by a sensor of each of the machine tools 110, and calculates the remaining life of the multiple machine tools 110 based on the acquired measurement data. The remaining life calculation unit 1010 calculates the remaining life of each of the machine tools 110 based on, for example, information on the sensor value, elapsed time, and endurance time of each of the machine tools 110 as the measurement data.

[0104] Furthermore, the remaining life calculation unit 1010 may perform a learning process to calculate the remaining life of multiple machine tools 110. In this case, the remaining life calculation unit 1010 acquires measurement data measured in the past by sensors provided in each machine tool 110 and the time when replacement work for each machine tool 110 was previously performed. The information processing device 100 learns a model that outputs a deadline for performing replacement work for each machine tool 110 in response to input of the measurement data for each machine tool 110. The information processing device 100 uses the learned model to calculate a deadline for performing replacement work for each machine tool 110 based on the measurement data. The measurement data measured by the sensor indicates a sensor value corresponding to a change in the operating state of the machine tool 110 over time, and the information processing device 100 predicts a deadline corresponding to the life of the machine tool 110 based on the fluctuation state of the sensor value of this measurement data. Furthermore, the information processing device 100 may calculate the remaining life based on the difference between the predicted deadline and a life limit (endurance time) set for the machine tool 110.

[0105] The first objective function setting unit 1011 and the second objective function setting unit 1012 set a first objective function and a second objective function to be used in multi-objective optimization by the multi-objective optimization unit 1013. The first objective function setting unit 1011 sets, for each machine tool 110, a first objective function including an equation for a first cost according to the remaining life of each machine tool 110, assuming that early replacement work will be carried out before the remaining life is reached. The first objective function setting unit 1011 refers to information such as the sensor value, elapsed time, and endurance time of each machine tool 110, stored in the machine tool status information table 400 stored in the storage unit 1001, for example.

[0106] For example, the first objective function setting unit 1011 calculates the cost when machine tool 110 is used until the endurance time expires, that is, when there is no remaining life and it is used until the endurance limit, as the basic cost. Furthermore, the first objective function setting unit 1011 sets the cost when machine tool 110 is replaced ahead of schedule before the endurance time expires, that is, the basic cost, as the cost for the loss that occurs when the replacement is carried out ahead of schedule.

[0107] The second objective function setting unit 1012 sets a second cost according to the period of shutdown of all or part of the production line due to each replacement work when the replacement work is carried out before the deadline for each machine tool 110. Each machine tool 110 is arranged on a part of the production line, and depending on the arrangement state of the machine tool 110 on the production line, the shutdown of the machine tool 110 may result in the shutdown of part of the production line or the shutdown of the entire production line.

[0108] The second objective function setting unit 1012 refers to information such as the placement of each machine tool 110 on the production line and planned downtime, which are stored in the maintenance information table 500, the line placement information table 600, and the machine tool placement information table 700 stored in the storage unit 1001. The second objective function setting unit 1012 sets the loss cost caused by the stoppage of production when a planned stoppage of production on the production line occurs.

[0109] The multi-objective optimization unit 1013 performs multi-objective optimization processing using the first cost set by the first objective function setting unit 1011 as the first objective function and the second cost calculated by the second objective function setting unit 1012 as the second objective function. Through the multi-objective optimization processing, the multi-objective optimization unit 1013 calculates one or more optimal combinations of the timings for performing replacement work for each machine tool 110, for example, Pareto solutions.

[0110] The output unit 1004 outputs information on one or more optimal combinations of timings for performing replacement work for each machine tool 110 calculated by the multi-objective optimization unit 1013. The output unit 1004 outputs the information to, for example, the client device 150 shown in Fig. 2. The output of the output unit 1004 takes into consideration both the cost of replacing parts for the machine tool 110 and the cost of losses due to planned shutdowns of the production line through multi-objective optimization, and indicates multiple optimal replacement timings.

[0111] (Operation example 1 of information processing device 100) Fig. 11 is a functional block diagram showing an operation example 1 of the information processing device. In Fig. 11, components that are the same as those described above are assigned the same reference numerals. Fig. 11 shows a detailed example of the function of the calculation unit 1003 of the information processing device 100 shown in Fig. 10.

[0112] The machine tools A to C (110) are each provided with a sensor 202. The sensor 202 outputs measurement data of the machine tools A to C (110) to the information processing device 100.

[0113] The information processing device 100 includes the above-described first objective function setting unit 1011, second objective function setting unit 1012, multi-objective optimization unit 1013, and output unit 1004. The information processing device 100 also includes a remaining life calculation unit 1010 and a maintenance planning unit 1110.

[0114] The remaining life calculation unit 1010 includes a learning data generation unit 1101 , a learning unit 1102 , a remaining life inference unit 1103 , and an inference data generation unit 1104 , and calculates the remaining life of the device 110 .

[0115] The learning data generation unit 1101 to the remaining life estimation unit 1103 learn a prediction model for the remaining life of each machine tool 110. The learning data generation unit 1101 creates learning data for predicting the remaining life of each machine tool 110 based on the information stored in the machine tool status information table 400. The learning data generation unit 1101 creates learning data relating to fluctuations in sensor values ​​for each elapsed time of the machine tool 110 stored in the machine tool status information table 400, for example. The learning data generation unit 1101 creates learning data for each machine tool 110 and for each part (operation unit 810) that each machine tool 110 has.

[0116] The learning unit 1102 performs a learning process for a model that predicts the remaining life of each machine tool 110 and each component using the learning data generated by the learning data generation unit 1101. The learning unit 1102 performs learning using, for example, a machine learning (ML) algorithm such as linear regression, GBDT (Gradient Boosting Decision Tree), or NN (Neural Network).

[0117] For example, in the NN, the difference between the output result output by the NN when the time-series sensor values ​​periodically output by sensor 202 are input to the NN as explanatory variables and the sensor value at the time when machine tool 110 is finally replaced is calculated. Then, the parameters of the NN are changed to create a model so that the error with the correct label up until replacement is reduced.

[0118] Based on the learning results of the learning unit 1102, the remaining life prediction unit 1103 outputs a model for predicting the remaining life of each machine tool 110 and each part.

[0119] The inference data generation unit 1104 generates inference data for each machine tool 110 based on, for example, the sensor values ​​of the machine tool 110 for each elapsed time stored in the machine tool status information table 400. The inference data generation unit 1104 inputs the generated inference data into the trained remaining life prediction model output by the remaining life inference unit 1103, and calculates a predicted value of the remaining life. For example, the inference data generation unit 1104 may store the calculated predicted value of the remaining life in a field of the record of the corresponding machine tool 110 in the machine tool status information table 400.

[0120] The first objective function setting unit 1011 performs the calculation process of the above formula (1) using the remaining life information obtained by the learning process by the remaining life calculation unit 1010, and sets the loss cost due to the acceleration of the machine tool 110.

[0121] The second objective function setting unit 1012 sets the loss cost due to the planned stoppage of the line.

[0122] The multi-objective optimization unit 1013 calculates an optimal solution for the combination of the loss cost due to the advancement set by the first objective function setting unit 1011 and the loss cost due to the planned stoppage of the line set by the second objective function setting unit 1012.

[0123] The maintenance planning unit 1110 creates a maintenance plan including the replacement timing of the machine tool 110 based on the optimal solution calculated by the multi-objective optimization unit 1013 for the combination of the loss cost due to early implementation and the loss cost due to planned line shutdown.

[0124] The output unit 1004 displays the maintenance plan created by the maintenance planning unit 1110 on the client device 150 .

[0125] (Example of calculation of loss costs due to planned line shutdown) Fig. 12 is an explanatory diagram of an example of calculating the loss cost due to a planned stoppage of a line. Using Fig. 12, an example of calculating the loss cost due to a planned stoppage of a production line by the second objective function setting unit 1012 will be described. Fig. 12(a) shows an example of a connection configuration in which multiple partial lines are connected. Line 1, Line 2, and Line 3, which are arranged in parallel with each other, are connected to Line 4.

[0126] Line 1 has machine tool A in the front row and machine tool B in the rear row. Line 2 has machine tool P in the front row and machine tool Q in the rear row. Line 3 has machine tool L in the front row and machine tool M in the rear row. Each of Lines 1 to 3 is connected to Line 4 in the rear row. Line 4 has machine tool D in it.

[0127] Let x be the daily sales for the total production volume of the production line. Also, let's assume that the production volume of each partial line is 1 / 4 for Line 1, 1 / 2 for Line 2, and 1 / 4 for Line 3. In this case, the loss cost per day due to planned shutdown of each partial line is x / 4 for Line 1, x / 2 for Line 2, x / 4 for Line 3, and x for Line 4.

[0128] The information processing device 100 calculates the loss cost due to planned shutdown taking into account the connection configuration of the production line. For example, if maintenance is performed on machine tool D, production on the entire line will stop, and the loss cost due to planned shutdown will be large. On the other hand, if machine tools A, B, P, Q, L, and M are each operating on separate partial lines, only a reduction in production will be necessary, and the loss cost due to planned shutdown will be relatively low.

[0129] FIG. 12(b) shows a state in which settings equivalent to those in the maintenance information table 500 described above have been allocated to machine tools 110 by manufacturer. As shown in the maintenance information table 500, a production line may include multiple machine tool manufacturers. In this case, as shown in FIG. 12(b), the planned downtime may differ for each manufacturer. Furthermore, in order to accommodate cases in which the planned downtime differs not by manufacturer but by product type (model number), planned downtimes for each product type are set in the maintenance information table 500.

[0130] In the example shown in Figure 12(b), machine tools A, B, L, and M are made by manufacturer X and have a planned downtime of 3 days. Machine tools P and Q are made by manufacturer Y and have a planned downtime of 5 days. For example, if machine tools P and Q of manufacturer Y undergo maintenance, the loss cost due to the planned downtime will be large. More specifically, for example, if machine tool A undergoes a planned downtime, a loss cost of x / 4 x 3 (days) will be incurred in Line 1. Furthermore, if machine tool P undergoes a planned downtime, a loss cost of x / 2 x 5 (days) will be incurred in Line 2.

[0131] The information processing device 100 calculates the loss cost during planned downtime, taking into account the planned downtime that differs for each manufacturer of machine tool 110 on the production line. For example, when replacement work is performed on machine tool 110, the information processing device 100 sets the second cost according to the planned downtime for each partial line due to the replacement work and a weighting coefficient that represents the degree of influence of the partial line on the entire production line. For example, the weighting coefficient corresponds to the coefficient shown by x / 4×3 (days) for each partial line described above.

[0132] (Multi-objective optimization processing example 1) Next, a description will be given of a first processing example of multi-objective optimization by the multi-objective optimization unit 1013. The multi-objective optimization unit 1013 calculates an optimal solution for a combination of a first cost (part replacement cost + loss cost) and a second cost (loss cost due to planned stoppage of the production line), which have a trade-off relationship with each other.

[0133] The multi-objective optimization unit 1013 uses a combination optimization processing technique for the first cost and the second cost, and calculates the replacement timing of the machine tool 110 that minimizes the first cost and the second cost while changing the parameters of these first cost and second cost.

[0134] The multi-objective optimization unit 1013 uses an optimization solver to find multiple combinations that minimize the first cost and the second cost, which have a trade-off relationship as two objective functions. At this time, the multi-objective optimization unit 1013 changes the part replacement timing of each machine tool 110 as a parameter (variable). The multi-objective optimization unit 1013 also uses a constraint that the replacement timing of each machine tool 110 does not exceed the remaining lifespan. For example, the multi-objective optimization unit 1013 sets the future operating time of each machine tool 110≦the predicted remaining lifespan of the machine tool as a constraint.

[0135] The multi-objective optimization unit 1013 calculates the minimization of the first cost using the first objective function shown in the following formula (2), for example.

[0136] min:ΣΣc_i×x_it (2) (i: machine tool A, B, P, Q, L, M, D, t: replacement time, c_i: cost of replacing parts for machine tool i, x_it: replacement flag for machine i at time t, where "1" indicates replacement and "0" indicates no replacement)

[0137] The multi-objective optimization unit 1013 calculates the minimization of the second cost using the second objective function shown in the following formula (3), for example.

[0138] min:ΣΣd_j×l_jt (3) (j: lines 1, 2, 3, 4, t: replacement time, d_j: loss cost when line j is stopped, l_jt: stop flag for line j at time t, where "1" indicates stopped and "0" indicates operation (no stop))

[0139] Here, according to the line configurations shown in FIGS. 6 and 12, etc., for the machine tools 110 arranged on each partial line, for Line1, l_1t = max(x_At, x_Bt), for Line2, l_2t = max(x_Pt, x_Qt). Also, for Line3, l_3t = max(x_Lt, x_Mt), and for Line4, l_4t = max(x_Dt). The above is a max function indicating that if the replacement flag of any of the machine tools A to Q on the partial line l at time t is stopped "1", then the stop flag of this partial line is stopped "1", indicating that this partial line stops.

[0140] The multi-objective optimization unit 1013 outputs the binary values of 0 or 1 of x_it as the output of multi-objective optimization of the combination. The multi-objective optimization unit 1013, for example, when x_it = 1, replaces the parts of the machine tool i at the replacement time t.

[0141] The multi-objective optimization unit 1013 sets the following formula (4) as a constraint condition of the combination and performs the multi-objective optimization process.

[0142] Σx_it≧1 ···(4) (i: the number of machine tools, t: replacement time, provided that t < p_i + today (today's date), p_i: remaining life of the machine tool)

[0143] (Example 2 of multi-objective optimization process) Next, an example 2 of the multi-objective optimization process by the multi-objective optimization unit 1013 will be described. In this example 2 of the multi-objective optimization process, optimization of the cost considering elements specific to the production line is performed. For example, the contractors for requesting replacement work are different for each manufacturer of the production line, and the cost of calling a serviceman for the replacement work is different for each contractor. Therefore, in example 2 of the multi-objective optimization process, in addition to the cost described in example 1 of the above process, a multi-objective optimization process including the cost (third cost) of calling a serviceman for each contractor to the site where the production line is installed is performed.

[0144] For example, as described above, machine tools A, B, L, and M are from the same manufacturer. In this case, if individual optimization for each machine tool 110 is performed using conventional technology, the result would be, for example, replacing machine tools A and B this month and replacing machine tool M next month. In contrast, processing example 2 of the multi-objective optimization of the embodiment can result in the replacement of machine tools A and B this month, as well as machine tool M being replaced ahead of schedule.

[0145] In the processing example 2 of the multi-objective optimization, the multi-objective optimization unit 1013 calculates, for example, minimization of the first cost using the first objective function shown in the above formula (2).

[0146] The multi-objective optimization unit 1013 calculates the minimization of the second cost using the second objective function shown in the above formula (3), for example.

[0147] Furthermore, the multi-objective optimization unit 1013 calculates, for example, a third cost minimization according to a client to be requested to perform replacement work on the machine tool 110 before the deadline, using a third objective function shown in the following equation (5).

[0148] min:ΣΣs_k×m_kt (5) (k: manufacturer X, Y, Z, t: replacement time, s_k: cost per unit time, m_kt: call flag for manufacturer k at time t, where "1" indicates a call and "0" indicates no call)

[0149] Here, m_Xt=max(x_At,x_Bt,x_Lt,x_Mt), m_Yt=max(x_Pt,Qt), m_Zt=x_Dt, based on the manufacturer information for each machine tool shown in Figure 5. c_i is the cost of replacing parts on machine tool i, d_j is the loss cost when line j is stopped, and s_k is the cost of calling a service technician from manufacturer k.

[0150] In processing example 2 of multi-objective optimization, similarly to processing example 1, the above formula (4) is set as a constraint condition for the combination, and multi-objective optimization processing is performed. Then, according to the embodiment, multi-objective optimization unit 1013 calculates one or more combinations of timings for performing replacement work for each machine tool 110 by performing multi-objective optimization of the first to third objective functions.

[0151] The multi-objective optimization unit 1013 outputs the binary value of x_it, 0 or 1, as an output of the optimized combination. For example, when x_it=1, the multi-objective optimization unit 1013 replaces a part of the machine tool i at replacement time t.

[0152] Fig. 13 is an explanatory diagram showing an example of replacement timing optimized by multi-objective optimization. An example of calculation of the optimal replacement timing for each machine tool 110 by the multi-objective optimization unit 1013 will be described using Fig. 13. The horizontal axis in Fig. 13 represents time.

[0153] Assume that each of the three machine tools A to C starts operation at time t0. The remaining lifespans of parts of the machine tools A to C differ. As time passes, the remaining lifespan of the machine tool A expires first at time t1. In this case, the multi-objective optimization unit 1013 replaces parts of the machine tool A at time t1, and also determines whether parts of the other machine tools B and C can be replaced at time t1 based on the remaining lifespans of the machine tools B and C.

[0154] At time t1, the remaining life of machine tool B is relatively long, whereas the remaining life of machine tool C is short. In this case, based on the part replacement timings and cost calculations of machine tools B and C, if part replacement of machine tool C is appropriate, the multi-objective optimization unit 1013 brings forward the replacement of part of machine tool C to time t1.

[0155] At time t1, machine tools A and C resume operation with new remaining lifespans due to part replacement. Note that time t1' is the time when machine tool C's part is replaced at the end of its remaining lifespan without being replaced ahead of schedule.

[0156] Next, assume that the remaining life of machine tool B expires at time t2. In this case, the multi-objective optimization unit 1013 replaces parts of machine tool B at time t2, and also determines whether parts of other machine tools A and C can be replaced at time t2 based on the remaining life of machine tools A and C.

[0157] At time t2, the remaining life of machine tool A is relatively short, while the remaining life of machine tool C is long. In this case, based on the part replacement timings and cost calculations of machine tools A and C, if part replacement of machine tool A is appropriate, multi-objective optimization unit 1013 will bring forward the part replacement of machine tool A to time t2.

[0158] At time t2, machine tools A and B resume operation with new remaining lifespans due to part replacement. Note that time t2' is the time when machine tool A's part is replaced at the end of its remaining lifespan, rather than being replaced ahead of schedule.

[0159] As shown in Fig. 13, the multi-objective optimization unit 1013 takes into account the remaining lifespan of each of the multiple machine tools A to C, and determines whether there are any other machine tools 110 for which parts replacement can be brought forward when it is time to replace a part of a machine tool 110 whose remaining lifespan has expired. If parts were replaced for each of the multiple machine tools 110 simply upon expiration of their remaining lifespan, the production line would be stopped each time, increasing the frequency of stoppages. In contrast, the information processing device 100 uses multi-objective optimization to determine whether, when parts replacement is to be performed on a certain machine tool 110, parts replacement can be brought forward for other machine tools at the same time, thereby reducing the frequency of production line stoppages and reducing loss costs.

[0160] (Maintenance plan display example) Next, a display example of a maintenance plan output by the information processing device 100 will be described with reference to Fig. 14 and Fig. 15. The display screens shown in Fig. 14 and Fig. 15 are created by the maintenance planning unit 1110 based on the multi-objective optimization results by the multi-objective optimization unit 1013 of the information processing device 100. The created maintenance plan is output and displayed on the client device 150 via the output unit 1004.

[0161] Fig. 14 is a diagram showing a selection screen for a maintenance plan output by an information processing device. The horizontal axis displayed on the selection screen 1400 for a maintenance plan shown in Fig. 14 represents the loss cost due to a planned stoppage of the production line (second cost), and the vertical axis represents the cost of replacing machine tool parts (first cost). The information processing device 100 displays, on the selection screen 1400 for a maintenance plan, a predetermined characteristic curve 1401 corresponding to a Pareto solution, which is the result of multi-objective optimization of the first cost and second cost by the multi-objective optimization unit 1013.

[0162] The characteristic curve 1401 is a combination of multiple timings for carrying out replacement work for each machine tool 110, and the information processing device 100 displays multiple selection points P1 to P4 on the characteristic curve 1401. Each of the selection points P1 to P4 is a maintenance plan that combines a first cost and a second cost that are mutually exclusive.

[0163] For example, at selection point P1, the loss cost due to planned shutdowns of the production line is small, but the cost of replacing machine tool parts is high. The information processing device 100 displays a guide 1411 with the explanation "Line shutdowns are few, but parts are replaced even though they still have remaining life" in response to selection point P1. Also, at selection point P4, the loss cost due to planned shutdowns of the production line is large, but the cost of replacing machine tool parts is small. The information processing device 100 displays a guide 1412 with the explanation "Each machine tool part is used until the very end of its remaining life, but line shutdowns for maintenance are frequent" in response to selection point P4.

[0164] By viewing the maintenance plan selection screen 1400 displayed on the client device 150, the user can intuitively understand the advantages and disadvantages of each maintenance plan by referring to the guides 1411, 1412 displayed at the selection points P1 to P4. The user then selects one of the selection points P1 to P4 as the maintenance plan. When the user selects one of the selection points P1 to P4, the information processing device 100 displays a details screen (see FIG. 15) for the corresponding maintenance plan.

[0165] Fig. 15 is a diagram showing a details screen of the maintenance plan output by the information processing device. When the user selects one of the selection points P1 to P4 on the selection screen 1400 of Fig. 14, the information processing device 100 displays and outputs a details screen 1500 of the maintenance plan shown in Fig. 15. Fig. 15 shows the details screen 1500 when the user selects the selection point P1 of Fig. 14. The information processing device 100 displays the details screen 1500 based on the multi-objective optimization result corresponding to the state indicated by the user selection of the selection point P1 of Fig. 14, namely, "the loss cost due to the planned stoppage of the production line is small, and the cost of replacing machine tool parts is large."

[0166] The information processing device 100 displays, as a details screen 1500 of the proposed maintenance plan, the status of planned shutdowns currently being implemented (for example, for this month) when the maintenance plan period is set to two months from the present to next month, for example.

[0167] The line connection configuration shown in Fig. 15 is the same as that shown in Fig. 12. The information processing device 100 displays that four machine tools A, B, P, and M are candidates for replacement during a two-month maintenance period. For example, the information processing device 100 highlights the machine tools A, B, P, and M that are candidates for replacement in a predetermined color compared to the machine tools D, Q, and L that are not candidates for replacement, and displays that Line 1 and Line 3 will undergo planned shutdowns this month. Here, the information processing device 100 displays a guide 1511 indicating that machine tool A on Line 1 and machine tool M on Line 3 will be shut down as scheduled this month due to their respective life limits.

[0168] For example, the information processing device 100 displays the machine tool B that will be replaced ahead of schedule in a specific color (for example, green). Furthermore, the information processing device 100 displays the machine tool P that was a candidate for forward replacement based on the calculation result of the first cost but for which forward replacement will not be performed as a result of multi-objective optimization in another specific color (for example, red).

[0169] In the example shown in FIG. 15, based on the replacement of machine tool A, information processing device 100 displays guide 1512 for early replacement of machine tool B, which is arranged on the same partial line (Line 1) as machine tool A.

[0170] Furthermore, the information processing device 100 displays a guide 1513 for machine tool P on Line 2, which was a candidate for replacement, to the effect that the replacement will not be brought forward within this month. For example, the information processing device 100 displays an explanation for the guide such as "additional line stoppages will be required, which will result in a decrease in production volume, so the replacement will not be brought forward." The information processing device 100 may display these guides 1511 to 1513 as pop-ups based on the user's cursor operation.

[0171] As a result, the information processing device 100 allows the user to easily grasp which machine tools A, B, P, and M are candidates for replacement among a plurality of machine tools. Furthermore, the information processing device 100 enables the user to distinguish between machine tools A and M that will be replaced as scheduled due to their life limits and machine tool B that will be replaced ahead of schedule, among the machine tools A, B, P, and M that are candidates for replacement. Furthermore, the information processing device 100 enables the user to grasp that there is a machine tool P that will be replaced next month, rather than being replaced ahead of schedule within this month.

[0172] (Comparison between the prior art and the embodiment) Figure 16 is a comparative explanatory diagram of the impact of planned shutdowns between the prior art and the embodiment. Figure 16(a) shows the impact of planned shutdowns using the prior art, and Figure 16(b) shows the impact of planned shutdowns using the embodiment. The line connection configuration in Figure 12(a) is shown at the top of both Figures 16(a) and (b).

[0173] The conventional technology shown in Figure 16(a) calculates the optimal maintenance timing for each machine tool, but does not take into account the line connection configuration when calculating the maintenance timing. As a result, with the conventional technology, optimization is performed for each of machine tools A to Q, resulting in machine tools A and M being replaced this month and machine tools B and P being replaced next month. As a result, with the conventional technology, lines 1 and 3 will stop this month and lines 1 and 2 will stop next month, meaning that line 1 will stop both this month and next month.

[0174] On the other hand, according to the embodiment shown in FIG. 16(b), the information processing device 100 calculates the maintenance timing of machine tools taking into account the line connection configuration. Based on the fact that machine tools A and B are located on the same Line 1, the information processing device 100 of the embodiment replaces machine tools A, B, and M this month and machine tool P next month. Here, because machine tools A and B are located on the same Line 1, the information processing device 100 advances the replacement of machine tool B to this month. As a result, the information processing device 100 shuts down Lines 1 and 3 this month and only Line 2 next month, thereby eliminating the impact of the planned shutdown of Line 1 next month compared to the prior art. The information processing device 100 of the embodiment can present the user with a maintenance plan that minimizes production cost reductions on multiple production lines.

[0175] (Operation example 2 of information processing device 100) Fig. 17 is a functional block diagram showing operation example 2 of the information processing device. In Fig. 17, the same components as those described above are assigned the same reference numerals. In Fig. 17, of the functions of information processing device 100 shown in Fig. 11, the function of remaining life calculation unit 1010 is located on the machine tool 110 side.

[0176] Machine tools A to C (110) may have a function to calculate the remaining lifespan by themselves. In the example of Fig. 17, the functions of remaining lifespan calculation unit 1010 shown in Fig. 11, that is, learning data generation unit 1101 to inference data generation unit 1104, are arranged on the machine tool 110 side. The functions related to remaining lifespan calculation in machine tool 110 are not limited to learning data generation unit 1101 to inference data generation unit 1104 related to the learning process shown in Fig. 17.

[0177] The calculation unit 1003 of the information processing device 100 stores the remaining life information transmitted from each of the machine tools A to C (110) in the machine tool status information table 400. In the information processing device 100, the first objective function setting unit 1011 calculates the first cost based on the information stored in the machine tool status information table 400. The second objective function setting unit 1012, the multi-objective optimization unit 1013, and the like arranged in the calculation unit 1003 shown in FIG. 17 perform the same operations as in FIG. 11.

[0178] (Overall processing procedure) Next, an example of an overall processing procedure executed by the information processing device 100 will be described with reference to Fig. 18. The overall processing is realized by, for example, the CPU 301, storage areas such as the memory 302 and the recording medium 305, and the network I / F 303 shown in Fig. 3.

[0179] 18 is a flowchart showing an example of the overall processing procedure. First, information processing device 100 periodically acquires measurement data from each machine tool 110 (step S1801). Next, information processing device 100 learns a prediction model for the remaining life of parts for each machine tool from the accumulated measurement data and the part replacement timing of machine tool 110 (step S1802). Information processing device 100 performs the processes of steps S1801 to S1802 at regular intervals as preprocessing for creating and learning a learning model.

[0180] Next, the information processing device 100 predicts the remaining life of each machine tool from the latest measurement data (step S1803). For example, the information processing device 100 performs the processes of step S1803 and thereafter when a maintenance plan is requested by a user operation of the client device 150.

[0181] Next, the information processing device 100 uses the calculated remaining life to create multiple maintenance plans while varying the cost (step S1804). In the processing of step S1804, the information processing device 100 calculates the first cost and second cost described above and performs multi-objective optimization of the first cost and the second cost.

[0182] Next, the information processing device 100 presents the created combination of the maintenance plan and the cost to the user (step S1805), and ends the above processing. The created maintenance plan is presented to the user by a screen display or the like as candidates for the maintenance plan, which are combinations of multiple replacement times for each machine tool 110 through multi-objective optimization.

[0183] (Detailed processing procedure) Next, an example of a detailed processing procedure executed by the information processing device 100 will be described with reference to Fig. 19 to Fig. 21. Fig. 19 is a flowchart showing an example of a detailed processing procedure for generating a prediction model for remaining life. Fig. 19 shows in detail the processing of step S1802 in Fig. 18.

[0184] 19, when generating a remaining life prediction model shown in S1802, information processing device 100 creates learning data for each machine tool 110 or for each model of machine tool 110. First, information processing device 100 creates learning data for predicting the remaining life of components of each machine tool 110 from accumulated measurement data (step S1901). For example, information processing device 100 acquires the accumulated measurement data by referring to machine tool status information table 400 shown in FIG.

[0185] Next, the information processing device 100 applies an ML algorithm to the created learning data to learn a remaining life prediction model that predicts the remaining life of the parts (step S1902). The information processing device 100 uses, as the ML algorithm, for example, linear regression, GBDT, NN, etc. to learn a model that predicts the remaining life of the parts of each machine tool 110.

[0186] Information processing device 100 can use NN to create a model used to infer the remaining life of machine tool 110, for example. When an NN algorithm is used, a single learning session is sufficient for subsequent learning sessions, such as fine-tuning, and therefore the processing load can be reduced compared to other algorithms.

[0187] Next, the information processing device 100 outputs the remaining life prediction model learned in step S1902 (step S1903), and ends the above processing.

[0188] Fig. 20 is a flowchart showing an example of detailed steps in the process of predicting remaining life. Fig. 20 shows in detail the process of step S1803 in Fig. 18. In Fig. 20, when predicting remaining life shown in step S1803, information processing device 100 generates inference data for parts of each machine tool 110 from accumulated measurement data (step S2001). For example, information processing device 100 acquires the accumulated measurement data by referring to machine tool status information table 400 shown in Fig. 4.

[0189] Next, the information processing device 100 inputs the inference data into the remaining life prediction model that has been learned by the process in Fig. 19, and calculates the predicted value of the remaining life (step S2002). The information processing device 100 performs the process of step S2002 for each machine tool 110 or for each model of machine tool 110, etc.

[0190] Next, the information processing device 100 stores the remaining life of each machine tool 110 calculated in step S2002 (step S2003), and ends the above processing. For example, the information processing device 100 stores the remaining life in the record of the corresponding machine tool in the machine tool status information table 400 shown in FIG.

[0191] Fig. 21 is a flowchart showing an example of detailed steps for creating a plurality of maintenance plan proposals. Fig. 21 shows in detail the processing of step S1804 in Fig. 18. In Fig. 21, when creating a plurality of maintenance plan proposals, information processing device 100 calculates the cost of using machine tool 110 until its remaining life limit is reached and then replacing it, as the basic cost of the maintenance plan (step S2101).

[0192] Next, information processing device 100 calculates a combination of replacement times that minimizes the sum of the first cost and the second cost while changing parameters for cost calculation through multi-objective optimization (step S2102). Information processing device 100 uses the cost due to the stoppage of the production line due to replacement of machine tool 110 as the second cost.

[0193] The replacement timing obtained in step S2102 is, for example, as shown in FIG. 14, a combination of a first cost and a second cost that have a trade-off relationship with each other.

[0194] Next, the information processing device 100 combines a plurality of replacement times obtained as a result of the multi-objective optimization, outputs the first cost and the second cost for each combination as candidates for the maintenance plan (step S2103), and ends the above processing.

[0195] The above description has been given of an example in which the information processing method of the embodiment is applied to a production line. The maintenance plan created by the information processing method of the embodiment may target various target flows other than a production line. For example, the method can also be applied to a work plan for collaborative work by multiple workers. In this case, the information processing device 100 creates a work plan in which the target flow is branched and joined using multiple partial flows. The information processing device 100 creates a work plan based on changes in the working status of each worker during a target period, such as change information on planned holidays and absences. In addition, the information processing device 100 can also be applied to transmission plans based on change information on the distribution status of logistics and change information on network transmission routes during a target period.

[0196] As described above, the information processing device 100 obtains a deadline for replacement work involving the complete or partial shutdown of a target flow for each of multiple devices that form a target flow and are responsible for different tasks. The information processing device 100 calculates a first cost corresponding to the remaining lifespan of each device if the replacement work is performed before the deadline. The information processing device 100 calculates a second cost corresponding to the duration of the target flow's shutdown due to each replacement work if the replacement work is performed before the deadline. The information processing device 100 performs multi-objective optimization using a first objective function related to the first cost and a second objective function related to the second cost to calculate one or more combinations of timings for performing the replacement work for each device. As a result, the information processing device 100 outputs the calculated one or more combinations. The information processing device 100 can present an appropriate replacement timing that takes into account the replacement of each device on the target flow and the shutdown of the target flow due to device replacement. Although the first cost and the second cost are in a trade-off relationship, multi-objective optimization can present the user with multiple replacement timings that minimize the sum of the first cost and the second cost.

[0197] Furthermore, the information processing device 100 learns a model that outputs a deadline for performing replacement work in response to input of measurement data measured by the sensor of each device, based on measurement data measured in the past by a sensor provided in each device and the time when replacement work was previously performed on each device. The information processing device 100 performs an acquisition process that uses the learned model for each device to calculate a deadline for performing replacement work for the device based on the measurement data measured by the sensor provided in the device. As a result, the information processing device 100 can calculate a deadline for replacing a device using the learning process at each location.

[0198] Furthermore, the target flow processed by the information processing device 100 includes two or more partial flows that operate in parallel and merge into the same partial flow, or that branch off from the same partial flow and operate in parallel. According to the information processing device 100, the second cost is calculated to include a cost corresponding to the downtime of any of the two or more partial flows due to replacement work when replacement work is performed on a device responsible for work forming the partial flow. This makes it possible for the information processing device 100 to calculate the second costs of various target flows to which partial flows branch or join.

[0199] Furthermore, according to the information processing device 100, the second cost is calculated to include a cost corresponding to a stop period of a partial flow when a device on one of two or more partial flows performs replacement work and a weighting coefficient representing the impact of each partial flow on the entire target flow. As a result, according to the information processing device 100, it is possible to calculate the second cost taking into account, for example, production volume as the impact when a device on a partial flow is stopped.

[0200] Furthermore, according to the information processing device 100, the calculation process calculates one or more combinations of timings for the replacement work by multi-objective optimization of the first objective function, the second objective function, and a third objective function related to a third cost according to a party to which the replacement work for each device is requested to be performed before the deadline. As a result, according to the information processing device 100, it is possible to calculate the replacement time that minimizes the sum of the first cost to the third cost, including the third cost that differs for each party to which the replacement work for the device is requested to be performed.

[0201] Furthermore, according to the information processing device 100, the output process outputs one or more calculated combinations and the first cost value and the second cost value corresponding to each of the one or more combinations. As a result, according to the information processing device 100, it is possible to specifically present to the user the combinations of the first cost and the second cost that have a trade-off relationship with each other regarding the replacement times of multiple devices, and the values ​​of the first cost and the second cost.

[0202] The information processing method described in this embodiment can be realized by executing a prepared program on a computer such as a PC or a workstation. The information processing program described in this embodiment is recorded on a computer-readable recording medium and executed by being read from the recording medium by the computer. The recording medium may be a hard disk, a flexible disk, a CD (Compact Disc)-ROM, an MO (Magneto Optical disc), a DVD (Digital Versatile Disc), or the like. The information processing program described in this embodiment may also be distributed via a network such as the Internet.

[0203] The following additional notes are provided regarding the above-described embodiment.

[0204] (Supplementary Note 1) For each of a plurality of devices that are responsible for different tasks among the plurality of tasks that form the target flow, a deadline for performing replacement work that involves stopping the target flow is obtained; calculating one or more combinations of timings for performing the replacement work for each of the devices by performing multi-objective optimization using a first objective function related to a first cost corresponding to a remaining life of each of the devices when the replacement work is performed for each of the devices before the deadline, and a second objective function related to a second cost corresponding to a stoppage period of the target flow due to each of the replacement work when the replacement work is performed for each of the devices before the deadline; outputting the calculated one or more combinations; An information processing program that causes a computer to execute a process.

[0205] (Supplementary Note 2) Based on measurement data previously measured by a sensor provided in each of the devices and the time when the replacement work was previously performed for each of the devices, a model is learned that outputs a deadline for performing the replacement work for each of the devices in response to input of measurement data measured by a sensor provided in the device. causing the computer to execute a process; The acquiring process includes: The information processing program described in Appendix 1, characterized in that for each of the devices, the learned model is used to calculate a deadline for performing the replacement work for the device based on measurement data measured by a sensor installed in the device.

[0206] (Supplementary Note 3) The target flow includes two or more partial flows that operate in parallel and merge into the same partial flow, or branch off from the same partial flow and operate in parallel, 3. The information processing program according to claim 1, wherein the second cost includes a cost corresponding to a period during which any one of the two or more partial flows is stopped due to the replacement work when the replacement work is performed on a device that is responsible for work forming any one of the two or more partial flows.

[0207] (Appendix 4) The information processing program described in Appendix 3, characterized in that the second cost includes a cost corresponding to a period of downtime of any of the two or more partial flows due to the replacement work when the replacement work is performed on a device responsible for the work of forming any of the partial flows of the two or more partial flows, and a weighting coefficient representing the degree of influence of any of the partial flows on the entire target flow.

[0208] (Appendix 5) The calculation process is The information processing program according to claim 1, wherein one or more combinations of timings for performing the replacement work for each of the devices are calculated by performing multi-objective optimization using the first objective function, the second objective function, and a third objective function related to a third cost according to a party to which the replacement work is to be requested before the deadline for each of the devices.

[0209] (Appendix 6) The output process is 2. The information processing program according to claim 1, further comprising: outputting the calculated one or more combinations, and the first cost value and the second cost value corresponding to each of the one or more combinations.

[0210] (Supplementary Note 7) For each of a plurality of devices that are responsible for different tasks among the plurality of tasks that form the target flow, a deadline for performing replacement work that involves stopping the target flow is obtained; calculating one or more combinations of timings for performing the replacement work for each of the devices by performing multi-objective optimization using a first objective function related to a first cost corresponding to a remaining life of each of the devices when the replacement work is performed for each of the devices before the deadline, and a second objective function related to a second cost corresponding to a stoppage period of the target flow due to each of the replacement work when the replacement work is performed for each of the devices before the deadline; outputting the calculated one or more combinations; An information processing method characterized in that the processing is executed by a computer.

[0211] (Supplementary Note 8) For each of a plurality of devices that are responsible for different tasks among the plurality of tasks that form the target flow, a deadline for performing replacement work that involves stopping the target flow is obtained; calculating one or more combinations of timings for performing the replacement work for each of the devices by performing multi-objective optimization using a first objective function related to a first cost corresponding to a remaining life of each of the devices when the replacement work is performed for each of the devices before the deadline, and a second objective function related to a second cost corresponding to a stoppage period of the target flow due to each of the replacement work when the replacement work is performed for each of the devices before the deadline; outputting the calculated one or more combinations; An information processing device comprising a control unit. [Explanation of symbols]

[0212] 100 Information processing device 110 Machine tools (equipment) 150 client devices 202,811 sensors 210 Network 301, 801, 901 CPU 302,802,902 memory 303,803,903 Network I / F 304,904 Recording media I / F 305,905 Recording media 400 Machine tool status information table 500 Maintenance Information Table 600 Line Placement Information Table 700 Machine tool layout information table 810 Operating unit (parts) 812 Touch Panel 910 Input / Output Interface 911 Input Device 912 Display 1001 Storage section 1002 Acquisition Department 1003 Calculation Unit 1004 Output section 1010 Remaining life calculation section 1011 First objective function setting unit 1012 Second objective function setting unit 1013 Multi-objective optimization section 1101 Learning data generation unit 1102 Learning Department 1103 Remaining life inference section 1104 Inference data generation unit 1110 Maintenance Planning Department 1400 Maintenance plan selection screen 1401 Characteristic curve 1411, 1412, 1511~1513 Guide 1500 Maintenance plan details screen

Claims

1. In a case where, for at least two or more devices among a plurality of devices in charge of a plurality of different operations that form a target flow, a common client is requested to perform replacement work involving stopping the target flow, and a third cost is incurred in calling a person who will perform the replacement work to a site according to the client who is requested to perform the replacement work, each time the replacement work is requested, obtaining, for each of the plurality of devices, a remaining usable time until a life limit is reached; calculating a plurality of Pareto solutions each representing a combination of timings for performing the replacement work for each of the devices by performing multi-objective optimization using a first objective function related to a first cost that increases in accordance with the remaining life of each of the devices when the replacement work is performed within the available time for each of the devices, a second objective function related to a second cost that corresponds to a stoppage period of the target flow due to each of the replacement work when the replacement work is performed within the available time for each of the devices, and a third objective function related to a third cost when the replacement work is performed within the available time for each of the devices; displaying at least one of a selection point corresponding to each of the calculated Pareto solutions and a characteristic curve corresponding to a set of the calculated Pareto solutions on a display area having at least the first axis and the second axis out of a first axis corresponding to the first cost, a second axis corresponding to the second cost, and a third axis corresponding to the third cost; An information processing program that causes a computer to execute a process.

2. learning a model that outputs, for each of the devices, the remaining usable time until the device reaches the life limit in response to input of the measurement data measured by the sensor provided in the device, based on measurement data measured in the past by a sensor provided in each of the devices and the time when the replacement work was performed in the past for each of the devices; causing the computer to execute a process; The acquiring process includes: The information processing program according to claim 1, characterized in that for each of the devices, the learned model is used to calculate the remaining usable time until the device reaches the life limit based on measurement data measured by a sensor installed in the device.

3. The target flow includes two or more partial flows that operate in parallel and merge into the same partial flow, or branch off from the same partial flow and operate in parallel, 3. The information processing program according to claim 1, wherein the second cost includes a cost corresponding to a period during which any one of the two or more partial flows is stopped due to the replacement work when the replacement work is performed on a device responsible for work forming any one of the two or more partial flows.

4. The information processing program according to claim 3, characterized in that the second cost includes a cost corresponding to a period of downtime of any of the two or more partial flows due to the replacement work when the replacement work is performed on a device responsible for work forming any of the partial flows of the two or more partial flows, and a weighting coefficient representing the influence of any of the partial flows on the entire target flow.

5. In the case where, for at least two or more devices among a plurality of devices responsible for a plurality of different tasks forming a target flow, a common party is requested to perform replacement work involving the stopping of the target flow, and a third cost is incurred each time the replacement work is requested, in order to summon a person to perform the replacement work to the site according to the party to which the replacement work is requested, obtaining, for each of the plurality of devices, a remaining usable time until a life limit is reached; calculating a plurality of Pareto solutions each representing a combination of timings for performing the replacement work for each of the devices by performing multi-objective optimization using a first objective function related to a first cost that increases in accordance with the remaining life of each of the devices when the replacement work is performed within the available time for each of the devices, a second objective function related to a second cost that corresponds to a stoppage period of the target flow due to each of the replacement work when the replacement work is performed within the available time for each of the devices, and a third objective function related to a third cost when the replacement work is performed within the available time for each of the devices; displaying at least one of a selection point corresponding to each of the calculated Pareto solutions and a characteristic curve corresponding to a set of the calculated Pareto solutions on a display area having at least the first axis and the second axis out of a first axis corresponding to the first cost, a second axis corresponding to the second cost, and a third axis corresponding to the third cost; An information processing method characterized in that the processing is executed by a computer.

6. In the case where, for at least two or more devices among a plurality of devices responsible for a plurality of different tasks forming a target flow, a common party is requested to perform replacement work involving the stopping of the target flow, and a third cost is incurred each time the replacement work is requested, in order to summon a person to the site to perform the replacement work according to the party to which the replacement work is requested, obtaining, for each of the plurality of devices, a remaining usable time until a life limit is reached; calculating a plurality of Pareto solutions each representing a combination of timings for performing the replacement work for each of the devices by performing multi-objective optimization using a first objective function related to a first cost that increases in accordance with the remaining life of each of the devices when the replacement work is performed within the available time for each of the devices, a second objective function related to a second cost that corresponds to a stoppage period of the target flow due to each of the replacement work when the replacement work is performed within the available time for each of the devices, and a third objective function related to a third cost when the replacement work is performed within the available time for each of the devices; displaying at least one of a selection point corresponding to each of the calculated Pareto solutions and a characteristic curve corresponding to a set of the calculated Pareto solutions on a display area having at least the first axis and the second axis out of a first axis corresponding to the first cost, a second axis corresponding to the second cost, and a third axis corresponding to the third cost; An information processing device comprising a control unit.

Images