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

The information processing device addresses the challenge of identifying unsensed abnormalities in production line causal relationships by using a process analysis device to specify, generate, and update event causality, improving maintenance efficiency.

JP7585941B2Active Publication Date: 2024-11-19OMRON CORP
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
JP2021059850
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2021-03-31
Publication Date
2024-11-19
Estimated Expiration
2041-03-31

AI Technical Summary

Technical Problem

Existing technologies struggle to accurately identify causal relationships between mechanisms in a production line, especially when abnormalities cannot be sensed as data, leading to difficulties in pinpointing the true cause of an abnormality.

Method used

An information processing device that includes a relationship identifying unit to specify causal relationships between mechanisms, an event causality generation unit to generate event causality based on event data, and an event causality update unit to update these relationships, incorporating events that cannot be sensed as data, using a process analysis device to manage and update event lists for easy identification.

Benefits of technology

Enables the incorporation of unsensed events into causal relationships, facilitating accurate identification and management of production line abnormalities, thereby enhancing maintenance efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007585941000003
    Figure 0007585941000003
  • Figure 0007585941000004
    Figure 0007585941000004
  • Figure 0007585941000005
    Figure 0007585941000005
Patent Text Reader

Abstract

To provide an information processing device capable of incorporating events that cannot be sensed as data into a causal relation.SOLUTION: An information processing device includes: a relation identification unit that identifies a causal relation between multiple mechanisms or between multiple events related to the multiple mechanisms in a process performed on a manufacturing line; an event causal relation generator that generates an event causal relation based on the causal relation and event data when the event occurs; and an event causal relation updating unit that updates the event causal relation based on the event causal relation and events associated with the multiple mechanisms identified when the event occurred.SELECTED DRAWING: Figure 4
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

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

[0002] A manufacturing line in a factory is composed of multiple mechanisms such as conveyors and robot arms. If an abnormality occurs in any of the mechanisms in this manufacturing line, the manufacturing of products will stop, which can cause significant damage. Therefore, in factories, maintenance personnel regularly patrol the manufacturing line to check for any abnormalities or signs of abnormalities.

[0003] When an abnormality or a sign of an abnormality is detected in a production line, the true cause of the abnormality may exist in a mechanism preceding the mechanism in which the abnormality was detected. Therefore, in order to identify the true cause of the abnormality, it is important to understand the causal relationships of each mechanism in the production line. However, as the number of mechanisms constituting a production line increases and the operating conditions of each mechanism can change daily, it is difficult to accurately understand the causal relationships of all mechanisms.

[0004] Therefore, in the past, experienced maintenance personnel have had to grasp the causal relationships between multiple mechanisms that make up a production line and detect abnormalities or their signs that have occurred in the production line based on their own experience and intuition. In order to enable unskilled maintenance personnel to perform such maintenance work, there has been a demand for the development of technology that visualizes the causal relationships between multiple mechanisms that make up a production line.

[0005] For example, the device disclosed in Patent Document 1 discloses a technique for visualizing the detection of anomalies by easily modeling the relationships between devices in a production line. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] JP 2009-64407 A Summary of the Invention [Problem to be solved by the invention]

[0007] On the other hand, there are types of abnormalities, such as physical phenomena and conditions that cannot be sensed as data, and in such cases, the abnormality cannot be identified even when the above model is used.

[0008] The present disclosure has been made to solve the above-mentioned problems, and aims to provide an information processing device, an information processing method, and an information processing program that are capable of incorporating events that cannot be sensed as data into causal relationships. [Means for solving the problem]

[0009] According to an example of the present disclosure, an information processing device includes a relationship specifying unit that specifies a causal relationship between multiple mechanisms or multiple events related to the multiple mechanisms in a process performed on a manufacturing line, an event causal relationship generating unit that generates an event causal relationship based on the causal relationship and event data when an event occurs, and an event causal relationship updating unit that updates the event causal relationship based on the event causal relationship and events related to the multiple mechanisms confirmed when the event occurs. With this configuration, it is possible to incorporate events that cannot be sensed as data into the causal relationship.

[0010] The event causal relationship includes a plurality of nodes set for a plurality of mechanisms or events, and edge information indicating connections between the plurality of nodes. The event causal relationship update unit adds edge information indicating connections between nodes corresponding to events related to the plurality of mechanisms and nodes that are candidate factors extracted by the event causal relationship. With this configuration, it is possible to easily identify the causal relationship based on the edge information.

[0011] The information processing device further includes an event relation registering unit that registers an event list corresponding to the event by using the updated event causal relations. With this configuration, it is possible to easily manage events by using the event list.

[0012] The event list includes an event summary, event data when the event occurred, possible locations of causes based on the updated event causal relationships, confirmed events related to multiple mechanisms, and event work details. With this configuration, the event list makes it easy to manage various types of event information.

[0013] The information processing device further includes an event estimation unit that acquires the event data and extracts an event list including the same event data as the acquired event data from the event lists registered by the event relation registration unit. With this configuration, it is possible to easily extract the event list.

[0014] An information processing method according to another example of the present disclosure includes steps of identifying a causal relationship between a plurality of mechanisms or a plurality of events related to the plurality of mechanisms in a process performed on a manufacturing line; An information processing method comprising: a step of generating an event causal relationship based on event data when an event occurs; and a step of updating the event causal relationship based on the event relationship and events related to a plurality of mechanisms confirmed when the event occurs. With this configuration, it is possible to incorporate events that cannot be sensed as data into the causal relationship.

[0015] An information processing program according to yet another example of the present disclosure causes a computer to execute the steps of: identifying a causal relationship between a plurality of mechanisms or a plurality of events related to the plurality of mechanisms in a process performed on a manufacturing line; generating an event causal relationship based on event data when an event occurs; and updating the event causal relationship based on the event relationship and the events related to the plurality of mechanisms confirmed when the event occurs. With this configuration, it is possible to incorporate events that cannot be sensed as data into the causal relationship. Effect of the Invention

[0016] According to the present disclosure, it is possible to incorporate events that cannot be sensed as data into causal relationships. [Brief description of the drawings]

[0017] [Figure 1] FIG. 1 is a diagram illustrating an example of a usage scene of a process analysis device 1 that is an information processing device according to an embodiment. [Diagram 2] 1 is a diagram illustrating an example of a hardware configuration of a process analysis device 1 according to an embodiment. [Diagram 3] 2 is a diagram illustrating an example of a hardware configuration of a PLC 2 according to an embodiment. FIG. [Figure 4] FIG. 2 is a diagram illustrating an example of a software configuration of the process analysis device 1 according to the embodiment. [Diagram 5] 4 is a flowchart illustrating an example of a processing procedure of the process analysis device 1 according to the embodiment. [Figure 6] 4 is a diagram for explaining the operation of the first analyzer 113. FIG. [Figure 7] FIG. 11 is a diagram illustrating an example of directed graph information created according to an embodiment. [Figure 8] FIG. 2 is a diagram illustrating an FTA according to an embodiment. [Figure 9] FIG. 11 is a diagram illustrating a flow of modifying an FTA according to an embodiment. [Figure 10]FIG. 11 is a flow diagram illustrating a subroutine of a process of analyzing and editing a node event in second relationship identifying unit 118 according to the embodiment. [Figure 11] FIG. 11 is a conceptual diagram illustrating setting of node attribute information in second relationship identifying unit 118 according to the embodiment. [Figure 12] FIG. 11 is a diagram illustrating node integration according to an embodiment. [Figure 13] 11A to 11C are diagrams for explaining an integration process of an event causal relationship generating unit 116 according to an embodiment. [Figure 14] FIG. 11 is a diagram illustrating a flow of integration processing by an event causal relationship generation unit 116 according to the embodiment. [Figure 15] FIG. 1 is a diagram illustrating a specific example of a data causal model according to an embodiment. [Figure 16] 1A and 1B are diagrams illustrating an example of normal data and abnormal data as an example according to an embodiment. [Figure 17] 1A and 1B are diagrams illustrating data causal models in normal and abnormal states according to an embodiment. [Figure 18] FIG. 2 is a diagram illustrating an event causal model according to an embodiment. [Figure 19] FIG. 1 is a diagram illustrating a usage pattern using an event causal model according to an embodiment. [Figure 20] FIG. 2 is a diagram illustrating a mechanism of a production line of a packaging machine according to an embodiment. [Figure 21] FIG. 1 illustrates an updated event causality model according to an embodiment. [Figure 22] 11 is a flow diagram illustrating an update process of an event causal relation update unit 119 according to the embodiment. FIG. [Figure 23] FIG. 11 is a diagram illustrating an event list in an event relation registration unit 120 according to the embodiment. [Figure 24] FIG. 11 is a diagram illustrating an event estimation process of an event estimation unit 117 according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] The embodiments will be described in detail with reference to the drawings. In the drawings, the same or corresponding parts are denoted by the same reference characters and the description thereof will not be repeated. The modifications described below may be combined as appropriate.

[0019] Hereinafter, an embodiment of a process analysis device, which is one form of an information processing device, will be described with reference to the drawings.

[0020] <1. Application Examples> FIG. 1 is a diagram illustrating an example of a usage scene of a process analysis device 1, which is one form of an information processing device according to an embodiment. As shown in FIG. 1, the process analysis device 1 according to an embodiment acquires a plurality of status data 222 and log data 223 related to the status of a plurality of mechanisms 31 constituting a production line 3. The production line 3 may be composed of a plurality of devices or a single device such as a packaging machine as long as it is capable of manufacturing something. Furthermore, each mechanism 31 may be composed of one or a plurality of devices or may be composed of a part of a device as long as it is capable of performing some process of the production process. When one mechanism 31 is composed of a part of a device, the multiple mechanisms 31 may be composed of a single device. Furthermore, when the same device performs a plurality of processes, each may be regarded as a different mechanism 31. For example, when the same device performs a first process and a second process, the device performing the first process may be regarded as a first mechanism 31, and the device performing the second process may be regarded as a second mechanism 31. Furthermore, the status data 222 may include any kind of data related to the status of each mechanism 31 constituting the production line 3.

[0021] Moreover, the process analysis device 1 according to the embodiment acquires a control program 221 for controlling the operation of the manufacturing line 3. The control program 221 may include any kind of program for controlling the operation of each mechanism 31 constituting the manufacturing line 3. The control program 221 may be composed of one program or multiple programs. In the embodiment, the operation of the manufacturing line 3 is controlled by a PLC (programmable logic controller) 2. Therefore, the process analysis device 1 acquires multiple items of status data 222, log data 223, and control program 221 from the PLC 2.

[0022] Next, the process analysis device 1 according to the embodiment specifies the strength of the relationship between the multiple mechanisms 31 in the production line 3 by statistically analyzing the multiple acquired state data 222. The strength of the relationship is an example of the "connection state" of the present disclosure. Furthermore, the process analysis device 1 according to the embodiment specifies the order relationship between the multiple mechanisms 31 in the production line 3 by analyzing the acquired control program 221 and log data 223. Then, the process analysis device 1 according to the embodiment specifies the causal relationship (first causal relationship) between the multiple mechanisms 31 in the process executed in the production line 3 based on the strength and order relationship of the relationship respectively specified. In the embodiment, in the process of analyzing the causal relationship (first causal relationship) between the multiple mechanisms 31, the control program 221 is used to specify the order relationship between the multiple mechanisms 31. Since the control program 221 specifies the operation of each mechanism 31, the order relationship between each mechanism 31 can be specified more accurately by using the control program 221.

[0023] The process analysis device 1 according to the embodiment identifies a causal relationship (second causal relationship) between a plurality of events related to a plurality of mechanisms 31 in a process performed in a manufacturing line 3 according to a user setting.

[0024] The second causal relationship corresponds to a causal relationship between a plurality of events based on the failure mechanisms of a plurality of mechanisms 31 in the processes carried out in the manufacturing line 3. For example, it corresponds to a Fault Tree Analysis (FTA) created by an expert.

[0025] The process analysis device 1 according to the embodiment integrates the second causal relationship and generates an event causal relationship for the first causal relationship by using normal data and abnormal data (event data). According to the embodiment, by generating the event causal relationship, it is possible to accurately model the causal relationships between the multiple mechanisms 31 constituting the processes performed in the manufacturing line 3 with higher accuracy.

[0026] The process analysis device 1 according to the embodiment extracts candidate factors based on the event causal relationships. A user specifies an occurrence in which an event related to a plurality of mechanisms 31 occurs in a process performed on a production line 3 according to the extracted candidate factors.

[0027] The process analysis device 1 according to the embodiment updates the event causal relationship based on the event causal relationship and events related to the multiple mechanisms 31 confirmed when the identified event occurred.

[0028] This updates the event causal relationships, improving the accuracy of extracting candidate factors when an event occurs. It is also possible to incorporate events that cannot be sensed as data into the causal relationships.

[0029] <2. Hardware configuration of process analysis device> Fig. 2 is a diagram illustrating an example of a hardware configuration of the process analysis device 1 according to the embodiment. As shown in Fig. 2, the process analysis device 1 according to the embodiment is a computer to which a control unit 11, a storage unit 12, a communication interface 13, an input device 14, an output device 15, and a drive 16 are electrically connected. In Fig. 2, the communication interface is described as a "communication I / F".

[0030] The control unit 11 includes a hardware processor such as a central processing unit (CPU), a random access memory (RAM), and a read only memory (ROM), and controls each component in response to information processing. The storage unit 12 is an auxiliary storage device such as a hard disk drive or a solid state drive, and stores a process analysis program 121 to be executed by the control unit 11, etc.

[0031] The process analysis program 121 is a program for causing the process analysis device 1 to execute a process of analyzing the causal relationships between multiple mechanisms 31 in the manufacturing process performed by the manufacturing line 3, using multiple items of status data 222, log data 223, and the control program 221.

[0032] The communication interface 13 is, for example, a wired LAN (Local Area Network) module, a wireless LAN module, etc., and is an interface for performing wired or wireless communication via a network. The process analysis device 1 can perform data communication with the PLC 2 via the network by using this communication interface 13. The type of network may be appropriately selected from, for example, the Internet, a wireless communication network, a mobile communication network, a telephone network, a dedicated network, etc.

[0033] The input device 14 is a device for performing input, such as a mouse, a keyboard, etc. The output device 15 is a device for performing output, such as a display, a speaker, etc. An operator can operate the process analysis apparatus 1 via the input device 14 and the output device 15.

[0034] The drive 16 is, for example, a CD drive, a DVD drive, or the like, and is a drive device for reading a program stored in the storage medium 91. The type of the drive 16 may be appropriately selected according to the type of the storage medium 91. The process analysis program 121 may be stored in this storage medium 91.

[0035] The storage medium 91 is a medium that stores information such as a program by electrical, magnetic, optical, mechanical, or chemical action so that a computer or other device, machine, etc. can read the recorded information such as the program. The process analysis apparatus 1 may obtain the process analysis program 121 from the storage medium 91.

[0036] 2, a disk-type storage medium such as a CD or a DVD is illustrated as an example of the storage medium 91. However, the type of the storage medium 91 is not limited to the disk type, and may be other than the disk type. Examples of storage media other than the disk type include semiconductor memories such as flash memories.

[0037] Regarding the specific hardware configuration of the process analysis apparatus 1, components can be omitted, replaced, or added as appropriate depending on the embodiment. For example, the control unit 11 may include multiple processors. The process analysis apparatus 1 may be composed of multiple information processing devices. Furthermore, the process analysis apparatus 1 may be an information processing device designed specifically for the services provided, as well as a general-purpose server device, a PC (Personal Computer), etc.

[0038] <3.PLC> Fig. 3 is a diagram illustrating an example of a hardware configuration of the PLC 2 according to the embodiment. As shown in Fig. 3, the PLC 2 is a computer to which a control unit 21, a storage unit 22, an input / output interface 23, and a communication interface 24 are electrically connected. As a result, the PLC 2 is configured to control the operation of each mechanism 31 of the production line 3. In Fig. 3, the input / output interface and the communication interface are described as an "input / output I / F" and a "communication I / F", respectively.

[0039] The control unit 21 includes a CPU, RAM, ROM, etc., and is configured to execute various information processing based on programs and data. The storage unit 22 is composed of, for example, RAM, ROM, etc., and stores a control program 221, status data 222, log data 223, etc. The control program 221 is a program for controlling the operation of the production line 3. The status data 222 is data related to the status of each mechanism 31. The log data 223 is data indicating a log of the operation of the production line 3.

[0040] The input / output interface 23 is an interface for connecting to an external device, and is configured appropriately according to the external device to be connected. In the embodiment, the PLC 2 is connected to the production line 3 via the input / output interface 23. When different status data can be acquired for a single device, the target single device may be regarded as multiple mechanisms 31 or as a single mechanism 31. Therefore, the number of input / output interfaces 23 may be the same as the number of mechanisms 31 constituting the production line 3, or may be different from the number of mechanisms 31 constituting the production line 3.

[0041] The communication interface 24 is, for example, a wired LAN module, a wireless LAN module, etc., and is an interface for performing wired or wireless communication. The PLC 2 can perform data communication with the process analysis device 1 through the communication interface 24.

[0042] Regarding the specific hardware configuration of PLC2, components can be omitted, replaced, or added as appropriate depending on the embodiment. For example, control unit 21 may include multiple processors. Storage unit 22 may be configured with RAM and ROM included in control unit 21. Storage unit 22 may be configured with auxiliary storage devices such as hard disk drives and solid state drives. Furthermore, PLC2 may be replaced with an information processing device designed specifically for the services provided, as well as a general-purpose desktop PC, tablet PC, or the like depending on the target to be controlled.

[0043] <4. Software configuration of process analysis device> Fig. 4 is a diagram illustrating an example of a software configuration of the process analysis apparatus 1 according to the embodiment. As shown in Fig. 4, the control unit 11 of the process analysis apparatus 1 loads the process analysis program 121 stored in the storage unit 12 in the RAM. Then, the control unit 11 interprets and executes the process analysis program 121 loaded in the RAM by the CPU to control each component. As a result, as shown in Fig. 4, the process analysis apparatus 1 according to the embodiment includes, as software modules, a first acquisition unit 111, a second acquisition unit 112, a first analysis unit 113, a second analysis unit 114, a first relationship identification unit 115, an event causal relationship generation unit 116, a second relationship identification unit 118, an event causal relationship update unit 119, an event relationship registration unit 120, and an event estimation unit 117.

[0044] The first acquisition unit 111 acquires a plurality of status data 222 related to the status of a plurality of mechanisms 31 constituting the production line 3. The second acquisition unit 112 acquires a control program 221 for controlling the operation of the production line 3. The first analysis unit 113 identifies the strength of the relationship between the plurality of mechanisms 31 by statistically analyzing the acquired plurality of status data 222. The second analysis unit 114 identifies the order relationship between the plurality of mechanisms 31 by analyzing the acquired control program 221. In the embodiment, the second analysis unit 114 identifies the order relationship between the plurality of mechanisms 31 by using log data 223 obtained by executing the control program 221. Then, the first relationship identification unit 115 identifies a causal relationship (first causal relationship) between the plurality of mechanisms 31 in the process performed in the production line 3 based on the strength of the relationship and the order relationship respectively identified.

[0045] The second relationship identifying unit 118 identifies a causal relationship (a second causal relationship) between a plurality of events related to a plurality of mechanisms 31 in a process performed in the manufacturing line 3 according to a user setting.

[0046] The event causal relation generating unit 116 integrates the second causal relation and generates an event causal relation for the first causal relation by using the normal data 224 and the abnormal data 225 (event data).

[0047] The event causal relationship generation unit 116 extracts candidate factors of the event based on the event causal relationship. The user specifies an occurrence of an event related to the multiple mechanisms 31 in a process performed on the production line 3 according to the candidate factors extracted based on the event causal relationship.

[0048] The event causality update unit 119 updates the event causality based on the event causality and events related to the multiple mechanisms 31 confirmed when the identified event occurred.

[0049] The event relation registration unit 120 registers an event list corresponding to an event. The event list includes an event summary, event data when the event occurred, candidate cause positions based on the updated event causal relationships, confirmed events related to multiple mechanisms, and event work contents.

[0050] The event estimation unit 117 acquires event data and extracts an event list including the same event data as the acquired event data from among the event lists registered by the event relation registration unit 120. The event estimation unit 117 outputs the extracted event list, so that the user can easily identify candidate causes of the event and can quickly perform recovery work by checking the contents of the event work.

[0051] In this example, a configuration will be described for the case where the second causal relationship is identified using the second relationship identifying unit 118 in the process analysis apparatus 1, but the second relationship identifying unit 118 does not necessarily have to be included in the process analysis apparatus 1. Also, a method will be described in which the event causal relationship generation unit 116 integrates the first causal relationship and the second causal relationship, but this is not limiting, and the event causal relationship may be generated based on only one of the first causal relationship or the second causal relationship.

[0052] Each software module of the process analysis apparatus 1 will be described in detail in an operation example described later. In the embodiment, an example is described in which each software module of the process analysis apparatus 1 is realized by a general-purpose CPU. However, some or all of the above software modules may be realized by one or more dedicated hardware processors. Furthermore, with regard to the software configuration of the process analysis apparatus 1, software modules may be omitted, replaced, or added as appropriate depending on the embodiment.

[0053] <5.1 First causal relationship> 5 is a flow diagram illustrating an example of a processing procedure of the process analysis device 1 according to the embodiment. However, the processing procedure described below is merely an example, and each process may be changed as much as possible. In addition, steps may be omitted, replaced, or added to the processing procedure described below as appropriate depending on the embodiment.

[0054] First, in step S101, the control unit 11 operates as the first acquisition unit 111 and acquires a plurality of status data 222 related to the status of each mechanism 31 from the PLC 2. Each mechanism 31 may be, for example, a conveyor, a robot arm, a servo motor, a cylinder (such as a molding machine), a suction pad, a cutter device, a sealing device, or a part of such a device. Also, each mechanism 31 may be, for example, a composite device such as a printer, a mounting machine, a reflow oven, or a substrate inspection device. Furthermore, each mechanism 31 may include devices that perform internal processing, such as a device that detects some information using various sensors, a device that acquires data from various sensors, a device that detects some information from the acquired data, and a device that processes the acquired data, in addition to the devices that perform some physical operations as described above. As a specific example, in a manufacturing line equipped with an optical sensor that detects a mark given to an object moving on a conveyor, the optical sensor and a device that uses the information detected by the optical sensor may be treated as each mechanism 31. Furthermore, the status data 222 for each item may be data indicating at least one of torque, speed, acceleration, temperature, current, voltage, air pressure, pressure, flow rate, position, dimensions (height, length, width), and area. Such status data 222 can be obtained by known measuring devices such as sensors and cameras. For example, the flow rate can be obtained by a float sensor. Furthermore, the position, dimensions, and area can be obtained by an image sensor.

[0055] The status data 222 may be composed of data obtained from one or more measuring devices. The status data 222 may be data obtained directly from the measuring device, or may be data obtainable by applying some processing to data obtained from the measuring device, such as position data obtained from image data. The status data 222 for each case is obtained corresponding to each mechanism 31.

[0056] Each measuring device is appropriately positioned so as to be able to monitor each mechanism 31 of the production line 3. The PLC 2 operates the production line 3 and collects status data 222 for each item from each measuring device. The control unit 11 acquires, from the PLC 2, status data 222 relating to the status of each mechanism 31 when the production line 3 is operating normally. This allows the control unit 11 to acquire multiple items of status data 222. When acquisition of multiple items of status data 222 is completed, the control unit 11 proceeds to the next step S102.

[0057] In the next step S102, the control unit 11 operates as the second acquisition unit 112 and acquires the control program 221 from the PLC 2. The control program 221 may be written using at least one of, for example, a ladder diagram language, a function block diagram language, a structured text language, an instruction list language, a sequential function chart language, and a C language so that the control program 221 can be executed by the PLC 2. When the acquisition of the control program 221 is completed, the control unit 11 advances the process to the next step S103. Note that step S102 may be executed in parallel with the above step S101, or may be executed before the above step S101.

[0058] In the next step S103, the control unit 11 operates as the first analysis unit 113 and identifies the strength of the relationship between the multiple mechanisms 31 in the production line 3 by statistically analyzing the multiple items of status data 222 acquired in step S101. When the analysis process of the multiple items of status data 222 is completed, the control unit 11 proceeds to the next step S104. Note that step S103 may be executed at any timing after the above step S101. For example, step S103 may be executed before the above step S102.

[0059] In the following explanation, for the sake of convenience, it is assumed that the production line 3 has four mechanisms (e.g., four servo motors) F1 to F4 as the multiple mechanisms 31, and that in step S101 above, the control unit 11 has acquired the status data 222 of each of the mechanisms F1 to F4.

[0060] FIG. 6 is a diagram for explaining the operation of the first analysis unit 113. As shown in FIG. 6, the control unit 11 calculates the feature amount 2221 from the state data 222 of each case acquired in step S101. The type of the feature amount 2221 is not particularly limited and may be appropriately selected according to the embodiment. In addition, the method of calculating the feature amount 2221 can be appropriately determined according to the embodiment. As a specific example, in the embodiment, the control unit 11 calculates the feature amount 2221 from the state data 222 by the following method. First, the control unit 11 divides the acquired state data 222 of each case into frames to define the processing range for calculating the feature amount 2221. The length of each frame may be appropriately set according to the embodiment.

[0061] For example, the control unit 11 may divide each item of status data 222 into frames of a certain time length.

[0062] Next, the control unit 11 calculates the value of the feature amount 2221 from each frame of the state data 222. When the state data 222 is continuous value data such as measurement data, the control unit 11 may calculate, for example, the amplitude, maximum value, minimum value, average value, variance value, standard deviation, instantaneous value (one-point sample) and the like in the frame as the feature amount 2221. When the state data 222 is discrete value data such as detection data, the control unit 11 may calculate, for example, the "on" time, "off" time, duty ratio, "on" count, "off" count and the like in each frame as the feature amount 2221. When the calculation of each feature amount 2221 is completed, the control unit 11 calculates the correlation coefficient or partial correlation coefficient between each feature amount 2221. The correlation coefficient can be calculated by the following formula 1. The partial correlation coefficient can be calculated by the following formula 2.

[0063]

number

[0064] In addition, r ij indicates the element in the i-th row and j-th column of the matrix 2222. i and x j corresponds to data indicating the feature amount 2221 calculated from the state data 222 of each case. i and X j are x i and x j indicates the sample mean of each feature 2221 used to calculate the correlation.

[0065]

number

[0066] Note that the matrix R(r ij ) inverse matrix in R -1 (r ij ) and r ij indicates the element in the i-th row and j-th column of the inverse matrix of matrix 2222.

[0067] This allows the control unit 11 to obtain a matrix 2222 having correlation coefficients or partial correlation coefficients as each element. The correlation coefficients and partial correlation coefficients between each feature amount 2221 indicate the strength of the relationship between the corresponding mechanisms 31. That is, the strength of the relationship between the corresponding mechanisms 31 is specified by each element of the matrix 2222. Upon completing the calculation of the correlation coefficients or partial correlation coefficients between each feature amount 2221, the control unit 11 constructs undirected graph information 2223 indicating the strength of the relationship between the corresponding mechanisms 31 based on the correlation coefficients or partial correlation coefficients between each feature amount 2221.

[0068] For example, the control unit 11 creates a node corresponding to each mechanism 31. Then, when the value of the correlation coefficient or partial correlation coefficient calculated between two mechanisms 31 is equal to or greater than the threshold, the control unit 11 connects the two corresponding nodes with an edge. On the other hand, when the value of the correlation coefficient or partial correlation coefficient calculated between two mechanisms 31 is less than the threshold, the control unit 11 does not connect the two corresponding nodes with an edge. The threshold may be a fixed value defined in the process analysis program 121, or may be a setting value that can be changed by an operator or the like. The thickness of the edge may be determined according to the magnitude of the value of the corresponding correlation coefficient or partial correlation coefficient.

[0069] As a result, it is possible to create the undirected graph information 2223 as illustrated. In the example, four nodes corresponding to the four mechanisms F1 to F4 are created. Then, edges are formed between the nodes of the mechanisms F1 and F2, between the nodes of the mechanisms F1 and F3, between the nodes of the mechanisms F2 and F3, and between the nodes of the mechanisms F3 and F4. In addition, since the correlation between the mechanisms F1 and F3 and between the mechanisms F3 and F4 is greater than the correlation between the other mechanisms, the edges between the nodes of the mechanisms F1 and F3 and between the nodes of the mechanisms F3 and F4 are formed thicker than the other edges. When the construction of the undirected graph information 2223 indicating the strength of the relationship between the multiple mechanisms 31 is completed as described above, the analysis process of the state data 222 according to the embodiment is completed, and the control unit 11 proceeds to the next step S104.

[0070] In the example, the undirected graph information 2223 expresses the formed undirected graph by an image. However, the output format of the undirected graph information 2223 is not limited to an image, and may be expressed by text or the like. In the above example, an edge is not formed between nodes (mechanisms 31) with a weak relationship by comparing the correlation coefficient or partial correlation coefficient with a threshold value. However, the method of removing edges between nodes with a weak relationship is not limited to this example. For example, after forming a graph in which all nodes are connected by edges, the control unit 11 may delete edges of the formed graph in order from the edge with the smallest correlation coefficient or partial correlation coefficient so that the goodness of fit index (GFI, SRMR, etc.) representing the deviation does not exceed a threshold value.

[0071] Returning to FIG. 5, in the next step S104, the control unit 11 operates as the second analysis unit 114 and identifies the order relationship of the multiple mechanisms 31 in the production line 3 by analyzing the control program 221 acquired in step S102. In the embodiment, the control unit 11 identifies the order relationship of the multiple mechanisms 31 based on the log data 223 obtained by operating the production line 3 using the control program 221. When the analysis process of the control program 221 is completed, the control unit 11 proceeds to the next step S105. Note that step S104 may be executed at any timing after the above step S102. For example, when the above step S102 is executed before the above step S101, step S104 may be executed before the above step S101.

[0072] A detailed description will be given of the process of analyzing the control program 221. In the following description, for convenience of explanation, it is assumed that, as in the above, the production line 3 includes four mechanisms F1 to F4 as the multiple mechanisms 31, and in the above step S102, the control unit 11 has acquired the control program 221 in which the variables v1 to v4 corresponding to the four mechanisms F1 to F4 are used.

[0073] The control unit 11 acquires from the PLC 2 the log data 223 indicating the execution result when the manufacturing line 3 is normally operated using the control program 221. For example, when collecting the above-mentioned status data 222, the PLC 2 may also create the log data 223 indicating the execution result of the control program 221. In this case, a time stamp, values ​​of variables used, and the like are recorded in the log data 223. Also, for example, the control program 221 may be provided with a debug mode for collecting information such as the frequency at which each code line is executed, the executed code lines, and the calculation time consumed by each section of the code. In this case, the PLC 2 can create the log data 223 in which each piece of information is recorded by executing the control program 221 in the debug mode. The control unit 11 may acquire the log data 223 created in this way from the PLC 2. When the acquisition of the log data 223 is completed, the control unit 11 refers to the acquired log data 223 and sequentially orders the above-mentioned variables (v1 to v4) to identify the order relationship of each mechanism 31 in the manufacturing line 3.

[0074] When the sequential order relationship of the multiple mechanisms 31 has been specified as described above, the analysis process of the control program 221 according to the embodiment is completed, and the control unit 11 advances the process to the next step S105.

[0075] 5, in the next step S105, the control unit 11 operates as a first relationship identifying unit 115. That is, the control unit 11 identifies a causal relationship between the multiple mechanisms 31 in the processes performed in the production line 3, based on the strength of the relationship and the order relationship between the multiple mechanisms 31 in the production line 3 identified in steps S103 and S104, respectively.

[0076] In the embodiment, the control unit 11 creates directed graph information indicating the causal relationships between the mechanisms 31 by applying the order relationships of the identified mechanisms 31 to the constructed undirected graph information 2223 .

[0077] 7 is a diagram illustrating an example of directed graph information created according to an embodiment. The directed graph 122 in FIG. 7 shows the following causal relationships (a) to (d). (a) Of the mechanisms "F1" to "F4," mechanism "F1" or "F2" is used first. (b) After mechanisms "F1" and "F2", mechanism "F3" is utilized. (c) After mechanism "F3", mechanism "F4" is used. (d) Of the mechanisms "F1" to "F4," mechanism "F4" is used last.

[0078] Furthermore, the thickness of each edge of the directed graph 122 is set corresponding to the thickness of each edge of the undirected graph information 2223. When the creation of the directed graph information is completed as described above, the control unit 11 advances the process to the next step S106.

[0079] In the example of FIG. 7, the directed graph information expresses the directed graph (directed graph 122) by an image. However, the output format of the directed graph information is not limited to an image, and may be expressed by text, etc. In the above example, the strength of the relationship between the nodes (mechanisms 31) is expressed by the thickness of the edge. However, the method of expressing the strength of the relationship between the nodes is not limited to this example. The strength of the relationship between each node may be expressed by adding a number near each edge.

[0080] In the next step S106, the control unit 11 outputs the directed graph information (first causal relationship) created in step S105. Specifically, the first relationship identifying unit 115 outputs effective graph information indicating the generated causal relationship to the event causal relationship generating unit 116. With the above, the control unit 11 ends the process of generating the first causal relationship according to this operation example.

[0081] As described above, in the embodiment, the control program 221 is analyzed in step S104 to identify the order relationship between the multiple mechanisms 31 in the production line 3. Then, the order relationship identified from the control program 221 is applied to the undirected graph information indicating the strength of the relationship derived from the state data 222 in step S103 to create directed graph information indicating the causal relationship between the multiple mechanisms 31 in the process performed in the production line 3. Here, the control program 221 specifies the operation of each mechanism 31. Therefore, in the process of analyzing the causal relationship between the multiple mechanisms 31, the control program 221 can be used to appropriately identify the order relationship between the multiple mechanisms 31. Therefore, according to the embodiment, the causal relationship between the multiple mechanisms 31 constituting the production line 3 can be accurately modeled.

[0082] <5.2 Second causal relationship> Fig. 8 is a diagram for explaining an FTA according to an embodiment. Fig. 8 shows, as an example, an Fault Tree Analysis (FTA) created by an expert for the packaging machine production line 3. The FTA corresponds to effective graph information indicating the causal relationships between a plurality of events occurring in the packaging machine production line 3.

[0083] Specifically, each event is shown in the form of a node, and nodes N0 to N15 (collectively referred to as node N) are provided. Nodes N0 ("cannot seal") and N1 ("weak adhesion") are provided corresponding to the final two events. Nodes N2 to N8 corresponding to other events leading up to nodes N0 and N1 are provided based on causal relationships.

[0084] With respect to node N0, node N2 ("inaccurate temperature measurement"), node N3 ("weak sealing pressure"), node N4 ("sealer surface not sufficiently heated"), node N5 ("temperature cannot be measured"), node N6 ("inappropriate temperature (film transport main / sub speed and sealing temperature do not match)"), node N7 ("inappropriate temperature (film thickness and sealing temperature do not match)"), and node N8 ("sealing temperature does not rise") are set as causally related events.

[0085] A node N6 ("Temperature unsuitable (film transport main / sub-speed and sealing temperature do not match)") is provided for node N1.

[0086] Then, nodes N9 to N15 corresponding to other events leading up to the nodes N2 to N8 are provided based on causal relationships.

[0087] A node N9 ("thermocouple deterioration") is provided for node N2. A node N10 ("press roller wear") and a node N11 ("press spring deterioration") are provided for node N3. A node N11 ("warm-up procedure ignored / no procedure") is provided for node N4. A node N12 ("thermocouple disconnection") is provided for node N5. A node N13 ("set temperature, conveying speed setting error") is provided for node N6. A node N14 ("set temperature, film thickness setting error") is provided for node N7. A node N15 ("heater deterioration") is provided for node N8.

[0088] Fig. 9 is a diagram illustrating a flow of correcting an FTA according to an embodiment. The process in Fig. 9 is a process in second relationship identifying unit 118. Second relationship identifying unit 118 analyzes and edits events of a node (step S2). Second relationship identifying unit 118 has a user interface that accepts input from a user, and may execute a process based on the user input as necessary.

[0089] Next, the second relationship identifying unit 118 integrates the edited nodes (step S4).

[0090] Then, the process ends (END).

[0091] Fig. 10 is a flow diagram illustrating a subroutine of a process of analyzing and editing an event of a node in second relationship identifying unit 118 according to an embodiment. With reference to Fig. 10, second relationship identifying unit 118 selects a node (step S10). For example, it selects one of the nodes (N0) described in Fig. 8. Next, second relationship identifying unit 118 extracts a physical quantity or a state from the event corresponding to the selected node (step S12).

[0092] For example, the second relationship identifying unit 118 extracts a physical quantity ("sealing adhesive strength") based on the event of "unsealable" at node N0. Similarly, the second relationship identifying unit 118 extracts a physical quantity ("sealing adhesive strength") based on the event of "weak adhesion" at node N1. The physical quantity or state for the event is extracted by referring to a physical quantity / state correspondence table that is provided in advance and in which physical quantities or states are associated with events. If a corresponding physical quantity or state does not exist in the physical quantity / state correspondence table, the user may input the physical quantity or state via a user interface. The physical quantity / state correspondence table may be updated as needed by the user inputting the physical quantity or state via the user interface. It is not necessary for the event and the physical quantity or state to be associated one-to-one, and the physical quantity or state may be extracted based on the degree of association related to the event.

[0093] Next, the second relationship identifying unit 118 identifies a variable from the extracted physical quantity or state (step S14). For example, the second relationship identifying unit 118 identifies a variable ("CurrentTemperature CenterSeal") from a physical quantity ("Seal Temperature"). In identifying a variable from the extracted physical quantity or state, a variable correspondence table in which variables are associated with physical quantities or states is provided in advance, and the variable is identified by referring to the variable correspondence table. If a corresponding variable does not exist in the variable correspondence table, the user may input the variable via a user interface. A method for the user to input the variable via a user interface will be described later.

[0094] The variable correspondence table may be updated at any time by the user's input via the user interface.

[0095] Next, the second relationship specifying unit 118 determines whether or not a plurality of variables have been specified from the extracted physical quantities or states (step S16).

[0096] In step S16, if second relationship identifying unit 118 determines that a plurality of variables have not been identified (NO in step S16), it sets attribute information of the node (step S18).

[0097] On the other hand, if second relationship identifying unit 118 determines in step S16 that a plurality of variables have been identified (YES in step S16), it divides the node (step S20). Next, the process proceeds to step S18, where attribute information of the node is set.

[0098] Next, second relationship identifying unit 118 determines whether or not the analysis of all nodes has been completed (Step S22).

[0099] In step S22, if second relationship identifying unit 118 determines that analysis of all nodes has been completed (YES in step S22), it ends the processing (returns).

[0100] On the other hand, in step S22, if second relationship identifying unit 118 determines that analysis of all nodes has not been completed (NO in step S22), the process proceeds to step S24.

[0101] In step S24, second relationship identifying unit 118 selects another node, and then returns to step S12 to repeat the above processing.

[0102] FIG. 11 is a conceptual diagram for explaining setting of attribute information of nodes in second relationship identifying unit 118 according to an embodiment. Referring to FIG. 11(A), a data structure of attribute information provided corresponding to each node is shown. As an example, three-layered data D1 to D3 are provided as attribute information corresponding to each node. In this example, extracted physical quantity or state information is set in the first layer data D1 as attribute information corresponding to each node. Event information is set in the second layer data D2. Variables are set in the third layer data D3. Note that this data structure is an example, and any order may be used.

[0103] Referring to FIG. 11(B), a case is shown in which a physical quantity ("film transport main / sub speed and seal temperature") is extracted for node N6.

[0104] 11(C), a case is shown in which it is determined that multiple variables have been identified for node N7 because there are separate variables for the physical quantity ("film feed main speed"), the physical quantity ("film feed sub speed"), and the physical quantity ("sealing temperature"). In this example, a case is shown in which a variable ("FilmFeedMain") has been identified for the physical quantity ("film feed main speed"), a variable ("FilmFeedSub") has been identified for the physical quantity ("film feed sub speed"), and a variable ("CurrentTemperature CenterSeal") has been identified for the physical quantity ("sealing temperature").

[0105] Therefore, in this case, the node is split. A case is shown in which nodes N16 and N17 are provided as split nodes.

[0106] 11(D) shows a case where attribute information is set for each of nodes N6, N16, and N17. Specifically, data D1 ("film transport main speed"), data D2 ("unsuitable temperature"), and data D3 ("FilmFeedMain") are set as attribute information corresponding to node N6. Data D1 ("film transport sub speed") and data D3 ("FilmFeedSub") are set as attribute information corresponding to node N16. Data D1 ("sealing temperature"), data D2 ("unsuitable temperature"), and data D3 ("CurrentTemprature CenterSeal") are set as attribute information corresponding to node N17.

[0107] The above process is executed for each node in turn.

[0108] 12 is a diagram for explaining node integration according to an embodiment of the present invention, which illustrates a case where nodes after editing are integrated with reference to FIG.

[0109] There are various integration methods, but as an example, integration is performed based on physical quantity or state information included in the attribute information corresponding to each node N. In other words, if the physical quantity or state information included in the attribute information corresponding to each node N is the same, the nodes are integrated. For example, nodes N0 and N1 in FIG. 8 are provided as an integrated node N20 because the same physical quantity ("sealing adhesive strength") is extracted from both. Data D1 ("sealing adhesive strength"), data D2 ("cannot seal, weak adhesion"), and data D3 ("none") are set as attribute information for node N20. In addition, edge information (arrow information) of causal relationships is also integrated.

[0110] Similarly, integrated nodes N21 to N32 are provided. In the case of integration, the attribute information of each node is set such that data D1 and D3 are common, but D2 has additional information added.

[0111] As attribute information of node N21, data D1 ("Seal temperature"), data D2 ("Measurement inaccurate, temperature does not rise, temperature inappropriate, temperature cannot be measured"), and data D3 ("Current Temperature Center Seal") are set.

[0112] As attribute information of the node N22, data D1 ("sealing pressure"), data D2 ("weak sealing pressure"), and data D3 ("none") are set.

[0113] As attribute information of the node N23, data D1 ("film transport main speed"), data D2 ("unsuitable temperature"), and data D3 ("FilmFeedMain") are set.

[0114] As attribute information of the node N24, data D1 ("film transport sub-speed"), data D2 ("unsuitable temperature"), and data D3 ("FilmFeedSub") are set.

[0115] As attribute information for node N25, data D1 ("film thickness"), data D2 ("unsuitable temperature"), and data D3 ("none") are set.

[0116] As attribute information of node N26, data D1 ("thermocouple state"), data D2 ("disconnection, deterioration"), and data D3 ("absent") are set.

[0117] As attribute information of node N27, data D1 ("warm-up procedure status"), data D2 ("ignored, no procedure"), and data D3 ("none") are set.

[0118] As the attribute information of the node N28, data D1 ("heater state"), data D2 ("deteriorated"), and data D3 ("absent") are set.

[0119] As attribute information of the node N29, data D1 ("Sealer set temperature"), data D2 ("Setting error"), and data D3 ("CenterHeaterDPC_MV") are set.

[0120] As the attribute information of the node N30, data D1 ("press roller state"), data D2 ("press roller wear"), and data D3 ("none") are set.

[0121] As attribute information of the node N31, data D1 ("press spring state"), data D2 ("press spring deterioration"), and data D3 ("none") are set.

[0122] As attribute information of node N31, data D1 ("film transport speed setting"), data D2 ("setting error"), and data D3 ("FilmFeed_MV") are set.

[0123] Through the above process, nodes N21 to N25 are provided as nodes having a causal relationship with node N20. In addition, nodes N26 to N29 are provided as nodes having a causal relationship with node N21. Nodes N30 and N31 are provided as nodes having a causal relationship with node N22. Node N23 is provided as a node having a causal relationship with node N32.

[0124] The control unit 11 outputs effective graph information (second causal relations) corrected based on the effective graph information of the FTA. Specifically, the second relation identifying unit 118 identifies effective graph information (second causal relations) indicating the causal relations between a plurality of events related to a plurality of mechanisms 31 in the process performed in the manufacturing line 3 according to the user setting. The event causal relation generating unit 116 acquires effective graph information (second causal relations) indicating the causal relations between a plurality of events from the second relation identifying unit 118.

[0125] <5.3 Integration process> 13A and 13B are diagrams for explaining the integration process of the event causal relationship generation unit 116 according to the embodiment. With reference to Fig. 13A, in this example, a method for integrating the effective graph information (first causal relationship) output from the first relationship identification unit 115 and the effective graph information (second causal relationship) output from the second relationship identification unit 118 is shown as an example.

[0126] As will be described later, an event causal relationship (event causal model) is generated based on the valid graph information (first causal relationship) output from the first relationship identifying unit 115, the normal data 224 and the abnormal data 225.

[0127] The event causal relationship generating unit 116 generates an event causal model by integrating the generated event causal model with the FTA causal model, which is the effective graph information (second causal relationship) output from the second relationship identifying unit 118.

[0128] For the sake of simplicity, the event causal model includes nodes A1 to A5, and the FTA causal model includes nodes B1 to B4 and a node A2.

[0129] 13B, a node of the FTA causal model is added to a node of the event causal model. Also, nodes having the same variables are merged into one node. Here, a case where node A2 is merged into one node is shown.

[0130] 13(C) shows a case where edge information of the FTA causal model is added to the event causal model to which the node of the FTA causal model is added. This makes it possible to integrate the FTA causal model into the event causal model.

[0131] FIG. 14 is a diagram for explaining a flow of integration processing of the event causal relationship generation unit 116 according to the embodiment. Referring to FIG. 14, the event causal relationship generation unit 116 adds a node of the FTA causal model to a node of the event causal model (step S30). Next, the event causal relationship generation unit 116 combines nodes having the same variable into one node (step S32). Next, the event causal relationship generation unit 116 adds edge information of the FTA causal model to the event causal model to which the node of the FTA causal model has been added (step S34). Next, the event causal relationship generation unit 116 registers data origin information in attribute information of the node and edge (step S36). Specifically, the data origin information indicating the origin of the data causal model, the origin of the FTA causal model, or both origins is registered.

[0132] Then, the event causal relationship generating unit 116 ends the processing (END).

[0133] <6. Specific Examples> A specific example of the event causal model generated by the event causal relationship generating unit 116 will be described below.

[0134] FIG. 15 is a diagram illustrating a specific example of a data causal model according to an embodiment.

[0135] 15(A) shows a data causal model output from the first relationship identifying unit 115. Specifically, as an example, this is a causal model identified based on the strength of relationships between multiple mechanisms 31 for the production line 3 of the packaging machine and the order relationships of the multiple mechanisms 31 obtained by analyzing the control program 221.

[0136] Specifically, nodes N40 to N56 are provided, and edge information between the nodes is shown. Also, each node N is associated with a variable used in the control program 221.

[0137] Fig. 15(B) shows an example of graph structure data of a data causal model. As shown in Fig. 15(B), the graph structure data describes edge information between each node along with information about each node. As an example, a case is shown in which a variable is assigned as an example of attribute information of a node (node ​​ID). Note that the above graph structure data is an example, and is not limited to this description.

[0138] 16 is a diagram illustrating an example of normal data and abnormal data according to an embodiment of the present invention, in which normal data and abnormal data are shown in each node.

[0139] A data causal model in normal conditions is generated based on the above-described data causal model and normal data.

[0140] In addition, a data causal model in an abnormal state is generated based on the above-described data causal model and abnormal data.

[0141] FIG. 17 is a diagram for explaining data causal models in normal and abnormal states according to an embodiment. FIG. 17(A) is a data causal model in normal states. FIG. 17(B) is a data causal model in abnormal states. By using normal data for the data causal model, a causal relationship between nodes in normal states is identified. Also, by using abnormal data for the data causal model, a causal relationship between nodes in abnormal states is identified. The numerical values ​​between nodes indicate the strength of the relationship.

[0142] FIG. 18 is a diagram for explaining an event causal model according to an embodiment. With reference to FIG. 18, the event causal relationship generating unit 116 calculates the degree of deviation using the data causal model in normal times and the data causal model in abnormal times described in FIG. 17. An event causal model is generated in which a node that is a cause candidate is estimated from the magnitude of the deviation degree. In addition, an FTA causal model is integrated into the event causal model according to the method described in the flow of FIG. 13 and FIG. 14. A case is shown in which a node of the FTA causal model is added to a node of the event causal model, and edge information of the FTA causal model is added to the event causal model to which the node of the FTA causal model is added. As described above, a case is shown in which nodes having the same variable are combined into one node.

[0143] Specifically, the variable ("CurrentTemprature CenterSeal") included in the attribute information of node N21 described in FIG. 12 is the same as that of node N54, and is therefore combined into one. The variable ("FilmFeedMain") included in the attribute information of node N23 is the same as that of node N45, and is therefore combined into one. The variable ("FilmFeedSub") included in the attribute information of node N24 is the same as that of node N50, and is therefore combined into one. The variable ("CenterHeaterDPC_MV") included in the attribute information of node N29 is the same as that of node N53, and is therefore combined into one. The variable ("FilmFeed_MV") included in the attribute information of node N32 is newly added because there is no identical variable.

[0144] This process enables the event causal relationship generating unit 116 to generate an event causal model that integrates FTA causal models. <7. Usage form> FIG. 19 is a diagram illustrating a usage mode using the event causality model according to the embodiment.

[0145] 19, a case where an abnormality occurs in the adhesive strength of the seal is considered as an example. The nodes at the ends of the edges are extracted by using an event causal model. In this example, nodes N25 to N28, N30 to N31, and N50 and N51 are extracted.

[0146] Therefore, by displaying the information of the extracted node, the user can easily predict the cause of the abnormality based on the information of the node.

[0147] FIG. 20 is a diagram illustrating a mechanism of a production line of a packaging machine according to an embodiment.

[0148] 20, the production line includes mechanisms such as a work position deviation sensor 300, a film transport shaft 302, a work climbing sensor 303, a work detection sensor 304, a work transport shaft 306, a film transport shaft 307, and a top seal shaft 310. Variables are assigned to each of these mechanisms.

[0149] Variables are also assigned to data related to the mechanism, such as remaining film amount 301 ("RoomHumidity"), drive time 305 ("Chapter"), center seal temperature 308 ("CurrentTemprature CenterSeal"), center seal temperature manipulated variable 309 ("CenterHeaterDPC_MV"), top seal lower temperature ("CurrentTempratureLowerTopSeal"), top seal lower temperature manipulated variable ("TopSealLowHeaterDPC_MC"), top seal upper temperature 314 ("CurrentTempratureUpperTopSeal"), and top seal upper temperature manipulated variable 313 ("TopSealUpHeaterDPC_MC") are assigned.

[0150] The user checks the actual location related to the node extracted by the event causal model. In this example, a case will be described in which the user checks the wear of the press roller as an event when there is an abnormality in the adhesive strength of the seal.

[0151] <8. Model Update> The event causality update unit 119 updates the event causality based on the event causality and events related to the multiple mechanisms 31 confirmed when the identified event occurred.

[0152] In this example, it is assumed that the user has confirmed that the press roller is worn by actually checking the seal adhesive strength.

[0153] 21 is a diagram illustrating an updated event causal model according to an embodiment. In FIG. 21, an updated event causal model is shown.

[0154] The event causal relationship update unit 119 accepts an input from the user that the degree of wear of the press roller is an event that has caused a seal adhesive strength defect.

[0155] The event causal relationship update unit 119 identifies the node N30 corresponding to the wear degree of the press roller according to the user's input as an event in which a defect has occurred, and updates the causal relationships between the node and the nodes extracted as candidate factors in the extracted event causal model. Specifically, it adds edges from the node N30 to the nodes N50 and N51.

[0156] This allows the event causal model to be updated.

[0157] Fig. 22 is a flow diagram illustrating an update process of the event causal relation update unit 119 according to the embodiment. With reference to Fig. 22, the event causal relation update unit 119 determines whether or not there is an input for the identified event (step S40).

[0158] In step S40, when it is determined that there is an input for the identified event (YES in step S40), the event causal relationship update unit 119 determines whether or not there is a corresponding node (step S42).

[0159] In step S42, if the event causal relationship update unit 119 determines that there is no corresponding node (NO in step S42), it creates a node (step S48).

[0160] Then, the event causal relationship update unit 119 adds an edge between the cause candidate and the node (step S44).

[0161] Then, the event causal relationship update unit 119 updates the model (step S46).

[0162] Then, the process ends (END).

[0163] On the other hand, in step S42, if the event causal relationship update unit 119 determines that a corresponding node exists (YES in step S42), it skips step S48 and proceeds to step S44. Subsequent processing is similar.

[0164] 21, the event causal relation update unit 119 receives an input from a user that the degree of wear of the press roller is an event that has caused poor seal adhesive strength. The event causal relation update unit 119 determines that there is a node N30 for the degree of wear of the press roller, skips step S48, and adds edges to nodes N50 and N51 in step S44. Then, the event causal relation update unit 119 updates the event causal model in step S46.

[0165] <9. Event List> Fig. 23 is a diagram illustrating an event list in event relation registration unit 120 according to an embodiment. Referring to Fig. 23, an event list in which a plurality of events are registered by a user is shown.

[0166] Specifically, the event relation registration unit 120 stores, as an event list, information on an event summary, event data, a causal model, an actual physical phenomenon, and details of recovery work.

[0167] As an event summary, event data and a causal model are registered corresponding to "poor seal adhesion strength," and a case is shown in which "press roller wear" is registered as the actual physical phenomenon and "replacement of press roller" is registered as the recovery work content.

[0168] In addition, as an event summary, event data and a causal model are registered corresponding to "poor seal adhesive strength," and a case is shown in which "leather belt wear" is registered as the actual physical phenomenon and "replacement of leather belt" is registered as the recovery work content.

[0169] As an event summary, the event data and causal model corresponding to "poor seal adhesive strength" are registered, and an example is shown in which "poor contact of collector ring" is registered as the actual physical phenomenon and "replacement of collector ring" is registered as the recovery work.

[0170] In addition, as an event summary, event data and a causal model corresponding to "poor seal adhesive strength" are registered, and an example is shown in which "film meandering" is registered as the actual physical phenomenon and "correction of distortion of the film transport axis" is registered as the recovery work content.

[0171] <10. Event Estimation> 24 is a diagram illustrating an event estimation process of event estimation unit 117 according to the embodiment. With reference to FIG. 24, event estimation unit 117 performs event estimation using an event list registered in event relation registration unit 120.

[0172] Specifically, the event estimation unit 117 acquires event data, and refers to an event list having event data that matches the acquired event data.

[0173] In this example, the event estimation unit 117 indicates that the topmost event list matches the event data.

[0174] Specifically, this is an event list in which the event summary "poor seal adhesive strength", the causal model, the actual physical phenomenon "press roller wear", and the recovery work content "replacement of press roller" are registered.

[0175] Therefore, based on the content, by presenting the user with "press roller wear" as the suspected location of the abnormality and presenting the recovery work to be done, which is to replace the press roller, it is possible to carry out recovery work for the event at an early stage.

[0176] Note that the event estimation unit 117 may determine that the event data matches when the event data is not completely identical, for example, by calculating the degree of match (similarity) and the degree of match (similarity) is equal to or greater than a predetermined value.

[0177] <11. Notes> As described above, the present embodiment includes the following disclosure.

[0178] (Configuration 1) A relationship identifying unit (115, 118) that identifies a causal relationship between a plurality of mechanisms or a plurality of events related to the plurality of mechanisms in a process performed on a manufacturing line; an event causal relationship generating unit (116) that generates an event causal relationship based on the causal relationship and event data when an event occurs; and an event causal relationship update unit (119) that updates the event causal relationship based on the event causal relationship and an event related to the plurality of mechanisms confirmed when the event occurred.

[0179] (Configuration 2) The event causality is A plurality of nodes configured with respect to the plurality of mechanisms or events; edge information indicating connections between the plurality of nodes; The information processing device according to claim 1 , wherein the event causal relationship update unit adds edge information indicating a connection between a node corresponding to an event related to the plurality of mechanisms and a node that is a candidate cause extracted based on the event causal relationship.

[0180] (Configuration 3) 2. The information processing apparatus according to claim 1, further comprising an event relation registration unit (120) that uses the updated event causal relations to register an event list corresponding to the event.

[0181] (Configuration 4) 4. The information processing device of claim 3, wherein the event list includes an event summary, event data when the event occurred, a candidate cause location based on the updated event causal relationship, confirmed events related to the multiple mechanisms, and event work content.

[0182] (Configuration 5) 5. The information processing device according to claim 4, further comprising an event estimation unit (121) that acquires event data and extracts an event list including the same event data as the acquired event data from the event lists registered by the event relation registration unit.

[0183] (Configuration 6) Identifying causal relationships between a plurality of mechanisms or a plurality of events associated with the plurality of mechanisms in a process performed on a manufacturing line; generating an event causal relationship based on event data when the event occurs; updating the event causality based on the event relationship and events related to the plurality of mechanisms identified when the event occurred.

[0184] (Configuration 7) On the computer, Identifying causal relationships between a plurality of mechanisms or a plurality of events associated with the plurality of mechanisms in a process performed on a manufacturing line; generating an event causal relationship based on event data when the event occurs; updating the event causal relationships based on the event relationships and events related to the multiple mechanisms identified when the events occurred.

[0185] Although the embodiments of the present disclosure have been described, the embodiments disclosed herein should be considered to be illustrative and not restrictive in all respects. The scope of the present disclosure is defined by the claims, and it is intended to include all modifications within the scope and meaning equivalent to the claims. [Explanation of symbols]

[0186] 1 process analysis device, 3 manufacturing line, 11, 21 control unit, 12, 22 memory unit, 13, 24 communication interface, 14 input device, 15 output device, 16 drive, 23 input / output interface, 31 mechanism, 91 storage medium, 111 first acquisition unit, 112 second acquisition unit, 113 first analysis unit, 114 second analysis unit, 115 first relationship identification unit, 116 event causal relationship generation unit, 117 event estimation unit, 118 second relationship identification unit, 119 event causal relationship update unit, 120 event relationship registration unit, 121 process analysis program, 221 control program, 222 status data, 223 log data.

Claims

1. a relationship identifying unit that identifies a causal relationship between a plurality of mechanisms or a plurality of events related to the plurality of mechanisms in a process performed on a production line; an event causal relationship generation unit that generates an event causal relationship based on the causal relationship and event data when an event occurs; an event causality update unit that updates the event causality based on the event causality and an event related to the plurality of mechanisms that is confirmed when the event occurs; an event relation registration unit that uses the updated event causal relations to register an event list corresponding to the event.

2. The event causality is A plurality of nodes configured with respect to the plurality of mechanisms or events; edge information indicating connections between the plurality of nodes; The event causality update unit includes: a node corresponding to an event related to the plurality of mechanisms; The information processing apparatus according to claim 1 , further comprising: adding edge information indicating a connection between the nodes that are candidate cause nodes extracted based on the event causal relationships.

3. 2 . The information processing device according to claim 1 , wherein the event list includes an event summary, event data when the event occurred, a candidate cause location based on the updated event causal relationship, confirmed events related to the multiple mechanisms, and event work content.

4. 4. The information processing apparatus according to claim 3, further comprising an event estimation unit that acquires event data and extracts an event list including the same event data as the acquired event data from the event lists registered by the event relation registration unit.

5. Identifying causal relationships between a plurality of mechanisms or a plurality of events associated with the plurality of mechanisms in a process performed on a manufacturing line; generating an event causal relationship based on event data when the event occurs; updating the event causality based on the event causality and events related to the plurality of mechanisms identified when the event occurred; and registering an event list corresponding to the event using the updated event causality.

6. On the computer, Identifying causal relationships between a plurality of mechanisms or a plurality of events associated with the plurality of mechanisms in a process performed on a manufacturing line; generating an event causal relationship based on event data when the event occurs; updating the event causality based on the event causality and events related to the plurality of mechanisms identified when the event occurred; and registering an event list corresponding to the event using the updated event causal relationship.

Citation Information

Patent Citations

  • Process analysis apparatus, process analysis method, and process analysis program

    JP2009064407A

  • Ft diagram creation program, ft diagram creation apparatus, recording medium, and ft diagram creation method

    JP2009301134A

  • Event analyzer, event analysis method and computer program

    JP2016099930A

  • Model integration device, model integration method, model integration program, inference system, inspection system and control system

    JP2020115311A

  • System integrated fault-tree analysis methods (SIFTAN)

    US4870575A