Information processing system, information processing method, and program

JP2026123522APending Publication Date: 2026-07-30PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO LTD
Filing Date
2025-01-17
Publication Date
2026-07-30

AI Technical Summary

Benefits of technology

【0008】 本開示の情報処理システムは、製品または工程において生じ得る故障モードを適切に出力することができる。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2026123522000001_ABST
    Figure 2026123522000001_ABST
Patent Text Reader

Abstract

We provide information processing systems and other tools that can effectively support FMEA (Functional Mechanism of Analysis and Optimization). [Solution] The information processing system 1 comprises a memory 3 and a processor 2. The processor 2 reads structure-function data 13a from first information D1 that shows one or more combinations of unit structure a3 and unit function b3, and for each of the one or more combinations shown in the structure-function data 13a, if a failure-influencing element c related to the unit structure a3 and unit function b3 included in that combination is shown in second information D2, it reads that failure-influencing element c. Then, for each of the one or more combinations shown in the structure-function data 13a, if a failure-influencing element c has been read from second information D2, the processor 2 enumerates the failure modes m corresponding to that combination using the failure-influencing element c from second information D2.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to an information processing system that performs processing related to failures, etc.

Background Art

[0002] Conventionally, an accident information extraction system that extracts accident cause-related information has been proposed as an example of an information processing system (see, for example, Patent Document 1). This accident information extraction system includes a server computer configured to access a first database. The server computer extracts accident cause-related information by performing text mining on product accident information stored in the first database based on the input product information.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the accident information extraction system of Patent Document 1 above has a problem that it is difficult to effectively support FMEA (Failure Mode and Effects Analysis). Note that FMEA is a measure in the manufacturing industry for pre-examining possible defects (i.e., failure modes) that can occur in a product or in the process for producing that product, and taking countermeasures in advance for those that are unacceptable.

[0005] Therefore, the present disclosure provides an information processing system that can effectively support FMEA, etc.

Means for Solving the Problems

[0006] An information processing system according to one aspect of the present disclosure includes a processor, the processor acquires first information, reads structural-functional data from the first information indicating one or more combinations of structures and functions used in a product or process, acquires second information, reads from the second information for each of the one or more combinations indicated in the structural-functional data, failure-influencing elements that may cause failures in the structures and functions included in the combination, and outputs a failure mode, which is a type of failure that may occur in the structures and functions included in the combination, for each of the one or more combinations indicated in the structural-functional data, using the failure-influencing elements.

[0007] Furthermore, the comprehensive or specific embodiments may be implemented as devices, methods, integrated circuits, computer programs, or recording media such as computer-readable CD-ROMs, or as any combination of devices, methods, integrated circuits, computer programs, and recording media. The recording media may also be non-temporary recording media. [Effects of the Invention]

[0008] The information processing system disclosed herein can appropriately output failure modes that may occur in a product or process.

[0009] Further advantages and effects of one aspect of this disclosure will be made apparent from the specification and drawings. Such advantages and / or effects are provided by several embodiments and configurations described in the specification and drawings, but not all configurations are necessarily required. [Brief explanation of the drawing]

[0010] [Figure 1] Figure 1 shows an example of the configuration of an information processing system in an embodiment. [Figure 2] Figure 2 shows an example of the hardware configuration of the information processing system in the embodiment. [Figure 3]Figure 3 shows an example of structural and functional data in the embodiment. [Figure 4] Figure 4 shows an example of the second information in the embodiment. [Figure 5] Figure 5 shows an example of failure mode list information in the embodiment. [Figure 6] Figure 6 shows an example of element list information in an embodiment. [Figure 7] Figure 7 is a diagram illustrating an example of the processing operation of the failure mode enumeration unit in the embodiment. [Figure 8] Figure 8 shows an example of a screen displayed by the display selection unit in the embodiment. [Figure 9] Figure 9 shows an example of the third piece of information in the embodiment. [Figure 10] Figure 10 is a flowchart showing an example of the processing operation of the information processing system in the embodiment. [Modes for carrying out the invention]

[0011] (Knowledge that forms the basis of this disclosure) The inventors have found that the accident information extraction system described in Patent Document 1, as outlined in the "Background Art" section, has the following problems.

[0012] In manufacturing, the engineering chain from product planning to manufacturing and maintenance aims to reduce rework from later stages, thereby lowering development costs and shortening development time by improving the completeness of the product or the process design for producing it from the outset. FMEA is one analytical method used in this process. FMEA enumerates and evaluates potential defects (i.e., failure modes) that may occur in the product or process, and implements countermeasures and re-evaluations for those that cannot be overlooked. Comprehensive coverage of failure modes is key to FMEA, and automotive quality standards require a systematic analysis based on the decomposition of structural and functional elements included in the product or process.

[0013] However, the failure modes proposed by the accident information extraction system of Patent Document 1 are limited to the past failure modes stored in the database. Therefore, there is a problem that it is difficult to propose failure modes for new products or processes without precedent.

[0014] In order to solve such problems, an information processing system according to a first aspect of the present disclosure includes a processor. The processor acquires first information, reads out structure-function data indicating one or more combinations of structures and functions used in a product or process from the first information, acquires second information, and for each of the one or more combinations indicated in the structure-function data, reads out failure influence factors that can cause failures in the structure and the function included in the combination from the second information, and for each of the one or more combinations indicated in the structure-function data, outputs a failure mode, which is a mode of a possible failure in the structure and the function included in the combination, using the failure influence factors.

[0015] As a result, a failure mode is output using the failure influence factors for each combination of the structure and the function used in the product or process. Therefore, regardless of past cases, many more reliable failure modes can be output, and the performance of outputting failure modes can be improved. As a result, FMEA can be effectively supported.

[0016] The information processing system according to the second aspect further includes a memory connected to the processor. The processor further refers to element list information, which is information stored in the memory and indicates failure impact elements for each combination of structure and function, and for each of the one or more combinations shown in the structure and function data, associates the failure impact elements related to the structure and the function included in the combination with the combination. In the output of the failure mode, for each of the one or more combinations shown in the structure and function data, the failure mode corresponding to the combination may be output using the failure impact elements in the element list information. Note that the second aspect may be dependent on the first aspect.

[0017] For example, the element list information shows the failure impact elements for each combination obtained from products manufactured in the past or processes performed in the past. Therefore, in the second aspect, since the failure mode is output using the failure impact elements obtained from past products or processes, more reliable failure modes can be output by utilizing past experience.

[0018] The information processing system according to the third aspect further includes a memory connected to the processor. The processor further refers to failure mode list information, which is information stored in the memory and indicates the failure mode for each combination of structure and function, and in the output of the failure mode, for each of the one or more combinations shown in the structure and function data, the failure mode may be output by obtaining the failure mode corresponding to the combination. Note that the third aspect may be dependent on the first aspect or the second aspect.

[0019] For example, the failure mode list information shows failure modes for each combination obtained from products manufactured in the past or processes performed in the past. Therefore, in the third embodiment, since failure modes obtained from past products or processes are output, it is possible to output even more likely failure modes by utilizing past experience.

[0020] Furthermore, in the information processing system according to the fourth embodiment, the processor may delete the other failure modes from the one or more failure modes output, while retaining one or more failure modes selected by the user. Note that the fourth embodiment may be subordinate to any one of the first to third embodiments.

[0021] This allows, for example, one of several overlapping failure modes to remain while one or more others are eliminated. Therefore, by eliminating unnecessary failure modes, the efficiency of FMEA can be improved.

[0022] Furthermore, in the information processing system according to the fifth embodiment, the processor may reflect the selected one or more failure modes by adding them to the structural function data. Note that the fifth embodiment may be subordinate to any one of the first to fourth embodiments.

[0023] This allows structural and functional data reflecting one or more failure modes to be output as, for example, third-party information, enabling effective FMEA based on that third-party information.

[0024] Furthermore, in the information processing system according to the sixth embodiment, the processor may output the failure mode by inputting either only the combination, or the combination and the failure-influencing elements, for each of the one or more combinations shown in the structural-functional data into a large-scale language model. Note that the sixth embodiment may be dependent on any one of the first to fifth embodiments.

[0025] This allows for the use of a large-scale language model in the output of failure modes, enabling the output of appropriate failure modes for structures and functions not present in past products or processes.

[0026] An information processing method according to a first aspect of this disclosure is an information processing method performed by a computer, comprising: acquiring first information; reading structural function data from the first information that indicates one or more combinations of structures and functions used in a product or process; acquiring second information; for each of the one or more combinations shown in the structural function data, reading from the second information failure influencing elements that may cause failures in the structure and function included in the combination; and for each of the one or more combinations shown in the structural function data, outputting a failure mode, which is a type of failure that may occur in the structure and function included in the combination, using the failure influencing elements.

[0027] This makes it possible to achieve the same effects and advantages as the information processing system according to the first embodiment.

[0028] The embodiments will be described in detail below with reference to the drawings.

[0029] The embodiments described below are all general or specific examples. The numerical values, shapes, materials, components, arrangement and connection configurations of components, steps, and the order of steps shown in the following embodiments are examples only and are not intended to limit this disclosure. Furthermore, among the components in the following embodiments, those not described in the independent claim representing the highest-level concept are described as optional components. In addition, each figure is a schematic diagram and is not necessarily a precise representation. Also, the same components are denoted by the same reference numerals in each figure.

[0030] (Embodiment) Figure 1 shows an example of the configuration of the information processing system in this embodiment.

[0031] The information processing system 1 in this embodiment is a system that enumerates possible failure modes in a product or process in order to effectively support FMEA, and includes a reader 10, a presentation device 20, and a reflection device 30. For example, the automotive quality standard (IATF16949) outlines the procedure for FMEA. In this procedure, the scope of analysis of the product or process under consideration is subdivided and analyzed down to the level of unit structure and unit function. Next, possible failure modes for each unit structure and unit function are enumerated, the impact of the failure mode is evaluated, and then it is decided whether or not to take countermeasures for that failure mode. The information processing system 1 in this embodiment can be applied to such an FMEA procedure compliant with IATF16949. It should be noted that a failure mode can also be described as the manner of failure in an item. In a specific example, a failure mode in a bearing product could be deformation of the outer ring, or breakage or wear of the rollers. Alternatively, failure modes include cracks that occur during transportation of the electrical circuit board during the production process, short circuits that occur during wiring in the production process, or degradation of characteristics that occur during storage of the electrical circuit board during the production process.

[0032] The reading device 10 is a device that reads data or information from the first information D1 and the second information D2, and comprises a first reading unit 11, a second reading unit 12, and a first storage unit 13. The first reading unit 11 acquires the first information D1, reads the structural function data 13a from the first information D1, and outputs the structural function data 13a to the second reading unit 12. The first reading unit 11 also stores the structural function data 13a in the first storage unit 13. Here, the first information D1 is, for example, information obtained by performing a functional analysis in accordance with IATF16949 on the product or process to be analyzed, and is also called an FMEA report. The structural function data 13a may be the entirety of the first information D1, or it may be a part of the first information D1.

[0033] The second reading unit 12 acquires the second information D2 and also acquires at least a portion of the structural function data 13a from the first reading unit 11. The second reading unit 12 then reads one or more failure-influencing elements corresponding to the structural function data 13a from its second information D2. The second reading unit 12 outputs the one or more failure-influencing elements it has read to the presentation device 20, associating them with at least a portion of the structural function data 13a. Here, the second information D2 is information indicating multiple failure-influencing elements considered for each product or each process, and is also called an element review sheet or failure-influencing element review sheet. Failure-influencing elements are elements that cause failure modes or elements that can cause failure. In a specific example, a failure-influencing element may be the mechanical stress when transporting the electrical circuit board during the production process of the electrical circuit board, which can cause cracks to occur. Alternatively, a failure-influencing element may be the amount of solder used during soldering in the production process of the electrical circuit board, which can cause short circuits to occur. Alternatively, a factor influencing failure may be the high humidity environment during storage of electrical circuit boards in the production process, which can cause degradation of the electrical circuit board's characteristics. Furthermore, the second piece of information D2 may be included in the FMEA report, or it may be in a separate report from the FMEA report, such as a Fault Tree diagram.

[0034] The first storage unit 13 is a recording medium for storing structural and functional data 13a. Such a recording medium may be a hard disk drive, RAM (Random Access Memory), ROM (Read Only Memory), or semiconductor memory. Such a recording medium may be volatile or non-volatile.

[0035] The display device 20 is a device that enumerates and displays failure modes that may occur in a product or process, and comprises a failure mode enumeration unit 21, a database 22, and a display selection unit 25.

[0036] The database 22 comprises a second storage unit 23 and a third storage unit 24. The second storage unit 23 is a recording medium that stores failure mode list information 23a. The third storage unit 24 is a recording medium that stores element list information 24a. These recording media are hard disk drives, RAM, ROM, or semiconductor memory, etc. These recording media may be volatile or non-volatile.

[0037] The failure mode enumeration unit 21 acquires at least a portion of the structural function data 13a from the reader 10. At least a portion of this structural function data 13a is associated with one or more failure-influencing elements. The failure mode enumeration unit 21 enumerates multiple failure modes corresponding to the structural function data 13a while referring to the failure mode list information 23a and element list information 24a in the database 22. Here, the failure mode enumeration unit 21 has an LLM (Large-Scale Language Model) 21a. The LLM 21a is a machine learning model that has the function of outputting sentences that are likely to follow the input sentence. The failure mode enumeration unit 21 enumerates these failure modes by inputting at least a portion of the structural function data 13a and one or more failure-influencing elements into its LLM 21a and having the LLM 21a output multiple failure modes. In other words, the failure mode enumeration unit 21 infers multiple failure modes. In this embodiment, an LLM 21a is used, but a machine learning model other than a large-scale language model may be used. This machine learning model is a pre-trained model obtained by performing machine learning so that it outputs failure modes in response to input information. The input information may be a combination of structures and functions (specifically, unit structures and unit functions) as described below, or it may be a set that includes such combinations and failure influence elements.

[0038] The display selection unit 25 displays multiple failure modes enumerated by the failure mode enumeration unit 21 on the display. The display selection unit 25 then removes all but the failure modes selected by the user's input operation. The display selection unit 25 outputs the selected one or more failure modes to the reflection device 30.

[0039] When the reflection device 30 obtains one or more failure modes from the display selection unit 25, it reads the structural function data 13a from the first storage unit 13 of the reading device 10 and adds the one or more failure modes to the structural function data 13a. In other words, one or more failure modes are reflected in the structural function data 13a. The reflection device 30 then outputs the structural function data 13a with the one or more failure modes reflected as third information D3. The third information D3 may also be called a failure mode appended FMEA report.

[0040] Figure 2 shows an example of the hardware configuration of the information processing system 1 in this embodiment.

[0041] The information processing system 1 may be configured as a system comprising a processor 2 and a memory 3. The memory 3 stores the above-mentioned LLM 21a, structural function data 13a, failure mode list information 23a, and element list information 24a, as well as a computer program 4.

[0042] Processor 2 is, for example, a CPU (Central Processing Unit) connected to memory 3. Such a processor 2 functions as the first reading unit 11, second reading unit 12, failure mode enumeration unit 21, display selection unit 25, and reflection device 30 by reading and executing the program 4 stored in memory 3.

[0043] Figure 3 shows an example of structural and functional data 13a.

[0044] The structure-function data 13a shows process d, structure a1 and function b1, substructure a2 and subfunction b2, and unit structure a3 and unit function b3. Process d is the process under analysis, for example, the production process of a product. Structure a1 and function b1 are the structures and functions included in the equipment or facilities used in process d. Substructure a2 and subfunction b2 are the structures and functions included in structure a1 and function b1, and unit structure a3 and unit function b3 are the structures and functions included in substructure a2 and subfunction b2. Structure a1 and function b1 may also be called the major classification of structure and function, substructure a2 and subfunction b2 may be called the medium classification of structure and function, and unit structure a3 and unit function b3 may be called the minor classification of structure and function.

[0045] In a specific example, process d is "sheet winding," and the structure a1 and function b1 corresponding to process d are "winding machine" and "winding the sheet conveyed from the previous process to form a roll." Structure a1 and function b1 include substructure a2 and subfunction b2, which are "sheet conveying section" and "conveying the sheet to the winding section while applying tension." Substructure a2 and subfunction b2 include unit structure a3 and unit function b3, which are "tension cut roller" and "adjusting the tension of the sheet during conveying."

[0046] Figure 4 shows an example of the second piece of information D2.

[0047] Secondary Information D2 shows the failure-influencing element c associated with each combination of unit structure a and unit function b. Here, secondary Information D2 shows the failure-influencing elements for each combination that were considered for each product or process. For example, secondary Information D2 shows the failure-influencing element "C1" associated with the combination of unit structure "A1" and unit function "B1", and shows the failure-influencing element "C2" associated with the combination of unit structure "A2" and unit function "B2".

[0048] Figure 5 shows an example of failure mode list information 23a.

[0049] Failure mode list information 23a shows the failure mode m corresponding to each combination of unit structure a and unit function b. For example, failure mode list information 23a shows failure modes obtained from products manufactured in the past or processes performed in the past, for each combination. In a specific example, failure mode list information 23a shows the failure mode "sheet tearing" for the combination of unit structure "tension cut roller" and unit function "tension adjustment of sheet during transport". This type of failure mode list information 23a may also be called a failure mode database.

[0050] Figure 6 shows an example of element list information 24a.

[0051] Element list information 24a shows the failure-influencing elements c associated with each combination of unit structure a and unit function b. For example, element list information 24a shows failure-influencing elements c obtained from products manufactured in the past or processes performed in the past, for each combination. In a specific example, element list information 24a associates the failure-influencing element "tension change" with the combination of unit structure "tension cut roller" and unit function "tension adjustment of sheet during transport". Such element list information 24a may also be called a failure-influencing element database.

[0052] Figure 7 is a diagram illustrating an example of the processing operation of the failure mode enumeration unit 21.

[0053] The failure mode enumeration unit 21 acquires multiple combinations as at least part of the structure-function data 13a. Each of these multiple combinations is a combination of a unit structure a3 and a unit function b3. For each combination of unit structure a3 and unit function b3 shown in the structure-function data 13a, the failure mode enumeration unit 21 acquires the failure mode m from the failure mode list information 23a if a failure mode m is associated with that combination. In other words, the failure mode enumeration unit 21 derives or infers the failure mode m for that combination.

[0054] For example, the structural function data 13a shows "tension cut roller" and "sheet tension adjustment during transport" as unit structure a3 and unit function b3. Then, the failure mode list information 23a associates "sheet tearing" as the failure mode m with the combination of "tension cut roller" and "sheet tension adjustment during transport". In this case, the failure mode enumeration unit 21 obtains "sheet tearing" as the failure mode m from the failure mode list information 23a for the combination of "tension cut roller" and "sheet tension adjustment during transport" shown in the structural function data 13a. In other words, the failure mode enumeration unit 21 derives or infers "sheet tearing" as the failure mode m for the combination of "tension cut roller" and "sheet tension adjustment during transport" shown in the structural function data 13a.

[0055] Similarly, the structural function data 13a shows "winding clamp" and "sheet slip suppression at the start of winding" as unit structure a3 and unit function b3. Then, the failure mode list information 23a associates "winding direction misalignment" as the failure mode m with the combination of "winding clamp" and "sheet slip suppression at the start of winding". In this case, the failure mode enumeration unit 21 obtains "winding direction misalignment" as the failure mode m from the failure mode list information 23a for the combination of "winding clamp" and "sheet slip suppression at the start of winding" shown in the structural function data 13a. In other words, the failure mode enumeration unit 21 derives or infers "winding direction misalignment" as the failure mode m for the combination of "winding clamp" and "sheet slip suppression at the start of winding" shown in the structural function data 13a.

[0056] Similarly, the structural function data 13a shows "rotating shaft" and "winding up a sheet to form a roll" as unit structure a3 and unit function b3. Then, the failure mode list information 23a associates "shaft tilt" as the failure mode m with the combination of "rotating shaft" and "winding up a sheet to form a roll". In this case, the failure mode enumeration unit 21 obtains "shaft tilt" as the failure mode m from the failure mode list information 23a for the combination of "rotating shaft" and "winding up a sheet to form a roll" shown in the structural function data 13a. In other words, the failure mode enumeration unit 21 derives or infers "shaft tilt" as the failure mode m for the combination of "rotating shaft" and "winding up a sheet to form a roll" shown in the structural function data 13a.

[0057] The failure mode enumeration unit 21 further obtains, for each combination of unit structure a3 and unit function b3 shown in the structural function data 13a, the failure-influencing element c associated with that combination from the element list information 24a. Then, the failure mode enumeration unit 21 associates the obtained failure-influencing element c with the combination of unit structure a3 and unit function b3 shown in the structural function data 13a.

[0058] For example, the structural function data 13a shows "tension cut roller" and "tension adjustment of the sheet during transport" as unit structure a3 and unit function b3. Then, in the element list information 24a, "tension change" is associated with the combination of "tension cut roller" and "tension adjustment of the sheet during transport" as failure influence element c. In this case, the failure mode enumeration unit 21 obtains "tension change" from the element list information 24a as failure influence element c and associates it with the combination of "tension cut roller" and "tension adjustment of the sheet during transport" shown in the structural function data 13a.

[0059] Similarly, the structural function data 13a shows "nip roller" and "sheet transport stabilization" as unit structure a3 and unit function b3, respectively. The element list information 24a associates "sheet deformation" as failure influence element c with the combination of "nip roller" and "sheet transport stabilization". In this case, the failure mode enumeration unit 21 obtains "sheet deformation" as failure influence element c from the element list information 24a and associates it with the combination of "nip roller" and "sheet transport stabilization" shown in the structural function data 13a.

[0060] Similarly, the structural function data 13a shows "rotating shaft" and "winding up a sheet to form a roll" as unit structure a3 and unit function b3, respectively. Then, in the element list information 24a, "foreign matter" is associated with the combination of "rotating shaft" and "winding up a sheet to form a roll" as failure influencing element c. In this case, the failure mode enumeration unit 21 obtains "foreign matter" from the element list information 24a and associates it with the combination of "rotating shaft" and "winding up a sheet to form a roll" shown in the structural function data 13a as failure influencing element c.

[0061] The failure mode enumeration unit 21 then derives or infers, using LLM21a, the failure mode m corresponding to each combination of unit structure a3 and unit function b3 shown in the structural function data 13a, provided that a failure influencing element c is associated with that combination. In other words, the failure mode enumeration unit 21 derives the failure mode m by inputting the combination and its failure influencing element c into LLM21a. On the other hand, if no failure influencing element c is associated with any combination of unit structure a3 and unit function b3 shown in the structural function data 13a, the failure mode enumeration unit 21 derives or infers, using LLM21a, the failure mode m corresponding to that combination. In other words, the failure mode enumeration unit 21 derives the failure mode m by inputting the combination into LLM21a.

[0062] Furthermore, if the failure mode enumeration unit 21 associates a failure-influencing element c with a combination of unit structure a3 and unit function b3 shown in the structural-function data 13a by the second reading unit 12, it derives or infers the failure mode m corresponding to that combination and its failure-influencing element c using the LLM 21a. In other words, the failure mode enumeration unit 21 derives the failure mode m by inputting the combination and the failure-influencing element c read by the second reading unit 12 into the LLM 21a.

[0063] The failure mode enumeration unit 21 enumerates multiple failure modes m by performing the derivation or inference of such failure modes m multiple times.

[0064] Figure 8 shows an example of a screen displayed by the display selection unit 25.

[0065] When the display selection unit 25 obtains a list of failure modes m enumerated by the failure mode enumeration unit 21, it displays, for example, the screen 25a shown in Figure 8 on the display. The screen 25a displays the list of failure modes m enumerated by the failure mode enumeration unit 21, for example, in list format. More specifically, for each combination of unit structure a3 and unit function b3, the combination and, if one or more failure-influencing elements c are associated with that combination, those failure-influencing elements c are shown on the screen 25a. Furthermore, for each of those one or more failure-influencing elements c, a failure mode m is shown. This failure mode m is a failure mode derived by the LLM 21a of the failure mode enumeration unit 21 using the failure-influencing element c and the combination of unit structure a3 and unit function b3 corresponding to that failure-influencing element c. If no failure-influencing element c is associated with a combination of unit structure a3 and unit function b3, the failure mode m derived by the LLM 21a of the failure mode enumeration unit 21 for that combination, or a failure mode m obtained from the failure mode list information 23a, is shown. In Figure 8, the "-" indicates that failure-affecting element c is not associated with the above combination.

[0066] Furthermore, the display selection unit 25 determines whether to accept or reject each of the enumerated failure modes m in response to the user's input operation to the input device after viewing the screen 25a, and displays the result of the acceptance or rejection on the display, for example, with ○ or ×. In other words, the display selection unit 25 selects at least one failure mode m from the enumerated failure modes m in response to the user's input operation, and deletes the other remaining at least one failure mode m. The display selection unit 25 then outputs the selected at least one failure mode m to the reflection device 30.

[0067] The display selection unit 25 may include the above-mentioned display and input device, or it may be connected to the display and input device. The display is not limited to, but may be a liquid crystal display, plasma display, or organic EL (Electro-Luminescence) display. The input device may be configured as, for example, a keyboard, touch sensor, touchpad, or mouse.

[0068] Figure 9 shows an example of the third piece of information, D3.

[0069] The third information D3 includes structural function data 13a and at least one failure mode m. Each of these at least one failure mode m is a failure mode selected (i.e., adopted) by the display selection unit 25 using the screen 25a described above. When the reflection device 30 obtains at least one failure mode m from the display selection unit 25, it reads the structural function data 13a from the first storage unit 13 and adds (i.e., reflects) the at least one failure mode m to the structural function data 13a. This generates the third information D3 shown in Figure 9, for example. The reflection device 30 outputs the third information D3.

[0070] More specifically, the reflection device 30 adds the failure mode m selected by the display selection unit 25 for each combination of unit structure a3 and unit function b3 shown in the structural function data 13a, associating it with that combination. For example, for the combination of unit structure a3 and unit function b3, namely "tension cut roller" and "sheet tension adjustment during transport," the display selection unit 25 has selected "sheet tearing" and "sheet wrinkling" as failure modes m. In this case, the reflection device 30 adds "sheet tearing" and "sheet wrinkling" as failure modes m to the structural function data 13a, associating them with the combination of "tension cut roller" and "sheet tension adjustment during transport."

[0071] Figure 10 is a flowchart showing an example of the processing operation of the information processing system 1 in this embodiment.

[0072] First, the first reading unit 11 acquires the first information D1 (step S1), reads the structural function data 13a from the first information D1, and stores it in the first storage unit 13 (step S2).

[0073] Next, the second reading unit 12 acquires the second information D2 (step S3). Then, for each (unit structure, unit function) shown in the structure-function data 13a, the second reading unit 12 reads the failure-influencing element c related to that (unit structure, unit function) if it is included in the second information D2, and associates it with the (unit structure, unit function) (step S4). Note that (unit structure, unit function) is a combination of unit structure a3 and unit function b3.

[0074] Next, the failure mode enumeration unit 21 associates each (unit structure, unit function) shown in the structure function data 13a with the (unit structure, unit function) if the failure influencing element c associated with that (unit structure, unit function) is included in the element list information 24a (step S5).

[0075] Next, the failure mode enumeration unit 21 derives the failure mode m corresponding to each (unit structure, unit function, failure-influencing element) using LLM21a (step S6). Note that (unit structure, unit function, failure-influencing element) is a set of combinations of unit structure a3 and unit function b3, and failure-influencing elements c associated with those combinations. Furthermore, if no failure-influencing element c is associated with a (unit structure, unit function), the failure mode enumeration unit 21 derives the failure mode m corresponding to that (unit structure, unit function) using LLM21a without using the failure-influencing element c.

[0076] Next, the failure mode enumeration unit 21 retrieves the failure mode m corresponding to (unit structure, unit function) from the failure mode list information 23a if it is shown in the failure mode list information 23a (step S7). Multiple failure modes m are enumerated by the processing in steps S6 and S7.

[0077] The display selection unit 25 displays on screen 25a one or more failure modes m derived in step S6 and one or more failure modes m acquired in step S7 (step S8). Furthermore, in response to user input, the display selection unit 25 selects one or more failure modes m from the multiple failure modes m shown on screen 25a and deletes the other one or more failure modes m (step S9).

[0078] The reflection device 30 generates third information D3 by adding one or more failure modes m selected in step S9 to the structural function data 13a stored in the first storage unit 13 in step S2 (step S10), and outputs the third information D3 (step S11).

[0079] As described above, the information processing system 1 in this embodiment acquires first information D1 and reads structural function data 13a from the first information D1 that shows one or more combinations of unit structure a3 and unit function b3 used in a product or process. Furthermore, the information processing system 1 acquires second information D2 and, for each of the one or more combinations shown in the structural function data 13a, reads from the second information D2 the failure influencing elements c that may cause failures in the unit structure a3 and unit function b3 included in that combination. Then, for each of the one or more combinations shown in the structural function data 13a, the information processing system 1 outputs a failure mode m, which is a type of failure that may occur in the unit structure a3 and unit function b3 included in that combination, using the failure influencing elements c.

[0080] As a result, for each combination of unit structure a3 and unit function b3 used in a product or process, a failure mode m is output using failure influencing element c. This allows for the output of many more probable failure modes m, regardless of past cases, thereby improving the performance of failure mode m output. Consequently, it can effectively support FMEA.

[0081] Furthermore, the information processing system 1 includes a memory and a processor connected to the memory, and the processor may perform the above-described processing using the memory. In addition, when reading the failure-influencing element c, the information processing system 1 may read the failure-influencing element c for each of the one or more combinations shown in the structural-function data 13a, if the failure-influencing element c that may cause failures in the unit structure a3 and unit function b3 included in that combination is shown in the second information D2. Also, when outputting the failure mode m, the information processing system 1 may enumerate the failure mode m, which is the form of failure that may occur in the unit structure a3 and unit function b3 included in the combination, using the failure-influencing element c from the second information D2, for each of the one or more combinations shown in the structural-function data 13a, if the failure-influencing element c has been read from the second information D2.

[0082] Furthermore, the information processing system 1 in this embodiment refers to element list information 24a, which is information stored in memory 3 and indicates the failure-affecting elements c for each combination of unit structure a and unit function b. The information processing system 1 then associates the failure-affecting elements c related to the unit structure a3 and unit function b3 included in each of the one or more combinations shown in structure-function data 13a with that combination. In outputting the failure mode m, the information processing system 1 further outputs the failure mode m corresponding to each of the one or more combinations shown in structure-function data 13a, using the failure-affecting elements c from element list information 24a.

[0083] For example, element list information 24a shows failure-influencing elements c obtained from products manufactured in the past or processes performed in the past, for each combination. Therefore, since failure modes m are output using failure-influencing elements c obtained from past products or processes, it is possible to output even more likely failure modes m by utilizing past experience.

[0084] Furthermore, in the mapping of failure-influencing elements c, the information processing system 1 may, for each of the one or more combinations shown in the structural-function data 13a, map the failure-influencing elements c related to the unit structure a3 and unit function b3 included in that combination to that combination, if those elements are shown in the element list information 24a. In the output of failure modes m, the information processing system 1 may, for each of the one or more combinations shown in the structural-function data 13a, further enumerate the failure modes m corresponding to that combination using the failure-influencing elements c in the element list information 24a, if the failure-influencing elements c in the element list information 24a are mapped to that combination.

[0085] Furthermore, the information processing system 1 in this embodiment refers to failure mode list information 23a, which is information stored in memory 3 and indicates failure mode m for each combination of unit structure a and unit function b. Then, in outputting failure mode m, the information processing system 1 further outputs failure mode m by obtaining the failure mode m corresponding to each of the one or more combinations shown in the structure function data 13a.

[0086] For example, the failure mode list information 23a shows failure modes m obtained from products manufactured in the past or processes performed in the past, for each combination. Therefore, since failure modes m obtained from past products or processes are output, it is possible to output even more likely failure modes m by utilizing past experience.

[0087] Furthermore, in the output of failure mode m, the information processing system 1 may also enumerate failure modes m by obtaining the failure mode m corresponding to each of the one or more combinations shown in the structural function data 13a from the failure mode list information 23a, if the failure mode m corresponding to that combination is shown in the failure mode list information 23a.

[0088] Furthermore, in this embodiment, the information processing system 1 deletes the other failure modes m, keeping one or more failure modes m selected by the user from among the one or more failure modes m that have been output.

[0089] This allows, for example, one of several overlapping failure modes m to remain while one or more other failure modes m are removed. Therefore, by removing unnecessary failure modes m, the efficiency of FMEA can be improved. Note that the one or more failure modes m output may be one or more of the enumerated failure modes m.

[0090] Furthermore, the information processing system 1 in this embodiment reflects one or more selected failure modes m by adding them to the structural function data 13a.

[0091] As a result, structural and functional data 13a reflecting one or more failure modes m is output as third information D3, and FMEA can be effectively performed based on this third information D3.

[0092] Furthermore, in this embodiment, the information processing system 1 outputs the failure mode m by inputting either only the combination shown in the structural function data 13a, or the combination and the failure-influencing element c, to the LLM 21a for each of the one or more combinations shown in the structural function data 13a.

[0093] As a result, LLM21a is used for the output of failure mode m, making it possible to output an appropriate failure mode m corresponding to a unit structure a3 and unit function b3 that are not present in past products or processes.

[0094] Furthermore, in enumerating failure modes m, the information processing system 1 may enumerate failure modes m by inputting each of the one or more combinations shown in the structural function data 13a, along with the failure-influencing element c, into the LLM 21a, if the failure-influencing element c has been read from the second information D2. Alternatively, if the failure-influencing element c has not been read from the second information D2, the information processing system 1 may enumerate failure modes m by inputting the combination into the LLM 21a.

[0095] In this embodiment, the combination includes a unit structure a3 and a unit function b3 (or a unit structure a and a unit function b), but it may also include structure a1 and function b1, or substructure a2 and subfunction b2.

[0096] (Other variations) The above description has been made based on the above embodiment of an information processing system 1 according to one aspect of the present disclosure. However, the present disclosure is not limited to that embodiment. Various modifications to the above embodiment that a person skilled in the art could conceive of may also be included in the present disclosure, as long as they do not deviate from the spirit of the present disclosure.

[0097] In the above embodiment, each component may be implemented by dedicated hardware or by executing a software program suitable for each component. Each component may also be implemented by a program execution unit such as a CPU or processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory. Here, the software that implements each device or system in the above embodiment is, for example, a program that causes a computer to execute each step of the flowchart shown in Figure 10.

[0098] The following cases are also included in this disclosure.

[0099] (1) The at least one device described above is specifically a computer system consisting of a microprocessor, ROM (Read Only Memory), RAM (Random Access Memory), a hard disk unit, a display unit, a keyboard, a mouse, etc. A computer program is stored in the RAM or hard disk unit. The at least one device described above achieves its function by the operation of the microprocessor in accordance with the computer program. Here, the computer program is composed of a combination of multiple instruction codes that indicate commands to the computer in order to achieve a predetermined function.

[0100] (2) Some or all of the components constituting at least one of the above-described devices may be made up of a single system LSI (Large Scale Integration). The system LSI is a multi-functional LSI manufactured by integrating multiple components onto a single chip, and specifically, it is a computer system comprising a microprocessor, ROM, RAM, etc. The RAM stores a computer program. The system LSI achieves its function by operating the microprocessor in accordance with the computer program.

[0101] (3) Some or all of the components constituting at least one of the above-described devices may consist of an IC card or a standalone module that is detachable from the device. The IC card or module is a computer system consisting of a microprocessor, ROM, RAM, etc. The IC card or module may include the above-described multi-function LSI. The IC card or module achieves its function by the operation of the microprocessor in accordance with a computer program. The IC card or module may be tamper-resistant.

[0102] (4) The disclosure may also be the methods described above. Alternatively, it may be a computer program that implements these methods using a computer, or a digital signal consisting of a computer program.

[0103] Furthermore, this disclosure may also refer to a computer program or digital signal recorded on a computer-readable recording medium, such as a flexible disk, hard disk, CD (Compact Disc)-ROM, DVD, DVD-ROM, DVD-RAM, BD (Blu-ray® Disc), semiconductor memory, etc. Alternatively, it may refer to a digital signal recorded on such a recording medium.

[0104] Furthermore, this disclosure may also include the transmission of computer programs or digital signals via telecommunications lines, wireless or wired communication lines, networks such as the Internet, data broadcasting, etc.

[0105] Alternatively, the program or digital signal may be carried out by another independent computer system by recording and transferring it on a recording medium, or by transferring the program or digital signal via a network or the like. [Industrial applicability]

[0106] The information processing system disclosed herein can effectively support FMEA, for example, and can be applied to systems or equipment in the manufacturing industry. [Explanation of Symbols]

[0107] 1. Information Processing System 2 processors 3 memory 4 Programs 10. Reader 11. First reading section 12 Second reading section 13 1st memory section 13a Structural and functional data 20 Presentation device 21 Failure Mode Enumeration Section 21a LLM (Large-Scale Language Model) 22 Databases 23 2nd memory section 23a Failure Mode List Information 24 Third memory section 24a Element List Information 25 Display Selection Section 25a screen 30 Reflection device a1 structure a2 small structure a, a3 Unit structure b1 Function b2 small function b, b3 Unit Function c Failure influencing factors d process D1 First Information D2 2nd information D3 Third Information m Failure Mode

Claims

1. Equipped with a processor, The aforementioned processor, First information is obtained, Structural and functional data indicating one or more combinations of structure and function used in a product or process are read from the first information. Obtain the second piece of information, For each of the one or more combinations shown in the structural and functional data, the failure-influencing elements that may cause failures in the structure and function included in the combination are read from the second information. For each of the one or more combinations shown in the structural and functional data, a failure mode, which is a type of failure that may occur in the structure and function included in that combination, is output using the failure influence element. Information processing system.

2. The processor further comprises memory connected to the aforementioned processor, The aforementioned processor further, The information stored in the memory refers to element list information, which is information indicating the failure-affecting elements for each combination of structure and function, For each of the one or more combinations shown in the aforementioned structural and functional data, the failure-influencing elements related to the structure and function included in the combination are associated with the combination. In the output of the aforementioned failure mode, further, For each of the one or more combinations shown in the structural and functional data, the failure mode corresponding to that combination is output using the failure influence elements in the element list information. The information processing system according to claim 1.

3. The processor further comprises memory connected to the aforementioned processor, The aforementioned processor further, The system refers to the failure mode list information, which is information stored in the memory that indicates failure modes for each combination of structure and function. In the output of the aforementioned failure mode, further, For each of the one or more combinations shown in the structural and functional data, the failure mode corresponding to that combination is obtained, and the failure mode is output. The information processing system according to claim 1.

4. The aforementioned processor, Of the one or more failure modes output, one or more selected by the user are retained, while the other failure modes are deleted. The information processing system according to claim 1.

5. The aforementioned processor, The selected one or more failure modes are reflected by adding them to the structural and functional data. The information processing system according to claim 4.

6. In the output of the failure mode, the processor For each of the one or more combinations shown in the aforementioned structural and functional data, By inputting only the combination in question, or the combination and the failure-influencing elements, into a large-scale language model, the failure mode is output. The information processing system according to claim 1.

7. A method of information processing performed by a computer, First information is obtained, Structural and functional data indicating one or more combinations of structure and function used in a product or process are read from the first information. Obtain the second piece of information, For each of the one or more combinations shown in the structural and functional data, the failure-influencing elements that may cause failures in the structure and function included in the combination are read from the second information. For each of the one or more combinations shown in the structural and functional data, a failure mode, which is a type of failure that may occur in the structure and function included in that combination, is output using the failure influence element. Information processing methods.

8. First information is obtained, Structural and functional data indicating one or more combinations of structure and function used in a product or process are read from the first information. Obtain the second piece of information, For each of the one or more combinations shown in the structural and functional data, the failure-influencing elements that may cause failures in the structure and function included in the combination are read from the second information. For each of the one or more combinations shown in the structural and functional data, a failure mode, which is a type of failure that may occur in the structure and function included in that combination, is output using the failure influence element. A program that causes a computer to perform a task.

Citation Information

Patent Citations

  • Accident information extraction system

    JP2020194531A