JP7262367B2 - Maintenance support system, maintenance support method and computer program - Google Patents

Description

The present invention relates to a maintenance support system, a maintenance support method, and a computer program.

The present invention relates to a technique for assisting maintenance work of equipment by estimating a failure mode when equipment failure occurs. In particular, it relates to a technique for editing and managing a model describing causal relationships of failure phenomena for estimating failure modes.

In order to keep equipment such as gas engines, elevators, mining and construction equipment in constant operation, equipment maintenance work is essential. In particular, when a device breaks down and stops working, it is required to quickly investigate the details of the failure, take appropriate measures, and restore the device to operation. In the investigation, it is important to check each part of the equipment and identify the failure mode, which is the condition of the equipment causing the failure.

As a technique for automatically identifying a failure mode, there is a technique disclosed in Patent Literature 1, for example. Patent Document 1 discloses a technique for estimating what kind of failure mode is currently occurring from the probability using a model that defines the failure probability for each state of each part of the device and the operation history of the user who uses the device. there is The failure probability is set based on the knowledge and experience of the device designer, reliability information, and the like. In addition to this technology, by updating the occurrence probability of failure modes whose frequency of occurrence exceeds a certain value, a technology has been published that can perform temporary updates in line with the actual failure situation in the market.

JP 2009-223362 A

In the technique disclosed in the above-mentioned Patent Document 1, because of the mechanism of updating the failure mode with high occurrence frequency, the model cannot be updated until the equipment is shipped and the failure occurs enough to actually estimate the failure probability.

One of the reasons why a model for estimating a failure mode becomes inaccurate is a change in equipment specifications. For example, there is a case where the specification of equipment is changed due to cost reduction activities (VEC), and the failure mode that has occurred so far no longer occurs, making accurate diagnosis impossible.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and an object of the present invention is to provide a maintenance support system, a maintenance support method, and a computer program capable of improving the accuracy of specifying failure modes of equipment.

In order to solve the above problems, a maintenance support system according to one aspect of the present invention is created based on an information source relating to maintenance target equipment, and has a causal model describing the causal relationship between the state of the maintenance target equipment and inspection items. A stored causal model part, a linked database part that stores a linked database that describes the correspondence between information sources and causal models, and an updated part that extracts the updated part when the information source is updated. It has an extraction unit and an update part identification unit that identifies a part to be updated in the causal model by searching the linking database based on the updated part.

Advantageous Effects of Invention According to the present invention, it is possible to realize a maintenance support system, a maintenance support method, and a computer program capable of improving the accuracy of specifying failure modes of equipment.

It is a figure which shows schematic structure of the maintenance support system which concerns on an Example. It is a figure which shows an example of the failure causal model database of the maintenance support system which concerns on an Example. It is a figure which shows an example of the failure causal model of the maintenance support system which concerns on an Example. It is a figure which shows an example of the manual used with the maintenance support system which concerns on an Example. It is a figure which shows an example of the update of the manual used with the maintenance assistance system which concerns on an Example. FIG. 7 is a diagram showing another example of manual update used in the maintenance support system according to the embodiment; FIG. 10 is a diagram showing still another example of manual update used in the maintenance support system according to the embodiment; FIG. 10 is a diagram showing still another example of manual update used in the maintenance support system according to the embodiment; It is a figure which shows an example of the connection database of the maintenance support system which concerns on an Example. 4 is a flow chart showing an example of the operation of the maintenance support system according to the embodiment; 9 is a flowchart showing an example of deletion candidate node information display processing of the maintenance support system according to the embodiment; It is a figure which shows an example of the display screen displayed on the display part of the maintenance assistance system which concerns on an Example. It is a figure which shows the other example of the display screen displayed on the display part of the maintenance assistance system which concerns on an Example. It is a figure which shows the other example of the display screen displayed on the display part of the maintenance assistance system which concerns on an Example. FIG. 10 is a diagram showing still another example of a display screen displayed on the display unit of the maintenance support system according to the embodiment; It is a figure which shows an example of the update part extracted by the manual update part extraction part of the maintenance support system which concerns on an Example.

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described with reference to the drawings. It should be noted that the embodiments described below do not limit the invention according to the scope of claims, and that all of the elements described in the embodiments and their combinations are essential to the solution of the invention. Not exclusively.

As already explained, one of the reasons why the model for estimating the failure mode becomes inaccurate is the change in equipment specifications. For example, there is a case where the specification of equipment is changed due to cost reduction activities (VEC), and the failure mode that has occurred so far no longer occurs, making accurate diagnosis impossible. To address this issue, create a new model that reflects the specification change. Devices shipped after the specification change can be diagnosed with a new model.

In order to achieve the above, this embodiment detects a specification change based on whether or not the maintenance manual of the equipment has been updated. Then, when the manual is updated, the engineer is notified of the updated part of the failure causal model based on the type and part of the update. When the engineer edits the old failure causal model based on the notification contents, a new failure causal model corresponding to the specification change is placed in the failure causal model database. As a result, it is possible to correctly diagnose the device even after the specification change.

In the drawings for explaining the embodiments, portions having the same functions are denoted by the same reference numerals, and repeated description thereof will be omitted.

In addition, in the following description, an expression such as "xxx data" may be used as an example of information, but information may have any data structure. That is, "xxx data" can be referred to as "xxx tables" to indicate that the information is independent of the data structure. Furthermore, "xxx data" may be simply referred to as "xxx". In the following description, the configuration of each information is an example, and the information may be divided and held or combined and held.

First, referring to FIG. 1, the schematic configuration of the maintenance support system of the embodiment will be described, and the processing of the maintenance support method executed by the maintenance support system will be described with reference to FIGS. 10 and 11. FIG.

FIG. 1 is a diagram showing a schematic configuration of a maintenance support system according to an embodiment.

The maintenance support system S of this embodiment has a terminal 100 and a center server 150 . The terminal 100 is carried by maintenance personnel 102 who perform maintenance work on the equipment 104 , especially repair work on the equipment 104 . The maintenance staff 102 operates the terminal 100 to investigate the failure of the equipment 104 .

The center-side server 150 is mainly operated by an engineer 160 and an equipment designer 172 . Engineer 160 develops fault causal models for diagnosing equipment 104 . Further, the device designer 172 stores the manual (information source) of the device 104 in the manual management unit 170, which will be described later.

The terminal 100 and the center-side server 150 can mutually transmit and receive information through the communication units 125 and 190 of each other. Communication means between the terminal 100 and the center server 150 is not particularly limited, and both wired and wireless communication means can be employed. Also, the communication means can be at least one of a so-called LAN (Local Area Network) or a WAN (Wide Area Network) represented by the Internet or a mobile communication network.

The center-side server 150 is an information processing device such as a computer as an example of a device capable of performing various types of information processing. The information processing device has an arithmetic element, a storage medium, and a communication interface, and further has an input section 199 such as a mouse and a keyboard, and a display section 198 such as a display.

The computing element is, for example, a CPU (Central Processing Unit), an FPGA (Field-Programmable Gate Array), or the like. The storage medium includes, for example, a magnetic storage medium such as a HDD (Hard Disk Drive), a semiconductor storage medium such as a RAM (Random Access Memory), a ROM (Read Only Memory), and an SSD (Solid State Drive). A combination of an optical disk such as a DVD (Digital Versatile Disk) and an optical disk drive is also used as a storage medium. In addition, known storage media such as magnetic tape media are also used as storage media.

The storage medium stores programs such as firmware. When the center side server 150 starts to operate (for example, when the power is turned on), a program such as firmware is read from the storage medium and executed to control the center side server 150 as a whole. In addition to the program, the storage medium stores data required for each process of the center side server 150 and the like.

Similar to the center server 150, the terminal 100 is also an information processing device such as a computer that can perform various types of information processing. In particular, the terminal 100 is preferably a lightweight tablet or the like that the maintenance staff 102 can easily carry to the site where the equipment 104 is operated.

Note that each of the center-side servers 150 of this embodiment may be configured by a so-called cloud, in which information processing devices are configured to be able to communicate via a communication network.

The terminal 100 has a display section 105 such as a liquid crystal display, and an input section 120 configured by a touch display or the like.

Equipment 104 is equipment to be maintained, such as a generator, construction equipment, and medical equipment. By checking the state of each part of the equipment 104 and inputting the result into the terminal 100, the maintenance personnel obtains the estimation result of the failure mode. Also, even if the terminal 100 is built in the device 104, it is essentially equivalent to the present invention.

The center-side server 150 mainly has two roles 1) and 2). 1) receives the check result of the device 104 input to the terminal 100 via the communication units 125 and 190, estimates the failure mode using the failure causal model, and returns the estimation result to the terminal 100. FIG. 2) is the role of editing and managing the failure causal model used for failure mode estimation in synchronism with the update of the equipment manual. Here, role 1) will be briefly described as a known technique, and role 2) will be described in detail later.

The center-side server 150 will be described in detail. Elements for realizing the role 1) described above are the failure causal model database 180 and the failure mode probability calculator 175 . The elements that realize role 2) are everything else. Each element is described below.

The failure causal model database 180 is a database storing failure causal models for estimating failure modes.

FIG. 2 is a diagram showing an example of the failure causal model database 180 of the maintenance support system S according to the embodiment.

The failure causal model database 180 has a table structure, and each horizontal row corresponds to one model used for failure mode estimation of the equipment 104 . Each model is created with reference to the manual (information source) of the equipment 104 and therefore has a corresponding manual version 210 , model ID 220 , model body 230 and target equipment lot number 240 . This makes it possible to detect the need for a new model when the manual is updated. Additionally, when estimating a failure mode, a valid failure causal model 230 can be called from the lot number 240 of the equipment 104 to be diagnosed.

FIG. 3 is a diagram showing an example of the failure causal model 230 of the maintenance support system S according to the embodiment.

The fault causal model 230 is represented by a Bayesian network model as shown in FIG. The example shown in FIG. 3 shows the causal relationship between the failure modes F1 310 to F3 330 when the equipment 104 is a refrigerator and the inspection items I1 340 to I5 380 when the failure modes occur. Link 312 indicates that it affects I1 when the failure shown in failure mode F1 occurs, that is, it affects the probability of occurrence of an increase in input power if chilled water in the condenser decreases. Similarly, link 315 indicates that I2 will be affected when the failure shown in failure mode F1 occurs, ie, if the chilled water in the condenser is reduced, it will affect the rise in condenser outlet temperature.

In addition to the above, by setting the general occurrence probability of failure modes F1, F2, and F3 and the occurrence probability of inspection items I1 to I5 when failure modes F1 to F3 occur, based on knowledge and statistical data , the occurrence probabilities of failure modes F1 to F3 when inspection items I1 to I5 occur. A specific method for calculating this probability is a well-known technique for Bayesian networks. disclosed.

Information from which the failure causal model 230 is created is the equipment manual, an example of which is shown in FIG.

FIG. 4 is a diagram showing an example of a manual used in the maintenance support system S according to the embodiment.

In FIG. 4, reference numeral 410 denotes an example of a page of the manual on which a diagnosis flow for failure occurrence is written. The left column of the manual 410, for example 420, indicates the failure mode, and the right column of the manual 410, for example, 430 indicates the inspection items when the failure mode occurs. Therefore, if the item 420 is to be found, the item 430 is checked.

The Bayesian network in FIG. 3 was modeled with reference to this manual 410 . For example, 420 in FIG. 4 indicates failure mode "Condenser Cold Water Low", which is F1 310 in FIG. 430 in FIG. 4 refers to I1 340 in FIG. Assuming such a correspondence relationship, it is possible to model FIG. 3 from the manual. As shown in 450 in FIG. 4, the manual 450 does not need to be written in a flow format, and even if it is written in a natural language, the concept of correspondence with the model is the same.

Next, elements for editing and managing the fault causal model 230, which are the point of this embodiment, will be described. First, the manual management unit 170 is a storage that manages electronic data of manuals. By copying a manual to the manual management unit 170, it is managed with a version number attached, and has a function of notifying that when a new manual is copied.

The linking database 173 is a database in which the reference parts of the manual and the parts of the model created based thereon are linked. The internal structure of this database is as shown in FIG.

FIG. 9 is a diagram showing an example of the linking database 173 of the maintenance support system S according to the embodiment.

The linking database 173 includes a manual version 910, reference points 920 to 940 in the manual when the failure causal model 230 is created with reference to the manual of this manual version 910, and the failure causal model 230 created with reference. It has an ID 950 and a link destination node 960 inside the failure causal model 230 linked to the referenced manual.

For example, according to the first line in FIG. 9, it means that the node named F1 with the model ID=0001 was created by referring to the 1st to 7th characters in the first line of the manual p50 whose manual version is 0001. . This corresponds to creating 310 in FIG. 3 with reference to 420 in FIG. 4 described above. Therefore, when the manual is updated, it is possible to know which node of the failure causal model 230 should be reflected from the updated part and contents.

The manual update part extracting unit 185 compares the new manual with the old version of the manual, and extracts the update type (addition, deletion, change) and the update part (page, number of lines, number of characters in the line). It has a function to extract and output. The manual update portion extraction unit 185 can be realized by using a well-known technology for comparing document differences, such as the Linux (registered trademark) OS diff command.

What kind of output the manual update part extraction unit 185 returns in response to what kind of input will be described. Specific examples of manual updating as input are shown in FIGS.

5 to 8 are diagrams showing an example of manual update used in the maintenance support system S according to the embodiment. 5 shows an example of addition, FIG. 6 shows a change, and FIGS. 7 and 8 show an example of deletion.

FIG. 5 shows an example in which a failure mode 560 and inspection items 570 are added when the manual 510 before updating is updated to the manual 550 .

FIG. 6 shows an example in which when the manual 610 before updating is updated to the manual 650, the content of the inspection item on the third line is changed to 670 "Decrease in input power immediately after start-up".

7 and 8 are examples in which failure modes and inspection items are deleted. As for deletion, when reflecting the deleted manual item, it is different whether only the link of the failure causal model is deleted or the node is also deleted. Therefore, FIG. 7 and FIG. 8 are separately explained.

FIG. 7 shows a case where only links are removed. The failure mode 720 and inspection item 730 disappear from the manual 710 before updating. Since the same failure mode 735 is described in the failure mode 720 "evaporator cold water decrease", even if this update is reflected in the failure causal model 230, the failure mode 330 shown in FIG. 3 is not deleted. Only links 335 between failure modes 330 and check items 340 are removed.

Conversely, FIG. 8 is a pattern that removes not only links but also nodes. The failure mode 820 and inspection item 830 that were in the manual 810 before updating are deleted in the manual 850 after updating. In this case, since check item 830 is not linked from other failure modes, to reflect this deletion in failure causal model 230, in addition to link 375 shown in FIG. must be removed.

FIG. 16 explains the information output by the manual update portion extracting unit 185 with the input of the events shown in FIGS. 5, 6 and 8 occurring simultaneously.

FIG. 16 is a diagram showing an example of an updated part extracted by the manual updated part extraction unit 185 of the maintenance support system S according to the embodiment.

Reference numeral 1650 indicates the manual before update, 1670 indicates the manual after update, and 1670 to 1690 are balloon displays corresponding to the updated contents described in FIGS. Note that balloon displays of 1675 and 1680 are information provided for explanation, and are not displayed in the actual manual.

At this time, the manual update portion extracting unit 185 outputs table information as indicated by 1600 in FIG. One horizontal row of the table corresponds to an update such as one addition or deletion. The type of update 1610, the number of pages in the updated part 1620, the number of rows in the updated part 1630, the position in the row of the updated part, that is, the number of characters in the row It has information 1640 indicating how many characters have been updated. Since the update part 1600 extracted and output by the manual update part extraction unit 185 is linked to the reference parts 920 to 940 of the linking database 173 shown in FIG. , the nodes and links to be corrected in the fault causal model 230 can be found.

The model update portion identification unit 188 identifies portions to be updated in the failure causal model 230 by searching the linking database 173 based on the manual update portion extracted by the manual update portion extraction unit 185 . The operation of the model update location identification unit 188 will be detailed later.

Next, with reference to the flowchart shown in FIG. 10, the flow of processing of the maintenance support method performed by the maintenance support system of this embodiment from when the manual is updated to when the editing of the failure causal model 230 is completed will be described.

FIG. 10 is a flow chart showing an example of the operation of the maintenance support system S according to the embodiment.

In FIG. 10 , in step S 1010 , the equipment designer 172 copies the updated new manual to the manual management unit 170 . This is simply a file copy.

In step S1020, manual update portion extraction unit 185 compares the new manual and the old manual, and outputs information such as table 1600 shown in FIG. Thereafter, branching from step S1040 onward is performed based on the value of the update type 1610 of the table 1600 as a condition.

In step S 1030 , in order to update the fault causal model 230 corresponding to the old manual, the model update part identifying unit 188 makes a copy of it and stores it in the fault causal model database 180 . Specifically, the model update location identification unit 188 generates a manual version number and a model ID in sequence or at random, inputs them into the manual version 210 and model ID 220 of the failure causal model database 180, and the model body is an existing model. The latest version of the fault causal model 230 is copied and generated. The target equipment lot number 240 is extracted from within the manual or input by the equipment designer 172 .

As information for the engineer 160 to edit the failure causal model in S1040 to S1070 described below, the model update location identification unit 188 causes the display unit 198 to display a GUI screen as shown in FIG. The screen shown in FIG. 12 is for the engineer 160 to edit the failure causal model 1200 through the input unit 199 while viewing the manual 1230 before update and the manual 1260 after update. In order to support the editing work, the model update part specifying unit 188 displays balloons 1235, 1265, . . . In addition, the model update location identification unit 188 identifies locations to be corrected in the failure causal model 1200 by reflecting the updated portion of the manual, and displays balloons 1205, 1220, . . .

For example, deletion of manual 1230 shown in callout 1235 corresponds to deletion of node 1220 of failure causal model 1200, addition to manual 1260 shown in callouts 1265, 1267, 1270 corresponds to failure mode 1215 of failure causal model 1200, node 1225 and the addition of inspection items 1227 are supported. The wording change of the inspection item of the manual 1260 shown in the balloon 1275 corresponds to the change of the inspection item 1205 of the failure causal model 1200 .

Therefore, for example, on the screen shown in FIG. can streamline the editing of In order to create this screen, the model update location specifying unit 188 repeats the processing shown in steps S1040 to S1070. One row of the update part 1600 is processed in one loop.

If the update type is added in step S1040, the process proceeds to step S1045; otherwise, the process proceeds to step S1050.

In step S1045, the model update location identification unit 188 displays balloons 1215, 1225, and 1227 written as "add" among the balloons shown in FIG.

For this purpose, the model update part identification unit 188 first extracts the manual 1230 before update and the manual 1260 after update from the update part 1600 output by the manual update part extraction unit 185, the manual before update 1650, and the manual 1655 after update. display (see FIG. 16). Specifically, the wording of the balloon is extracted from the update type 1610 of the updated portion 1600, and the position of the balloon is known from the number of pages 1620 to 1640 of the updated portion, etc., and is displayed based thereon.

Next, in order to identify nodes displaying balloons 1215, 1225, and 1227 of “addition”, the model update location identification unit 188 searches the reference locations 920, 930, and 940 of the linking database 173. FIG. The number of pages 1620, 1630, 1640, etc. of the updated portion 1600 are used as search keys. As a result of the search, balloons 1215, 1225, and 1227 of “addition” are displayed on the nodes and links written in the tying destination node 960 of the tying database 173 .

If the type of update is changed in step S1050, the process proceeds to step S1055; otherwise, the process proceeds to step S1060.

Step S1055 is processing for displaying a balloon 1205 of "change". This is according to the same procedure as that for displaying the additional balloon in step S1045. That is, the model update location identifying unit 188 searches the linking database 173 using the page numbers 1620, 1630, and 1640 read from the updated part 1600 as search keys, and acquires the linking destination node 960. FIG. Then, the model update location identification unit 188 displays a change balloon as 1205 .

If the update type is delete in step S1060, the process proceeds to step S1065; otherwise, the process proceeds to step S1070.

Also in step S1065, the model update location identification unit 188 causes the "delete" balloon to be displayed by the same procedure as in step S1045. At this time, at the stage of step S1065, only links between nodes are given as shown in FIG. After that, in step S1075 after all the loops of the table of the update part 1600 have been processed, a "delete" balloon is added to the node whose links are all lost, as in the balloon 1220 in FIG. This processing will be described later with reference to FIG.

In step S1070, the model update location identification unit 188 determines whether or not an unconfirmed update location remains. This is determined by determining whether or not there is a row in the updated portion 1600 for which the processing of steps S1040 to S1070 has not been performed. If so, the process returns to step S 1040 to move to the next unprocessed row of the next update portion 1600 .

In step S1075, if there is a node to be deleted by the model update location identification unit 188, a subroutine is called that finds it and attaches a deletion balloon. A specific subroutine flow will be described with reference to FIG. FIG. 11 shows the procedure for examining the nodes displayed at 1200 in FIG. 12 one by one and marking the nodes with deletion balloons on the links for deletion.

In step S1110, the model update location identification unit 188 refers to the link connected to one node X. FIG. In step S1120, if all the links have deletion balloons, the process goes to S1130 to attach a deletion balloon to the node X like the balloon 1220 in FIG. Thereafter, the delete mark is removed from the link in step S1140. On the other hand, if no deletion balloon is attached to all links, the node X cannot be deleted, so the process proceeds to S1150.

At step S1150, it is determined whether or not the link information of all nodes has been confirmed. If it has been confirmed, this subroutine is terminated, and after returning to step S1075, the process proceeds to step S1080. Otherwise, return to step S1110.

In step S1080, engineer 160 corrects fault causal model 1200 using input unit 199 while viewing the balloon in FIG. The correction method is to click balloons 1215, 1205, and 1220 to add a node for balloon 1215, change the node name for balloon 1205, and delete a node for balloon 1220. FIG. FIG. 13 shows a screen on which those corrections are reflected.

Also, when a link 1410 is accompanied by a deletion balloon 1420 as shown in FIG. 14, the corresponding link is deleted as shown in FIG. However, if the engineer 160 determines that these deletions and additions are not desirable, the links and nodes may be edited manually.

The result of correction is reflected in the linking database 173 by the model update location identification unit 188 . If the balloon in FIG. 12 is clicked to accept the correction, the information in 1620, 1630, and 1640 of the updated portion 1600 overwrites the corresponding portion of the linking database 173. FIG. When the engineer 160 manually edits, the information corresponding to 1620, 1630, and 1640 of the updated portion 1600 is input by selecting the character strings of the manual with a mouse.

In step S<b>1085 , the failure causal model 1200 edited by the model update location identification unit 188 is stored in the failure causal model database 180 . This is done by overwriting the copy of the old version of the failure causal model 230 stored in the failure causal model database 180 of FIG. 2 in step S1030.

Therefore, according to this embodiment, it is possible to improve the accuracy of specifying the failure mode of the device 104 . Further, it is possible to improve the accuracy of identifying the failure mode of the device 104, reduce wasteful replacement work, shorten the investigation time, and shorten the time from the failure of the device 104 to recovery.

In addition, the above-described embodiment is a detailed description of the configuration for the purpose of explaining the present invention in an easy-to-understand manner, and is not necessarily limited to those having all the described configurations. Moreover, it is possible to add, delete, or replace a part of the configuration of each embodiment with another configuration.

Further, each of the above configurations, functions, processing units, processing means, and the like may be realized by hardware, for example, by designing them in an integrated circuit. The present invention can also be implemented by software program code that implements the functions of the embodiments. In this case, a computer is provided with a storage medium recording the program code, and the processor of the computer reads the program code stored in the storage medium. In this case, the program code itself read out from the storage medium implements the functions of the above-described embodiments, and the program code itself and the storage medium storing it constitute the present invention. Examples of storage media for supplying such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs (Solid State Drives), optical disks, magneto-optical disks, CD-Rs, magnetic tapes, A nonvolatile memory card, ROM, or the like is used.

Also, the program code that implements the functions described in this embodiment can be implemented in a wide range of program or script languages such as assembler, C/C++, perl, Shell, PHP, and Java (registered trademark).

Furthermore, by distributing the program code of the software that realizes the functions of the embodiment via a network, it can be stored in storage means such as a hard disk or memory of a computer or in a storage medium such as a CD-RW or CD-R. Alternatively, a processor provided in the computer may read and execute the program code stored in the storage means or the storage medium.

In the above-described embodiments, the control lines and information lines indicate those considered necessary for explanation, and not all control lines and information lines are necessarily indicated on the product. All configurations may be interconnected.

S... maintenance support system, F1 to F3... failure mode, I1 to I5... inspection item, 100... terminal, 104... equipment, 150... center side server, 170... manual management unit, 173... linkage database, 175... failure mode Probability calculation unit 180 Failure causal model database 185 Manual update part extraction unit 188 Model update part identification unit 190 Communication unit 198 Display unit 199 Input unit 230, 1200 Failure causal model 1600 ... Updated part

Claims (11)

a causal model unit that stores a causal model that is created based on an information source regarding the maintenance target equipment and that describes the causal relationship between the state of the maintenance target equipment and inspection items;
a linking database section storing a linking database that describes the correspondence between the information source and the causal model;
an updated part extraction unit for extracting an updated part when the information source is updated;
A maintenance support system comprising: an update part identification unit that identifies a part to be updated in the causal model by searching the linking database based on the update part. 2. The maintenance support system according to claim 1, wherein said updated part extraction unit extracts at least one of an added part, a changed part and a deleted part of said information source as said updated part. 2. The maintenance support system according to claim 1, further comprising a presentation unit for presenting the location to be updated specified by the update location specifying unit. 4. The maintenance support system according to claim 3, wherein the presenting unit presents the information source and the updated part extracted by the updated part extracting unit. 4. The maintenance support system according to claim 3, wherein the presenting unit presents the causal model before updating and the causal model in which portions to be updated are presented. 5. The maintenance support system according to claim 4, wherein the presenting unit presents the type of update in the updated portion extracted by the updated portion extracting unit. 6. The maintenance support system according to claim 5, wherein the presenting unit presents the update type of the location to be updated specified by the update location specifying unit. 4. The maintenance support system according to claim 3, further comprising an input section for receiving an update input for said causal model based on the content presented by said presentation section. 9. The maintenance support system according to claim 8, wherein the update location identification unit updates the causal model based on the update input received by the input unit. a causal model unit that stores a causal model that is created based on an information source regarding the maintenance target equipment and that describes the causal relationship between the state of the maintenance target equipment and inspection items;
A maintenance support method executed by a maintenance support system having:
extracting the updated portion when the information source is updated;
A maintenance support method, wherein a portion to be updated in the causal model is identified by searching the linking database based on the updated portion. a causal model unit that stores a causal model that is created based on an information source regarding the maintenance target equipment and that describes the causal relationship between the state of the maintenance target equipment and inspection items;
A computer program executed by a computer having an association database unit that stores an association database that describes the correspondence between the information source and the causal model,
an updated portion extracting function for extracting an updated portion when the information source is updated;
A computer program for realizing an update part identification function of identifying a part to be updated in the causal model by searching the linking database based on the update part.

Images