JPS62165264A - Device for supporting maintenance and diagnostic work of plant apparatus - Google Patents

Abstract

PURPOSE:To improve the efficiency of data retrieval work by providing a data input/output device where data is displayed in a format adapted to the form of data on a basis of the presenting signal from a plant data management system. CONSTITUTION:Plant data management system 20 outputs a signal to private data base systems 21A-21D and outputs the presenting signal to data input/ output devices 23A-23D connected to private data base systems 21A-21D. Since data is displayed in a format adapted to the form of data on data input/ output devices 23A-23D, displayed data is easy for a plant operator to understand and has the format easy to use. Presented data is used to compare and grasp the current state of a plant apparatus, and the plant operator fixes the cause of abnormality and determines a countermeasure. Thus, the efficiency of the data retrieval work in trouble shooting is improved.

Description

DETAILED DESCRIPTION OF THE INVENTION (Technical Field of the Invention) The present invention relates to a plant equipment maintenance and diagnosis work support system (i) that supports maintenance and diagnosis work of equipment constituting an industrial plan h such as a nuclear power plant.

[Technical background of the invention]

In general, industrial plan 1-1 for example nuclear valve 7a bran 1
Various inspection items are carried out during actual size inspection work.

Furthermore, the large amount of data obtained as a result of this maintenance inspection is compared with the basic data that each separate device has individually, and a comprehensive judgment is made to ensure that the condition of the device is always correct (IN) and
Must be 3.

By the way, if any abnormality is discovered in the equipment during such inspection work or while the blunt is in operation, the cause of the abnormality must be quickly investigated and countermeasures must be taken immediately. .

The work to investigate the cause of such an abnormality is called troubleshooting, and requires detailed collection of various data obtained from the equipment subject to maintenance diagnosis. For example, on a blunt operation day, some kind of No. 1j is forcibly applied to the equipment to be inspected for maintenance, and the operation is performed accordingly.

Collect data related to reactions and IiC history from manufacturing to operation of specified equipment, and use these data to search for the cause of the abnormality through trial and error, that is, troubleshooting.

The following is an example of the data to be used for J3 in such a 1~rable shooting.

(1) Data related to machine IS A] Data indicating the basic specifications of the device, such as operating rated values of the device, data indicating the mechanical and electrical characteristics of the device, etc. (2) Data related to the status of the device Parameter value, part status l3Il'? 1' Information, etc. (3) Test data Results of various tests conducted on equipment such as component inspections, factory tests, and on-site characteristic tests (4) Trouble experience Before manufacturing, during operation, and during development Experience with past trouble cases that have occurred. In addition, 1~
Test data corresponding to troubles (5) Outage inspection records Check list of periodic inspection items, data on replacement parts at regular inspections, etc. (6) Data related to operation Operation procedures, abnormal experience during operation Data on the caps These data and current It is necessary to select the state of the equipment and investigate the cause of the abnormality by comparing data on various parameters obtained from the equipment.

In addition, each item of the above data must be prepared for the equipment to be inspected for maintenance in the plant, and the total amount of data is extremely large.

Conventionally, all such data has been organized as documents, and the necessary data must be searched and referenced from a huge amount of documents, requiring a great deal of effort.

On the other hand, there are cases in which only a limited number of people memorize all of the data regarding a certain limited number of devices subject to maintenance and diagnosis. For example, the person who designed the required equipment or the person who manufactured the equipment memorizes a considerable amount of data. In other words, in the case of experts in these fields, they can troubleshoot equipment subject to maintenance diagnosis to some extent without referring to documented data. is possible.

In such cases, all troubleshooting know-how is concentrated in the hands of experts, which is extremely efficient.

However, there are usually very few such experts, and they cannot be dispatched immediately if an abnormality occurs.

For this reason, in conventional plants, necessary data had to be searched sequentially from a huge amount of documents, which was extremely inefficient.

Therefore, in recent years, with the advancement of computer technology, the know-how and other specialized knowledge possessed by such experts has been integrated into a single unit, and by using this specialized knowledge, the efficiency of diagnosis of equipment subject to maintenance diagnosis has been improved. So-called expert systems are being tried to do this.

This uses a new method called knowledge engineering, and the system configuration of a conventional blunt equipment maintenance/diagnosis work support system using this is shown in Figure 2.

This is clearly explained by using a knowledge base 1 that stores specialized knowledge such as know-how of a room expressed in a predetermined format, and a reasoning mechanism 2 that executes diagnosis of an FM device that is subject to maintenance diagnosis (not shown). It is distinctive in that it is separated into 1C.

The knowledge base 1 contains work procedures or judgment criteria for performing maintenance diagnosis of equipment subject to maintenance diagnosis in a predetermined format, for example, I
It has a storage unit 1A that stores rules written in the F-TI (EN format) and a variable value storage unit 1B that stores state variables that do not represent the status of equipment subject to maintenance/diagnosis. When performing this, a value is set to a state variable from the input data, and a rule related to that state variable is stored in the rule storage unit 1.
A is extracted from A, and it is determined whether the condition specified in the rfFJ part of that rule is satisfied.

The data necessary for this determination is retrieved by referring to the data stored in the variable value storage section 1B.

Further, if necessary, the process is carried out while interacting with the plant operation port using the outlet device 4 having a CR7 display device 4a connected via the input/output section 13.

[Problems with back dance technique]

By the way, the knowledge stored in the knowledge base 1 is, for example, an expert who exports information obtained through experience in the form of a series of fragmentary articles f1, and IF-
It is converted into a conditional-executable statement in TI-IEN format. Therefore, in the knowledge base 1, a large number of definitive specialized knowledge of such experts is stored in the form of a collection.

For this reason, most problems such as troubles within the knowledge within the knowledge base 1 can be solved. However, if a problem occurs in the equipment subject to maintenance diagnosis, the cause of the problem can be immediately determined and immediate action can be taken.

However, for problems that are outside the scope of the knowledge stored in the knowledge base 1, there is no further problem-solving ability. In other words, if a problem that has never been experienced before occurs in a plant, there is a problem in that it is not possible to investigate the cause or select a countermeasure for the problem. Ta.

The conventional plan l-1 equipment maintenance diagnosis work support + 1 VC installation does not have the ability to solve problems that have never been experienced before, so in order to investigate the cause of the problem, it is necessary to investigate the equipment that is thought to be the cause of the problem. This requires the expertise of design and manufacturing experts. Therefore, I had to index the data necessary for troubleshooting from human documents that contained the data mentioned above.

Therefore, there was a risk that work efficiency would be poor and response times would tend to be delayed.

(Purpose of the Invention) The present invention has been made in consideration of the above circumstances, and aims to improve the efficiency of data retrieval work for troubleshooting, and to provide data in an easy-to-understand format according to the data format. The purpose of the present invention is to provide a plant equipment maintenance/diagnosis work support device that can provide the following information.

[Summary of the Invention] The plant equipment maintenance/diagnosis work support device 6 according to the present invention stores maintenance diagnosis knowledge for performing maintenance diagnosis on equipment to be inspected for maintenance diagnosis that is inserted into a plant, and is capable of referring to this maintenance diagnosis knowledge. A maintenance diagnosis inference system that grasps the state of the equipment subject to maintenance diagnosis and makes diagnostic inferences based on the diagnosis, and generates keywords for the equipment subject to maintenance diagnosis based on this diagnosis, and investigates the cause of failure when the equipment subject to maintenance diagnosis breaks down. A dedicated database system that stores the data necessary for the
The maintenance diagnosis inference system is connected to the dedicated database system, identifies the format of data based on the keywords from the maintenance inference system, and extracts and presents data from the dedicated database system that stores data in that format. It has a plant data management system and a data input/output device that is provided individually for each of the above-mentioned dedicated databases and that displays data in a format compatible with the data format based on the presentation signal from the above-mentioned plant data management system. be.

[Embodiments of the invention]

Embodiments of the present invention will be described below with reference to the drawings.

FIG. 1 shows a system R4 configuration according to an embodiment of the present invention, in which a maintenance diagnosis reasoning system 10 is connected to a plurality of dedicated database systems 2 via a plant data management system 20.
Connect 1A-D and create a database system 21 for each fi.
It is constructed by connecting data input/output devices 23A to 23D to Δ to D.

The maintenance diagnosis If theory system 1o has a knowledge base 11 and an inference d structure 12, and the knowledge base 11 provides maintenance diagnosis for a maintenance process, a diagnosis inference process, and its work procedure for performing a maintenance diagnosis of a maintenance diagnosis target device (not shown). It is stored as knowledge. This knowledge base 11 consists of a rule base 11Δ and a variable value storage section 11B. The rule base 11Δ stores specialized knowledge obtained by experts regarding equipment to be inspected (not shown) in a predetermined format, for example [F-T I-I E N
It is converted into type rules and stored. Further, the variable value storage unit 1113 stores status variables indicating the status of the maintenance diagnosis system (not shown).

The inference mechanism 12 is a rule base 11A in the knowledge base 11.
It executes maintenance diagnosis of the target equipment while referring to the contents of the and variable value storage section 11B, and assigns values to state variables from the data given from the diagnostic input/output device 13 on the right side of the CRT display device 13a. Ku is determined, a rule related to the state fg variable is selectively read from the rule base 11A, and it is determined whether the condition of the rlFJ part of the read rule is satisfied.

When evaluating the mouth, it is subject to maintenance diagnosis &'! ! The state variable value indicating the state of the plant is obtained by referring to the variable value in the variable storage section 11B or by interacting with the plant operator via the diagnostic input/output device 13. As a result, the data value newly increased by 1q is additionally stored in the variable value storage section 11B as a state variable.

However, an abnormality (trouble) that has never been experienced before occurs in an industrial plant, and trouble information is given to the diagnostic input/output device 13 for which it is impossible to make a diagnosis based on the knowledge in the knowledge base 11. In this case, the inference mechanism 12 performs some troubleshooting, narrows down the causes of the abnormality, and generates one or more keywords in accordance with these causes.

For example, the type of alarm that occurred, the indicated value of the monitor,
This is a group of keywords for distinguishing between similar events that have been experienced in the past. These keyword groups are provided to the plant data management system 20 via the transmission line 14.

Plant data management system 20 is connected to a plurality of dedicated database systems 21A-D via transmission line 31. Each dedicated database system 21A to 21D contains data that is necessary for troubleshooting equipment subject to maintenance diagnosis and that has not been analyzed to the point where it can be expressed in the required rule format for storage in the knowledge base 11. Store it. This stored data is stored in a plurality of dedicated database systems 21A to 21D for each data type. This dedicated database system 21A
-D is, for example, a wrestling data processing system 21A, a diagram processing system 21B, an image system 21C, and a drawing/document management system 21D.

The wrestling data processing system 21A collects process data and time series data obtained from the plant via a data recorder 25 and stores the data. Stores the rated value of. In addition, the diagram processing system 21B
Stores and accepts data related to Bran, which is handled in graph and tabular format. Roughly speaking, the image data system 2IC stores video and image data representing the status of plant equipment either in its original form or in a form with its features extracted. In addition, drawing/document management system 2
Among basic data related to plant equipment, 1D stores data expressed in drawings or documents such as design drawings or procedure manuals in the form of drawings.

On the other hand, the plant data management system 20 determines the keyword groups output from the inference mechanism 12 of the maintenance diagnosis system 10, and identifies the form of data related to these keyword groups. A dedicated database system 21 A- stores data according to the data format.
A start signal is output to D, and a data request signal is output. Furthermore, a presentation signal is output to the data input/output device H23A''D.

These data input/output devices 23A-D are individually connected to each dedicated database system 21A-D. Then, based on a presentation request signal from the data management system 20, the data is displayed in a format suitable for the data format.

For example, the data input/output device 23B connected to the diagram processing system 21B is a color graphic CRT' (Cathode RaVttlbe) that can display diagrams.
), and the data input/output device 23C connected to the image system 21G uses a video projector for images.

In FIG. 1, numerals 15 and 16 are input/output units of the maintenance diagnosis inference system 10, and numerals 27 and 29 are input/output units of the plant data management system 20. Also, code 1
7.33.35 is a transmission line.

Next, we will discuss the effect of the Motominoura example.

When some kind of trouble (abnormality) information regarding an industrial plant such as an atomic horn power generation plant is input from the diagnostic input/output device 13, the inference mechanism 12 of the maintenance diagnosis inference system 10
The diagnostic procedure for this trouble information is shown in Knowledge Base 1.
1 from the rule base 11A, for example, IF-T.
It is output to the CRT display device 13a in HEN format.

The inference mechanism 12 uses the variable value storage unit 11B to determine the status of the equipment subject to maintenance diagnosis II! ! Read variables and infer diagnostics. Alternatively, the plant operation q sequentially determines whether or not each conditional term (1'') holds true in accordance with these diagnostic procedures.

The state variable values of the maintenance/diagnosis target equipment necessary for this judgment can be retrieved from the variable 1 direct storage section 11B and referred to in response to a requested operation of the input/output device 13. Alternatively, state variable values can also be input from the plant operation port.

When all of the above diagnostic procedures are executed, the final and detailed diagnosis result of the cause of the abnormality is displayed on the CRT display neck 13a of the diagnostic input/output device 13 by the inference mechanism 12. Along with this, the CRT display device η1 provides instructions on maintenance procedures, evaluates the degree of impact on the entire plant, and determines countermeasures based on diagnosis results.
It can be output to 3a.

However, if the input trouble information deviates from and exceeds the knowledge in the knowledge base 11, the inference mechanism 1
2 because it is not possible to infer a detailed and final diagnosis about the cause of the abnormality? ! Narrow it down to two causes of the abnormality and make inferences. The cause of the abnormality can be narrowed down based on, for example, the lighting state of an alarm indicating an abnormality in the monitor, whether the indicated value of the monitor deviates significantly from a reference value or expected value, or whether it indicates abnormal behavior. Then,
The Jet W 41 structure 12 generates a plurality of keywords according to these plurality of abnormal causes. This keyword is for distinguishing from, for example, the type of alarm that has occurred, the indicated value of the monitor, etc.

These keyword groups are given to the plan 1 to the data management system 20. This blank data management system 20 identifies the form of the data based on the sent keyword group by 1°L, and sends an activation request signal d3J to all of the dedicated database systems 23A to 23D according to the form.
and outputs a data request signal.

For example, if there is a request for presentation of data related to professional wrestling data and drawings/documents, the process data processing
l system 21A and drawing/branch management system 23D
Outputs a start request signal and a data request signal to. Dedicated database system 21 A-D into which the activation request signal was input
searches the database it owns for the data requested to be presented.

The plant data management system 20 outputs signals to the dedicated database systems 21A-D, and also outputs presentation signals to the data input/output devices 23Δ-D connected to the dedicated database systems 21A-D. Then, the data input/output devices 23A to 23D display the data in a format suitable for the data format. Therefore, the displayed data is displayed in a format that is easy to understand and use for plant operation C. In this way, the presented data can be used to compare and understand the current condition of the blunt equipment, and whether the plant operation is 0 or 5? Identify the cause of the problem and decide on countermeasures.

According to the above embodiment, the data output to the data input/output devices 21A to 21D is limited to data related to a plurality of causes of abnormality, and therefore is necessary in the process of proceeding with 1 to rubriccoating. In the process, it is possible to efficiently search for the most important and necessary data in the process.1 Therefore, it saves the effort of searching a huge amount of documents and improves the efficiency of troubleshooting. In addition to speeding up the process and saving labor, it is also possible to reduce the risk of making decisions.

In addition, the data input/output devices 23A-D display data in a format that is compatible with the data format, so it is possible to display data in the most understandable and easy-to-use format for plant operation 0. 1. Therefore, it is possible to more accurately judge operation U in J3 for troubleshooting.

Note that new knowledge obtained during troubleshooting may be exchanged into a required rule format and additionally stored in the rule base 11Δ to enhance the efficiency of the maintenance diagnosis reasoning system 10.

Further, the data in each dedicated database system 21A-D may be referred to directly by the data input/output equipment 23A-1) without going through the inference mechanism 12 of the maintenance diagnosis inference system 10.

Further, the dedicated database systems 21A to 21D are not limited to those in the above-mentioned example, but various systems may be used depending on the data format. For example, there are an audio data system that stores audio data of plan 1 equipment, and a video data system that stores work procedures and event transitions as videos.

In addition, the database 21 can be used not only to display data required during diagnostic work, but also to
After the diagnostic work is completed, related data can be output to the input/output device in order to show the basis of the diagnostic result.

〔Effect of the invention〕

As described above, according to the plant equipment maintenance diagnosis work support device according to the present invention, a plurality of dedicated database systems are connected to the maintenance diagnosis system for diagnosing equipment subject to maintenance diagnosis through Plan 1 to the data management system. Since each dedicated database system is configured to store data in each data format, the plant data management system cannot perform a final and detailed diagnosis of equipment subject to maintenance diagnosis using the maintenance diagnosis inference system. This allows blunt data to be retrieved and output from a dedicated database system.

Moreover, this outputted plant data is data related to multiple diagnoses narrowed down based on the keywords from the inference mechanism of the maintenance diagnosis inference system, so the outputted data is narrowed down to a relatively small number of J3 As a result, it is possible to improve the efficiency of data retrieval work in troubleshooting.

In addition, the data input/output devices connected to each dedicated database system are configured to display data in a format that is compatible with the format of the data being displayed, so data can be presented to plant operators in an easy-to-understand and easy-to-read format. - can.

[Brief explanation of drawings]

FIG. 1 is a block diagram, not showing the system configuration, of an embodiment of the plant equipment maintenance diagnosis work support device according to the present invention, and FIG. 2 is a block diagram showing the system configuration of a conventional example. DESCRIPTION OF SYMBOLS 10... Maintenance diagnosis inference system, 11... Knowledge base, 11A... Rule storage unit, 11B... Variable value storage unit, 12... Inference mechanism, 20... Plan 1 data management system, 21A-D... Dedicated database system, 23A-D... Data input/output device.

Claims (1)

[Claims] Stores maintenance diagnosis knowledge for performing maintenance diagnosis of equipment subject to maintenance diagnosis in a plant, refers to this maintenance diagnosis knowledge to grasp the status of the equipment subject to maintenance diagnosis and makes diagnostic inferences, and determines the subject of maintenance diagnosis based on this diagnosis. A maintenance diagnosis inference system that generates keywords for equipment, and a dedicated database that stores data necessary to investigate the cause of failure when the equipment subject to maintenance diagnosis fails, and has multiple dedicated databases for each type of stored data. The system is connected to the maintenance diagnosis inference system and the dedicated database system, and identifies the format of data based on the keywords from the maintenance inference system, and pulls and presents data from the dedicated database system that stores data in that format. and a data input/output device that is provided individually for each of the above-mentioned dedicated databases and that displays data in a format compatible with the data format based on the presentation signal from the above-mentioned plant data management system. A plant equipment maintenance diagnosis work support device characterized by: