JPS6312093A - Abnormality diagnosing apparatus for power generation plant - Google Patents

Abstract

(57) [Summary] This bulletin contains application data before electronic filing, so abstract data is not recorded.

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to an abnormality diagnosis device for estimating the cause of abnormality in a power generation plant.

[Conventional technology]

FIG. 3 is a block diagram showing a conventional abnormality diagnosis device. In the figure, a computer +11 has a process input section (3) that reads process quantities from a power generation plant (2), and detects abnormalities from the process quantities. An abnormality detection unit (41), an abnormality cause estimation unit 151 that estimates the cause of the abnormality from abnormal events detected in the abnormality detection unit (4), a knowledge database (6) in which knowledge based on causal relationships is accumulated, and a CRT display device (
7), and a display processing section (8) that performs output processing.

Further, FIG. 4 is an explanatory diagram for explaining an abnormality cause estimation method in a conventional abnormality diagnosis device.

Next, the operation will be explained. The abnormality detection processing section (4) monitors changes in the process amount of the power generation plant inputted by the process input section (3), and detects that an abnormality has occurred when it deviates from the normal range.

The abnormality cause estimation unit +51 operates when an abnormality is detected by the abnormality detection processing unit (4), estimates the cause of the abnormality based on the detected abnormal event, and the inference result is displayed by the display processing unit (81) and sent to the ORT. It is displayed on the display device (7).The cause of the abnormality is inferred based on the knowledge based on the causal relationships accumulated in the knowledge database (61).

For example, in Figure 4, if the cause is rMJ, the event "Ml"
and "Ml" are generated. Cause [If MJ, event “Ml
l" and "MxJ" occur, and if the cause is "Zen", then "M2J
and "M22 J, [M23J occur. In this way, with the knowledge of the causal relationship expressed as related water, we search for and estimate the cause from the abnormal event that occurred.

[Problem that the invention seeks to solve]

Conventional abnormality diagnosis equipment is configured as described above, so it is easy to clearly express the causal relationship between causes and events as shown in Figure 4. There were problems in that knowledge could not be adequately expressed and it was difficult to apply knowledge about things for which there was no clear cause-and-effect relationship.

This invention was made to solve the above-mentioned problems, and aims to provide a power plant abnormality diagnosis device equipped with a knowledge database that can easily express knowledge that includes knowledge that has no clear causal relationship. purpose.

[Means for solving problems]

The power generation plant abnormality diagnosis device according to the present invention expresses the knowledge database using a cause-event relationship matrix (IJ) table, and expresses the cause-event relationship as a ratio representing the probability that the event will occur if the cause is the cause. It is expressed.

[Effect]

The anomaly cause estimating unit in this invention performs cause inference based on a knowledge database expressed in a cause-event relationship matrix table to determine the cause-and-effect relationship, such as the process amount of a power generation plant. It is also possible to estimate the cause when an abnormality occurs, even for things that do not occur.

〔Example〕

An embodiment of the present invention will be described below with reference to the drawings. 1st
In the figure, an electronic computer (1) is connected to a process input section (3) that reads process quantities from a power generation plant (21), an anomaly detection section (4) that detects an abnormality based on the process quantity, and an anomaly detection section (4) that detects an abnormality. An abnormality cause estimation unit (5) that estimates the cause of an abnormality based on abnormal events that occur, a knowledge database +61 that stores knowledge based on a matrix table of relationships between causes and events, and a CRT display device fi!
It consists of a display processing unit (8) that performs processing to output estimated causes, countermeasures, etc.

Further, FIG. 2 is an explanatory diagram for explaining the abnormality cause estimation method according to the present invention.

Next, the operation of the above embodiment will be explained. The abnormality detection processing section (4) monitors changes in the process amount of the power generation plant inputted by the process input section (3), and detects that an abnormality has occurred when it deviates from the normal range. The abnormality cause estimation unit (51 operates when an abnormality is detected by the abnormality detection processing unit (4), infers the cause of the abnormality based on the detected abnormal event, and the inference result is displayed and processed by the display processing unit (8). It is displayed on the CRT display device (7).The cause of the abnormality is inferred based on the knowledge based on the cause-event relationship matrix table stored in the knowledge database (6).

For example, in Figure 2, the relationship between cause "C1" and event "Ml" is expressed as [10eel J, and if "C1", then "
The probability that "1A1" will occur is 10%. Cause “C1”
The relationship between and event “M3” is expressed as “0 (%)”, and “C1
” indicates that the probability that “M3” will occur is 0%. In this way, causes can be inferred from events that have occurred based on knowledge expressed using the probability of occurrence of an event in the cause-event relationship matrix. That is, the event [M
If IJ occurs, the causes ``otJ, ``cJ, ``c
sJ, “The probability of being c4J is 10 to 1.
9RA), 25%), 0%), and for example, 30%) or more is indicated as the cause, and less than 30%) is indicated as the cause.
If the possibility of this being the cause is very low and can be ignored, then "C2" remains as the cause, with a probability of 91%)
It is estimated that

Also, if event M" and rM3J occur, the cause is "C1".

``The possibilities of OJ, rcaJ, and ro'J are
The probabilities for events rMIJ and -3 are added, respectively, and are 10 (! too), 94%), 90e4
1.0 cabinets, leaving "C2" and "03" as causes, each with a probability of 94%), which is estimated to be 90 cabinets.

〔Effect of the invention〕

As described above, according to the present invention, the knowledge database used for cause estimation is configured using a representation method using a cause-event relationship matrix table, so it can be applied even to cases where the causal relationship is not clear, and the estimation results can be Since numerical values indicating the values can be displayed at the same time, the estimation results can be presented to the operator in an easy-to-understand format, and countermeasures can be taken efficiently.

[Brief explanation of the drawing]

FIG. 1 is a configuration diagram showing a power plant abnormality diagnosis apparatus according to an embodiment of the present invention, and FIG. 2 is an explanatory diagram for explaining an abnormality cause estimation method. Figure 3 is a configuration diagram of a conventional power plant abnormality diagnosis device;
FIG. 4 is an explanatory diagram for explaining the abnormality cause estimation method. (11 is an electronic computer, (2) is a power generation brush), +31
is the process input section, (41 is the abnormality detection processing section, (5) is the abnormality cause estimation section, (61 is the knowledge database, (7) is the (ERT display processing section, and (8) is the display processing section. The same reference numerals in the middle indicate the same or equivalent parts.

Claims (1)

[Claims] In an abnormality diagnosis device that detects abnormality signs based on changes in process values, estimates the cause of the abnormality, and guides operators, the relationship between cause and event is expressed as the probability that the event will occur if the cause is the cause in a relationship matrix table. An abnormality diagnosing device for a power plant, characterized in that it is equipped with a cause estimation method that can be applied to abnormal phenomena in which the causal relationship is unclear, using the expressed knowledge.