JP2540909B2 - Plant abnormality diagnosis device - Google Patents

Description

Description: TECHNICAL FIELD The present invention relates to an abnormality diagnosing apparatus for estimating a location and a cause of an abnormality in a plant including a plurality of devices such as a power plant.

[Conventional technology]

FIG. 4 is a block diagram showing a conventional plant abnormality diagnosis device disclosed in, for example, Japanese Patent Laid-Open No. 60-91413.

In the figure, a computer (1) is a power plant (2)
A process input unit (3) for reading more process amount, and an abnormality detection unit (4) for detecting an abnormality from the process amount,
An abnormality cause inference unit (5) that infers an abnormality cause from an abnormal event detected in the abnormality detection unit (4), a knowledge database (6) in which knowledge on a causal relationship is accumulated, and a CRT display device (7) are output. And a display processing unit (8) for performing processing.

Further, FIG. 5 is an explanatory diagram for explaining an abnormality cause estimation method in a conventional abnormality diagnosis device.

Next, the operation will be described. The abnormality detection processing unit (4) monitors a change in the process amount of the power plant input by the process input unit (3) and detects the occurrence of an abnormality when the process amount deviates from the normal range. The anomaly cause inference unit (5) operates when an anomaly is detected by the anomaly detection processing unit (4), infers an anomaly cause based on the detected anomalous event, and the inference result is displayed by the display processing unit (8). It is displayed and displayed on the CRT display device (7). The reason of the abnormality is inferred by the knowledge based on the causal relationship accumulated in the knowledge database (6). For example, in FIG. 5, if the cause is "M", the events "M" and "M2" occur. If the cause is "M1", the events "M11" and "M12" occur, and if the cause is "M2", "M21", "M22", and "M23" occur. With the knowledge of the causal relationship represented as the relation tree in this way, the cause is searched and estimated from the abnormal event that has occurred.

[Problems to be Solved by the Invention]

Since the conventional plant abnormality diagnosing device is configured as described above, it can be easily realized when the causal relationship between the cause and the event is arranged as shown in FIG. It is difficult to assume. In addition, even if it can be assumed, if the event for the failure cause is a power plant or the like, it depends on the operating state of the plant, so it is not easy to organize the knowledge of the causal relationship between the cause and the event, and it is difficult to apply. There were challenges.

The present invention has been made in order to solve the above problems, and is provided with easy-to-express knowledge and inference means for a target plant in which knowledge of causal relationships between failure causes and events is difficult to organize. The purpose is to obtain a plant abnormality diagnosis device.

[Means for solving the problem]

A plant abnormality diagnosing device according to the present invention is a plant abnormality diagnosing device that estimates an abnormality from a change in a process value input from a plant including a plurality of devices and guides the operator to the plant constituent device. The knowledge that is created for each device and expresses the characteristics when the device is normal is qualitatively and quantitatively compared with the process value from the plant, and the device having the point causing the abnormality is specified. It is equipped with means.

[Action]

The plant abnormality diagnosing device according to the present invention qualitatively expresses the characteristics when the device created for each component device of the plant is normal: quantitatively expresses the process value from the plant by comparing and inferring the abnormality. The device having the point that is the cause of is identified, and the cause of the abnormality is estimated for the identified device.

Example of Invention

An embodiment of the present invention will be described below with reference to the drawings. In FIG. 1, (1) is an electronic computer, a process input section (3) for reading a process amount from a power plant (2), an abnormality detection section (4) for detecting an abnormality from the process amount, and an abnormality detection An abnormal cause inferring unit (5) that infers an abnormal place and an abnormal cause from an abnormal event detected in the unit (4) and data input in the process input unit (3), and a normal created for each constituent device of the plant. A knowledge base composed of knowledge that qualitatively and quantitatively expresses the characteristics of time and knowledge of causal relationships between causes of failures and events (6)
To the CRT display device (7), occurrence event, failure location / cause,
Display processing unit (8) for performing processing for outputting corresponding measures, etc.
Consists of

Further, FIG. 2 is an explanatory diagram for explaining an abnormality cause inference system according to the present invention.
A device 2, ..., A device n each represents a device that constitutes a plant, and is a part that is divided by inputting a process value into a process input unit (3), and can be necessarily separated as an independent device. It doesn't have to be.

FIG. 3 is an explanatory diagram for explaining the knowledge created for each device that constitutes the plant, and is stored in the knowledge base (6).

Next, the operation of the above embodiment will be described. In the process input section (3), data is input from the power plant (2), and quantitative process values are converted into qualitative data such as "slow increase" and "constant" used in the abnormality cause inference section (5). Convert. In the abnormality detection processing unit (4),
The process input section (3) monitors the process amount input and detects the occurrence of an abnormality when it deviates from the normal range. The anomaly cause inference unit (5) operates when an anomaly is detected by the anomaly detection processing unit (4), and detects a failure location based on the detected anomalous event and a qualitative / quantitative process amount.
The reason is inferred and the inference result is displayed by the display processing unit (8).
Is displayed on the CRT display device (7).
The reason for the abnormality is inferred by the knowledge accumulated in the knowledge base (6) for each component of the plant that qualitatively and quantitatively expresses the characteristics under normal conditions and the knowledge of the causal relationship between the failure cause and the event. Be done. For example, in FIG. 2, the plant is composed of devices 1 to n, and the knowledge created for each device is such that “if the input data slowly increases, the output data slowly increases” as shown in FIG. Knowledge that qualitatively expresses the characteristics under normal conditions and knowledge that expresses the relationship between input data and output data under normal conditions and “Cause A
If so, the output data is hunting when the input data is constant "and the knowledge of causal relationships between events. For example, if the abnormal event Z is detected by the abnormality detection processing unit, the abnormal cause inference unit detects the abnormal event Z.
The search is started from the device 5 that has as output data, and the device causing the abnormality is specified by comparing the normal characteristic knowledge of each device with the qualitative / quantitative data. Further, the cause of the failure is inferred from the knowledge of the causal relationship between the failure cause and the event, which is included in the knowledge of the specified device.

[Effects of the Invention] As described above, according to the present invention, the knowledge base used for inferring the cause of abnormality is created for each constituent device of the plant, and is composed mainly of a knowledge base that qualitatively and quantitatively expresses the characteristics at normal times. As a result, it is possible to infer an abnormal location even for an unexpected cause of abnormality, and it is easy to acquire and organize the knowledge of the causal relationship between the cause of abnormality and the event because it is possible to limit it to each component device of the plant. There is an effect such as.

[Brief description of drawings]

FIG. 1 is a block diagram showing an abnormality diagnosing device for a plant according to an embodiment of the present invention, FIG. 2 is an explanatory diagram for explaining an abnormality cause inference system of the device of FIG. 1, and FIG. 3 is FIG. 4 is an explanatory view for explaining the knowledge stored in the knowledge base of the device, FIG. 4 is a configuration diagram showing a conventional plant abnormality diagnosis device, and FIG. 5 is an explanation of an abnormality cause inference system of the device of FIG. It is explanatory drawing for doing. In the figure, (1) is an electronic computer, (2) is a power plant, (3) is a process input section, (4) is an abnormality detection processing section, (5) is an abnormality cause inference section, (6) is a knowledge base,
(7) is a CRT display device, and (8) is a display processing unit. The same reference numerals in the drawings indicate the same or corresponding parts.

Claims (1)

(57) [Claims] 1. A plant abnormality diagnosing device for estimating an abnormality based on a change in a process value composed of a plurality of devices and guiding the operator to the abnormality, which is created for each component device of the plant and is used when the device is normal. The knowledge that expresses the characteristics qualitatively and quantitatively and the process value from the plant are compared and inferred to identify the device having the location causing the abnormality, and the knowledge of the identified device An apparatus for diagnosing an abnormality in a plant, which is provided with means for inferring a cause of failure based on knowledge of a causal relationship between the cause of failure and the event in 1.