JPH0769199B2 - Plant abnormality diagnosis device - Google Patents

Description

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

[Prior Art] FIG. 5 is a block diagram showing a conventional plant abnormality diagnosis device described in, for example, Japanese Patent Application No. 63-120916.

In FIG. 5, (1) is an electronic computer, a process input section (3) for reading a process amount from a power plant (2), an abnormality detecting 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 processing, etc.
Consists of.

Further, FIG. 2 is an explanatory diagram for explaining the anomaly cause inference method, and device 1, device 2, ..., Device n in FIG.
Indicates the devices that make up the plant,
It is a part that is divided by inputting a process value into the process input unit (3), and may not necessarily be separated as an independent device.

FIG. 3 is an explanatory diagram for explaining the knowledge created for each of the devices that make up the plant.
Remembered in.

Next, the operation will be described. In the process input section (3), qualitative data such as "increased build-up" and "constant" that are used to input data from the power plant (2) and to use quantitative process values in the abnormality cause inference section (5). Convert to. The abnormality detection processing unit (4) monitors the process amount input and processed by the process input unit (3) and detects that an abnormality has occurred 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), and detects the anomalous event and qualitative
The failure location and cause are inferred by the quantitative process amount, and the inference result is displayed and processed by the display processing unit (8).
It 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 the devices 1 to n, and the knowledge created for each device is such that “if the input data is increased in the increase, the output data is increased in the increase” as shown in FIG. As described above, the knowledge that qualitatively expresses the characteristics in the normal state, the knowledge that quantitatively expresses the relationship between the input data and the output data in the normal state, and "If cause A, the output data hunts when the input data is constant" It consists of various causes of failure and knowledge of causal relationships between events. For example, when the abnormal event Z is detected by the abnormality detection processing unit, the abnormal cause inference unit starts the search from the device 5 having the abnormal event Z as output data, and the normal characteristic knowledge of each device and stable / quantitative analysis. The device causing the abnormality is identified by comparing with the 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.

[Problems to be Solved by the Invention]

The conventional plant abnormality diagnosing device is configured as described above, and infers the location / cause of failure, but the content displayed on the display processing unit (8) is the location / cause of failure obtained as a result of the inference. Only operation guidance corresponding to the cause,
There is a problem that the operator who actually sees the displayed contents cannot determine whether to perform the operation according to the displayed contents when the reason for the inference is unclear.

The present invention has been made to solve the above problems, and an operator can be displayed by automatically synthesizing and displaying the reasoning reason for an inference result using a knowledge base and process value information. It is an object of the present invention to obtain a plant abnormality diagnosing device capable of presenting inference grounds to.

[Means for Solving the Problems]

The plant abnormality diagnosing device according to the present invention provides an input process value used for inference for identifying an occurrence point and a cause of an abnormality and an inference for identifying an occurrence point and a cause of an abnormality obtained from a knowledge base (6). Edit and display the sentence that explains the reasoning that led to the identification of the location and cause of the abnormality, based on the normal characteristics of the equipment used, the cause of failure, and knowledge of causal relationships between events. Means (CRT display (7
Inference reason explanation sentence generation processing means (inference reason explanation processing unit (81)) displayed in 1) is provided.

[Action]

Inference basis The explanation sentence generation processing means, based on the input process value and knowledge used for inference to identify the location and cause of the abnormality at the time of occurrence of the abnormality, the inference basis for identifying the location and cause of the abnormality. Edit and display the sentence that describes.

Example of Invention

An embodiment of the present invention will be described below with reference to the drawings. First
In the figure, (1) is an electronic computer, and a process input section (3) for reading a process amount from a power plant (2).
And an abnormality detecting section (4) for detecting an abnormality from the process amount, and an abnormal point and an abnormal cause from the abnormal event detected by the abnormality detecting section (4) and the data input in the process input section (3). Knowledge composed of an abnormal cause inferring unit (5) for inferring, knowledge that is created qualitatively and quantitatively for characteristics in normal times created for each component device of the plant, and knowledge of causal relationships between failure causes and events Base (6)
And an inference reason explanation processing unit (81) that generates an inference basis explanation sentence from the result inferred by the abnormality cause inference unit (5) and also generates a voice message using the voice word dictionary (82).
And a display processing unit (83) that displays an occurrence event, a failure location, an abnormality cause, a corresponding operation guide, and an inference basis explanation on the CRT display device (71), and an abnormality occurrence and a failure location on the audio output device (72). A voice output processing unit (84) for outputting the cause of abnormality and the corresponding device guide by voice.

Further, FIG. 2 is an explanatory diagram for explaining an abnormality cause inference system and an inference basis explanation system in the present invention. Device 1, device 2, ..., Device n in FIG. In the figure, each is a part divided by inputting a process value into the process input unit (3), and may not necessarily be separated as an independent device.

FIG. 3 is an explanatory diagram for explaining the knowledge created for each of the devices that make up the plant.
Remembered in.

FIG. 4 is an explanatory diagram for explaining the inference basis explanation sentence generation processing method. The underlined portion shows the current value of the process amount described in the knowledge used in the inference. Is.

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 the process value is periodically inferred from the abnormality cause inference section (5).
Convert it to qualitative data such as "Increase in flatness" and "Constant" used in. The abnormality detection processing unit (4) monitors the process amount input by the process input unit (3),
When it deviates from the normal range, it detects that an abnormality has occurred. The anomaly cause inference unit (5) operates when an anomaly is detected by the anomaly detection processing unit (4), and infers the location and cause of the failure based on the detected anomalous event and qualitative / quantitative process amount. The result is displayed by the display processing unit (83) and displayed on the CTR display device (71) together with the inference reason explanation sentence created by the inference reason explanation processing unit (81). The audio output processing (84) performs audio output processing and outputs the audio output processing to the audio output device (72). Nest inference of anomalous causes is based on knowledge qualitatively and quantitatively expressing the characteristics at normal times created for each plant constituent device accumulated in the knowledge base (6) and knowledge of causal relationships between failure causes and events. Done. For example, in FIG. 2, the plant is composed of the devices 1 to n, and the knowledge created for each device is such that “if the input data is increased in the increase, the output data is increased in the increase” as shown in FIG. As described above, the knowledge that qualitatively expresses the characteristics in the normal state, the knowledge that quantitatively expresses the relationship between the input data and the output data in the normal state, and "If cause A, the output data hunts when the input data is constant" It consists of various causes of failure and knowledge of causal relationships between events. For example, when the abnormal event Z is detected by the abnormality detection processing unit (4), the abnormal cause inference unit (5) starts the search from the device 5 having the abnormal event Z as output data, and detects the normal characteristic knowledge of each device. The device causing the abnormality is identified by comparing the qualitative and quantitative data with the qualitative and quantitative data. Further, the cause of the failure is inferred from the knowledge of the causal relationship between the cause of failure and the event, which is included in the knowledge of the specified device.

Next, the operation of the reasoning explanation processing unit (81) will be described. As shown in FIG. 4, the reasoning reason explanation is composed of an abnormal event name, a failure part name, a failure part reasoning reason, and mainly a failure cause name and a failure cause reasoning reason. In the grounds for inferring failure location, the searched device names are listed, and the knowledge of normal characteristics is compared with the qualitative / quantitative data, and the equipment that satisfies all the normal characteristics is regarded as normal, and the data that does not satisfy the normal characteristics is detected. In this case, the device is regarded as abnormal, and the normal characteristic and the qualitative or quantitative data are incorporated into the explanation as inference base. Next, in the cause of failure reasoning, the knowledge of the causal relationship between the cause of failure and the event that matches the current data is incorporated into the explanation as the reasoning reason.

The method of synthesizing the inference basis explanation sentence is to perform a standard sentence edit using the underlined portion shown in FIG. 4 as a variable element.

At the same time, a voice output message is routinely synthesized using voice words corresponding to device names, data names, characteristics, etc. stored in the voice word dictionary (82). Note that FIG. 4 shows an example of the inference basis explanation when the abnormal event Z is detected in FIG.

〔The invention's effect〕

As described above, according to the present invention, the reasoning statement of the cause of the abnormality is used to infer the input process value used for the inference, and the characteristics of the device used for the reasoning for identifying the place and the cause of the abnormality in the normal condition and Generation of an inference reason explanation sentence in which a sentence explaining the reason for inferring the occurrence location and cause of the abnormality is edited and displayed on the display means based on the knowledge of the cause of failure and the causal relationship between events Since the processing means is provided, the reason can be easily confirmed with respect to the inference result output when an abnormality occurs, so that the operator can perform the corresponding operation after being satisfied, and It has the effect of increasing reliability.

[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 an explanatory view for explaining the reasoning explanation process, and FIG. 5 is a configuration diagram showing a conventional plant abnormality diagnosis device. is there. 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,
(71) is a CRT display device, (72) is a voice output device, (81)
Is an inference reason explanation processing unit, (82) is a voice word dictionary, (83)
Is a display processing unit. The same reference numerals in the drawings indicate the same or corresponding parts.

Claims (1)

[Claims] 1. Input process values from a plant composed of a plurality of devices, normal characteristics of each device obtained from a knowledge base created for each device, cause of failure, and causal relationship between events, etc. An input used for inference that characterizes the location and cause of the above abnormality in a plant abnormality diagnosis device that guides the operator by identifying the location and cause of the abnormality at the time of occurrence of abnormality by comparing and inferring knowledge Based on the process value and the knowledge, the reasoning reason explanation sentence generation processing means for editing and displaying on the display means the reasoning reason for identifying the location and cause of the abnormality is provided. Characteristic plant abnormality diagnosis device.