JPH07261825A - Plant operation assistance device - Google Patents

Abstract

PURPOSE:To provide the plant operation assistance device which can accurately predict the cause and progress of abnormality of a plant. CONSTITUTION:This device consists of a 1st means which detects the abnormality of the plant, identifies the cause of the abnormality, and predicts the progress of the abnormality to diagnose the progress state of the abnormality, a 2nd means which stores knowledge regarding the abnormality cause of the plant, a 3rd means which stores knowledge regarding the abnormality progress at the time of the plant abnormality, a 4th means which inputs a process signal of the plant and converts it into a signal to easily be processed by the 1st means, and a 5th means which outputs the abnormality cause, an operation guide, the prediction result of the abnormality progress, and the progress state of the abnormality; and the 4th means inputs a measurement signal and an alarm signal regarding the state of the plant from the object plant 10 and the 1st means inputs signals from the 4th means, 2nd means, and 3rd means and outputs a signal regarding the diagnostic result to the 5th means.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a driving support device applied to driving support for a thermal power plant or the like. INDUSTRIAL APPLICABILITY The present invention can be used not only for thermal power plants but also for operation support of general plants and machinery.

[0002]

2. Description of the Related Art In recent years, various plants have been equipped with an abnormality diagnosis device and a driving support device for supporting the driving operation. However, the operation guides output by them are only the cause of the abnormality and the corresponding operation, and are not for predicting the progress of the abnormality such as the state of the plant going forward.

[0003]

[Problems to be Solved by the Invention] Since prediction of abnormal progress of a plant is entrusted to the knowledge and experience of operators,
There are the following problems. Depending on the person or even the same person, his / her physical and mental states cannot accurately predict abnormal development. Therefore, anxiety increases and mental load increases, which may result in erroneous operation or misjudgment.

In addition, in extreme cases, unnecessary plant stoppages may occur, or a great amount of time may be required to settle an abnormal state. An object of the present invention is to provide a device capable of solving such a problem.

[0005]

[Means for Solving the Problems]

(First Solving Means) A plant operation support apparatus according to the present invention (A) detects a plant abnormality by means of the processing device 1, identifies the cause of the abnormality, predicts the progress of the abnormality, and diagnoses the progress of the abnormality. A first means for storing the knowledge about the cause of abnormality of the plant by the first memory 2; and a second means for storing the knowledge about the progress of abnormality at the plant by the second memory 3. The process signal of the plant is input by the 3 means and (D) the communication input device 4,
A fourth means for converting the signal into a signal that can be easily processed by the means;
(E) The output device 5 is provided with a fifth means for outputting the cause of abnormality of the plant, the operation guide, the prediction result of the abnormality progress, and the progress status of the abnormality, and the fourth means is the target plant 1 for assistance.
The measurement signal and the alarm signal regarding the state of the plant are input from 0, the first means is the fourth means, the second means,
It is characterized in that a signal is inputted from the third means and a signal relating to a diagnosis result is outputted to the fifth means.

(Second Solution Means) In the plant operation support system according to the present invention, in the first solution means, the abnormality described in (A) is detected, the cause of the abnormality is identified, and the progress of the abnormality is predicted. Then, the first means for diagnosing the progress of the abnormality stores the process signal converted by the fourth means for inputting the process signal of the plant and converting it into a signal that can be easily processed by the first means and the knowledge about the cause of the abnormality of the plant. Using the knowledge stored in the second means, the abnormality of the plant is detected, the cause of the abnormality is identified, the possible ripple events due to the progress of the identified abnormality cause are extracted, and further, the knowledge about the abnormality development at the time of the plant abnormality Using the knowledge about the corresponding ripple event stored in the knowledge stored in the third means for storing the information, the ripple event caused by the development of the abnormality is identified and the stage of ripple is diagnosed.

(Third Solving Means) In the plant operation support apparatus according to the present invention, in the first solving means, the second means for storing the knowledge about the cause of the abnormality of the plant described in (B) causes the cause of the abnormality. It is characterized by describing the knowledge for identifying the cause and the ripple events that can occur due to the development of individual abnormal causes.

(Fourth Solving Means) In the plant operation supporting apparatus according to the present invention, in the first solving means, the third means for storing the knowledge about the abnormal progress of the plant at the time of an abnormality described in (C), It is characterized by describing the knowledge for identifying the spillover event caused by the progress of anomaly and the knowledge for diagnosing the stage of spillover.

(Fifth Solving Means) In the plant operation supporting apparatus according to the present invention, in the first solving means, the cause of the plant abnormality described in (E), the operation guide, the prediction result of the abnormality progress, and the abnormality progress. It is characterized in that the fifth means for outputting the situation notifies the cause of abnormality identified by the first means, the operation guide, the prediction result of the abnormality progress, and the progress situation.

[0010]

The process signal is input by the fourth means, converted into a signal which can be easily processed by the first means, and transmitted to the first means. The first means uses the knowledge stored in the second means and the third means and the signal received from the fourth means to identify the cause of abnormality of the plant, predict the abnormality development, and diagnose the abnormality development situation. , To the fifth means. The fifth means outputs the cause of the abnormality received from the first means, the operation guide, the prediction result of the abnormality progress, and the abnormality progress situation.

[0011]

【Example】

(1) Device Configuration FIG. 1 shows the first embodiment of the present invention. The part surrounded by the broken line in FIG. 1 is the scope of the present invention.

A first memory for storing knowledge about the cause of an abnormality of a plant for a processing apparatus 1 which detects an abnormality of a plant, identifies the cause of the abnormality, predicts the progress of the abnormality, and diagnoses the progress of the abnormality. 2, a second memory 3 for storing knowledge about abnormal progress at the time of plant abnormality, a communication input device 4 for inputting a process signal of the plant and converting it into a signal that can be easily processed by the processing device 1, an abnormality cause, an operation guide , The abnormality prediction result, and the output device 5 that outputs the abnormality progress. Then, the communication input device 4 is connected to the plant 10 that is the target of support of the present driving support device. (2) Abnormal cause knowledge In the first memory 2, the following contents are described for each cause of the plant abnormality. (A) Abnormal cause name The name uniquely assigned to the cause of the abnormality. (B) Trigger A condition for extracting the cause of abnormality in (a) as a candidate for the cause of abnormality. (C) Demonstration conditions Conditions for identifying the cause of the abnormality in (a) as the cause of the abnormality. (D) Ripple event The name of a ripple event that can occur when the abnormality in (a) occurs. (E) Guide Contents of guidance output when the cause of abnormality in (a) occurs.

FIG. 3 shows a format example of the description of the knowledge of the cause of abnormality.
A specific example of the description is shown in FIG. In the figure, items with a + after it mean that a plurality of items can be described. Below,
In accordance with the general term of knowledge engineering, the whole description of FIG. 3 is called a frame, especially the frame in this case is called an abnormal cause frame, and the inside of one stage is (trigger ...), (verification condition ...).
The contents of knowledge about etc. are called slots, and (trigger condition name), (condition) etc. inside one stage are called facets.

In the description example of FIG. 4, (4-1) "Defective water supply flow rate control system" is taken out as a candidate for the cause of abnormality by (4-2) "Drum water level caution alarm", and (4-3) " If "Drum water level control deviation is large" and it is not "large water flow rate" and "small water supply flow rate controller output", or is not "small water supply flow rate" and "large water supply flow rate controller output", identify the cause of abnormality (4-4) “G due to rise in drum water level
"T trip", "GT trip due to lowering of drum water level"
The guideline is (4-5) "Manually operate the drum water level control valve. If the operating end is locked or the operating end is abnormal, and if normal operation does not recover, stop GT after contacting the middle feed". It is shown that. (3) Spillover event knowledge The second memory 3 stores knowledge about abnormal progress of the plant for each pattern of the spread of abnormalities. Specifically, the following contents are described. (A) Ripple event name The name uniquely assigned to the abnormal ripple pattern. (B) Occurrence conditions Conditions under which this ripple event is judged to occur. (D) Spillover stage The name of a series of stages of this spillover event is described along with the conditions for determining that the stage has been reached.

FIG. 5 shows a format example of the description of knowledge, and FIG. 6 shows a specific example of the description. In the figure, items with a + after it mean that a plurality of items can be described. In the following, in accordance with general terms of knowledge engineering, the entire description of FIG. 5 will be referred to as a ripple event frame.

In the description example of FIG. 6, (6-1) "GT trip due to rise of drum water level" occurs when (6-2) "Drum water level" is larger than "Drum water level standard value + 200 mm", 6-3) "Boiler security device detector operation"
If the above condition is satisfied, a “boiler security device detector operation alarm” is given, and (6-4) “drum water level” becomes “drum water level standard value +
If it becomes larger than "300 mm", "drum water level high trip" and "GT trip" will occur. It is shown that. (4) Communication Input Device The communication input device 4 inputs process measurement signals such as temperature, pressure, valve open / closed state, pump start / stop state, and alarm signals (analog and digital) from the support target plant 10, and will be described later. The processing device 1 converts the signal into a signal that can be easily numerically processed, and transmits the signal to the processing device 1. (5) Processing Device The processing device 1 uses the signal received from the communication input device 4 and the knowledge about the cause of abnormality stored in the first memory 2 and the knowledge about the progress of abnormality stored in the second memory 3. Then, the abnormality is detected, the abnormality is identified, the abnormality is predicted, and the progress is diagnosed at regular intervals.

Specifically, the following processing is performed according to the flowchart of FIG. Step 1, data fetching The data received from the communication input device 4 is stored in the memory inside the device.

Step 2, Detection of Abnormality It is sequentially examined whether or not all the abnormal cause frames are in the plant state described in the trigger condition, that is, whether or not an abnormality has occurred. If an error has occurred, the name of the error cause is extracted and placed in the judgment queue without duplication. If no abnormality has occurred, the process returns to step 1.

Step 3, Identification of Cause of Abnormality For the cause frames of abnormality, which correspond to all the cause names of abnormality in the diagnostic queue, the verification conditions are sequentially evaluated. It is transmitted to the guide output device 5 and the corresponding ripple event is extracted and placed in the ripple event queue without duplication. If not established, delete from diagnostic queue.

Step 4, Prediction of anomalous progress Sequential event conditions are sequentially evaluated for succession event frames corresponding to all the succession event names in the succession event queue. Is transmitted to the output device 5. If it does not hold, delete it from the ripple event queue.

Step 5, Diagnosis of Abnormal Progress Situation The conditions described in the spread stage are successively evaluated for the spread event frames corresponding to all spread event names in the spread event queue, and they are satisfied. For example, the corresponding stage name is transmitted to the output device 5. If it does not hold, it is not sent. When the processing for all the ripple event names is completed, the process returns to step 1. (6) Output Device The output device 5 outputs the plant abnormality cause, the operation guide, the abnormality development prediction result, and the abnormality development situation diagnosis result received from the processing device 1.

[0022]

Since the present invention is constructed as described above, it has the following effects. (1) With the device of the present invention, it is possible to know the prediction result of abnormal progress of a plant and the progress status of abnormal progress. The load is reduced, and the possibility of erroneous operation or erroneous judgment can be reduced. (2) Therefore, it is possible to prevent an unnecessary plant stop due to an erroneous judgment, and it is possible to reduce the possibility that it takes a lot of time to converge the abnormal state.

[Brief description of drawings]

FIG. 1 is a diagram showing a plant operation support device according to a first embodiment of the present invention. The part surrounded by the broken line in the figure is the scope of the present invention.

FIG. 2 is a flowchart of a process according to the first embodiment.

FIG. 3 is a diagram showing a format example of a description of abnormality cause knowledge and a specific example (1) of the description in the first embodiment.

FIG. 4 is a diagram showing a format example of a description of abnormality cause knowledge and a specific example (2) of the description in the first embodiment.

FIG. 5 is a diagram showing a format example of a description of a ripple event knowledge and a specific example (1) of the description in the first embodiment.

FIG. 6 is a diagram showing a format example of a description of the spread event knowledge and a specific example (2) of the description in the first embodiment.

[Explanation of symbols]

 1 ... Processing device, 2 ... 1st memory, 3 ... 2nd memory, 4 ... Communication input device, 5 ... Output device, 10 ... Support target plant.

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Satoshi Tanaka 2-1-1 Niihama, Arai-cho, Takasago-shi, Hyogo Mitsubishi Heavy Industries Ltd. Takasago Plant

Claims (5)

[Claims] 1. A first means for detecting an abnormality of a plant by a processing device (1), identifying the cause of the abnormality, predicting the progress of the abnormality, and diagnosing the progress of the abnormality (A). First
Means (2) for storing knowledge about the cause of abnormalities in the plant, and (C) third means (3) for storing knowledge about abnormal progress at the time of plant abnormality in the second memory (3); A fourth means for inputting a process signal of a plant through a communication input device (4) and converting it into a signal that can be easily processed by the first means, and (E) an output device (5) for causing a plant abnormality, an operation guide, and an abnormality development. The fifth means for outputting the prediction result and the progress of the abnormality, the fourth means inputs a measurement signal and an alarm signal regarding the state of the plant from the support target plant (10), and the first means, A plant operation support device, wherein signals are input from the fourth means, the second means, and the third means, and a signal relating to a diagnosis result is output to the fifth means. 2. A plant abnormality according to (A) is detected,
The first means for identifying the cause of the abnormality, predicting the progress of the abnormality, and diagnosing the progress of the abnormality is converted by the fourth means for inputting the process signal of the plant and converting it into a signal that can be easily processed by the first means. The abnormalities of the plant by using the knowledge stored in the second means for storing the process signal and the knowledge of the abnormal cause of the plant, identify the abnormal cause, and extract the possible ripple events due to the development of the identified abnormal cause Furthermore, by using the knowledge about the corresponding ripple event in the knowledge stored in the third means for storing the knowledge about abnormality progress at the time of plant abnormality, the ripple event caused by the abnormality progress is identified and the spread stage is determined. The plant operation support device according to claim 1, wherein the diagnosis is performed. 3. The second means for storing the knowledge about the cause of abnormality of the plant described in (B) describes the knowledge for identifying the cause of the abnormality and the ripple events that may occur due to the development of each abnormality cause. The plant operation support device according to claim 1, wherein 4. A third means for storing knowledge about abnormal progress at the time of abnormalities of the plant described in (C), for knowledge for identifying a ripple event caused by the progress of the abnormality and for diagnosing a stage of ripple. 2. The plant operation support device according to claim 1, wherein the knowledge of is described. 5. The cause of abnormality, the operation guide described in (E),
5th, which outputs the prediction result of abnormal progress and the progress of abnormal progress
The plant operation support device according to claim 1, wherein the means notifies the cause of abnormality identified by the first means, the operation guide, the prediction result of abnormality progress, and the progress status of abnormality.