JPH063637B2 - Abnormal time plan support device for process plant - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION Object of the Invention (Industrial field of use) The present invention is directed to a failure or malfunction of equipment during operation of a process plant such as a power plant or an oil refining plant, an erroneous operation of an operator, a disturbance, etc. The present invention relates to an abnormality plan support device for a process plant, which diagnoses the cause of an abnormality and the state of the plant based on knowledge engineering based on data on process disturbances caused by the above, and formulates and synthesizes a countermeasure plan for the abnormality.

(Prior Art) Generally, when a disturbance of a process plant occurs, if the disturbance is left undisturbed, imbalance of substances or concentration of energy may occur locally in the plant, resulting in damage to the plant or release of harmful substances to the environment. There is. Therefore, it is necessary to detect the disturbance at an early stage, diagnose the state of the plant, and take appropriate measures. Therefore, in a conventional process plant, generally, necessary information about the plant is collected in a central control room, and the abnormality is detected and diagnosed by monitoring the information.

That is, in the conventional abnormality detection diagnosis, a normal operation range is defined in advance for the measured value from the plant, and an alarm device is provided to issue an alarm to the operator when the measured value deviates from this range. It makes it possible to monitor the entire plant widely. In addition, regarding the abnormality diagnosis and the measures against the abnormality when an alarm occurs,
Regarding the alarm, we are dealing with it by referring to the procedure manual and educating the operator by driving training beforehand.

(Problems to be Solved by the Invention) However, as the process plant generally becomes larger and more complicated, the scale of these alarm devices also increases,
The contents of procedure manuals and the contents of training are becoming more complicated. Therefore, the number of alarms far exceeding the processing capability of the operator may occur during the disturbance, and in such a case, it is difficult to properly process the alarms.

Therefore, we developed a system that uses computer information processing technology to reduce the number of alarms and provides only truly valuable and appropriate information to the operator, and an abnormality support system that provides the operator with an operation to respond to the abnormality. Has been done. As such an alarm suppression system, for example, a system that selects the earliest in time from a large number of alarms, or a relatively simple logic, for example, when multiple alarms occur due to the same cause, is directly connected to the cause A system has been proposed that suppresses unnecessary alarms by the logic of excluding other alarms and deleting other alarms. Although these alarm suppression systems have some effects, they are generally partial measures and cannot be considered as drastic measures.

On the other hand, as an abnormality support system, there is a system in which a corresponding operation is determined in advance for an assumed abnormality and is provided to an operator as an operation procedure when an abnormality occurs. It is pointed out as a problem. In addition, although a system that provides a countermeasure operation plan that is not based on the abnormality diagnosis result has been proposed, the effect is recognized from the viewpoint of ensuring the safety of the plant, but it cannot be said to be the optimum countermeasure operation. This is because the optimum driving procedure cannot be determined unless the cause and phenomenon of the abnormality are clarified.

However, in recent years, an abnormality diagnosis / driving operation guide system based on a new concept using a knowledge engineering method has been developed. This abnormality diagnosis and operation guide system contains a knowledge base that contains knowledge about the causes of abnormalities and the abnormal changes that appear in the measurement signals of the plant as a result, as well as knowledge that determines the handling procedures for abnormalities, and this knowledge. An inference mechanism that reads the above knowledge from the base and infers the cause of the abnormality and the corresponding operating procedure is provided.
In this abnormality diagnosis / operation guide system, for example, when one abnormal pattern is obtained from the measured value of the plant, the inference mechanism searches the knowledge base to determine whether there is knowledge matching the pattern. Ask and pick up the ones that match. Then, if there is a plurality of matched knowledge, the cause of abnormality and the corresponding operation procedure are estimated by selecting the most probable one from the plurality of knowledge.

However, in the above-mentioned abnormality diagnosis / driving operation guide system, it is possible to derive a diagnosis and a corresponding operation procedure for an abnormality cause and an abnormal pattern that are stored in the knowledge base in advance, Diagnosis and derivation of corresponding operating procedures cannot be performed for abnormal patterns. In addition, individual knowledge of such causes of abnormalities, abnormal patterns, and corresponding operating procedures is essentially equivalent and difficult to structure.
As the system becomes larger, the number of them will increase dramatically. Therefore, there is a problem that the processing time becomes enormous and it becomes difficult to quickly deal with the abnormality.

The present invention has been made in consideration of the above circumstances, and uses knowledge engineering techniques to perform abnormality diagnosis of a process plant and planning / synthesis of a countermeasure plan for the abnormality, and to ensure production and safety as the original purpose of the plant. It is an object of the present invention to provide an abnormal time plan support device for a process plant capable of grasping the state of the plant in a wide range and promptly and quickly responding to the abnormality of the plant by systematically performing from the viewpoint of .

Another object of the present invention is to provide an abnormal time plan support device for a process plant capable of diagnosing unknown abnormal causes and abnormal patterns which are not assumed in advance and dealing with the abnormalities.

Further, another object of the present invention is to provide a knowledge base in which the functions in the process plant are hierarchized by paying attention to mass transfer and energy transfer in the process plant, and to formulate and synthesize a top-down abnormality diagnosis and countermeasure plan. An object is to provide an abnormal time plan support device for a process plant.

[Structure of Invention]

(Means for Solving Problems) An abnormal time planning support device for a process plant according to the present invention is a process for storing plant data from a process plant that produces a substance or energy using a physical process or a chemical process. Database, abnormality diagnosis of the above process plant and planning of countermeasures against abnormalities
A knowledge base that has the knowledge to perform synthesis, and the plant data and knowledge necessary for the process plant abnormality diagnosis and countermeasure plan formulation / synthesis from the plant database and knowledge base described above are read, and abnormality diagnosis and countermeasure plan formulation / synthesis are performed. An inference mechanism that performs inference for
And a man-machine interface for displaying the result of the inference by this inference mechanism, wherein the knowledge base focuses on the movement of substances and the movement of energy in the process plant, hierarchizes the functions in the process plant, and Knowledge describing the function hierarchy, knowledge for performing abnormality diagnosis for each node of the function hierarchy, knowledge for performing abnormality diagnosis for the entire plant, and countermeasure plan for abnormality based on these abnormality diagnosis results And the knowledge for synthesizing this countermeasure plan into a coherent overall plan for the entire plant.

(Operation) Plant data from a process plant that produces a substance or energy using a physical process or a chemical process is stored in a plant database. Further, the knowledge base is provided with knowledge for diagnosing abnormalities in the process plant and for planning and synthesizing countermeasure plans for abnormalities. The knowledge base focuses on material movement and energy movement in the process plant, hierarchizes the functions in the process plant, describes the functional hierarchy of the process plant, and the abnormalities at each node of the functional hierarchy. Knowledge for making a diagnosis, knowledge for making an abnormality diagnosis for the entire plant, knowledge for making a countermeasure plan for an abnormality based on these abnormality diagnosis results, and this countermeasure plan for the whole plant should be consistent. The knowledge base has
Focusing on mass transfer in the process plant and energy transfer using the mass transfer as the medium, abnormality diagnosis and countermeasure plan planning and synthesis are performed using hierarchical structure knowledge that hierarchizes the functions in the process plant. Widely and swiftly from top to bottom, it is possible to perform abnormality diagnosis and countermeasure plan planning / synthesis without omission, and to systematically and widely perform abnormality diagnosis and countermeasure plan planning / synthesis. You can

The inference mechanism first reads plant data and knowledge for performing abnormality diagnosis of a process plant and planning and synthesis of a countermeasure plan for the abnormality from the plant database and knowledge base. Then, the inference mechanism makes an abnormality diagnosis in accordance with the knowledge for making an abnormality diagnosis while referring to the plant data.

Next, the inference mechanism formulates and synthesizes a countermeasure plan for an abnormality based on the above-mentioned abnormality diagnosis result and according to knowledge for formulating and synthesizing a countermeasure plan for the abnormality. Then, the result of the inference by the inference mechanism is provided to the operator through the man-machine interface.

(Embodiment) An embodiment of the abnormal time plan support device for a process plant according to the present invention will be described with reference to the drawings. INDUSTRIAL APPLICABILITY The present invention is suitably used as an abnormal time plan support device 2 for a nuclear power plant 1, and as shown in FIG. 1, a plant database 3 for storing plant data from the nuclear power plant 1, and an abnormality diagnosis for the nuclear power plant 1. And a knowledge base 4 having knowledge for formulating and synthesizing a countermeasure plan for abnormality, and plant data necessary for abnormality diagnosis of the nuclear power plant 1 and formulation / synthesis of a countermeasure plan from the plant database 3 and the knowledge base 4 described above. An inference mechanism 5 for reading knowledge to make an inference for abnormality diagnosis and for planning / synthesizing a countermeasure plan, and a man-machine interface 6 for displaying a result of inference by the inference mechanism 5 are provided.

The plant database 3 is a nuclear power plant 1.
Information about the operating state of the plant such as the process measurement value from is input and stored as plant data.

Further, the knowledge base 4 has knowledge describing the functional hierarchical structure of the nuclear power plant 1 (hereinafter referred to as hierarchical structure knowledge) as knowledge for performing abnormality diagnosis of the nuclear power plant 1 and planning / synthesis of a countermeasure plan for the abnormality. Based on the knowledge for performing abnormality diagnosis for each node of the function hierarchical structure (hereinafter referred to as node diagnosis knowledge), the knowledge for performing abnormality diagnosis for the entire plant (hereinafter referred to as overall diagnosis knowledge), and these abnormality diagnosis results It has knowledge for formulating a countermeasure plan for abnormalities (hereinafter referred to as planning knowledge), and knowledge for synthesizing this countermeasure plan into an overall plan that is consistent with the entire plant (hereinafter referred to as plan synthesis knowledge).

The contents of each piece of knowledge will be described in detail below.

The hierarchical structure knowledge is obtained by understanding the nuclear power plant 1 as a hierarchical structure from the viewpoint of its function, based on a knowledge engineering concept.

That is, in general, an artifact such as a process plant is constructed with a clear purpose-function, and its structure has a system for achieving the final goal of the process plant and various sub-goals for achieving the final goal. It is considered that a hierarchical structure is formed, such as a subsystem that has, and a subsystem for that subsystem. Further, it is considered that the above subsystems are provided with an auxiliary system that configures these subsystems and maintains and exerts their functions.

Such a hierarchical structure can be clearly recognized especially when the process plant is observed in terms of function, since a physical structure generally performs many functions.

In the present embodiment, in converting the functional hierarchical structure of the nuclear power plant 1 into a knowledge base, attention is paid to the movement of substances within the plant, which is the basis of the process plant, and the movement of energy using the substance movement as a medium. , Creating a clear functional hierarchy knowledge.

The hierarchical structure knowledge of the nuclear power plant 1 is, for example, as shown in FIG.
Created for one purpose: the production of electricity and the maintenance of safety.

In FIG. 2, flow functions such as storage, transportation, branching, and barrier are expressed by using the symbols shown in FIG.

In FIG. 2, the functional hierarchical structure for power production is composed of a plurality of nodes, and these plurality of nodes are structured in a hierarchical structure. The node in this hierarchical structure is called a flow structure and has a specific function.

The uppermost power production flow structure 11 has a function for achieving power production and is composed of a plurality of flow functions. That is, the nuclear power plant 1
Is a system that uses fission reaction to generate electricity, so as a flow function to achieve its purpose, source 1 that generates energy by fission reaction
2. A system 13 for converting and transporting the energy and a user 14 for consuming the transported energy are provided.

Then, in the electric power production control flow structure 15 below the electric power production flow structure 11, a nuclear energy generation system 16 as a subsystem of the source 12 for generating energy by the nuclear fission reaction, and a system for converting and transporting the energy. Energy transfer system 17 and energy conversion system 1 as subsystems of
8. An electric energy conversion system 19 and a waste heat transportation system 20 are provided, and a power grid 21 as the user 14 and an environment 22 are further provided.

In addition, each system 16 to 20 has a support 2 as an auxiliary system necessary for maintaining its function.
3 to 27 are provided. These supports 23 to 27 are provided with a flow structure below them,
The function of each support 23-27 is maintained by the system in these flow structures.

For example, as a flow structure for maintaining the function of the nuclear energy generation system support 23, a control rod drive flow structure 30 for controlling the fission reaction, a core recirculation flow structure 31 for circulating cooling water into the reactor, A feed water heating flow structure 32 for heating the feed water into the reactor and a pressure control flow structure 33 for controlling the pressure of the reactor are provided.
A subsystem and a support (not shown) are provided inside each of the flow structures 30 to 33, and a flow structure for maintaining the function is provided below each support.

On the other hand, in the functional hierarchical structure for maintaining safety, a safety ensuring flow structure 35 is provided as the uppermost node, and this safety ensuring flow structure 35 has a radioactive source 36 as a flow function and this radioactive source 36.
It is composed of a radioactivity barrier 37 that shields radioactivity from the radioactivity and an environment 38 around the radioactivity barrier 37.

The radioactivity release prevention flow structure 40 below the radioactivity source 4 serves as a flow function.
1, a fuel cladding tube 42, a primary coolant boundary 43, a relief safety valve 44, a reactor containment vessel 45, an emergency gas treatment system 46, a rare gas holdup system 47 and an environment 48 are provided. Furthermore, each flow function 4
2 to 47, support 50 to 5 as an auxiliary system
7 is provided. A flow structure (not shown) is further provided below each of these supports 50 to 57.

Each flow structure in the above-mentioned function hierarchical structure has a large number of basic measures for dealing with anomalies in each flow function and support as knowledge data. 4 and 5 are diagrams showing an example of the above-mentioned basic measures.

FIG. 4 shows an example of basic measures provided in the feed water heating flow structure 32, and describes the purpose and the measure when condensate leaks to a feed water thin tube or the like in the feed water heater. The purpose of countermeasures in this case is to prevent leakage of the primary system cooling water. When condensate leaks to the feed water heater, it is possible to reduce the reactor output and to isolate the leaked feed water heater system as a measure to achieve the objective.

FIG. 5 shows an example of basic measures provided in the power production management flow structure 15, and describes the purpose and measures when the feed water temperature decreases and the reactor output increases. The purpose of countermeasures in this case is to maintain the integrity of the core. For example, when the feed water heater is isolated from one system, the core inlet sub-cooling increases due to the decrease in the feed water temperature, and as a result, the reactor output rises and the control value for maintaining the integrity of the core is monitored. The new nuclear energy generation system support 23 becomes abnormal. As a countermeasure against this abnormality, it is possible to reduce the reactor power by reducing the core recirculation flow rate. In this case, since the lower core recirculation flow structure 31 having a function necessary for executing the measure needs to be normal, it is described as a restriction clause that the recirculation control system is normal.

The hierarchical structure knowledge shown in FIG. 2 is roughly expressed for the purpose of explanation, and actually, more detailed hierarchical structure knowledge is created. Further, if the type of the nuclear power plant 1 is different, the hierarchical structure knowledge corresponding to the type is created.

The node diagnosis knowledge describes a method for diagnosing an abnormality in each node constituting the functional hierarchy.

This node diagnosis knowledge is abnormal in consideration of knowledge for judging the soundness of each node (hereinafter referred to as soundness judgment knowledge), and a node judged to be unhealthy by this soundness judgment knowledge, considering a structure related to a substance or an energy balance. It is divided into knowledge for diagnosis (hereinafter referred to as node abnormality diagnosis knowledge). The soundness judgment knowledge is based on a knowledge engineering concept and will be described below.

That is, generally, an abnormality (fault) that occurs in a physical structure such as a process plant affects some of the functions of the structure, and the influence spreads from the lower part to the upper part of the hierarchical structure. In other words, the propagation of anomalies takes the process of bottom up.

On the other hand, when diagnosing such an anomaly, a person usually checks from the upper level of the hierarchy and takes a form of top down where the range of the search is narrowed down the hierarchy while chasing the anomaly. . This thinking method is considered to be a matter of course because it is the greatest concern for human beings whether or not a process plant operating with a predetermined purpose always achieves its final purpose. Therefore, in the present invention, similarly to such a human thinking method,
A top-down search is performed on the hierarchical structure to perform abnormality diagnosis.

This abnormality diagnosis is specifically performed as follows. First, for each flow function and support of each flow structure of the hierarchical structure knowledge, parameters such as the generation amount and the storage amount for determining the soundness of the performance are designated in advance. This parameter is a plant data from the nuclear power plant 1 or a calculated value calculated based on the plant data.

Then, at any time, starting from the top of the hierarchical structure while referring to the plant data, while following the hierarchy in sequence, determination of the soundness of the performance of each flow function and support is performed sequentially based on the specified parameters, The result of pass / fail judgment is obtained for each flow function and support.

Next, the node abnormality diagnosis knowledge is knowledge for performing abnormality diagnosis on a flow structure including a flow function or a support which is determined to be soundness abnormality based on the judgment result of the soundness judgment knowledge, and will be described below. It is like this.

First, the abnormal states are classified according to the type of flow function, as shown in FIG. That is, the above-mentioned soundness determination is performed, for example, for the Source.
It is performed based on the performance parameter regarding the generation amount or the storage amount. In this case, the amount generated is (Kg / se
c) and (Kcal / sec), and the storage capacity is determined by performance parameters in units such as (Kg) and (Kca / sec).
It is judged by the performance parameter in the unit of l). Then, the cause of the abnormality diagnosed for each flow function from the determination result is the generation amount abnormality, the heat generation amount abnormality, the change rate abnormality due to the transportation abnormality, and the change amount abnormality.

Also, regarding transport, soundness is determined based on the performance parameter regarding the flow rate. The flow rate is determined by performance parameters in units of (Kg / sec) and (Kcal / sec), and the cause of abnormality as a diagnostic result is transport abnormality or branch abnormality. In addition, similarly, storage (Storage), branch (Distribution), dump site (S
ink) and barriers are classified into abnormal states.

In this case, the rate of change in the storage amount may be due to a transport abnormality, but this abnormality is not the abnormality in the flow function itself, but is the cause of the abnormality in the transport or barrier connected to the flow function. That is the case. At the time of this diagnosis, knowledge of the flow function in each flow structure and the connection relation of the flow function is used.

Based on FIG. 4, the results of diagnosis for each flow function are summarized for any flow function and classified into any of the cases shown in FIG. 7. FIG. 7 shows the results of diagnosing a specific flow function, support of the flow function, and flow functions adjacent to the flow function, and the determination results of the diagnosis results are described. In FIG. 7, normal cases are indicated by ◯, and abnormal cases are indicated by x. Further, Δ indicates that the performance parameter is abnormal, but it is determined that it is due to the peripheral flow function.

The abnormal cases shown in FIG. 7 are classified into 10 cases.
For example, Case 1 shows the case where a specific flow function, its support, and an adjacent flow function are all normal, and the determination is also normal. Case 2 shows the case where there is no abnormality in the specific flow function and the adjacent flow function, but there is abnormality in the support, and the judgment result is "potential failure, abnormality in the corresponding flow function due to abnormality in support appears sooner or later. It is.

In the same manner, Case 10 is classified below.

Although cases 5 and 6 are the determination results when the movement of the substance is assumed, if there is almost no movement of the substance and there is a problem in accuracy, the determination as in cases 5 and 6 may not be performed. Good.

In this way, by determining and classifying an abnormal case for each flow function of a specific flow structure, one of the following determination results can be obtained for the abnormal source of that flow structure.

1. There is an abnormality in a specific flow function, and there is no abnormality in its support.

2. There is a problem with a specific flow function, and there is also a problem with its support.

3. There is an error in the specific support, and there is no error in the corresponding flow function.

4. Multiple anomalous sources consisting of any combination of the above three (for multiple flow functions).

From this judgment result, a diagnostic result about the propagation range of the abnormality in the flow structure and the performance evaluation of the flow structure can be obtained.

The overall diagnosis knowledge is knowledge that describes a method for diagnosing the entire plant from the diagnosis result of each node based on the node diagnosis knowledge, and will be described below.

When an abnormal flow structure is sequentially diagnosed from the top of the plant function hierarchical structure according to the node diagnosis knowledge, which node has an anomaly in the hierarchical structure, how the anomalies are connected, and how they are scattered. It becomes clear whether to do it.

Then, if there is a connection in the anomaly of the node and the connection matches the support relationship between the hierarchical flow structures, it can be clearly confirmed that the anomaly at the lower part has propagated based on the relationship of the support functions. . If the agreement is incomplete, the size of the anomaly is still small and it is expected that the support relationship has not become apparent. Even in this case, it becomes clear which function in the hierarchical structure is abnormal. The same judgment is made in the case where the anomalies are scattered.

The planning knowledge is knowledge that describes a method for planning a countermeasure plan for an abnormality based on the result of abnormality diagnosis based on the above-mentioned knowledge.

In this planning knowledge, first, for each flow structure that has been diagnosed as anomaly, the basic measures provided in advance as the knowledge data in the hierarchical structure knowledge are derived, and then the constraint clauses and plant status regarding whether or not each basic measure can be executed. Judgment based on.

The derivation of such basic measures is based on the diagnosis result of the overall diagnosis knowledge, from the highest flow structure among the flow structures diagnosed as abnormal to the lower flow which is the source of the abnormality of the flow structure. It is done in the process of top-down toward the structure.
As a result, according to the functional hierarchy as shown in FIG.
A hierarchical structure is formed from the upper level abstracted basic measures to the sequentially broken down basic measures. In this hierarchical structure, the contents of the basic measures become more specific as going from the higher level to the lower level.

As a general rule, the basic measures are derived by top-down to the level of the lowest-level flow structure with anomalies.However, in the middle of the process, there are cases where the plant conditions do not meet the constraint clauses or when some other constraints make the measures infeasible. Sometimes it comes out. In such a case, the basic measures should be derived up to a feasible level. As a result of such processing, an appropriate basic plan is derived for all events, and a concrete hierarchical structure of concrete basic measures that is as feasible as possible is drafted as a countermeasure plan.

The plan synthesizing knowledge is knowledge describing a method for synthesizing a plan of measures, which is a hierarchical structure of basic measures, which is drafted by the plan planning knowledge, into an overall plan that is consistent with the entire plant.

The hierarchical structure of basic measures created according to the above planning knowledge may include mutually contradictory basic measures. Therefore, it is necessary to take consistency as a whole. The contradiction is resolved based on the purpose of the measures described in the basic measures for each layer. In other words, since the higher the level is, the basic policy is abstracted in the hierarchical structure of the basic measures, the dependency relations are set in advance for the purpose of the measures described in the basic measures between layers, and the measures of the higher level are set. Countermeasures against the purpose Delete the lower-level basic measures that describe the purpose.

After the contradiction of the hierarchical structure of the basic measures is resolved in this way, the final measures plan as the overall plan is synthesized by aggregating the basic measures of the lowest layer of this hierarchical structure for each purpose of measures. In this case, the purpose of the measures described in the basic measures, which are at a higher level than the combined measures plan, are:
It shows the reason and effect when implementing the countermeasure plan,
This is useful data that will be useful for the operators to evaluate the provided countermeasure plan.

Next, the knowledge base 4 and the plant database 3
An inference mechanism 5 connected to the plant reads the plant data from the plant database 3 and the knowledge base 4 and knowledge for performing abnormality diagnosis of the nuclear power plant 1 and planning / synthesis of a countermeasure plan for the abnormality, and the periodically read plant While referring to the data, reasoning is performed based on the knowledge for performing abnormality diagnosis and planning / synthesis of countermeasure plans for abnormalities, diagnosing plant abnormalities, and formulating / synthesizing countermeasure plans for abnormalities based on the abnormality diagnosis results. I am supposed to do it.

First, the inference mechanism 5 refers to plant data,
According to the soundness judgment knowledge using the hierarchical structure knowledge, the soundness of each node in the functional hierarchical structure at that time is judged. Then, for the node determined to be unhealthy, the abnormality diagnosis is performed by referring to the knowledge about the internal structure and the plant data according to the node abnormality diagnosis knowledge. After that, the inference mechanism 5 synthesizes the abnormality diagnosis results of each node according to the overall diagnosis knowledge and performs the abnormality diagnosis for the entire plant.

Further, the inference mechanism 5 formulates a countermeasure plan against the abnormality according to the planning knowledge, and then synthesizes the planned countermeasure plan into a coherent overall plan for the entire plant according to the plan synthesis knowledge.

The man-machine interface 6 connected to the inference mechanism 5 is provided with a display device such as a CRT, and the inference result by the inference mechanism 5 is displayed on this display device. The displayed inference results include the location of abnormal nodes on the functional hierarchy of the plant, their connections,
Locations of abnormal flow functions and abnormal supports in the flow structure corresponding to abnormal nodes and their relations, that is, causal relationships and the range of influence of abnormalities, and countermeasure plans for dealing with those abnormalities.
The purpose of the countermeasure plan, reasons for derivation, etc.

Next, the operation of the above embodiment will be described.

When an abnormality occurs in the nuclear power plant 1, the abnormality is input to the plant database 3 as plant data through various detectors, amplifiers, signal transmission lines, etc., and stored in the plant database 3. Then, the inference mechanism 5 reads from the plant database 3 and the knowledge base 4 the plant data including the data about the abnormality and the knowledge for the abnormality diagnosis of the nuclear power plant 1 and the planning / synthesis of the countermeasure plan for the abnormality. After that, the inference mechanism 5 determines the soundness of each flow function and each support in a top-down manner from the top of the hierarchical structure according to the soundness judgment knowledge while referring to the plant data. The determination result is temporarily stored in the working memory in the plant database, for example.

Then, the inference mechanism 5 diagnoses an abnormality in the flow structure including the flow function or the support which is determined to be soundness abnormality by the soundness determination according to the node abnormality diagnosis knowledge. After diagnosing the node including the abnormality, the abnormality diagnosis of the entire plant is performed according to the overall diagnosis knowledge based on the diagnosis result.

After that, the inference mechanism 5 formulates a countermeasure plan for an abnormality based on the abnormality diagnosis result based on the above-mentioned knowledge according to the planning knowledge, and further synthesizes the above-mentioned countermeasure plan into overall knowledge that is consistent with the entire plant according to the plan synthesis knowledge. To do.

The inference result by the inference mechanism 5 is displayed on the display device by the man-machine interface 6, and the operator is provided with an abnormality diagnosis result and a countermeasure plan for the abnormality. The operator can easily recognize the plant status by visually checking the abnormality diagnosis result and the countermeasure plan displayed on the display device,
The driving operation can be quickly executed according to the countermeasure plan.

In the above-described embodiment, based on the final goal of the nuclear power plant 1, the production of electric power and ensuring of safety, the hierarchical structure knowledge that hierarchically represents the functional structure is used to create and synthesize an abnormality diagnosis and a countermeasure plan. Therefore, the abnormality diagnosis and the countermeasure plan can be prepared and synthesized in a wide range and in a swift order in the order of importance, without any omission.

In addition, since diagnosis is performed based on typical performance parameters for highly abstracted functions, it is possible to perform plant diagnosis and plan / synthesize countermeasure plans at high speed in order from important functions without being confused by trivial information. it can.

Further, since the hierarchical structure knowledge is created based on the universal mass and energy balance which is essential to the nuclear power plant 1, the abnormality diagnosis result created by using the hierarchical structure knowledge, the countermeasure plan and its purpose / There is no foreseeable reason for derivation, and the effect is that it is easy to understand.

In particular, it is not necessary to assume in advance the individual causes of abnormalities and abnormal patterns as in the conventional case, and it is very effective in that unknown causes of abnormalities can be diagnosed and a countermeasure plan can be prepared and synthesized.

In the above-described embodiment, the knowledge base is provided with the knowledge about the function hierarchical structure for the electric power production in the steady operation state of the nuclear power plant 1, but in addition, the function hierarchical structure aiming at the safe shutdown of the plant is created. You may prepare for the knowledge base. According to this embodiment, when an abnormality occurs in the plant and an emergency stop is made, it is possible to perform abnormality diagnosis and plan / synthesize a countermeasure plan in the process of reaching the safety stop of the plant.

Further, in the above embodiment, the abnormal time plan support device for the nuclear power plant 1 has been described, but the present invention is not limited to this, and a physical process or a chemical process such as a thermal power plant or a chemical industrial plant is used. The present invention can be widely applied as an abnormal time plan support device for a process plant that produces substances and energy.

〔The invention's effect〕

As described above, the abnormal time planning support device for a process plant according to the present invention includes a plant database that stores plant data from a process plant that produces a substance or energy using a physical process or a chemical process, A knowledge base with knowledge for performing abnormality diagnosis of the above process plant and planning / synthesis of a countermeasure plan for the abnormality, and plant data required for abnormality diagnosis of the process plant and drafting / synthesis of a countermeasure plan from the above plant database and knowledge base. And a man-machine interface for displaying the result of the inference by this inference mechanism, and an inference mechanism that reads in knowledge and makes an inference for abnormality diagnosis and drafting / synthesizing a countermeasure plan, and the knowledge base is provided in the process plant. Focus on mass transfer and energy transfer Knowledge that describes the function hierarchical structure of the process plant by hierarchizing the functions in the process plant, knowledge for performing abnormality diagnosis for each node of the function hierarchy, and knowledge for performing abnormality diagnosis for the entire plant. And knowledge for formulating a countermeasure plan for abnormality based on these abnormality diagnosis results, and knowledge for synthesizing this countermeasure plan into a coherent overall plan for the entire plant, the knowledge base functions. Focusing on the mass transfer in the process plant and energy transfer using this mass transfer as a medium based on the hierarchical structure, the functions in the process plant are hierarchically arranged, in a wide and swift order in descending order of importance, without omission. You can perform top-down abnormality diagnosis and plan / synthesis of countermeasure plans. In the formation systematic (top-down), it can be performed extensively and rapidly. In particular, it is not necessary to assume each abnormality cause and abnormal pattern in advance as in the conventional case, and it is effective in that unknown abnormality causes can be diagnosed and countermeasure plans can be prepared and synthesized. .

[Brief description of drawings]

FIG. 1 is a block diagram showing an embodiment of an abnormal time plan support apparatus for a process plant according to the present invention, and FIG. 2 is a knowledge describing a functional hierarchical structure of a nuclear power plant provided in a knowledge base of the above embodiment. FIG. 3, FIG. 3 is a diagram showing symbols used in FIG. 2, FIGS. 4 and 5 are diagrams showing an example of basic measures provided in the knowledge base of the above embodiment, and FIG. FIG. 7 is a diagram in which abnormal states are classified according to the type of flow function in the example, FIG. 7 is a diagram summarizing the results of judgment for each flow function in the above embodiment, and FIG. 8 is a diagram of the above embodiment. It is a figure which shows the hierarchical structure of the basic countermeasure created by the planning knowledge. 1 ... Nuclear power plant, 2 ... Abnormality plan support device, 3
... plant database, 4 ... knowledge base, 5 ... inference mechanism, 6 ... man-machine interface.

Claims (1)

[Claims] 1. A process database for storing plant data from a process plant that produces a substance or energy using a physical process or a chemical process, and an abnormality diagnosis of the process plant and a plan / synthesis of a countermeasure plan for the abnormality. A knowledge base that has the knowledge to carry out, and the plant data and knowledge necessary for the process plant abnormality diagnosis and the planning / synthesis of the countermeasure plan are read from the plant database and the knowledge base, and the abnormality diagnosis and the countermeasure plan are drafted / synthesized. And a man-machine interface for displaying the result of the inference by this inference mechanism.
Focusing on the movement of substances and energy in the process plant, the functions in the process plant are hierarchized, knowledge that describes the function hierarchical structure of the process plant, and abnormality diagnosis for each node of the function hierarchical structure Knowledge for performing abnormality diagnosis for the entire plant, knowledge for formulating a countermeasure plan for abnormality based on these abnormality diagnosis results, and this countermeasure plan for the overall plan consistent with the entire plant. An abnormal time plan support device for a process plant, which has knowledge for synthesizing.